1727 files changed, 62619 insertions, 24602 deletions

diff --git a/.mailmap b/.mailmap
index 08b80428f583..52489f564069 100644
--- a/.mailmap
+++ b/.mailmap
@@ -21,6 +21,7 @@ Andrey Ryabinin <[email protected]> <[email protected]>
 Andrew Morton <[email protected]>
 Andrew Vasquez <[email protected]>
 Andy Adamson <[email protected]>
+Antoine Tenart <[email protected]>
 Antonio Ospite <[email protected]> <[email protected]>
 Archit Taneja <[email protected]>
 Arnaud Patard <[email protected]>
@@ -30,6 +31,9 @@ Axel Lin <[email protected]>
 Ben Gardner <[email protected]>
 Ben M Cahill <[email protected]>
 Björn Steinbrink <[email protected]>
+Boris Brezillon <[email protected]>
+Boris Brezillon <[email protected]> <[email protected]>
+Boris Brezillon <[email protected]> <[email protected]>
 Brian Avery <[email protected]>
 Brian King <[email protected]>
 Christoph Hellwig <[email protected]>
@@ -89,6 +93,7 @@ Leonid I Ananiev <[email protected]>
 Linas Vepstas <[email protected]>
 Mark Brown <[email protected]>
 Matthieu CASTET <[email protected]>
+Mauro Carvalho Chehab <[email protected]> <[email protected]> <[email protected]> <[email protected]> <[email protected]> <[email protected]> <[email protected]>
 Mayuresh Janorkar <[email protected]>
 Michael Buesch <[email protected]>
 Michel Dänzer <[email protected]>
@@ -122,6 +127,7 @@ Santosh Shilimkar <[email protected]>
 Sascha Hauer <[email protected]>
 S.Çağlar Onur <[email protected]>
 Shiraz Hashim <[email protected]> <[email protected]>
+Shuah Khan <[email protected]> <[email protected]> <[email protected]> <[email protected]> <[email protected]>
 Simon Kelley <[email protected]>
 Stéphane Witzmann <[email protected]>
 Stephen Hemminger <[email protected]>
diff --git a/CREDITS b/CREDITS
index 0f0bf22afe0c..2a3fbcd229e6 100644
--- a/CREDITS
+++ b/CREDITS
@@ -649,6 +649,7 @@ D: Configure, Menuconfig, xconfig
 
 N: Mauro Carvalho Chehab
 E: [email protected]
+E: [email protected]
 E: [email protected]
 D: Media subsystem (V4L/DVB) drivers and core
 D: EDAC drivers and EDAC 3.0 core rework
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-uvc b/Documentation/ABI/testing/configfs-usb-gadget-uvc
index 2f4a0051b32d..1ba0d0fda9c0 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-uvc
+++ b/Documentation/ABI/testing/configfs-usb-gadget-uvc
@@ -1,6 +1,6 @@
 What:		/config/usb-gadget/gadget/functions/uvc.name
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	UVC function directory
 
 		streaming_maxburst	- 0..15 (ss only)
@@ -9,37 +9,37 @@ Description:	UVC function directory
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Control descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/class
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Class descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/class/ss
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Super speed control class descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/class/fs
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Full speed control class descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/terminal
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Terminal descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/terminal/output
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Output terminal descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/terminal/output/default
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Default output terminal descriptors
 
 		All attributes read only:
@@ -53,12 +53,12 @@ Description:	Default output terminal descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/terminal/camera
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Camera terminal descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/terminal/camera/default
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Default camera terminal descriptors
 
 		All attributes read only:
@@ -75,12 +75,12 @@ Description:	Default camera terminal descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/processing
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Processing unit descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/processing/default
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Default processing unit descriptors
 
 		All attributes read only:
@@ -94,49 +94,49 @@ Description:	Default processing unit descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/header
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Control header descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/control/header/name
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Specific control header descriptors
 
 dwClockFrequency
 bcdUVC
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Streaming descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/class
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Streaming class descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/class/ss
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Super speed streaming class descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/class/hs
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	High speed streaming class descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/class/fs
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Full speed streaming class descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/color_matching
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Color matching descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/color_matching/default
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Default color matching descriptors
 
 		All attributes read only:
@@ -150,12 +150,12 @@ Description:	Default color matching descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	MJPEG format descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg/name
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Specific MJPEG format descriptors
 
 		All attributes read only,
@@ -174,7 +174,7 @@ Description:	Specific MJPEG format descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg/name/name
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Specific MJPEG frame descriptors
 
 		dwFrameInterval		- indicates how frame interval can be
@@ -196,12 +196,12 @@ Description:	Specific MJPEG frame descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Uncompressed format descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed/name
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Specific uncompressed format descriptors
 
 		bmaControls		- this format's data for bmaControls in
@@ -221,7 +221,7 @@ Description:	Specific uncompressed format descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed/name/name
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Specific uncompressed frame descriptors
 
 		dwFrameInterval		- indicates how frame interval can be
@@ -243,12 +243,12 @@ Description:	Specific uncompressed frame descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/header
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Streaming header descriptors
 
 What:		/config/usb-gadget/gadget/functions/uvc.name/streaming/header/name
 Date:		Dec 2014
-KernelVersion:	3.20
+KernelVersion:	4.0
 Description:	Specific streaming header descriptors
 
 		All attributes read only:
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
index 6708c5e264aa..33e96f740639 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
+++ b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
@@ -1,4 +1,4 @@
-What		/sys/bus/iio/devices/iio:deviceX/in_proximity_raw
+What		/sys/bus/iio/devices/iio:deviceX/in_proximity_input
 Date:		March 2014
 KernelVersion:	3.15
 Contact:	Matt Ranostay <[email protected]>
diff --git a/Documentation/ABI/testing/sysfs-class-net-batman-adv b/Documentation/ABI/testing/sysfs-class-net-batman-adv
index 518f6a1dbc0c..898106849e27 100644
--- a/Documentation/ABI/testing/sysfs-class-net-batman-adv
+++ b/Documentation/ABI/testing/sysfs-class-net-batman-adv
@@ -1,19 +1,10 @@
 
-What:		/sys/class/net/<iface>/batman-adv/throughput_override
-Date:		Feb 2014
-Contact:	Antonio Quartulli <[email protected]>
-description:
-		Defines the throughput value to be used by B.A.T.M.A.N. V
-		when estimating the link throughput using this interface.
-		If the value is set to 0 then batman-adv will try to
-		estimate the throughput by itself.
-
 What:           /sys/class/net/<iface>/batman-adv/elp_interval
 Date:           Feb 2014
 Contact:        Linus Lüssing <[email protected]>
 Description:
                 Defines the interval in milliseconds in which batman
-                sends its probing packets for link quality measurements.
+                emits probing packets for neighbor sensing (ELP).
 
 What:           /sys/class/net/<iface>/batman-adv/iface_status
 Date:           May 2010
@@ -28,3 +19,12 @@ Description:
                 The /sys/class/net/<iface>/batman-adv/mesh_iface file
                 displays the batman mesh interface this <iface>
                 currently is associated with.
+
+What:           /sys/class/net/<iface>/batman-adv/throughput_override
+Date:           Feb 2014
+Contact:        Antonio Quartulli <[email protected]>
+description:
+                Defines the throughput value to be used by B.A.T.M.A.N. V
+                when estimating the link throughput using this interface.
+                If the value is set to 0 then batman-adv will try to
+                estimate the throughput by itself.
diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl
index 5f7c55999c77..800fe7a9024c 100644
--- a/Documentation/DocBook/80211.tmpl
+++ b/Documentation/DocBook/80211.tmpl
@@ -136,6 +136,7 @@
 !Finclude/net/cfg80211.h cfg80211_ibss_joined
 !Finclude/net/cfg80211.h cfg80211_connect_result
 !Finclude/net/cfg80211.h cfg80211_connect_bss
+!Finclude/net/cfg80211.h cfg80211_connect_timeout
 !Finclude/net/cfg80211.h cfg80211_roamed
 !Finclude/net/cfg80211.h cfg80211_disconnected
 !Finclude/net/cfg80211.h cfg80211_ready_on_channel
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index de79efdad46c..8c68768ebee5 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -128,16 +128,44 @@ X!Edrivers/base/interface.c
 !Edrivers/base/platform.c
 !Edrivers/base/bus.c
      </sect1>
-     <sect1><title>Device Drivers DMA Management</title>
+     <sect1>
+       <title>Buffer Sharing and Synchronization</title>
+       <para>
+         The dma-buf subsystem provides the framework for sharing buffers
+         for hardware (DMA) access across multiple device drivers and
+         subsystems, and for synchronizing asynchronous hardware access.
+       </para>
+       <para>
+         This is used, for example, by drm "prime" multi-GPU support, but
+         is of course not limited to GPU use cases.
+       </para>
+       <para>
+         The three main components of this are: (1) dma-buf, representing
+         a sg_table and exposed to userspace as a file descriptor to allow
+         passing between devices, (2) fence, which provides a mechanism
+         to signal when one device as finished access, and (3) reservation,
+         which manages the shared or exclusive fence(s) associated with
+         the buffer.
+       </para>
+       <sect2><title>dma-buf</title>
 !Edrivers/dma-buf/dma-buf.c
+!Iinclude/linux/dma-buf.h
+       </sect2>
+       <sect2><title>reservation</title>
+!Pdrivers/dma-buf/reservation.c Reservation Object Overview
+!Edrivers/dma-buf/reservation.c
+!Iinclude/linux/reservation.h
+       </sect2>
+       <sect2><title>fence</title>
 !Edrivers/dma-buf/fence.c
-!Edrivers/dma-buf/seqno-fence.c
 !Iinclude/linux/fence.h
+!Edrivers/dma-buf/seqno-fence.c
 !Iinclude/linux/seqno-fence.h
-!Edrivers/dma-buf/reservation.c
-!Iinclude/linux/reservation.h
 !Edrivers/dma-buf/sync_file.c
 !Iinclude/linux/sync_file.h
+       </sect2>
+     </sect1>
+     <sect1><title>Device Drivers DMA Management</title>
 !Edrivers/base/dma-coherent.c
 !Edrivers/base/dma-mapping.c
      </sect1>
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index c6938e50e71f..4da60b463995 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -56,6 +56,7 @@ stable kernels.
 | ARM            | MMU-500         | #841119,#826419 | N/A                     |
 |                |                 |                 |                         |
 | Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375    |
+| Cavium         | ThunderX ITS    | #23144          | CAVIUM_ERRATUM_23144    |
 | Cavium         | ThunderX GICv3  | #23154          | CAVIUM_ERRATUM_23154    |
 | Cavium         | ThunderX Core   | #27456          | CAVIUM_ERRATUM_27456    |
 | Cavium         | ThunderX SMMUv2 | #27704          | N/A		       |
diff --git a/Documentation/devicetree/bindings/display/imx/ldb.txt b/Documentation/devicetree/bindings/display/imx/ldb.txt
index 0a175d991b52..a407462c885e 100644
--- a/Documentation/devicetree/bindings/display/imx/ldb.txt
+++ b/Documentation/devicetree/bindings/display/imx/ldb.txt
@@ -62,6 +62,7 @@ Required properties:
    display-timings are used instead.
 
 Optional properties (required if display-timings are used):
+ - ddc-i2c-bus: phandle of an I2C controller used for DDC EDID probing
  - display-timings : A node that describes the display timings as defined in
    Documentation/devicetree/bindings/display/display-timing.txt.
  - fsl,data-mapping : should be "spwg" or "jeida"
diff --git a/Documentation/devicetree/bindings/hwmon/ina2xx.txt b/Documentation/devicetree/bindings/hwmon/ina2xx.txt
index 9bcd5e87830d..02af0d94e921 100644
--- a/Documentation/devicetree/bindings/hwmon/ina2xx.txt
+++ b/Documentation/devicetree/bindings/hwmon/ina2xx.txt
@@ -7,6 +7,7 @@ Required properties:
 	- "ti,ina220" for ina220
 	- "ti,ina226" for ina226
 	- "ti,ina230" for ina230
+	- "ti,ina231" for ina231
 - reg: I2C address
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt b/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt
index bfeabb843941..71191ff0e781 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt
@@ -44,8 +44,8 @@ Required properties:
 - our-claim-gpio: The GPIO that we use to claim the bus.
 - their-claim-gpios: The GPIOs that the other sides use to claim the bus.
   Note that some implementations may only support a single other master.
-- Standard I2C mux properties. See mux.txt in this directory.
-- Single I2C child bus node at reg 0. See mux.txt in this directory.
+- Standard I2C mux properties. See i2c-mux.txt in this directory.
+- Single I2C child bus node at reg 0. See i2c-mux.txt in this directory.
 
 Optional properties:
 - slew-delay-us: microseconds to wait for a GPIO to go high. Default is 10 us.
diff --git a/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt b/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt
index 6078aefe7ed4..7ce23ac61308 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt
@@ -27,7 +27,8 @@ Required properties:
 - i2c-bus-name: The name of this bus. Also needed as pinctrl-name for the I2C
 		parents.
 
-Furthermore, I2C mux properties and child nodes. See mux.txt in this directory.
+Furthermore, I2C mux properties and child nodes. See i2c-mux.txt in this
+directory.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt
index 66709a825541..21da3ecbb370 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt
@@ -22,8 +22,8 @@ Required properties:
 - i2c-parent: The phandle of the I2C bus that this multiplexer's master-side
   port is connected to.
 - mux-gpios: list of gpios used to control the muxer
-* Standard I2C mux properties. See mux.txt in this directory.
-* I2C child bus nodes. See mux.txt in this directory.
+* Standard I2C mux properties. See i2c-mux.txt in this directory.
+* I2C child bus nodes. See i2c-mux.txt in this directory.
 
 Optional properties:
 - idle-state: value to set the muxer to when idle. When no value is
@@ -33,7 +33,7 @@ For each i2c child node, an I2C child bus will be created. They will
 be numbered based on their order in the device tree.
 
 Whenever an access is made to a device on a child bus, the value set
-in the revelant node's reg property will be output using the list of
+in the relevant node's reg property will be output using the list of
 GPIOs, the first in the list holding the least-significant value.
 
 If an idle state is defined, using the idle-state (optional) property,
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt
index ae8af1694e95..33119a98e144 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt
@@ -28,9 +28,9 @@ Also required are:
 * Standard pinctrl properties that specify the pin mux state for each child
   bus. See ../pinctrl/pinctrl-bindings.txt.
 
-* Standard I2C mux properties. See mux.txt in this directory.
+* Standard I2C mux properties. See i2c-mux.txt in this directory.
 
-* I2C child bus nodes. See mux.txt in this directory.
+* I2C child bus nodes. See i2c-mux.txt in this directory.
 
 For each named state defined in the pinctrl-names property, an I2C child bus
 will be created. I2C child bus numbers are assigned based on the index into
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt
index 688783fbe696..de00d7fc450b 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt
@@ -7,8 +7,8 @@ Required properties:
 - compatible: i2c-mux-reg
 - i2c-parent: The phandle of the I2C bus that this multiplexer's master-side
   port is connected to.
-* Standard I2C mux properties. See mux.txt in this directory.
-* I2C child bus nodes. See mux.txt in this directory.
+* Standard I2C mux properties. See i2c-mux.txt in this directory.
+* I2C child bus nodes. See i2c-mux.txt in this directory.
 
 Optional properties:
 - reg: this pair of <offset size> specifies the register to control the mux.
@@ -24,7 +24,7 @@ Optional properties:
   given, it defaults to the last value used.
 
 Whenever an access is made to a device on a child bus, the value set
-in the revelant node's reg property will be output to the register.
+in the relevant node's reg property will be output to the register.
 
 If an idle state is defined, using the idle-state (optional) property,
 whenever an access is not being made to a device on a child bus, the
diff --git a/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt
new file mode 100644
index 000000000000..dfe287a5d6f2
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt
@@ -0,0 +1,59 @@
+Properties for an MDIO bus multiplexer found in Broadcom iProc based SoCs.
+
+This MDIO bus multiplexer defines buses that could be internal as well as
+external to SoCs and could accept MDIO transaction compatible to C-22 or
+C-45 Clause. When child bus is selected, one needs to select these two
+properties as well to generate desired MDIO transaction on appropriate bus.
+
+Required properties in addition to the generic multiplexer properties:
+
+MDIO multiplexer node:
+- compatible: brcm,mdio-mux-iproc.
+
+Every non-ethernet PHY requires a compatible so that it could be probed based
+on this compatible string.
+
+Additional information regarding generic multiplexer properties can be found
+at- Documentation/devicetree/bindings/net/mdio-mux.txt
+
+
+for example:
+		mdio_mux_iproc: mdio-mux@6602023c {
+			compatible = "brcm,mdio-mux-iproc";
+			reg = <0x6602023c 0x14>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			mdio@0 {
+				reg = <0x0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				pci_phy0: pci-phy@0 {
+					compatible = "brcm,ns2-pcie-phy";
+					reg = <0x0>;
+					#phy-cells = <0>;
+				};
+			};
+
+			mdio@7 {
+				reg = <0x7>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				pci_phy1: pci-phy@0 {
+					compatible = "brcm,ns2-pcie-phy";
+					reg = <0x0>;
+					#phy-cells = <0>;
+				};
+			};
+			mdio@10 {
+				reg = <0x10>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				gphy0: eth-phy@10 {
+					reg = <0x10>;
+				};
+			};
+		};
diff --git a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
new file mode 100644
index 000000000000..22a6f10bab05
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
@@ -0,0 +1,96 @@
+Renesas R-Car CAN FD controller Device Tree Bindings
+----------------------------------------------------
+
+Required properties:
+- compatible: Must contain one or more of the following:
+  - "renesas,rcar-gen3-canfd" for R-Car Gen3 compatible controller.
+  - "renesas,r8a7795-canfd" for R8A7795 (R-Car H3) compatible controller.
+
+  When compatible with the generic version, nodes must list the
+  SoC-specific version corresponding to the platform first, followed by the
+  family-specific and/or generic versions.
+
+- reg: physical base address and size of the R-Car CAN FD register map.
+- interrupts: interrupt specifier for the Global & Channel interrupts
+- clocks: phandles and clock specifiers for 3 clock inputs.
+- clock-names: 3 clock input name strings: "fck", "canfd", "can_clk".
+- pinctrl-0: pin control group to be used for this controller.
+- pinctrl-names: must be "default".
+
+Required child nodes:
+The controller supports two channels and each is represented as a child node.
+The name of the child nodes are "channel0" and "channel1" respectively. Each
+child node supports the "status" property only, which is used to
+enable/disable the respective channel.
+
+Required properties for "renesas,r8a7795-canfd" compatible:
+In R8A7795 SoC, canfd clock is a div6 clock and can be used by both CAN
+and CAN FD controller at the same time. It needs to be scaled to maximum
+frequency if any of these controllers use it. This is done using the
+below properties.
+
+- assigned-clocks: phandle of canfd clock.
+- assigned-clock-rates: maximum frequency of this clock.
+
+Optional property:
+The controller can operate in either CAN FD only mode (default) or
+Classical CAN only mode. The mode is global to both the channels. In order to
+enable the later, define the following optional property.
+ - renesas,no-can-fd: puts the controller in Classical CAN only mode.
+
+Example
+-------
+
+SoC common .dtsi file:
+
+		canfd: can@e66c0000 {
+			compatible = "renesas,r8a7795-canfd",
+				     "renesas,rcar-gen3-canfd";
+			reg = <0 0xe66c0000 0 0x8000>;
+			interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+				   <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 914>,
+			       <&cpg CPG_CORE R8A7795_CLK_CANFD>,
+			       <&can_clk>;
+			clock-names = "fck", "canfd", "can_clk";
+			assigned-clocks = <&cpg CPG_CORE R8A7795_CLK_CANFD>;
+			assigned-clock-rates = <40000000>;
+			power-domains = <&cpg>;
+			status = "disabled";
+
+			channel0 {
+				status = "disabled";
+			};
+
+			channel1 {
+				status = "disabled";
+			};
+		};
+
+Board specific .dts file:
+
+E.g. below enables Channel 1 alone in the board in Classical CAN only mode.
+
+&canfd {
+	pinctrl-0 = <&canfd1_pins>;
+	pinctrl-names = "default";
+	renesas,no-can-fd;
+	status = "okay";
+
+	channel1 {
+		status = "okay";
+	};
+};
+
+E.g. below enables Channel 0 alone in the board using External clock
+as fCAN clock.
+
+&canfd {
+	pinctrl-0 = <&canfd0_pins &can_clk_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	channel0 {
+		status = "okay";
+	};
+};
diff --git a/Documentation/devicetree/bindings/net/cirrus,cs89x0.txt b/Documentation/devicetree/bindings/net/cirrus,cs89x0.txt
new file mode 100644
index 000000000000..c070076bacb9
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/cirrus,cs89x0.txt
@@ -0,0 +1,13 @@
+* Cirrus Logic CS8900/CS8920 Network Controller
+
+Required properties:
+- compatible	: Should be "cirrus,cs8900" or "cirrus,cs8920".
+- reg		: Address and length of the IO space.
+- interrupts	: Should contain the controller interrupt line.
+
+Examples:
+	eth0: eth@10000000 {
+		compatible = "cirrus,cs8900";
+		reg = <0x10000000 0x400>;
+		interrupts = <10>;
+	};
diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index 0ae06491b430..5ad439f30135 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -15,7 +15,6 @@ Required properties:
 - cpdma_channels 	: Specifies number of channels in CPDMA
 - ale_entries		: Specifies No of entries ALE can hold
 - bd_ram_size		: Specifies internal descriptor RAM size
-- rx_descs		: Specifies number of Rx descriptors
 - mac_control		: Specifies Default MAC control register content
 			  for the specific platform
 - slaves		: Specifies number for slaves
diff --git a/Documentation/devicetree/bindings/net/davinci-mdio.txt b/Documentation/devicetree/bindings/net/davinci-mdio.txt
index 0369e25aabd2..621156ca4ffd 100644
--- a/Documentation/devicetree/bindings/net/davinci-mdio.txt
+++ b/Documentation/devicetree/bindings/net/davinci-mdio.txt
@@ -2,7 +2,10 @@ TI SoC Davinci/Keystone2 MDIO Controller Device Tree Bindings
 ---------------------------------------------------
 
 Required properties:
-- compatible		: Should be "ti,davinci_mdio" or "ti,keystone_mdio"
+- compatible		: Should be "ti,davinci_mdio"
+			  and "ti,keystone_mdio" for Keystone 2 SoCs
+			  and "ti,cpsw-mdio" for am335x, am472x, am57xx/dra7, dm814x SoCs
+			  and "ti,am4372-mdio" for am472x SoC
 - reg			: physical base address and size of the davinci mdio
 			  registers map
 - bus_freq		: Mdio Bus frequency
diff --git a/Documentation/devicetree/bindings/net/dsa/b53.txt b/Documentation/devicetree/bindings/net/dsa/b53.txt
new file mode 100644
index 000000000000..ca752db14dff
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/dsa/b53.txt
@@ -0,0 +1,88 @@
+Broadcom BCM53xx Ethernet switches
+==================================
+
+Required properties:
+
+- compatible: For external switch chips, compatible string must be exactly one
+  of: "brcm,bcm5325"
+      "brcm,bcm53115"
+      "brcm,bcm53125"
+      "brcm,bcm53128"
+      "brcm,bcm5365"
+      "brcm,bcm5395"
+      "brcm,bcm5397"
+      "brcm,bcm5398"
+
+  For the BCM5310x SoCs with an integrated switch, must be one of:
+      "brcm,bcm53010-srab"
+      "brcm,bcm53011-srab"
+      "brcm,bcm53012-srab"
+      "brcm,bcm53018-srab"
+      "brcm,bcm53019-srab" and the mandatory "brcm,bcm5301x-srab" string
+
+  For the BCM63xx/33xx SoCs with an integrated switch, must be one of:
+      "brcm,bcm3384-switch"
+      "brcm,bcm6328-switch"
+      "brcm,bcm6368-switch" and the mandatory "brcm,bcm63xx-switch"
+
+See Documentation/devicetree/bindings/dsa/dsa.txt for a list of additional
+required and optional properties.
+
+Examples:
+
+Ethernet switch connected via MDIO to the host, CPU port wired to eth0:
+
+	eth0: ethernet@10001000 {
+		compatible = "brcm,unimac";
+		reg = <0x10001000 0x1000>;
+
+		fixed-link {
+			speed = <1000>;
+			duplex-full;
+		};
+	};
+
+	mdio0: mdio@10000000 {
+		compatible = "brcm,unimac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		switch0: ethernet-switch@30 {
+			compatible = "brcm,bcm53125";
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			ports {
+				port0@0 {
+					reg = <0>;
+					label = "lan1";
+				};
+
+				port1@1 {
+					reg = <1>;
+					label = "lan2";
+				};
+
+				port5@5 {
+					reg = <5>;
+					label = "cable-modem";
+					fixed-link {
+						speed = <1000>;
+						duplex-full;
+					};
+					phy-mode = "rgmii-txid";
+				};
+
+				port8@8 {
+					reg = <8>;
+					label = "cpu";
+					fixed-link {
+						speed = <1000>;
+						duplex-full;
+					};
+					phy-mode = "rgmii-txid";
+					ethernet = <&eth0>;
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/net/keystone-netcp.txt b/Documentation/devicetree/bindings/net/keystone-netcp.txt
index b30ab6b5cbfa..04ba1dc34fd6 100644
--- a/Documentation/devicetree/bindings/net/keystone-netcp.txt
+++ b/Documentation/devicetree/bindings/net/keystone-netcp.txt
@@ -2,7 +2,7 @@ This document describes the device tree bindings associated with the
 keystone network coprocessor(NetCP) driver support.
 
 The network coprocessor (NetCP) is a hardware accelerator that processes
-Ethernet packets. NetCP has a gigabit Ethernet (GbE) subsytem with a ethernet
+Ethernet packets. NetCP has a gigabit Ethernet (GbE) subsystem with a ethernet
 switch sub-module to send and receive packets. NetCP also includes a packet
 accelerator (PA) module to perform packet classification operations such as
 header matching, and packet modification operations such as checksum
diff --git a/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt b/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt
index 14aa6cf58201..6a9a63cb0543 100644
--- a/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt
+++ b/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt
@@ -13,10 +13,10 @@ Optional properties:
 		      initialization. This is an array of 28 values(u8).
 
   - marvell,wakeup-pin: It represents wakeup pin number of the bluetooth chip.
-		        firmware will use the pin to wakeup host system.
+		        firmware will use the pin to wakeup host system (u16).
   - marvell,wakeup-gap-ms: wakeup gap represents wakeup latency of the host
 		      platform. The value will be configured to firmware. This
-		      is needed to work chip's sleep feature as expected.
+		      is needed to work chip's sleep feature as expected (u16).
   - interrupt-parent: phandle of the parent interrupt controller
   - interrupts : interrupt pin number to the cpu. Driver will request an irq based
 		 on this interrupt number. During system suspend, the irq will be
@@ -50,7 +50,7 @@ calibration data is also available in below example.
 			0x37 0x01 0x1c 0x00 0xff 0xff 0xff 0xff 0x01 0x7f 0x04 0x02
 			0x00 0x00 0xba 0xce 0xc0 0xc6 0x2d 0x00 0x00 0x00 0x00 0x00
 			0x00 0x00 0xf0 0x00>;
-		marvell,wakeup-pin = <0x0d>;
-		marvell,wakeup-gap-ms = <0x64>;
+		marvell,wakeup-pin = /bits/ 16 <0x0d>;
+		marvell,wakeup-gap-ms = /bits/ 16 <0x64>;
 	};
 };
diff --git a/Documentation/devicetree/bindings/net/mdio-mux.txt b/Documentation/devicetree/bindings/net/mdio-mux.txt
index 491f5bd55203..f58571f36570 100644
--- a/Documentation/devicetree/bindings/net/mdio-mux.txt
+++ b/Documentation/devicetree/bindings/net/mdio-mux.txt
@@ -5,11 +5,12 @@ numbered uniquely in a device dependent manner.  The nodes for an MDIO
 bus multiplexer/switch will have one child node for each child bus.
 
 Required properties:
-- mdio-parent-bus : phandle to the parent MDIO bus.
 - #address-cells = <1>;
 - #size-cells = <0>;
 
 Optional properties:
+- mdio-parent-bus : phandle to the parent MDIO bus.
+
 - Other properties specific to the multiplexer/switch hardware.
 
 Required properties for child nodes:
diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
index 93eac7ce1446..cccd945fc45b 100644
--- a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
@@ -3,7 +3,8 @@ Rockchip SoC RK3288 10/100/1000 Ethernet driver(GMAC)
 The device node has following properties.
 
 Required properties:
- - compatible: Can be one of "rockchip,rk3288-gmac", "rockchip,rk3368-gmac"
+ - compatible: Can be one of "rockchip,rk3228-gmac", "rockchip,rk3288-gmac",
+                             "rockchip,rk3368-gmac"
  - reg: addresses and length of the register sets for the device.
  - interrupts: Should contain the GMAC interrupts.
  - interrupt-names: Should contain the interrupt names "macirq".
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index 95816c5fc589..41b49e6075f5 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -47,6 +47,9 @@ Optional properties:
 				supported by this device instance
 - snps,perfect-filter-entries:	Number of perfect filter entries supported
 				by this device instance
+- snps,ps-speed: port selection speed that can be passed to the core when
+		 PCS is supported. For example, this is used in case of SGMII
+		 and MAC2MAC connection.
 - AXI BUS Mode parameters: below the list of all the parameters to program the
 			   AXI register inside the DMA module:
 	- snps,lpi_en: enable Low Power Interface
diff --git a/Documentation/devicetree/bindings/phy/brcm,mdio-mux-bus-pci.txt b/Documentation/devicetree/bindings/phy/brcm,mdio-mux-bus-pci.txt
new file mode 100644
index 000000000000..5b51007c6f24
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/brcm,mdio-mux-bus-pci.txt
@@ -0,0 +1,27 @@
+* Broadcom NS2 PCIe PHY binding document
+
+Required bus properties:
+- reg: MDIO Bus number for the MDIO interface
+- #address-cells: must be 1
+- #size-cells: must be 0
+
+Required PHY properties:
+- compatible: should be "brcm,ns2-pcie-phy"
+- reg: MDIO Phy ID for the MDIO interface
+- #phy-cells: must be 0
+
+This is a child bus node of "brcm,mdio-mux-iproc" node.
+
+Example:
+
+mdio@0 {
+	reg = <0x0>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	pci_phy0: pci-phy@0 {
+		compatible = "brcm,ns2-pcie-phy";
+		reg = <0x0>;
+		#phy-cells = <0>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index a7440bcd67ff..2c2500df0dce 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -255,6 +255,7 @@ synology	Synology, Inc.
 SUNW	Sun Microsystems, Inc
 tbs	TBS Technologies
 tcl	Toby Churchill Ltd.
+technexion	TechNexion
 technologic	Technologic Systems
 thine	THine Electronics, Inc.
 ti	Texas Instruments
@@ -269,6 +270,7 @@ tronsmart	Tronsmart
 truly	Truly Semiconductors Limited
 tyan	Tyan Computer Corporation
 upisemi	uPI Semiconductor Corp.
+uniwest	United Western Technologies Corp (UniWest)
 urt	United Radiant Technology Corporation
 usi	Universal Scientific Industrial Co., Ltd.
 v3	V3 Semiconductor
diff --git a/Documentation/filesystems/devpts.txt b/Documentation/filesystems/devpts.txt
index 30d2fcb32f72..9f94fe276dea 100644
--- a/Documentation/filesystems/devpts.txt
+++ b/Documentation/filesystems/devpts.txt
@@ -1,141 +1,26 @@
+Each mount of the devpts filesystem is now distinct such that ptys
+and their indicies allocated in one mount are independent from ptys
+and their indicies in all other mounts.
 
-To support containers, we now allow multiple instances of devpts filesystem,
-such that indices of ptys allocated in one instance are independent of indices
-allocated in other instances of devpts.
+All mounts of the devpts filesystem now create a /dev/pts/ptmx node
+with permissions 0000.
 
-To preserve backward compatibility, this support for multiple instances is
-enabled only if:
+To retain backwards compatibility the a ptmx device node (aka any node
+created with "mknod name c 5 2") when opened will look for an instance
+of devpts under the name "pts" in the same directory as the ptmx device
+node.
 
-	- CONFIG_DEVPTS_MULTIPLE_INSTANCES=y, and
-	- '-o newinstance' mount option is specified while mounting devpts
-
-IOW, devpts now supports both single-instance and multi-instance semantics.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=n, there is no change in behavior and
-this referred to as the "legacy" mode. In this mode, the new mount options
-(-o newinstance and -o ptmxmode) will be ignored with a 'bogus option' message
-on console.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and devpts is mounted without the
-'newinstance' option (as in current start-up scripts) the new mount binds
-to the initial kernel mount of devpts. This mode is referred to as the
-'single-instance' mode and the current, single-instance semantics are
-preserved, i.e PTYs are common across the system.
-
-The only difference between this single-instance mode and the legacy mode
-is the presence of new, '/dev/pts/ptmx' node with permissions 0000, which
-can safely be ignored.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and 'newinstance' option is specified,
-the mount is considered to be in the multi-instance mode and a new instance
-of the devpts fs is created. Any ptys created in this instance are independent
-of ptys in other instances of devpts. Like in the single-instance mode, the
-/dev/pts/ptmx node is present. To effectively use the multi-instance mode,
-open of /dev/ptmx must be a redirected to '/dev/pts/ptmx' using a symlink or
-bind-mount.
-
-Eg: A container startup script could do the following:
-
-	$ chmod 0666 /dev/pts/ptmx
-	$ rm /dev/ptmx
-	$ ln -s pts/ptmx /dev/ptmx
-	$ ns_exec -cm /bin/bash
-
-	# We are now in new container
-
-	$ umount /dev/pts
-	$ mount -t devpts -o newinstance lxcpts /dev/pts
-	$ sshd -p 1234
-
-where 'ns_exec -cm /bin/bash' calls clone() with CLONE_NEWNS flag and execs
-/bin/bash in the child process.  A pty created by the sshd is not visible in
-the original mount of /dev/pts.
+As an option instead of placing a /dev/ptmx device node at /dev/ptmx
+it is possible to place a symlink to /dev/pts/ptmx at /dev/ptmx or
+to bind mount /dev/ptx/ptmx to /dev/ptmx.  If you opt for using
+the devpts filesystem in this manner devpts should be mounted with
+the ptmxmode=0666, or chmod 0666 /dev/pts/ptmx should be called.
 
 Total count of pty pairs in all instances is limited by sysctls:
 kernel.pty.max = 4096		- global limit
-kernel.pty.reserve = 1024	- reserve for initial instance
+kernel.pty.reserve = 1024	- reserved for filesystems mounted from the initial mount namespace
 kernel.pty.nr			- current count of ptys
 
 Per-instance limit could be set by adding mount option "max=<count>".
 This feature was added in kernel 3.4 together with sysctl kernel.pty.reserve.
 In kernels older than 3.4 sysctl kernel.pty.max works as per-instance limit.
-
-User-space changes
-------------------
-
-In multi-instance mode (i.e '-o newinstance' mount option is specified at least
-once), following user-space issues should be noted.
-
-1. If -o newinstance mount option is never used, /dev/pts/ptmx can be ignored
-   and no change is needed to system-startup scripts.
-
-2. To effectively use multi-instance mode (i.e -o newinstance is specified)
-   administrators or startup scripts should "redirect" open of /dev/ptmx to
-   /dev/pts/ptmx using either a bind mount or symlink.
-
-	$ mount -t devpts -o newinstance devpts /dev/pts
-
-   followed by either
-
-	$ rm /dev/ptmx
-	$ ln -s pts/ptmx /dev/ptmx
-	$ chmod 666 /dev/pts/ptmx
-   or
-	$ mount -o bind /dev/pts/ptmx /dev/ptmx
-
-3. The '/dev/ptmx -> pts/ptmx' symlink is the preferred method since it
-   enables better error-reporting and treats both single-instance and
-   multi-instance mounts similarly.
-
-   But this method requires that system-startup scripts set the mode of
-   /dev/pts/ptmx correctly (default mode is 0000). The scripts can set the
-   mode by, either
-
-   	- adding ptmxmode mount option to devpts entry in /etc/fstab, or
-	- using 'chmod 0666 /dev/pts/ptmx'
-
-4. If multi-instance mode mount is needed for containers, but the system
-   startup scripts have not yet been updated, container-startup scripts
-   should bind mount /dev/ptmx to /dev/pts/ptmx to avoid breaking single-
-   instance mounts.
-
-   Or, in general, container-startup scripts should use:
-
-	mount -t devpts -o newinstance -o ptmxmode=0666 devpts /dev/pts
-	if [ ! -L /dev/ptmx ]; then
-		mount -o bind /dev/pts/ptmx /dev/ptmx
-	fi
-
-   When all devpts mounts are multi-instance, /dev/ptmx can permanently be
-   a symlink to pts/ptmx and the bind mount can be ignored.
-
-5. A multi-instance mount that is not accompanied by the /dev/ptmx to
-   /dev/pts/ptmx redirection would result in an unusable/unreachable pty.
-
-	mount -t devpts -o newinstance lxcpts /dev/pts
-
-   immediately followed by:
-
-	open("/dev/ptmx")
-
-    would create a pty, say /dev/pts/7, in the initial kernel mount.
-    But /dev/pts/7 would be invisible in the new mount.
-
-6. The permissions for /dev/pts/ptmx node should be specified when mounting
-   /dev/pts, using the '-o ptmxmode=%o' mount option (default is 0000).
-
-	mount -t devpts -o newinstance -o ptmxmode=0644 devpts /dev/pts
-
-   The permissions can be later be changed as usual with 'chmod'.
-
-	chmod 666 /dev/pts/ptmx
-
-7. A mount of devpts without the 'newinstance' option results in binding to
-   initial kernel mount.  This behavior while preserving legacy semantics,
-   does not provide strict isolation in a container environment. i.e by
-   mounting devpts without the 'newinstance' option, a container could
-   get visibility into the 'host' or root container's devpts.
-   
-   To workaround this and have strict isolation, all mounts of devpts,
-   including the mount in the root container, should use the newinstance
-   option.
diff --git a/Documentation/kdump/gdbmacros.txt b/Documentation/kdump/gdbmacros.txt
index 35f6a982a0d5..220d0a80ca2c 100644
--- a/Documentation/kdump/gdbmacros.txt
+++ b/Documentation/kdump/gdbmacros.txt
@@ -170,21 +170,92 @@ document trapinfo
 	address the kernel panicked.
 end
 
+define dump_log_idx
+	set $idx = $arg0
+	if ($argc > 1)
+		set $prev_flags = $arg1
+	else
+		set $prev_flags = 0
+	end
+	set $msg = ((struct printk_log *) (log_buf + $idx))
+	set $prefix = 1
+	set $newline = 1
+	set $log = log_buf + $idx + sizeof(*$msg)
 
-define dmesg
-	set $i = 0
-	set $end_idx = (log_end - 1) & (log_buf_len - 1)
+	# prev & LOG_CONT && !(msg->flags & LOG_PREIX)
+	if (($prev_flags & 8) && !($msg->flags & 4))
+		set $prefix = 0
+	end
+
+	# msg->flags & LOG_CONT
+	if ($msg->flags & 8)
+		# (prev & LOG_CONT && !(prev & LOG_NEWLINE))
+		if (($prev_flags & 8) && !($prev_flags & 2))
+			set $prefix = 0
+		end
+		# (!(msg->flags & LOG_NEWLINE))
+		if (!($msg->flags & 2))
+			set $newline = 0
+		end
+	end
+
+	if ($prefix)
+		printf "[%5lu.%06lu] ", $msg->ts_nsec / 1000000000, $msg->ts_nsec % 1000000000
+	end
+	if ($msg->text_len != 0)
+		eval "printf \"%%%d.%ds\", $log", $msg->text_len, $msg->text_len
+	end
+	if ($newline)
+		printf "\n"
+	end
+	if ($msg->dict_len > 0)
+		set $dict = $log + $msg->text_len
+		set $idx = 0
+		set $line = 1
+		while ($idx < $msg->dict_len)
+			if ($line)
+				printf " "
+				set $line = 0
+			end
+			set $c = $dict[$idx]
+			if ($c == '\0')
+				printf "\n"
+				set $line = 1
+			else
+				if ($c < ' ' || $c >= 127 || $c == '\\')
+					printf "\\x%02x", $c
+				else
+					printf "%c", $c
+				end
+			end
+			set $idx = $idx + 1
+		end
+		printf "\n"
+	end
+end
+document dump_log_idx
+	Dump a single log given its index in the log buffer.  The first
+	parameter is the index into log_buf, the second is optional and
+	specified the previous log buffer's flags, used for properly
+	formatting continued lines.
+end
 
-	while ($i < logged_chars)
-		set $idx = (log_end - 1 - logged_chars + $i) & (log_buf_len - 1)
+define dmesg
+	set $i = log_first_idx
+	set $end_idx = log_first_idx
+	set $prev_flags = 0
 
-		if ($idx + 100 <= $end_idx) || \
-		   ($end_idx <= $idx && $idx + 100 < log_buf_len)
-			printf "%.100s", &log_buf[$idx]
-			set $i = $i + 100
+	while (1)
+		set $msg = ((struct printk_log *) (log_buf + $i))
+		if ($msg->len == 0)
+			set $i = 0
 		else
-			printf "%c", log_buf[$idx]
-			set $i = $i + 1
+			dump_log_idx $i $prev_flags
+			set $i = $i + $msg->len
+			set $prev_flags = $msg->flags
+		end
+		if ($i == $end_idx)
+			loop_break
 		end
 	end
 end
diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt
index d406d98339b2..44f5e6bccd97 100644
--- a/Documentation/leds/leds-class.txt
+++ b/Documentation/leds/leds-class.txt
@@ -74,8 +74,8 @@ blink_set() function (see <linux/leds.h>). To set an LED to blinking,
 however, it is better to use the API function led_blink_set(), as it
 will check and implement software fallback if necessary.
 
-To turn off blinking again, use the API function led_brightness_set()
-as that will not just set the LED brightness but also stop any software
+To turn off blinking, use the API function led_brightness_set()
+with brightness value LED_OFF, which should stop any software
 timers that may have been required for blinking.
 
 The blink_set() function should choose a user friendly blinking value
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index d58ff8467953..aa15b9ee2e70 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -31,6 +31,7 @@ This file contains
       4.2.4 Broadcast Manager message sequence transmission
       4.2.5 Broadcast Manager receive filter timers
       4.2.6 Broadcast Manager multiplex message receive filter
+      4.2.7 Broadcast Manager CAN FD support
     4.3 connected transport protocols (SOCK_SEQPACKET)
     4.4 unconnected transport protocols (SOCK_DGRAM)
 
@@ -799,7 +800,7 @@ solution for a couple of reasons:
     } mytxmsg;
 
     (..)
-    mytxmsg.nframes = 4;
+    mytxmsg.msg_head.nframes = 4;
     (..)
 
     write(s, &mytxmsg, sizeof(mytxmsg));
@@ -852,6 +853,28 @@ solution for a couple of reasons:
 
     write(s, &msg, sizeof(msg));
 
+  4.2.7 Broadcast Manager CAN FD support
+
+  The programming API of the CAN_BCM depends on struct can_frame which is
+  given as array directly behind the bcm_msg_head structure. To follow this
+  schema for the CAN FD frames a new flag 'CAN_FD_FRAME' in the bcm_msg_head
+  flags indicates that the concatenated CAN frame structures behind the
+  bcm_msg_head are defined as struct canfd_frame.
+
+    struct {
+            struct bcm_msg_head msg_head;
+            struct canfd_frame frame[5];
+    } msg;
+
+    msg.msg_head.opcode  = RX_SETUP;
+    msg.msg_head.can_id  = 0x42;
+    msg.msg_head.flags   = CAN_FD_FRAME;
+    msg.msg_head.nframes = 5;
+    (..)
+
+  When using CAN FD frames for multiplex filtering the MUX mask is still
+  expected in the first 64 bit of the struct canfd_frame data section.
+
   4.3 connected transport protocols (SOCK_SEQPACKET)
   4.4 unconnected transport protocols (SOCK_DGRAM)
 
diff --git a/Documentation/networking/gen_stats.txt b/Documentation/networking/gen_stats.txt
index ff630a87b511..179b18ce45ff 100644
--- a/Documentation/networking/gen_stats.txt
+++ b/Documentation/networking/gen_stats.txt
@@ -21,7 +21,7 @@ struct mystruct {
 	...
 };
 
-Update statistics:
+Update statistics, in dequeue() methods only, (while owning qdisc->running)
 mystruct->tstats.packet++;
 mystruct->qstats.backlog += skb->pkt_len;
 
diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt
index 671fe3dd56d3..e226f8925c9e 100644
--- a/Documentation/networking/stmmac.txt
+++ b/Documentation/networking/stmmac.txt
@@ -285,6 +285,7 @@ Please see the following document:
  o mmc_core.c/mmc.h: Management MAC Counters;
  o stmmac_hwtstamp.c: HW timestamp support for PTP;
  o stmmac_ptp.c: PTP 1588 clock;
+ o stmmac_pcs.h: Physical Coding Sublayer common implementation;
  o dwmac-<XXX>.c: these are for the platform glue-logic file; e.g. dwmac-sti.c
    for STMicroelectronics SoCs.
 
diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt
index 8638f61c8c9d..37eca00796ee 100644
--- a/Documentation/scsi/scsi_eh.txt
+++ b/Documentation/scsi/scsi_eh.txt
@@ -263,19 +263,23 @@ scmd->allowed.
 
  3. scmd recovered
     ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd
-	- shost->host_failed--
 	- clear scmd->eh_eflags
 	- scsi_setup_cmd_retry()
 	- move from local eh_work_q to local eh_done_q
     LOCKING: none
+    CONCURRENCY: at most one thread per separate eh_work_q to
+		 keep queue manipulation lockless
 
  4. EH completes
     ACTION: scsi_eh_flush_done_q() retries scmds or notifies upper
-	    layer of failure.
+	    layer of failure. May be called concurrently but must have
+	    a no more than one thread per separate eh_work_q to
+	    manipulate the queue locklessly
 	- scmd is removed from eh_done_q and scmd->eh_entry is cleared
 	- if retry is necessary, scmd is requeued using
           scsi_queue_insert()
 	- otherwise, scsi_finish_command() is invoked for scmd
+	- zero shost->host_failed
     LOCKING: queue or finish function performs appropriate locking
 
 
diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt
index 20d05719bceb..3849814bfe6d 100644
--- a/Documentation/security/keys.txt
+++ b/Documentation/security/keys.txt
@@ -826,7 +826,8 @@ The keyctl syscall functions are:
  (*) Compute a Diffie-Hellman shared secret or public key
 
        long keyctl(KEYCTL_DH_COMPUTE, struct keyctl_dh_params *params,
-		   char *buffer, size_t buflen);
+		   char *buffer, size_t buflen,
+		   void *reserved);
 
      The params struct contains serial numbers for three keys:
 
@@ -843,6 +844,8 @@ The keyctl syscall functions are:
      public key.  If the base is the remote public key, the result is
      the shared secret.
 
+     The reserved argument must be set to NULL.
+
      The buffer length must be at least the length of the prime, or zero.
 
      If the buffer length is nonzero, the length of the result is
diff --git a/MAINTAINERS b/MAINTAINERS
index f8d5a3772e47..6374be26dde3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -595,6 +595,10 @@ S:	Odd Fixes
 L:	[email protected]
 F:	arch/alpha/
 
+ALPS PS/2 TOUCHPAD DRIVER
+R:	Pali Rohár <[email protected]>
+F:	drivers/input/mouse/alps.*
+
 ALTERA MAILBOX DRIVER
 M:	Ley Foon Tan <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
@@ -1159,6 +1163,7 @@ F:	arch/arm/mach-footbridge/
 ARM/FREESCALE IMX / MXC ARM ARCHITECTURE
 M:	Shawn Guo <[email protected]>
 M:	Sascha Hauer <[email protected]>
+R:	Fabio Estevam <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
@@ -2242,7 +2247,8 @@ F:	include/net/ax25.h
 F:	net/ax25/
 
 AZ6007 DVB DRIVER
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
@@ -2291,6 +2297,7 @@ S:	Maintained
 F:	Documentation/ABI/testing/sysfs-class-net-batman-adv
 F:	Documentation/ABI/testing/sysfs-class-net-mesh
 F:	Documentation/networking/batman-adv.txt
+F:	include/uapi/linux/batman_adv.h
 F:	net/batman-adv/
 
 BAYCOM/HDLCDRV DRIVERS FOR AX.25
@@ -2454,6 +2461,14 @@ L:	[email protected]
 S:	Supported
 F:	drivers/net/ethernet/broadcom/b44.*
 
+BROADCOM B53 ETHERNET SWITCH DRIVER
+M:	Florian Fainelli <[email protected]>
+L:	[email protected]
+L:	[email protected] (subscribers-only)
+S:	Supported
+F:	drivers/net/dsa/b53/*
+F:	include/linux/platform_data/b53.h
+
 BROADCOM GENET ETHERNET DRIVER
 M:	Florian Fainelli <[email protected]>
 L:	[email protected]
@@ -2570,12 +2585,11 @@ S:	Supported
 F:	drivers/net/ethernet/broadcom/tg3.*
 
 BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER
-M:	Brett Rudley <[email protected]>
-M:	Arend van Spriel <[email protected]>
-M:	Franky (Zhenhui) Lin <[email protected]>
-M:	Hante Meuleman <[email protected]>
+M:	Arend van Spriel <[email protected]>
+M:	Franky Lin <[email protected]>
+M:	Hante Meuleman <[email protected]>
 L:	[email protected]
-L:	[email protected]
+L:	[email protected]
 S:	Supported
 F:	drivers/net/wireless/broadcom/brcm80211/
 
@@ -2709,7 +2723,8 @@ F:	Documentation/filesystems/btrfs.txt
 F:	fs/btrfs/
 
 BTTV VIDEO4LINUX DRIVER
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
@@ -2773,9 +2788,9 @@ F:	include/net/caif/
 F:	net/caif/
 
 CALGARY x86-64 IOMMU
-M:	Muli Ben-Yehuda <[email protected]>
-M:	"Jon D. Mason" <[email protected]>
-L:	[email protected]
+M:	Muli Ben-Yehuda <[email protected]>
+M:	Jon Mason <[email protected]>
+L:	[email protected]
 S:	Maintained
 F:	arch/x86/kernel/pci-calgary_64.c
 F:	arch/x86/kernel/tce_64.c
@@ -2806,6 +2821,7 @@ W:	https://github.com/linux-can
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/net/can/
 F:	drivers/net/can/
 F:	include/linux/can/dev.h
 F:	include/linux/can/platform/
@@ -3086,6 +3102,7 @@ M:	Stephen Boyd <[email protected]>
 L:	[email protected]
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/clock/
 F:	drivers/clk/
 X:	drivers/clk/clkdev.c
 F:	include/linux/clk-pr*
@@ -3343,7 +3360,8 @@ S:	Maintained
 F:	drivers/media/dvb-frontends/cx24120*
 
 CX88 VIDEO4LINUX DRIVER
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
@@ -3773,6 +3791,7 @@ Q:	https://patchwork.kernel.org/project/linux-dmaengine/list/
 S:	Maintained
 F:	drivers/dma/
 F:	include/linux/dmaengine.h
+F:	Documentation/devicetree/bindings/dma/
 F:	Documentation/dmaengine/
 T:	git git://git.infradead.org/users/vkoul/slave-dma.git
 
@@ -4290,7 +4309,8 @@ F:	fs/ecryptfs/
 EDAC-CORE
 M:	Doug Thompson <[email protected]>
 M:	Borislav Petkov <[email protected]>
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git for-next
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-edac.git linux_next
@@ -4335,7 +4355,8 @@ S:	Maintained
 F:	drivers/edac/e7xxx_edac.c
 
 EDAC-GHES
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/edac/ghes_edac.c
@@ -4359,19 +4380,22 @@ S:	Maintained
 F:	drivers/edac/i5000_edac.c
 
 EDAC-I5400
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/edac/i5400_edac.c
 
 EDAC-I7300
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/edac/i7300_edac.c
 
 EDAC-I7CORE
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/edac/i7core_edac.c
@@ -4408,7 +4432,8 @@ S:	Maintained
 F:	drivers/edac/r82600_edac.c
 
 EDAC-SBRIDGE
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/edac/sb_edac.c
@@ -4467,7 +4492,8 @@ S:	Maintained
 F:	drivers/net/ethernet/ibm/ehea/
 
 EM28XX VIDEO4LINUX DRIVER
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
@@ -4870,6 +4896,13 @@ F:	drivers/net/ethernet/freescale/gianfar*
 X:	drivers/net/ethernet/freescale/gianfar_ptp.c
 F:	Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
 
+FREESCALE QUICC ENGINE UCC HDLC DRIVER
+M:	Zhao Qiang <[email protected]>
+L:	[email protected]
+L:	[email protected]
+S:	Maintained
+F:	drivers/net/wan/fsl_ucc_hdlc*
+
 FREESCALE QUICC ENGINE UCC UART DRIVER
 M:	Timur Tabi <[email protected]>
 L:	[email protected]
@@ -5405,6 +5438,15 @@ F:	include/uapi/linux/if_hippi.h
 F:	net/802/hippi.c
 F:	drivers/net/hippi/
 
+HISILICON NETWORK SUBSYSTEM DRIVER
+M:	Yisen Zhuang <[email protected]>
+M:	Salil Mehta <[email protected]>
+L:	[email protected]
+W:	http://www.hisilicon.com
+S:	Maintained
+F:	drivers/net/ethernet/hisilicon/
+F:	Documentation/devicetree/bindings/net/hisilicon*.txt
+
 HISILICON SAS Controller
 M:	John Garry <[email protected]>
 W:	http://www.hisilicon.com
@@ -6486,6 +6528,7 @@ F:	include/uapi/linux/sunrpc/
 
 KERNEL SELFTEST FRAMEWORK
 M:	Shuah Khan <[email protected]>
+M:	Shuah Khan <[email protected]>
 L:	[email protected]
 T:	git git://git.kernel.org/pub/scm/shuah/linux-kselftest
 S:	Maintained
@@ -7155,6 +7198,12 @@ W:	http://www.kernel.org/doc/man-pages
 L:	[email protected]
 S:	Maintained
 
+MARVELL 88E6XXX ETHERNET SWITCH FABRIC DRIVER
+M:	Andrew Lunn <[email protected]>
+M:	Vivien Didelot <[email protected]>
+S:	Maintained
+F:	drivers/net/dsa/mv88e6xxx/
+
 MARVELL ARMADA DRM SUPPORT
 M:	Russell King <[email protected]>
 S:	Maintained
@@ -7162,11 +7211,6 @@ F:	drivers/gpu/drm/armada/
 F:	include/uapi/drm/armada_drm.h
 F:	Documentation/devicetree/bindings/display/armada/
 
-MARVELL 88E6352 DSA support
-M:	Guenter Roeck <[email protected]>
-S:	Maintained
-F:	drivers/net/dsa/mv88e6352.c
-
 MARVELL CRYPTO DRIVER
 M:	Boris Brezillon <[email protected]>
 M:	Arnaud Ebalard <[email protected]>
@@ -7357,7 +7401,8 @@ S:	Supported
 F:	drivers/media/pci/netup_unidvb/*
 
 MEDIA INPUT INFRASTRUCTURE (V4L/DVB)
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 P:	LinuxTV.org Project
 L:	[email protected]
 W:	https://linuxtv.org
@@ -7405,7 +7450,7 @@ F:	drivers/scsi/megaraid.*
 F:	drivers/scsi/megaraid/
 
 MELLANOX ETHERNET DRIVER (mlx4_en)
-M: 	Eugenia Emantayev <[email protected]>
+M:	Tariq Toukan <[email protected]>
 L:	[email protected]
 S:	Supported
 W:	http://www.mellanox.com
@@ -8008,6 +8053,7 @@ Q:	http://patchwork.kernel.org/project/linux-wireless/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/net/wireless/
 F:	drivers/net/wireless/
 
 NETXEN (1/10) GbE SUPPORT
@@ -8405,10 +8451,9 @@ F:	drivers/i2c/busses/i2c-ocores.c
 OPEN FIRMWARE AND FLATTENED DEVICE TREE
 M:	Rob Herring <[email protected]>
 M:	Frank Rowand <[email protected]>
-M:	Grant Likely <[email protected]>
 L:	[email protected]
 W:	http://www.devicetree.org/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/glikely/linux.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git
 S:	Maintained
 F:	drivers/of/
 F:	include/linux/of*.h
@@ -8416,12 +8461,10 @@ F:	scripts/dtc/
 
 OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS
 M:	Rob Herring <[email protected]>
-M:	Pawel Moll <[email protected]>
 M:	Mark Rutland <[email protected]>
-M:	Ian Campbell <[email protected]>
-M:	Kumar Gala <[email protected]>
 L:	[email protected]
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git
+Q:	http://patchwork.ozlabs.org/project/devicetree-bindings/list/
 S:	Maintained
 F:	Documentation/devicetree/
 F:	arch/*/boot/dts/
@@ -8945,6 +8988,8 @@ M:	Linus Walleij <[email protected]>
 L:	[email protected]
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/pinctrl/
+F:	Documentation/pinctrl.txt
 F:	drivers/pinctrl/
 F:	include/linux/pinctrl/
 
@@ -9514,7 +9559,7 @@ M:	Florian Fainelli <[email protected]>
 S:	Maintained
 
 RDC R6040 FAST ETHERNET DRIVER
-M:	Florian Fainelli <[email protected]>
+M:	Florian Fainelli <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/net/ethernet/rdc/r6040.c
@@ -9852,7 +9897,8 @@ S:	Odd Fixes
 F:	drivers/media/i2c/saa6588*
 
 SAA7134 VIDEO4LINUX DRIVER
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
@@ -10261,10 +10307,9 @@ W:	http://www.avagotech.com
 S:	Supported
 F:	drivers/scsi/be2iscsi/
 
-Emulex 10Gbps NIC BE2, BE3-R, Lancer, Skyhawk-R DRIVER
+Emulex 10Gbps NIC BE2, BE3-R, Lancer, Skyhawk-R DRIVER (be2net)
 M:	Sathya Perla <[email protected]>
 M:	Ajit Khaparde <[email protected]>
-M:	Padmanabh Ratnakar <[email protected]>
 M:	Sriharsha Basavapatna <[email protected]>
 M:	Somnath Kotur <[email protected]>
 L:	[email protected]
@@ -10371,7 +10416,8 @@ S:	Maintained
 F:	drivers/media/radio/si4713/radio-usb-si4713.c
 
 SIANO DVB DRIVER
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
@@ -11137,7 +11183,8 @@ S:	Maintained
 F:	drivers/media/i2c/tda9840*
 
 TEA5761 TUNER DRIVER
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
@@ -11145,7 +11192,8 @@ S:	Odd fixes
 F:	drivers/media/tuners/tea5761.*
 
 TEA5767 TUNER DRIVER
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
@@ -11532,7 +11580,8 @@ F:	include/linux/shmem_fs.h
 F:	mm/shmem.c
 
 TM6000 VIDEO4LINUX DRIVER
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
@@ -11886,7 +11935,8 @@ F:	drivers/usb/common/usb-otg-fsm.c
 
 USB OVER IP DRIVER
 M:	Valentina Manea <[email protected]>
-M:	Shuah Khan <[email protected]>
+M:	Shuah Khan <[email protected]>
+M:	Shuah Khan <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	Documentation/usb/usbip_protocol.txt
@@ -11957,6 +12007,7 @@ L:	[email protected]
 W:	http://www.linux-usb.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git
 S:	Supported
+F:	Documentation/devicetree/bindings/usb/
 F:	Documentation/usb/
 F:	drivers/usb/
 F:	include/linux/usb.h
@@ -12130,6 +12181,7 @@ VIRTIO CORE, NET AND BLOCK DRIVERS
 M:	"Michael S. Tsirkin" <[email protected]>
 L:	[email protected]
 S:	Maintained
+F:	Documentation/devicetree/bindings/virtio/
 F:	drivers/virtio/
 F:	tools/virtio/
 F:	drivers/net/virtio_net.c
@@ -12518,7 +12570,8 @@ S:	Maintained
 F:	arch/x86/entry/vdso/
 
 XC2028/3028 TUNER DRIVER
-M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
+M:	Mauro Carvalho Chehab <[email protected]>
 L:	[email protected]
 W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
diff --git a/Makefile b/Makefile
index 0f70de63cfdb..2d24babe6f8b 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 7
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc5
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*
@@ -363,11 +363,13 @@ CHECK		= sparse
 
 CHECKFLAGS     := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \
 		  -Wbitwise -Wno-return-void $(CF)
+NOSTDINC_FLAGS  =
 CFLAGS_MODULE   =
 AFLAGS_MODULE   =
 LDFLAGS_MODULE  =
 CFLAGS_KERNEL	=
 AFLAGS_KERNEL	=
+LDFLAGS_vmlinux =
 CFLAGS_GCOV	= -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized
 CFLAGS_KCOV	= -fsanitize-coverage=trace-pc
 
diff --git a/arch/Kconfig b/arch/Kconfig
index d794384a0404..15996290fed4 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -226,8 +226,8 @@ config ARCH_INIT_TASK
 config ARCH_TASK_STRUCT_ALLOCATOR
 	bool
 
-# Select if arch has its private alloc_thread_info() function
-config ARCH_THREAD_INFO_ALLOCATOR
+# Select if arch has its private alloc_thread_stack() function
+config ARCH_THREAD_STACK_ALLOCATOR
 	bool
 
 # Select if arch wants to size task_struct dynamically via arch_task_struct_size:
@@ -606,6 +606,9 @@ config HAVE_ARCH_HASH
 	  file which provides platform-specific implementations of some
 	  functions in <linux/hash.h> or fs/namei.c.
 
+config ISA_BUS_API
+	def_bool ISA
+
 #
 # ABI hall of shame
 #
diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h
index aab14a019c20..c2ebb6f36c9d 100644
--- a/arch/alpha/include/asm/pgalloc.h
+++ b/arch/alpha/include/asm/pgalloc.h
@@ -40,7 +40,7 @@ pgd_free(struct mm_struct *mm, pgd_t *pgd)
 static inline pmd_t *
 pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	return ret;
 }
 
@@ -53,7 +53,7 @@ pmd_free(struct mm_struct *mm, pmd_t *pmd)
 static inline pte_t *
 pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	return pte;
 }
 
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 0dcbacfdea4b..0d3e59f56974 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -61,7 +61,7 @@ config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
 config ARCH_DISCONTIGMEM_ENABLE
-	def_bool y
+	def_bool n
 
 config ARCH_FLATMEM_ENABLE
 	def_bool y
@@ -186,9 +186,6 @@ if SMP
 config ARC_HAS_COH_CACHES
 	def_bool n
 
-config ARC_HAS_REENTRANT_IRQ_LV2
-	def_bool n
-
 config ARC_MCIP
 	bool "ARConnect Multicore IP (MCIP) Support "
 	depends on ISA_ARCV2
@@ -366,25 +363,10 @@ config NODES_SHIFT
 if ISA_ARCOMPACT
 
 config ARC_COMPACT_IRQ_LEVELS
-	bool "ARCompact IRQ Priorities: High(2)/Low(1)"
+	bool "Setup Timer IRQ as high Priority"
 	default n
-	# Timer HAS to be high priority, for any other high priority config
-	select ARC_IRQ3_LV2
 	# if SMP, LV2 enabled ONLY if ARC implementation has LV2 re-entrancy
-	depends on !SMP || ARC_HAS_REENTRANT_IRQ_LV2
-
-if ARC_COMPACT_IRQ_LEVELS
-
-config ARC_IRQ3_LV2
-	bool
-
-config ARC_IRQ5_LV2
-	bool
-
-config ARC_IRQ6_LV2
-	bool
-
-endif	#ARC_COMPACT_IRQ_LEVELS
+	depends on !SMP
 
 config ARC_FPU_SAVE_RESTORE
 	bool "Enable FPU state persistence across context switch"
@@ -407,11 +389,6 @@ config ARC_HAS_LLSC
 	default y
 	depends on !ARC_CANT_LLSC
 
-config ARC_STAR_9000923308
-	bool "Workaround for llock/scond livelock"
-	default n
-	depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC
-
 config ARC_HAS_SWAPE
 	bool "Insn: SWAPE (endian-swap)"
 	default y
@@ -471,7 +448,7 @@ config LINUX_LINK_BASE
 
 config HIGHMEM
 	bool "High Memory Support"
-	select DISCONTIGMEM
+	select ARCH_DISCONTIGMEM_ENABLE
 	help
 	  With ARC 2G:2G address split, only upper 2G is directly addressable by
 	  kernel. Enable this to potentially allow access to rest of 2G and PAE
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 02fabef2891c..d4df6be66d58 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -127,7 +127,7 @@ libs-y		+= arch/arc/lib/ $(LIBGCC)
 
 boot		:= arch/arc/boot
 
-#default target for make without any arguements.
+#default target for make without any arguments.
 KBUILD_IMAGE	:= bootpImage
 
 all:	$(KBUILD_IMAGE)
diff --git a/arch/arc/boot/dts/abilis_tb100.dtsi b/arch/arc/boot/dts/abilis_tb100.dtsi
index 3942634f805a..02410b211433 100644
--- a/arch/arc/boot/dts/abilis_tb100.dtsi
+++ b/arch/arc/boot/dts/abilis_tb100.dtsi
@@ -23,8 +23,6 @@
 
 
 / {
-	clock-frequency		= <500000000>;	/* 500 MHZ */
-
 	soc100 {
 		bus-frequency	= <166666666>;
 
diff --git a/arch/arc/boot/dts/abilis_tb101.dtsi b/arch/arc/boot/dts/abilis_tb101.dtsi
index b0467229a5c4..f9e7686044eb 100644
--- a/arch/arc/boot/dts/abilis_tb101.dtsi
+++ b/arch/arc/boot/dts/abilis_tb101.dtsi
@@ -23,8 +23,6 @@
 
 
 / {
-	clock-frequency		= <500000000>;	/* 500 MHZ */
-
 	soc100 {
 		bus-frequency	= <166666666>;
 
diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi
index 3e02f152edcb..6ae2c476ad82 100644
--- a/arch/arc/boot/dts/axc001.dtsi
+++ b/arch/arc/boot/dts/axc001.dtsi
@@ -15,7 +15,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <750000000>;	/* 750 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index 378e455a94c4..14df46f141bf 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -14,7 +14,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index 64c94b2860ab..3d6cfa32bf51 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -14,7 +14,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/eznps.dts b/arch/arc/boot/dts/eznps.dts
index b89f6c3eb352..1e0d225791c1 100644
--- a/arch/arc/boot/dts/eznps.dts
+++ b/arch/arc/boot/dts/eznps.dts
@@ -18,7 +18,6 @@
 
 / {
 	compatible = "ezchip,arc-nps";
-	clock-frequency = <83333333>;	/* 83.333333 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&intc>;
diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts
index 5d5e373e0ebc..63970513e4ae 100644
--- a/arch/arc/boot/dts/nsim_700.dts
+++ b/arch/arc/boot/dts/nsim_700.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsim";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index b5b060adce8a..763d66c883da 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsimosci";
-	clock-frequency = <20000000>;	/* 20 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
index 325e73090a18..4eb97c584b18 100644
--- a/arch/arc/boot/dts/nsimosci_hs.dts
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsimosci_hs";
-	clock-frequency = <20000000>;	/* 20 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
index ee03d7126581..853f897eb2a3 100644
--- a/arch/arc/boot/dts/nsimosci_hs_idu.dts
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsimosci_hs";
-	clock-frequency = <5000000>;	/* 5 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/skeleton.dtsi b/arch/arc/boot/dts/skeleton.dtsi
index 3a10cc633e2b..65808fe0a290 100644
--- a/arch/arc/boot/dts/skeleton.dtsi
+++ b/arch/arc/boot/dts/skeleton.dtsi
@@ -13,7 +13,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	chosen { };
diff --git a/arch/arc/boot/dts/skeleton_hs.dtsi b/arch/arc/boot/dts/skeleton_hs.dtsi
index 71fd308a9298..2dfe8037dfbb 100644
--- a/arch/arc/boot/dts/skeleton_hs.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs.dtsi
@@ -8,7 +8,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	chosen { };
diff --git a/arch/arc/boot/dts/skeleton_hs_idu.dtsi b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
index d1cb25a66989..4c11079f3565 100644
--- a/arch/arc/boot/dts/skeleton_hs_idu.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
@@ -8,7 +8,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	chosen { };
diff --git a/arch/arc/boot/dts/vdk_axc003.dtsi b/arch/arc/boot/dts/vdk_axc003.dtsi
index ad4ee43bd2ac..0fd6ba985b16 100644
--- a/arch/arc/boot/dts/vdk_axc003.dtsi
+++ b/arch/arc/boot/dts/vdk_axc003.dtsi
@@ -14,7 +14,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <50000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/vdk_axc003_idu.dtsi b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
index a3cb6263c581..82214cd7ba0c 100644
--- a/arch/arc/boot/dts/vdk_axc003_idu.dtsi
+++ b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
@@ -15,7 +15,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <50000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 5f3dcbbc0cc9..dd683995bc9d 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -25,50 +25,17 @@
 
 #define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
 
-#ifdef CONFIG_ARC_STAR_9000923308
-
-#define SCOND_FAIL_RETRY_VAR_DEF						\
-	unsigned int delay = 1, tmp;						\
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"	bz	4f			\n"				\
-	"   ; --- scond fail delay ---		\n"				\
-	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
-	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
-	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
-	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
-	"	b	1b			\n"	/* start over */	\
-	"4: ; --- success ---			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS							\
-	  ,[delay] "+&r" (delay),[tmp] "=&r"	(tmp)				\
-
-#else	/* !CONFIG_ARC_STAR_9000923308 */
-
-#define SCOND_FAIL_RETRY_VAR_DEF
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"	bnz     1b			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS
-
-#endif
-
 #define ATOMIC_OP(op, c_op, asm_op)					\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
-	unsigned int val;				                \
-	SCOND_FAIL_RETRY_VAR_DEF                                        \
+	unsigned int val;						\
 									\
 	__asm__ __volatile__(						\
 	"1:	llock   %[val], [%[ctr]]		\n"		\
 	"	" #asm_op " %[val], %[val], %[i]	\n"		\
 	"	scond   %[val], [%[ctr]]		\n"		\
-	"						\n"		\
-	SCOND_FAIL_RETRY_ASM						\
-									\
+	"	bnz     1b				\n"		\
 	: [val]	"=&r"	(val) /* Early clobber to prevent reg reuse */	\
-	  SCOND_FAIL_RETRY_VARS						\
 	: [ctr]	"r"	(&v->counter), /* Not "m": llock only supports reg direct addr mode */	\
 	  [i]	"ir"	(i)						\
 	: "cc");							\
@@ -77,8 +44,7 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
-	unsigned int val;				                \
-	SCOND_FAIL_RETRY_VAR_DEF                                        \
+	unsigned int val;						\
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -90,11 +56,8 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	"1:	llock   %[val], [%[ctr]]		\n"		\
 	"	" #asm_op " %[val], %[val], %[i]	\n"		\
 	"	scond   %[val], [%[ctr]]		\n"		\
-	"						\n"		\
-	SCOND_FAIL_RETRY_ASM						\
-									\
+	"	bnz     1b				\n"		\
 	: [val]	"=&r"	(val)						\
-	  SCOND_FAIL_RETRY_VARS						\
 	: [ctr]	"r"	(&v->counter),					\
 	  [i]	"ir"	(i)						\
 	: "cc");							\
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index e0e1faf03c50..14c310f2e0b1 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -76,8 +76,8 @@
 	 * We need to be a bit more cautious here. What if a kernel bug in
 	 * L1 ISR, caused SP to go whaco (some small value which looks like
 	 * USER stk) and then we take L2 ISR.
-	 * Above brlo alone would treat it as a valid L1-L2 sceanrio
-	 * instead of shouting alound
+	 * Above brlo alone would treat it as a valid L1-L2 scenario
+	 * instead of shouting around
 	 * The only feasible way is to make sure this L2 happened in
 	 * L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in
 	 * L1 ISR before it switches stack
diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h
index 1fd467ef658f..b0b87f2447f5 100644
--- a/arch/arc/include/asm/mmu_context.h
+++ b/arch/arc/include/asm/mmu_context.h
@@ -83,7 +83,7 @@ static inline void get_new_mmu_context(struct mm_struct *mm)
 		local_flush_tlb_all();
 
 		/*
-		 * Above checke for rollover of 8 bit ASID in 32 bit container.
+		 * Above check for rollover of 8 bit ASID in 32 bit container.
 		 * If the container itself wrapped around, set it to a non zero
 		 * "generation" to distinguish from no context
 		 */
diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h
index 86ed671286df..3749234b7419 100644
--- a/arch/arc/include/asm/pgalloc.h
+++ b/arch/arc/include/asm/pgalloc.h
@@ -95,7 +95,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
 	pte_t *pte;
 
-	pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO,
+	pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_ZERO,
 					 __get_order_pte());
 
 	return pte;
@@ -107,7 +107,7 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	pgtable_t pte_pg;
 	struct page *page;
 
-	pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte());
+	pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL, __get_order_pte());
 	if (!pte_pg)
 		return 0;
 	memzero((void *)pte_pg, PTRS_PER_PTE * sizeof(pte_t));
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 034bbdc0ff61..858f98ef7f1b 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -47,7 +47,7 @@
  * Page Tables are purely for Linux VM's consumption and the bits below are
  * suited to that (uniqueness). Hence some are not implemented in the TLB and
  * some have different value in TLB.
- * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible becoz they live in
+ * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible because they live in
  *      seperate PD0 and PD1, which combined forms a translation entry)
  *      while for PTE perspective, they are 8 and 9 respectively
  * with MMU v3: Most bits (except SHARED) represent the exact hardware pos
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index f9048994b22f..16b630fbeb6a 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -78,7 +78,7 @@ struct task_struct;
 #define KSTK_ESP(tsk)   (task_pt_regs(tsk)->sp)
 
 /*
- * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode.
+ * Where about of Task's sp, fp, blink when it was last seen in kernel mode.
  * Look in process.c for details of kernel stack layout
  */
 #define TSK_K_ESP(tsk)		(tsk->thread.ksp)
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
index 991380438d6b..89fdd1b0a76e 100644
--- a/arch/arc/include/asm/smp.h
+++ b/arch/arc/include/asm/smp.h
@@ -86,7 +86,7 @@ static inline const char *arc_platform_smp_cpuinfo(void)
  * (1) These insn were introduced only in 4.10 release. So for older released
  *	support needed.
  *
- * (2) In a SMP setup, the LLOCK/SCOND atomiticity across CPUs needs to be
+ * (2) In a SMP setup, the LLOCK/SCOND atomicity across CPUs needs to be
  *	gaurantted by the platform (not something which core handles).
  *	Assuming a platform won't, SMP Linux needs to use spinlocks + local IRQ
  *	disabling for atomicity.
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index 800e7c430ca5..cded4a9b5438 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -20,11 +20,6 @@
 
 #ifdef CONFIG_ARC_HAS_LLSC
 
-/*
- * A normal LLOCK/SCOND based system, w/o need for livelock workaround
- */
-#ifndef CONFIG_ARC_STAR_9000923308
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned int val;
@@ -238,293 +233,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	smp_mb();
 }
 
-#else	/* CONFIG_ARC_STAR_9000923308 */
-
-/*
- * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping
- * coherency transactions in the SCU. The exclusive line state keeps rotating
- * among contenting cores leading to a never ending cycle. So break the cycle
- * by deferring the retry of failed exclusive access (SCOND). The actual delay
- * needed is function of number of contending cores as well as the unrelated
- * coherency traffic from other cores. To keep the code simple, start off with
- * small delay of 1 which would suffice most cases and in case of contention
- * double the delay. Eventually the delay is sufficient such that the coherency
- * pipeline is drained, thus a subsequent exclusive access would succeed.
- */
-
-#define SCOND_FAIL_RETRY_VAR_DEF						\
-	unsigned int delay, tmp;						\
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"   ; --- scond fail delay ---		\n"				\
-	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
-	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
-	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
-	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
-	"	b	1b			\n"	/* start over */	\
-	"					\n"				\
-	"4: ; --- done ---			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS							\
-	  ,[delay] "=&r" (delay), [tmp] "=&r"	(tmp)				\
-
-static inline void arch_spin_lock(arch_spinlock_t *lock)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[slock]]	\n"
-	"	breq	%[val], %[LOCKED], 0b	\n"	/* spin while LOCKED */
-	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
-	"	bz	4f			\n"	/* done */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [slock]	"r"	(&(lock->slock)),
-	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_spin_trylock(arch_spinlock_t *lock)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[slock]]	\n"
-	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
-	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [slock]	"r"	(&(lock->slock)),
-	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
-	smp_mb();
-
-	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
-
-	smp_mb();
-}
-
-/*
- * Read-write spinlocks, allowing multiple readers but only one writer.
- * Unfair locking as Writers could be starved indefinitely by Reader(s)
- */
-
-static inline void arch_read_lock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	/*
-	 * zero means writer holds the lock exclusively, deny Reader.
-	 * Otherwise grant lock to first/subseq reader
-	 *
-	 * 	if (rw->counter > 0) {
-	 *		rw->counter--;
-	 *		ret = 1;
-	 *	}
-	 */
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brls	%[val], %[WR_LOCKED], 0b\n"	/* <= 0: spin while write locked */
-	"	sub	%[val], %[val], 1	\n"	/* reader lock */
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz	4f			\n"	/* done */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_read_trylock(arch_rwlock_t *rw)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
-	"	sub	%[val], %[val], 1	\n"	/* counter-- */
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_write_lock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	/*
-	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
-	 * deny writer. Otherwise if unlocked grant to writer
-	 * Hence the claim that Linux rwlocks are unfair to writers.
-	 * (can be starved for an indefinite time by readers).
-	 *
-	 *	if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
-	 *		rw->counter = 0;
-	 *		ret = 1;
-	 *	}
-	 */
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brne	%[val], %[UNLOCKED], 0b	\n"	/* while !UNLOCKED spin */
-	"	mov	%[val], %[WR_LOCKED]	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz	4f			\n"
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_write_trylock(arch_rwlock_t *rw)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
-	"	mov	%[val], %[WR_LOCKED]	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_read_unlock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-
-	smp_mb();
-
-	/*
-	 * rw->counter++;
-	 */
-	__asm__ __volatile__(
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	add	%[val], %[val], 1	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bnz	1b			\n"
-	"					\n"
-	: [val]		"=&r"	(val)
-	: [rwlock]	"r"	(&(rw->counter))
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-static inline void arch_write_unlock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-
-	smp_mb();
-
-	/*
-	 * rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
-	 */
-	__asm__ __volatile__(
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	scond	%[UNLOCKED], [%[rwlock]]\n"
-	"	bnz	1b			\n"
-	"					\n"
-	: [val]		"=&r"	(val)
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"r"	(__ARCH_RW_LOCK_UNLOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-#undef SCOND_FAIL_RETRY_VAR_DEF
-#undef SCOND_FAIL_RETRY_ASM
-#undef SCOND_FAIL_RETRY_VARS
-
-#endif	/* CONFIG_ARC_STAR_9000923308 */
-
 #else	/* !CONFIG_ARC_HAS_LLSC */
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 3af67455659a..2d79e527fa50 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -103,7 +103,7 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void)
 
 /*
  * _TIF_ALLWORK_MASK includes SYSCALL_TRACE, but we don't need it.
- * SYSCALL_TRACE is anways seperately/unconditionally tested right after a
+ * SYSCALL_TRACE is anyway seperately/unconditionally tested right after a
  * syscall, so all that reamins to be tested is _TIF_WORK_MASK
  */
 
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index d1da6032b715..a78d5670884f 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -32,7 +32,7 @@
 #define __kernel_ok		(segment_eq(get_fs(), KERNEL_DS))
 
 /*
- * Algorthmically, for __user_ok() we want do:
+ * Algorithmically, for __user_ok() we want do:
  * 	(start < TASK_SIZE) && (start+len < TASK_SIZE)
  * where TASK_SIZE could either be retrieved from thread_info->addr_limit or
  * emitted directly in code.
diff --git a/arch/arc/include/uapi/asm/swab.h b/arch/arc/include/uapi/asm/swab.h
index 095599a73195..71f3918b0fc3 100644
--- a/arch/arc/include/uapi/asm/swab.h
+++ b/arch/arc/include/uapi/asm/swab.h
@@ -74,7 +74,7 @@
 	__tmp ^ __in;						\
 })
 
-#elif (ARC_BSWAP_TYPE == 2)	/* Custom single cycle bwap instruction */
+#elif (ARC_BSWAP_TYPE == 2)	/* Custom single cycle bswap instruction */
 
 #define __arch_swab32(x)						\
 ({									\
diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S
index 0cb0abaa0479..98812c1248df 100644
--- a/arch/arc/kernel/entry-compact.S
+++ b/arch/arc/kernel/entry-compact.S
@@ -91,27 +91,13 @@ VECTOR   mem_service             ; 0x8, Mem exception   (0x1)
 VECTOR   instr_service           ; 0x10, Instrn Error   (0x2)
 
 ; ******************** Device ISRs **********************
-#ifdef CONFIG_ARC_IRQ3_LV2
-VECTOR   handle_interrupt_level2
-#else
-VECTOR   handle_interrupt_level1
-#endif
-
-VECTOR   handle_interrupt_level1
-
-#ifdef CONFIG_ARC_IRQ5_LV2
-VECTOR   handle_interrupt_level2
-#else
-VECTOR   handle_interrupt_level1
-#endif
-
-#ifdef CONFIG_ARC_IRQ6_LV2
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
 VECTOR   handle_interrupt_level2
 #else
 VECTOR   handle_interrupt_level1
 #endif
 
-.rept   25
+.rept   28
 VECTOR   handle_interrupt_level1 ; Other devices
 .endr
 
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
index c5cceca36118..ce9deb953ca9 100644
--- a/arch/arc/kernel/intc-compact.c
+++ b/arch/arc/kernel/intc-compact.c
@@ -28,10 +28,8 @@ void arc_init_IRQ(void)
 {
 	int level_mask = 0;
 
-       /* setup any high priority Interrupts (Level2 in ARCompact jargon) */
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ3_LV2) << 3;
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5;
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6;
+       /* Is timer high priority Interrupt (Level2 in ARCompact jargon) */
+	level_mask |= IS_ENABLED(CONFIG_ARC_COMPACT_IRQ_LEVELS) << TIMER0_IRQ;
 
 	/*
 	 * Write to register, even if no LV2 IRQs configured to reset it
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 6fd48021324b..08f03d9b5b3e 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -108,7 +108,7 @@ static void arc_perf_event_update(struct perf_event *event,
 	int64_t delta = new_raw_count - prev_raw_count;
 
 	/*
-	 * We don't afaraid of hwc->prev_count changing beneath our feet
+	 * We aren't afraid of hwc->prev_count changing beneath our feet
 	 * because there's no way for us to re-enter this function anytime.
 	 */
 	local64_set(&hwc->prev_count, new_raw_count);
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index f63b8bfefb0c..2ee7a4d758a8 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -392,7 +392,7 @@ void __init setup_arch(char **cmdline_p)
 		/*
 		 * If we are here, it is established that @uboot_arg didn't
 		 * point to DT blob. Instead if u-boot says it is cmdline,
-		 * Appent to embedded DT cmdline.
+		 * append to embedded DT cmdline.
 		 * setup_machine_fdt() would have populated @boot_command_line
 		 */
 		if (uboot_tag == 1) {
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 004b7f0bc76c..6cb3736b6b83 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -34,7 +34,7 @@
  *  -ViXS were still seeing crashes when using insmod to load drivers.
  *   It turned out that the code to change Execute permssions for TLB entries
  *   of user was not guarded for interrupts (mod_tlb_permission)
- *   This was cauing TLB entries to be overwritten on unrelated indexes
+ *   This was causing TLB entries to be overwritten on unrelated indexes
  *
  * Vineetg: July 15th 2008: Bug #94183
  *  -Exception happens in Delay slot of a JMP, and before user space resumes,
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index a6f91e88ce36..934150e7ac48 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -276,7 +276,7 @@ static int tlb_stats_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-/* called on user read(): display the couters */
+/* called on user read(): display the counters */
 static ssize_t tlb_stats_output(struct file *file,	/* file descriptor */
 				char __user *user_buf,	/* user buffer */
 				size_t len,		/* length of buffer */
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 9e5eddbb856f..5a294b2c3cb3 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -215,7 +215,7 @@ slc_chk:
  * ------------------
  * This ver of MMU supports variable page sizes (1k-16k): although Linux will
  * only support 8k (default), 16k and 4k.
- * However from hardware perspective, smaller page sizes aggrevate aliasing
+ * However from hardware perspective, smaller page sizes aggravate aliasing
  * meaning more vaddr bits needed to disambiguate the cache-line-op ;
  * the existing scheme of piggybacking won't work for certain configurations.
  * Two new registers IC_PTAG and DC_PTAG inttoduced.
@@ -302,7 +302,7 @@ void __cache_line_loop_v3(phys_addr_t paddr, unsigned long vaddr,
 
 	/*
 	 * This is technically for MMU v4, using the MMU v3 programming model
-	 * Special work for HS38 aliasing I-cache configuratino with PAE40
+	 * Special work for HS38 aliasing I-cache configuration with PAE40
 	 *   - upper 8 bits of paddr need to be written into PTAG_HI
 	 *   - (and needs to be written before the lower 32 bits)
 	 * Note that PTAG_HI is hoisted outside the line loop
@@ -936,7 +936,7 @@ void arc_cache_init(void)
 			      ic->ver, CONFIG_ARC_MMU_VER);
 
 		/*
-		 * In MMU v4 (HS38x) the alising icache config uses IVIL/PTAG
+		 * In MMU v4 (HS38x) the aliasing icache config uses IVIL/PTAG
 		 * pair to provide vaddr/paddr respectively, just as in MMU v3
 		 */
 		if (is_isa_arcv2() && ic->alias)
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 8c8e36fa5659..73d7e4c75b7d 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -10,7 +10,7 @@
  * DMA Coherent API Notes
  *
  * I/O is inherently non-coherent on ARC. So a coherent DMA buffer is
- * implemented by accessintg it using a kernel virtual address, with
+ * implemented by accessing it using a kernel virtual address, with
  * Cache bit off in the TLB entry.
  *
  * The default DMA address == Phy address which is 0x8000_0000 based.
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 06b6c2d695bf..414b42710a36 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -741,6 +741,7 @@ dtb-$(CONFIG_MACH_SUN7I) += \
 	sun7i-a20-olimex-som-evb.dtb \
 	sun7i-a20-olinuxino-lime.dtb \
 	sun7i-a20-olinuxino-lime2.dtb \
+	sun7i-a20-olinuxino-lime2-emmc.dtb \
 	sun7i-a20-olinuxino-micro.dtb \
 	sun7i-a20-orangepi.dtb \
 	sun7i-a20-orangepi-mini.dtb \
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 52be48bbd2dd..7fa295155543 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -766,7 +766,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
@@ -789,7 +788,7 @@
 			status = "disabled";
 
 			davinci_mdio: mdio@4a101000 {
-				compatible = "ti,davinci_mdio";
+				compatible = "ti,cpsw-mdio","ti,davinci_mdio";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				ti,hwmods = "davinci_mdio";
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index 12fcde4d4d2e..cd81ecf12731 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -626,7 +626,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
@@ -636,7 +635,7 @@
 			syscon = <&scm_conf>;
 
 			davinci_mdio: mdio@4a101000 {
-				compatible = "ti,am4372-mdio","ti,davinci_mdio";
+				compatible = "ti,am4372-mdio","ti,cpsw-mdio","ti,davinci_mdio";
 				reg = <0x4a101000 0x100>;
 				#address-cells = <1>;
 				#size-cells = <0>;
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index d82dd6e3f9b1..5687d6b4da60 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -418,7 +418,7 @@
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c0_pins>;
-	clock-frequency = <400000>;
+	clock-frequency = <100000>;
 
 	tps@24 {
 		compatible = "ti,tps65218";
diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi
index b01a5948cdd0..0e63b9dff6e7 100644
--- a/arch/arm/boot/dts/am57xx-idk-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi
@@ -60,10 +60,26 @@
 
 		tps659038_pmic {
 			compatible = "ti,tps659038-pmic";
+
+			smps12-in-supply = <&vmain>;
+			smps3-in-supply = <&vmain>;
+			smps45-in-supply = <&vmain>;
+			smps6-in-supply = <&vmain>;
+			smps7-in-supply = <&vmain>;
+			smps8-in-supply = <&vmain>;
+			smps9-in-supply = <&vmain>;
+			ldo1-in-supply = <&vmain>;
+			ldo2-in-supply = <&vmain>;
+			ldo3-in-supply = <&vmain>;
+			ldo4-in-supply = <&vmain>;
+			ldo9-in-supply = <&vmain>;
+			ldoln-in-supply = <&vmain>;
+			ldousb-in-supply = <&vmain>;
+			ldortc-in-supply = <&vmain>;
+
 			regulators {
 				smps12_reg: smps12 {
 					/* VDD_MPU */
-					vin-supply = <&vmain>;
 					regulator-name = "smps12";
 					regulator-min-microvolt = <850000>;
 					regulator-max-microvolt = <1250000>;
@@ -73,7 +89,6 @@
 
 				smps3_reg: smps3 {
 					/* VDD_DDR EMIF1 EMIF2 */
-					vin-supply = <&vmain>;
 					regulator-name = "smps3";
 					regulator-min-microvolt = <1350000>;
 					regulator-max-microvolt = <1350000>;
@@ -84,7 +99,6 @@
 				smps45_reg: smps45 {
 					/* VDD_DSPEVE on AM572 */
 					/* VDD_IVA + VDD_DSP on AM571 */
-					vin-supply = <&vmain>;
 					regulator-name = "smps45";
 					regulator-min-microvolt = <850000>;
 					regulator-max-microvolt = <1250000>;
@@ -94,7 +108,6 @@
 
 				smps6_reg: smps6 {
 					/* VDD_GPU */
-					vin-supply = <&vmain>;
 					regulator-name = "smps6";
 					regulator-min-microvolt = <850000>;
 					regulator-max-microvolt = <1250000>;
@@ -104,7 +117,6 @@
 
 				smps7_reg: smps7 {
 					/* VDD_CORE */
-					vin-supply = <&vmain>;
 					regulator-name = "smps7";
 					regulator-min-microvolt = <850000>;
 					regulator-max-microvolt = <1150000>;
@@ -115,13 +127,11 @@
 				smps8_reg: smps8 {
 					/* 5728 - VDD_IVAHD */
 					/* 5718 - N.C. test point */
-					vin-supply = <&vmain>;
 					regulator-name = "smps8";
 				};
 
 				smps9_reg: smps9 {
 					/* VDD_3_3D */
-					vin-supply = <&vmain>;
 					regulator-name = "smps9";
 					regulator-min-microvolt = <3300000>;
 					regulator-max-microvolt = <3300000>;
@@ -132,7 +142,6 @@
 				ldo1_reg: ldo1 {
 					/* VDDSHV8 - VSDMMC  */
 					/* NOTE: on rev 1.3a, data supply */
-					vin-supply = <&vmain>;
 					regulator-name = "ldo1";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <3300000>;
@@ -142,7 +151,6 @@
 
 				ldo2_reg: ldo2 {
 					/* VDDSH18V */
-					vin-supply = <&vmain>;
 					regulator-name = "ldo2";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
@@ -152,7 +160,6 @@
 
 				ldo3_reg: ldo3 {
 					/* R1.3a 572x V1_8PHY_LDO3: USB, SATA */
-					vin-supply = <&vmain>;
 					regulator-name = "ldo3";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
@@ -162,7 +169,6 @@
 
 				ldo4_reg: ldo4 {
 					/* R1.3a 572x V1_8PHY_LDO4: PCIE, HDMI*/
-					vin-supply = <&vmain>;
 					regulator-name = "ldo4";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
@@ -174,7 +180,6 @@
 
 				ldo9_reg: ldo9 {
 					/* VDD_RTC  */
-					vin-supply = <&vmain>;
 					regulator-name = "ldo9";
 					regulator-min-microvolt = <840000>;
 					regulator-max-microvolt = <1160000>;
@@ -184,7 +189,6 @@
 
 				ldoln_reg: ldoln {
 					/* VDDA_1V8_PLL */
-					vin-supply = <&vmain>;
 					regulator-name = "ldoln";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
@@ -194,7 +198,6 @@
 
 				ldousb_reg: ldousb {
 					/* VDDA_3V_USB: VDDA_USBHS33 */
-					vin-supply = <&vmain>;
 					regulator-name = "ldousb";
 					regulator-min-microvolt = <3300000>;
 					regulator-max-microvolt = <3300000>;
@@ -204,7 +207,6 @@
 
 				ldortc_reg: ldortc {
 					/* VDDA_RTC  */
-					vin-supply = <&vmain>;
 					regulator-name = "ldortc";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts
index cbc17b0794b1..4128fa91823c 100644
--- a/arch/arm/boot/dts/dm8148-evm.dts
+++ b/arch/arm/boot/dts/dm8148-evm.dts
@@ -93,6 +93,10 @@
 	};
 };
 
+&mmc1 {
+        status = "disabled";
+};
+
 &mmc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&sd1_pins>;
@@ -101,6 +105,10 @@
 	cd-gpios = <&gpio2 6 GPIO_ACTIVE_LOW>;
 };
 
+&mmc3 {
+        status = "disabled";
+};
+
 &pincntl {
 	sd1_pins: pinmux_sd1_pins {
 		pinctrl-single,pins = <
diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts
index 5d4313fd5a46..3f184863e0c5 100644
--- a/arch/arm/boot/dts/dm8148-t410.dts
+++ b/arch/arm/boot/dts/dm8148-t410.dts
@@ -45,6 +45,14 @@
 	phy-mode = "rgmii";
 };
 
+&mmc1 {
+	status = "disabled";
+};
+
+&mmc2 {
+	status = "disabled";
+};
+
 &mmc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&sd2_pins>;
@@ -53,6 +61,7 @@
 	dmas = <&edma_xbar 8 0 1	/* use SDTXEVT1 instead of MCASP0TX */
 		&edma_xbar 9 0 2>;	/* use SDRXEVT1 instead of MCASP0RX */
 	dma-names = "tx", "rx";
+	non-removable;
 };
 
 &pincntl {
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index d4537dc61497..f23cae0c2179 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -509,7 +509,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index e0074014385a..de559f6e4fee 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1451,6 +1451,8 @@
 			ti,hwmods = "gpmc";
 			reg = <0x50000000 0x37c>;      /* device IO registers */
 			interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
+			dmas = <&edma_xbar 4 0>;
+			dma-names = "rxtx";
 			gpmc,num-cs = <8>;
 			gpmc,num-waitpins = <2>;
 			#address-cells = <2>;
@@ -1626,7 +1628,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
@@ -1661,7 +1662,7 @@
 			status = "disabled";
 
 			davinci_mdio: mdio@48485000 {
-				compatible = "ti,davinci_mdio";
+				compatible = "ti,cpsw-mdio","ti,davinci_mdio";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				ti,hwmods = "davinci_mdio";
diff --git a/arch/arm/boot/dts/dra74x.dtsi b/arch/arm/boot/dts/dra74x.dtsi
index 4220eeffc65a..5e06020f450b 100644
--- a/arch/arm/boot/dts/dra74x.dtsi
+++ b/arch/arm/boot/dts/dra74x.dtsi
@@ -107,8 +107,8 @@
 	reg = <0x58000000 0x80>,
 	      <0x58004054 0x4>,
 	      <0x58004300 0x20>,
-	      <0x58005054 0x4>,
-	      <0x58005300 0x20>;
+	      <0x58009054 0x4>,
+	      <0x58009300 0x20>;
 	reg-names = "dss", "pll1_clkctrl", "pll1",
 		    "pll2_clkctrl", "pll2";
 
diff --git a/arch/arm/boot/dts/exynos5250-snow-common.dtsi b/arch/arm/boot/dts/exynos5250-snow-common.dtsi
index ddfe1f558c10..fa14f77df563 100644
--- a/arch/arm/boot/dts/exynos5250-snow-common.dtsi
+++ b/arch/arm/boot/dts/exynos5250-snow-common.dtsi
@@ -242,7 +242,7 @@
 	hpd-gpios = <&gpx0 7 GPIO_ACTIVE_HIGH>;
 
 	ports {
-		port0 {
+		port {
 			dp_out: endpoint {
 				remote-endpoint = <&bridge_in>;
 			};
@@ -485,13 +485,20 @@
 		edid-emulation = <5>;
 
 		ports {
-			port0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
 				bridge_out: endpoint {
 					remote-endpoint = <&panel_in>;
 				};
 			};
 
-			port1 {
+			port@1 {
+				reg = <1>;
+
 				bridge_in: endpoint {
 					remote-endpoint = <&dp_out>;
 				};
diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts
index f9d2e4f1a0e0..1de972d46a87 100644
--- a/arch/arm/boot/dts/exynos5420-peach-pit.dts
+++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts
@@ -163,7 +163,7 @@
 	hpd-gpios = <&gpx2 6 GPIO_ACTIVE_HIGH>;
 
 	ports {
-		port0 {
+		port {
 			dp_out: endpoint {
 				remote-endpoint = <&bridge_in>;
 			};
@@ -631,13 +631,20 @@
 		use-external-pwm;
 
 		ports {
-			port0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
 				bridge_out: endpoint {
 					remote-endpoint = <&panel_in>;
 				};
 			};
 
-			port1 {
+			port@1 {
+				reg = <1>;
+
 				bridge_in: endpoint {
 					remote-endpoint = <&dp_out>;
 				};
diff --git a/arch/arm/boot/dts/omap3-evm-37xx.dts b/arch/arm/boot/dts/omap3-evm-37xx.dts
index 76056ba92ced..ed449827c3d3 100644
--- a/arch/arm/boot/dts/omap3-evm-37xx.dts
+++ b/arch/arm/boot/dts/omap3-evm-37xx.dts
@@ -85,7 +85,7 @@
 			OMAP3_CORE1_IOPAD(0x2158, PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc2_clk.sdmmc2_clk */
 			OMAP3_CORE1_IOPAD(0x215a, PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc2_cmd.sdmmc2_cmd */
 			OMAP3_CORE1_IOPAD(0x215c, PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc2_dat0.sdmmc2_dat0 */
-			OMAP3_CORE1_IOPAD(0x215e, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat1.sdmmc2_dat1 */
+			OMAP3_CORE1_IOPAD(0x215e, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat1.sdmmc2_dat1 */
 			OMAP3_CORE1_IOPAD(0x2160, PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc2_dat2.sdmmc2_dat2 */
 			OMAP3_CORE1_IOPAD(0x2162, PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc2_dat3.sdmmc2_dat3 */
 		>;
diff --git a/arch/arm/boot/dts/omap3-igep.dtsi b/arch/arm/boot/dts/omap3-igep.dtsi
index 41f5d386f21f..f4f2ce46d681 100644
--- a/arch/arm/boot/dts/omap3-igep.dtsi
+++ b/arch/arm/boot/dts/omap3-igep.dtsi
@@ -188,6 +188,7 @@
 	vmmc-supply = <&vmmc1>;
 	vmmc_aux-supply = <&vsim>;
 	bus-width = <4>;
+	cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_LOW>;
 };
 
 &mmc3 {
diff --git a/arch/arm/boot/dts/omap3-igep0020-common.dtsi b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
index d6f839cab649..b6971060648a 100644
--- a/arch/arm/boot/dts/omap3-igep0020-common.dtsi
+++ b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
@@ -194,6 +194,12 @@
 			OMAP3630_CORE2_IOPAD(0x25f8, PIN_OUTPUT | MUX_MODE4) /* etk_d14.gpio_28 */
 		>;
 	};
+
+	mmc1_wp_pins: pinmux_mmc1_cd_pins {
+		pinctrl-single,pins = <
+			OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT | MUX_MODE4)   /* etk_d15.gpio_29 */
+		>;
+	};
 };
 
 &i2c3 {
@@ -250,3 +256,8 @@
 		};
 	};
 };
+
+&mmc1 {
+	pinctrl-0 = <&mmc1_pins &mmc1_wp_pins>;
+	wp-gpios = <&gpio1 29 GPIO_ACTIVE_LOW>;	/* gpio_29 */
+};
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index d9e2d9c6e999..2b74a81d1de2 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -288,7 +288,7 @@
 		pinctrl-single,pins = <
 			OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLUP | MUX_MODE1)	/* ssi1_rdy_tx */
 			OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE1)		/* ssi1_flag_tx */
-			OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */
+			OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4)		/* ssi1_wake_tx (cawake) */
 			OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE1)		/* ssi1_dat_tx */
 			OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE1)		/* ssi1_dat_rx */
 			OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE1)		/* ssi1_flag_rx */
@@ -300,7 +300,7 @@
 	modem_pins: pinmux_modem {
 		pinctrl-single,pins = <
 			OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE4)		/* gpio 70 => cmt_apeslpx */
-			OMAP3_CORE1_IOPAD(0x20e0, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* gpio 72 => ape_rst_rq */
+			OMAP3_CORE1_IOPAD(0x20e0, PIN_INPUT | MUX_MODE4)		/* gpio 72 => ape_rst_rq */
 			OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE4)		/* gpio 73 => cmt_rst_rq */
 			OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE4)		/* gpio 74 => cmt_en */
 			OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE4)		/* gpio 75 => cmt_rst */
diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index a00ca761675d..927b17fc4ed8 100644
--- a/arch/arm/boot/dts/omap3-n950-n9.dtsi
+++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi
@@ -97,7 +97,7 @@
 			OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE1)            /* ssi1_dat_tx */
 			OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE1)            /* ssi1_flag_tx */
 			OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLUP | MUX_MODE1)      /* ssi1_rdy_tx */
-			OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */
+			OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4)	/* ssi1_wake_tx (cawake) */
 			OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE1)             /* ssi1_dat_rx */
 			OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE1)             /* ssi1_flag_rx */
 			OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | MUX_MODE1)            /* ssi1_rdy_rx */
@@ -110,7 +110,7 @@
 			OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE7)            /* ssi1_dat_tx */
 			OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE7)            /* ssi1_flag_tx */
 			OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLDOWN | MUX_MODE7)    /* ssi1_rdy_tx */
-			OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */
+			OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4)	/* ssi1_wake_tx (cawake) */
 			OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE7)             /* ssi1_dat_rx */
 			OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE7)             /* ssi1_flag_rx */
 			OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | MUX_MODE4)            /* ssi1_rdy_rx */
@@ -120,7 +120,7 @@
 
 	modem_pins1: pinmux_modem_core1_pins {
 		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x207a, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* gpio_34 (ape_rst_rq) */
+			OMAP3_CORE1_IOPAD(0x207a, PIN_INPUT | MUX_MODE4)	/* gpio_34 (ape_rst_rq) */
 			OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE4)            /* gpio_88 (cmt_rst_rq) */
 			OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE4)            /* gpio_93 (cmt_apeslpx) */
 		>;
diff --git a/arch/arm/boot/dts/omap3-zoom3.dts b/arch/arm/boot/dts/omap3-zoom3.dts
index f19170bdcc1f..c29b41dc7b95 100644
--- a/arch/arm/boot/dts/omap3-zoom3.dts
+++ b/arch/arm/boot/dts/omap3-zoom3.dts
@@ -98,7 +98,7 @@
 		pinctrl-single,pins = <
                         OMAP3_CORE1_IOPAD(0x2174, PIN_INPUT_PULLUP | MUX_MODE0)	/* uart2_cts.uart2_cts */
                         OMAP3_CORE1_IOPAD(0x2176, PIN_OUTPUT | MUX_MODE0)		/* uart2_rts.uart2_rts */
-                        OMAP3_CORE1_IOPAD(0x217a, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart2_rx.uart2_rx */
+                        OMAP3_CORE1_IOPAD(0x217a, PIN_INPUT | MUX_MODE0)		/* uart2_rx.uart2_rx */
                         OMAP3_CORE1_IOPAD(0x2178, PIN_OUTPUT | MUX_MODE0)		/* uart2_tx.uart2_tx */
 		>;
 	};
@@ -107,7 +107,7 @@
 		pinctrl-single,pins = <
                         OMAP3_CORE1_IOPAD(0x219a, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* uart3_cts_rctx.uart3_cts_rctx */
                         OMAP3_CORE1_IOPAD(0x219c, PIN_OUTPUT | MUX_MODE0)		/* uart3_rts_sd.uart3_rts_sd */
-                        OMAP3_CORE1_IOPAD(0x219e, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart3_rx_irrx.uart3_rx_irrx */
+                        OMAP3_CORE1_IOPAD(0x219e, PIN_INPUT | MUX_MODE0)		/* uart3_rx_irrx.uart3_rx_irrx */
                         OMAP3_CORE1_IOPAD(0x21a0, PIN_OUTPUT | MUX_MODE0)		/* uart3_tx_irtx.uart3_tx_irtx */
 		>;
 	};
@@ -125,7 +125,7 @@
 		pinctrl-single,pins = <
 			OMAP3630_CORE2_IOPAD(0x25d8, PIN_INPUT_PULLUP | MUX_MODE2)	/* etk_clk.sdmmc3_clk */
 			OMAP3630_CORE2_IOPAD(0x25e4, PIN_INPUT_PULLUP | MUX_MODE2)	/* etk_d4.sdmmc3_dat0 */
-			OMAP3630_CORE2_IOPAD(0x25e6, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d5.sdmmc3_dat1 */
+			OMAP3630_CORE2_IOPAD(0x25e6, PIN_INPUT_PULLUP | MUX_MODE2)	/* etk_d5.sdmmc3_dat1 */
 			OMAP3630_CORE2_IOPAD(0x25e8, PIN_INPUT_PULLUP | MUX_MODE2)	/* etk_d6.sdmmc3_dat2 */
 			OMAP3630_CORE2_IOPAD(0x25e2, PIN_INPUT_PULLUP | MUX_MODE2)	/* etk_d3.sdmmc3_dat3 */
 		>;
diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi
index dc759a3028b7..5d5b620b7d9b 100644
--- a/arch/arm/boot/dts/omap5-board-common.dtsi
+++ b/arch/arm/boot/dts/omap5-board-common.dtsi
@@ -14,6 +14,29 @@
 		display0 = &hdmi0;
 	};
 
+	vmain: fixedregulator-vmain {
+		compatible = "regulator-fixed";
+		regulator-name = "vmain";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	vsys_cobra: fixedregulator-vsys_cobra {
+		compatible = "regulator-fixed";
+		regulator-name = "vsys_cobra";
+		vin-supply = <&vmain>;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	vdds_1v8_main: fixedregulator-vdds_1v8_main {
+		compatible = "regulator-fixed";
+		regulator-name = "vdds_1v8_main";
+		vin-supply = <&smps7_reg>;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+
 	vmmcsd_fixed: fixedregulator-mmcsd {
 		compatible = "regulator-fixed";
 		regulator-name = "vmmcsd_fixed";
@@ -309,7 +332,7 @@
 
 	wlcore_irq_pin: pinmux_wlcore_irq_pin {
 		pinctrl-single,pins = <
-			OMAP5_IOPAD(0x40, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE6)	/* llia_wakereqin.gpio1_wk14 */
+			OMAP5_IOPAD(0x40, PIN_INPUT_PULLUP | MUX_MODE6)	/* llia_wakereqin.gpio1_wk14 */
 		>;
 	};
 };
@@ -409,6 +432,26 @@
 
 			ti,ldo6-vibrator;
 
+			smps123-in-supply = <&vsys_cobra>;
+			smps45-in-supply = <&vsys_cobra>;
+			smps6-in-supply = <&vsys_cobra>;
+			smps7-in-supply = <&vsys_cobra>;
+			smps8-in-supply = <&vsys_cobra>;
+			smps9-in-supply = <&vsys_cobra>;
+			smps10_out2-in-supply = <&vsys_cobra>;
+			smps10_out1-in-supply = <&vsys_cobra>;
+			ldo1-in-supply = <&vsys_cobra>;
+			ldo2-in-supply = <&vsys_cobra>;
+			ldo3-in-supply = <&vdds_1v8_main>;
+			ldo4-in-supply = <&vdds_1v8_main>;
+			ldo5-in-supply = <&vsys_cobra>;
+			ldo6-in-supply = <&vdds_1v8_main>;
+			ldo7-in-supply = <&vsys_cobra>;
+			ldo8-in-supply = <&vsys_cobra>;
+			ldo9-in-supply = <&vmmcsd_fixed>;
+			ldoln-in-supply = <&vsys_cobra>;
+			ldousb-in-supply = <&vsys_cobra>;
+
 			regulators {
 				smps123_reg: smps123 {
 					/* VDD_OPP_MPU */
@@ -600,7 +643,8 @@
 		pinctrl-0 = <&twl6040_pins>;
 
 		interrupts = <GIC_SPI 119 IRQ_TYPE_NONE>; /* IRQ_SYS_2N cascaded to gic */
-		ti,audpwron-gpio = <&gpio5 13 GPIO_ACTIVE_HIGH>;  /* gpio line 141 */
+
+		/* audpwron gpio defined in the board specific dts */
 
 		vio-supply = <&smps7_reg>;
 		v2v1-supply = <&smps9_reg>;
diff --git a/arch/arm/boot/dts/omap5-igep0050.dts b/arch/arm/boot/dts/omap5-igep0050.dts
index 46ecb1dd3b5c..f75ce02fb398 100644
--- a/arch/arm/boot/dts/omap5-igep0050.dts
+++ b/arch/arm/boot/dts/omap5-igep0050.dts
@@ -35,6 +35,22 @@
 	};
 };
 
+/* LDO4 is VPP1 - ball AD9 */
+&ldo4_reg {
+	regulator-min-microvolt = <2000000>;
+	regulator-max-microvolt = <2000000>;
+};
+
+/*
+ * LDO7 is used for HDMI: VDDA_DSIPORTA - ball AA33, VDDA_DSIPORTC - ball AE33,
+ * VDDA_HDMI - ball AN25
+ */
+&ldo7_reg {
+	status = "okay";
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
+};
+
 &omap5_pmx_core {
 	i2c4_pins: pinmux_i2c4_pins {
 		pinctrl-single,pins = <
@@ -52,3 +68,13 @@
 		<&gpio7 3 0>;		/* 195, SDA */
 };
 
+&twl6040 {
+	ti,audpwron-gpio = <&gpio5 16 GPIO_ACTIVE_HIGH>;  /* gpio line 144 */
+};
+
+&twl6040_pins {
+	pinctrl-single,pins = <
+		OMAP5_IOPAD(0x1c4, PIN_OUTPUT | MUX_MODE6)	/* mcspi1_somi.gpio5_144 */
+		OMAP5_IOPAD(0x1ca, PIN_OUTPUT | MUX_MODE6)	/* perslimbus2_clock.gpio5_145 */
+	>;
+};
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index 60b3fbb3bf07..a51e60518eb6 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -51,3 +51,13 @@
 		<&gpio9 1 GPIO_ACTIVE_HIGH>,	/* TCA6424A P00, LS OE */
 		<&gpio7 1 GPIO_ACTIVE_HIGH>;	/* GPIO 193, HPD */
 };
+
+&twl6040 {
+	ti,audpwron-gpio = <&gpio5 13 GPIO_ACTIVE_HIGH>;  /* gpio line 141 */
+};
+
+&twl6040_pins {
+	pinctrl-single,pins = <
+		OMAP5_IOPAD(0x1be, PIN_OUTPUT | MUX_MODE6)	/* mcspi1_somi.gpio5_141 */
+	>;
+};
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 3b44ef3cff12..3ebee530f2b0 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -539,8 +539,9 @@
 	gmac: ethernet@ff290000 {
 		compatible = "rockchip,rk3288-gmac";
 		reg = <0xff290000 0x10000>;
-		interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "macirq";
+		interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
+				<GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "macirq", "eth_wake_irq";
 		rockchip,grf = <&grf>;
 		clocks = <&cru SCLK_MAC>,
 			<&cru SCLK_MAC_RX>, <&cru SCLK_MAC_TX>,
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
index a3601e4c0a2e..b844473601d2 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
@@ -136,6 +136,7 @@
 &gmac1 {
 	status = "okay";
 	phy-mode = "rgmii";
+	phy-handle = <&phy1>;
 
 	snps,reset-gpio = <&porta 0 GPIO_ACTIVE_LOW>;
 	snps,reset-active-low;
diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi
index ad8ba10764a3..d294e82447a2 100644
--- a/arch/arm/boot/dts/stih407-family.dtsi
+++ b/arch/arm/boot/dts/stih407-family.dtsi
@@ -24,18 +24,21 @@
 			compatible = "shared-dma-pool";
 			reg = <0x40000000 0x01000000>;
 			no-map;
+			status = "disabled";
 		};
 
 		gp1_reserved: rproc@41000000 {
 			compatible = "shared-dma-pool";
 			reg = <0x41000000 0x01000000>;
 			no-map;
+			status = "disabled";
 		};
 
 		audio_reserved: rproc@42000000 {
 			compatible = "shared-dma-pool";
 			reg = <0x42000000 0x01000000>;
 			no-map;
+			status = "disabled";
 		};
 
 		dmu_reserved: rproc@43000000 {
diff --git a/arch/arm/boot/dts/sun6i-a31s-primo81.dts b/arch/arm/boot/dts/sun6i-a31s-primo81.dts
index 68b479b8772c..73c133f5e79c 100644
--- a/arch/arm/boot/dts/sun6i-a31s-primo81.dts
+++ b/arch/arm/boot/dts/sun6i-a31s-primo81.dts
@@ -176,8 +176,6 @@
 };
 
 &reg_dc1sw {
-	regulator-min-microvolt = <3000000>;
-	regulator-max-microvolt = <3000000>;
 	regulator-name = "vcc-lcd";
 };
 
diff --git a/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts b/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts
index 360adfb1e9ca..d6ad6196a768 100644
--- a/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts
+++ b/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts
@@ -135,8 +135,6 @@
 
 &reg_dc1sw {
 	regulator-name = "vcc-lcd-usb2";
-	regulator-min-microvolt = <3000000>;
-	regulator-max-microvolt = <3000000>;
 };
 
 &reg_dc5ldo {
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 10f49ab5328e..47195e8690b4 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -82,6 +82,7 @@ CONFIG_TOUCHSCREEN_MMS114=y
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_MAX77693_HAPTIC=y
 CONFIG_INPUT_MAX8997_HAPTIC=y
+CONFIG_KEYBOARD_SAMSUNG=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_SAMSUNG=y
 CONFIG_SERIAL_SAMSUNG_CONSOLE=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 8f857564657f..8a5fff1b7f6f 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -264,6 +264,7 @@ CONFIG_KEYBOARD_TEGRA=y
 CONFIG_KEYBOARD_SPEAR=y
 CONFIG_KEYBOARD_ST_KEYSCAN=y
 CONFIG_KEYBOARD_CROS_EC=m
+CONFIG_KEYBOARD_SAMSUNG=m
 CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_MOUSE_CYAPA=m
 CONFIG_MOUSE_ELAN_I2C=y
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 19cfab526d13..20febb368844 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -29,7 +29,7 @@
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+	return (pmd_t *)get_zeroed_page(GFP_KERNEL);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index aeddd28b3595..92fd2c8a9af0 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -193,6 +193,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 
 #define pmd_large(pmd)		(pmd_val(pmd) & 2)
 #define pmd_bad(pmd)		(pmd_val(pmd) & 2)
+#define pmd_present(pmd)	(pmd_val(pmd))
 
 #define copy_pmd(pmdpd,pmdps)		\
 	do {				\
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index fa70db7c714b..2a029bceaf2f 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -211,6 +211,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 						: !!(pmd_val(pmd) & (val)))
 #define pmd_isclear(pmd, val)	(!(pmd_val(pmd) & (val)))
 
+#define pmd_present(pmd)	(pmd_isset((pmd), L_PMD_SECT_VALID))
 #define pmd_young(pmd)		(pmd_isset((pmd), PMD_SECT_AF))
 #define pte_special(pte)	(pte_isset((pte), L_PTE_SPECIAL))
 static inline pte_t pte_mkspecial(pte_t pte)
@@ -249,10 +250,10 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 #define pfn_pmd(pfn,prot)	(__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
-/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
+/* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */
 static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 {
-	return __pmd(0);
+	return __pmd(pmd_val(pmd) & ~L_PMD_SECT_VALID);
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 348caabb7625..d62204060cbe 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -182,7 +182,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 #define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
 
 #define pmd_none(pmd)		(!pmd_val(pmd))
-#define pmd_present(pmd)	(pmd_val(pmd))
 
 static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 {
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ef9119f7462e..4d9375814b53 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -733,8 +733,8 @@ static int vfp_set(struct task_struct *target,
 	if (ret)
 		return ret;
 
-	vfp_flush_hwstate(thread);
 	thread->vfpstate.hard = new_vfp;
+	vfp_flush_hwstate(thread);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index df90bc59bfce..861521606c6d 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -486,7 +486,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 
 static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
 {
-	trace_ipi_raise(target, ipi_types[ipinr]);
+	trace_ipi_raise_rcuidle(target, ipi_types[ipinr]);
 	__smp_cross_call(target, ipinr);
 }
 
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index e65aa7d11b20..20dcf6e904b2 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -61,7 +61,6 @@ config ARCH_EXYNOS4
 	select CLKSRC_SAMSUNG_PWM if CPU_EXYNOS4210
 	select CPU_EXYNOS4210
 	select GIC_NON_BANKED
-	select KEYBOARD_SAMSUNG if INPUT_KEYBOARD
 	select MIGHT_HAVE_CACHE_L2X0
 	help
 	  Samsung EXYNOS4 (Cortex-A9) SoC based systems
diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c
index a38b16b69923..b56de4b8cdf2 100644
--- a/arch/arm/mach-imx/mach-imx6ul.c
+++ b/arch/arm/mach-imx/mach-imx6ul.c
@@ -46,7 +46,7 @@ static int ksz8081_phy_fixup(struct phy_device *dev)
 static void __init imx6ul_enet_phy_init(void)
 {
 	if (IS_BUILTIN(CONFIG_PHYLIB))
-		phy_register_fixup_for_uid(PHY_ID_KSZ8081, 0xffffffff,
+		phy_register_fixup_for_uid(PHY_ID_KSZ8081, MICREL_PHY_ID_MASK,
 					   ksz8081_phy_fixup);
 }
 
diff --git a/arch/arm/mach-omap1/ams-delta-fiq-handler.S b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
index 5d7fb596bf4a..bf608441b357 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq-handler.S
+++ b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
@@ -43,8 +43,8 @@
 #define OTHERS_MASK			(MODEM_IRQ_MASK | HOOK_SWITCH_MASK)
 
 /* IRQ handler register bitmasks */
-#define DEFERRED_FIQ_MASK		(0x1 << (INT_DEFERRED_FIQ % IH2_BASE))
-#define GPIO_BANK1_MASK  		(0x1 << INT_GPIO_BANK1)
+#define DEFERRED_FIQ_MASK		OMAP_IRQ_BIT(INT_DEFERRED_FIQ)
+#define GPIO_BANK1_MASK  		OMAP_IRQ_BIT(INT_GPIO_BANK1)
 
 /* Driver buffer byte offsets */
 #define BUF_MASK			(FIQ_MASK * 4)
@@ -110,7 +110,7 @@ ENTRY(qwerty_fiqin_start)
 	mov r8, #2				@ reset FIQ agreement
 	str r8, [r12, #IRQ_CONTROL_REG_OFFSET]
 
-	cmp r10, #INT_GPIO_BANK1		@ is it GPIO bank interrupt?
+	cmp r10, #(INT_GPIO_BANK1 - NR_IRQS_LEGACY)	@ is it GPIO interrupt?
 	beq gpio				@ yes - process it
 
 	mov r8, #1
diff --git a/arch/arm/mach-omap1/ams-delta-fiq.c b/arch/arm/mach-omap1/ams-delta-fiq.c
index d1f12095f315..ec760ae2f917 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq.c
+++ b/arch/arm/mach-omap1/ams-delta-fiq.c
@@ -109,7 +109,8 @@ void __init ams_delta_init_fiq(void)
 	 * Since no set_type() method is provided by OMAP irq chip,
 	 * switch to edge triggered interrupt type manually.
 	 */
-	offset = IRQ_ILR0_REG_OFFSET + INT_DEFERRED_FIQ * 0x4;
+	offset = IRQ_ILR0_REG_OFFSET +
+			((INT_DEFERRED_FIQ - NR_IRQS_LEGACY) & 0x1f) * 0x4;
 	val = omap_readl(DEFERRED_FIQ_IH_BASE + offset) & ~(1 << 1);
 	omap_writel(val, DEFERRED_FIQ_IH_BASE + offset);
 
@@ -149,7 +150,7 @@ void __init ams_delta_init_fiq(void)
 	/*
 	 * Redirect GPIO interrupts to FIQ
 	 */
-	offset = IRQ_ILR0_REG_OFFSET + INT_GPIO_BANK1 * 0x4;
+	offset = IRQ_ILR0_REG_OFFSET + (INT_GPIO_BANK1 - NR_IRQS_LEGACY) * 0x4;
 	val = omap_readl(OMAP_IH1_BASE + offset) | 1;
 	omap_writel(val, OMAP_IH1_BASE + offset);
 }
diff --git a/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h b/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h
index adb5e7649659..6dfc3e1210a3 100644
--- a/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h
+++ b/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h
@@ -14,6 +14,8 @@
 #ifndef __AMS_DELTA_FIQ_H
 #define __AMS_DELTA_FIQ_H
 
+#include <mach/irqs.h>
+
 /*
  * Interrupt number used for passing control from FIQ to IRQ.
  * IRQ12, described as reserved, has been selected.
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 0517f0c1581a..1a648e9dfaa0 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -17,6 +17,7 @@ config ARCH_OMAP3
 	select PM_OPP if PM
 	select PM if CPU_IDLE
 	select SOC_HAS_OMAP2_SDRC
+	select ARM_ERRATA_430973
 
 config ARCH_OMAP4
 	bool "TI OMAP4"
@@ -36,6 +37,7 @@ config ARCH_OMAP4
 	select PM if CPU_IDLE
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_775420
+	select OMAP_INTERCONNECT
 
 config SOC_OMAP5
 	bool "TI OMAP5"
@@ -67,6 +69,8 @@ config SOC_AM43XX
 	select HAVE_ARM_SCU
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select HAVE_ARM_TWD
+	select ARM_ERRATA_754322
+	select ARM_ERRATA_775420
 
 config SOC_DRA7XX
 	bool "TI DRA7XX"
@@ -240,4 +244,12 @@ endmenu
 
 endif
 
+config OMAP5_ERRATA_801819
+	bool "Errata 801819: An eviction from L1 data cache might stall indefinitely"
+	depends on SOC_OMAP5 || SOC_DRA7XX
+	help
+	  A livelock can occur in the L2 cache arbitration that might prevent
+	  a snoop from completing. Under certain conditions this can cause the
+	  system to deadlock.
+
 endmenu
diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h
index af2851fbcdf0..bae263fba640 100644
--- a/arch/arm/mach-omap2/omap-secure.h
+++ b/arch/arm/mach-omap2/omap-secure.h
@@ -46,6 +46,7 @@
 
 #define OMAP5_DRA7_MON_SET_CNTFRQ_INDEX	0x109
 #define OMAP5_MON_AMBA_IF_INDEX		0x108
+#define OMAP5_DRA7_MON_SET_ACR_INDEX	0x107
 
 /* Secure PPA(Primary Protected Application) APIs */
 #define OMAP4_PPA_L2_POR_INDEX		0x23
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index c625cc10d9f9..8cd1de914ee4 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -50,6 +50,39 @@ void __iomem *omap4_get_scu_base(void)
 	return scu_base;
 }
 
+#ifdef CONFIG_OMAP5_ERRATA_801819
+void omap5_erratum_workaround_801819(void)
+{
+	u32 acr, revidr;
+	u32 acr_mask;
+
+	/* REVIDR[3] indicates erratum fix available on silicon */
+	asm volatile ("mrc p15, 0, %0, c0, c0, 6" : "=r" (revidr));
+	if (revidr & (0x1 << 3))
+		return;
+
+	asm volatile ("mrc p15, 0, %0, c1, c0, 1" : "=r" (acr));
+	/*
+	 * BIT(27) - Disables streaming. All write-allocate lines allocate in
+	 * the L1 or L2 cache.
+	 * BIT(25) - Disables streaming. All write-allocate lines allocate in
+	 * the L1 cache.
+	 */
+	acr_mask = (0x3 << 25) | (0x3 << 27);
+	/* do we already have it done.. if yes, skip expensive smc */
+	if ((acr & acr_mask) == acr_mask)
+		return;
+
+	acr |= acr_mask;
+	omap_smc1(OMAP5_DRA7_MON_SET_ACR_INDEX, acr);
+
+	pr_debug("%s: ARM erratum workaround 801819 applied on CPU%d\n",
+		 __func__, smp_processor_id());
+}
+#else
+static inline void omap5_erratum_workaround_801819(void) { }
+#endif
+
 static void omap4_secondary_init(unsigned int cpu)
 {
 	/*
@@ -64,12 +97,15 @@ static void omap4_secondary_init(unsigned int cpu)
 		omap_secure_dispatcher(OMAP4_PPA_CPU_ACTRL_SMP_INDEX,
 							4, 0, 0, 0, 0, 0);
 
-	/*
-	 * Configure the CNTFRQ register for the secondary cpu's which
-	 * indicates the frequency of the cpu local timers.
-	 */
-	if (soc_is_omap54xx() || soc_is_dra7xx())
+	if (soc_is_omap54xx() || soc_is_dra7xx()) {
+		/*
+		 * Configure the CNTFRQ register for the secondary cpu's which
+		 * indicates the frequency of the cpu local timers.
+		 */
 		set_cntfreq();
+		/* Configure ACR to disable streaming WA for 801819 */
+		omap5_erratum_workaround_801819();
+	}
 
 	/*
 	 * Synchronise with the boot thread.
@@ -218,6 +254,8 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 
 	if (cpu_is_omap446x())
 		startup_addr = omap4460_secondary_startup;
+	if (soc_is_dra74x() || soc_is_omap54xx())
+		omap5_erratum_workaround_801819();
 
 	/*
 	 * Write the address of secondary startup routine into the
diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c
index 78af6d8cf2e2..daf2753de7aa 100644
--- a/arch/arm/mach-omap2/powerdomain.c
+++ b/arch/arm/mach-omap2/powerdomain.c
@@ -186,8 +186,9 @@ static int _pwrdm_state_switch(struct powerdomain *pwrdm, int flag)
 			trace_state = (PWRDM_TRACE_STATES_FLAG |
 				       ((next & OMAP_POWERSTATE_MASK) << 8) |
 				       ((prev & OMAP_POWERSTATE_MASK) << 0));
-			trace_power_domain_target(pwrdm->name, trace_state,
-						  smp_processor_id());
+			trace_power_domain_target_rcuidle(pwrdm->name,
+							  trace_state,
+							  smp_processor_id());
 		}
 		break;
 	default:
@@ -523,8 +524,8 @@ int pwrdm_set_next_pwrst(struct powerdomain *pwrdm, u8 pwrst)
 
 	if (arch_pwrdm && arch_pwrdm->pwrdm_set_next_pwrst) {
 		/* Trace the pwrdm desired target state */
-		trace_power_domain_target(pwrdm->name, pwrst,
-					  smp_processor_id());
+		trace_power_domain_target_rcuidle(pwrdm->name, pwrst,
+						  smp_processor_id());
 		/* Program the pwrdm desired target state */
 		ret = arch_pwrdm->pwrdm_set_next_pwrst(pwrdm, pwrst);
 	}
diff --git a/arch/arm/mach-omap2/powerdomains7xx_data.c b/arch/arm/mach-omap2/powerdomains7xx_data.c
index 0ec2d00f4237..eb350a673133 100644
--- a/arch/arm/mach-omap2/powerdomains7xx_data.c
+++ b/arch/arm/mach-omap2/powerdomains7xx_data.c
@@ -36,14 +36,7 @@ static struct powerdomain iva_7xx_pwrdm = {
 	.prcm_offs	  = DRA7XX_PRM_IVA_INST,
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
-	.pwrsts_logic_ret = PWRSTS_OFF,
 	.banks		  = 4,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* hwa_mem */
-		[1] = PWRSTS_OFF_RET,	/* sl2_mem */
-		[2] = PWRSTS_OFF_RET,	/* tcm1_mem */
-		[3] = PWRSTS_OFF_RET,	/* tcm2_mem */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* hwa_mem */
 		[1] = PWRSTS_ON,	/* sl2_mem */
@@ -76,12 +69,7 @@ static struct powerdomain ipu_7xx_pwrdm = {
 	.prcm_offs	  = DRA7XX_PRM_IPU_INST,
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
-	.pwrsts_logic_ret = PWRSTS_OFF,
 	.banks		  = 2,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* aessmem */
-		[1] = PWRSTS_OFF_RET,	/* periphmem */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* aessmem */
 		[1] = PWRSTS_ON,	/* periphmem */
@@ -95,11 +83,7 @@ static struct powerdomain dss_7xx_pwrdm = {
 	.prcm_offs	  = DRA7XX_PRM_DSS_INST,
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
-	.pwrsts_logic_ret = PWRSTS_OFF,
 	.banks		  = 1,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* dss_mem */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* dss_mem */
 	},
@@ -111,13 +95,8 @@ static struct powerdomain l4per_7xx_pwrdm = {
 	.name		  = "l4per_pwrdm",
 	.prcm_offs	  = DRA7XX_PRM_L4PER_INST,
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
-	.pwrsts		  = PWRSTS_RET_ON,
-	.pwrsts_logic_ret = PWRSTS_RET,
+	.pwrsts		  = PWRSTS_ON,
 	.banks		  = 2,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* nonretained_bank */
-		[1] = PWRSTS_OFF_RET,	/* retained_bank */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* nonretained_bank */
 		[1] = PWRSTS_ON,	/* retained_bank */
@@ -132,9 +111,6 @@ static struct powerdomain gpu_7xx_pwrdm = {
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
 	.banks		  = 1,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* gpu_mem */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* gpu_mem */
 	},
@@ -148,8 +124,6 @@ static struct powerdomain wkupaon_7xx_pwrdm = {
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_ON,
 	.banks		  = 1,
-	.pwrsts_mem_ret	= {
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* wkup_bank */
 	},
@@ -161,15 +135,7 @@ static struct powerdomain core_7xx_pwrdm = {
 	.prcm_offs	  = DRA7XX_PRM_CORE_INST,
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_ON,
-	.pwrsts_logic_ret = PWRSTS_RET,
 	.banks		  = 5,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* core_nret_bank */
-		[1] = PWRSTS_OFF_RET,	/* core_ocmram */
-		[2] = PWRSTS_OFF_RET,	/* core_other_bank */
-		[3] = PWRSTS_OFF_RET,	/* ipu_l2ram */
-		[4] = PWRSTS_OFF_RET,	/* ipu_unicache */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* core_nret_bank */
 		[1] = PWRSTS_ON,	/* core_ocmram */
@@ -226,11 +192,7 @@ static struct powerdomain vpe_7xx_pwrdm = {
 	.prcm_offs	  = DRA7XX_PRM_VPE_INST,
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
-	.pwrsts_logic_ret = PWRSTS_OFF,
 	.banks		  = 1,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* vpe_bank */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* vpe_bank */
 	},
@@ -260,14 +222,8 @@ static struct powerdomain l3init_7xx_pwrdm = {
 	.name		  = "l3init_pwrdm",
 	.prcm_offs	  = DRA7XX_PRM_L3INIT_INST,
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
-	.pwrsts		  = PWRSTS_RET_ON,
-	.pwrsts_logic_ret = PWRSTS_RET,
+	.pwrsts		  = PWRSTS_ON,
 	.banks		  = 3,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* gmac_bank */
-		[1] = PWRSTS_OFF_RET,	/* l3init_bank1 */
-		[2] = PWRSTS_OFF_RET,	/* l3init_bank2 */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* gmac_bank */
 		[1] = PWRSTS_ON,	/* l3init_bank1 */
@@ -283,9 +239,6 @@ static struct powerdomain eve3_7xx_pwrdm = {
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
 	.banks		  = 1,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* eve3_bank */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* eve3_bank */
 	},
@@ -299,9 +252,6 @@ static struct powerdomain emu_7xx_pwrdm = {
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
 	.banks		  = 1,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* emu_bank */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* emu_bank */
 	},
@@ -314,11 +264,6 @@ static struct powerdomain dsp2_7xx_pwrdm = {
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
 	.banks		  = 3,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* dsp2_edma */
-		[1] = PWRSTS_OFF_RET,	/* dsp2_l1 */
-		[2] = PWRSTS_OFF_RET,	/* dsp2_l2 */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* dsp2_edma */
 		[1] = PWRSTS_ON,	/* dsp2_l1 */
@@ -334,11 +279,6 @@ static struct powerdomain dsp1_7xx_pwrdm = {
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
 	.banks		  = 3,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* dsp1_edma */
-		[1] = PWRSTS_OFF_RET,	/* dsp1_l1 */
-		[2] = PWRSTS_OFF_RET,	/* dsp1_l2 */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* dsp1_edma */
 		[1] = PWRSTS_ON,	/* dsp1_l1 */
@@ -354,9 +294,6 @@ static struct powerdomain cam_7xx_pwrdm = {
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
 	.banks		  = 1,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* vip_bank */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* vip_bank */
 	},
@@ -370,9 +307,6 @@ static struct powerdomain eve4_7xx_pwrdm = {
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
 	.banks		  = 1,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* eve4_bank */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* eve4_bank */
 	},
@@ -386,9 +320,6 @@ static struct powerdomain eve2_7xx_pwrdm = {
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
 	.banks		  = 1,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* eve2_bank */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* eve2_bank */
 	},
@@ -402,9 +333,6 @@ static struct powerdomain eve1_7xx_pwrdm = {
 	.prcm_partition	  = DRA7XX_PRM_PARTITION,
 	.pwrsts		  = PWRSTS_OFF_ON,
 	.banks		  = 1,
-	.pwrsts_mem_ret	= {
-		[0] = PWRSTS_OFF_RET,	/* eve1_bank */
-	},
 	.pwrsts_mem_on	= {
 		[0] = PWRSTS_ON,	/* eve1_bank */
 	},
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 5b385bb8aff9..cb9497a20fb3 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -496,8 +496,7 @@ void __init omap_init_time(void)
 	__omap_sync32k_timer_init(1, "timer_32k_ck", "ti,timer-alwon",
 			2, "timer_sys_ck", NULL, false);
 
-	if (of_have_populated_dt())
-		clocksource_probe();
+	clocksource_probe();
 }
 
 #if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM43XX)
@@ -505,6 +504,8 @@ void __init omap3_secure_sync32k_timer_init(void)
 {
 	__omap_sync32k_timer_init(12, "secure_32k_fck", "ti,timer-secure",
 			2, "timer_sys_ck", NULL, false);
+
+	clocksource_probe();
 }
 #endif /* CONFIG_ARCH_OMAP3 */
 
@@ -513,6 +514,8 @@ void __init omap3_gptimer_timer_init(void)
 {
 	__omap_sync32k_timer_init(2, "timer_sys_ck", NULL,
 			1, "timer_sys_ck", "ti,timer-alwon", true);
+
+	clocksource_probe();
 }
 #endif
 
diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c
index 5766ce2be32b..8409cab3f760 100644
--- a/arch/arm/mach-vexpress/spc.c
+++ b/arch/arm/mach-vexpress/spc.c
@@ -547,7 +547,7 @@ static struct clk *ve_spc_clk_register(struct device *cpu_dev)
 
 	init.name = dev_name(cpu_dev);
 	init.ops = &clk_spc_ops;
-	init.flags = CLK_IS_ROOT | CLK_GET_RATE_NOCACHE;
+	init.flags = CLK_GET_RATE_NOCACHE;
 	init.num_parents = 0;
 
 	return devm_clk_register(cpu_dev, &spc->hw);
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 84baa16f4c0b..e93aa6734147 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -68,7 +68,7 @@
 #include <linux/platform_data/asoc-s3c.h>
 #include <linux/platform_data/spi-s3c64xx.h>
 
-static u64 samsung_device_dma_mask = DMA_BIT_MASK(32);
+#define samsung_device_dma_mask (*((u64[]) { DMA_BIT_MASK(32) }))
 
 /* AC97 */
 #ifdef CONFIG_CPU_S3C2440
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 76747d92bc72..5a0a691d4220 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -113,6 +113,18 @@ config ARCH_PHYS_ADDR_T_64BIT
 config MMU
 	def_bool y
 
+config ARM64_PAGE_SHIFT
+	int
+	default 16 if ARM64_64K_PAGES
+	default 14 if ARM64_16K_PAGES
+	default 12
+
+config ARM64_CONT_SHIFT
+	int
+	default 5 if ARM64_64K_PAGES
+	default 7 if ARM64_16K_PAGES
+	default 4
+
 config ARCH_MMAP_RND_BITS_MIN
        default 14 if ARM64_64K_PAGES
        default 16 if ARM64_16K_PAGES
@@ -426,6 +438,15 @@ config CAVIUM_ERRATUM_22375
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_23144
+	bool "Cavium erratum 23144: ITS SYNC hang on dual socket system"
+	depends on NUMA
+	default y
+	help
+	  ITS SYNC command hang for cross node io and collections/cpu mapping.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_23154
 	bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed"
 	default y
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 710fde4ad0f0..0cc758cdd0dc 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -12,7 +12,8 @@ config ARM64_PTDUMP
 	  who are working in architecture specific areas of the kernel.
 	  It is probably not a good idea to enable this feature in a production
 	  kernel.
-	  If in doubt, say "N"
+
+	  If in doubt, say N.
 
 config PID_IN_CONTEXTIDR
 	bool "Write the current PID to the CONTEXTIDR register"
@@ -38,15 +39,15 @@ config ARM64_RANDOMIZE_TEXT_OFFSET
 	  value.
 
 config DEBUG_SET_MODULE_RONX
-        bool "Set loadable kernel module data as NX and text as RO"
-        depends on MODULES
-        help
-          This option helps catch unintended modifications to loadable
-          kernel module's text and read-only data. It also prevents execution
-          of module data. Such protection may interfere with run-time code
-          patching and dynamic kernel tracing - and they might also protect
-          against certain classes of kernel exploits.
-          If in doubt, say "N".
+	bool "Set loadable kernel module data as NX and text as RO"
+	depends on MODULES
+	default y
+	help
+	  Is this is set, kernel module text and rodata will be made read-only.
+	  This is to help catch accidental or malicious attempts to change the
+	  kernel's executable code.
+
+	  If in doubt, say Y.
 
 config DEBUG_RODATA
 	bool "Make kernel text and rodata read-only"
@@ -56,7 +57,7 @@ config DEBUG_RODATA
 	  is to help catch accidental or malicious attempts to change the
 	  kernel's executable code.
 
-	  If in doubt, say Y
+	  If in doubt, say Y.
 
 config DEBUG_ALIGN_RODATA
 	depends on DEBUG_RODATA
@@ -69,7 +70,7 @@ config DEBUG_ALIGN_RODATA
 	  alignment and potentially wasted space. Turn on this option if
 	  performance is more important than memory pressure.
 
-	  If in doubt, say N
+	  If in doubt, say N.
 
 source "drivers/hwtracing/coresight/Kconfig"
 
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 354d75402ace..648a32c89541 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -60,7 +60,9 @@ head-y		:= arch/arm64/kernel/head.o
 
 # The byte offset of the kernel image in RAM from the start of RAM.
 ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y)
-TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%03x000\n", int(512 * rand())}')
+TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \
+		 int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \
+		 rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}")
 else
 TEXT_OFFSET := 0x00080000
 endif
@@ -93,7 +95,7 @@ boot := arch/arm64/boot
 Image: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
-Image.%: vmlinux
+Image.%: Image
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 zinstall install:
diff --git a/arch/arm64/boot/dts/broadcom/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
index 54ca40c9f711..ea5603fd106a 100644
--- a/arch/arm64/boot/dts/broadcom/ns2-svk.dts
+++ b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
@@ -52,6 +52,14 @@
 	};
 };
 
+&pci_phy0 {
+	status = "ok";
+};
+
+&pci_phy1 {
+	status = "ok";
+};
+
 &pcie0 {
 	status = "ok";
 };
@@ -132,3 +140,11 @@
 		#size-cells = <1>;
 	};
 };
+
+&mdio_mux_iproc {
+	mdio@10 {
+		gphy0: eth-phy@10 {
+			reg = <0x10>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index ec68ec1a80c8..46b78fa89f4c 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -263,6 +263,45 @@
 				      IRQ_TYPE_LEVEL_HIGH)>;
 		};
 
+		mdio_mux_iproc: mdio-mux@6602023c {
+			compatible = "brcm,mdio-mux-iproc";
+			reg = <0x6602023c 0x14>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			mdio@0 {
+				reg = <0x0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				pci_phy0: pci-phy@0 {
+					compatible = "brcm,ns2-pcie-phy";
+					reg = <0x0>;
+					#phy-cells = <0>;
+					status = "disabled";
+				};
+			};
+
+			mdio@7 {
+				reg = <0x7>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				pci_phy1: pci-phy@0 {
+					compatible = "brcm,ns2-pcie-phy";
+					reg = <0x0>;
+					#phy-cells = <0>;
+					status = "disabled";
+				};
+			};
+
+			mdio@10 {
+				reg = <0x10>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
 		timer0: timer@66030000 {
 			compatible = "arm,sp804", "arm,primecell";
 			reg = <0x66030000 0x1000>;
diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi
index 3a4e9a2ab313..fbafa24cd533 100644
--- a/arch/arm64/boot/dts/lg/lg1312.dtsi
+++ b/arch/arm64/boot/dts/lg/lg1312.dtsi
@@ -125,7 +125,7 @@
 		#size-cells = <1>;
 		#interrupts-cells = <3>;
 
-		compatible = "arm,amba-bus";
+		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
 		ranges;
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 46f325a143b0..d7f8e06910bc 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -163,7 +163,7 @@
 	};
 
 	amba {
-		compatible = "arm,amba-bus";
+		compatible = "simple-bus";
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 7a09c48c0475..579b6e654f2d 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -160,14 +160,14 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define STACK_RND_MASK			(0x3ffff >> (PAGE_SHIFT - 12))
 #endif
 
-#ifdef CONFIG_COMPAT
-
 #ifdef __AARCH64EB__
 #define COMPAT_ELF_PLATFORM		("v8b")
 #else
 #define COMPAT_ELF_PLATFORM		("v8l")
 #endif
 
+#ifdef CONFIG_COMPAT
+
 #define COMPAT_ELF_ET_DYN_BASE		(2 * TASK_SIZE_32 / 3)
 
 /* AArch32 registers. */
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
index f69f69c8120c..da84645525b9 100644
--- a/arch/arm64/include/asm/kgdb.h
+++ b/arch/arm64/include/asm/kgdb.h
@@ -38,25 +38,54 @@ extern int kgdb_fault_expected;
 #endif /* !__ASSEMBLY__ */
 
 /*
- * gdb is expecting the following registers layout.
+ * gdb remote procotol (well most versions of it) expects the following
+ * register layout.
  *
  * General purpose regs:
  *     r0-r30: 64 bit
  *     sp,pc : 64 bit
- *     pstate  : 64 bit
- *     Total: 34
+ *     pstate  : 32 bit
+ *     Total: 33 + 1
  * FPU regs:
  *     f0-f31: 128 bit
- *     Total: 32
- * Extra regs
  *     fpsr & fpcr: 32 bit
- *     Total: 2
+ *     Total: 32 + 2
  *
+ * To expand a little on the "most versions of it"... when the gdb remote
+ * protocol for AArch64 was developed it depended on a statement in the
+ * Architecture Reference Manual that claimed "SPSR_ELx is a 32-bit register".
+ * and, as a result, allocated only 32-bits for the PSTATE in the remote
+ * protocol. In fact this statement is still present in ARM DDI 0487A.i.
+ *
+ * Unfortunately "is a 32-bit register" has a very special meaning for
+ * system registers. It means that "the upper bits, bits[63:32], are
+ * RES0.". RES0 is heavily used in the ARM architecture documents as a
+ * way to leave space for future architecture changes. So to translate a
+ * little for people who don't spend their spare time reading ARM architecture
+ * manuals, what "is a 32-bit register" actually means in this context is
+ * "is a 64-bit register but one with no meaning allocated to any of the
+ * upper 32-bits... *yet*".
+ *
+ * Perhaps then we should not be surprised that this has led to some
+ * confusion. Specifically a patch, influenced by the above translation,
+ * that extended PSTATE to 64-bit was accepted into gdb-7.7 but the patch
+ * was reverted in gdb-7.8.1 and all later releases, when this was
+ * discovered to be an undocumented protocol change.
+ *
+ * So... it is *not* wrong for us to only allocate 32-bits to PSTATE
+ * here even though the kernel itself allocates 64-bits for the same
+ * state. That is because this bit of code tells the kernel how the gdb
+ * remote protocol (well most versions of it) describes the register state.
+ *
+ * Note that if you are using one of the versions of gdb that supports
+ * the gdb-7.7 version of the protocol you cannot use kgdb directly
+ * without providing a custom register description (gdb can load new
+ * protocol descriptions at runtime).
  */
 
-#define _GP_REGS		34
+#define _GP_REGS		33
 #define _FP_REGS		32
-#define _EXTRA_REGS		2
+#define _EXTRA_REGS		3
 /*
  * general purpose registers size in bytes.
  * pstate is only 4 bytes. subtract 4 bytes
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 72a3025bb583..31b73227b41f 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -55,8 +55,9 @@
 #define VMEMMAP_SIZE (UL(1) << (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT))
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image (top
+ * PAGE_OFFSET - the virtual address of the start of the linear map (top
  *		 (VA_BITS - 1))
+ * KIMAGE_VADDR - the virtual address of the start of the kernel image
  * VA_BITS - the maximum number of bits for virtual addresses.
  * VA_START - the first kernel virtual address.
  * TASK_SIZE - the maximum size of a user space task.
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 17b45f7d96d3..8472c6def5ef 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -23,16 +23,8 @@
 
 /* PAGE_SHIFT determines the page size */
 /* CONT_SHIFT determines the number of pages which can be tracked together  */
-#ifdef CONFIG_ARM64_64K_PAGES
-#define PAGE_SHIFT		16
-#define CONT_SHIFT		5
-#elif defined(CONFIG_ARM64_16K_PAGES)
-#define PAGE_SHIFT		14
-#define CONT_SHIFT		7
-#else
-#define PAGE_SHIFT		12
-#define CONT_SHIFT		4
-#endif
+#define PAGE_SHIFT		CONFIG_ARM64_PAGE_SHIFT
+#define CONT_SHIFT		CONFIG_ARM64_CONT_SHIFT
 #define PAGE_SIZE		(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK		(~(PAGE_SIZE-1))
 
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index ff98585d085a..d25f4f137c2a 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
 
 #define check_pgt_cache()		do { } while (0)
 
-#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 #define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
 
 #if CONFIG_PGTABLE_LEVELS > 2
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 433e50405274..022644704a93 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -124,6 +124,18 @@ static inline void cpu_panic_kernel(void)
 	cpu_park_loop();
 }
 
+/*
+ * If a secondary CPU enters the kernel but fails to come online,
+ * (e.g. due to mismatched features), and cannot exit the kernel,
+ * we increment cpus_stuck_in_kernel and leave the CPU in a
+ * quiesecent loop within the kernel text. The memory containing
+ * this loop must not be re-used for anything else as the 'stuck'
+ * core is executing it.
+ *
+ * This function is used to inhibit features like kexec and hibernate.
+ */
+bool cpus_are_stuck_in_kernel(void);
+
 #endif /* ifndef __ASSEMBLY__ */
 
 #endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index fc9682bfe002..e875a5a551d7 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -30,22 +30,53 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
 	unsigned int tmp;
 	arch_spinlock_t lockval;
+	u32 owner;
+
+	/*
+	 * Ensure prior spin_lock operations to other locks have completed
+	 * on this CPU before we test whether "lock" is locked.
+	 */
+	smp_mb();
+	owner = READ_ONCE(lock->owner) << 16;
 
 	asm volatile(
 "	sevl\n"
 "1:	wfe\n"
 "2:	ldaxr	%w0, %2\n"
+	/* Is the lock free? */
 "	eor	%w1, %w0, %w0, ror #16\n"
-"	cbnz	%w1, 1b\n"
+"	cbz	%w1, 3f\n"
+	/* Lock taken -- has there been a subsequent unlock->lock transition? */
+"	eor	%w1, %w3, %w0, lsl #16\n"
+"	cbz	%w1, 1b\n"
+	/*
+	 * The owner has been updated, so there was an unlock->lock
+	 * transition that we missed. That means we can rely on the
+	 * store-release of the unlock operation paired with the
+	 * load-acquire of the lock operation to publish any of our
+	 * previous stores to the new lock owner and therefore don't
+	 * need to bother with the writeback below.
+	 */
+"	b	4f\n"
+"3:\n"
+	/*
+	 * Serialise against any concurrent lockers by writing back the
+	 * unlocked lock value
+	 */
 	ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
 "	stxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 2b\n", /* Serialise against any concurrent lockers */
-	/* LSE atomics */
 "	nop\n"
-"	nop\n")
+"	nop\n",
+	/* LSE atomics */
+"	mov	%w1, %w0\n"
+"	cas	%w0, %w0, %2\n"
+"	eor	%w1, %w1, %w0\n")
+	/* Somebody else wrote to the lock, GOTO 10 and reload the value */
+"	cbnz	%w1, 2b\n"
+"4:"
 	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
-	:
+	: "r" (owner)
 	: "memory");
 }
 
@@ -148,6 +179,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
+	smp_mb(); /* See arch_spin_unlock_wait */
 	return !arch_spin_value_unlocked(READ_ONCE(*lock));
 }
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 0685d74572af..9e397a542756 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -81,19 +81,6 @@ static inline void set_fs(mm_segment_t fs)
 #define segment_eq(a, b)	((a) == (b))
 
 /*
- * Return 1 if addr < current->addr_limit, 0 otherwise.
- */
-#define __addr_ok(addr)							\
-({									\
-	unsigned long flag;						\
-	asm("cmp %1, %0; cset %0, lo"					\
-		: "=&r" (flag)						\
-		: "r" (addr), "0" (current_thread_info()->addr_limit)	\
-		: "cc");						\
-	flag;								\
-})
-
-/*
  * Test whether a block of memory is a valid user space address.
  * Returns 1 if the range is valid, 0 otherwise.
  *
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 41e58fe3c041..e78ac26324bd 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
 #define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
 
-#define __NR_compat_syscalls		390
+#define __NR_compat_syscalls		394
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 5b925b761a2a..b7e8ef16ff0d 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -801,6 +801,14 @@ __SYSCALL(__NR_execveat, compat_sys_execveat)
 __SYSCALL(__NR_userfaultfd, sys_userfaultfd)
 #define __NR_membarrier 389
 __SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 390
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 391
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 392
+__SYSCALL(__NR_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 393
+__SYSCALL(__NR_pwritev2, compat_sys_pwritev2)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 3808470486f3..c173d329397f 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -22,6 +22,8 @@
 
 #include <linux/bitops.h>
 #include <linux/bug.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/personality.h>
@@ -104,6 +106,7 @@ static const char *const compat_hwcap2_str[] = {
 static int c_show(struct seq_file *m, void *v)
 {
 	int i, j;
+	bool compat = personality(current->personality) == PER_LINUX32;
 
 	for_each_online_cpu(i) {
 		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
@@ -115,6 +118,9 @@ static int c_show(struct seq_file *m, void *v)
 		 * "processor".  Give glibc what it expects.
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
+		if (compat)
+			seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
+				   MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);
 
 		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
 			   loops_per_jiffy / (500000UL/HZ),
@@ -127,7 +133,7 @@ static int c_show(struct seq_file *m, void *v)
 		 * software which does already (at least for 32-bit).
 		 */
 		seq_puts(m, "Features\t:");
-		if (personality(current->personality) == PER_LINUX32) {
+		if (compat) {
 #ifdef CONFIG_COMPAT
 			for (j = 0; compat_hwcap_str[j]; j++)
 				if (compat_elf_hwcap & (1 << j))
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index f8df75d740f4..21ab5df9fa76 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -33,6 +33,7 @@
 #include <asm/pgtable.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/sections.h>
+#include <asm/smp.h>
 #include <asm/suspend.h>
 #include <asm/virt.h>
 
@@ -236,6 +237,11 @@ int swsusp_arch_suspend(void)
 	unsigned long flags;
 	struct sleep_stack_data state;
 
+	if (cpus_are_stuck_in_kernel()) {
+		pr_err("Can't hibernate: no mechanism to offline secondary CPUs.\n");
+		return -EBUSY;
+	}
+
 	local_dbg_save(flags);
 
 	if (__cpu_suspend_enter(&state)) {
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index b67531a13136..b5f063e5eff7 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -58,7 +58,17 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
 	{ "x30", 8, offsetof(struct pt_regs, regs[30])},
 	{ "sp", 8, offsetof(struct pt_regs, sp)},
 	{ "pc", 8, offsetof(struct pt_regs, pc)},
-	{ "pstate", 8, offsetof(struct pt_regs, pstate)},
+	/*
+	 * struct pt_regs thinks PSTATE is 64-bits wide but gdb remote
+	 * protocol disagrees. Therefore we must extract only the lower
+	 * 32-bits. Look for the big comment in asm/kgdb.h for more
+	 * detail.
+	 */
+	{ "pstate", 4, offsetof(struct pt_regs, pstate)
+#ifdef CONFIG_CPU_BIG_ENDIAN
+							+ 4
+#endif
+	},
 	{ "v0", 16, -1 },
 	{ "v1", 16, -1 },
 	{ "v2", 16, -1 },
@@ -128,6 +138,8 @@ sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
 	memset((char *)gdb_regs, 0, NUMREGBYTES);
 	thread_regs = task_pt_regs(task);
 	memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES);
+	/* Special case for PSTATE (check comments in asm/kgdb.h for details) */
+	dbg_get_reg(33, gdb_regs + GP_REG_BYTES, thread_regs);
 }
 
 void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 678e0842cb3b..62ff3c0622e2 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -909,3 +909,21 @@ int setup_profiling_timer(unsigned int multiplier)
 {
 	return -EINVAL;
 }
+
+static bool have_cpu_die(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	int any_cpu = raw_smp_processor_id();
+
+	if (cpu_ops[any_cpu]->cpu_die)
+		return true;
+#endif
+	return false;
+}
+
+bool cpus_are_stuck_in_kernel(void)
+{
+	bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
+
+	return !!cpus_stuck_in_kernel || smp_spin_tables;
+}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c5392081b49b..2a43012616b7 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -64,8 +64,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
 
 	/*
 	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.  Note that we now dump the
-	 * code first, just in case the backtrace kills us.
+	 * to safely read from kernel space.
 	 */
 	fs = get_fs();
 	set_fs(KERNEL_DS);
@@ -111,21 +110,12 @@ static void dump_backtrace_entry(unsigned long where)
 	print_ip_sym(where);
 }
 
-static void dump_instr(const char *lvl, struct pt_regs *regs)
+static void __dump_instr(const char *lvl, struct pt_regs *regs)
 {
 	unsigned long addr = instruction_pointer(regs);
-	mm_segment_t fs;
 	char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
 	int i;
 
-	/*
-	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.  Note that we now dump the
-	 * code first, just in case the backtrace kills us.
-	 */
-	fs = get_fs();
-	set_fs(KERNEL_DS);
-
 	for (i = -4; i < 1; i++) {
 		unsigned int val, bad;
 
@@ -139,8 +129,18 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 		}
 	}
 	printk("%sCode: %s\n", lvl, str);
+}
 
-	set_fs(fs);
+static void dump_instr(const char *lvl, struct pt_regs *regs)
+{
+	if (!user_mode(regs)) {
+		mm_segment_t fs = get_fs();
+		set_fs(KERNEL_DS);
+		__dump_instr(lvl, regs);
+		set_fs(fs);
+	} else {
+		__dump_instr(lvl, regs);
+	}
 }
 
 static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
@@ -477,8 +477,9 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 	void __user *pc = (void __user *)instruction_pointer(regs);
 	console_verbose();
 
-	pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n",
-		handler[reason], esr, esr_get_class_string(esr));
+	pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n",
+		handler[reason], smp_processor_id(), esr,
+		esr_get_class_string(esr));
 	__show_regs(regs);
 
 	info.si_signo = SIGILL;
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index fff7cd42b3a3..5f8f80b4a224 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -169,7 +169,8 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 	 * Make sure stores to the GIC via the memory mapped interface
 	 * are now visible to the system register interface.
 	 */
-	dsb(st);
+	if (!cpu_if->vgic_sre)
+		dsb(st);
 
 	cpu_if->vgic_vmcr  = read_gicreg(ICH_VMCR_EL2);
 
@@ -190,12 +191,11 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 			if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
 				continue;
 
-			if (cpu_if->vgic_elrsr & (1 << i)) {
+			if (cpu_if->vgic_elrsr & (1 << i))
 				cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
-				continue;
-			}
+			else
+				cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
 
-			cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
 			__gic_v3_set_lr(0, i);
 		}
 
@@ -236,8 +236,12 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 
 	val = read_gicreg(ICC_SRE_EL2);
 	write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2);
-	isb(); /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
-	write_gicreg(1, ICC_SRE_EL1);
+
+	if (!cpu_if->vgic_sre) {
+		/* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
+		isb();
+		write_gicreg(1, ICC_SRE_EL1);
+	}
 }
 
 void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
@@ -256,8 +260,10 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	 * been actually programmed with the value we want before
 	 * starting to mess with the rest of the GIC.
 	 */
-	write_gicreg(cpu_if->vgic_sre, ICC_SRE_EL1);
-	isb();
+	if (!cpu_if->vgic_sre) {
+		write_gicreg(0, ICC_SRE_EL1);
+		isb();
+	}
 
 	val = read_gicreg(ICH_VTR_EL2);
 	max_lr_idx = vtr_to_max_lr_idx(val);
@@ -306,18 +312,18 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	 * (re)distributors. This ensure the guest will read the
 	 * correct values from the memory-mapped interface.
 	 */
-	isb();
-	dsb(sy);
+	if (!cpu_if->vgic_sre) {
+		isb();
+		dsb(sy);
+	}
 	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
 
 	/*
 	 * Prevent the guest from touching the GIC system registers if
 	 * SRE isn't enabled for GICv3 emulation.
 	 */
-	if (!cpu_if->vgic_sre) {
-		write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
-			     ICC_SRE_EL2);
-	}
+	write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
+		     ICC_SRE_EL2);
 }
 
 void __hyp_text __vgic_v3_init_lrs(void)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 7bbe3ff02602..a57d650f552c 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -134,6 +134,17 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_gic_sre(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre;
+	return true;
+}
+
 static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
@@ -958,7 +969,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  access_gic_sgi },
 	/* ICC_SRE_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101),
-	  trap_raz_wi },
+	  access_gic_sre },
 
 	/* CONTEXTIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index b7b397802088..efcf1f7ef1e4 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -179,7 +179,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 						 &asid_generation);
 	flush_context(cpu);
 
-	/* We have at least 1 ASID per CPU, so this will always succeed */
+	/* We have more ASIDs than CPUs, so this will always succeed */
 	asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 
 set_asid:
@@ -227,8 +227,11 @@ switch_mm_fastpath:
 static int asids_init(void)
 {
 	asid_bits = get_cpu_asid_bits();
-	/* If we end up with more CPUs than ASIDs, expect things to crash */
-	WARN_ON(NUM_USER_ASIDS < num_possible_cpus());
+	/*
+	 * Expect allocation after rollover to fail if we don't have at least
+	 * one more ASID than CPUs. ASID #0 is reserved for init_mm.
+	 */
+	WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus());
 	atomic64_set(&asid_generation, ASID_FIRST_VERSION);
 	asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map),
 			   GFP_KERNEL);
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 8404190fe2bd..ccfde237d6e6 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -150,6 +150,7 @@ static const struct prot_bits pte_bits[] = {
 
 struct pg_level {
 	const struct prot_bits *bits;
+	const char *name;
 	size_t num;
 	u64 mask;
 };
@@ -157,15 +158,19 @@ struct pg_level {
 static struct pg_level pg_level[] = {
 	{
 	}, { /* pgd */
+		.name	= "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pud */
+		.name	= (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pmd */
+		.name	= (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pte */
+		.name	= "PTE",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	},
@@ -214,7 +219,8 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 				delta >>= 10;
 				unit++;
 			}
-			seq_printf(st->seq, "%9lu%c", delta, *unit);
+			seq_printf(st->seq, "%9lu%c %s", delta, *unit,
+				   pg_level[st->level].name);
 			if (pg_level[st->level].bits)
 				dump_prot(st, pg_level[st->level].bits,
 					  pg_level[st->level].num);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 5954881a35ac..013e2cbe7924 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -109,7 +109,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	 * PTE_RDONLY is cleared by default in the asm below, so set it in
 	 * back if necessary (read-only or clean PTE).
 	 */
-	if (!pte_write(entry) || !dirty)
+	if (!pte_write(entry) || !pte_sw_dirty(entry))
 		pte_val(entry) |= PTE_RDONLY;
 
 	/*
@@ -441,7 +441,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 	return 1;
 }
 
-static struct fault_info {
+static const struct fault_info {
 	int	(*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
 	int	sig;
 	int	code;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index dbd12ea8ce68..43a76b07eb32 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -71,10 +71,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
 {
 	struct page *page = pte_page(pte);
 
-	/* no flushing needed for anonymous pages */
-	if (!page_mapping(page))
-		return;
-
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		sync_icache_aliases(page_address(page),
 				    PAGE_SIZE << compound_order(page));
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index aa8aee7d6929..2e49bd252fe7 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -306,6 +306,10 @@ static __init int setup_hugepagesz(char *opt)
 		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
 	} else if (ps == PUD_SIZE) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	} else if (ps == (PAGE_SIZE * CONT_PTES)) {
+		hugetlb_add_hstate(CONT_PTE_SHIFT);
+	} else if (ps == (PMD_SIZE * CONT_PMDS)) {
+		hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
 	} else {
 		hugetlb_bad_size();
 		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
@@ -314,3 +318,13 @@ static __init int setup_hugepagesz(char *opt)
 	return 1;
 }
 __setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+		hugetlb_add_hstate(CONT_PMD_SHIFT);
+	return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index aee5637ea436..7c16e547ccb2 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -1,7 +1,7 @@
 /*
  * BPF JIT compiler for ARM64
  *
- * Copyright (C) 2014-2015 Zi Shen Lim <[email protected]>
+ * Copyright (C) 2014-2016 Zi Shen Lim <[email protected]>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -55,6 +55,7 @@
 #define A64_BL(imm26) A64_BRANCH((imm26) << 2, LINK)
 
 /* Unconditional branch (register) */
+#define A64_BR(Rn)  aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_NOLINK)
 #define A64_BLR(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_LINK)
 #define A64_RET(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_RETURN)
 
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 49ba37e4bfc0..b2fc97a2c56c 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -18,6 +18,7 @@
 
 #define pr_fmt(fmt) "bpf_jit: " fmt
 
+#include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/printk.h>
 #include <linux/skbuff.h>
@@ -33,6 +34,7 @@ int bpf_jit_enable __read_mostly;
 
 #define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
 #define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
+#define TCALL_CNT (MAX_BPF_JIT_REG + 2)
 
 /* Map BPF registers to A64 registers */
 static const int bpf2a64[] = {
@@ -54,6 +56,8 @@ static const int bpf2a64[] = {
 	/* temporary registers for internal BPF JIT */
 	[TMP_REG_1] = A64_R(10),
 	[TMP_REG_2] = A64_R(11),
+	/* tail_call_cnt */
+	[TCALL_CNT] = A64_R(26),
 	/* temporary register for blinding constants */
 	[BPF_REG_AX] = A64_R(9),
 };
@@ -146,13 +150,18 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 
 #define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
 
-static void build_prologue(struct jit_ctx *ctx)
+#define PROLOGUE_OFFSET 8
+
+static int build_prologue(struct jit_ctx *ctx)
 {
 	const u8 r6 = bpf2a64[BPF_REG_6];
 	const u8 r7 = bpf2a64[BPF_REG_7];
 	const u8 r8 = bpf2a64[BPF_REG_8];
 	const u8 r9 = bpf2a64[BPF_REG_9];
 	const u8 fp = bpf2a64[BPF_REG_FP];
+	const u8 tcc = bpf2a64[TCALL_CNT];
+	const int idx0 = ctx->idx;
+	int cur_offset;
 
 	/*
 	 * BPF prog stack layout
@@ -162,8 +171,6 @@ static void build_prologue(struct jit_ctx *ctx)
 	 *                        |FP/LR|
 	 * current A64_FP =>  -16:+-----+
 	 *                        | ... | callee saved registers
-	 *                        +-----+
-	 *                        |     | x25/x26
 	 * BPF fp register => -64:+-----+ <= (BPF_FP)
 	 *                        |     |
 	 *                        | ... | BPF prog stack
@@ -183,18 +190,90 @@ static void build_prologue(struct jit_ctx *ctx)
 	emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
 	emit(A64_MOV(1, A64_FP, A64_SP), ctx);
 
-	/* Save callee-saved register */
+	/* Save callee-saved registers */
 	emit(A64_PUSH(r6, r7, A64_SP), ctx);
 	emit(A64_PUSH(r8, r9, A64_SP), ctx);
+	emit(A64_PUSH(fp, tcc, A64_SP), ctx);
 
-	/* Save fp (x25) and x26. SP requires 16 bytes alignment */
-	emit(A64_PUSH(fp, A64_R(26), A64_SP), ctx);
-
-	/* Set up BPF prog stack base register (x25) */
+	/* Set up BPF prog stack base register */
 	emit(A64_MOV(1, fp, A64_SP), ctx);
 
+	/* Initialize tail_call_cnt */
+	emit(A64_MOVZ(1, tcc, 0, 0), ctx);
+
 	/* Set up function call stack */
 	emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
+
+	cur_offset = ctx->idx - idx0;
+	if (cur_offset != PROLOGUE_OFFSET) {
+		pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
+			    cur_offset, PROLOGUE_OFFSET);
+		return -1;
+	}
+	return 0;
+}
+
+static int out_offset = -1; /* initialized on the first pass of build_body() */
+static int emit_bpf_tail_call(struct jit_ctx *ctx)
+{
+	/* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */
+	const u8 r2 = bpf2a64[BPF_REG_2];
+	const u8 r3 = bpf2a64[BPF_REG_3];
+
+	const u8 tmp = bpf2a64[TMP_REG_1];
+	const u8 prg = bpf2a64[TMP_REG_2];
+	const u8 tcc = bpf2a64[TCALL_CNT];
+	const int idx0 = ctx->idx;
+#define cur_offset (ctx->idx - idx0)
+#define jmp_offset (out_offset - (cur_offset))
+	size_t off;
+
+	/* if (index >= array->map.max_entries)
+	 *     goto out;
+	 */
+	off = offsetof(struct bpf_array, map.max_entries);
+	emit_a64_mov_i64(tmp, off, ctx);
+	emit(A64_LDR32(tmp, r2, tmp), ctx);
+	emit(A64_CMP(0, r3, tmp), ctx);
+	emit(A64_B_(A64_COND_GE, jmp_offset), ctx);
+
+	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+	 *     goto out;
+	 * tail_call_cnt++;
+	 */
+	emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx);
+	emit(A64_CMP(1, tcc, tmp), ctx);
+	emit(A64_B_(A64_COND_GT, jmp_offset), ctx);
+	emit(A64_ADD_I(1, tcc, tcc, 1), ctx);
+
+	/* prog = array->ptrs[index];
+	 * if (prog == NULL)
+	 *     goto out;
+	 */
+	off = offsetof(struct bpf_array, ptrs);
+	emit_a64_mov_i64(tmp, off, ctx);
+	emit(A64_LDR64(tmp, r2, tmp), ctx);
+	emit(A64_LDR64(prg, tmp, r3), ctx);
+	emit(A64_CBZ(1, prg, jmp_offset), ctx);
+
+	/* goto *(prog->bpf_func + prologue_size); */
+	off = offsetof(struct bpf_prog, bpf_func);
+	emit_a64_mov_i64(tmp, off, ctx);
+	emit(A64_LDR64(tmp, prg, tmp), ctx);
+	emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx);
+	emit(A64_BR(tmp), ctx);
+
+	/* out: */
+	if (out_offset == -1)
+		out_offset = cur_offset;
+	if (cur_offset != out_offset) {
+		pr_err_once("tail_call out_offset = %d, expected %d!\n",
+			    cur_offset, out_offset);
+		return -1;
+	}
+	return 0;
+#undef cur_offset
+#undef jmp_offset
 }
 
 static void build_epilogue(struct jit_ctx *ctx)
@@ -499,13 +578,15 @@ emit_cond_jmp:
 		const u64 func = (u64)__bpf_call_base + imm;
 
 		emit_a64_mov_i64(tmp, func, ctx);
-		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
-		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
-		emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
 		break;
 	}
+	/* tail call */
+	case BPF_JMP | BPF_CALL | BPF_X:
+		if (emit_bpf_tail_call(ctx))
+			return -EFAULT;
+		break;
 	/* function return */
 	case BPF_JMP | BPF_EXIT:
 		/* Optimization: when last instruction is EXIT,
@@ -650,11 +731,8 @@ emit_cond_jmp:
 		emit_a64_mov_i64(r3, size, ctx);
 		emit(A64_SUB_I(1, r4, fp, STACK_SIZE), ctx);
 		emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
-		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
-		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
 		emit(A64_BLR(r5), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
-		emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
 
 		jmp_offset = epilogue_offset(ctx);
 		check_imm19(jmp_offset);
@@ -780,7 +858,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		goto out_off;
 	}
 
-	build_prologue(&ctx);
+	if (build_prologue(&ctx)) {
+		prog = orig_prog;
+		goto out_off;
+	}
 
 	ctx.epilogue_offset = ctx.idx;
 	build_epilogue(&ctx);
diff --git a/arch/avr32/include/asm/pgalloc.h b/arch/avr32/include/asm/pgalloc.h
index 1aba19d68c5e..db039cb368be 100644
--- a/arch/avr32/include/asm/pgalloc.h
+++ b/arch/avr32/include/asm/pgalloc.h
@@ -43,7 +43,7 @@ static inline void pgd_ctor(void *x)
  */
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return quicklist_alloc(QUICK_PGD, GFP_KERNEL | __GFP_REPEAT, pgd_ctor);
+	return quicklist_alloc(QUICK_PGD, GFP_KERNEL, pgd_ctor);
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
@@ -54,7 +54,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+	return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -63,7 +63,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	struct page *page;
 	void *pg;
 
-	pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+	pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
 	if (!pg)
 		return NULL;
 
diff --git a/arch/cris/include/asm/pgalloc.h b/arch/cris/include/asm/pgalloc.h
index 235ece437ddd..42f1affb9c2d 100644
--- a/arch/cris/include/asm/pgalloc.h
+++ b/arch/cris/include/asm/pgalloc.h
@@ -24,14 +24,14 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-  	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
  	return pte;
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	struct page *pte;
-	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+	pte = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0);
 	if (!pte)
 		return NULL;
 	if (!pgtable_page_ctor(pte)) {
diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c
index 41907d25ed38..c9ed14f6c67d 100644
--- a/arch/frv/mm/pgalloc.c
+++ b/arch/frv/mm/pgalloc.c
@@ -22,7 +22,7 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((aligned(PAGE_SIZE)));
 
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL);
 	if (pte)
 		clear_page(pte);
 	return pte;
@@ -33,9 +33,9 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	struct page *page;
 
 #ifdef CONFIG_HIGHPTE
-	page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0);
+	page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0);
 #else
-	page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+	page = alloc_pages(GFP_KERNEL, 0);
 #endif
 	if (!page)
 		return NULL;
diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h
index 77da3b0ae3c2..eeebf862c46c 100644
--- a/arch/hexagon/include/asm/pgalloc.h
+++ b/arch/hexagon/include/asm/pgalloc.h
@@ -64,7 +64,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 {
 	struct page *pte;
 
-	pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+	pte = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (!pte)
 		return NULL;
 	if (!pgtable_page_ctor(pte)) {
@@ -78,7 +78,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	gfp_t flags =  GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO;
+	gfp_t flags =  GFP_KERNEL | __GFP_ZERO;
 	return (pte_t *) __get_free_page(flags);
 }
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index f80758cb7157..e109ee95e919 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -45,7 +45,7 @@ config IA64
 	select GENERIC_SMP_IDLE_THREAD
 	select ARCH_INIT_TASK
 	select ARCH_TASK_STRUCT_ALLOCATOR
-	select ARCH_THREAD_INFO_ALLOCATOR
+	select ARCH_THREAD_STACK_ALLOCATOR
 	select ARCH_CLOCKSOURCE_DATA
 	select GENERIC_TIME_VSYSCALL_OLD
 	select SYSCTL_ARCH_UNALIGN_NO_WARN
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index aa995b67c3f5..d1212b84fb83 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -48,15 +48,15 @@ struct thread_info {
 #ifndef ASM_OFFSETS_C
 /* how to get the thread information struct from C */
 #define current_thread_info()	((struct thread_info *) ((char *) current + IA64_TASK_SIZE))
-#define alloc_thread_info_node(tsk, node)	\
-		((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE))
+#define alloc_thread_stack_node(tsk, node)	\
+		((unsigned long *) ((char *) (tsk) + IA64_TASK_SIZE))
 #define task_thread_info(tsk)	((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE))
 #else
 #define current_thread_info()	((struct thread_info *) 0)
-#define alloc_thread_info_node(tsk, node)	((struct thread_info *) 0)
+#define alloc_thread_stack_node(tsk, node)	((unsigned long *) 0)
 #define task_thread_info(tsk)	((struct thread_info *) 0)
 #endif
-#define free_thread_info(ti)	/* nothing */
+#define free_thread_stack(ti)	/* nothing */
 #define task_stack_page(tsk)	((void *)(tsk))
 
 #define __HAVE_THREAD_FUNCTIONS
diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c
index f9efe9739d3f..0eaa89f3defd 100644
--- a/arch/ia64/kernel/init_task.c
+++ b/arch/ia64/kernel/init_task.c
@@ -26,6 +26,7 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
  * handled. This is done by having a special ".data..init_task" section...
  */
 #define init_thread_info	init_task_mem.s.thread_info
+#define init_stack		init_task_mem.stack
 
 union {
 	struct {
diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h
index f9924fbcfe42..fb95aed5f428 100644
--- a/arch/m68k/include/asm/mcf_pgalloc.h
+++ b/arch/m68k/include/asm/mcf_pgalloc.h
@@ -14,7 +14,7 @@ extern const char bad_pmd_string[];
 extern inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 	unsigned long address)
 {
-	unsigned long page = __get_free_page(GFP_DMA|__GFP_REPEAT);
+	unsigned long page = __get_free_page(GFP_DMA);
 
 	if (!page)
 		return NULL;
@@ -51,7 +51,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page,
 static inline struct page *pte_alloc_one(struct mm_struct *mm,
 	unsigned long address)
 {
-	struct page *page = alloc_pages(GFP_DMA|__GFP_REPEAT, 0);
+	struct page *page = alloc_pages(GFP_DMA, 0);
 	pte_t *pte;
 
 	if (!page)
diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h
index 24bcba496c75..c895b987202c 100644
--- a/arch/m68k/include/asm/motorola_pgalloc.h
+++ b/arch/m68k/include/asm/motorola_pgalloc.h
@@ -11,7 +11,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long ad
 {
 	pte_t *pte;
 
-	pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	if (pte) {
 		__flush_page_to_ram(pte);
 		flush_tlb_kernel_page(pte);
@@ -32,7 +32,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addres
 	struct page *page;
 	pte_t *pte;
 
-	page = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+	page = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0);
 	if(!page)
 		return NULL;
 	if (!pgtable_page_ctor(page)) {
diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h
index 0931388de47f..1901f61f926f 100644
--- a/arch/m68k/include/asm/sun3_pgalloc.h
+++ b/arch/m68k/include/asm/sun3_pgalloc.h
@@ -37,7 +37,7 @@ do {							\
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	unsigned long page = __get_free_page(GFP_KERNEL|__GFP_REPEAT);
+	unsigned long page = __get_free_page(GFP_KERNEL);
 
 	if (!page)
 		return NULL;
@@ -49,7 +49,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 					unsigned long address)
 {
-        struct page *page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+        struct page *page = alloc_pages(GFP_KERNEL, 0);
 
 	if (page == NULL)
 		return NULL;
diff --git a/arch/metag/include/asm/pgalloc.h b/arch/metag/include/asm/pgalloc.h
index 3104df0a4822..c2caa1ee4360 100644
--- a/arch/metag/include/asm/pgalloc.h
+++ b/arch/metag/include/asm/pgalloc.h
@@ -42,8 +42,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT |
-					      __GFP_ZERO);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 	return pte;
 }
 
@@ -51,7 +50,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 				      unsigned long address)
 {
 	struct page *pte;
-	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
+	pte = alloc_pages(GFP_KERNEL  | __GFP_ZERO, 0);
 	if (!pte)
 		return NULL;
 	if (!pgtable_page_ctor(pte)) {
diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h
index 61436d69775c..7c89390c0c13 100644
--- a/arch/microblaze/include/asm/pgalloc.h
+++ b/arch/microblaze/include/asm/pgalloc.h
@@ -116,9 +116,9 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 	struct page *ptepage;
 
 #ifdef CONFIG_HIGHPTE
-	int flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_REPEAT;
+	int flags = GFP_KERNEL | __GFP_HIGHMEM;
 #else
-	int flags = GFP_KERNEL | __GFP_REPEAT;
+	int flags = GFP_KERNEL;
 #endif
 
 	ptepage = alloc_pages(flags, 0);
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index 4f4520e779a5..eb99fcc76088 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -239,8 +239,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
 	pte_t *pte;
 	if (mem_init_done) {
-		pte = (pte_t *)__get_free_page(GFP_KERNEL |
-					__GFP_REPEAT | __GFP_ZERO);
+		pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 	} else {
 		pte = (pte_t *)early_get_page();
 		if (pte)
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 6733ac575da4..36a391d289aa 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -74,7 +74,7 @@
 #define KVM_GUEST_KUSEG			0x00000000UL
 #define KVM_GUEST_KSEG0			0x40000000UL
 #define KVM_GUEST_KSEG23		0x60000000UL
-#define KVM_GUEST_KSEGX(a)		((_ACAST32_(a)) & 0x60000000)
+#define KVM_GUEST_KSEGX(a)		((_ACAST32_(a)) & 0xe0000000)
 #define KVM_GUEST_CPHYSADDR(a)		((_ACAST32_(a)) & 0x1fffffff)
 
 #define KVM_GUEST_CKSEG0ADDR(a)		(KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG0)
@@ -338,6 +338,7 @@ struct kvm_mips_tlb {
 #define KVM_MIPS_GUEST_TLB_SIZE	64
 struct kvm_vcpu_arch {
 	void *host_ebase, *guest_ebase;
+	int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
 	unsigned long host_stack;
 	unsigned long host_gp;
 
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index b336037e8768..93c079a1cfc8 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -69,7 +69,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
 	pte_t *pte;
 
-	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, PTE_ORDER);
+	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
 
 	return pte;
 }
@@ -79,7 +79,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 {
 	struct page *pte;
 
-	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+	pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
 	if (!pte)
 		return NULL;
 	clear_highpage(pte);
@@ -113,7 +113,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	pmd_t *pmd;
 
-	pmd = (pmd_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT, PMD_ORDER);
+	pmd = (pmd_t *) __get_free_pages(GFP_KERNEL, PMD_ORDER);
 	if (pmd)
 		pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table);
 	return pmd;
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 396df6eb0a12..645c8a1982a7 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1636,6 +1636,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 		if (index < 0) {
 			vcpu->arch.host_cp0_entryhi = (va & VPN2_MASK);
 			vcpu->arch.host_cp0_badvaddr = va;
+			vcpu->arch.pc = curr_pc;
 			er = kvm_mips_emulate_tlbmiss_ld(cause, NULL, run,
 							 vcpu);
 			preempt_enable();
@@ -1647,6 +1648,8 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 			 * invalid exception to the guest
 			 */
 			if (!TLB_IS_VALID(*tlb, va)) {
+				vcpu->arch.host_cp0_badvaddr = va;
+				vcpu->arch.pc = curr_pc;
 				er = kvm_mips_emulate_tlbinv_ld(cause, NULL,
 								run, vcpu);
 				preempt_enable();
@@ -1666,7 +1669,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 			cache, op, base, arch->gprs[base], offset);
 		er = EMULATE_FAIL;
 		preempt_enable();
-		goto dont_update_pc;
+		goto done;
 
 	}
 
@@ -1694,16 +1697,20 @@ skip_fault:
 		kvm_err("NO-OP CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
 			cache, op, base, arch->gprs[base], offset);
 		er = EMULATE_FAIL;
-		preempt_enable();
-		goto dont_update_pc;
 	}
 
 	preempt_enable();
+done:
+	/* Rollback PC only if emulation was unsuccessful */
+	if (er == EMULATE_FAIL)
+		vcpu->arch.pc = curr_pc;
 
 dont_update_pc:
-	/* Rollback PC */
-	vcpu->arch.pc = curr_pc;
-done:
+	/*
+	 * This is for exceptions whose emulation updates the PC, so do not
+	 * overwrite the PC under any circumstances
+	 */
+
 	return er;
 }
 
diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h
index 4ab4bdfad703..2143884709e4 100644
--- a/arch/mips/kvm/interrupt.h
+++ b/arch/mips/kvm/interrupt.h
@@ -28,6 +28,7 @@
 #define MIPS_EXC_MAX                12
 /* XXXSL More to follow */
 
+extern char __kvm_mips_vcpu_run_end[];
 extern char mips32_exception[], mips32_exceptionEnd[];
 extern char mips32_GuestException[], mips32_GuestExceptionEnd[];
 
diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
index 3ef03009de5f..828fcfc1cd7f 100644
--- a/arch/mips/kvm/locore.S
+++ b/arch/mips/kvm/locore.S
@@ -202,6 +202,7 @@ FEXPORT(__kvm_mips_load_k0k1)
 
 	/* Jump to guest */
 	eret
+EXPORT(__kvm_mips_vcpu_run_end)
 
 VECTOR(MIPSX(exception), unknown)
 /* Find out what mode we came from and jump to the proper handler. */
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index dc052fb5c7a2..44da5259f390 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -315,6 +315,15 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	memcpy(gebase + offset, mips32_GuestException,
 	       mips32_GuestExceptionEnd - mips32_GuestException);
 
+#ifdef MODULE
+	offset += mips32_GuestExceptionEnd - mips32_GuestException;
+	memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run,
+	       __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run);
+	vcpu->arch.vcpu_run = gebase + offset;
+#else
+	vcpu->arch.vcpu_run = __kvm_mips_vcpu_run;
+#endif
+
 	/* Invalidate the icache for these ranges */
 	local_flush_icache_range((unsigned long)gebase,
 				(unsigned long)gebase + ALIGN(size, PAGE_SIZE));
@@ -404,7 +413,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	/* Disable hardware page table walking while in guest */
 	htw_stop();
 
-	r = __kvm_mips_vcpu_run(run, vcpu);
+	r = vcpu->arch.vcpu_run(run, vcpu);
 
 	/* Re-enable HTW before enabling interrupts */
 	htw_start();
diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h
index 4861a78c7160..f5f90bbf019d 100644
--- a/arch/mn10300/include/asm/thread_info.h
+++ b/arch/mn10300/include/asm/thread_info.h
@@ -115,7 +115,7 @@ static inline unsigned long current_stack_pointer(void)
 }
 
 #ifndef CONFIG_KGDB
-void arch_release_thread_info(struct thread_info *ti);
+void arch_release_thread_stack(unsigned long *stack);
 #endif
 #define get_thread_info(ti)	get_task_struct((ti)->task)
 #define put_thread_info(ti)	put_task_struct((ti)->task)
diff --git a/arch/mn10300/kernel/kgdb.c b/arch/mn10300/kernel/kgdb.c
index 99770823451a..2d7986c386fe 100644
--- a/arch/mn10300/kernel/kgdb.c
+++ b/arch/mn10300/kernel/kgdb.c
@@ -397,8 +397,9 @@ static bool kgdb_arch_undo_singlestep(struct pt_regs *regs)
  * single-step state is cleared.  At this point the breakpoints should have
  * been removed by __switch_to().
  */
-void arch_release_thread_info(struct thread_info *ti)
+void arch_release_thread_stack(unsigned long *stack)
 {
+	struct thread_info *ti = (void *)stack;
 	if (kgdb_sstep_thread == ti) {
 		kgdb_sstep_thread = NULL;
 
diff --git a/arch/mn10300/mm/pgtable.c b/arch/mn10300/mm/pgtable.c
index e77a7c728081..9577cf768875 100644
--- a/arch/mn10300/mm/pgtable.c
+++ b/arch/mn10300/mm/pgtable.c
@@ -63,7 +63,7 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
 
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL);
 	if (pte)
 		clear_page(pte);
 	return pte;
@@ -74,9 +74,9 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	struct page *pte;
 
 #ifdef CONFIG_HIGHPTE
-	pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0);
+	pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0);
 #else
-	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+	pte = alloc_pages(GFP_KERNEL, 0);
 #endif
 	if (!pte)
 		return NULL;
diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h
index 6e2985e0a7b9..bb47d08c8ef7 100644
--- a/arch/nios2/include/asm/pgalloc.h
+++ b/arch/nios2/include/asm/pgalloc.h
@@ -42,8 +42,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
 	pte_t *pte;
 
-	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO,
-					PTE_ORDER);
+	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
 
 	return pte;
 }
@@ -53,7 +52,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 {
 	struct page *pte;
 
-	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+	pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
 	if (pte) {
 		if (!pgtable_page_ctor(pte)) {
 			__free_page(pte);
diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h
index 21484e5b9e9a..87eebd185089 100644
--- a/arch/openrisc/include/asm/pgalloc.h
+++ b/arch/openrisc/include/asm/pgalloc.h
@@ -77,7 +77,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 					 unsigned long address)
 {
 	struct page *pte;
-	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+	pte = alloc_pages(GFP_KERNEL, 0);
 	if (!pte)
 		return NULL;
 	clear_page(page_address(pte));
diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c
index 62b08ef392be..5b2a95116e8f 100644
--- a/arch/openrisc/mm/ioremap.c
+++ b/arch/openrisc/mm/ioremap.c
@@ -122,7 +122,7 @@ pte_t __init_refok *pte_alloc_one_kernel(struct mm_struct *mm,
 	pte_t *pte;
 
 	if (likely(mem_init_done)) {
-		pte = (pte_t *) __get_free_page(GFP_KERNEL | __GFP_REPEAT);
+		pte = (pte_t *) __get_free_page(GFP_KERNEL);
 	} else {
 		pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
 #if 0
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index f2fd327dce2e..f08dda3f0995 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -63,8 +63,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT,
-					       PMD_ORDER);
+	pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL, PMD_ORDER);
 	if (pmd)
 		memset(pmd, 0, PAGE_SIZE<<PMD_ORDER);
 	return pmd;
@@ -124,7 +123,7 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 static inline pgtable_t
 pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	struct page *page = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	struct page *page = alloc_page(GFP_KERNEL|__GFP_ZERO);
 	if (!page)
 		return NULL;
 	if (!pgtable_page_ctor(page)) {
@@ -137,7 +136,7 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address)
 static inline pte_t *
 pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
 {
-	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	return pte;
 }
 
diff --git a/arch/parisc/include/asm/traps.h b/arch/parisc/include/asm/traps.h
index 4736020ba5ea..5e953ab4530d 100644
--- a/arch/parisc/include/asm/traps.h
+++ b/arch/parisc/include/asm/traps.h
@@ -8,6 +8,8 @@ struct pt_regs;
 void parisc_terminate(char *msg, struct pt_regs *regs,
 		int code, unsigned long offset) __noreturn __cold;
 
+void die_if_kernel(char *str, struct pt_regs *regs, long err);
+
 /* mm/fault.c */
 void do_page_fault(struct pt_regs *regs, unsigned long code,
 		unsigned long address);
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index e81ccf1716e9..5adc339eb7c8 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -324,8 +324,9 @@ int init_per_cpu(int cpunum)
 		per_cpu(cpu_data, cpunum).fp_rev = coproc_cfg.revision;
 		per_cpu(cpu_data, cpunum).fp_model = coproc_cfg.model;
 
-		printk(KERN_INFO  "FP[%d] enabled: Rev %ld Model %ld\n",
-			cpunum, coproc_cfg.revision, coproc_cfg.model);
+		if (cpunum == 0)
+			printk(KERN_INFO  "FP[%d] enabled: Rev %ld Model %ld\n",
+				cpunum, coproc_cfg.revision, coproc_cfg.model);
 
 		/*
 		** store status register to stack (hopefully aligned)
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 58dd6801f5be..31ec99a5f119 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -309,11 +309,6 @@ void __init time_init(void)
 	clocks_calc_mult_shift(&cyc2ns_mul, &cyc2ns_shift, current_cr16_khz,
 				NSEC_PER_MSEC, 0);
 
-#if defined(CONFIG_HAVE_UNSTABLE_SCHED_CLOCK) && defined(CONFIG_64BIT)
-	/* At bootup only one 64bit CPU is online and cr16 is "stable" */
-	set_sched_clock_stable();
-#endif
-
 	start_cpu_itimer();	/* get CPU 0 started */
 
 	/* register at clocksource framework */
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index d7c0acb35ec2..2b65c0177778 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -28,6 +28,7 @@
 #include <linux/ratelimit.h>
 #include <asm/uaccess.h>
 #include <asm/hardirq.h>
+#include <asm/traps.h>
 
 /* #define DEBUG_UNALIGNED 1 */
 
@@ -130,8 +131,6 @@
 
 int unaligned_enabled __read_mostly = 1;
 
-void die_if_kernel (char *str, struct pt_regs *regs, long err);
-
 static int emulate_ldh(struct pt_regs *regs, int toreg)
 {
 	unsigned long saddr = regs->ior;
@@ -666,7 +665,7 @@ void handle_unaligned(struct pt_regs *regs)
 		break;
 	}
 
-	if (modify && R1(regs->iir))
+	if (ret == 0 && modify && R1(regs->iir))
 		regs->gr[R1(regs->iir)] = newbase;
 
 
@@ -677,6 +676,14 @@ void handle_unaligned(struct pt_regs *regs)
 
 	if (ret)
 	{
+		/*
+		 * The unaligned handler failed.
+		 * If we were called by __get_user() or __put_user() jump
+		 * to it's exception fixup handler instead of crashing.
+		 */
+		if (!user_mode(regs) && fixup_exception(regs))
+			return;
+
 		printk(KERN_CRIT "Unaligned handler failed, ret = %d\n", ret);
 		die_if_kernel("Unaligned data reference", regs, 28);
 
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index ddd988b267a9..e278a87f43cc 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -75,7 +75,10 @@ find_unwind_entry(unsigned long addr)
 	if (addr >= kernel_unwind_table.start && 
 	    addr <= kernel_unwind_table.end)
 		e = find_unwind_entry_in_table(&kernel_unwind_table, addr);
-	else 
+	else {
+		unsigned long flags;
+
+		spin_lock_irqsave(&unwind_lock, flags);
 		list_for_each_entry(table, &unwind_tables, list) {
 			if (addr >= table->start && 
 			    addr <= table->end)
@@ -86,6 +89,8 @@ find_unwind_entry(unsigned long addr)
 				break;
 			}
 		}
+		spin_unlock_irqrestore(&unwind_lock, flags);
+	}
 
 	return e;
 }
@@ -303,18 +308,16 @@ static void unwind_frame_regs(struct unwind_frame_info *info)
 
 			insn = *(unsigned int *)npc;
 
-			if ((insn & 0xffffc000) == 0x37de0000 ||
-			    (insn & 0xffe00000) == 0x6fc00000) {
+			if ((insn & 0xffffc001) == 0x37de0000 ||
+			    (insn & 0xffe00001) == 0x6fc00000) {
 				/* ldo X(sp), sp, or stwm X,D(sp) */
-				frame_size += (insn & 0x1 ? -1 << 13 : 0) | 
-					((insn & 0x3fff) >> 1);
+				frame_size += (insn & 0x3fff) >> 1;
 				dbg("analyzing func @ %lx, insn=%08x @ "
 				    "%lx, frame_size = %ld\n", info->ip,
 				    insn, npc, frame_size);
-			} else if ((insn & 0xffe00008) == 0x73c00008) {
+			} else if ((insn & 0xffe00009) == 0x73c00008) {
 				/* std,ma X,D(sp) */
-				frame_size += (insn & 0x1 ? -1 << 13 : 0) | 
-					(((insn >> 4) & 0x3ff) << 3);
+				frame_size += ((insn >> 4) & 0x3ff) << 3;
 				dbg("analyzing func @ %lx, insn=%08x @ "
 				    "%lx, frame_size = %ld\n", info->ip,
 				    insn, npc, frame_size);
@@ -333,6 +336,9 @@ static void unwind_frame_regs(struct unwind_frame_info *info)
 			}
 		}
 
+		if (frame_size > e->Total_frame_size << 3)
+			frame_size = e->Total_frame_size << 3;
+
 		if (!unwind_special(info, e->region_start, frame_size)) {
 			info->prev_sp = info->sp - frame_size;
 			if (e->Millicode)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 01f7464d9fea..0a9d439bcda6 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -128,7 +128,7 @@ config PPC
 	select IRQ_FORCED_THREADING
 	select HAVE_RCU_TABLE_FREE if SMP
 	select HAVE_SYSCALL_TRACEPOINTS
-	select HAVE_CBPF_JIT
+	select HAVE_CBPF_JIT if CPU_BIG_ENDIAN
 	select HAVE_ARCH_JUMP_LABEL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_HAS_GCOV_PROFILE_ALL
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index a2350194fc76..8e21bb492dca 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -102,7 +102,6 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb,
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
-	tlb_flush_pgtable(tlb, address);
 	pgtable_page_dtor(table);
 	pgtable_free_tlb(tlb, page_address(table), 0);
 }
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 290157e8d5b2..74839f24f412 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -88,6 +88,7 @@
 #define HPTE_R_RPN_SHIFT	12
 #define HPTE_R_RPN		ASM_CONST(0x0ffffffffffff000)
 #define HPTE_R_PP		ASM_CONST(0x0000000000000003)
+#define HPTE_R_PPP		ASM_CONST(0x8000000000000003)
 #define HPTE_R_N		ASM_CONST(0x0000000000000004)
 #define HPTE_R_G		ASM_CONST(0x0000000000000008)
 #define HPTE_R_M		ASM_CONST(0x0000000000000010)
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 488279edb1f0..cd5e7aa8cc34 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -41,7 +41,7 @@ extern struct kmem_cache *pgtable_cache[];
 			pgtable_cache[(shift) - 1];	\
 		})
 
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO
 
 extern pte_t *pte_fragment_alloc(struct mm_struct *, unsigned long, int);
 extern void pte_fragment_free(unsigned long *, int);
@@ -56,7 +56,7 @@ static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
 	return (pgd_t *)__get_free_page(PGALLOC_GFP);
 #else
 	struct page *page;
-	page = alloc_pages(PGALLOC_GFP, 4);
+	page = alloc_pages(PGALLOC_GFP | __GFP_REPEAT, 4);
 	if (!page)
 		return NULL;
 	return (pgd_t *) page_address(page);
@@ -93,8 +93,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -110,13 +109,17 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
                                   unsigned long address)
 {
+	/*
+	 * By now all the pud entries should be none entries. So go
+	 * ahead and flush the page walk cache
+	 */
+	flush_tlb_pgtable(tlb, address);
         pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE);
 }
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
@@ -127,6 +130,11 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
                                   unsigned long address)
 {
+	/*
+	 * By now all the pud entries should be none entries. So go
+	 * ahead and flush the page walk cache
+	 */
+	flush_tlb_pgtable(tlb, address);
         return pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX);
 }
 
@@ -151,7 +159,7 @@ static inline pgtable_t pmd_pgtable(pmd_t pmd)
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -198,7 +206,11 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
-	tlb_flush_pgtable(tlb, address);
+	/*
+	 * By now all the pud entries should be none entries. So go
+	 * ahead and flush the page walk cache
+	 */
+	flush_tlb_pgtable(tlb, address);
 	pgtable_free_tlb(tlb, table, 0);
 }
 
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 937d4e247ac3..df294224e280 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -228,5 +228,20 @@ extern void radix__vmemmap_remove_mapping(unsigned long start,
 
 extern int radix__map_kernel_page(unsigned long ea, unsigned long pa,
 				 pgprot_t flags, unsigned int psz);
+
+static inline unsigned long radix__get_tree_size(void)
+{
+	unsigned long rts_field;
+	/*
+	 * we support 52 bits, hence 52-31 = 21, 0b10101
+	 * RTS encoding details
+	 * bits 0 - 3 of rts -> bits 6 - 8 unsigned long
+	 * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long
+	 */
+	rts_field = (0x5UL << 5); /* 6 - 8 bits */
+	rts_field |= (0x2UL << 61);
+
+	return rts_field;
+}
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 13ef38828dfe..3fa94fcac628 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -18,16 +18,19 @@ extern void radix__local_flush_tlb_mm(struct mm_struct *mm);
 extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 extern void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 				    unsigned long ap, int nid);
+extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__tlb_flush(struct mmu_gather *tlb);
 #ifdef CONFIG_SMP
 extern void radix__flush_tlb_mm(struct mm_struct *mm);
 extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 extern void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 			      unsigned long ap, int nid);
+extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 #else
 #define radix__flush_tlb_mm(mm)		radix__local_flush_tlb_mm(mm)
 #define radix__flush_tlb_page(vma,addr)	radix__local_flush_tlb_page(vma,addr)
 #define radix___flush_tlb_page(mm,addr,p,i)	radix___local_flush_tlb_page(mm,addr,p,i)
+#define radix__flush_tlb_pwc(tlb, addr)	radix__local_flush_tlb_pwc(tlb, addr)
 #endif
 
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index d98424ae356c..96e5769b18b0 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -72,5 +72,19 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 #define flush_tlb_mm(mm)		local_flush_tlb_mm(mm)
 #define flush_tlb_page(vma, addr)	local_flush_tlb_page(vma, addr)
 #endif /* CONFIG_SMP */
+/*
+ * flush the page walk cache for the address
+ */
+static inline void flush_tlb_pgtable(struct mmu_gather *tlb, unsigned long address)
+{
+	/*
+	 * Flush the page table walk cache on freeing a page table. We already
+	 * have marked the upper/higher level page table entry none by now.
+	 * So it is safe to flush PWC here.
+	 */
+	if (!radix_enabled())
+		return;
 
+	radix__flush_tlb_pwc(tlb, address);
+}
 #endif /*  _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */
diff --git a/arch/powerpc/include/asm/book3s/pgalloc.h b/arch/powerpc/include/asm/book3s/pgalloc.h
index 54f591e9572e..c0a69ae92256 100644
--- a/arch/powerpc/include/asm/book3s/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/pgalloc.h
@@ -4,11 +4,6 @@
 #include <linux/mm.h>
 
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
-				     unsigned long address)
-{
-
-}
 
 #ifdef CONFIG_PPC64
 #include <asm/book3s/64/pgalloc.h>
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index 0c12a3bfe2ab..897d2e1c8a9b 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -57,8 +57,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -88,7 +87,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -172,7 +171,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
-	pte_fragment_fre((unsigned long *)pte, 1);
+	pte_fragment_free((unsigned long *)pte, 1);
 }
 
 static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
@@ -190,8 +189,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index c1e82e968506..a0948f40bc7b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -717,7 +717,7 @@
 #define   MMCR0_FCWAIT	0x00000002UL /* freeze counter in WAIT state */
 #define   MMCR0_FCHV	0x00000001UL /* freeze conditions in hypervisor mode */
 #define SPRN_MMCR1	798
-#define SPRN_MMCR2	769
+#define SPRN_MMCR2	785
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
 #define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
@@ -754,13 +754,13 @@
 #define SPRN_PMC6	792
 #define SPRN_PMC7	793
 #define SPRN_PMC8	794
-#define SPRN_SIAR	780
-#define SPRN_SDAR	781
 #define SPRN_SIER	784
 #define   SIER_SIPR		0x2000000	/* Sampled MSR_PR */
 #define   SIER_SIHV		0x1000000	/* Sampled MSR_HV */
 #define   SIER_SIAR_VALID	0x0400000	/* SIAR contents valid */
 #define   SIER_SDAR_VALID	0x0200000	/* SDAR contents valid */
+#define SPRN_SIAR	796
+#define SPRN_SDAR	797
 #define SPRN_TACR	888
 #define SPRN_TCSCR	889
 #define SPRN_CSIGR	890
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 2714a3b81d24..b5f73cb5eeb6 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -642,7 +642,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 		if (pe->type & EEH_PE_VF) {
 			eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
 		} else {
-			eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 			pci_lock_rescan_remove();
 			pci_hp_remove_devices(bus);
 			pci_unlock_rescan_remove();
@@ -692,10 +691,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 		 */
 		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
 		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
-		if (pe->type & EEH_PE_VF)
+		if (pe->type & EEH_PE_VF) {
 			eeh_add_virt_device(edev, NULL);
-		else
+		} else {
+			eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 			pci_hp_add_devices(bus);
+		}
 	} else if (frozen_bus && rmv_data->removed) {
 		pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
 		ssleep(5);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4c9440629128..8bcc1b457115 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1399,11 +1399,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_RADIX)
 	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
 
 	mtlr	r10
-BEGIN_MMU_FTR_SECTION
-	b	2f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX)
 	andi.	r10,r12,MSR_RI	/* check for unrecoverable exception */
+BEGIN_MMU_FTR_SECTION
 	beq-	2f
+FTR_SECTION_ELSE
+	b	2f
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX)
 
 .machine	push
 .machine	"power4"
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index da5192590c44..6ee4b72cda42 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -656,6 +656,7 @@ unsigned char ibm_architecture_vec[] = {
 	W(0xffff0000), W(0x003e0000),	/* POWER6 */
 	W(0xffff0000), W(0x003f0000),	/* POWER7 */
 	W(0xffff0000), W(0x004b0000),	/* POWER8E */
+	W(0xffff0000), W(0x004c0000),   /* POWER8NVL */
 	W(0xffff0000), W(0x004d0000),	/* POWER8 */
 	W(0xffffffff), W(0x0f000004),	/* all 2.07-compliant */
 	W(0xffffffff), W(0x0f000003),	/* all 2.06-compliant */
@@ -718,7 +719,7 @@ unsigned char ibm_architecture_vec[] = {
 	 * must match by the macro below. Update the definition if
 	 * the structure layout changes.
 	 */
-#define IBM_ARCH_VEC_NRCORES_OFFSET	125
+#define IBM_ARCH_VEC_NRCORES_OFFSET	133
 	W(NR_CPUS),			/* number of cores supported */
 	0,
 	0,
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 30a03c03fe73..060b140f03c6 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -377,7 +377,7 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset,
 
 #else
 	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
-		     offsetof(struct thread_fp_state, fpr[32][0]));
+		     offsetof(struct thread_fp_state, fpr[32]));
 
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				   &target->thread.fp_state, 0, -1);
@@ -405,7 +405,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 	return 0;
 #else
 	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
-		     offsetof(struct thread_fp_state, fpr[32][0]));
+		     offsetof(struct thread_fp_state, fpr[32]));
 
 	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				  &target->thread.fp_state, 0, -1);
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index d873f6507f72..f8a871a72985 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -316,8 +316,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 			DBG_LOW(" -> hit\n");
 			/* Update the HPTE */
 			hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
-						~(HPTE_R_PP | HPTE_R_N)) |
-					       (newpp & (HPTE_R_PP | HPTE_R_N |
+						~(HPTE_R_PPP | HPTE_R_N)) |
+					       (newpp & (HPTE_R_PPP | HPTE_R_N |
 							 HPTE_R_C)));
 		}
 		native_unlock_hpte(hptep);
@@ -385,8 +385,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 
 	/* Update the HPTE */
 	hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
-			~(HPTE_R_PP | HPTE_R_N)) |
-		(newpp & (HPTE_R_PP | HPTE_R_N)));
+				~(HPTE_R_PPP | HPTE_R_N)) |
+			       (newpp & (HPTE_R_PPP | HPTE_R_N)));
 	/*
 	 * Ensure it is out of the tlb too. Bolted entries base and
 	 * actual page size will be same.
@@ -550,7 +550,11 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 		}
 	}
 	/* This works for all page sizes, and for 256M and 1T segments */
-	*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		*ssize = hpte_r >> HPTE_R_3_0_SSIZE_SHIFT;
+	else
+		*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
+
 	shift = mmu_psize_defs[size].shift;
 
 	avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 59268969a0bc..5b22ba0b58bc 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -159,6 +159,19 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = {
 	},
 };
 
+/*
+ * 'R' and 'C' update notes:
+ *  - Under pHyp or KVM, the updatepp path will not set C, thus it *will*
+ *     create writeable HPTEs without C set, because the hcall H_PROTECT
+ *     that we use in that case will not update C
+ *  - The above is however not a problem, because we also don't do that
+ *     fancy "no flush" variant of eviction and we use H_REMOVE which will
+ *     do the right thing and thus we don't have the race I described earlier
+ *
+ *    - Under bare metal,  we do have the race, so we need R and C set
+ *    - We make sure R is always set and never lost
+ *    - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping
+ */
 unsigned long htab_convert_pte_flags(unsigned long pteflags)
 {
 	unsigned long rflags = 0;
@@ -186,19 +199,28 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
 			rflags |= 0x1;
 	}
 	/*
-	 * Always add "C" bit for perf. Memory coherence is always enabled
+	 * We can't allow hardware to update hpte bits. Hence always
+	 * set 'R' bit and set 'C' if it is a write fault
 	 */
-	rflags |=  HPTE_R_C | HPTE_R_M;
+	rflags |=  HPTE_R_R;
+
+	if (pteflags & _PAGE_DIRTY)
+		rflags |= HPTE_R_C;
 	/*
 	 * Add in WIG bits
 	 */
 
 	if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_TOLERANT)
 		rflags |= HPTE_R_I;
-	if ((pteflags & _PAGE_CACHE_CTL ) == _PAGE_NON_IDEMPOTENT)
+	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
 		rflags |= (HPTE_R_I | HPTE_R_G);
-	if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
-		rflags |= (HPTE_R_I | HPTE_R_W);
+	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
+		rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
+	else
+		/*
+		 * Add memory coherence if cache inhibited is not set
+		 */
+		rflags |= HPTE_R_M;
 
 	return rflags;
 }
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 5aac1a3f86cd..119d18611500 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -73,7 +73,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	cachep = PGT_CACHE(pdshift - pshift);
 #endif
 
-	new = kmem_cache_zalloc(cachep, GFP_KERNEL|__GFP_REPEAT);
+	new = kmem_cache_zalloc(cachep, GFP_KERNEL);
 
 	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
 	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 227b2a6c4544..196222227e82 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -65,7 +65,7 @@ static int radix__init_new_context(struct mm_struct *mm, int index)
 	/*
 	 * set the process table entry,
 	 */
-	rts_field = 3ull << PPC_BITLSHIFT(2);
+	rts_field = radix__get_tree_size();
 	process_tb[index].prtb0 = cpu_to_be64(rts_field | __pa(mm->pgd) | RADIX_PGD_INDEX_SIZE);
 	return 0;
 }
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index eb4451144746..670318766545 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -33,10 +33,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 	changed = !pmd_same(*(pmdp), entry);
 	if (changed) {
 		__ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry));
-		/*
-		 * Since we are not supporting SW TLB systems, we don't
-		 * have any thing similar to flush_tlb_page_nohash()
-		 */
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	}
 	return changed;
 }
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 18b2c11604fa..e58707deef5c 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -160,9 +160,8 @@ redo:
 	process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT);
 	/*
 	 * Fill in the process table.
-	 * we support 52 bits, hence 52-28 = 24, 11000
 	 */
-	rts_field = 3ull << PPC_BITLSHIFT(2);
+	rts_field = radix__get_tree_size();
 	process_tb->prtb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE);
 	/*
 	 * Fill in the partition table. We are suppose to use effective address
@@ -176,10 +175,8 @@ redo:
 static void __init radix_init_partition_table(void)
 {
 	unsigned long rts_field;
-	/*
-	 * we support 52 bits, hence 52-28 = 24, 11000
-	 */
-	rts_field = 3ull << PPC_BITLSHIFT(2);
+
+	rts_field = radix__get_tree_size();
 
 	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
 	partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT);
@@ -296,11 +293,6 @@ found:
 void __init radix__early_init_mmu(void)
 {
 	unsigned long lpcr;
-	/*
-	 * setup LPCR UPRT based on mmu_features
-	 */
-	lpcr = mfspr(SPRN_LPCR);
-	mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
 
 #ifdef CONFIG_PPC_64K_PAGES
 	/* PAGE_SIZE mappings */
@@ -343,8 +335,11 @@ void __init radix__early_init_mmu(void)
 	__pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT;
 
 	radix_init_page_sizes();
-	if (!firmware_has_feature(FW_FEATURE_LPAR))
+	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+		lpcr = mfspr(SPRN_LPCR);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
 		radix_init_partition_table();
+	}
 
 	radix_init_pgtable();
 }
@@ -353,16 +348,15 @@ void radix__early_init_mmu_secondary(void)
 {
 	unsigned long lpcr;
 	/*
-	 * setup LPCR UPRT based on mmu_features
-	 */
-	lpcr = mfspr(SPRN_LPCR);
-	mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
-	/*
-	 * update partition table control register, 64 K size.
+	 * update partition table control register and UPRT
 	 */
-	if (!firmware_has_feature(FW_FEATURE_LPAR))
+	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+		lpcr = mfspr(SPRN_LPCR);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
+
 		mtspr(SPRN_PTCR,
 		      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
+	}
 }
 
 void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index bf7bf32b54f8..7f922f557936 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -84,7 +84,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add
 	pte_t *pte;
 
 	if (slab_is_available()) {
-		pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+		pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	} else {
 		pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
 		if (pte)
@@ -97,7 +97,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	struct page *ptepage;
 
-	gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO;
+	gfp_t flags = GFP_KERNEL | __GFP_ZERO;
 
 	ptepage = alloc_pages(flags, 0);
 	if (!ptepage)
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index e009e0604a8a..f5e8d4edb808 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -350,8 +350,7 @@ static pte_t *get_from_cache(struct mm_struct *mm)
 static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
 {
 	void *ret = NULL;
-	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
-				       __GFP_REPEAT | __GFP_ZERO);
+	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
 	if (!page)
 		return NULL;
 	if (!kernel && !pgtable_page_ctor(page)) {
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 0fdaf93a3e09..ab2f60e812e2 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -18,16 +18,20 @@
 
 static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
-static inline void __tlbiel_pid(unsigned long pid, int set)
+#define RIC_FLUSH_TLB 0
+#define RIC_FLUSH_PWC 1
+#define RIC_FLUSH_ALL 2
+
+static inline void __tlbiel_pid(unsigned long pid, int set,
+				unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = PPC_BIT(53); /* IS = 1 */
 	rb |= set << PPC_BITLSHIFT(51);
 	rs = ((unsigned long)pid) << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 2;  /* invalidate all the caches */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
@@ -39,25 +43,24 @@ static inline void __tlbiel_pid(unsigned long pid, int set)
 /*
  * We use 128 set in radix mode and 256 set in hpt mode.
  */
-static inline void _tlbiel_pid(unsigned long pid)
+static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 {
 	int set;
 
 	for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
-		__tlbiel_pid(pid, set);
+		__tlbiel_pid(pid, set, ric);
 	}
 	return;
 }
 
-static inline void _tlbie_pid(unsigned long pid)
+static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = PPC_BIT(53); /* IS = 1 */
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 2;  /* invalidate all the caches */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
@@ -67,16 +70,15 @@ static inline void _tlbie_pid(unsigned long pid)
 }
 
 static inline void _tlbiel_va(unsigned long va, unsigned long pid,
-			      unsigned long ap)
+			      unsigned long ap, unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = va & ~(PPC_BITMASK(52, 63));
 	rb |= ap << PPC_BITLSHIFT(58);
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 0;  /* no cluster flush yet */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
@@ -86,16 +88,15 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 }
 
 static inline void _tlbie_va(unsigned long va, unsigned long pid,
-			     unsigned long ap)
+			     unsigned long ap, unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = va & ~(PPC_BITMASK(52, 63));
 	rb |= ap << PPC_BITLSHIFT(58);
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 0;  /* no cluster flush yet */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
@@ -117,25 +118,40 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
  */
 void radix__local_flush_tlb_mm(struct mm_struct *mm)
 {
-	unsigned int pid;
+	unsigned long pid;
 
 	preempt_disable();
 	pid = mm->context.id;
 	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_pid(pid);
+		_tlbiel_pid(pid, RIC_FLUSH_ALL);
 	preempt_enable();
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_mm);
 
+void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+{
+	unsigned long pid;
+	struct mm_struct *mm = tlb->mm;
+
+	preempt_disable();
+
+	pid = mm->context.id;
+	if (pid != MMU_NO_CONTEXT)
+		_tlbiel_pid(pid, RIC_FLUSH_PWC);
+
+	preempt_enable();
+}
+EXPORT_SYMBOL(radix__local_flush_tlb_pwc);
+
 void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 			    unsigned long ap, int nid)
 {
-	unsigned int pid;
+	unsigned long pid;
 
 	preempt_disable();
 	pid = mm ? mm->context.id : 0;
 	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_va(vmaddr, pid, ap);
+		_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
 	preempt_enable();
 }
 
@@ -160,7 +176,7 @@ static int mm_is_core_local(struct mm_struct *mm)
 
 void radix__flush_tlb_mm(struct mm_struct *mm)
 {
-	unsigned int pid;
+	unsigned long pid;
 
 	preempt_disable();
 	pid = mm->context.id;
@@ -172,20 +188,46 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 
 		if (lock_tlbie)
 			raw_spin_lock(&native_tlbie_lock);
-		_tlbie_pid(pid);
+		_tlbie_pid(pid, RIC_FLUSH_ALL);
 		if (lock_tlbie)
 			raw_spin_unlock(&native_tlbie_lock);
 	} else
-		_tlbiel_pid(pid);
+		_tlbiel_pid(pid, RIC_FLUSH_ALL);
 no_context:
 	preempt_enable();
 }
 EXPORT_SYMBOL(radix__flush_tlb_mm);
 
+void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+{
+	unsigned long pid;
+	struct mm_struct *mm = tlb->mm;
+
+	preempt_disable();
+
+	pid = mm->context.id;
+	if (unlikely(pid == MMU_NO_CONTEXT))
+		goto no_context;
+
+	if (!mm_is_core_local(mm)) {
+		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+
+		if (lock_tlbie)
+			raw_spin_lock(&native_tlbie_lock);
+		_tlbie_pid(pid, RIC_FLUSH_PWC);
+		if (lock_tlbie)
+			raw_spin_unlock(&native_tlbie_lock);
+	} else
+		_tlbiel_pid(pid, RIC_FLUSH_PWC);
+no_context:
+	preempt_enable();
+}
+EXPORT_SYMBOL(radix__flush_tlb_pwc);
+
 void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 		       unsigned long ap, int nid)
 {
-	unsigned int pid;
+	unsigned long pid;
 
 	preempt_disable();
 	pid = mm ? mm->context.id : 0;
@@ -196,11 +238,11 @@ void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 
 		if (lock_tlbie)
 			raw_spin_lock(&native_tlbie_lock);
-		_tlbie_va(vmaddr, pid, ap);
+		_tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
 		if (lock_tlbie)
 			raw_spin_unlock(&native_tlbie_lock);
 	} else
-		_tlbiel_va(vmaddr, pid, ap);
+		_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
 bail:
 	preempt_enable();
 }
@@ -224,7 +266,7 @@ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
 
 	if (lock_tlbie)
 		raw_spin_lock(&native_tlbie_lock);
-	_tlbie_pid(0);
+	_tlbie_pid(0, RIC_FLUSH_ALL);
 	if (lock_tlbie)
 		raw_spin_unlock(&native_tlbie_lock);
 }
diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c
index c50ea76ba66c..6081fbd75330 100644
--- a/arch/powerpc/platforms/512x/clock-commonclk.c
+++ b/arch/powerpc/platforms/512x/clock-commonclk.c
@@ -221,7 +221,7 @@ static bool soc_has_mclk_mux0_canin(void)
 /* convenience wrappers around the common clk API */
 static inline struct clk *mpc512x_clk_fixed(const char *name, int rate)
 {
-	return clk_register_fixed_rate(NULL, name, NULL, CLK_IS_ROOT, rate);
+	return clk_register_fixed_rate(NULL, name, NULL, 0, rate);
 }
 
 static inline struct clk *mpc512x_clk_factor(
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 84fb984f29c1..85c85eb3e245 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -172,7 +172,7 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i,
 	if (rc < 0)
 		goto out;
 
-	skip = roundup(cprm->file->f_pos - total + sz, 4) - cprm->file->f_pos;
+	skip = roundup(cprm->pos - total + sz, 4) - cprm->pos;
 	if (!dump_skip(cprm, skip))
 		goto Eio;
 out:
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index ac3ffd97e059..3998e0f9a03b 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -53,7 +53,6 @@ static int ibm_read_slot_reset_state2;
 static int ibm_slot_error_detail;
 static int ibm_get_config_addr_info;
 static int ibm_get_config_addr_info2;
-static int ibm_configure_bridge;
 static int ibm_configure_pe;
 
 /*
@@ -81,7 +80,14 @@ static int pseries_eeh_init(void)
 	ibm_get_config_addr_info2	= rtas_token("ibm,get-config-addr-info2");
 	ibm_get_config_addr_info	= rtas_token("ibm,get-config-addr-info");
 	ibm_configure_pe		= rtas_token("ibm,configure-pe");
-	ibm_configure_bridge		= rtas_token("ibm,configure-bridge");
+
+	/*
+	 * ibm,configure-pe and ibm,configure-bridge have the same semantics,
+	 * however ibm,configure-pe can be faster.  If we can't find
+	 * ibm,configure-pe then fall back to using ibm,configure-bridge.
+	 */
+	if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE)
+		ibm_configure_pe 	= rtas_token("ibm,configure-bridge");
 
 	/*
 	 * Necessary sanity check. We needn't check "get-config-addr-info"
@@ -93,8 +99,7 @@ static int pseries_eeh_init(void)
 	    (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE &&
 	     ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE)	||
 	    ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE	||
-	    (ibm_configure_pe == RTAS_UNKNOWN_SERVICE		&&
-	     ibm_configure_bridge == RTAS_UNKNOWN_SERVICE)) {
+	    ibm_configure_pe == RTAS_UNKNOWN_SERVICE) {
 		pr_info("EEH functionality not supported\n");
 		return -EINVAL;
 	}
@@ -615,29 +620,41 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
 {
 	int config_addr;
 	int ret;
+	/* Waiting 0.2s maximum before skipping configuration */
+	int max_wait = 200;
 
 	/* Figure out the PE address */
 	config_addr = pe->config_addr;
 	if (pe->addr)
 		config_addr = pe->addr;
 
-	/* Use new configure-pe function, if supported */
-	if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
+	while (max_wait > 0) {
 		ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
 				config_addr, BUID_HI(pe->phb->buid),
 				BUID_LO(pe->phb->buid));
-	} else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
-		ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
-				config_addr, BUID_HI(pe->phb->buid),
-				BUID_LO(pe->phb->buid));
-	} else {
-		return -EFAULT;
-	}
 
-	if (ret)
-		pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
-			__func__, pe->phb->global_number, pe->addr, ret);
+		if (!ret)
+			return ret;
+
+		/*
+		 * If RTAS returns a delay value that's above 100ms, cut it
+		 * down to 100ms in case firmware made a mistake.  For more
+		 * on how these delay values work see rtas_busy_delay_time
+		 */
+		if (ret > RTAS_EXTENDED_DELAY_MIN+2 &&
+		    ret <= RTAS_EXTENDED_DELAY_MAX)
+			ret = RTAS_EXTENDED_DELAY_MIN+2;
+
+		max_wait -= rtas_busy_delay_time(ret);
+
+		if (max_wait < 0)
+			break;
+
+		rtas_busy_delay(ret);
+	}
 
+	pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
+		__func__, pe->phb->global_number, pe->addr, ret);
 	return ret;
 }
 
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index b7dfc1359d01..3e8865b187de 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -927,7 +927,7 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 	dn = pci_device_to_OF_node(dev);
 	pdn = PCI_DN(dn);
 	buid = pdn->phb->buid;
-	cfg_addr = (pdn->busno << 8) | pdn->devfn;
+	cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
 
 	ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query,
 		  cfg_addr, BUID_HI(buid), BUID_LO(buid));
@@ -956,7 +956,7 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 	dn = pci_device_to_OF_node(dev);
 	pdn = PCI_DN(dn);
 	buid = pdn->phb->buid;
-	cfg_addr = (pdn->busno << 8) | pdn->devfn;
+	cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
 
 	do {
 		/* extra outputs are LIOBN and dma-addr (hi, lo) */
diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h
index 5e04f3cbd320..8ae236b0f80b 100644
--- a/arch/s390/include/asm/fpu/api.h
+++ b/arch/s390/include/asm/fpu/api.h
@@ -22,7 +22,7 @@ static inline int test_fp_ctl(u32 fpc)
 		"	la	%0,0\n"
 		"1:\n"
 		EX_TABLE(0b,1b)
-		: "=d" (rc), "=d" (orig_fpc)
+		: "=d" (rc), "=&d" (orig_fpc)
 		: "d" (fpc), "0" (-EINVAL));
 	return rc;
 }
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 37b9017c6a96..ac82e8eb936d 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -245,6 +245,7 @@ struct kvm_vcpu_stat {
 	u32 exit_stop_request;
 	u32 exit_validity;
 	u32 exit_instruction;
+	u32 exit_pei;
 	u32 halt_successful_poll;
 	u32 halt_attempted_poll;
 	u32 halt_poll_invalid;
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index f20abdb5630a..d14069d4b88d 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2064,12 +2064,5 @@ void s390_reset_system(void)
 	S390_lowcore.program_new_psw.addr =
 		(unsigned long) s390_base_pgm_handler;
 
-	/*
-	 * Clear subchannel ID and number to signal new kernel that no CCW or
-	 * SCSI IPL has been done (for kexec and kdump)
-	 */
-	S390_lowcore.subchannel_id = 0;
-	S390_lowcore.subchannel_nr = 0;
-
 	do_reset_calls();
 }
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 59215c518f37..7ec63b1d920d 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -649,6 +649,8 @@ static int cpumf_pmu_commit_txn(struct pmu *pmu)
 
 /* Performance monitoring unit for s390x */
 static struct pmu cpumf_pmu = {
+	.task_ctx_nr  = perf_sw_context,
+	.capabilities = PERF_PMU_CAP_NO_INTERRUPT,
 	.pmu_enable   = cpumf_pmu_enable,
 	.pmu_disable  = cpumf_pmu_disable,
 	.event_init   = cpumf_pmu_event_init,
@@ -708,12 +710,6 @@ static int __init cpumf_pmu_init(void)
 		goto out;
 	}
 
-	/* The CPU measurement counter facility does not have overflow
-	 * interrupts to do sampling.  Sampling must be provided by
-	 * external means, for example, by timers.
-	 */
-	cpumf_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
-
 	cpumf_pmu.attr_groups = cpumf_cf_event_group();
 	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
 	if (rc) {
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 2e6b54e4d3f9..252157181302 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -341,6 +341,8 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 
 static int handle_partial_execution(struct kvm_vcpu *vcpu)
 {
+	vcpu->stat.exit_pei++;
+
 	if (vcpu->arch.sie_block->ipa == 0xb254)	/* MVPG */
 		return handle_mvpg_pei(vcpu);
 	if (vcpu->arch.sie_block->ipa >> 8 == 0xae)	/* SIGP */
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6d8ec3ac9dd8..43f2a2b80490 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -61,6 +61,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "exit_external_request", VCPU_STAT(exit_external_request) },
 	{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
 	{ "exit_instruction", VCPU_STAT(exit_instruction) },
+	{ "exit_pei", VCPU_STAT(exit_pei) },
 	{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
 	{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
@@ -657,7 +658,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 		kvm->arch.model.cpuid = proc->cpuid;
 		lowest_ibc = sclp.ibc >> 16 & 0xfff;
 		unblocked_ibc = sclp.ibc & 0xfff;
-		if (lowest_ibc) {
+		if (lowest_ibc && proc->ibc) {
 			if (proc->ibc > unblocked_ibc)
 				kvm->arch.model.ibc = unblocked_ibc;
 			else if (proc->ibc < lowest_ibc)
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index e8b5962ac12a..e2565d2d0c32 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -169,7 +169,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 			return table;
 	}
 	/* Allocate a fresh page */
-	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+	page = alloc_page(GFP_KERNEL);
 	if (!page)
 		return NULL;
 	if (!pgtable_page_ctor(page)) {
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 4324b87f9398..9f0ce0e6eeb4 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -437,7 +437,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
 	pgste = pgste_get_lock(ptep);
 	pgstev = pgste_val(pgste);
 	pte = *ptep;
-	if (pte_swap(pte) &&
+	if (!reset && pte_swap(pte) &&
 	    ((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED ||
 	     (pgstev & _PGSTE_GPS_ZERO))) {
 		ptep_zap_swap_entry(mm, pte_to_swp_entry(pte));
diff --git a/arch/score/include/asm/pgalloc.h b/arch/score/include/asm/pgalloc.h
index 2e067657db98..49b012d78c1a 100644
--- a/arch/score/include/asm/pgalloc.h
+++ b/arch/score/include/asm/pgalloc.h
@@ -42,8 +42,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
 	pte_t *pte;
 
-	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO,
-					PTE_ORDER);
+	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
 
 	return pte;
 }
@@ -53,7 +52,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 {
 	struct page *pte;
 
-	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+	pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
 	if (!pte)
 		return NULL;
 	clear_highpage(pte);
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index a33673b3687d..f3f42c84c40f 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -34,7 +34,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+	return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -43,7 +43,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	struct page *page;
 	void *pg;
 
-	pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+	pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
 	if (!pg)
 		return NULL;
 	page = virt_to_page(pg);
diff --git a/arch/sh/mm/pgtable.c b/arch/sh/mm/pgtable.c
index 26e03a1f7ca4..a62bd8696779 100644
--- a/arch/sh/mm/pgtable.c
+++ b/arch/sh/mm/pgtable.c
@@ -1,7 +1,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 
-#define PGALLOC_GFP GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_ZERO
 
 static struct kmem_cache *pgd_cachep;
 #if PAGETABLE_LEVELS > 2
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index 5e3187185b4a..3529f1378cd8 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -41,8 +41,7 @@ static inline void __pud_populate(pud_t *pud, pmd_t *pmd)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache,
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -52,8 +51,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache,
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 14bb0d5ed3c6..aec508e37490 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2704,8 +2704,7 @@ void __flush_tlb_all(void)
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 			    unsigned long address)
 {
-	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
-				       __GFP_REPEAT | __GFP_ZERO);
+	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
 	pte_t *pte = NULL;
 
 	if (page)
@@ -2717,8 +2716,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 pgtable_t pte_alloc_one(struct mm_struct *mm,
 			unsigned long address)
 {
-	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
-				       __GFP_REPEAT | __GFP_ZERO);
+	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
 	if (!page)
 		return NULL;
 	if (!pgtable_page_ctor(page)) {
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index 4b7cef9e94e0..c1467ac59ce6 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -78,7 +78,7 @@ struct thread_info {
 
 #ifndef __ASSEMBLY__
 
-void arch_release_thread_info(struct thread_info *info);
+void arch_release_thread_stack(unsigned long *stack);
 
 /* How to get the thread information struct from C. */
 register unsigned long stack_pointer __asm__("sp");
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 6b705ccc9cc1..a465d8372edd 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -73,8 +73,9 @@ void arch_cpu_idle(void)
 /*
  * Release a thread_info structure
  */
-void arch_release_thread_info(struct thread_info *info)
+void arch_release_thread_stack(unsigned long *stack)
 {
+	struct thread_info *info = (void *)stack;
 	struct single_step_state *step_state = info->step_state;
 
 	if (step_state) {
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index 7bf2491a9c1f..c4d5bf841a7f 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -231,7 +231,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 struct page *pgtable_alloc_one(struct mm_struct *mm, unsigned long address,
 			       int order)
 {
-	gfp_t flags = GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO;
+	gfp_t flags = GFP_KERNEL|__GFP_ZERO;
 	struct page *p;
 	int i;
 
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index b2a2dff50b4e..e7437ec62710 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -204,7 +204,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
 	pte_t *pte;
 
-	pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	return pte;
 }
 
@@ -212,7 +212,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	struct page *pte;
 
-	pte = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte = alloc_page(GFP_KERNEL|__GFP_ZERO);
 	if (!pte)
 		return NULL;
 	if (!pgtable_page_ctor(pte)) {
diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h
index 2e02d1356fdf..26775793c204 100644
--- a/arch/unicore32/include/asm/pgalloc.h
+++ b/arch/unicore32/include/asm/pgalloc.h
@@ -28,7 +28,7 @@ extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd);
 #define pgd_alloc(mm)			get_pgd_slow(mm)
 #define pgd_free(mm, pgd)		free_pgd_slow(mm, pgd)
 
-#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 
 /*
  * Allocate one PTE table.
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0a7b885964ba..d9a94da0c29f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2439,6 +2439,15 @@ config PCI_CNB20LE_QUIRK
 
 source "drivers/pci/Kconfig"
 
+config ISA_BUS
+	bool "ISA-style bus support on modern systems" if EXPERT
+	select ISA_BUS_API
+	help
+	  Enables ISA-style drivers on modern systems. This is necessary to
+	  support PC/104 devices on X86_64 platforms.
+
+	  If unsure, say N.
+
 # x86_64 have no ISA slots, but can have ISA-style DMA.
 config ISA_DMA_API
 	bool "ISA-style DMA support" if (X86_64 && EXPERT)
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 700a9c6e6159..be8e688fa0d4 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -162,6 +162,9 @@ isoimage: $(obj)/bzImage
 	for i in lib lib64 share end ; do \
 		if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \
 			cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \
+			if [ -f /usr/$$i/syslinux/ldlinux.c32 ]; then \
+				cp /usr/$$i/syslinux/ldlinux.c32 $(obj)/isoimage ; \
+			fi ; \
 			break ; \
 		fi ; \
 		if [ $$i = end ] ; then exit 1 ; fi ; \
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 99c4bab123cd..e30eef4f29a6 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -714,7 +714,7 @@ static void cleanup_rapl_pmus(void)
 	int i;
 
 	for (i = 0; i < rapl_pmus->maxpkg; i++)
-		kfree(rapl_pmus->pmus + i);
+		kfree(rapl_pmus->pmus[i]);
 	kfree(rapl_pmus);
 }
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index b2625867ebd1..874e8bd64d1d 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2868,27 +2868,10 @@ static struct intel_uncore_type bdx_uncore_cbox = {
 	.format_group		= &hswep_uncore_cbox_format_group,
 };
 
-static struct intel_uncore_type bdx_uncore_sbox = {
-	.name			= "sbox",
-	.num_counters		= 4,
-	.num_boxes		= 4,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= HSWEP_S0_MSR_PMON_CTL0,
-	.perf_ctr		= HSWEP_S0_MSR_PMON_CTR0,
-	.event_mask		= HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
-	.box_ctl		= HSWEP_S0_MSR_PMON_BOX_CTL,
-	.msr_offset		= HSWEP_SBOX_MSR_OFFSET,
-	.ops			= &hswep_uncore_sbox_msr_ops,
-	.format_group		= &hswep_uncore_sbox_format_group,
-};
-
-#define BDX_MSR_UNCORE_SBOX	3
-
 static struct intel_uncore_type *bdx_msr_uncores[] = {
 	&bdx_uncore_ubox,
 	&bdx_uncore_cbox,
 	&hswep_uncore_pcu,
-	&bdx_uncore_sbox,
 	NULL,
 };
 
@@ -2897,10 +2880,6 @@ void bdx_uncore_cpu_init(void)
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 	uncore_msr_uncores = bdx_msr_uncores;
-
-	/* BDX-DE doesn't have SBOX */
-	if (boot_cpu_data.x86_model == 86)
-		uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
 }
 
 static struct intel_uncore_type bdx_uncore_ha = {
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
new file mode 100644
index 000000000000..6999f7d01a0d
--- /dev/null
+++ b/arch/x86/include/asm/intel-family.h
@@ -0,0 +1,68 @@
+#ifndef _ASM_X86_INTEL_FAMILY_H
+#define _ASM_X86_INTEL_FAMILY_H
+
+/*
+ * "Big Core" Processors (Branded as Core, Xeon, etc...)
+ *
+ * The "_X" parts are generally the EP and EX Xeons, or the
+ * "Extreme" ones, like Broadwell-E.
+ *
+ * Things ending in "2" are usually because we have no better
+ * name for them.  There's no processor called "WESTMERE2".
+ */
+
+#define INTEL_FAM6_CORE_YONAH		0x0E
+#define INTEL_FAM6_CORE2_MEROM		0x0F
+#define INTEL_FAM6_CORE2_MEROM_L	0x16
+#define INTEL_FAM6_CORE2_PENRYN		0x17
+#define INTEL_FAM6_CORE2_DUNNINGTON	0x1D
+
+#define INTEL_FAM6_NEHALEM		0x1E
+#define INTEL_FAM6_NEHALEM_EP		0x1A
+#define INTEL_FAM6_NEHALEM_EX		0x2E
+#define INTEL_FAM6_WESTMERE		0x25
+#define INTEL_FAM6_WESTMERE2		0x1F
+#define INTEL_FAM6_WESTMERE_EP		0x2C
+#define INTEL_FAM6_WESTMERE_EX		0x2F
+
+#define INTEL_FAM6_SANDYBRIDGE		0x2A
+#define INTEL_FAM6_SANDYBRIDGE_X	0x2D
+#define INTEL_FAM6_IVYBRIDGE		0x3A
+#define INTEL_FAM6_IVYBRIDGE_X		0x3E
+
+#define INTEL_FAM6_HASWELL_CORE		0x3C
+#define INTEL_FAM6_HASWELL_X		0x3F
+#define INTEL_FAM6_HASWELL_ULT		0x45
+#define INTEL_FAM6_HASWELL_GT3E		0x46
+
+#define INTEL_FAM6_BROADWELL_CORE	0x3D
+#define INTEL_FAM6_BROADWELL_XEON_D	0x56
+#define INTEL_FAM6_BROADWELL_GT3E	0x47
+#define INTEL_FAM6_BROADWELL_X		0x4F
+
+#define INTEL_FAM6_SKYLAKE_MOBILE	0x4E
+#define INTEL_FAM6_SKYLAKE_DESKTOP	0x5E
+#define INTEL_FAM6_SKYLAKE_X		0x55
+#define INTEL_FAM6_KABYLAKE_MOBILE	0x8E
+#define INTEL_FAM6_KABYLAKE_DESKTOP	0x9E
+
+/* "Small Core" Processors (Atom) */
+
+#define INTEL_FAM6_ATOM_PINEVIEW	0x1C
+#define INTEL_FAM6_ATOM_LINCROFT	0x26
+#define INTEL_FAM6_ATOM_PENWELL		0x27
+#define INTEL_FAM6_ATOM_CLOVERVIEW	0x35
+#define INTEL_FAM6_ATOM_CEDARVIEW	0x36
+#define INTEL_FAM6_ATOM_SILVERMONT1	0x37 /* BayTrail/BYT / Valleyview */
+#define INTEL_FAM6_ATOM_SILVERMONT2	0x4D /* Avaton/Rangely */
+#define INTEL_FAM6_ATOM_AIRMONT		0x4C /* CherryTrail / Braswell */
+#define INTEL_FAM6_ATOM_MERRIFIELD1	0x4A /* Tangier */
+#define INTEL_FAM6_ATOM_MERRIFIELD2	0x5A /* Annidale */
+#define INTEL_FAM6_ATOM_GOLDMONT	0x5C
+#define INTEL_FAM6_ATOM_DENVERTON	0x5F /* Goldmont Microserver */
+
+/* Xeon Phi */
+
+#define INTEL_FAM6_XEON_PHI_KNL		0x57 /* Knights Landing */
+
+#endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 4421b5da409d..d1d1e5094c28 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -38,12 +38,11 @@ typedef u8 kprobe_opcode_t;
 #define RELATIVECALL_OPCODE 0xe8
 #define RELATIVE_ADDR_SIZE 4
 #define MAX_STACK_SIZE 64
-#define MIN_STACK_SIZE(ADDR)					       \
-	(((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \
-			      THREAD_SIZE - (unsigned long)(ADDR)))    \
-	 ? (MAX_STACK_SIZE)					       \
-	 : (((unsigned long)current_thread_info()) +		       \
-	    THREAD_SIZE - (unsigned long)(ADDR)))
+#define CUR_STACK_SIZE(ADDR) \
+	(current_top_of_stack() - (unsigned long)(ADDR))
+#define MIN_STACK_SIZE(ADDR)				\
+	(MAX_STACK_SIZE < CUR_STACK_SIZE(ADDR) ?	\
+	 MAX_STACK_SIZE : CUR_STACK_SIZE(ADDR))
 
 #define flush_insn_slot(p)	do { } while (0)
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e0fbe7e70dc1..69e62862b622 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -27,6 +27,7 @@
 #include <linux/irqbypass.h>
 #include <linux/hyperv.h>
 
+#include <asm/apic.h>
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
 #include <asm/mtrr.h>
@@ -1368,4 +1369,14 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 
 static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
 
+static inline int kvm_cpu_get_apicid(int mps_cpu)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+	return __default_cpu_present_to_apicid(mps_cpu);
+#else
+	WARN_ON_ONCE(1);
+	return BAD_APICID;
+#endif
+}
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 7dc1d8fef7fd..b5fee97813cd 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -122,7 +122,7 @@ notrace static inline void native_write_msr(unsigned int msr,
 		     "2:\n"
 		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
 		     : : "c" (msr), "a"(low), "d" (high) : "memory");
-	if (msr_tracepoint_active(__tracepoint_read_msr))
+	if (msr_tracepoint_active(__tracepoint_write_msr))
 		do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
 }
 
@@ -141,7 +141,7 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
 		     : "c" (msr), "0" (low), "d" (high),
 		       [fault] "i" (-EIO)
 		     : "memory");
-	if (msr_tracepoint_active(__tracepoint_read_msr))
+	if (msr_tracepoint_active(__tracepoint_write_msr))
 		do_trace_write_msr(msr, ((u64)high << 32 | low), err);
 	return err;
 }
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index bf7f8b55b0f9..574c23cf761a 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -81,7 +81,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
 	struct page *page;
-	page = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
+	page = alloc_pages(GFP_KERNEL |  __GFP_ZERO, 0);
 	if (!page)
 		return NULL;
 	if (!pgtable_pmd_page_ctor(page)) {
@@ -125,7 +125,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+	return (pud_t *)get_zeroed_page(GFP_KERNEL);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 7c247e7404be..0944218af9e2 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -14,7 +14,7 @@ extern int kstack_depth_to_print;
 struct thread_info;
 struct stacktrace_ops;
 
-typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo,
+typedef unsigned long (*walk_stack_t)(struct task_struct *task,
 				      unsigned long *stack,
 				      unsigned long bp,
 				      const struct stacktrace_ops *ops,
@@ -23,13 +23,13 @@ typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo,
 				      int *graph);
 
 extern unsigned long
-print_context_stack(struct thread_info *tinfo,
+print_context_stack(struct task_struct *task,
 		    unsigned long *stack, unsigned long bp,
 		    const struct stacktrace_ops *ops, void *data,
 		    unsigned long *end, int *graph);
 
 extern unsigned long
-print_context_stack_bp(struct thread_info *tinfo,
+print_context_stack_bp(struct task_struct *task,
 		       unsigned long *stack, unsigned long bp,
 		       const struct stacktrace_ops *ops, void *data,
 		       unsigned long *end, int *graph);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 84e33ff5a6d5..446702ed99dc 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2588,8 +2588,8 @@ static struct resource * __init ioapic_setup_resources(void)
 		res[num].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 		snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i);
 		mem += IOAPIC_RESOURCE_NAME_SIZE;
+		ioapics[i].iomem_res = &res[num];
 		num++;
-		ioapics[i].iomem_res = res;
 	}
 
 	ioapic_resources = res;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c343a54bed39..f5c69d8974e1 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -674,14 +674,14 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 	u64 value;
 
 	/* re-enable TopologyExtensions if switched off by BIOS */
-	if ((c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
+	if ((c->x86_model >= 0x10) && (c->x86_model <= 0x6f) &&
 	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
 
 		if (msr_set_bit(0xc0011005, 54) > 0) {
 			rdmsrl(0xc0011005, value);
 			if (value & BIT_64(54)) {
 				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
-				pr_info(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
+				pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
 			}
 		}
 	}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 2bb25c3fe2e8..ef8017ca5ba9 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -42,16 +42,14 @@ void printk_address(unsigned long address)
 static void
 print_ftrace_graph_addr(unsigned long addr, void *data,
 			const struct stacktrace_ops *ops,
-			struct thread_info *tinfo, int *graph)
+			struct task_struct *task, int *graph)
 {
-	struct task_struct *task;
 	unsigned long ret_addr;
 	int index;
 
 	if (addr != (unsigned long)return_to_handler)
 		return;
 
-	task = tinfo->task;
 	index = task->curr_ret_stack;
 
 	if (!task->ret_stack || index < *graph)
@@ -68,7 +66,7 @@ print_ftrace_graph_addr(unsigned long addr, void *data,
 static inline void
 print_ftrace_graph_addr(unsigned long addr, void *data,
 			const struct stacktrace_ops *ops,
-			struct thread_info *tinfo, int *graph)
+			struct task_struct *task, int *graph)
 { }
 #endif
 
@@ -79,10 +77,10 @@ print_ftrace_graph_addr(unsigned long addr, void *data,
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
  */
 
-static inline int valid_stack_ptr(struct thread_info *tinfo,
+static inline int valid_stack_ptr(struct task_struct *task,
 			void *p, unsigned int size, void *end)
 {
-	void *t = tinfo;
+	void *t = task_stack_page(task);
 	if (end) {
 		if (p < end && p >= (end-THREAD_SIZE))
 			return 1;
@@ -93,14 +91,14 @@ static inline int valid_stack_ptr(struct thread_info *tinfo,
 }
 
 unsigned long
-print_context_stack(struct thread_info *tinfo,
+print_context_stack(struct task_struct *task,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data,
 		unsigned long *end, int *graph)
 {
 	struct stack_frame *frame = (struct stack_frame *)bp;
 
-	while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
+	while (valid_stack_ptr(task, stack, sizeof(*stack), end)) {
 		unsigned long addr;
 
 		addr = *stack;
@@ -112,7 +110,7 @@ print_context_stack(struct thread_info *tinfo,
 			} else {
 				ops->address(data, addr, 0);
 			}
-			print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
+			print_ftrace_graph_addr(addr, data, ops, task, graph);
 		}
 		stack++;
 	}
@@ -121,7 +119,7 @@ print_context_stack(struct thread_info *tinfo,
 EXPORT_SYMBOL_GPL(print_context_stack);
 
 unsigned long
-print_context_stack_bp(struct thread_info *tinfo,
+print_context_stack_bp(struct task_struct *task,
 		       unsigned long *stack, unsigned long bp,
 		       const struct stacktrace_ops *ops, void *data,
 		       unsigned long *end, int *graph)
@@ -129,7 +127,7 @@ print_context_stack_bp(struct thread_info *tinfo,
 	struct stack_frame *frame = (struct stack_frame *)bp;
 	unsigned long *ret_addr = &frame->return_address;
 
-	while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) {
+	while (valid_stack_ptr(task, ret_addr, sizeof(*ret_addr), end)) {
 		unsigned long addr = *ret_addr;
 
 		if (!__kernel_text_address(addr))
@@ -139,7 +137,7 @@ print_context_stack_bp(struct thread_info *tinfo,
 			break;
 		frame = frame->next_frame;
 		ret_addr = &frame->return_address;
-		print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
+		print_ftrace_graph_addr(addr, data, ops, task, graph);
 	}
 
 	return (unsigned long)frame;
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 464ffd69b92e..fef917e79b9d 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -61,15 +61,13 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		bp = stack_frame(task, regs);
 
 	for (;;) {
-		struct thread_info *context;
 		void *end_stack;
 
 		end_stack = is_hardirq_stack(stack, cpu);
 		if (!end_stack)
 			end_stack = is_softirq_stack(stack, cpu);
 
-		context = task_thread_info(task);
-		bp = ops->walk_stack(context, stack, bp, ops, data,
+		bp = ops->walk_stack(task, stack, bp, ops, data,
 				     end_stack, &graph);
 
 		/* Stop if not on irq stack */
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 5f1c6266eb30..d558a8a49016 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -153,7 +153,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		const struct stacktrace_ops *ops, void *data)
 {
 	const unsigned cpu = get_cpu();
-	struct thread_info *tinfo;
 	unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
 	unsigned long dummy;
 	unsigned used = 0;
@@ -179,7 +178,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	 * current stack address. If the stacks consist of nested
 	 * exceptions
 	 */
-	tinfo = task_thread_info(task);
 	while (!done) {
 		unsigned long *stack_end;
 		enum stack_type stype;
@@ -202,7 +200,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 			if (ops->stack(data, id) < 0)
 				break;
 
-			bp = ops->walk_stack(tinfo, stack, bp, ops,
+			bp = ops->walk_stack(task, stack, bp, ops,
 					     data, stack_end, &graph);
 			ops->stack(data, "<EOE>");
 			/*
@@ -218,7 +216,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 
 			if (ops->stack(data, "IRQ") < 0)
 				break;
-			bp = ops->walk_stack(tinfo, stack, bp,
+			bp = ops->walk_stack(task, stack, bp,
 				     ops, data, stack_end, &graph);
 			/*
 			 * We link to the next stack (which would be
@@ -240,7 +238,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	/*
 	 * This handles the process stack:
 	 */
-	bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
+	bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph);
 	put_cpu();
 }
 EXPORT_SYMBOL(dump_trace);
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 4d38416e2a7f..04f89caef9c4 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -57,7 +57,7 @@
 # error "Need more than one PGD for the ESPFIX hack"
 #endif
 
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 
 /* This contains the *bottom* address of the espfix stack */
 DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 38da8f29a9c8..c627bf8d98ad 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -130,11 +130,9 @@ void irq_ctx_init(int cpu)
 
 void do_softirq_own_stack(void)
 {
-	struct thread_info *curstk;
 	struct irq_stack *irqstk;
 	u32 *isp, *prev_esp;
 
-	curstk = current_stack();
 	irqstk = __this_cpu_read(softirq_stack);
 
 	/* build the stack frame on the softirq stack */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 38cf7a741250..7847e5c0e0b5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -961,7 +961,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		 * normal page fault.
 		 */
 		regs->ip = (unsigned long)cur->addr;
+		/*
+		 * Trap flag (TF) has been set here because this fault
+		 * happened where the single stepping will be done.
+		 * So clear it by resetting the current kprobe:
+		 */
+		regs->flags &= ~X86_EFLAGS_TF;
+
+		/*
+		 * If the TF flag was set before the kprobe hit,
+		 * don't touch it:
+		 */
 		regs->flags |= kcb->kprobe_old_flags;
+
 		if (kcb->kprobe_status == KPROBE_REENTER)
 			restore_previous_kprobe(kcb);
 		else
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d1590486204a..00f03d82e69a 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -96,6 +96,12 @@ static inline void cond_local_irq_disable(struct pt_regs *regs)
 		local_irq_disable();
 }
 
+/*
+ * In IST context, we explicitly disable preemption.  This serves two
+ * purposes: it makes it much less likely that we would accidentally
+ * schedule in IST context and it will force a warning if we somehow
+ * manage to schedule by accident.
+ */
 void ist_enter(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
@@ -110,13 +116,7 @@ void ist_enter(struct pt_regs *regs)
 		rcu_nmi_enter();
 	}
 
-	/*
-	 * We are atomic because we're on the IST stack; or we're on
-	 * x86_32, in which case we still shouldn't schedule; or we're
-	 * on x86_64 and entered from user mode, in which case we're
-	 * still atomic unless ist_begin_non_atomic is called.
-	 */
-	preempt_count_add(HARDIRQ_OFFSET);
+	preempt_disable();
 
 	/* This code is a bit fragile.  Test it. */
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
@@ -124,7 +124,7 @@ void ist_enter(struct pt_regs *regs)
 
 void ist_exit(struct pt_regs *regs)
 {
-	preempt_count_sub(HARDIRQ_OFFSET);
+	preempt_enable_no_resched();
 
 	if (!user_mode(regs))
 		rcu_nmi_exit();
@@ -155,7 +155,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
 	BUG_ON((unsigned long)(current_top_of_stack() -
 			       current_stack_pointer()) >= THREAD_SIZE);
 
-	preempt_count_sub(HARDIRQ_OFFSET);
+	preempt_enable_no_resched();
 }
 
 /**
@@ -165,7 +165,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
  */
 void ist_end_non_atomic(void)
 {
-	preempt_count_add(HARDIRQ_OFFSET);
+	preempt_disable();
 }
 
 static nokprobe_inline int
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 769af907f824..7597b42a8a88 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -181,19 +181,22 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 			     struct kvm_cpuid_entry __user *entries)
 {
 	int r, i;
-	struct kvm_cpuid_entry *cpuid_entries;
+	struct kvm_cpuid_entry *cpuid_entries = NULL;
 
 	r = -E2BIG;
 	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
 		goto out;
 	r = -ENOMEM;
-	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent);
-	if (!cpuid_entries)
-		goto out;
-	r = -EFAULT;
-	if (copy_from_user(cpuid_entries, entries,
-			   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
-		goto out_free;
+	if (cpuid->nent) {
+		cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) *
+					cpuid->nent);
+		if (!cpuid_entries)
+			goto out;
+		r = -EFAULT;
+		if (copy_from_user(cpuid_entries, entries,
+				   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
+			goto out;
+	}
 	for (i = 0; i < cpuid->nent; i++) {
 		vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
 		vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
@@ -212,9 +215,8 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 	kvm_x86_ops->cpuid_update(vcpu);
 	r = kvm_update_cpuid(vcpu);
 
-out_free:
-	vfree(cpuid_entries);
 out:
+	vfree(cpuid_entries);
 	return r;
 }
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 24e800116ab4..def97b3a392b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -336,12 +336,12 @@ static gfn_t pse36_gfn_delta(u32 gpte)
 #ifdef CONFIG_X86_64
 static void __set_spte(u64 *sptep, u64 spte)
 {
-	*sptep = spte;
+	WRITE_ONCE(*sptep, spte);
 }
 
 static void __update_clear_spte_fast(u64 *sptep, u64 spte)
 {
-	*sptep = spte;
+	WRITE_ONCE(*sptep, spte);
 }
 
 static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
@@ -390,7 +390,7 @@ static void __set_spte(u64 *sptep, u64 spte)
 	 */
 	smp_wmb();
 
-	ssptep->spte_low = sspte.spte_low;
+	WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
 }
 
 static void __update_clear_spte_fast(u64 *sptep, u64 spte)
@@ -400,7 +400,7 @@ static void __update_clear_spte_fast(u64 *sptep, u64 spte)
 	ssptep = (union split_spte *)sptep;
 	sspte = (union split_spte)spte;
 
-	ssptep->spte_low = sspte.spte_low;
+	WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
 
 	/*
 	 * If we map the spte from present to nonpresent, we should clear
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1163e8173e5a..16ef31b87452 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -238,7 +238,9 @@ module_param(nested, int, S_IRUGO);
 
 /* enable / disable AVIC */
 static int avic;
+#ifdef CONFIG_X86_LOCAL_APIC
 module_param(avic, int, S_IRUGO);
+#endif
 
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
@@ -981,11 +983,14 @@ static __init int svm_hardware_setup(void)
 	} else
 		kvm_disable_tdp();
 
-	if (avic && (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC)))
-		avic = false;
-
-	if (avic)
-		pr_info("AVIC enabled\n");
+	if (avic) {
+		if (!npt_enabled ||
+		    !boot_cpu_has(X86_FEATURE_AVIC) ||
+		    !IS_ENABLED(CONFIG_X86_LOCAL_APIC))
+			avic = false;
+		else
+			pr_info("AVIC enabled\n");
+	}
 
 	return 0;
 
@@ -1324,7 +1329,7 @@ free_avic:
 static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
 {
 	u64 entry;
-	int h_physical_id = __default_cpu_present_to_apicid(vcpu->cpu);
+	int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (!kvm_vcpu_apicv_active(vcpu))
@@ -1349,7 +1354,7 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	u64 entry;
 	/* ID = 0xff (broadcast), ID > 0xff (reserved) */
-	int h_physical_id = __default_cpu_present_to_apicid(cpu);
+	int h_physical_id = kvm_cpu_get_apicid(cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (!kvm_vcpu_apicv_active(vcpu))
@@ -4236,7 +4241,7 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 
 	if (avic_vcpu_is_running(vcpu))
 		wrmsrl(SVM_AVIC_DOORBELL,
-		       __default_cpu_present_to_apicid(vcpu->cpu));
+		       kvm_cpu_get_apicid(vcpu->cpu));
 	else
 		kvm_vcpu_wake_up(vcpu);
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fb93010beaa4..003618e324ce 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2072,7 +2072,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	unsigned int dest;
 
 	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP))
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
 		return;
 
 	do {
@@ -2180,7 +2181,8 @@ static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
 	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP))
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
 		return;
 
 	/* Set SN when the vCPU is preempted */
@@ -10714,7 +10716,8 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
 	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP))
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
 		return 0;
 
 	vcpu->pre_pcpu = vcpu->cpu;
@@ -10780,7 +10783,8 @@ static void vmx_post_block(struct kvm_vcpu *vcpu)
 	unsigned long flags;
 
 	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP))
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
 		return;
 
 	do {
@@ -10833,7 +10837,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 	int idx, ret = -EINVAL;
 
 	if (!kvm_arch_has_assigned_device(kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP))
+		!irq_remapping_cap(IRQ_POSTING_CAP) ||
+		!kvm_vcpu_apicv_active(kvm->vcpus[0]))
 		return 0;
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c805cf494154..902d9da12392 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2314,6 +2314,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_AMD64_NB_CFG:
 	case MSR_FAM10H_MMIO_CONF_BASE:
 	case MSR_AMD64_BU_CFG2:
+	case MSR_IA32_PERF_CTL:
 		msr_info->data = 0;
 		break;
 	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
@@ -2972,6 +2973,10 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 			      | KVM_VCPUEVENT_VALID_SMM))
 		return -EINVAL;
 
+	if (events->exception.injected &&
+	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
+		return -EINVAL;
+
 	process_nmi(vcpu);
 	vcpu->arch.exception.pending = events->exception.injected;
 	vcpu->arch.exception.nr = events->exception.nr;
@@ -3036,6 +3041,11 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 	if (dbgregs->flags)
 		return -EINVAL;
 
+	if (dbgregs->dr6 & ~0xffffffffull)
+		return -EINVAL;
+	if (dbgregs->dr7 & ~0xffffffffull)
+		return -EINVAL;
+
 	memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
 	kvm_update_dr0123(vcpu);
 	vcpu->arch.dr6 = dbgregs->dr6;
@@ -7815,7 +7825,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 
 	slot = id_to_memslot(slots, id);
 	if (size) {
-		if (WARN_ON(slot->npages))
+		if (slot->npages)
 			return -EEXIST;
 
 		/*
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 4eb287e25043..aa0ff4b02a96 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -6,7 +6,7 @@
 #include <asm/fixmap.h>
 #include <asm/mtrr.h>
 
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO
 
 #ifdef CONFIG_HIGHPTE
 #define PGALLOC_USER_GFP __GFP_HIGHMEM
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 6e7242be1c87..b226b3f497f1 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -139,7 +139,7 @@ int __init efi_alloc_page_tables(void)
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return 0;
 
-	gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO;
+	gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO;
 	efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
 	if (!efi_pgd)
 		return -ENOMEM;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 478a2de543a5..67433714b791 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1113,7 +1113,7 @@ static void __init xen_cleanhighmap(unsigned long vaddr,
 
 	/* NOTE: The loop is more greedy than the cleanup_highmap variant.
 	 * We include the PMD passed in on _both_ boundaries. */
-	for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+	for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD));
 			pmd++, vaddr += PMD_SIZE) {
 		if (pmd_none(*pmd))
 			continue;
@@ -1551,41 +1551,6 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 #endif
 }
 
-#ifdef CONFIG_X86_32
-static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
-{
-	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
-	if (pte_val_ma(*ptep) & _PAGE_PRESENT)
-		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
-			       pte_val_ma(pte));
-
-	return pte;
-}
-#else /* CONFIG_X86_64 */
-static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
-{
-	unsigned long pfn;
-
-	if (xen_feature(XENFEAT_writable_page_tables) ||
-	    xen_feature(XENFEAT_auto_translated_physmap) ||
-	    xen_start_info->mfn_list >= __START_KERNEL_map)
-		return pte;
-
-	/*
-	 * Pages belonging to the initial p2m list mapped outside the default
-	 * address range must be mapped read-only. This region contains the
-	 * page tables for mapping the p2m list, too, and page tables MUST be
-	 * mapped read-only.
-	 */
-	pfn = pte_pfn(pte);
-	if (pfn >= xen_start_info->first_p2m_pfn &&
-	    pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
-		pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW);
-
-	return pte;
-}
-#endif /* CONFIG_X86_64 */
-
 /*
  * Init-time set_pte while constructing initial pagetables, which
  * doesn't allow RO page table pages to be remapped RW.
@@ -1600,13 +1565,37 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
  * so always write the PTE directly and rely on Xen trapping and
  * emulating any updates as necessary.
  */
-static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
+__visible pte_t xen_make_pte_init(pteval_t pte)
 {
-	if (pte_mfn(pte) != INVALID_P2M_ENTRY)
-		pte = mask_rw_pte(ptep, pte);
-	else
-		pte = __pte_ma(0);
+#ifdef CONFIG_X86_64
+	unsigned long pfn;
+
+	/*
+	 * Pages belonging to the initial p2m list mapped outside the default
+	 * address range must be mapped read-only. This region contains the
+	 * page tables for mapping the p2m list, too, and page tables MUST be
+	 * mapped read-only.
+	 */
+	pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+	if (xen_start_info->mfn_list < __START_KERNEL_map &&
+	    pfn >= xen_start_info->first_p2m_pfn &&
+	    pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
+		pte &= ~_PAGE_RW;
+#endif
+	pte = pte_pfn_to_mfn(pte);
+	return native_make_pte(pte);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init);
 
+static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
+{
+#ifdef CONFIG_X86_32
+	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
+	if (pte_mfn(pte) != INVALID_P2M_ENTRY
+	    && pte_val_ma(*ptep) & _PAGE_PRESENT)
+		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
+			       pte_val_ma(pte));
+#endif
 	native_set_pte(ptep, pte);
 }
 
@@ -2407,6 +2396,7 @@ static void __init xen_post_allocator_init(void)
 	pv_mmu_ops.alloc_pud = xen_alloc_pud;
 	pv_mmu_ops.release_pud = xen_release_pud;
 #endif
+	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte);
 
 #ifdef CONFIG_X86_64
 	pv_mmu_ops.write_cr3 = &xen_write_cr3;
@@ -2455,7 +2445,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.pte_val = PV_CALLEE_SAVE(xen_pte_val),
 	.pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
 
-	.make_pte = PV_CALLEE_SAVE(xen_make_pte),
+	.make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
 	.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
 
 #ifdef CONFIG_X86_PAE
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index cab9f766bb06..dd2a49a8aacc 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -182,7 +182,7 @@ static void * __ref alloc_p2m_page(void)
 	if (unlikely(!slab_is_available()))
 		return alloc_bootmem_align(PAGE_SIZE, PAGE_SIZE);
 
-	return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
+	return (void *)__get_free_page(GFP_KERNEL);
 }
 
 static void __ref free_p2m_page(void *p)
diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h
index d38eb9237e64..1065bc8bcae5 100644
--- a/arch/xtensa/include/asm/pgalloc.h
+++ b/arch/xtensa/include/asm/pgalloc.h
@@ -44,7 +44,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 	pte_t *ptep;
 	int i;
 
-	ptep = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+	ptep = (pte_t *)__get_free_page(GFP_KERNEL);
 	if (!ptep)
 		return NULL;
 	for (i = 0; i < 1024; i++)
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 23d7f301a196..9e29dc351695 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -113,6 +113,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		ret = submit_bio_wait(type, bio);
 		if (ret == -EOPNOTSUPP)
 			ret = 0;
+		bio_put(bio);
 	}
 	blk_finish_plug(&plug);
 
@@ -165,8 +166,10 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		}
 	}
 
-	if (bio)
+	if (bio) {
 		ret = submit_bio_wait(REQ_WRITE | REQ_WRITE_SAME, bio);
+		bio_put(bio);
+	}
 	return ret != -EOPNOTSUPP ? ret : 0;
 }
 EXPORT_SYMBOL(blkdev_issue_write_same);
@@ -206,8 +209,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		}
 	}
 
-	if (bio)
-		return submit_bio_wait(WRITE, bio);
+	if (bio) {
+		ret = submit_bio_wait(WRITE, bio);
+		bio_put(bio);
+		return ret;
+	}
 	return 0;
 }
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 29cbc1b5fbdb..f9b9049b1284 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1262,12 +1262,9 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(q, &bio, q->bio_split);
 
-	if (!is_flush_fua && !blk_queue_nomerges(q)) {
-		if (blk_attempt_plug_merge(q, bio, &request_count,
-					   &same_queue_rq))
-			return BLK_QC_T_NONE;
-	} else
-		request_count = blk_plug_queued_count(q);
+	if (!is_flush_fua && !blk_queue_nomerges(q) &&
+	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
+		return BLK_QC_T_NONE;
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
@@ -1358,9 +1355,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(q, &bio, q->bio_split);
 
-	if (!is_flush_fua && !blk_queue_nomerges(q) &&
-	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
-		return BLK_QC_T_NONE;
+	if (!is_flush_fua && !blk_queue_nomerges(q)) {
+		if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
+			return BLK_QC_T_NONE;
+	} else
+		request_count = blk_plug_queued_count(q);
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 43fe85f20d57..7097a3395b25 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -455,6 +455,7 @@ static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = {
 	[CRYPTO_MSG_NEWALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_DELALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_UPDATEALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
+	[CRYPTO_MSG_GETALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_DELRNG	- CRYPTO_MSG_BASE] = 0,
 };
 
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 0d92d0f915e9..c7ba948d253c 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -331,15 +331,6 @@ static int acpi_processor_get_info(struct acpi_device *device)
 		pr->throttling.duty_width = acpi_gbl_FADT.duty_width;
 
 		pr->pblk = object.processor.pblk_address;
-
-		/*
-		 * We don't care about error returns - we just try to mark
-		 * these reserved so that nobody else is confused into thinking
-		 * that this region might be unused..
-		 *
-		 * (In particular, allocating the IO range for Cardbus)
-		 */
-		request_region(pr->throttling.address, 6, "ACPI CPU throttle");
 	}
 
 	/*
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 3d5b8a099351..c1d138e128cb 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -754,7 +754,8 @@ static int acpi_video_bqc_quirk(struct acpi_video_device *device,
 }
 
 int acpi_video_get_levels(struct acpi_device *device,
-			  struct acpi_video_device_brightness **dev_br)
+			  struct acpi_video_device_brightness **dev_br,
+			  int *pmax_level)
 {
 	union acpi_object *obj = NULL;
 	int i, max_level = 0, count = 0, level_ac_battery = 0;
@@ -841,6 +842,8 @@ int acpi_video_get_levels(struct acpi_device *device,
 
 	br->count = count;
 	*dev_br = br;
+	if (pmax_level)
+		*pmax_level = max_level;
 
 out:
 	kfree(obj);
@@ -869,7 +872,7 @@ acpi_video_init_brightness(struct acpi_video_device *device)
 	struct acpi_video_device_brightness *br = NULL;
 	int result = -EINVAL;
 
-	result = acpi_video_get_levels(device->dev, &br);
+	result = acpi_video_get_levels(device->dev, &br, &max_level);
 	if (result)
 		return result;
 	device->brightness = br;
@@ -1737,7 +1740,7 @@ static void acpi_video_run_bcl_for_osi(struct acpi_video_bus *video)
 
 	mutex_lock(&video->device_list_lock);
 	list_for_each_entry(dev, &video->video_device_list, entry) {
-		if (!acpi_video_device_lcd_query_levels(dev, &levels))
+		if (!acpi_video_device_lcd_query_levels(dev->dev->handle, &levels))
 			kfree(levels);
 	}
 	mutex_unlock(&video->device_list_lock);
diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c
index a1d177d58254..21932d640a41 100644
--- a/drivers/acpi/acpica/exconfig.c
+++ b/drivers/acpi/acpica/exconfig.c
@@ -108,7 +108,9 @@ acpi_ex_add_table(u32 table_index,
 
 	/* Add the table to the namespace */
 
+	acpi_ex_exit_interpreter();
 	status = acpi_ns_load_table(table_index, parent_node);
+	acpi_ex_enter_interpreter();
 	if (ACPI_FAILURE(status)) {
 		acpi_ut_remove_reference(obj_desc);
 		*ddb_handle = NULL;
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index 0f18dbc9a37f..3b7fb99362b6 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -83,27 +83,22 @@ acpi_hw_write_multiple(u32 value,
 static u8
 acpi_hw_get_access_bit_width(struct acpi_generic_address *reg, u8 max_bit_width)
 {
-	u64 address;
-
 	if (!reg->access_width) {
+		if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
+			max_bit_width = 32;
+		}
+
 		/*
 		 * Detect old register descriptors where only the bit_width field
-		 * makes senses. The target address is copied to handle possible
-		 * alignment issues.
+		 * makes senses.
 		 */
-		ACPI_MOVE_64_TO_64(&address, &reg->address);
-		if (!reg->bit_offset && reg->bit_width &&
+		if (reg->bit_width < max_bit_width &&
+		    !reg->bit_offset && reg->bit_width &&
 		    ACPI_IS_POWER_OF_TWO(reg->bit_width) &&
-		    ACPI_IS_ALIGNED(reg->bit_width, 8) &&
-		    ACPI_IS_ALIGNED(address, reg->bit_width)) {
+		    ACPI_IS_ALIGNED(reg->bit_width, 8)) {
 			return (reg->bit_width);
-		} else {
-			if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
-				return (32);
-			} else {
-				return (max_bit_width);
-			}
 		}
+		return (max_bit_width);
 	} else {
 		return (1 << (reg->access_width + 2));
 	}
@@ -311,12 +306,6 @@ acpi_status acpi_hw_read(u32 *value, struct acpi_generic_address *reg)
 acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg)
 {
 	u64 address;
-	u8 access_width;
-	u32 bit_width;
-	u8 bit_offset;
-	u64 value64;
-	u32 new_value32, old_value32;
-	u8 index;
 	acpi_status status;
 
 	ACPI_FUNCTION_NAME(hw_write);
@@ -328,145 +317,23 @@ acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg)
 		return (status);
 	}
 
-	/* Convert access_width into number of bits based */
-
-	access_width = acpi_hw_get_access_bit_width(reg, 32);
-	bit_width = reg->bit_offset + reg->bit_width;
-	bit_offset = reg->bit_offset;
-
 	/*
 	 * Two address spaces supported: Memory or IO. PCI_Config is
 	 * not supported here because the GAS structure is insufficient
 	 */
-	index = 0;
-	while (bit_width) {
-		/*
-		 * Use offset style bit reads because "Index * AccessWidth" is
-		 * ensured to be less than 32-bits by acpi_hw_validate_register().
-		 */
-		new_value32 = ACPI_GET_BITS(&value, index * access_width,
-					    ACPI_MASK_BITS_ABOVE_32
-					    (access_width));
-
-		if (bit_offset >= access_width) {
-			bit_offset -= access_width;
-		} else {
-			/*
-			 * Use offset style bit masks because access_width is ensured
-			 * to be less than 32-bits by acpi_hw_validate_register() and
-			 * bit_offset/bit_width is less than access_width here.
-			 */
-			if (bit_offset) {
-				new_value32 &= ACPI_MASK_BITS_BELOW(bit_offset);
-			}
-			if (bit_width < access_width) {
-				new_value32 &= ACPI_MASK_BITS_ABOVE(bit_width);
-			}
-
-			if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
-				if (bit_offset || bit_width < access_width) {
-					/*
-					 * Read old values in order not to modify the bits that
-					 * are beyond the register bit_width/bit_offset setting.
-					 */
-					status =
-					    acpi_os_read_memory((acpi_physical_address)
-								address +
-								index *
-								ACPI_DIV_8
-								(access_width),
-								&value64,
-								access_width);
-					old_value32 = (u32)value64;
-
-					/*
-					 * Use offset style bit masks because access_width is
-					 * ensured to be less than 32-bits by
-					 * acpi_hw_validate_register() and bit_offset/bit_width is
-					 * less than access_width here.
-					 */
-					if (bit_offset) {
-						old_value32 &=
-						    ACPI_MASK_BITS_ABOVE
-						    (bit_offset);
-						bit_offset = 0;
-					}
-					if (bit_width < access_width) {
-						old_value32 &=
-						    ACPI_MASK_BITS_BELOW
-						    (bit_width);
-					}
-
-					new_value32 |= old_value32;
-				}
-
-				value64 = (u64)new_value32;
-				status =
-				    acpi_os_write_memory((acpi_physical_address)
-							 address +
-							 index *
-							 ACPI_DIV_8
-							 (access_width),
-							 value64, access_width);
-			} else {	/* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
-
-				if (bit_offset || bit_width < access_width) {
-					/*
-					 * Read old values in order not to modify the bits that
-					 * are beyond the register bit_width/bit_offset setting.
-					 */
-					status =
-					    acpi_hw_read_port((acpi_io_address)
-							      address +
-							      index *
-							      ACPI_DIV_8
-							      (access_width),
-							      &old_value32,
-							      access_width);
-
-					/*
-					 * Use offset style bit masks because access_width is
-					 * ensured to be less than 32-bits by
-					 * acpi_hw_validate_register() and bit_offset/bit_width is
-					 * less than access_width here.
-					 */
-					if (bit_offset) {
-						old_value32 &=
-						    ACPI_MASK_BITS_ABOVE
-						    (bit_offset);
-						bit_offset = 0;
-					}
-					if (bit_width < access_width) {
-						old_value32 &=
-						    ACPI_MASK_BITS_BELOW
-						    (bit_width);
-					}
-
-					new_value32 |= old_value32;
-				}
-
-				status = acpi_hw_write_port((acpi_io_address)
-							    address +
-							    index *
-							    ACPI_DIV_8
-							    (access_width),
-							    new_value32,
-							    access_width);
-			}
-		}
-
-		/*
-		 * Index * access_width is ensured to be less than 32-bits by
-		 * acpi_hw_validate_register().
-		 */
-		bit_width -=
-		    bit_width > access_width ? access_width : bit_width;
-		index++;
+	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
+		status = acpi_os_write_memory((acpi_physical_address)
+					      address, (u64)value,
+					      reg->bit_width);
+	} else {		/* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
+
+		status = acpi_hw_write_port((acpi_io_address)
+					    address, value, reg->bit_width);
 	}
 
 	ACPI_DEBUG_PRINT((ACPI_DB_IO,
 			  "Wrote: %8.8X width %2d   to %8.8X%8.8X (%s)\n",
-			  value, access_width, ACPI_FORMAT_UINT64(address),
+			  value, reg->bit_width, ACPI_FORMAT_UINT64(address),
 			  acpi_ut_get_region_name(reg->space_id)));
 
 	return (status);
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index f631a47724f0..1783cd7e1446 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -47,6 +47,7 @@
 #include "acparser.h"
 #include "acdispat.h"
 #include "actables.h"
+#include "acinterp.h"
 
 #define _COMPONENT          ACPI_NAMESPACE
 ACPI_MODULE_NAME("nsparse")
@@ -170,6 +171,8 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
 
 	ACPI_FUNCTION_TRACE(ns_parse_table);
 
+	acpi_ex_enter_interpreter();
+
 	/*
 	 * AML Parse, pass 1
 	 *
@@ -185,7 +188,7 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
 	status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS1,
 					    table_index, start_node);
 	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
+		goto error_exit;
 	}
 
 	/*
@@ -201,8 +204,10 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
 	status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS2,
 					    table_index, start_node);
 	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
+		goto error_exit;
 	}
 
+error_exit:
+	acpi_ex_exit_interpreter();
 	return_ACPI_STATUS(status);
 }
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 31e8da648fff..262ca31b86d9 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1051,7 +1051,7 @@ static int __init acpi_bus_init(void)
 	 * Maybe EC region is required at bus_scan/acpi_get_devices. So it
 	 * is necessary to enable it as early as possible.
 	 */
-	acpi_boot_ec_enable();
+	acpi_ec_dsdt_probe();
 
 	printk(KERN_INFO PREFIX "Interpreter enabled\n");
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 0e70181f150c..73c76d646064 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1446,10 +1446,30 @@ ec_parse_io_ports(struct acpi_resource *resource, void *context)
 	return AE_OK;
 }
 
-int __init acpi_boot_ec_enable(void)
+static const struct acpi_device_id ec_device_ids[] = {
+	{"PNP0C09", 0},
+	{"", 0},
+};
+
+int __init acpi_ec_dsdt_probe(void)
 {
-	if (!boot_ec)
+	acpi_status status;
+
+	if (boot_ec)
 		return 0;
+
+	/*
+	 * Finding EC from DSDT if there is no ECDT EC available. When this
+	 * function is invoked, ACPI tables have been fully loaded, we can
+	 * walk namespace now.
+	 */
+	boot_ec = make_acpi_ec();
+	if (!boot_ec)
+		return -ENOMEM;
+	status = acpi_get_devices(ec_device_ids[0].id,
+				  ec_parse_device, boot_ec, NULL);
+	if (ACPI_FAILURE(status) || !boot_ec->handle)
+		return -ENODEV;
 	if (!ec_install_handlers(boot_ec)) {
 		first_ec = boot_ec;
 		return 0;
@@ -1457,11 +1477,6 @@ int __init acpi_boot_ec_enable(void)
 	return -EFAULT;
 }
 
-static const struct acpi_device_id ec_device_ids[] = {
-	{"PNP0C09", 0},
-	{"", 0},
-};
-
 #if 0
 /*
  * Some EC firmware variations refuses to respond QR_EC when SCI_EVT is not
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 9bb0773d39bf..27cc7feabfe4 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -181,7 +181,7 @@ typedef int (*acpi_ec_query_func) (void *data);
 
 int acpi_ec_init(void);
 int acpi_ec_ecdt_probe(void);
-int acpi_boot_ec_enable(void);
+int acpi_ec_dsdt_probe(void);
 void acpi_ec_block_transactions(void);
 void acpi_ec_unblock_transactions(void);
 void acpi_ec_unblock_transactions_early(void);
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index f170d746336d..c72e64893d03 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -676,6 +676,15 @@ static int acpi_processor_get_throttling_fadt(struct acpi_processor *pr)
 	if (!pr->flags.throttling)
 		return -ENODEV;
 
+	/*
+	 * We don't care about error returns - we just try to mark
+	 * these reserved so that nobody else is confused into thinking
+	 * that this region might be unused..
+	 *
+	 * (In particular, allocating the IO range for Cardbus)
+	 */
+	request_region(pr->throttling.address, 6, "ACPI CPU throttle");
+
 	pr->throttling.state = 0;
 
 	duty_mask = pr->throttling.state_count - 1;
diff --git a/drivers/ata/ahci_seattle.c b/drivers/ata/ahci_seattle.c
index 6e702ab57220..1d31c0c0fc20 100644
--- a/drivers/ata/ahci_seattle.c
+++ b/drivers/ata/ahci_seattle.c
@@ -137,7 +137,7 @@ static const struct ata_port_info *ahci_seattle_get_port_info(
 	u32 val;
 
 	plat_data = devm_kzalloc(dev, sizeof(*plat_data), GFP_KERNEL);
-	if (IS_ERR(plat_data))
+	if (!plat_data)
 		return &ahci_port_info;
 
 	plat_data->sgpio_ctrl = devm_ioremap_resource(dev,
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 61dc7a99e89a..c6f017458958 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -606,7 +606,7 @@ void ata_scsi_error(struct Scsi_Host *host)
 	ata_scsi_port_error_handler(host, ap);
 
 	/* finish or retry handled scmd's and clean up */
-	WARN_ON(host->host_failed || !list_empty(&eh_work_q));
+	WARN_ON(!list_empty(&eh_work_q));
 
 	DPRINTK("EXIT\n");
 }
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index bd74ee555278..745489a1c86a 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -986,7 +986,7 @@ static inline void mv_write_cached_reg(void __iomem *addr, u32 *old, u32 new)
 		 * Looks like a lot of fuss, but it avoids an unnecessary
 		 * +1 usec read-after-write delay for unaffected registers.
 		 */
-		laddr = (long)addr & 0xffff;
+		laddr = (unsigned long)addr & 0xffff;
 		if (laddr >= 0x300 && laddr <= 0x33c) {
 			laddr &= 0x000f;
 			if (laddr == 0x4 || laddr == 0xc) {
diff --git a/drivers/atm/horizon.c b/drivers/atm/horizon.c
index 527bbd595e37..5fc81e240c24 100644
--- a/drivers/atm/horizon.c
+++ b/drivers/atm/horizon.c
@@ -2795,9 +2795,7 @@ static int hrz_probe(struct pci_dev *pci_dev,
 	dev->atm_dev->ci_range.vpi_bits = vpi_bits;
 	dev->atm_dev->ci_range.vci_bits = 10-vpi_bits;
 
-	init_timer(&dev->housekeeping);
-	dev->housekeeping.function = do_housekeeping;
-	dev->housekeeping.data = (unsigned long) dev;
+	setup_timer(&dev->housekeeping, do_housekeeping, (unsigned long) dev);
 	mod_timer(&dev->housekeeping, jiffies);
 
 out:
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 6b2a84e7f2be..2609ba20b396 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
 obj-y			+= power/
 obj-$(CONFIG_HAS_DMA)	+= dma-mapping.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
-obj-$(CONFIG_ISA)	+= isa.o
+obj-$(CONFIG_ISA_BUS_API)	+= isa.o
 obj-$(CONFIG_FW_LOADER)	+= firmware_class.o
 obj-$(CONFIG_NUMA)	+= node.o
 obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o
diff --git a/drivers/base/isa.c b/drivers/base/isa.c
index 91dba65d7264..cd6ccdcf9df0 100644
--- a/drivers/base/isa.c
+++ b/drivers/base/isa.c
@@ -180,4 +180,4 @@ static int __init isa_bus_init(void)
 	return error;
 }
 
-device_initcall(isa_bus_init);
+postcore_initcall(isa_bus_init);
diff --git a/drivers/base/module.c b/drivers/base/module.c
index db930d3ee312..2a215780eda2 100644
--- a/drivers/base/module.c
+++ b/drivers/base/module.c
@@ -24,10 +24,12 @@ static char *make_driver_name(struct device_driver *drv)
 
 static void module_create_drivers_dir(struct module_kobject *mk)
 {
-	if (!mk || mk->drivers_dir)
-		return;
+	static DEFINE_MUTEX(drivers_dir_mutex);
 
-	mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj);
+	mutex_lock(&drivers_dir_mutex);
+	if (mk && !mk->drivers_dir)
+		mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj);
+	mutex_unlock(&drivers_dir_mutex);
 }
 
 void module_add_driver(struct module *mod, struct device_driver *drv)
diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c
index 83d6e7ba1a34..8c3434bdb26d 100644
--- a/drivers/base/power/opp/cpu.c
+++ b/drivers/base/power/opp/cpu.c
@@ -211,7 +211,7 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
 		}
 
 		/* Mark opp-table as multiple CPUs are sharing it now */
-		opp_table->shared_opp = true;
+		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
 	}
 unlock:
 	mutex_unlock(&opp_table_lock);
@@ -227,7 +227,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus);
  *
  * This updates the @cpumask with CPUs that are sharing OPPs with @cpu_dev.
  *
- * Returns -ENODEV if OPP table isn't already present.
+ * Returns -ENODEV if OPP table isn't already present and -EINVAL if the OPP
+ * table's status is access-unknown.
  *
  * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
@@ -249,9 +250,14 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 		goto unlock;
 	}
 
+	if (opp_table->shared_opp == OPP_TABLE_ACCESS_UNKNOWN) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
 	cpumask_clear(cpumask);
 
-	if (opp_table->shared_opp) {
+	if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) {
 		list_for_each_entry(opp_dev, &opp_table->dev_list, node)
 			cpumask_set_cpu(opp_dev->dev->id, cpumask);
 	} else {
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 94d2010558e3..1dfd3dd92624 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -34,7 +34,10 @@ static struct opp_table *_managed_opp(const struct device_node *np)
 			 * But the OPPs will be considered as shared only if the
 			 * OPP table contains a "opp-shared" property.
 			 */
-			return opp_table->shared_opp ? opp_table : NULL;
+			if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED)
+				return opp_table;
+
+			return NULL;
 		}
 	}
 
@@ -353,7 +356,10 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 	}
 
 	opp_table->np = opp_np;
-	opp_table->shared_opp = of_property_read_bool(opp_np, "opp-shared");
+	if (of_property_read_bool(opp_np, "opp-shared"))
+		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
+	else
+		opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE;
 
 	mutex_unlock(&opp_table_lock);
 
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index 20f3be22e060..fabd5ca1a083 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -119,6 +119,12 @@ struct opp_device {
 #endif
 };
 
+enum opp_table_access {
+	OPP_TABLE_ACCESS_UNKNOWN = 0,
+	OPP_TABLE_ACCESS_EXCLUSIVE = 1,
+	OPP_TABLE_ACCESS_SHARED = 2,
+};
+
 /**
  * struct opp_table - Device opp structure
  * @node:	table node - contains the devices with OPPs that
@@ -166,7 +172,7 @@ struct opp_table {
 	/* For backward compatibility with v1 bindings */
 	unsigned int voltage_tolerance_v1;
 
-	bool shared_opp;
+	enum opp_table_access shared_opp;
 	struct dev_pm_opp *suspend_opp;
 
 	unsigned int *supported_hw;
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index d597e432e195..ab19adb07a12 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1750,7 +1750,7 @@ aoecmd_init(void)
 	int ret;
 
 	/* get_zeroed_page returns page with ref count 1 */
-	p = (void *) get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+	p = (void *) get_zeroed_page(GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
 	empty_page = virt_to_page(p);
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 31e73a7a40f2..6a48ed41963f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -941,7 +941,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd)
 	debugfs_create_u64("size_bytes", 0444, dir, &nbd->bytesize);
 	debugfs_create_u32("timeout", 0444, dir, &nbd->xmit_timeout);
 	debugfs_create_u32("blocksize", 0444, dir, &nbd->blksize);
-	debugfs_create_file("flags", 0444, dir, &nbd, &nbd_dbg_flags_ops);
+	debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_ops);
 
 	return 0;
 }
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index ca13df854639..2e6d1e9c3345 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -874,8 +874,12 @@ static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 			  const struct blk_mq_queue_data *qd)
 {
 	unsigned long flags;
-	struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)hctx->driver_data;
+	int qid = hctx->queue_num;
+	struct blkfront_info *info = hctx->queue->queuedata;
+	struct blkfront_ring_info *rinfo = NULL;
 
+	BUG_ON(info->nr_rings <= qid);
+	rinfo = &info->rinfo[qid];
 	blk_mq_start_request(qd->rq);
 	spin_lock_irqsave(&rinfo->ring_lock, flags);
 	if (RING_FULL(&rinfo->ring))
@@ -901,20 +905,9 @@ out_busy:
 	return BLK_MQ_RQ_QUEUE_BUSY;
 }
 
-static int blk_mq_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
-			    unsigned int index)
-{
-	struct blkfront_info *info = (struct blkfront_info *)data;
-
-	BUG_ON(info->nr_rings <= index);
-	hctx->driver_data = &info->rinfo[index];
-	return 0;
-}
-
 static struct blk_mq_ops blkfront_mq_ops = {
 	.queue_rq = blkif_queue_rq,
 	.map_queue = blk_mq_map_queue,
-	.init_hctx = blk_mq_init_hctx,
 };
 
 static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
@@ -950,6 +943,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 		return PTR_ERR(rq);
 	}
 
+	rq->queuedata = info;
 	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
 
 	if (info->feature_discard) {
@@ -2149,6 +2143,8 @@ static int blkfront_resume(struct xenbus_device *dev)
 		return err;
 
 	err = talk_to_blkback(dev, info);
+	if (!err)
+		blk_mq_update_nr_hw_queues(&info->tag_set, info->nr_rings);
 
 	/*
 	 * We have to wait for the backend to switch to
@@ -2485,10 +2481,23 @@ static void blkback_changed(struct xenbus_device *dev,
 		break;
 
 	case XenbusStateConnected:
-		if (dev->state != XenbusStateInitialised) {
+		/*
+		 * talk_to_blkback sets state to XenbusStateInitialised
+		 * and blkfront_connect sets it to XenbusStateConnected
+		 * (if connection went OK).
+		 *
+		 * If the backend (or toolstack) decides to poke at backend
+		 * state (and re-trigger the watch by setting the state repeatedly
+		 * to XenbusStateConnected (4)) we need to deal with this.
+		 * This is allowed as this is used to communicate to the guest
+		 * that the size of disk has changed!
+		 */
+		if ((dev->state != XenbusStateInitialised) &&
+		    (dev->state != XenbusStateConnected)) {
 			if (talk_to_blkback(dev, info))
 				break;
 		}
+
 		blkfront_connect(info);
 		break;
 
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 94fb407d8561..44b1bd6baa38 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -3820,6 +3820,7 @@ static void handle_new_recv_msgs(ipmi_smi_t intf)
 	while (!list_empty(&intf->waiting_rcv_msgs)) {
 		smi_msg = list_entry(intf->waiting_rcv_msgs.next,
 				     struct ipmi_smi_msg, link);
+		list_del(&smi_msg->link);
 		if (!run_to_completion)
 			spin_unlock_irqrestore(&intf->waiting_rcv_msgs_lock,
 					       flags);
@@ -3829,11 +3830,14 @@ static void handle_new_recv_msgs(ipmi_smi_t intf)
 		if (rv > 0) {
 			/*
 			 * To preserve message order, quit if we
-			 * can't handle a message.
+			 * can't handle a message.  Add the message
+			 * back at the head, this is safe because this
+			 * tasklet is the only thing that pulls the
+			 * messages.
 			 */
+			list_add(&smi_msg->link, &intf->waiting_rcv_msgs);
 			break;
 		} else {
-			list_del(&smi_msg->link);
 			if (rv == 0)
 				/* Message handled */
 				ipmi_free_smi_msg(smi_msg);
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 53ddba26578c..98efbfcdb503 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -175,6 +175,7 @@ config COMMON_CLK_KEYSTONE
 config COMMON_CLK_NXP
 	def_bool COMMON_CLK && (ARCH_LPC18XX || ARCH_LPC32XX)
 	select REGMAP_MMIO if ARCH_LPC32XX
+	select MFD_SYSCON if ARCH_LPC18XX
 	---help---
 	  Support for clock providers on NXP platforms.
 
diff --git a/drivers/clk/microchip/clk-pic32mzda.c b/drivers/clk/microchip/clk-pic32mzda.c
index 020a29acc5b0..51f54380474b 100644
--- a/drivers/clk/microchip/clk-pic32mzda.c
+++ b/drivers/clk/microchip/clk-pic32mzda.c
@@ -180,15 +180,15 @@ static int pic32mzda_clk_probe(struct platform_device *pdev)
 
 	/* register fixed rate clocks */
 	clks[POSCCLK] = clk_register_fixed_rate(&pdev->dev, "posc_clk", NULL,
-						CLK_IS_ROOT, 24000000);
+						0, 24000000);
 	clks[FRCCLK] =  clk_register_fixed_rate(&pdev->dev, "frc_clk", NULL,
-						CLK_IS_ROOT, 8000000);
+						0, 8000000);
 	clks[BFRCCLK] = clk_register_fixed_rate(&pdev->dev, "bfrc_clk", NULL,
-						CLK_IS_ROOT, 8000000);
+						0, 8000000);
 	clks[LPRCCLK] = clk_register_fixed_rate(&pdev->dev, "lprc_clk", NULL,
-						CLK_IS_ROOT, 32000);
+						0, 32000);
 	clks[UPLLCLK] = clk_register_fixed_rate(&pdev->dev, "usbphy_clk", NULL,
-						CLK_IS_ROOT, 24000000);
+						0, 24000000);
 	/* fixed rate (optional) clock */
 	if (of_find_property(np, "microchip,pic32mzda-sosc", NULL)) {
 		pr_info("pic32-clk: dt requests SOSC.\n");
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 15d06fcf0b50..a782ce87715c 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -22,7 +22,6 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
-#include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/ktime.h>
 #include <linux/init.h>
@@ -56,11 +55,21 @@ static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
 /* proc_event_counts is used as the sequence number of the netlink message */
 static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 };
 
-static inline void get_seq(__u32 *ts, int *cpu)
+static inline void send_msg(struct cn_msg *msg)
 {
 	preempt_disable();
-	*ts = __this_cpu_inc_return(proc_event_counts) - 1;
-	*cpu = smp_processor_id();
+
+	msg->seq = __this_cpu_inc_return(proc_event_counts) - 1;
+	((struct proc_event *)msg->data)->cpu = smp_processor_id();
+
+	/*
+	 * Preemption remains disabled during send to ensure the messages are
+	 * ordered according to their sequence numbers.
+	 *
+	 * If cn_netlink_send() fails, the data is not sent.
+	 */
+	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT);
+
 	preempt_enable();
 }
 
@@ -77,7 +86,6 @@ void proc_fork_connector(struct task_struct *task)
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_FORK;
 	rcu_read_lock();
@@ -92,8 +100,7 @@ void proc_fork_connector(struct task_struct *task)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	/*  If cn_netlink_send() failed, the data is not sent */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_exec_connector(struct task_struct *task)
@@ -108,7 +115,6 @@ void proc_exec_connector(struct task_struct *task)
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_EXEC;
 	ev->event_data.exec.process_pid = task->pid;
@@ -118,7 +124,7 @@ void proc_exec_connector(struct task_struct *task)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_id_connector(struct task_struct *task, int which_id)
@@ -150,14 +156,13 @@ void proc_id_connector(struct task_struct *task, int which_id)
 		return;
 	}
 	rcu_read_unlock();
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_sid_connector(struct task_struct *task)
@@ -172,7 +177,6 @@ void proc_sid_connector(struct task_struct *task)
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_SID;
 	ev->event_data.sid.process_pid = task->pid;
@@ -182,7 +186,7 @@ void proc_sid_connector(struct task_struct *task)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
@@ -197,7 +201,6 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_PTRACE;
 	ev->event_data.ptrace.process_pid  = task->pid;
@@ -215,7 +218,7 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_comm_connector(struct task_struct *task)
@@ -230,7 +233,6 @@ void proc_comm_connector(struct task_struct *task)
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_COMM;
 	ev->event_data.comm.process_pid  = task->pid;
@@ -241,7 +243,7 @@ void proc_comm_connector(struct task_struct *task)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_coredump_connector(struct task_struct *task)
@@ -256,7 +258,6 @@ void proc_coredump_connector(struct task_struct *task)
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_COREDUMP;
 	ev->event_data.coredump.process_pid = task->pid;
@@ -266,7 +267,7 @@ void proc_coredump_connector(struct task_struct *task)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_exit_connector(struct task_struct *task)
@@ -281,7 +282,6 @@ void proc_exit_connector(struct task_struct *task)
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_EXIT;
 	ev->event_data.exit.process_pid = task->pid;
@@ -293,7 +293,7 @@ void proc_exit_connector(struct task_struct *task)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 /*
@@ -325,7 +325,7 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack)
 	msg->ack = rcvd_ack + 1;
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 /**
@@ -389,5 +389,4 @@ static int __init cn_proc_init(void)
 	}
 	return 0;
 }
-
-module_init(cn_proc_init);
+device_initcall(cn_proc_init);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 36bc11a106aa..9009295f5134 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1832,7 +1832,7 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier);
 unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 					unsigned int target_freq)
 {
-	clamp_val(target_freq, policy->min, policy->max);
+	target_freq = clamp_val(target_freq, policy->min, policy->max);
 
 	return cpufreq_driver->fast_switch(policy, target_freq);
 }
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 3a9c4325d6e2..fe9dc17ea873 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -372,26 +372,9 @@ static bool intel_pstate_get_ppc_enable_status(void)
 	return acpi_ppc;
 }
 
-/*
- * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and
- * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and
- * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state
- * ratio, out of it only high 8 bits are used. For example 0x1700 is setting
- * target ratio 0x17. The _PSS control value stores in a format which can be
- * directly written to PERF_CTL MSR. But in intel_pstate driver this shift
- * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()).
- * This function converts the _PSS control value to intel pstate driver format
- * for comparison and assignment.
- */
-static int convert_to_native_pstate_format(struct cpudata *cpu, int index)
-{
-	return cpu->acpi_perf_data.states[index].control >> 8;
-}
-
 static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu;
-	int turbo_pss_ctl;
 	int ret;
 	int i;
 
@@ -441,15 +424,14 @@ static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
 	 * max frequency, which will cause a reduced performance as
 	 * this driver uses real max turbo frequency as the max
 	 * frequency. So correct this frequency in _PSS table to
-	 * correct max turbo frequency based on the turbo ratio.
+	 * correct max turbo frequency based on the turbo state.
 	 * Also need to convert to MHz as _PSS freq is in MHz.
 	 */
-	turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0);
-	if (turbo_pss_ctl > cpu->pstate.max_pstate)
+	if (!limits->turbo_disabled)
 		cpu->acpi_perf_data.states[0].core_frequency =
 					policy->cpuinfo.max_freq / 1000;
 	cpu->valid_pss_table = true;
-	pr_info("_PPC limits will be enforced\n");
+	pr_debug("_PPC limits will be enforced\n");
 
 	return;
 
@@ -1460,6 +1442,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 
 	intel_pstate_clear_update_util_hook(policy->cpu);
 
+	pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
+		 policy->cpuinfo.max_freq, policy->max);
+
 	cpu = all_cpu_data[0];
 	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
 	    policy->max < policy->cpuinfo.max_freq &&
@@ -1495,13 +1480,13 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 				   limits->max_sysfs_pct);
 	limits->max_perf_pct = max(limits->min_policy_pct,
 				   limits->max_perf_pct);
-	limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
 
 	/* Make sure min_perf_pct <= max_perf_pct */
 	limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
 
 	limits->min_perf = div_fp(limits->min_perf_pct, 100);
 	limits->max_perf = div_fp(limits->max_perf_pct, 100);
+	limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
 
  out:
 	intel_pstate_set_update_util_hook(policy->cpu);
@@ -1558,8 +1543,11 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	/* cpuinfo and default policy values */
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
-	policy->cpuinfo.max_freq =
-		cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+	update_turbo_state();
+	policy->cpuinfo.max_freq = limits->turbo_disabled ?
+			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
+	policy->cpuinfo.max_freq *= cpu->pstate.scaling;
+
 	intel_pstate_init_acpi_perf_limits(policy);
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	cpumask_set_cpu(policy->cpu, policy->cpus);
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 808a320e9d5d..a7ecb9a84c15 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -487,7 +487,7 @@ static int __init pcc_cpufreq_probe(void)
 	doorbell.space_id = reg_resource->space_id;
 	doorbell.bit_width = reg_resource->bit_width;
 	doorbell.bit_offset = reg_resource->bit_offset;
-	doorbell.access_width = 64;
+	doorbell.access_width = 4;
 	doorbell.address = reg_resource->address;
 
 	pr_debug("probe: doorbell: space_id is %d, bit_width is %d, "
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 574e87c7f2b8..9acccad26928 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -781,7 +781,7 @@ static int hash_process_data(struct hash_device_data *device_data,
 						&device_data->state);
 				memmove(req_ctx->state.buffer,
 					device_data->state.buffer,
-					HASH_BLOCK_SIZE / sizeof(u32));
+					HASH_BLOCK_SIZE);
 				if (ret) {
 					dev_err(device_data->dev,
 						"%s: hash_resume_state() failed!\n",
@@ -832,7 +832,7 @@ static int hash_process_data(struct hash_device_data *device_data,
 
 			memmove(device_data->state.buffer,
 				req_ctx->state.buffer,
-				HASH_BLOCK_SIZE / sizeof(u32));
+				HASH_BLOCK_SIZE);
 			if (ret) {
 				dev_err(device_data->dev, "%s: hash_save_state() failed!\n",
 					__func__);
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index 495577b6d31b..94ad5c0adbcb 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -182,7 +182,7 @@ struct crypto_alg p8_aes_cbc_alg = {
 	.cra_name = "cbc(aes)",
 	.cra_driver_name = "p8_aes_cbc",
 	.cra_module = THIS_MODULE,
-	.cra_priority = 1000,
+	.cra_priority = 2000,
 	.cra_type = &crypto_blkcipher_type,
 	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
 	.cra_alignmask = 0,
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index 0a3c1b04cf3c..38ed10d761d0 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -166,7 +166,7 @@ struct crypto_alg p8_aes_ctr_alg = {
 	.cra_name = "ctr(aes)",
 	.cra_driver_name = "p8_aes_ctr",
 	.cra_module = THIS_MODULE,
-	.cra_priority = 1000,
+	.cra_priority = 2000,
 	.cra_type = &crypto_blkcipher_type,
 	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
 	.cra_alignmask = 0,
diff --git a/drivers/crypto/vmx/ppc-xlate.pl b/drivers/crypto/vmx/ppc-xlate.pl
index 9f4994cabcc7..b18e67d0e065 100644
--- a/drivers/crypto/vmx/ppc-xlate.pl
+++ b/drivers/crypto/vmx/ppc-xlate.pl
@@ -141,7 +141,7 @@ my $vmr = sub {
 
 # Some ABIs specify vrsave, special-purpose register #256, as reserved
 # for system use.
-my $no_vrsave = ($flavour =~ /aix|linux64le/);
+my $no_vrsave = ($flavour =~ /linux-ppc64le/);
 my $mtspr = sub {
     my ($f,$idx,$ra) = @_;
     if ($idx == 256 && $no_vrsave) {
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 1d6c803804d5..e92418facc92 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -268,8 +268,11 @@ int update_devfreq(struct devfreq *devfreq)
 	devfreq_notify_transition(devfreq, &freqs, DEVFREQ_PRECHANGE);
 
 	err = devfreq->profile->target(devfreq->dev.parent, &freq, flags);
-	if (err)
+	if (err) {
+		freqs.new = cur_freq;
+		devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE);
 		return err;
+	}
 
 	freqs.new = freq;
 	devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE);
@@ -552,6 +555,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->profile = profile;
 	strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN);
 	devfreq->previous_freq = profile->initial_freq;
+	devfreq->last_status.current_frequency = profile->initial_freq;
 	devfreq->data = data;
 	devfreq->nb.notifier_call = devfreq_notifier_call;
 
@@ -561,23 +565,22 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		mutex_lock(&devfreq->lock);
 	}
 
-	devfreq->trans_table =	devm_kzalloc(dev, sizeof(unsigned int) *
-						devfreq->profile->max_state *
-						devfreq->profile->max_state,
-						GFP_KERNEL);
-	devfreq->time_in_state = devm_kzalloc(dev, sizeof(unsigned long) *
-						devfreq->profile->max_state,
-						GFP_KERNEL);
-	devfreq->last_stat_updated = jiffies;
-
 	dev_set_name(&devfreq->dev, "%s", dev_name(dev));
 	err = device_register(&devfreq->dev);
 	if (err) {
-		put_device(&devfreq->dev);
 		mutex_unlock(&devfreq->lock);
 		goto err_out;
 	}
 
+	devfreq->trans_table =	devm_kzalloc(&devfreq->dev, sizeof(unsigned int) *
+						devfreq->profile->max_state *
+						devfreq->profile->max_state,
+						GFP_KERNEL);
+	devfreq->time_in_state = devm_kzalloc(&devfreq->dev, sizeof(unsigned long) *
+						devfreq->profile->max_state,
+						GFP_KERNEL);
+	devfreq->last_stat_updated = jiffies;
+
 	srcu_init_notifier_head(&devfreq->transition_notifier_list);
 
 	mutex_unlock(&devfreq->lock);
@@ -603,7 +606,6 @@ struct devfreq *devfreq_add_device(struct device *dev,
 err_init:
 	list_del(&devfreq->node);
 	device_unregister(&devfreq->dev);
-	kfree(devfreq);
 err_out:
 	return ERR_PTR(err);
 }
@@ -621,7 +623,6 @@ int devfreq_remove_device(struct devfreq *devfreq)
 		return -EINVAL;
 
 	device_unregister(&devfreq->dev);
-	put_device(&devfreq->dev);
 
 	return 0;
 }
diff --git a/drivers/devfreq/event/exynos-nocp.c b/drivers/devfreq/event/exynos-nocp.c
index 6b6a5f310486..a5841403bde8 100644
--- a/drivers/devfreq/event/exynos-nocp.c
+++ b/drivers/devfreq/event/exynos-nocp.c
@@ -220,9 +220,6 @@ static int exynos_nocp_parse_dt(struct platform_device *pdev,
 
 	/* Maps the memory mapped IO to control nocp register */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (IS_ERR(res))
-		return PTR_ERR(res);
-
 	base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 4a2c07ee6677..6355ab38d630 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -33,6 +33,7 @@
 #include <linux/seq_file.h>
 #include <linux/poll.h>
 #include <linux/reservation.h>
+#include <linux/mm.h>
 
 #include <uapi/linux/dma-buf.h>
 
@@ -90,7 +91,7 @@ static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma)
 	dmabuf = file->private_data;
 
 	/* check for overflowing the buffer's size */
-	if (vma->vm_pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) >
+	if (vma->vm_pgoff + vma_pages(vma) >
 	    dmabuf->size >> PAGE_SHIFT)
 		return -EINVAL;
 
@@ -723,11 +724,11 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma,
 		return -EINVAL;
 
 	/* check for offset overflow */
-	if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) < pgoff)
+	if (pgoff + vma_pages(vma) < pgoff)
 		return -EOVERFLOW;
 
 	/* check for overflowing the buffer's size */
-	if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) >
+	if (pgoff + vma_pages(vma) >
 	    dmabuf->size >> PAGE_SHIFT)
 		return -EINVAL;
 
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index c0bd5722c997..9566a62ad8e3 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -35,6 +35,17 @@
 #include <linux/reservation.h>
 #include <linux/export.h>
 
+/**
+ * DOC: Reservation Object Overview
+ *
+ * The reservation object provides a mechanism to manage shared and
+ * exclusive fences associated with a buffer.  A reservation object
+ * can have attached one exclusive fence (normally associated with
+ * write operations) or N shared fences (read operations).  The RCU
+ * mechanism is used to protect read access to fences from locked
+ * write-side updates.
+ */
+
 DEFINE_WW_CLASS(reservation_ww_class);
 EXPORT_SYMBOL(reservation_ww_class);
 
@@ -43,9 +54,17 @@ EXPORT_SYMBOL(reservation_seqcount_class);
 
 const char reservation_seqcount_string[] = "reservation_seqcount";
 EXPORT_SYMBOL(reservation_seqcount_string);
-/*
- * Reserve space to add a shared fence to a reservation_object,
- * must be called with obj->lock held.
+
+/**
+ * reservation_object_reserve_shared - Reserve space to add a shared
+ * fence to a reservation_object.
+ * @obj: reservation object
+ *
+ * Should be called before reservation_object_add_shared_fence().  Must
+ * be called with obj->lock held.
+ *
+ * RETURNS
+ * Zero for success, or -errno
  */
 int reservation_object_reserve_shared(struct reservation_object *obj)
 {
@@ -180,7 +199,11 @@ done:
 		fence_put(old_fence);
 }
 
-/*
+/**
+ * reservation_object_add_shared_fence - Add a fence to a shared slot
+ * @obj: the reservation object
+ * @fence: the shared fence to add
+ *
  * Add a fence to a shared slot, obj->lock must be held, and
  * reservation_object_reserve_shared_fence has been called.
  */
@@ -200,6 +223,13 @@ void reservation_object_add_shared_fence(struct reservation_object *obj,
 }
 EXPORT_SYMBOL(reservation_object_add_shared_fence);
 
+/**
+ * reservation_object_add_excl_fence - Add an exclusive fence.
+ * @obj: the reservation object
+ * @fence: the shared fence to add
+ *
+ * Add a fence to the exclusive slot.  The obj->lock must be held.
+ */
 void reservation_object_add_excl_fence(struct reservation_object *obj,
 				       struct fence *fence)
 {
@@ -233,6 +263,18 @@ void reservation_object_add_excl_fence(struct reservation_object *obj,
 }
 EXPORT_SYMBOL(reservation_object_add_excl_fence);
 
+/**
+ * reservation_object_get_fences_rcu - Get an object's shared and exclusive
+ * fences without update side lock held
+ * @obj: the reservation object
+ * @pfence_excl: the returned exclusive fence (or NULL)
+ * @pshared_count: the number of shared fences returned
+ * @pshared: the array of shared fence ptrs returned (array is krealloc'd to
+ * the required size, and must be freed by caller)
+ *
+ * RETURNS
+ * Zero or -errno
+ */
 int reservation_object_get_fences_rcu(struct reservation_object *obj,
 				      struct fence **pfence_excl,
 				      unsigned *pshared_count,
@@ -319,6 +361,18 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(reservation_object_get_fences_rcu);
 
+/**
+ * reservation_object_wait_timeout_rcu - Wait on reservation's objects
+ * shared and/or exclusive fences.
+ * @obj: the reservation object
+ * @wait_all: if true, wait on all fences, else wait on just exclusive fence
+ * @intr: if true, do interruptible wait
+ * @timeout: timeout value in jiffies or zero to return immediately
+ *
+ * RETURNS
+ * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or
+ * greater than zer on success.
+ */
 long reservation_object_wait_timeout_rcu(struct reservation_object *obj,
 					 bool wait_all, bool intr,
 					 unsigned long timeout)
@@ -416,6 +470,16 @@ reservation_object_test_signaled_single(struct fence *passed_fence)
 	return ret;
 }
 
+/**
+ * reservation_object_test_signaled_rcu - Test if a reservation object's
+ * fences have been signaled.
+ * @obj: the reservation object
+ * @test_all: if true, test all fences, otherwise only test the exclusive
+ * fence
+ *
+ * RETURNS
+ * true if all fences signaled, else false
+ */
 bool reservation_object_test_signaled_rcu(struct reservation_object *obj,
 					  bool test_all)
 {
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 8e304b1befc5..75bd6621dc5d 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -242,7 +242,7 @@ struct at_xdmac_lld {
 	u32		mbr_dus;	/* Destination Microblock Stride Register */
 };
 
-
+/* 64-bit alignment needed to update CNDA and CUBC registers in an atomic way. */
 struct at_xdmac_desc {
 	struct at_xdmac_lld		lld;
 	enum dma_transfer_direction	direction;
@@ -253,7 +253,7 @@ struct at_xdmac_desc {
 	unsigned int			xfer_size;
 	struct list_head		descs_list;
 	struct list_head		xfer_node;
-};
+} __aligned(sizeof(u64));
 
 static inline void __iomem *at_xdmac_chan_reg_base(struct at_xdmac *atxdmac, unsigned int chan_nb)
 {
@@ -1400,6 +1400,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	u32			cur_nda, check_nda, cur_ubc, mask, value;
 	u8			dwidth = 0;
 	unsigned long		flags;
+	bool			initd;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_COMPLETE)
@@ -1424,7 +1425,16 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	residue = desc->xfer_size;
 	/*
 	 * Flush FIFO: only relevant when the transfer is source peripheral
-	 * synchronized.
+	 * synchronized. Flush is needed before reading CUBC because data in
+	 * the FIFO are not reported by CUBC. Reporting a residue of the
+	 * transfer length while we have data in FIFO can cause issue.
+	 * Usecase: atmel USART has a timeout which means I have received
+	 * characters but there is no more character received for a while. On
+	 * timeout, it requests the residue. If the data are in the DMA FIFO,
+	 * we will return a residue of the transfer length. It means no data
+	 * received. If an application is waiting for these data, it will hang
+	 * since we won't have another USART timeout without receiving new
+	 * data.
 	 */
 	mask = AT_XDMAC_CC_TYPE | AT_XDMAC_CC_DSYNC;
 	value = AT_XDMAC_CC_TYPE_PER_TRAN | AT_XDMAC_CC_DSYNC_PER2MEM;
@@ -1435,34 +1445,43 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	}
 
 	/*
-	 * When processing the residue, we need to read two registers but we
-	 * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where
-	 * we stand in the descriptor list and AT_XDMAC_CUBC is used
-	 * to know how many data are remaining for the current descriptor.
-	 * Since the dma channel is not paused to not loose data, between the
-	 * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of
-	 * descriptor.
-	 * For that reason, after reading AT_XDMAC_CUBC, we check if we are
-	 * still using the same descriptor by reading a second time
-	 * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to
-	 * read again AT_XDMAC_CUBC.
+	 * The easiest way to compute the residue should be to pause the DMA
+	 * but doing this can lead to miss some data as some devices don't
+	 * have FIFO.
+	 * We need to read several registers because:
+	 * - DMA is running therefore a descriptor change is possible while
+	 * reading these registers
+	 * - When the block transfer is done, the value of the CUBC register
+	 * is set to its initial value until the fetch of the next descriptor.
+	 * This value will corrupt the residue calculation so we have to skip
+	 * it.
+	 *
+	 * INITD --------                    ------------
+	 *              |____________________|
+	 *       _______________________  _______________
+	 * NDA       @desc2             \/   @desc3
+	 *       _______________________/\_______________
+	 *       __________  ___________  _______________
+	 * CUBC       0    \/ MAX desc1 \/  MAX desc2
+	 *       __________/\___________/\_______________
+	 *
+	 * Since descriptors are aligned on 64 bits, we can assume that
+	 * the update of NDA and CUBC is atomic.
 	 * Memory barriers are used to ensure the read order of the registers.
-	 * A max number of retries is set because unlikely it can never ends if
-	 * we are transferring a lot of data with small buffers.
+	 * A max number of retries is set because unlikely it could never ends.
 	 */
-	cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
-	rmb();
-	cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
 	for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) {
-		rmb();
 		check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
-
-		if (likely(cur_nda == check_nda))
-			break;
-
-		cur_nda = check_nda;
+		rmb();
+		initd = !!(at_xdmac_chan_read(atchan, AT_XDMAC_CC) & AT_XDMAC_CC_INITD);
 		rmb();
 		cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+		rmb();
+		cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+		rmb();
+
+		if ((check_nda == cur_nda) && initd)
+			break;
 	}
 
 	if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) {
@@ -1471,6 +1490,19 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	}
 
 	/*
+	 * Flush FIFO: only relevant when the transfer is source peripheral
+	 * synchronized. Another flush is needed here because CUBC is updated
+	 * when the controller sends the data write command. It can lead to
+	 * report data that are not written in the memory or the device. The
+	 * FIFO flush ensures that data are really written.
+	 */
+	if ((desc->lld.mbr_cfg & mask) == value) {
+		at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask);
+		while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS))
+			cpu_relax();
+	}
+
+	/*
 	 * Remove size of all microblocks already transferred and the current
 	 * one. Then add the remaining size to transfer of the current
 	 * microblock.
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 25d1dadcddd1..d0446a75990a 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -703,8 +703,9 @@ static int mv_chan_memcpy_self_test(struct mv_xor_chan *mv_chan)
 		goto free_resources;
 	}
 
-	src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src), 0,
-				 PAGE_SIZE, DMA_TO_DEVICE);
+	src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src),
+			       (size_t)src & ~PAGE_MASK, PAGE_SIZE,
+			       DMA_TO_DEVICE);
 	unmap->addr[0] = src_dma;
 
 	ret = dma_mapping_error(dma_chan->device->dev, src_dma);
@@ -714,8 +715,9 @@ static int mv_chan_memcpy_self_test(struct mv_xor_chan *mv_chan)
 	}
 	unmap->to_cnt = 1;
 
-	dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest), 0,
-				  PAGE_SIZE, DMA_FROM_DEVICE);
+	dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest),
+				(size_t)dest & ~PAGE_MASK, PAGE_SIZE,
+				DMA_FROM_DEVICE);
 	unmap->addr[1] = dest_dma;
 
 	ret = dma_mapping_error(dma_chan->device->dev, dest_dma);
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 6aa256b0a1ed..c3ee3ad98a63 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -565,7 +565,8 @@ void edac_mc_reset_delay_period(unsigned long value)
 	list_for_each(item, &mc_devices) {
 		mci = list_entry(item, struct mem_ctl_info, link);
 
-		edac_mod_work(&mci->work, value);
+		if (mci->op_state == OP_RUNNING_POLL)
+			edac_mod_work(&mci->work, value);
 	}
 	mutex_unlock(&mem_ctls_mutex);
 }
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index b4d0bf6534cf..6744d88bdea8 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -239,8 +239,11 @@ static const u32 rir_offset[MAX_RIR_RANGES][MAX_RIR_WAY] = {
 	{ 0x1a0, 0x1a4, 0x1a8, 0x1ac, 0x1b0, 0x1b4, 0x1b8, 0x1bc },
 };
 
-#define RIR_RNK_TGT(reg)		GET_BITFIELD(reg, 16, 19)
-#define RIR_OFFSET(reg)		GET_BITFIELD(reg,  2, 14)
+#define RIR_RNK_TGT(type, reg) (((type) == BROADWELL) ? \
+	GET_BITFIELD(reg, 20, 23) : GET_BITFIELD(reg, 16, 19))
+
+#define RIR_OFFSET(type, reg) (((type) == HASWELL || (type) == BROADWELL) ? \
+	GET_BITFIELD(reg,  2, 15) : GET_BITFIELD(reg,  2, 14))
 
 /* Device 16, functions 2-7 */
 
@@ -326,6 +329,7 @@ struct pci_id_descr {
 struct pci_id_table {
 	const struct pci_id_descr	*descr;
 	int				n_devs;
+	enum type			type;
 };
 
 struct sbridge_dev {
@@ -394,9 +398,14 @@ static const struct pci_id_descr pci_dev_descr_sbridge[] = {
 	{ PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_BR, 0)		},
 };
 
-#define PCI_ID_TABLE_ENTRY(A) { .descr=A, .n_devs = ARRAY_SIZE(A) }
+#define PCI_ID_TABLE_ENTRY(A, T) {	\
+	.descr = A,			\
+	.n_devs = ARRAY_SIZE(A),	\
+	.type = T			\
+}
+
 static const struct pci_id_table pci_dev_descr_sbridge_table[] = {
-	PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge),
+	PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge, SANDY_BRIDGE),
 	{0,}			/* 0 terminated list. */
 };
 
@@ -463,7 +472,7 @@ static const struct pci_id_descr pci_dev_descr_ibridge[] = {
 };
 
 static const struct pci_id_table pci_dev_descr_ibridge_table[] = {
-	PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge),
+	PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge, IVY_BRIDGE),
 	{0,}			/* 0 terminated list. */
 };
 
@@ -536,7 +545,7 @@ static const struct pci_id_descr pci_dev_descr_haswell[] = {
 };
 
 static const struct pci_id_table pci_dev_descr_haswell_table[] = {
-	PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell),
+	PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell, HASWELL),
 	{0,}			/* 0 terminated list. */
 };
 
@@ -580,7 +589,7 @@ static const struct pci_id_descr pci_dev_descr_knl[] = {
 };
 
 static const struct pci_id_table pci_dev_descr_knl_table[] = {
-	PCI_ID_TABLE_ENTRY(pci_dev_descr_knl),
+	PCI_ID_TABLE_ENTRY(pci_dev_descr_knl, KNIGHTS_LANDING),
 	{0,}
 };
 
@@ -648,7 +657,7 @@ static const struct pci_id_descr pci_dev_descr_broadwell[] = {
 };
 
 static const struct pci_id_table pci_dev_descr_broadwell_table[] = {
-	PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell),
+	PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell, BROADWELL),
 	{0,}			/* 0 terminated list. */
 };
 
@@ -1894,14 +1903,14 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 				pci_read_config_dword(pvt->pci_tad[i],
 						      rir_offset[j][k],
 						      &reg);
-				tmp_mb = RIR_OFFSET(reg) << 6;
+				tmp_mb = RIR_OFFSET(pvt->info.type, reg) << 6;
 
 				gb = div_u64_rem(tmp_mb, 1024, &mb);
 				edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n",
 					 i, j, k,
 					 gb, (mb*1000)/1024,
 					 ((u64)tmp_mb) << 20L,
-					 (u32)RIR_RNK_TGT(reg),
+					 (u32)RIR_RNK_TGT(pvt->info.type, reg),
 					 reg);
 			}
 		}
@@ -2234,7 +2243,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	pci_read_config_dword(pvt->pci_tad[ch_add + base_ch],
 			      rir_offset[n_rir][idx],
 			      &reg);
-	*rank = RIR_RNK_TGT(reg);
+	*rank = RIR_RNK_TGT(pvt->info.type, reg);
 
 	edac_dbg(0, "RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n",
 		 n_rir,
@@ -3357,12 +3366,12 @@ fail0:
 #define ICPU(model, table) \
 	{ X86_VENDOR_INTEL, 6, model, 0, (unsigned long)&table }
 
-/* Order here must match "enum type" */
 static const struct x86_cpu_id sbridge_cpuids[] = {
 	ICPU(0x2d, pci_dev_descr_sbridge_table),	/* SANDY_BRIDGE */
 	ICPU(0x3e, pci_dev_descr_ibridge_table),	/* IVY_BRIDGE */
 	ICPU(0x3f, pci_dev_descr_haswell_table),	/* HASWELL */
 	ICPU(0x4f, pci_dev_descr_broadwell_table),	/* BROADWELL */
+	ICPU(0x56, pci_dev_descr_broadwell_table),	/* BROADWELL-DE */
 	ICPU(0x57, pci_dev_descr_knl_table),		/* KNIGHTS_LANDING */
 	{ }
 };
@@ -3398,7 +3407,7 @@ static int sbridge_probe(const struct x86_cpu_id *id)
 			 mc, mc + 1, num_mc);
 
 		sbridge_dev->mc = mc++;
-		rc = sbridge_register_mci(sbridge_dev, id - sbridge_cpuids);
+		rc = sbridge_register_mci(sbridge_dev, ptable->type);
 		if (unlikely(rc < 0))
 			goto fail1;
 	}
diff --git a/drivers/extcon/extcon-palmas.c b/drivers/extcon/extcon-palmas.c
index 8b3226dca1d9..caff46c0e214 100644
--- a/drivers/extcon/extcon-palmas.c
+++ b/drivers/extcon/extcon-palmas.c
@@ -360,6 +360,8 @@ static int palmas_usb_probe(struct platform_device *pdev)
 
 	palmas_enable_irq(palmas_usb);
 	/* perform initial detection */
+	if (palmas_usb->enable_gpio_vbus_detection)
+		palmas_vbus_irq_handler(palmas_usb->gpio_vbus_irq, palmas_usb);
 	palmas_gpio_id_detect(&palmas_usb->wq_detectid.work);
 	device_set_wakeup_capable(&pdev->dev, true);
 	return 0;
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index a850cbc48d8d..c49d50e68aee 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -174,6 +174,7 @@ static __init void reserve_regions(void)
 {
 	efi_memory_desc_t *md;
 	u64 paddr, npages, size;
+	int resv;
 
 	if (efi_enabled(EFI_DBG))
 		pr_info("Processing EFI memory map:\n");
@@ -190,12 +191,14 @@ static __init void reserve_regions(void)
 		paddr = md->phys_addr;
 		npages = md->num_pages;
 
+		resv = is_reserve_region(md);
 		if (efi_enabled(EFI_DBG)) {
 			char buf[64];
 
-			pr_info("  0x%012llx-0x%012llx %s",
+			pr_info("  0x%012llx-0x%012llx %s%s\n",
 				paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1,
-				efi_md_typeattr_format(buf, sizeof(buf), md));
+				efi_md_typeattr_format(buf, sizeof(buf), md),
+				resv ? "*" : "");
 		}
 
 		memrange_efi_to_native(&paddr, &npages);
@@ -204,14 +207,9 @@ static __init void reserve_regions(void)
 		if (is_normal_ram(md))
 			early_init_dt_add_memory_arch(paddr, size);
 
-		if (is_reserve_region(md)) {
+		if (resv)
 			memblock_mark_nomap(paddr, size);
-			if (efi_enabled(EFI_DBG))
-				pr_cont("*");
-		}
 
-		if (efi_enabled(EFI_DBG))
-			pr_cont("\n");
 	}
 
 	set_bit(EFI_MEMMAP, &efi.flags);
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 48da857f4774..cebcb405812e 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -33,6 +33,7 @@ config ARCH_REQUIRE_GPIOLIB
 
 menuconfig GPIOLIB
 	bool "GPIO Support"
+	select ANON_INODES
 	help
 	  This enables GPIO support through the generic GPIO library.
 	  You only need to enable this, if you also want to enable
@@ -530,7 +531,7 @@ menu "Port-mapped I/O GPIO drivers"
 
 config GPIO_104_DIO_48E
 	tristate "ACCES 104-DIO-48E GPIO support"
-	depends on ISA
+	depends on ISA_BUS_API
 	select GPIOLIB_IRQCHIP
 	help
 	  Enables GPIO support for the ACCES 104-DIO-48E series (104-DIO-48E,
@@ -540,7 +541,7 @@ config GPIO_104_DIO_48E
 
 config GPIO_104_IDIO_16
 	tristate "ACCES 104-IDIO-16 GPIO support"
-	depends on ISA
+	depends on ISA_BUS_API
 	select GPIOLIB_IRQCHIP
 	help
 	  Enables GPIO support for the ACCES 104-IDIO-16 family (104-IDIO-16,
@@ -551,7 +552,7 @@ config GPIO_104_IDIO_16
 
 config GPIO_104_IDI_48
 	tristate "ACCES 104-IDI-48 GPIO support"
-	depends on ISA
+	depends on ISA_BUS_API
 	select GPIOLIB_IRQCHIP
 	help
 	  Enables GPIO support for the ACCES 104-IDI-48 family (104-IDI-48A,
@@ -627,7 +628,7 @@ config GPIO_TS5500
 
 config GPIO_WS16C48
 	tristate "WinSystems WS16C48 GPIO support"
-	depends on ISA
+	depends on ISA_BUS_API
 	select GPIOLIB_IRQCHIP
 	help
 	  Enables GPIO support for the WinSystems WS16C48. The base port
diff --git a/drivers/gpio/gpio-104-dio-48e.c b/drivers/gpio/gpio-104-dio-48e.c
index 1a647c07be67..fcf776971ca9 100644
--- a/drivers/gpio/gpio-104-dio-48e.c
+++ b/drivers/gpio/gpio-104-dio-48e.c
@@ -75,7 +75,7 @@ static int dio48e_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 {
 	struct dio48e_gpio *const dio48egpio = gpiochip_get_data(chip);
 	const unsigned io_port = offset / 8;
-	const unsigned control_port = io_port / 2;
+	const unsigned int control_port = io_port / 3;
 	const unsigned control_addr = dio48egpio->base + 3 + control_port*4;
 	unsigned long flags;
 	unsigned control;
@@ -115,7 +115,7 @@ static int dio48e_gpio_direction_output(struct gpio_chip *chip, unsigned offset,
 {
 	struct dio48e_gpio *const dio48egpio = gpiochip_get_data(chip);
 	const unsigned io_port = offset / 8;
-	const unsigned control_port = io_port / 2;
+	const unsigned int control_port = io_port / 3;
 	const unsigned mask = BIT(offset % 8);
 	const unsigned control_addr = dio48egpio->base + 3 + control_port*4;
 	const unsigned out_port = (io_port > 2) ? io_port + 1 : io_port;
diff --git a/drivers/gpio/gpio-104-idi-48.c b/drivers/gpio/gpio-104-idi-48.c
index 6c75c83baf5a..2d2763ea1a68 100644
--- a/drivers/gpio/gpio-104-idi-48.c
+++ b/drivers/gpio/gpio-104-idi-48.c
@@ -247,6 +247,7 @@ static int idi_48_probe(struct device *dev, unsigned int id)
 	idi48gpio->irq = irq[id];
 
 	spin_lock_init(&idi48gpio->lock);
+	spin_lock_init(&idi48gpio->ack_lock);
 
 	dev_set_drvdata(dev, idi48gpio);
 
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 9aabc48ff5de..953e4b829e32 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -547,11 +547,11 @@ static void bcm_kona_gpio_reset(struct bcm_kona_gpio *kona_gpio)
 	/* disable interrupts and clear status */
 	for (i = 0; i < kona_gpio->num_bank; i++) {
 		/* Unlock the entire bank first */
-		bcm_kona_gpio_write_lock_regs(kona_gpio, i, UNLOCK_CODE);
+		bcm_kona_gpio_write_lock_regs(reg_base, i, UNLOCK_CODE);
 		writel(0xffffffff, reg_base + GPIO_INT_MASK(i));
 		writel(0xffffffff, reg_base + GPIO_INT_STATUS(i));
 		/* Now re-lock the bank */
-		bcm_kona_gpio_write_lock_regs(kona_gpio, i, LOCK_CODE);
+		bcm_kona_gpio_write_lock_regs(reg_base, i, LOCK_CODE);
 	}
 }
 
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index ec891a27952f..661b0e34e067 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -98,7 +98,6 @@ struct tegra_gpio_info {
 	const struct tegra_gpio_soc_config	*soc;
 	struct gpio_chip			gc;
 	struct irq_chip				ic;
-	struct lock_class_key			lock_class;
 	u32					bank_count;
 };
 
@@ -547,6 +546,12 @@ static const struct dev_pm_ops tegra_gpio_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(tegra_gpio_suspend, tegra_gpio_resume)
 };
 
+/*
+ * This lock class tells lockdep that GPIO irqs are in a different category
+ * than their parents, so it won't report false recursion.
+ */
+static struct lock_class_key gpio_lock_class;
+
 static int tegra_gpio_probe(struct platform_device *pdev)
 {
 	const struct tegra_gpio_soc_config *config;
@@ -660,7 +665,7 @@ static int tegra_gpio_probe(struct platform_device *pdev)
 
 		bank = &tgi->bank_info[GPIO_BANK(gpio)];
 
-		irq_set_lockdep_class(irq, &tgi->lock_class);
+		irq_set_lockdep_class(irq, &gpio_lock_class);
 		irq_set_chip_data(irq, bank);
 		irq_set_chip_and_handler(irq, &tgi->ic, handle_simple_irq);
 	}
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index 75c6355b018d..e72794e463aa 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -709,7 +709,13 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "input clock not found.\n");
 		return PTR_ERR(gpio->clk);
 	}
+	ret = clk_prepare_enable(gpio->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "Unable to enable clock.\n");
+		return ret;
+	}
 
+	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0)
@@ -747,6 +753,7 @@ err_pm_put:
 	pm_runtime_put(&pdev->dev);
 err_pm_dis:
 	pm_runtime_disable(&pdev->dev);
+	clk_disable_unprepare(gpio->clk);
 
 	return ret;
 }
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index d22dcc38179d..4aabddb38b59 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -16,6 +16,7 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/io.h>
+#include <linux/io-mapping.h>
 #include <linux/gpio/consumer.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 24f60d28f0c0..570771ed19e6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -449,7 +449,6 @@ static void gpiodevice_release(struct device *dev)
 {
 	struct gpio_device *gdev = dev_get_drvdata(dev);
 
-	cdev_del(&gdev->chrdev);
 	list_del(&gdev->list);
 	ida_simple_remove(&gpio_ida, gdev->id);
 	kfree(gdev->label);
@@ -482,7 +481,6 @@ static int gpiochip_setup_dev(struct gpio_device *gdev)
 
 	/* From this point, the .release() function cleans up gpio_device */
 	gdev->dev.release = gpiodevice_release;
-	get_device(&gdev->dev);
 	pr_debug("%s: registered GPIOs %d to %d on device: %s (%s)\n",
 		 __func__, gdev->base, gdev->base + gdev->ngpio - 1,
 		 dev_name(&gdev->dev), gdev->chip->label ? : "generic");
@@ -770,6 +768,8 @@ void gpiochip_remove(struct gpio_chip *chip)
 	 * be removed, else it will be dangling until the last user is
 	 * gone.
 	 */
+	cdev_del(&gdev->chrdev);
+	device_del(&gdev->dev);
 	put_device(&gdev->dev);
 }
 EXPORT_SYMBOL_GPL(gpiochip_remove);
@@ -869,7 +869,7 @@ struct gpio_chip *gpiochip_find(void *data,
 
 	spin_lock_irqsave(&gpio_lock, flags);
 	list_for_each_entry(gdev, &gpio_devices, list)
-		if (match(gdev->chip, data))
+		if (gdev->chip && match(gdev->chip, data))
 			break;
 
 	/* No match? */
@@ -1373,8 +1373,12 @@ done:
 #define VALIDATE_DESC(desc) do { \
 	if (!desc) \
 		return 0; \
+	if (IS_ERR(desc)) {						\
+		pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \
+		return PTR_ERR(desc); \
+	} \
 	if (!desc->gdev) { \
-		pr_warn("%s: invalid GPIO\n", __func__); \
+		pr_warn("%s: invalid GPIO (no device)\n", __func__); \
 		return -EINVAL; \
 	} \
 	if ( !desc->gdev->chip ) { \
@@ -1386,8 +1390,12 @@ done:
 #define VALIDATE_DESC_VOID(desc) do { \
 	if (!desc) \
 		return; \
+	if (IS_ERR(desc)) {						\
+		pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \
+		return; \
+	} \
 	if (!desc->gdev) { \
-		pr_warn("%s: invalid GPIO\n", __func__); \
+		pr_warn("%s: invalid GPIO (no device)\n", __func__); \
 		return; \
 	} \
 	if (!desc->gdev->chip) { \
@@ -2056,7 +2064,14 @@ int gpiod_to_irq(const struct gpio_desc *desc)
 	struct gpio_chip *chip;
 	int offset;
 
-	VALIDATE_DESC(desc);
+	/*
+	 * Cannot VALIDATE_DESC() here as gpiod_to_irq() consumer semantics
+	 * requires this function to not return zero on an invalid descriptor
+	 * but rather a negative error number.
+	 */
+	if (!desc || IS_ERR(desc) || !desc->gdev || !desc->gdev->chip)
+		return -EINVAL;
+
 	chip = desc->gdev->chip;
 	offset = gpio_chip_hwgpio(desc);
 	if (chip->to_irq) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 992f00b65be4..e055d5be1c3c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1820,6 +1820,8 @@ struct amdgpu_asic_funcs {
 	/* MM block clocks */
 	int (*set_uvd_clocks)(struct amdgpu_device *adev, u32 vclk, u32 dclk);
 	int (*set_vce_clocks)(struct amdgpu_device *adev, u32 evclk, u32 ecclk);
+	/* query virtual capabilities */
+	u32 (*get_virtual_caps)(struct amdgpu_device *adev);
 };
 
 /*
@@ -1914,8 +1916,12 @@ void amdgpu_cgs_destroy_device(struct cgs_device *cgs_device);
 
 
 /* GPU virtualization */
+#define AMDGPU_VIRT_CAPS_SRIOV_EN       (1 << 0)
+#define AMDGPU_VIRT_CAPS_IS_VF          (1 << 1)
 struct amdgpu_virtualization {
 	bool supports_sr_iov;
+	bool is_virtual;
+	u32 caps;
 };
 
 /*
@@ -2204,6 +2210,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_asic_get_xclk(adev) (adev)->asic_funcs->get_xclk((adev))
 #define amdgpu_asic_set_uvd_clocks(adev, v, d) (adev)->asic_funcs->set_uvd_clocks((adev), (v), (d))
 #define amdgpu_asic_set_vce_clocks(adev, ev, ec) (adev)->asic_funcs->set_vce_clocks((adev), (ev), (ec))
+#define amdgpu_asic_get_virtual_caps(adev) ((adev)->asic_funcs->get_virtual_caps((adev)))
 #define amdgpu_asic_get_gpu_clock_counter(adev) (adev)->asic_funcs->get_gpu_clock_counter((adev))
 #define amdgpu_asic_read_disabled_bios(adev) (adev)->asic_funcs->read_disabled_bios((adev))
 #define amdgpu_asic_read_bios_from_rom(adev, b, l) (adev)->asic_funcs->read_bios_from_rom((adev), (b), (l))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 199f76baf22c..cf6f49fc1c75 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -696,6 +696,17 @@ static uint32_t fw_type_convert(struct cgs_device *cgs_device, uint32_t fw_type)
 	return result;
 }
 
+static int amdgpu_cgs_rel_firmware(struct cgs_device *cgs_device, enum cgs_ucode_id type)
+{
+	CGS_FUNC_ADEV;
+	if ((CGS_UCODE_ID_SMU == type) || (CGS_UCODE_ID_SMU_SK == type)) {
+		release_firmware(adev->pm.fw);
+		return 0;
+	}
+	/* cannot release other firmware because they are not created by cgs */
+	return -EINVAL;
+}
+
 static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 					enum cgs_ucode_id type,
 					struct cgs_firmware_info *info)
@@ -898,7 +909,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
 	struct cgs_acpi_method_argument *argument = NULL;
 	uint32_t i, count;
 	acpi_status status;
-	int result;
+	int result = 0;
 	uint32_t func_no = 0xFFFFFFFF;
 
 	handle = ACPI_HANDLE(&adev->pdev->dev);
@@ -1125,6 +1136,7 @@ static const struct cgs_ops amdgpu_cgs_ops = {
 	amdgpu_cgs_pm_query_clock_limits,
 	amdgpu_cgs_set_camera_voltages,
 	amdgpu_cgs_get_firmware_info,
+	amdgpu_cgs_rel_firmware,
 	amdgpu_cgs_set_powergating_state,
 	amdgpu_cgs_set_clockgating_state,
 	amdgpu_cgs_get_active_displays_info,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index bb8b149786d7..6e920086af46 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -827,8 +827,10 @@ static uint32_t cail_ioreg_read(struct card_info *info, uint32_t reg)
  */
 static void amdgpu_atombios_fini(struct amdgpu_device *adev)
 {
-	if (adev->mode_info.atom_context)
+	if (adev->mode_info.atom_context) {
 		kfree(adev->mode_info.atom_context->scratch);
+		kfree(adev->mode_info.atom_context->iio);
+	}
 	kfree(adev->mode_info.atom_context);
 	adev->mode_info.atom_context = NULL;
 	kfree(adev->mode_info.atom_card_info);
@@ -1325,6 +1327,11 @@ static int amdgpu_fini(struct amdgpu_device *adev)
 		adev->ip_block_status[i].valid = false;
 	}
 
+	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
+		if (adev->ip_blocks[i].funcs->late_fini)
+			adev->ip_blocks[i].funcs->late_fini((void *)adev);
+	}
+
 	return 0;
 }
 
@@ -1378,6 +1385,15 @@ static int amdgpu_resume(struct amdgpu_device *adev)
 	return 0;
 }
 
+static bool amdgpu_device_is_virtual(void)
+{
+#ifdef CONFIG_X86
+	return boot_cpu_has(X86_FEATURE_HYPERVISOR);
+#else
+	return false;
+#endif
+}
+
 /**
  * amdgpu_device_init - initialize the driver
  *
@@ -1512,9 +1528,14 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	adev->virtualization.supports_sr_iov =
 		amdgpu_atombios_has_gpu_virtualization_table(adev);
 
+	/* Check if we are executing in a virtualized environment */
+	adev->virtualization.is_virtual = amdgpu_device_is_virtual();
+	adev->virtualization.caps = amdgpu_asic_get_virtual_caps(adev);
+
 	/* Post card if necessary */
 	if (!amdgpu_card_posted(adev) ||
-	    adev->virtualization.supports_sr_iov) {
+	    (adev->virtualization.is_virtual &&
+	     !(adev->virtualization.caps & AMDGPU_VIRT_CAPS_SRIOV_EN))) {
 		if (!adev->bios) {
 			dev_err(adev->dev, "Card not posted and no BIOS - ignoring\n");
 			return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 40a23704a981..d851ea15059f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -447,7 +447,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			dev_info.max_memory_clock = adev->pm.default_mclk * 10;
 		}
 		dev_info.enabled_rb_pipes_mask = adev->gfx.config.backend_enable_mask;
-		dev_info.num_rb_pipes = adev->gfx.config.num_rbs;
+		dev_info.num_rb_pipes = adev->gfx.config.max_backends_per_se *
+			adev->gfx.config.max_shader_engines;
 		dev_info.num_hw_gfx_contexts = adev->gfx.config.max_hw_contexts;
 		dev_info._pad = 0;
 		dev_info.ids_flags = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 589b36e8c5cf..0e13d80d2a95 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -270,30 +270,28 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	enum amd_pm_state_type state = 0;
-	long idx;
+	unsigned long idx;
 	int ret;
 
 	if (strlen(buf) == 1)
 		adev->pp_force_state_enabled = false;
-	else {
-		ret = kstrtol(buf, 0, &idx);
+	else if (adev->pp_enabled) {
+		struct pp_states_info data;
 
-		if (ret) {
+		ret = kstrtoul(buf, 0, &idx);
+		if (ret || idx >= ARRAY_SIZE(data.states)) {
 			count = -EINVAL;
 			goto fail;
 		}
 
-		if (adev->pp_enabled) {
-			struct pp_states_info data;
-			amdgpu_dpm_get_pp_num_states(adev, &data);
-			state = data.states[idx];
-			/* only set user selected power states */
-			if (state != POWER_STATE_TYPE_INTERNAL_BOOT &&
-				state != POWER_STATE_TYPE_DEFAULT) {
-				amdgpu_dpm_dispatch_task(adev,
-						AMD_PP_EVENT_ENABLE_USER_STATE, &state, NULL);
-				adev->pp_force_state_enabled = true;
-			}
+		amdgpu_dpm_get_pp_num_states(adev, &data);
+		state = data.states[idx];
+		/* only set user selected power states */
+		if (state != POWER_STATE_TYPE_INTERNAL_BOOT &&
+		    state != POWER_STATE_TYPE_DEFAULT) {
+			amdgpu_dpm_dispatch_task(adev,
+					AMD_PP_EVENT_ENABLE_USER_STATE, &state, NULL);
+			adev->pp_force_state_enabled = true;
 		}
 	}
 fail:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
index 6bd961fb43dc..82256558e0f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
@@ -183,13 +183,6 @@ static int amdgpu_pp_sw_fini(void *handle)
 	if (ret)
 		return ret;
 
-#ifdef CONFIG_DRM_AMD_POWERPLAY
-	if (adev->pp_enabled) {
-		amdgpu_pm_sysfs_fini(adev);
-		amd_powerplay_fini(adev->powerplay.pp_handle);
-	}
-#endif
-
 	return ret;
 }
 
@@ -223,6 +216,22 @@ static int amdgpu_pp_hw_fini(void *handle)
 	return ret;
 }
 
+static void amdgpu_pp_late_fini(void *handle)
+{
+#ifdef CONFIG_DRM_AMD_POWERPLAY
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (adev->pp_enabled) {
+		amdgpu_pm_sysfs_fini(adev);
+		amd_powerplay_fini(adev->powerplay.pp_handle);
+	}
+
+	if (adev->powerplay.ip_funcs->late_fini)
+		adev->powerplay.ip_funcs->late_fini(
+			  adev->powerplay.pp_handle);
+#endif
+}
+
 static int amdgpu_pp_suspend(void *handle)
 {
 	int ret = 0;
@@ -311,6 +320,7 @@ const struct amd_ip_funcs amdgpu_pp_ip_funcs = {
 	.sw_fini = amdgpu_pp_sw_fini,
 	.hw_init = amdgpu_pp_hw_init,
 	.hw_fini = amdgpu_pp_hw_fini,
+	.late_fini = amdgpu_pp_late_fini,
 	.suspend = amdgpu_pp_suspend,
 	.resume = amdgpu_pp_resume,
 	.is_idle = amdgpu_pp_is_idle,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 3b02272db678..870f9494252c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -343,6 +343,7 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
 	ring->ring = NULL;
 	ring->ring_obj = NULL;
 
+	amdgpu_wb_free(ring->adev, ring->cond_exe_offs);
 	amdgpu_wb_free(ring->adev, ring->fence_offs);
 	amdgpu_wb_free(ring->adev, ring->rptr_offs);
 	amdgpu_wb_free(ring->adev, ring->wptr_offs);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 8bf84efafb04..48618ee324eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -115,6 +115,7 @@ int amdgpu_sa_bo_manager_start(struct amdgpu_device *adev,
 		return r;
 	}
 	r = amdgpu_bo_kmap(sa_manager->bo, &sa_manager->cpu_ptr);
+	memset(sa_manager->cpu_ptr, 0, sa_manager->size);
 	amdgpu_bo_unreserve(sa_manager->bo);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 01abfc21b4a2..e19520c4b4b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -253,19 +253,20 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 {
 	int r;
 
-	if (adev->uvd.vcpu_bo == NULL)
-		return 0;
+	kfree(adev->uvd.saved_bo);
 
 	amd_sched_entity_fini(&adev->uvd.ring.sched, &adev->uvd.entity);
 
-	r = amdgpu_bo_reserve(adev->uvd.vcpu_bo, false);
-	if (!r) {
-		amdgpu_bo_kunmap(adev->uvd.vcpu_bo);
-		amdgpu_bo_unpin(adev->uvd.vcpu_bo);
-		amdgpu_bo_unreserve(adev->uvd.vcpu_bo);
-	}
+	if (adev->uvd.vcpu_bo) {
+		r = amdgpu_bo_reserve(adev->uvd.vcpu_bo, false);
+		if (!r) {
+			amdgpu_bo_kunmap(adev->uvd.vcpu_bo);
+			amdgpu_bo_unpin(adev->uvd.vcpu_bo);
+			amdgpu_bo_unreserve(adev->uvd.vcpu_bo);
+		}
 
-	amdgpu_bo_unref(&adev->uvd.vcpu_bo);
+		amdgpu_bo_unref(&adev->uvd.vcpu_bo);
+	}
 
 	amdgpu_ring_fini(&adev->uvd.ring);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index ea407db1fbcf..5ec1f1e9c983 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -6221,6 +6221,9 @@ static int ci_dpm_sw_fini(void *handle)
 	ci_dpm_fini(adev);
 	mutex_unlock(&adev->pm.mutex);
 
+	release_firmware(adev->pm.fw);
+	adev->pm.fw = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 07bc795a4ca9..910431808542 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -962,6 +962,12 @@ static bool cik_read_bios_from_rom(struct amdgpu_device *adev,
 	return true;
 }
 
+static u32 cik_get_virtual_caps(struct amdgpu_device *adev)
+{
+	/* CIK does not support SR-IOV */
+	return 0;
+}
+
 static const struct amdgpu_allowed_register_entry cik_allowed_read_registers[] = {
 	{mmGRBM_STATUS, false},
 	{mmGB_ADDR_CONFIG, false},
@@ -2007,6 +2013,7 @@ static const struct amdgpu_asic_funcs cik_asic_funcs =
 	.get_xclk = &cik_get_xclk,
 	.set_uvd_clocks = &cik_set_uvd_clocks,
 	.set_vce_clocks = &cik_set_vce_clocks,
+	.get_virtual_caps = &cik_get_virtual_caps,
 	/* these should be moved to their own ip modules */
 	.get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter,
 	.wait_for_mc_idle = &gmc_v7_0_mc_wait_for_idle,
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 518dca43b133..9dc4e24e31e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -66,6 +66,16 @@ MODULE_FIRMWARE("radeon/mullins_sdma1.bin");
 
 u32 amdgpu_cik_gpu_check_soft_reset(struct amdgpu_device *adev);
 
+
+static void cik_sdma_free_microcode(struct amdgpu_device *adev)
+{
+	int i;
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+			release_firmware(adev->sdma.instance[i].fw);
+			adev->sdma.instance[i].fw = NULL;
+	}
+}
+
 /*
  * sDMA - System DMA
  * Starting with CIK, the GPU has new asynchronous
@@ -419,6 +429,8 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev)
 		/* Initialize the ring buffer's read and write pointers */
 		WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0);
 		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0);
 
 		/* set the wb address whether it's enabled or not */
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
@@ -446,7 +458,12 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev)
 		WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl);
 
 		ring->ready = true;
+	}
+
+	cik_sdma_enable(adev, true);
 
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		ring = &adev->sdma.instance[i].ring;
 		r = amdgpu_ring_test_ring(ring);
 		if (r) {
 			ring->ready = false;
@@ -529,8 +546,8 @@ static int cik_sdma_start(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	/* unhalt the MEs */
-	cik_sdma_enable(adev, true);
+	/* halt the engine before programing */
+	cik_sdma_enable(adev, false);
 
 	/* start the gfx rings and rlc compute queues */
 	r = cik_sdma_gfx_resume(adev);
@@ -998,6 +1015,7 @@ static int cik_sdma_sw_fini(void *handle)
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	cik_sdma_free_microcode(adev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c b/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
index 245cabf06575..ed03b75175d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
@@ -72,6 +72,11 @@ static int fiji_dpm_sw_init(void *handle)
 
 static int fiji_dpm_sw_fini(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	release_firmware(adev->pm.fw);
+	adev->pm.fw = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 7f18a53ab53a..fc8ff4d3ccf8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -991,6 +991,22 @@ out:
 	return err;
 }
 
+static void gfx_v7_0_free_microcode(struct amdgpu_device *adev)
+{
+	release_firmware(adev->gfx.pfp_fw);
+	adev->gfx.pfp_fw = NULL;
+	release_firmware(adev->gfx.me_fw);
+	adev->gfx.me_fw = NULL;
+	release_firmware(adev->gfx.ce_fw);
+	adev->gfx.ce_fw = NULL;
+	release_firmware(adev->gfx.mec_fw);
+	adev->gfx.mec_fw = NULL;
+	release_firmware(adev->gfx.mec2_fw);
+	adev->gfx.mec2_fw = NULL;
+	release_firmware(adev->gfx.rlc_fw);
+	adev->gfx.rlc_fw = NULL;
+}
+
 /**
  * gfx_v7_0_tiling_mode_table_init - init the hw tiling table
  *
@@ -4489,6 +4505,7 @@ static int gfx_v7_0_sw_fini(void *handle)
 	gfx_v7_0_cp_compute_fini(adev);
 	gfx_v7_0_rlc_fini(adev);
 	gfx_v7_0_mec_fini(adev);
+	gfx_v7_0_free_microcode(adev);
 
 	return 0;
 }
@@ -4816,7 +4833,7 @@ static int gfx_v7_0_eop_irq(struct amdgpu_device *adev,
 	case 2:
 		for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 			ring = &adev->gfx.compute_ring[i];
-			if ((ring->me == me_id) & (ring->pipe == pipe_id))
+			if ((ring->me == me_id) && (ring->pipe == pipe_id))
 				amdgpu_fence_process(ring);
 		}
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index f19bab68fd83..1a5cbaff1e34 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -297,7 +297,8 @@ static const u32 polaris11_golden_common_all[] =
 static const u32 golden_settings_polaris10_a11[] =
 {
 	mmATC_MISC_CG, 0x000c0fc0, 0x000c0200,
-	mmCB_HW_CONTROL, 0xfffdf3cf, 0x00006208,
+	mmCB_HW_CONTROL, 0xfffdf3cf, 0x00007208,
+	mmCB_HW_CONTROL_2, 0, 0x0f000000,
 	mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040,
 	mmDB_DEBUG2, 0xf00fffff, 0x00000400,
 	mmPA_SC_ENHANCE, 0xffffffff, 0x20000001,
@@ -836,6 +837,26 @@ err1:
 	return r;
 }
 
+
+static void gfx_v8_0_free_microcode(struct amdgpu_device *adev) {
+	release_firmware(adev->gfx.pfp_fw);
+	adev->gfx.pfp_fw = NULL;
+	release_firmware(adev->gfx.me_fw);
+	adev->gfx.me_fw = NULL;
+	release_firmware(adev->gfx.ce_fw);
+	adev->gfx.ce_fw = NULL;
+	release_firmware(adev->gfx.rlc_fw);
+	adev->gfx.rlc_fw = NULL;
+	release_firmware(adev->gfx.mec_fw);
+	adev->gfx.mec_fw = NULL;
+	if ((adev->asic_type != CHIP_STONEY) &&
+	    (adev->asic_type != CHIP_TOPAZ))
+		release_firmware(adev->gfx.mec2_fw);
+	adev->gfx.mec2_fw = NULL;
+
+	kfree(adev->gfx.rlc.register_list_format);
+}
+
 static int gfx_v8_0_init_microcode(struct amdgpu_device *adev)
 {
 	const char *chip_name;
@@ -1983,7 +2004,7 @@ static int gfx_v8_0_sw_fini(void *handle)
 
 	gfx_v8_0_rlc_fini(adev);
 
-	kfree(adev->gfx.rlc.register_list_format);
+	gfx_v8_0_free_microcode(adev);
 
 	return 0;
 }
@@ -3974,11 +3995,15 @@ static int gfx_v8_0_cp_gfx_start(struct amdgpu_device *adev)
 		amdgpu_ring_write(ring, 0x3a00161a);
 		amdgpu_ring_write(ring, 0x0000002e);
 		break;
-	case CHIP_TOPAZ:
 	case CHIP_CARRIZO:
 		amdgpu_ring_write(ring, 0x00000002);
 		amdgpu_ring_write(ring, 0x00000000);
 		break;
+	case CHIP_TOPAZ:
+		amdgpu_ring_write(ring, adev->gfx.config.num_rbs == 1 ?
+				0x00000000 : 0x00000002);
+		amdgpu_ring_write(ring, 0x00000000);
+		break;
 	case CHIP_STONEY:
 		amdgpu_ring_write(ring, 0x00000000);
 		amdgpu_ring_write(ring, 0x00000000);
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
index 460bc8ad37e6..825ccd63f2dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
@@ -72,6 +72,11 @@ static int iceland_dpm_sw_init(void *handle)
 
 static int iceland_dpm_sw_fini(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	release_firmware(adev->pm.fw);
+	adev->pm.fw = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index f4c3130d3fdb..b556bd0a8797 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -105,6 +105,15 @@ static void sdma_v2_4_init_golden_registers(struct amdgpu_device *adev)
 	}
 }
 
+static void sdma_v2_4_free_microcode(struct amdgpu_device *adev)
+{
+	int i;
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		release_firmware(adev->sdma.instance[i].fw);
+		adev->sdma.instance[i].fw = NULL;
+	}
+}
+
 /**
  * sdma_v2_4_init_microcode - load ucode images from disk
  *
@@ -461,6 +470,8 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev)
 		/* Initialize the ring buffer's read and write pointers */
 		WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0);
 		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0);
 
 		/* set the wb address whether it's enabled or not */
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
@@ -489,7 +500,11 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev)
 		WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl);
 
 		ring->ready = true;
+	}
 
+	sdma_v2_4_enable(adev, true);
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		ring = &adev->sdma.instance[i].ring;
 		r = amdgpu_ring_test_ring(ring);
 		if (r) {
 			ring->ready = false;
@@ -580,8 +595,8 @@ static int sdma_v2_4_start(struct amdgpu_device *adev)
 			return -EINVAL;
 	}
 
-	/* unhalt the MEs */
-	sdma_v2_4_enable(adev, true);
+	/* halt the engine before programing */
+	sdma_v2_4_enable(adev, false);
 
 	/* start the gfx rings and rlc compute queues */
 	r = sdma_v2_4_gfx_resume(adev);
@@ -1012,6 +1027,7 @@ static int sdma_v2_4_sw_fini(void *handle)
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	sdma_v2_4_free_microcode(adev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 31d99b0010f7..532ea88da66a 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -236,6 +236,15 @@ static void sdma_v3_0_init_golden_registers(struct amdgpu_device *adev)
 	}
 }
 
+static void sdma_v3_0_free_microcode(struct amdgpu_device *adev)
+{
+	int i;
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		release_firmware(adev->sdma.instance[i].fw);
+		adev->sdma.instance[i].fw = NULL;
+	}
+}
+
 /**
  * sdma_v3_0_init_microcode - load ucode images from disk
  *
@@ -672,6 +681,8 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
 		/* Initialize the ring buffer's read and write pointers */
 		WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0);
 		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0);
 
 		/* set the wb address whether it's enabled or not */
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
@@ -711,7 +722,15 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
 		WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl);
 
 		ring->ready = true;
+	}
+
+	/* unhalt the MEs */
+	sdma_v3_0_enable(adev, true);
+	/* enable sdma ring preemption */
+	sdma_v3_0_ctx_switch_enable(adev, true);
 
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		ring = &adev->sdma.instance[i].ring;
 		r = amdgpu_ring_test_ring(ring);
 		if (r) {
 			ring->ready = false;
@@ -804,10 +823,9 @@ static int sdma_v3_0_start(struct amdgpu_device *adev)
 		}
 	}
 
-	/* unhalt the MEs */
-	sdma_v3_0_enable(adev, true);
-	/* enable sdma ring preemption */
-	sdma_v3_0_ctx_switch_enable(adev, true);
+	/* disble sdma engine before programing it */
+	sdma_v3_0_ctx_switch_enable(adev, false);
+	sdma_v3_0_enable(adev, false);
 
 	/* start the gfx rings and rlc compute queues */
 	r = sdma_v3_0_gfx_resume(adev);
@@ -1247,6 +1265,7 @@ static int sdma_v3_0_sw_fini(void *handle)
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	sdma_v3_0_free_microcode(adev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
index b7615cefcac4..f06f6f4dc3a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
@@ -71,6 +71,11 @@ static int tonga_dpm_sw_init(void *handle)
 
 static int tonga_dpm_sw_fini(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	release_firmware(adev->pm.fw);
+	adev->pm.fw = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 2c88d0b66cf3..a65c96029476 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -421,6 +421,20 @@ static bool vi_read_bios_from_rom(struct amdgpu_device *adev,
 	return true;
 }
 
+static u32 vi_get_virtual_caps(struct amdgpu_device *adev)
+{
+	u32 caps = 0;
+	u32 reg = RREG32(mmBIF_IOV_FUNC_IDENTIFIER);
+
+	if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, IOV_ENABLE))
+		caps |= AMDGPU_VIRT_CAPS_SRIOV_EN;
+
+	if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, FUNC_IDENTIFIER))
+		caps |= AMDGPU_VIRT_CAPS_IS_VF;
+
+	return caps;
+}
+
 static const struct amdgpu_allowed_register_entry tonga_allowed_read_registers[] = {
 	{mmGB_MACROTILE_MODE7, true},
 };
@@ -1118,6 +1132,7 @@ static const struct amdgpu_asic_funcs vi_asic_funcs =
 	.get_xclk = &vi_get_xclk,
 	.set_uvd_clocks = &vi_set_uvd_clocks,
 	.set_vce_clocks = &vi_set_vce_clocks,
+	.get_virtual_caps = &vi_get_virtual_caps,
 	/* these should be moved to their own ip modules */
 	.get_gpu_clock_counter = &gfx_v8_0_get_gpu_clock_counter,
 	.wait_for_mc_idle = &gmc_v8_0_mc_wait_for_idle,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index ac005796b71c..7708d90b9da9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -242,13 +242,19 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
 	pqm_uninit(&p->pqm);
 
 	/* Iterate over all process device data structure and check
-	 * if we should reset all wavefronts */
-	list_for_each_entry(pdd, &p->per_device_data, per_device_list)
+	 * if we should delete debug managers and reset all wavefronts
+	 */
+	list_for_each_entry(pdd, &p->per_device_data, per_device_list) {
+		if ((pdd->dev->dbgmgr) &&
+				(pdd->dev->dbgmgr->pasid == p->pasid))
+			kfd_dbgmgr_destroy(pdd->dev->dbgmgr);
+
 		if (pdd->reset_wavefronts) {
 			pr_warn("amdkfd: Resetting all wave fronts\n");
 			dbgdev_wave_reset_wavefronts(pdd->dev, p);
 			pdd->reset_wavefronts = false;
 		}
+	}
 
 	mutex_unlock(&p->mutex);
 
@@ -404,42 +410,52 @@ void kfd_unbind_process_from_device(struct kfd_dev *dev, unsigned int pasid)
 
 	idx = srcu_read_lock(&kfd_processes_srcu);
 
+	/*
+	 * Look for the process that matches the pasid. If there is no such
+	 * process, we either released it in amdkfd's own notifier, or there
+	 * is a bug. Unfortunately, there is no way to tell...
+	 */
 	hash_for_each_rcu(kfd_processes_table, i, p, kfd_processes)
-		if (p->pasid == pasid)
-			break;
+		if (p->pasid == pasid) {
 
-	srcu_read_unlock(&kfd_processes_srcu, idx);
+			srcu_read_unlock(&kfd_processes_srcu, idx);
 
-	BUG_ON(p->pasid != pasid);
+			pr_debug("Unbinding process %d from IOMMU\n", pasid);
 
-	mutex_lock(&p->mutex);
+			mutex_lock(&p->mutex);
 
-	if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid))
-		kfd_dbgmgr_destroy(dev->dbgmgr);
+			if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid))
+				kfd_dbgmgr_destroy(dev->dbgmgr);
 
-	pqm_uninit(&p->pqm);
+			pqm_uninit(&p->pqm);
 
-	pdd = kfd_get_process_device_data(dev, p);
+			pdd = kfd_get_process_device_data(dev, p);
 
-	if (!pdd) {
-		mutex_unlock(&p->mutex);
-		return;
-	}
+			if (!pdd) {
+				mutex_unlock(&p->mutex);
+				return;
+			}
 
-	if (pdd->reset_wavefronts) {
-		dbgdev_wave_reset_wavefronts(pdd->dev, p);
-		pdd->reset_wavefronts = false;
-	}
+			if (pdd->reset_wavefronts) {
+				dbgdev_wave_reset_wavefronts(pdd->dev, p);
+				pdd->reset_wavefronts = false;
+			}
 
-	/*
-	 * Just mark pdd as unbound, because we still need it to call
-	 * amd_iommu_unbind_pasid() in when the process exits.
-	 * We don't call amd_iommu_unbind_pasid() here
-	 * because the IOMMU called us.
-	 */
-	pdd->bound = false;
+			/*
+			 * Just mark pdd as unbound, because we still need it
+			 * to call amd_iommu_unbind_pasid() in when the
+			 * process exits.
+			 * We don't call amd_iommu_unbind_pasid() here
+			 * because the IOMMU called us.
+			 */
+			pdd->bound = false;
 
-	mutex_unlock(&p->mutex);
+			mutex_unlock(&p->mutex);
+
+			return;
+		}
+
+	srcu_read_unlock(&kfd_processes_srcu, idx);
 }
 
 struct kfd_process_device *kfd_get_first_process_device_data(struct kfd_process *p)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 74909e72a009..884c96f50c3d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -666,7 +666,7 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 			dev->node_props.simd_count);
 
 	if (dev->mem_bank_count < dev->node_props.mem_banks_count) {
-		pr_warn("kfd: mem_banks_count truncated from %d to %d\n",
+		pr_info_once("kfd: mem_banks_count truncated from %d to %d\n",
 				dev->node_props.mem_banks_count,
 				dev->mem_bank_count);
 		sysfs_show_32bit_prop(buffer, "mem_banks_count",
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 6080951d539d..afce1edbe250 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -157,6 +157,7 @@ struct amd_ip_funcs {
 	int (*hw_init)(void *handle);
 	/* tears down the hw state */
 	int (*hw_fini)(void *handle);
+	void (*late_fini)(void *handle);
 	/* handles IP specific hw/sw changes for suspend */
 	int (*suspend)(void *handle);
 	/* handles IP specific hw/sw changes for resume */
diff --git a/drivers/gpu/drm/amd/include/atombios.h b/drivers/gpu/drm/amd/include/atombios.h
index 32f3e345de08..3493da5c8f0e 100644
--- a/drivers/gpu/drm/amd/include/atombios.h
+++ b/drivers/gpu/drm/amd/include/atombios.h
@@ -5538,6 +5538,78 @@ typedef struct  _ATOM_ASIC_PROFILING_INFO_V3_5
   ULONG  ulReserved[12];
 }ATOM_ASIC_PROFILING_INFO_V3_5;
 
+/* for Polars10/11 AVFS parameters */
+typedef struct  _ATOM_ASIC_PROFILING_INFO_V3_6
+{
+  ATOM_COMMON_TABLE_HEADER         asHeader;
+  ULONG  ulMaxVddc;
+  ULONG  ulMinVddc;
+  USHORT usLkgEuseIndex;
+  UCHAR  ucLkgEfuseBitLSB;
+  UCHAR  ucLkgEfuseLength;
+  ULONG  ulLkgEncodeLn_MaxDivMin;
+  ULONG  ulLkgEncodeMax;
+  ULONG  ulLkgEncodeMin;
+  EFUSE_LINEAR_FUNC_PARAM sRoFuse;
+  ULONG  ulEvvDefaultVddc;
+  ULONG  ulEvvNoCalcVddc;
+  ULONG  ulSpeed_Model;
+  ULONG  ulSM_A0;
+  ULONG  ulSM_A1;
+  ULONG  ulSM_A2;
+  ULONG  ulSM_A3;
+  ULONG  ulSM_A4;
+  ULONG  ulSM_A5;
+  ULONG  ulSM_A6;
+  ULONG  ulSM_A7;
+  UCHAR  ucSM_A0_sign;
+  UCHAR  ucSM_A1_sign;
+  UCHAR  ucSM_A2_sign;
+  UCHAR  ucSM_A3_sign;
+  UCHAR  ucSM_A4_sign;
+  UCHAR  ucSM_A5_sign;
+  UCHAR  ucSM_A6_sign;
+  UCHAR  ucSM_A7_sign;
+  ULONG  ulMargin_RO_a;
+  ULONG  ulMargin_RO_b;
+  ULONG  ulMargin_RO_c;
+  ULONG  ulMargin_fixed;
+  ULONG  ulMargin_Fmax_mean;
+  ULONG  ulMargin_plat_mean;
+  ULONG  ulMargin_Fmax_sigma;
+  ULONG  ulMargin_plat_sigma;
+  ULONG  ulMargin_DC_sigma;
+  ULONG  ulLoadLineSlop;
+  ULONG  ulaTDClimitPerDPM[8];
+  ULONG  ulaNoCalcVddcPerDPM[8];
+  ULONG  ulAVFS_meanNsigma_Acontant0;
+  ULONG  ulAVFS_meanNsigma_Acontant1;
+  ULONG  ulAVFS_meanNsigma_Acontant2;
+  USHORT usAVFS_meanNsigma_DC_tol_sigma;
+  USHORT usAVFS_meanNsigma_Platform_mean;
+  USHORT usAVFS_meanNsigma_Platform_sigma;
+  ULONG  ulGB_VDROOP_TABLE_CKSOFF_a0;
+  ULONG  ulGB_VDROOP_TABLE_CKSOFF_a1;
+  ULONG  ulGB_VDROOP_TABLE_CKSOFF_a2;
+  ULONG  ulGB_VDROOP_TABLE_CKSON_a0;
+  ULONG  ulGB_VDROOP_TABLE_CKSON_a1;
+  ULONG  ulGB_VDROOP_TABLE_CKSON_a2;
+  ULONG  ulAVFSGB_FUSE_TABLE_CKSOFF_m1;
+  USHORT usAVFSGB_FUSE_TABLE_CKSOFF_m2;
+  ULONG  ulAVFSGB_FUSE_TABLE_CKSOFF_b;
+  ULONG  ulAVFSGB_FUSE_TABLE_CKSON_m1;
+  USHORT usAVFSGB_FUSE_TABLE_CKSON_m2;
+  ULONG  ulAVFSGB_FUSE_TABLE_CKSON_b;
+  USHORT usMaxVoltage_0_25mv;
+  UCHAR  ucEnableGB_VDROOP_TABLE_CKSOFF;
+  UCHAR  ucEnableGB_VDROOP_TABLE_CKSON;
+  UCHAR  ucEnableGB_FUSE_TABLE_CKSOFF;
+  UCHAR  ucEnableGB_FUSE_TABLE_CKSON;
+  USHORT usPSM_Age_ComFactor;
+  UCHAR  ucEnableApplyAVFS_CKS_OFF_Voltage;
+  UCHAR  ucReserved;
+}ATOM_ASIC_PROFILING_INFO_V3_6;
+
 
 typedef struct _ATOM_SCLK_FCW_RANGE_ENTRY_V1{
   ULONG  ulMaxSclkFreq;
diff --git a/drivers/gpu/drm/amd/include/cgs_common.h b/drivers/gpu/drm/amd/include/cgs_common.h
index a461e155a160..7464daf89ca1 100644
--- a/drivers/gpu/drm/amd/include/cgs_common.h
+++ b/drivers/gpu/drm/amd/include/cgs_common.h
@@ -581,6 +581,9 @@ typedef int (*cgs_get_firmware_info)(struct cgs_device *cgs_device,
 				     enum cgs_ucode_id type,
 				     struct cgs_firmware_info *info);
 
+typedef int (*cgs_rel_firmware)(struct cgs_device *cgs_device,
+					 enum cgs_ucode_id type);
+
 typedef int(*cgs_set_powergating_state)(struct cgs_device *cgs_device,
 				  enum amd_ip_block_type block_type,
 				  enum amd_powergating_state state);
@@ -645,6 +648,7 @@ struct cgs_ops {
 	cgs_set_camera_voltages_t set_camera_voltages;
 	/* Firmware Info */
 	cgs_get_firmware_info get_firmware_info;
+	cgs_rel_firmware rel_firmware;
 	/* cg pg interface*/
 	cgs_set_powergating_state set_powergating_state;
 	cgs_set_clockgating_state set_clockgating_state;
@@ -738,6 +742,8 @@ struct cgs_device
 	CGS_CALL(set_camera_voltages,dev,mask,voltages)
 #define cgs_get_firmware_info(dev, type, info)	\
 	CGS_CALL(get_firmware_info, dev, type, info)
+#define cgs_rel_firmware(dev, type)	\
+	CGS_CALL(rel_firmware, dev, type)
 #define cgs_set_powergating_state(dev, block_type, state)	\
 	CGS_CALL(set_powergating_state, dev, block_type, state)
 #define cgs_set_clockgating_state(dev, block_type, state)	\
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index 8e345bfddb69..e629f8a9fe93 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -73,11 +73,14 @@ static int pp_sw_init(void *handle)
 
 	ret = hwmgr->hwmgr_func->backend_init(hwmgr);
 	if (ret)
-		goto err;
+		goto err1;
 
 	pr_info("amdgpu: powerplay initialized\n");
 
 	return 0;
+err1:
+	if (hwmgr->pptable_func->pptable_fini)
+		hwmgr->pptable_func->pptable_fini(hwmgr);
 err:
 	pr_err("amdgpu: powerplay initialization failed\n");
 	return ret;
@@ -100,6 +103,9 @@ static int pp_sw_fini(void *handle)
 	if (hwmgr->hwmgr_func->backend_fini != NULL)
 		ret = hwmgr->hwmgr_func->backend_fini(hwmgr);
 
+	if (hwmgr->pptable_func->pptable_fini)
+		hwmgr->pptable_func->pptable_fini(hwmgr);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
index 46410e3c7349..fb88e4e5d625 100644
--- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
@@ -58,9 +58,6 @@ static void pem_fini(struct pp_eventmgr *eventmgr)
 	pem_unregister_interrupts(eventmgr);
 
 	pem_handle_event(eventmgr, AMD_PP_EVENT_UNINITIALIZE, &event_data);
-
-	if (eventmgr != NULL)
-		kfree(eventmgr);
 }
 
 int eventmgr_init(struct pp_instance *handle)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
index 24a16e49b571..92912ab20944 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
@@ -633,6 +633,8 @@ static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	data->vddci_control = FIJI_VOLTAGE_CONTROL_NONE;
 	data->mvdd_control = FIJI_VOLTAGE_CONTROL_NONE;
 
+	data->force_pcie_gen = PP_PCIEGenInvalid;
+
 	if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr,
 			VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2))
 		data->voltage_control = FIJI_VOLTAGE_CONTROL_BY_SVID2;
@@ -1830,7 +1832,7 @@ static uint16_t fiji_find_closest_vddci(struct pp_hwmgr *hwmgr, uint16_t vddci)
 
 	PP_ASSERT_WITH_CODE(false,
 			"VDDCI is larger than max VDDCI in VDDCI Voltage Table!",
-			return vddci_table->entries[i].value);
+			return vddci_table->entries[i-1].value);
 }
 
 static int fiji_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
index fa208ada6892..efb77eda7508 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
@@ -306,10 +306,14 @@ int phm_store_dal_configuration_data(struct pp_hwmgr *hwmgr,
 {
 	PHM_FUNC_CHECK(hwmgr);
 
-	if (hwmgr->hwmgr_func->store_cc6_data == NULL)
+	if (display_config == NULL)
 		return -EINVAL;
 
 	hwmgr->display_config = *display_config;
+
+	if (hwmgr->hwmgr_func->store_cc6_data == NULL)
+		return -EINVAL;
+
 	/* to do pass other display configuration in furture */
 
 	if (hwmgr->hwmgr_func->store_cc6_data)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index 1c48917da3cf..20f20e075588 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -93,6 +93,13 @@ int hwmgr_fini(struct pp_hwmgr *hwmgr)
 	if (hwmgr == NULL || hwmgr->ps == NULL)
 		return -EINVAL;
 
+	/* do hwmgr finish*/
+	kfree(hwmgr->backend);
+
+	kfree(hwmgr->start_thermal_controller.function_list);
+
+	kfree(hwmgr->set_temperature_range.function_list);
+
 	kfree(hwmgr->ps);
 	kfree(hwmgr);
 	return 0;
@@ -462,7 +469,7 @@ uint16_t phm_find_closest_vddci(struct pp_atomctrl_voltage_table *vddci_table, u
 
 	PP_ASSERT_WITH_CODE(false,
 			"VDDCI is larger than max VDDCI in VDDCI Voltage Table!",
-			return vddci_table->entries[i].value);
+			return vddci_table->entries[i-1].value);
 }
 
 int phm_find_boot_level(void *table,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h
index 347fef127ce9..2930a3355948 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h
@@ -39,6 +39,7 @@ struct phm_ppt_v1_clock_voltage_dependency_record {
 	uint8_t phases;
 	uint8_t cks_enable;
 	uint8_t cks_voffset;
+	uint32_t sclk_offset;
 };
 
 typedef struct phm_ppt_v1_clock_voltage_dependency_record phm_ppt_v1_clock_voltage_dependency_record;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
index aa6be033f21b..64ee78f7d41e 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
@@ -999,7 +999,7 @@ static int polaris10_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr,
 				vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
 						(dep_table->entries[i].vddc -
 								(uint16_t)data->vddc_vddci_delta));
-				*voltage |= (vddci * VOLTAGE_SCALE) <<	VDDCI_SHIFT;
+				*voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
 			}
 
 			if (POLARIS10_VOLTAGE_CONTROL_NONE == data->mvdd_control)
@@ -1296,7 +1296,6 @@ static int polaris10_populate_single_memory_level(struct pp_hwmgr *hwmgr,
 	}
 
 	mem_level->MclkFrequency = clock;
-	mem_level->StutterEnable = 0;
 	mem_level->EnabledForThrottle = 1;
 	mem_level->EnabledForActivity = 0;
 	mem_level->UpHyst = 0;
@@ -1304,7 +1303,6 @@ static int polaris10_populate_single_memory_level(struct pp_hwmgr *hwmgr,
 	mem_level->VoltageDownHyst = 0;
 	mem_level->ActivityLevel = (uint16_t)data->mclk_activity_target;
 	mem_level->StutterEnable = false;
-
 	mem_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
 
 	data->display_timing.num_existing_displays = info.display_count;
@@ -1363,7 +1361,7 @@ static int polaris10_populate_all_memory_levels(struct pp_hwmgr *hwmgr)
 	 * a higher state by default such that we are not effected by
 	 * up threshold or and MCLK DPM latency.
 	 */
-	levels[0].ActivityLevel = (uint16_t)data->mclk_dpm0_activity_target;
+	levels[0].ActivityLevel = 0x1f;
 	CONVERT_FROM_HOST_TO_SMC_US(levels[0].ActivityLevel);
 
 	data->smc_state_table.MemoryDpmLevelCount =
@@ -1761,12 +1759,9 @@ static int polaris10_populate_smc_initailial_state(struct pp_hwmgr *hwmgr)
 
 static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 {
-	uint32_t ro, efuse, efuse2, clock_freq, volt_without_cks,
-			volt_with_cks, value;
-	uint16_t clock_freq_u16;
+	uint32_t ro, efuse, volt_without_cks, volt_with_cks, value, max, min;
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
-	uint8_t type, i, j, cks_setting, stretch_amount, stretch_amount2,
-			volt_offset = 0;
+	uint8_t i, stretch_amount, stretch_amount2, volt_offset = 0;
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
@@ -1778,50 +1773,38 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 	 * if the part is SS or FF. if RO >= 1660MHz, part is FF.
 	 */
 	efuse = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC,
-			ixSMU_EFUSE_0 + (146 * 4));
-	efuse2 = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC,
-			ixSMU_EFUSE_0 + (148 * 4));
+			ixSMU_EFUSE_0 + (67 * 4));
 	efuse &= 0xFF000000;
 	efuse = efuse >> 24;
-	efuse2 &= 0xF;
-
-	if (efuse2 == 1)
-		ro = (2300 - 1350) * efuse / 255 + 1350;
-	else
-		ro = (2500 - 1000) * efuse / 255 + 1000;
 
-	if (ro >= 1660)
-		type = 0;
-	else
-		type = 1;
+	if (hwmgr->chip_id == CHIP_POLARIS10) {
+		min = 1000;
+		max = 2300;
+	} else {
+		min = 1100;
+		max = 2100;
+	}
 
-	/* Populate Stretch amount */
-	data->smc_state_table.ClockStretcherAmount = stretch_amount;
+	ro = efuse * (max -min)/255 + min;
 
 	/* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset */
 	for (i = 0; i < sclk_table->count; i++) {
 		data->smc_state_table.Sclk_CKS_masterEn0_7 |=
 				sclk_table->entries[i].cks_enable << i;
-		volt_without_cks = (uint32_t)((14041 *
-			(sclk_table->entries[i].clk/100) / 10000 + 3571 + 75 - ro) * 1000 /
-			(4026 - (13924 * (sclk_table->entries[i].clk/100) / 10000)));
-		volt_with_cks = (uint32_t)((13946 *
-			(sclk_table->entries[i].clk/100) / 10000 + 3320 + 45 - ro) * 1000 /
-			(3664 - (11454 * (sclk_table->entries[i].clk/100) / 10000)));
+
+		volt_without_cks =  (uint32_t)(((ro - 40) * 1000 - 2753594 - sclk_table->entries[i].clk/100 * 136418 /1000) / \
+					(sclk_table->entries[i].clk/100 * 1132925 /10000 - 242418)/100);
+
+		volt_with_cks = (uint32_t)((ro * 1000 -2396351 - sclk_table->entries[i].clk/100 * 329021/1000) / \
+				(sclk_table->entries[i].clk/10000 * 649434 /1000  - 18005)/10);
+
 		if (volt_without_cks >= volt_with_cks)
 			volt_offset = (uint8_t)(((volt_without_cks - volt_with_cks +
 					sclk_table->entries[i].cks_voffset) * 100 / 625) + 1);
+
 		data->smc_state_table.Sclk_voltageOffset[i] = volt_offset;
 	}
 
-	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE,
-			STRETCH_ENABLE, 0x0);
-	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE,
-			masterReset, 0x1);
-	/* PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE, staticEnable, 0x1); */
-	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE,
-			masterReset, 0x0);
-
 	/* Populate CKS Lookup Table */
 	if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5)
 		stretch_amount2 = 0;
@@ -1835,69 +1818,6 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 				return -EINVAL);
 	}
 
-	value = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC,
-			ixPWR_CKS_CNTL);
-	value &= 0xFFC2FF87;
-	data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].minFreq =
-			polaris10_clock_stretcher_lookup_table[stretch_amount2][0];
-	data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].maxFreq =
-			polaris10_clock_stretcher_lookup_table[stretch_amount2][1];
-	clock_freq_u16 = (uint16_t)(PP_SMC_TO_HOST_UL(data->smc_state_table.
-			GraphicsLevel[data->smc_state_table.GraphicsDpmLevelCount - 1].SclkSetting.SclkFrequency) / 100);
-	if (polaris10_clock_stretcher_lookup_table[stretch_amount2][0] < clock_freq_u16
-	&& polaris10_clock_stretcher_lookup_table[stretch_amount2][1] > clock_freq_u16) {
-		/* Program PWR_CKS_CNTL. CKS_USE_FOR_LOW_FREQ */
-		value |= (polaris10_clock_stretcher_lookup_table[stretch_amount2][3]) << 16;
-		/* Program PWR_CKS_CNTL. CKS_LDO_REFSEL */
-		value |= (polaris10_clock_stretcher_lookup_table[stretch_amount2][2]) << 18;
-		/* Program PWR_CKS_CNTL. CKS_STRETCH_AMOUNT */
-		value |= (polaris10_clock_stretch_amount_conversion
-				[polaris10_clock_stretcher_lookup_table[stretch_amount2][3]]
-				 [stretch_amount]) << 3;
-	}
-	CONVERT_FROM_HOST_TO_SMC_US(data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].minFreq);
-	CONVERT_FROM_HOST_TO_SMC_US(data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].maxFreq);
-	data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].setting =
-			polaris10_clock_stretcher_lookup_table[stretch_amount2][2] & 0x7F;
-	data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].setting |=
-			(polaris10_clock_stretcher_lookup_table[stretch_amount2][3]) << 7;
-
-	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
-			ixPWR_CKS_CNTL, value);
-
-	/* Populate DDT Lookup Table */
-	for (i = 0; i < 4; i++) {
-		/* Assign the minimum and maximum VID stored
-		 * in the last row of Clock Stretcher Voltage Table.
-		 */
-		data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].minVID =
-				(uint8_t) polaris10_clock_stretcher_ddt_table[type][i][2];
-		data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].maxVID =
-				(uint8_t) polaris10_clock_stretcher_ddt_table[type][i][3];
-		/* Loop through each SCLK and check the frequency
-		 * to see if it lies within the frequency for clock stretcher.
-		 */
-		for (j = 0; j < data->smc_state_table.GraphicsDpmLevelCount; j++) {
-			cks_setting = 0;
-			clock_freq = PP_SMC_TO_HOST_UL(
-					data->smc_state_table.GraphicsLevel[j].SclkSetting.SclkFrequency);
-			/* Check the allowed frequency against the sclk level[j].
-			 *  Sclk's endianness has already been converted,
-			 *  and it's in 10Khz unit,
-			 *  as opposed to Data table, which is in Mhz unit.
-			 */
-			if (clock_freq >= (polaris10_clock_stretcher_ddt_table[type][i][0]) * 100) {
-				cks_setting |= 0x2;
-				if (clock_freq < (polaris10_clock_stretcher_ddt_table[type][i][1]) * 100)
-					cks_setting |= 0x1;
-			}
-			data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].setting
-							|= cks_setting << (j * 2);
-		}
-		CONVERT_FROM_HOST_TO_SMC_US(
-			data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].setting);
-	}
-
 	value = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL);
 	value &= 0xFFFFFFFE;
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL, value);
@@ -1956,6 +1876,90 @@ static int polaris10_populate_vr_config(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
+
+int polaris10_populate_avfs_parameters(struct pp_hwmgr *hwmgr)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	SMU74_Discrete_DpmTable  *table = &(data->smc_state_table);
+	int result = 0;
+	struct pp_atom_ctrl__avfs_parameters avfs_params = {0};
+	AVFS_meanNsigma_t AVFS_meanNsigma = { {0} };
+	AVFS_Sclk_Offset_t AVFS_SclkOffset = { {0} };
+	uint32_t tmp, i;
+	struct pp_smumgr *smumgr = hwmgr->smumgr;
+	struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(smumgr->backend);
+
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)hwmgr->pptable;
+	struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
+			table_info->vdd_dep_on_sclk;
+
+
+	if (smu_data->avfs.avfs_btc_status == AVFS_BTC_NOTSUPPORTED)
+		return result;
+
+	result = atomctrl_get_avfs_information(hwmgr, &avfs_params);
+
+	if (0 == result) {
+		table->BTCGB_VDROOP_TABLE[0].a0  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a0);
+		table->BTCGB_VDROOP_TABLE[0].a1  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a1);
+		table->BTCGB_VDROOP_TABLE[0].a2  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a2);
+		table->BTCGB_VDROOP_TABLE[1].a0  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a0);
+		table->BTCGB_VDROOP_TABLE[1].a1  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a1);
+		table->BTCGB_VDROOP_TABLE[1].a2  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a2);
+		table->AVFSGB_VDROOP_TABLE[0].m1 = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_m1);
+		table->AVFSGB_VDROOP_TABLE[0].m2 = PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSON_m2);
+		table->AVFSGB_VDROOP_TABLE[0].b  = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_b);
+		table->AVFSGB_VDROOP_TABLE[0].m1_shift = 24;
+		table->AVFSGB_VDROOP_TABLE[0].m2_shift  = 12;
+		table->AVFSGB_VDROOP_TABLE[1].m1 = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_m1);
+		table->AVFSGB_VDROOP_TABLE[1].m2 = PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSOFF_m2);
+		table->AVFSGB_VDROOP_TABLE[1].b  = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_b);
+		table->AVFSGB_VDROOP_TABLE[1].m1_shift = 24;
+		table->AVFSGB_VDROOP_TABLE[1].m2_shift  = 12;
+		table->MaxVoltage                = PP_HOST_TO_SMC_US(avfs_params.usMaxVoltage_0_25mv);
+		AVFS_meanNsigma.Aconstant[0]      = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant0);
+		AVFS_meanNsigma.Aconstant[1]      = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant1);
+		AVFS_meanNsigma.Aconstant[2]      = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant2);
+		AVFS_meanNsigma.DC_tol_sigma      = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_DC_tol_sigma);
+		AVFS_meanNsigma.Platform_mean     = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_mean);
+		AVFS_meanNsigma.PSM_Age_CompFactor = PP_HOST_TO_SMC_US(avfs_params.usPSM_Age_ComFactor);
+		AVFS_meanNsigma.Platform_sigma     = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_sigma);
+
+		for (i = 0; i < NUM_VFT_COLUMNS; i++) {
+			AVFS_meanNsigma.Static_Voltage_Offset[i] = (uint8_t)(sclk_table->entries[i].cks_voffset * 100 / 625);
+			AVFS_SclkOffset.Sclk_Offset[i] = PP_HOST_TO_SMC_US((uint16_t)(sclk_table->entries[i].sclk_offset) / 100);
+		}
+
+		result = polaris10_read_smc_sram_dword(smumgr,
+				SMU7_FIRMWARE_HEADER_LOCATION + offsetof(SMU74_Firmware_Header, AvfsMeanNSigma),
+				&tmp, data->sram_end);
+
+		polaris10_copy_bytes_to_smc(smumgr,
+					tmp,
+					(uint8_t *)&AVFS_meanNsigma,
+					sizeof(AVFS_meanNsigma_t),
+					data->sram_end);
+
+		result = polaris10_read_smc_sram_dword(smumgr,
+				SMU7_FIRMWARE_HEADER_LOCATION + offsetof(SMU74_Firmware_Header, AvfsSclkOffsetTable),
+				&tmp, data->sram_end);
+		polaris10_copy_bytes_to_smc(smumgr,
+					tmp,
+					(uint8_t *)&AVFS_SclkOffset,
+					sizeof(AVFS_Sclk_Offset_t),
+					data->sram_end);
+
+		data->avfs_vdroop_override_setting = (avfs_params.ucEnableGB_VDROOP_TABLE_CKSON << BTCGB0_Vdroop_Enable_SHIFT) |
+						(avfs_params.ucEnableGB_VDROOP_TABLE_CKSOFF << BTCGB1_Vdroop_Enable_SHIFT) |
+						(avfs_params.ucEnableGB_FUSE_TABLE_CKSON << AVFSGB0_Vdroop_Enable_SHIFT) |
+						(avfs_params.ucEnableGB_FUSE_TABLE_CKSOFF << AVFSGB1_Vdroop_Enable_SHIFT);
+		data->apply_avfs_cks_off_voltage = (avfs_params.ucEnableApplyAVFS_CKS_OFF_Voltage == 1) ? true : false;
+	}
+	return result;
+}
+
+
 /**
 * Initializes the SMC table and uploads it
 *
@@ -2056,6 +2060,10 @@ static int polaris10_init_smc_table(struct pp_hwmgr *hwmgr)
 				"Failed to populate Clock Stretcher Data Table!",
 				return result);
 	}
+
+	result = polaris10_populate_avfs_parameters(hwmgr);
+	PP_ASSERT_WITH_CODE(0 == result, "Failed to populate AVFS Parameters!", return result;);
+
 	table->CurrSclkPllRange = 0xff;
 	table->GraphicsVoltageChangeEnable  = 1;
 	table->GraphicsThermThrottleEnable  = 1;
@@ -2252,6 +2260,9 @@ static int polaris10_enable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr)
 static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	uint32_t soft_register_value = 0;
+	uint32_t handshake_disables_offset = data->soft_regs_start
+				+ offsetof(SMU74_SoftRegisters, HandshakeDisables);
 
 	/* enable SCLK dpm */
 	if (!data->sclk_dpm_key_disabled)
@@ -2262,6 +2273,12 @@ static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 
 	/* enable MCLK dpm */
 	if (0 == data->mclk_dpm_key_disabled) {
+/* Disable UVD - SMU handshake for MCLK. */
+		soft_register_value = cgs_read_ind_register(hwmgr->device,
+					CGS_IND_REG__SMC, handshake_disables_offset);
+		soft_register_value |= SMU7_UVD_MCLK_HANDSHAKE_DISABLE;
+		cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+				handshake_disables_offset, soft_register_value);
 
 		PP_ASSERT_WITH_CODE(
 				(0 == smum_send_msg_to_smc(hwmgr->smumgr,
@@ -2269,7 +2286,6 @@ static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 				"Failed to enable MCLK DPM during DPM Start Function!",
 				return -1);
 
-
 		PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1);
 
 		cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC0_CNTL, 0x5);
@@ -2606,6 +2622,7 @@ int polaris10_set_features_platform_caps(struct pp_hwmgr *hwmgr)
 
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 						PHM_PlatformCaps_FanSpeedInTableIsRPM);
+
 	if (hwmgr->chip_id == CHIP_POLARIS11)
 		phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 					PHM_PlatformCaps_SPLLShutdownSupport);
@@ -2938,6 +2955,11 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	data->vddci_control = POLARIS10_VOLTAGE_CONTROL_NONE;
 	data->mvdd_control = POLARIS10_VOLTAGE_CONTROL_NONE;
 
+	data->enable_tdc_limit_feature = true;
+	data->enable_pkg_pwr_tracking_feature = true;
+	data->force_pcie_gen = PP_PCIEGenInvalid;
+	data->mclk_stutter_mode_threshold = 40000;
+
 	if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr,
 			VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2))
 		data->voltage_control = POLARIS10_VOLTAGE_CONTROL_BY_SVID2;
@@ -2962,6 +2984,10 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 			data->vddci_control = POLARIS10_VOLTAGE_CONTROL_BY_SVID2;
 	}
 
+	if (table_info->cac_dtp_table->usClockStretchAmount != 0)
+		phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+					PHM_PlatformCaps_ClockStretcher);
+
 	polaris10_set_features_platform_caps(hwmgr);
 
 	polaris10_init_dpm_defaults(hwmgr);
@@ -3520,10 +3546,11 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr,
 	ATOM_Tonga_State *state_entry = (ATOM_Tonga_State *)state;
 	ATOM_Tonga_POWERPLAYTABLE *powerplay_table =
 			(ATOM_Tonga_POWERPLAYTABLE *)pp_table;
-	ATOM_Tonga_SCLK_Dependency_Table *sclk_dep_table =
-			(ATOM_Tonga_SCLK_Dependency_Table *)
+	PPTable_Generic_SubTable_Header *sclk_dep_table =
+			(PPTable_Generic_SubTable_Header *)
 			(((unsigned long)powerplay_table) +
 				le16_to_cpu(powerplay_table->usSclkDependencyTableOffset));
+
 	ATOM_Tonga_MCLK_Dependency_Table *mclk_dep_table =
 			(ATOM_Tonga_MCLK_Dependency_Table *)
 			(((unsigned long)powerplay_table) +
@@ -3575,7 +3602,11 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr,
 	/* Performance levels are arranged from low to high. */
 	performance_level->memory_clock = mclk_dep_table->entries
 			[state_entry->ucMemoryClockIndexLow].ulMclk;
-	performance_level->engine_clock = sclk_dep_table->entries
+	if (sclk_dep_table->ucRevId == 0)
+		performance_level->engine_clock = ((ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table)->entries
+			[state_entry->ucEngineClockIndexLow].ulSclk;
+	else if (sclk_dep_table->ucRevId == 1)
+		performance_level->engine_clock = ((ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table)->entries
 			[state_entry->ucEngineClockIndexLow].ulSclk;
 	performance_level->pcie_gen = get_pcie_gen_support(data->pcie_gen_cap,
 			state_entry->ucPCIEGenLow);
@@ -3586,8 +3617,14 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr,
 			[polaris10_power_state->performance_level_count++]);
 	performance_level->memory_clock = mclk_dep_table->entries
 			[state_entry->ucMemoryClockIndexHigh].ulMclk;
-	performance_level->engine_clock = sclk_dep_table->entries
+
+	if (sclk_dep_table->ucRevId == 0)
+		performance_level->engine_clock = ((ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table)->entries
 			[state_entry->ucEngineClockIndexHigh].ulSclk;
+	else if (sclk_dep_table->ucRevId == 1)
+		performance_level->engine_clock = ((ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table)->entries
+			[state_entry->ucEngineClockIndexHigh].ulSclk;
+
 	performance_level->pcie_gen = get_pcie_gen_support(data->pcie_gen_cap,
 			state_entry->ucPCIEGenHigh);
 	performance_level->pcie_lane = get_pcie_lane_support(data->pcie_lane_cap,
@@ -3645,7 +3682,6 @@ static int polaris10_get_pp_table_entry(struct pp_hwmgr *hwmgr,
 		switch (state->classification.ui_label) {
 		case PP_StateUILabel_Performance:
 			data->use_pcie_performance_levels = true;
-
 			for (i = 0; i < ps->performance_level_count; i++) {
 				if (data->pcie_gen_performance.max <
 						ps->performance_levels[i].pcie_gen)
@@ -3661,7 +3697,6 @@ static int polaris10_get_pp_table_entry(struct pp_hwmgr *hwmgr,
 						ps->performance_levels[i].pcie_lane)
 					data->pcie_lane_performance.max =
 							ps->performance_levels[i].pcie_lane;
-
 				if (data->pcie_lane_performance.min >
 						ps->performance_levels[i].pcie_lane)
 					data->pcie_lane_performance.min =
@@ -4187,12 +4222,9 @@ int polaris10_update_samu_dpm(struct pp_hwmgr *hwmgr, bool bgate)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
 	uint32_t mm_boot_level_offset, mm_boot_level_value;
-	struct phm_ppt_v1_information *table_info =
-			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 
 	if (!bgate) {
-		data->smc_state_table.SamuBootLevel =
-				(uint8_t) (table_info->mm_dep_table->count - 1);
+		data->smc_state_table.SamuBootLevel = 0;
 		mm_boot_level_offset = data->dpm_table_start +
 				offsetof(SMU74_Discrete_DpmTable, SamuBootLevel);
 		mm_boot_level_offset /= 4;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
index beedf35cbfa6..d717789441f5 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
@@ -312,6 +312,9 @@ struct polaris10_hwmgr {
 
 	/* soft pptable for re-uploading into smu */
 	void *soft_pp_table;
+
+	uint32_t                              avfs_vdroop_override_setting;
+	bool                                  apply_avfs_cks_off_voltage;
 };
 
 /* To convert to Q8.8 format for firmware */
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
index 0b99ab3ba0c5..ae96f14b827c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
@@ -286,7 +286,7 @@ int polaris10_populate_pm_fuses(struct pp_hwmgr *hwmgr)
 
 		if (polaris10_copy_bytes_to_smc(hwmgr->smumgr, pm_fuse_table_offset,
 				(uint8_t *)&data->power_tune_table,
-				sizeof(struct SMU74_Discrete_PmFuses), data->sram_end))
+				(sizeof(struct SMU74_Discrete_PmFuses) - 92), data->sram_end))
 			PP_ASSERT_WITH_CODE(false,
 					"Attempt to download PmFuseTable Failed!",
 					return -EINVAL);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c
index aba167f7d167..b206632d4650 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c
@@ -625,10 +625,14 @@ static int tf_polaris10_thermal_avfs_enable(struct pp_hwmgr *hwmgr,
 	int ret;
 	struct pp_smumgr *smumgr = (struct pp_smumgr *)(hwmgr->smumgr);
 	struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(smumgr->backend);
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
 
-	if (smu_data->avfs.avfs_btc_status != AVFS_BTC_ENABLEAVFS)
+	if (smu_data->avfs.avfs_btc_status == AVFS_BTC_NOTSUPPORTED)
 		return 0;
 
+	ret = smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+			PPSMC_MSG_SetGBDroopSettings, data->avfs_vdroop_override_setting);
+
 	ret = (smum_send_msg_to_smc(smumgr, PPSMC_MSG_EnableAvfs) == 0) ?
 			0 : -1;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
index 58742e0d1492..a3c38bbd1e94 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
@@ -44,6 +44,20 @@ bool acpi_atcs_functions_supported(void *device, uint32_t index)
 	return result == 0 ? (output_buf.function_bits & (1 << (index - 1))) != 0 : false;
 }
 
+bool acpi_atcs_notify_pcie_device_ready(void *device)
+{
+	int32_t temp_buffer = 1;
+
+	return cgs_call_acpi_method(device, CGS_ACPI_METHOD_ATCS,
+				ATCS_FUNCTION_PCIE_DEVICE_READY_NOTIFICATION,
+						&temp_buffer,
+						NULL,
+						0,
+						sizeof(temp_buffer),
+						0);
+}
+
+
 int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise)
 {
 	struct atcs_pref_req_input atcs_input;
@@ -52,7 +66,7 @@ int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise)
 	int result;
 	struct cgs_system_info info = {0};
 
-	if (!acpi_atcs_functions_supported(device, ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST))
+	if( 0 != acpi_atcs_notify_pcie_device_ready(device))
 		return -EINVAL;
 
 	info.size = sizeof(struct cgs_system_info);
@@ -77,7 +91,7 @@ int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise)
 						ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST,
 						&atcs_input,
 						&atcs_output,
-						0,
+						1,
 						sizeof(atcs_input),
 						sizeof(atcs_output));
 		if (result != 0)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index da9f5f1b6dc2..bf4e18fd3872 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -1302,3 +1302,46 @@ int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctr
 
 	return 0;
 }
+
+int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param)
+{
+	ATOM_ASIC_PROFILING_INFO_V3_6 *profile = NULL;
+
+	if (param == NULL)
+		return -EINVAL;
+
+	profile = (ATOM_ASIC_PROFILING_INFO_V3_6 *)
+			cgs_atom_get_data_table(hwmgr->device,
+					GetIndexIntoMasterTable(DATA, ASIC_ProfilingInfo),
+					NULL, NULL, NULL);
+	if (!profile)
+		return -1;
+
+	param->ulAVFS_meanNsigma_Acontant0 = profile->ulAVFS_meanNsigma_Acontant0;
+	param->ulAVFS_meanNsigma_Acontant1 = profile->ulAVFS_meanNsigma_Acontant1;
+	param->ulAVFS_meanNsigma_Acontant2 = profile->ulAVFS_meanNsigma_Acontant2;
+	param->usAVFS_meanNsigma_DC_tol_sigma = profile->usAVFS_meanNsigma_DC_tol_sigma;
+	param->usAVFS_meanNsigma_Platform_mean = profile->usAVFS_meanNsigma_Platform_mean;
+	param->usAVFS_meanNsigma_Platform_sigma = profile->usAVFS_meanNsigma_Platform_sigma;
+	param->ulGB_VDROOP_TABLE_CKSOFF_a0 = profile->ulGB_VDROOP_TABLE_CKSOFF_a0;
+	param->ulGB_VDROOP_TABLE_CKSOFF_a1 = profile->ulGB_VDROOP_TABLE_CKSOFF_a1;
+	param->ulGB_VDROOP_TABLE_CKSOFF_a2 = profile->ulGB_VDROOP_TABLE_CKSOFF_a2;
+	param->ulGB_VDROOP_TABLE_CKSON_a0 = profile->ulGB_VDROOP_TABLE_CKSON_a0;
+	param->ulGB_VDROOP_TABLE_CKSON_a1 = profile->ulGB_VDROOP_TABLE_CKSON_a1;
+	param->ulGB_VDROOP_TABLE_CKSON_a2 = profile->ulGB_VDROOP_TABLE_CKSON_a2;
+	param->ulAVFSGB_FUSE_TABLE_CKSOFF_m1 = profile->ulAVFSGB_FUSE_TABLE_CKSOFF_m1;
+	param->usAVFSGB_FUSE_TABLE_CKSOFF_m2 = profile->usAVFSGB_FUSE_TABLE_CKSOFF_m2;
+	param->ulAVFSGB_FUSE_TABLE_CKSOFF_b = profile->ulAVFSGB_FUSE_TABLE_CKSOFF_b;
+	param->ulAVFSGB_FUSE_TABLE_CKSON_m1 = profile->ulAVFSGB_FUSE_TABLE_CKSON_m1;
+	param->usAVFSGB_FUSE_TABLE_CKSON_m2 = profile->usAVFSGB_FUSE_TABLE_CKSON_m2;
+	param->ulAVFSGB_FUSE_TABLE_CKSON_b = profile->ulAVFSGB_FUSE_TABLE_CKSON_b;
+	param->usMaxVoltage_0_25mv = profile->usMaxVoltage_0_25mv;
+	param->ucEnableGB_VDROOP_TABLE_CKSOFF = profile->ucEnableGB_VDROOP_TABLE_CKSOFF;
+	param->ucEnableGB_VDROOP_TABLE_CKSON = profile->ucEnableGB_VDROOP_TABLE_CKSON;
+	param->ucEnableGB_FUSE_TABLE_CKSOFF = profile->ucEnableGB_FUSE_TABLE_CKSOFF;
+	param->ucEnableGB_FUSE_TABLE_CKSON = profile->ucEnableGB_FUSE_TABLE_CKSON;
+	param->usPSM_Age_ComFactor = profile->usPSM_Age_ComFactor;
+	param->ucEnableApplyAVFS_CKS_OFF_Voltage = profile->ucEnableApplyAVFS_CKS_OFF_Voltage;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
index d24ebb566905..248c5db5f380 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
@@ -250,6 +250,35 @@ struct pp_atomctrl_gpio_pin_assignment {
 };
 typedef struct pp_atomctrl_gpio_pin_assignment pp_atomctrl_gpio_pin_assignment;
 
+struct pp_atom_ctrl__avfs_parameters {
+	uint32_t  ulAVFS_meanNsigma_Acontant0;
+	uint32_t  ulAVFS_meanNsigma_Acontant1;
+	uint32_t  ulAVFS_meanNsigma_Acontant2;
+	uint16_t usAVFS_meanNsigma_DC_tol_sigma;
+	uint16_t usAVFS_meanNsigma_Platform_mean;
+	uint16_t usAVFS_meanNsigma_Platform_sigma;
+	uint32_t  ulGB_VDROOP_TABLE_CKSOFF_a0;
+	uint32_t  ulGB_VDROOP_TABLE_CKSOFF_a1;
+	uint32_t  ulGB_VDROOP_TABLE_CKSOFF_a2;
+	uint32_t  ulGB_VDROOP_TABLE_CKSON_a0;
+	uint32_t  ulGB_VDROOP_TABLE_CKSON_a1;
+	uint32_t  ulGB_VDROOP_TABLE_CKSON_a2;
+	uint32_t  ulAVFSGB_FUSE_TABLE_CKSOFF_m1;
+	uint16_t  usAVFSGB_FUSE_TABLE_CKSOFF_m2;
+	uint32_t  ulAVFSGB_FUSE_TABLE_CKSOFF_b;
+	uint32_t  ulAVFSGB_FUSE_TABLE_CKSON_m1;
+	uint16_t  usAVFSGB_FUSE_TABLE_CKSON_m2;
+	uint32_t  ulAVFSGB_FUSE_TABLE_CKSON_b;
+	uint16_t  usMaxVoltage_0_25mv;
+	uint8_t  ucEnableGB_VDROOP_TABLE_CKSOFF;
+	uint8_t  ucEnableGB_VDROOP_TABLE_CKSON;
+	uint8_t  ucEnableGB_FUSE_TABLE_CKSOFF;
+	uint8_t  ucEnableGB_FUSE_TABLE_CKSON;
+	uint16_t usPSM_Age_ComFactor;
+	uint8_t  ucEnableApplyAVFS_CKS_OFF_Voltage;
+	uint8_t  ucReserved;
+};
+
 extern bool atomctrl_get_pp_assign_pin(struct pp_hwmgr *hwmgr, const uint32_t pinId, pp_atomctrl_gpio_pin_assignment *gpio_pin_assignment);
 extern int atomctrl_get_voltage_evv_on_sclk(struct pp_hwmgr *hwmgr, uint8_t voltage_type, uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage);
 extern uint32_t atomctrl_get_mpll_reference_clock(struct pp_hwmgr *hwmgr);
@@ -278,5 +307,8 @@ extern int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clo
 extern int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
 				uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage);
 extern int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl_sclk_range_table *table);
+
+extern int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param);
+
 #endif
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
index 16fed487973b..233eb7f36c1d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
@@ -2847,27 +2847,6 @@ static int tonga_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 		}
 	}
 
-	/* Initialize Vddc DPM table based on allow Vddc values.  And populate corresponding std values. */
-	for (i = 0; i < allowed_vdd_sclk_table->count; i++) {
-		data->dpm_table.vddc_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].vddc;
-		/* tonga_hwmgr->dpm_table.VddcTable.dpm_levels[i].param1 = stdVoltageTable->entries[i].Leakage; */
-		/* param1 is for corresponding std voltage */
-		data->dpm_table.vddc_table.dpm_levels[i].enabled = 1;
-	}
-	data->dpm_table.vddc_table.count = allowed_vdd_sclk_table->count;
-
-	if (NULL != allowed_vdd_mclk_table) {
-		/* Initialize Vddci DPM table based on allow Mclk values */
-		for (i = 0; i < allowed_vdd_mclk_table->count; i++) {
-			data->dpm_table.vdd_ci_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].vddci;
-			data->dpm_table.vdd_ci_table.dpm_levels[i].enabled = 1;
-			data->dpm_table.mvdd_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].mvdd;
-			data->dpm_table.mvdd_table.dpm_levels[i].enabled = 1;
-		}
-		data->dpm_table.vdd_ci_table.count = allowed_vdd_mclk_table->count;
-		data->dpm_table.mvdd_table.count = allowed_vdd_mclk_table->count;
-	}
-
 	/* setup PCIE gen speed levels*/
 	tonga_setup_default_pcie_tables(hwmgr);
 
@@ -4510,6 +4489,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	data->vdd_ci_control = TONGA_VOLTAGE_CONTROL_NONE;
 	data->vdd_gfx_control = TONGA_VOLTAGE_CONTROL_NONE;
 	data->mvdd_control = TONGA_VOLTAGE_CONTROL_NONE;
+	data->force_pcie_gen = PP_PCIEGenInvalid;
 
 	if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr,
 				VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2)) {
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h
index 1b44f4e9b8f5..f127198aafc4 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h
@@ -197,6 +197,22 @@ typedef struct _ATOM_Tonga_SCLK_Dependency_Table {
 	ATOM_Tonga_SCLK_Dependency_Record entries[1];				 /* Dynamically allocate entries. */
 } ATOM_Tonga_SCLK_Dependency_Table;
 
+typedef struct _ATOM_Polaris_SCLK_Dependency_Record {
+	UCHAR  ucVddInd;											/* Base voltage */
+	USHORT usVddcOffset;										/* Offset relative to base voltage */
+	ULONG ulSclk;
+	USHORT usEdcCurrent;
+	UCHAR  ucReliabilityTemperature;
+	UCHAR  ucCKSVOffsetandDisable;			/* Bits 0~6: Voltage offset for CKS, Bit 7: Disable/enable for the SCLK level. */
+	ULONG  ulSclkOffset;
+} ATOM_Polaris_SCLK_Dependency_Record;
+
+typedef struct _ATOM_Polaris_SCLK_Dependency_Table {
+	UCHAR ucRevId;
+	UCHAR ucNumEntries;							/* Number of entries. */
+	ATOM_Polaris_SCLK_Dependency_Record entries[1];				 /* Dynamically allocate entries. */
+} ATOM_Polaris_SCLK_Dependency_Table;
+
 typedef struct _ATOM_Tonga_PCIE_Record {
 	UCHAR ucPCIEGenSpeed;
 	UCHAR usPCIELaneWidth;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
index 10e3630ee39d..671fdb4d615a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
@@ -408,41 +408,78 @@ static int get_mclk_voltage_dependency_table(
 static int get_sclk_voltage_dependency_table(
 		struct pp_hwmgr *hwmgr,
 		phm_ppt_v1_clock_voltage_dependency_table **pp_tonga_sclk_dep_table,
-		const ATOM_Tonga_SCLK_Dependency_Table * sclk_dep_table
+		const PPTable_Generic_SubTable_Header *sclk_dep_table
 		)
 {
 	uint32_t table_size, i;
 	phm_ppt_v1_clock_voltage_dependency_table *sclk_table;
 
-	PP_ASSERT_WITH_CODE((0 != sclk_dep_table->ucNumEntries),
-		"Invalid PowerPlay Table!", return -1);
+	if (sclk_dep_table->ucRevId < 1) {
+		const ATOM_Tonga_SCLK_Dependency_Table *tonga_table =
+			    (ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table;
 
-	table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record)
-		* sclk_dep_table->ucNumEntries;
+		PP_ASSERT_WITH_CODE((0 != tonga_table->ucNumEntries),
+			"Invalid PowerPlay Table!", return -1);
 
-	sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *)
-		kzalloc(table_size, GFP_KERNEL);
+		table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record)
+			* tonga_table->ucNumEntries;
 
-	if (NULL == sclk_table)
-		return -ENOMEM;
+		sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *)
+			kzalloc(table_size, GFP_KERNEL);
 
-	memset(sclk_table, 0x00, table_size);
-
-	sclk_table->count = (uint32_t)sclk_dep_table->ucNumEntries;
-
-	for (i = 0; i < sclk_dep_table->ucNumEntries; i++) {
-		sclk_table->entries[i].vddInd =
-			sclk_dep_table->entries[i].ucVddInd;
-		sclk_table->entries[i].vdd_offset =
-			sclk_dep_table->entries[i].usVddcOffset;
-		sclk_table->entries[i].clk =
-			sclk_dep_table->entries[i].ulSclk;
-		sclk_table->entries[i].cks_enable =
-			(((sclk_dep_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0;
-		sclk_table->entries[i].cks_voffset =
-			(sclk_dep_table->entries[i].ucCKSVOffsetandDisable & 0x7F);
-	}
+		if (NULL == sclk_table)
+			return -ENOMEM;
+
+		memset(sclk_table, 0x00, table_size);
+
+		sclk_table->count = (uint32_t)tonga_table->ucNumEntries;
+
+		for (i = 0; i < tonga_table->ucNumEntries; i++) {
+			sclk_table->entries[i].vddInd =
+				tonga_table->entries[i].ucVddInd;
+			sclk_table->entries[i].vdd_offset =
+				tonga_table->entries[i].usVddcOffset;
+			sclk_table->entries[i].clk =
+				tonga_table->entries[i].ulSclk;
+			sclk_table->entries[i].cks_enable =
+				(((tonga_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0;
+			sclk_table->entries[i].cks_voffset =
+				(tonga_table->entries[i].ucCKSVOffsetandDisable & 0x7F);
+		}
+	} else {
+		const ATOM_Polaris_SCLK_Dependency_Table *polaris_table =
+			    (ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table;
+
+		PP_ASSERT_WITH_CODE((0 != polaris_table->ucNumEntries),
+			"Invalid PowerPlay Table!", return -1);
+
+		table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record)
+			* polaris_table->ucNumEntries;
+
+		sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *)
+			kzalloc(table_size, GFP_KERNEL);
 
+		if (NULL == sclk_table)
+			return -ENOMEM;
+
+		memset(sclk_table, 0x00, table_size);
+
+		sclk_table->count = (uint32_t)polaris_table->ucNumEntries;
+
+		for (i = 0; i < polaris_table->ucNumEntries; i++) {
+			sclk_table->entries[i].vddInd =
+				polaris_table->entries[i].ucVddInd;
+			sclk_table->entries[i].vdd_offset =
+				polaris_table->entries[i].usVddcOffset;
+			sclk_table->entries[i].clk =
+				polaris_table->entries[i].ulSclk;
+			sclk_table->entries[i].cks_enable =
+				(((polaris_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0;
+			sclk_table->entries[i].cks_voffset =
+				(polaris_table->entries[i].ucCKSVOffsetandDisable & 0x7F);
+			sclk_table->entries[i].sclk_offset = polaris_table->entries[i].ulSclkOffset;
+		}
+	}
 	*pp_tonga_sclk_dep_table = sclk_table;
 
 	return 0;
@@ -708,8 +745,8 @@ static int init_clock_voltage_dependency(
 	const ATOM_Tonga_MCLK_Dependency_Table *mclk_dep_table =
 		(const ATOM_Tonga_MCLK_Dependency_Table *)(((unsigned long) powerplay_table) +
 		le16_to_cpu(powerplay_table->usMclkDependencyTableOffset));
-	const ATOM_Tonga_SCLK_Dependency_Table *sclk_dep_table =
-		(const ATOM_Tonga_SCLK_Dependency_Table *)(((unsigned long) powerplay_table) +
+	const PPTable_Generic_SubTable_Header *sclk_dep_table =
+		(const PPTable_Generic_SubTable_Header *)(((unsigned long) powerplay_table) +
 		le16_to_cpu(powerplay_table->usSclkDependencyTableOffset));
 	const ATOM_Tonga_Hard_Limit_Table *pHardLimits =
 		(const ATOM_Tonga_Hard_Limit_Table *)(((unsigned long) powerplay_table) +
@@ -1040,48 +1077,44 @@ int tonga_pp_tables_uninitialize(struct pp_hwmgr *hwmgr)
 	struct phm_ppt_v1_information *pp_table_information =
 		(struct phm_ppt_v1_information *)(hwmgr->pptable);
 
-	if (NULL != hwmgr->soft_pp_table) {
-		kfree(hwmgr->soft_pp_table);
+	if (NULL != hwmgr->soft_pp_table)
 		hwmgr->soft_pp_table = NULL;
-	}
 
-	if (NULL != pp_table_information->vdd_dep_on_sclk)
-		pp_table_information->vdd_dep_on_sclk = NULL;
+	kfree(pp_table_information->vdd_dep_on_sclk);
+	pp_table_information->vdd_dep_on_sclk = NULL;
 
-	if (NULL != pp_table_information->vdd_dep_on_mclk)
-		pp_table_information->vdd_dep_on_mclk = NULL;
+	kfree(pp_table_information->vdd_dep_on_mclk);
+	pp_table_information->vdd_dep_on_mclk = NULL;
 
-	if (NULL != pp_table_information->valid_mclk_values)
-		pp_table_information->valid_mclk_values = NULL;
+	kfree(pp_table_information->valid_mclk_values);
+	pp_table_information->valid_mclk_values = NULL;
 
-	if (NULL != pp_table_information->valid_sclk_values)
-		pp_table_information->valid_sclk_values = NULL;
+	kfree(pp_table_information->valid_sclk_values);
+	pp_table_information->valid_sclk_values = NULL;
 
-	if (NULL != pp_table_information->vddc_lookup_table)
-		pp_table_information->vddc_lookup_table = NULL;
+	kfree(pp_table_information->vddc_lookup_table);
+	pp_table_information->vddc_lookup_table = NULL;
 
-	if (NULL != pp_table_information->vddgfx_lookup_table)
-		pp_table_information->vddgfx_lookup_table = NULL;
+	kfree(pp_table_information->vddgfx_lookup_table);
+	pp_table_information->vddgfx_lookup_table = NULL;
 
-	if (NULL != pp_table_information->mm_dep_table)
-		pp_table_information->mm_dep_table = NULL;
+	kfree(pp_table_information->mm_dep_table);
+	pp_table_information->mm_dep_table = NULL;
 
-	if (NULL != pp_table_information->cac_dtp_table)
-		pp_table_information->cac_dtp_table = NULL;
+	kfree(pp_table_information->cac_dtp_table);
+	pp_table_information->cac_dtp_table = NULL;
 
-	if (NULL != hwmgr->dyn_state.cac_dtp_table)
-		hwmgr->dyn_state.cac_dtp_table = NULL;
+	kfree(hwmgr->dyn_state.cac_dtp_table);
+	hwmgr->dyn_state.cac_dtp_table = NULL;
 
-	if (NULL != pp_table_information->ppm_parameter_table)
-		pp_table_information->ppm_parameter_table = NULL;
+	kfree(pp_table_information->ppm_parameter_table);
+	pp_table_information->ppm_parameter_table = NULL;
 
-	if (NULL != pp_table_information->pcie_table)
-		pp_table_information->pcie_table = NULL;
+	kfree(pp_table_information->pcie_table);
+	pp_table_information->pcie_table = NULL;
 
-	if (NULL != hwmgr->pptable) {
-		kfree(hwmgr->pptable);
-		hwmgr->pptable = NULL;
-	}
+	kfree(hwmgr->pptable);
+	hwmgr->pptable = NULL;
 
 	return result;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
index 0c6a413eaa5b..d41d37ab5b7c 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
@@ -27,6 +27,7 @@
 
 #pragma pack(push, 1)
 
+#define PPSMC_MSG_SetGBDroopSettings          ((uint16_t) 0x305)
 
 #define PPSMC_SWSTATE_FLAG_DC                           0x01
 #define PPSMC_SWSTATE_FLAG_UVD                          0x02
diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h b/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h
index 3bd5e69b9045..3df5de2cdab0 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h
@@ -26,3 +26,4 @@ extern bool acpi_atcs_functions_supported(void *device,
 extern int acpi_pcie_perf_request(void *device,
 						uint8_t perf_req,
 						bool advertise);
+extern bool acpi_atcs_notify_pcie_device_ready(void *device);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74.h b/drivers/gpu/drm/amd/powerplay/inc/smu74.h
index 1a12d85b8e97..fd10a9fa843d 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu74.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu74.h
@@ -34,6 +34,30 @@
 #define SMU__NUM_LCLK_DPM_LEVELS 8
 #define SMU__NUM_PCIE_DPM_LEVELS 8
 
+#define EXP_M1  35
+#define EXP_M2  92821
+#define EXP_B   66629747
+
+#define EXP_M1_1  365
+#define EXP_M2_1  658700
+#define EXP_B_1   305506134
+
+#define EXP_M1_2  189
+#define EXP_M2_2  379692
+#define EXP_B_2   194609469
+
+#define EXP_M1_3  99
+#define EXP_M2_3  217915
+#define EXP_B_3   122255994
+
+#define EXP_M1_4  51
+#define EXP_M2_4  122643
+#define EXP_B_4   74893384
+
+#define EXP_M1_5  423
+#define EXP_M2_5  1103326
+#define EXP_B_5   728122621
+
 enum SID_OPTION {
 	SID_OPTION_HI,
 	SID_OPTION_LO,
@@ -548,20 +572,20 @@ struct SMU74_Firmware_Header {
 	uint32_t CacConfigTable;
 	uint32_t CacStatusTable;
 
-
 	uint32_t mcRegisterTable;
 
-
 	uint32_t mcArbDramTimingTable;
 
-
-
-
 	uint32_t PmFuseTable;
 	uint32_t Globals;
 	uint32_t ClockStretcherTable;
 	uint32_t VftTable;
-	uint32_t Reserved[21];
+	uint32_t Reserved1;
+	uint32_t AvfsTable;
+	uint32_t AvfsCksOffGbvTable;
+	uint32_t AvfsMeanNSigma;
+	uint32_t AvfsSclkOffsetTable;
+	uint32_t Reserved[16];
 	uint32_t Signature;
 };
 
@@ -701,8 +725,6 @@ VR Config info is contained in dpmTable.VRConfig */
 struct SMU_ClockStretcherDataTableEntry {
 	uint8_t minVID;
 	uint8_t maxVID;
-
-
 	uint16_t setting;
 };
 typedef struct SMU_ClockStretcherDataTableEntry SMU_ClockStretcherDataTableEntry;
@@ -769,6 +791,43 @@ struct VFT_TABLE_t {
 typedef struct VFT_TABLE_t VFT_TABLE_t;
 
 
+/* Total margin, root mean square of Fmax + DC + Platform */
+struct AVFS_Margin_t {
+	VFT_CELL_t Cell[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_Margin_t AVFS_Margin_t;
+
+#define BTCGB_VDROOP_TABLE_MAX_ENTRIES 2
+#define AVFSGB_VDROOP_TABLE_MAX_ENTRIES 2
+
+struct GB_VDROOP_TABLE_t {
+	int32_t a0;
+	int32_t a1;
+	int32_t a2;
+	uint32_t spare;
+};
+typedef struct GB_VDROOP_TABLE_t GB_VDROOP_TABLE_t;
+
+struct AVFS_CksOff_Gbv_t {
+	VFT_CELL_t Cell[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_CksOff_Gbv_t AVFS_CksOff_Gbv_t;
+
+struct AVFS_meanNsigma_t {
+	uint32_t Aconstant[3];
+	uint16_t DC_tol_sigma;
+	uint16_t Platform_mean;
+	uint16_t Platform_sigma;
+	uint16_t PSM_Age_CompFactor;
+	uint8_t  Static_Voltage_Offset[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_meanNsigma_t AVFS_meanNsigma_t;
+
+struct AVFS_Sclk_Offset_t {
+	uint16_t Sclk_Offset[8];
+};
+typedef struct AVFS_Sclk_Offset_t AVFS_Sclk_Offset_t;
+
 #endif
 
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
index 0dfe82336dc7..b85ff5400e57 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
@@ -223,6 +223,16 @@ struct SMU74_Discrete_StateInfo {
 
 typedef struct SMU74_Discrete_StateInfo SMU74_Discrete_StateInfo;
 
+struct SMU_QuadraticCoeffs {
+	int32_t m1;
+	uint32_t b;
+
+	int16_t m2;
+	uint8_t m1_shift;
+	uint8_t m2_shift;
+};
+typedef struct SMU_QuadraticCoeffs SMU_QuadraticCoeffs;
+
 struct SMU74_Discrete_DpmTable {
 
 	SMU74_PIDController                  GraphicsPIDController;
@@ -258,7 +268,14 @@ struct SMU74_Discrete_DpmTable {
 	uint8_t                             ThermOutPolarity;
 	uint8_t                             ThermOutMode;
 	uint8_t                             BootPhases;
-	uint32_t                            Reserved[4];
+
+	uint8_t                             VRHotLevel;
+	uint8_t                             Reserved1[3];
+	uint16_t                            FanStartTemperature;
+	uint16_t                            FanStopTemperature;
+	uint16_t                            MaxVoltage;
+	uint16_t                            Reserved2;
+	uint32_t                            Reserved[1];
 
 	SMU74_Discrete_GraphicsLevel        GraphicsLevel[SMU74_MAX_LEVELS_GRAPHICS];
 	SMU74_Discrete_MemoryLevel          MemoryACPILevel;
@@ -347,6 +364,8 @@ struct SMU74_Discrete_DpmTable {
 
 	uint32_t                            CurrSclkPllRange;
 	sclkFcwRange_t                      SclkFcwRangeTable[NUM_SCLK_RANGE];
+	GB_VDROOP_TABLE_t                   BTCGB_VDROOP_TABLE[BTCGB_VDROOP_TABLE_MAX_ENTRIES];
+	SMU_QuadraticCoeffs                 AVFSGB_VDROOP_TABLE[AVFSGB_VDROOP_TABLE_MAX_ENTRIES];
 };
 
 typedef struct SMU74_Discrete_DpmTable SMU74_Discrete_DpmTable;
@@ -550,16 +569,6 @@ struct SMU7_AcpiScoreboard {
 
 typedef struct SMU7_AcpiScoreboard SMU7_AcpiScoreboard;
 
-struct SMU_QuadraticCoeffs {
-	int32_t m1;
-	uint32_t b;
-
-	int16_t m2;
-	uint8_t m1_shift;
-	uint8_t m2_shift;
-};
-typedef struct SMU_QuadraticCoeffs SMU_QuadraticCoeffs;
-
 struct SMU74_Discrete_PmFuses {
 	uint8_t BapmVddCVidHiSidd[8];
 	uint8_t BapmVddCVidLoSidd[8];
@@ -821,6 +830,17 @@ typedef struct SMU7_GfxCuPgScoreboard SMU7_GfxCuPgScoreboard;
 #define DB_PCC_SHIFT 26 
 #define DB_EDC_SHIFT 27
 
+#define BTCGB0_Vdroop_Enable_MASK  0x1
+#define BTCGB1_Vdroop_Enable_MASK  0x2
+#define AVFSGB0_Vdroop_Enable_MASK 0x4
+#define AVFSGB1_Vdroop_Enable_MASK 0x8
+
+#define BTCGB0_Vdroop_Enable_SHIFT  0
+#define BTCGB1_Vdroop_Enable_SHIFT  1
+#define AVFSGB0_Vdroop_Enable_SHIFT 2
+#define AVFSGB1_Vdroop_Enable_SHIFT 3
+
+
 #pragma pack(pop)
 
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
index 673a75c74e18..8e52a2e82db5 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
@@ -1006,10 +1006,16 @@ static int fiji_smu_init(struct pp_smumgr *smumgr)
 
 static int fiji_smu_fini(struct pp_smumgr *smumgr)
 {
+	struct fiji_smumgr *priv = (struct fiji_smumgr *)(smumgr->backend);
+
+	smu_free_memory(smumgr->device, (void *)priv->header_buffer.handle);
+
 	if (smumgr->backend) {
 		kfree(smumgr->backend);
 		smumgr->backend = NULL;
 	}
+
+	cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index de618ead9db8..5dba7c509710 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -52,19 +52,18 @@
 static const SMU74_Discrete_GraphicsLevel avfs_graphics_level_polaris10[8] = {
 	/*  Min      pcie   DeepSleep Activity  CgSpll      CgSpll    CcPwr  CcPwr  Sclk         Enabled      Enabled                       Voltage    Power */
 	/* Voltage, DpmLevel, DivId,  Level,  FuncCntl3,  FuncCntl4,  DynRm, DynRm1 Did, Padding,ForActivity, ForThrottle, UpHyst, DownHyst, DownHyst, Throttle */
-	{ 0x3c0fd047, 0x00, 0x03, 0x1e00, 0x00200410, 0x87020000, 0, 0, 0x16, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x30750000, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0xa00fd047, 0x01, 0x04, 0x1e00, 0x00800510, 0x87020000, 0, 0, 0x16, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x409c0000, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0x0410d047, 0x01, 0x00, 0x1e00, 0x00600410, 0x87020000, 0, 0, 0x0e, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x50c30000, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0x6810d047, 0x01, 0x00, 0x1e00, 0x00800410, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x60ea0000, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0xcc10d047, 0x01, 0x00, 0x1e00, 0x00e00410, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0xe8fd0000, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0x3011d047, 0x01, 0x00, 0x1e00, 0x00400510, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x70110100, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0x9411d047, 0x01, 0x00, 0x1e00, 0x00a00510, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0xf8240100, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0xf811d047, 0x01, 0x00, 0x1e00, 0x00000610, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x80380100, 0, 0, 0, 0, 0, 0, 0 } }
+	{ 0x100ea446, 0x00, 0x03, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x30750000, 0x3000, 0, 0x2600, 0, 0, 0x0004, 0x8f02, 0xffff, 0x2f00, 0x300e, 0x2700 } },
+	{ 0x400ea446, 0x01, 0x04, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x409c0000, 0x2000, 0, 0x1e00, 1, 1, 0x0004, 0x8300, 0xffff, 0x1f00, 0xcb5e, 0x1a00 } },
+	{ 0x740ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x50c30000, 0x2800, 0, 0x2000, 1, 1, 0x0004, 0x0c02, 0xffff, 0x2700, 0x6433, 0x2100 } },
+	{ 0xa40ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x60ea0000, 0x3000, 0, 0x2600, 1, 1, 0x0004, 0x8f02, 0xffff, 0x2f00, 0x300e, 0x2700 } },
+	{ 0xd80ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x70110100, 0x3800, 0, 0x2c00, 1, 1, 0x0004, 0x1203, 0xffff, 0x3600, 0xc9e2, 0x2e00 } },
+	{ 0x3c0fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x80380100, 0x2000, 0, 0x1e00, 2, 1, 0x0004, 0x8300, 0xffff, 0x1f00, 0xcb5e, 0x1a00 } },
+	{ 0x6c0fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x905f0100, 0x2400, 0, 0x1e00, 2, 1, 0x0004, 0x8901, 0xffff, 0x2300, 0x314c, 0x1d00 } },
+	{ 0xa00fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0xa0860100, 0x2800, 0, 0x2000, 2, 1, 0x0004, 0x0c02, 0xffff, 0x2700, 0x6433, 0x2100 } }
 };
 
 static const SMU74_Discrete_MemoryLevel avfs_memory_level_polaris10 =
-	{0x50140000, 0x50140000, 0x00320000, 0x00, 0x00,
-	 0x00, 0x10, 0x00, 0x00, 0x00, 0x00, 0x0000, 0x00, 0x00};
+	{0x100ea446, 0, 0x30750000, 0x01, 0x01, 0x01, 0x00, 0x00, 0x64, 0x00, 0x00, 0x1f00, 0x00, 0x00};
 
 /**
 * Set the address for reading/writing the SMC SRAM space.
@@ -219,6 +218,18 @@ bool polaris10_is_smc_ram_running(struct pp_smumgr *smumgr)
 	&& (0x20100 <= cgs_read_ind_register(smumgr->device, CGS_IND_REG__SMC, ixSMC_PC_C)));
 }
 
+static bool polaris10_is_hw_avfs_present(struct pp_smumgr *smumgr)
+{
+	uint32_t efuse;
+
+	efuse = cgs_read_ind_register(smumgr->device, CGS_IND_REG__SMC, ixSMU_EFUSE_0 + (49*4));
+	efuse &= 0x00000001;
+	if (efuse)
+		return true;
+
+	return false;
+}
+
 /**
 * Send a message to the SMC, and wait for its response.
 *
@@ -228,21 +239,27 @@ bool polaris10_is_smc_ram_running(struct pp_smumgr *smumgr)
 */
 int polaris10_send_msg_to_smc(struct pp_smumgr *smumgr, uint16_t msg)
 {
+	int ret;
+
 	if (!polaris10_is_smc_ram_running(smumgr))
 		return -1;
 
+
 	SMUM_WAIT_FIELD_UNEQUAL(smumgr, SMC_RESP_0, SMC_RESP, 0);
 
-	if (1 != SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP))
-		printk("Failed to send Previous Message.\n");
+	ret = SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP);
 
+	if (ret != 1)
+		printk("\n failed to send pre message %x ret is %d \n",  msg, ret);
 
 	cgs_write_register(smumgr->device, mmSMC_MESSAGE_0, msg);
 
 	SMUM_WAIT_FIELD_UNEQUAL(smumgr, SMC_RESP_0, SMC_RESP, 0);
 
-	if (1 != SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP))
-		printk("Failed to send Message.\n");
+	ret = SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP);
+
+	if (ret != 1)
+		printk("\n failed to send message %x ret is %d \n",  msg, ret);
 
 	return 0;
 }
@@ -469,6 +486,7 @@ int polaris10_smu_fini(struct pp_smumgr *smumgr)
 		kfree(smumgr->backend);
 		smumgr->backend = NULL;
 	}
+	cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU);
 	return 0;
 }
 
@@ -952,6 +970,11 @@ static int polaris10_smu_init(struct pp_smumgr *smumgr)
 		(cgs_handle_t)smu_data->smu_buffer.handle);
 		return -1;);
 
+	if (polaris10_is_hw_avfs_present(smumgr))
+		smu_data->avfs.avfs_btc_status = AVFS_BTC_BOOT;
+	else
+		smu_data->avfs.avfs_btc_status = AVFS_BTC_NOTSUPPORTED;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
index c483baf6b4fb..0728c1e3d97a 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
@@ -81,6 +81,7 @@ int smum_init(struct amd_pp_init *pp_init, struct pp_instance *handle)
 
 int smum_fini(struct pp_smumgr *smumgr)
 {
+	kfree(smumgr->device);
 	kfree(smumgr);
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
index 32820b680d88..b22722eabafc 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
@@ -328,10 +328,17 @@ int tonga_write_smc_sram_dword(struct pp_smumgr *smumgr,
 
 static int tonga_smu_fini(struct pp_smumgr *smumgr)
 {
+	struct tonga_smumgr *priv = (struct tonga_smumgr *)(smumgr->backend);
+
+	smu_free_memory(smumgr->device, (void *)priv->smu_buffer.handle);
+	smu_free_memory(smumgr->device, (void *)priv->header_buffer.handle);
+
 	if (smumgr->backend != NULL) {
 		kfree(smumgr->backend);
 		smumgr->backend = NULL;
 	}
+
+	cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c
index fef1b04c2aab..0813c2f06931 100644
--- a/drivers/gpu/drm/arm/hdlcd_crtc.c
+++ b/drivers/gpu/drm/arm/hdlcd_crtc.c
@@ -33,8 +33,17 @@
  *
  */
 
+static void hdlcd_crtc_cleanup(struct drm_crtc *crtc)
+{
+	struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
+
+	/* stop the controller on cleanup */
+	hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0);
+	drm_crtc_cleanup(crtc);
+}
+
 static const struct drm_crtc_funcs hdlcd_crtc_funcs = {
-	.destroy = drm_crtc_cleanup,
+	.destroy = hdlcd_crtc_cleanup,
 	.set_config = drm_atomic_helper_set_config,
 	.page_flip = drm_atomic_helper_page_flip,
 	.reset = drm_atomic_helper_crtc_reset,
@@ -97,7 +106,7 @@ static void hdlcd_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
 	struct drm_display_mode *m = &crtc->state->adjusted_mode;
 	struct videomode vm;
-	unsigned int polarities, line_length, err;
+	unsigned int polarities, err;
 
 	vm.vfront_porch = m->crtc_vsync_start - m->crtc_vdisplay;
 	vm.vback_porch = m->crtc_vtotal - m->crtc_vsync_end;
@@ -113,23 +122,18 @@ static void hdlcd_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	if (m->flags & DRM_MODE_FLAG_PVSYNC)
 		polarities |= HDLCD_POLARITY_VSYNC;
 
-	line_length = crtc->primary->state->fb->pitches[0];
-
 	/* Allow max number of outstanding requests and largest burst size */
 	hdlcd_write(hdlcd, HDLCD_REG_BUS_OPTIONS,
 		    HDLCD_BUS_MAX_OUTSTAND | HDLCD_BUS_BURST_16);
 
-	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_LENGTH, line_length);
-	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_PITCH, line_length);
-	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_COUNT, m->crtc_vdisplay - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_V_DATA, m->crtc_vdisplay - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_V_BACK_PORCH, vm.vback_porch - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_V_FRONT_PORCH, vm.vfront_porch - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_V_SYNC, vm.vsync_len - 1);
+	hdlcd_write(hdlcd, HDLCD_REG_H_DATA, m->crtc_hdisplay - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_H_BACK_PORCH, vm.hback_porch - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_H_FRONT_PORCH, vm.hfront_porch - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_H_SYNC, vm.hsync_len - 1);
-	hdlcd_write(hdlcd, HDLCD_REG_H_DATA, m->crtc_hdisplay - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_POLARITIES, polarities);
 
 	err = hdlcd_set_pxl_fmt(crtc);
@@ -144,20 +148,19 @@ static void hdlcd_crtc_enable(struct drm_crtc *crtc)
 	struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
 
 	clk_prepare_enable(hdlcd->clk);
+	hdlcd_crtc_mode_set_nofb(crtc);
 	hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 1);
-	drm_crtc_vblank_on(crtc);
 }
 
 static void hdlcd_crtc_disable(struct drm_crtc *crtc)
 {
 	struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
 
-	if (!crtc->primary->fb)
+	if (!crtc->state->active)
 		return;
 
-	clk_disable_unprepare(hdlcd->clk);
 	hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0);
-	drm_crtc_vblank_off(crtc);
+	clk_disable_unprepare(hdlcd->clk);
 }
 
 static int hdlcd_crtc_atomic_check(struct drm_crtc *crtc,
@@ -179,20 +182,17 @@ static int hdlcd_crtc_atomic_check(struct drm_crtc *crtc,
 static void hdlcd_crtc_atomic_begin(struct drm_crtc *crtc,
 				    struct drm_crtc_state *state)
 {
-	struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
-	unsigned long flags;
-
-	if (crtc->state->event) {
-		struct drm_pending_vblank_event *event = crtc->state->event;
+	struct drm_pending_vblank_event *event = crtc->state->event;
 
+	if (event) {
 		crtc->state->event = NULL;
-		event->pipe = drm_crtc_index(crtc);
-
-		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
 
-		spin_lock_irqsave(&crtc->dev->event_lock, flags);
-		list_add_tail(&event->base.link, &hdlcd->event_list);
-		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+		spin_lock_irq(&crtc->dev->event_lock);
+		if (drm_crtc_vblank_get(crtc) == 0)
+			drm_crtc_arm_vblank_event(crtc, event);
+		else
+			drm_crtc_send_vblank_event(crtc, event);
+		spin_unlock_irq(&crtc->dev->event_lock);
 	}
 }
 
@@ -225,6 +225,15 @@ static const struct drm_crtc_helper_funcs hdlcd_crtc_helper_funcs = {
 static int hdlcd_plane_atomic_check(struct drm_plane *plane,
 				    struct drm_plane_state *state)
 {
+	u32 src_w, src_h;
+
+	src_w = state->src_w >> 16;
+	src_h = state->src_h >> 16;
+
+	/* we can't do any scaling of the plane source */
+	if ((src_w != state->crtc_w) || (src_h != state->crtc_h))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -233,20 +242,31 @@ static void hdlcd_plane_atomic_update(struct drm_plane *plane,
 {
 	struct hdlcd_drm_private *hdlcd;
 	struct drm_gem_cma_object *gem;
+	unsigned int depth, bpp;
+	u32 src_w, src_h, dest_w, dest_h;
 	dma_addr_t scanout_start;
 
-	if (!plane->state->crtc || !plane->state->fb)
+	if (!plane->state->fb)
 		return;
 
-	hdlcd = crtc_to_hdlcd_priv(plane->state->crtc);
+	drm_fb_get_bpp_depth(plane->state->fb->pixel_format, &depth, &bpp);
+	src_w = plane->state->src_w >> 16;
+	src_h = plane->state->src_h >> 16;
+	dest_w = plane->state->crtc_w;
+	dest_h = plane->state->crtc_h;
 	gem = drm_fb_cma_get_gem_obj(plane->state->fb, 0);
-	scanout_start = gem->paddr;
+	scanout_start = gem->paddr + plane->state->fb->offsets[0] +
+		plane->state->crtc_y * plane->state->fb->pitches[0] +
+		plane->state->crtc_x * bpp / 8;
+
+	hdlcd = plane->dev->dev_private;
+	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_LENGTH, plane->state->fb->pitches[0]);
+	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_PITCH, plane->state->fb->pitches[0]);
+	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_COUNT, dest_h - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_FB_BASE, scanout_start);
 }
 
 static const struct drm_plane_helper_funcs hdlcd_plane_helper_funcs = {
-	.prepare_fb = NULL,
-	.cleanup_fb = NULL,
 	.atomic_check = hdlcd_plane_atomic_check,
 	.atomic_update = hdlcd_plane_atomic_update,
 };
@@ -294,16 +314,6 @@ static struct drm_plane *hdlcd_plane_init(struct drm_device *drm)
 	return plane;
 }
 
-void hdlcd_crtc_suspend(struct drm_crtc *crtc)
-{
-	hdlcd_crtc_disable(crtc);
-}
-
-void hdlcd_crtc_resume(struct drm_crtc *crtc)
-{
-	hdlcd_crtc_enable(crtc);
-}
-
 int hdlcd_setup_crtc(struct drm_device *drm)
 {
 	struct hdlcd_drm_private *hdlcd = drm->dev_private;
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c
index b987c63ba8d6..a6ca36f0096f 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.c
+++ b/drivers/gpu/drm/arm/hdlcd_drv.c
@@ -49,8 +49,6 @@ static int hdlcd_load(struct drm_device *drm, unsigned long flags)
 	atomic_set(&hdlcd->dma_end_count, 0);
 #endif
 
-	INIT_LIST_HEAD(&hdlcd->event_list);
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	hdlcd->mmio = devm_ioremap_resource(drm->dev, res);
 	if (IS_ERR(hdlcd->mmio)) {
@@ -84,11 +82,7 @@ static int hdlcd_load(struct drm_device *drm, unsigned long flags)
 		goto setup_fail;
 	}
 
-	pm_runtime_enable(drm->dev);
-
-	pm_runtime_get_sync(drm->dev);
 	ret = drm_irq_install(drm, platform_get_irq(pdev, 0));
-	pm_runtime_put_sync(drm->dev);
 	if (ret < 0) {
 		DRM_ERROR("failed to install IRQ handler\n");
 		goto irq_fail;
@@ -164,24 +158,9 @@ static irqreturn_t hdlcd_irq(int irq, void *arg)
 		atomic_inc(&hdlcd->vsync_count);
 
 #endif
-	if (irq_status & HDLCD_INTERRUPT_VSYNC) {
-		bool events_sent = false;
-		unsigned long flags;
-		struct drm_pending_vblank_event	*e, *t;
-
+	if (irq_status & HDLCD_INTERRUPT_VSYNC)
 		drm_crtc_handle_vblank(&hdlcd->crtc);
 
-		spin_lock_irqsave(&drm->event_lock, flags);
-		list_for_each_entry_safe(e, t, &hdlcd->event_list, base.link) {
-			list_del(&e->base.link);
-			drm_crtc_send_vblank_event(&hdlcd->crtc, e);
-			events_sent = true;
-		}
-		if (events_sent)
-			drm_crtc_vblank_put(&hdlcd->crtc);
-		spin_unlock_irqrestore(&drm->event_lock, flags);
-	}
-
 	/* acknowledge interrupt(s) */
 	hdlcd_write(hdlcd, HDLCD_REG_INT_CLEAR, irq_status);
 
@@ -275,6 +254,7 @@ static int hdlcd_show_pxlclock(struct seq_file *m, void *arg)
 static struct drm_info_list hdlcd_debugfs_list[] = {
 	{ "interrupt_count", hdlcd_show_underrun_count, 0 },
 	{ "clocks", hdlcd_show_pxlclock, 0 },
+	{ "fb", drm_fb_cma_debugfs_show, 0 },
 };
 
 static int hdlcd_debugfs_init(struct drm_minor *minor)
@@ -357,6 +337,8 @@ static int hdlcd_drm_bind(struct device *dev)
 		return -ENOMEM;
 
 	drm->dev_private = hdlcd;
+	dev_set_drvdata(dev, drm);
+
 	hdlcd_setup_mode_config(drm);
 	ret = hdlcd_load(drm, 0);
 	if (ret)
@@ -366,14 +348,18 @@ static int hdlcd_drm_bind(struct device *dev)
 	if (ret)
 		goto err_unload;
 
-	dev_set_drvdata(dev, drm);
-
 	ret = component_bind_all(dev, drm);
 	if (ret) {
 		DRM_ERROR("Failed to bind all components\n");
 		goto err_unregister;
 	}
 
+	ret = pm_runtime_set_active(dev);
+	if (ret)
+		goto err_pm_active;
+
+	pm_runtime_enable(dev);
+
 	ret = drm_vblank_init(drm, drm->mode_config.num_crtc);
 	if (ret < 0) {
 		DRM_ERROR("failed to initialise vblank\n");
@@ -399,16 +385,16 @@ err_fbdev:
 	drm_mode_config_cleanup(drm);
 	drm_vblank_cleanup(drm);
 err_vblank:
+	pm_runtime_disable(drm->dev);
+err_pm_active:
 	component_unbind_all(dev, drm);
 err_unregister:
 	drm_dev_unregister(drm);
 err_unload:
-	pm_runtime_get_sync(drm->dev);
 	drm_irq_uninstall(drm);
-	pm_runtime_put_sync(drm->dev);
-	pm_runtime_disable(drm->dev);
 	of_reserved_mem_device_release(drm->dev);
 err_free:
+	dev_set_drvdata(dev, NULL);
 	drm_dev_unref(drm);
 
 	return ret;
@@ -495,30 +481,34 @@ MODULE_DEVICE_TABLE(of, hdlcd_of_match);
 static int __maybe_unused hdlcd_pm_suspend(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct drm_crtc *crtc;
+	struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
 
-	if (pm_runtime_suspended(dev))
+	if (!hdlcd)
 		return 0;
 
-	drm_modeset_lock_all(drm);
-	list_for_each_entry(crtc, &drm->mode_config.crtc_list, head)
-		hdlcd_crtc_suspend(crtc);
-	drm_modeset_unlock_all(drm);
+	drm_kms_helper_poll_disable(drm);
+
+	hdlcd->state = drm_atomic_helper_suspend(drm);
+	if (IS_ERR(hdlcd->state)) {
+		drm_kms_helper_poll_enable(drm);
+		return PTR_ERR(hdlcd->state);
+	}
+
 	return 0;
 }
 
 static int __maybe_unused hdlcd_pm_resume(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct drm_crtc *crtc;
+	struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
 
-	if (!pm_runtime_suspended(dev))
+	if (!hdlcd)
 		return 0;
 
-	drm_modeset_lock_all(drm);
-	list_for_each_entry(crtc, &drm->mode_config.crtc_list, head)
-		hdlcd_crtc_resume(crtc);
-	drm_modeset_unlock_all(drm);
+	drm_atomic_helper_resume(drm, hdlcd->state);
+	drm_kms_helper_poll_enable(drm);
+	pm_runtime_set_active(dev);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.h b/drivers/gpu/drm/arm/hdlcd_drv.h
index aa234784f053..e3950a071152 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.h
+++ b/drivers/gpu/drm/arm/hdlcd_drv.h
@@ -9,10 +9,9 @@ struct hdlcd_drm_private {
 	void __iomem			*mmio;
 	struct clk			*clk;
 	struct drm_fbdev_cma		*fbdev;
-	struct drm_framebuffer		*fb;
-	struct list_head		event_list;
 	struct drm_crtc			crtc;
 	struct drm_plane		*plane;
+	struct drm_atomic_state		*state;
 #ifdef CONFIG_DEBUG_FS
 	atomic_t buffer_underrun_count;
 	atomic_t bus_error_count;
@@ -36,7 +35,5 @@ static inline u32 hdlcd_read(struct hdlcd_drm_private *hdlcd, unsigned int reg)
 
 int hdlcd_setup_crtc(struct drm_device *dev);
 void hdlcd_set_scanout(struct hdlcd_drm_private *hdlcd);
-void hdlcd_crtc_suspend(struct drm_crtc *crtc);
-void hdlcd_crtc_resume(struct drm_crtc *crtc);
 
 #endif /* __HDLCD_DRV_H__ */
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index cf23a755f777..bd12231ab0cd 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -391,12 +391,11 @@ void atmel_hlcdc_crtc_reset(struct drm_crtc *crtc)
 {
 	struct atmel_hlcdc_crtc_state *state;
 
-	if (crtc->state && crtc->state->mode_blob)
-		drm_property_unreference_blob(crtc->state->mode_blob);
-
 	if (crtc->state) {
+		__drm_atomic_helper_crtc_destroy_state(crtc->state);
 		state = drm_crtc_state_to_atmel_hlcdc_crtc_state(crtc->state);
 		kfree(state);
+		crtc->state = NULL;
 	}
 
 	state = kzalloc(sizeof(*state), GFP_KERNEL);
@@ -415,8 +414,9 @@ atmel_hlcdc_crtc_duplicate_state(struct drm_crtc *crtc)
 		return NULL;
 
 	state = kmalloc(sizeof(*state), GFP_KERNEL);
-	if (state)
-		__drm_atomic_helper_crtc_duplicate_state(crtc, &state->base);
+	if (!state)
+		return NULL;
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &state->base);
 
 	cur = drm_crtc_state_to_atmel_hlcdc_crtc_state(crtc->state);
 	state->output_mode = cur->output_mode;
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
index 39802c0539b6..3d34fc4ca826 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
@@ -266,9 +266,10 @@ int atmel_hlcdc_create_outputs(struct drm_device *dev)
 		if (!ret)
 			ret = atmel_hlcdc_check_endpoint(dev, &ep);
 
-		of_node_put(ep_np);
-		if (ret)
+		if (ret) {
+			of_node_put(ep_np);
 			return ret;
+		}
 	}
 
 	for_each_endpoint_of_node(dev->dev->of_node, ep_np) {
@@ -276,9 +277,10 @@ int atmel_hlcdc_create_outputs(struct drm_device *dev)
 		if (!ret)
 			ret = atmel_hlcdc_attach_endpoint(dev, &ep);
 
-		of_node_put(ep_np);
-		if (ret)
+		if (ret) {
+			of_node_put(ep_np);
 			return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index aef3ca8a81fa..016c191221f3 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -339,6 +339,8 @@ atmel_hlcdc_plane_update_pos_and_size(struct atmel_hlcdc_plane *plane,
 
 		atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff,
 					     factor_reg);
+	} else {
+		atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, 0);
 	}
 }
 
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 3ff1ed7b33db..9bb99e274d23 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -351,6 +351,8 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
 	drm_property_unreference_blob(state->mode_blob);
 	state->mode_blob = NULL;
 
+	memset(&state->mode, 0, sizeof(state->mode));
+
 	if (blob) {
 		if (blob->length != sizeof(struct drm_mode_modeinfo) ||
 		    drm_mode_convert_umode(&state->mode,
@@ -363,7 +365,6 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
 		DRM_DEBUG_ATOMIC("Set [MODE:%s] for CRTC state %p\n",
 				 state->mode.name, state);
 	} else {
-		memset(&state->mode, 0, sizeof(state->mode));
 		state->enable = false;
 		DRM_DEBUG_ATOMIC("Set [NOMODE] for CRTC state %p\n",
 				 state);
@@ -1295,14 +1296,39 @@ EXPORT_SYMBOL(drm_atomic_add_affected_planes);
  */
 void drm_atomic_legacy_backoff(struct drm_atomic_state *state)
 {
+	struct drm_device *dev = state->dev;
+	unsigned crtc_mask = 0;
+	struct drm_crtc *crtc;
 	int ret;
+	bool global = false;
+
+	drm_for_each_crtc(crtc, dev) {
+		if (crtc->acquire_ctx != state->acquire_ctx)
+			continue;
+
+		crtc_mask |= drm_crtc_mask(crtc);
+		crtc->acquire_ctx = NULL;
+	}
+
+	if (WARN_ON(dev->mode_config.acquire_ctx == state->acquire_ctx)) {
+		global = true;
+
+		dev->mode_config.acquire_ctx = NULL;
+	}
 
 retry:
 	drm_modeset_backoff(state->acquire_ctx);
 
-	ret = drm_modeset_lock_all_ctx(state->dev, state->acquire_ctx);
+	ret = drm_modeset_lock_all_ctx(dev, state->acquire_ctx);
 	if (ret)
 		goto retry;
+
+	drm_for_each_crtc(crtc, dev)
+		if (drm_crtc_mask(crtc) & crtc_mask)
+			crtc->acquire_ctx = state->acquire_ctx;
+
+	if (global)
+		dev->mode_config.acquire_ctx = state->acquire_ctx;
 }
 EXPORT_SYMBOL(drm_atomic_legacy_backoff);
 
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index d2a6d958ca76..0e3cc66aa8b7 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -2821,8 +2821,6 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 			goto out;
 		}
 
-		drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V);
-
 		/*
 		 * Check whether the primary plane supports the fb pixel format.
 		 * Drivers not implementing the universal planes API use a
@@ -4841,7 +4839,8 @@ bool drm_property_change_valid_get(struct drm_property *property,
 		if (value == 0)
 			return true;
 
-		return _object_find(property->dev, value, property->values[0]) != NULL;
+		*ref = _object_find(property->dev, value, property->values[0]);
+		return *ref != NULL;
 	}
 
 	for (i = 0; i < property->num_values; i++)
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index a6e42433ef0e..26feb2f8453f 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -528,11 +528,11 @@ drm_crtc_helper_disable(struct drm_crtc *crtc)
 int drm_crtc_helper_set_config(struct drm_mode_set *set)
 {
 	struct drm_device *dev;
-	struct drm_crtc *new_crtc;
-	struct drm_encoder *save_encoders, *new_encoder, *encoder;
+	struct drm_crtc **save_encoder_crtcs, *new_crtc;
+	struct drm_encoder **save_connector_encoders, *new_encoder, *encoder;
 	bool mode_changed = false; /* if true do a full mode set */
 	bool fb_changed = false; /* if true and !mode_changed just do a flip */
-	struct drm_connector *save_connectors, *connector;
+	struct drm_connector *connector;
 	int count = 0, ro, fail = 0;
 	const struct drm_crtc_helper_funcs *crtc_funcs;
 	struct drm_mode_set save_set;
@@ -574,15 +574,15 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
 	 * Allocate space for the backup of all (non-pointer) encoder and
 	 * connector data.
 	 */
-	save_encoders = kzalloc(dev->mode_config.num_encoder *
-				sizeof(struct drm_encoder), GFP_KERNEL);
-	if (!save_encoders)
+	save_encoder_crtcs = kzalloc(dev->mode_config.num_encoder *
+				sizeof(struct drm_crtc *), GFP_KERNEL);
+	if (!save_encoder_crtcs)
 		return -ENOMEM;
 
-	save_connectors = kzalloc(dev->mode_config.num_connector *
-				sizeof(struct drm_connector), GFP_KERNEL);
-	if (!save_connectors) {
-		kfree(save_encoders);
+	save_connector_encoders = kzalloc(dev->mode_config.num_connector *
+				sizeof(struct drm_encoder *), GFP_KERNEL);
+	if (!save_connector_encoders) {
+		kfree(save_encoder_crtcs);
 		return -ENOMEM;
 	}
 
@@ -593,12 +593,12 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
 	 */
 	count = 0;
 	drm_for_each_encoder(encoder, dev) {
-		save_encoders[count++] = *encoder;
+		save_encoder_crtcs[count++] = encoder->crtc;
 	}
 
 	count = 0;
 	drm_for_each_connector(connector, dev) {
-		save_connectors[count++] = *connector;
+		save_connector_encoders[count++] = connector->encoder;
 	}
 
 	save_set.crtc = set->crtc;
@@ -631,8 +631,12 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
 		mode_changed = true;
 	}
 
-	/* take a reference on all connectors in set */
+	/* take a reference on all unbound connectors in set, reuse the
+	 * already taken reference for bound connectors
+	 */
 	for (ro = 0; ro < set->num_connectors; ro++) {
+		if (set->connectors[ro]->encoder)
+			continue;
 		drm_connector_reference(set->connectors[ro]);
 	}
 
@@ -754,30 +758,28 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
 		}
 	}
 
-	/* after fail drop reference on all connectors in save set */
-	count = 0;
-	drm_for_each_connector(connector, dev) {
-		drm_connector_unreference(&save_connectors[count++]);
-	}
-
-	kfree(save_connectors);
-	kfree(save_encoders);
+	kfree(save_connector_encoders);
+	kfree(save_encoder_crtcs);
 	return 0;
 
 fail:
 	/* Restore all previous data. */
 	count = 0;
 	drm_for_each_encoder(encoder, dev) {
-		*encoder = save_encoders[count++];
+		encoder->crtc = save_encoder_crtcs[count++];
 	}
 
 	count = 0;
 	drm_for_each_connector(connector, dev) {
-		*connector = save_connectors[count++];
+		connector->encoder = save_connector_encoders[count++];
 	}
 
-	/* after fail drop reference on all connectors in set */
+	/* after fail drop reference on all unbound connectors in set, let
+	 * bound connectors keep their reference
+	 */
 	for (ro = 0; ro < set->num_connectors; ro++) {
+		if (set->connectors[ro]->encoder)
+			continue;
 		drm_connector_unreference(set->connectors[ro]);
 	}
 
@@ -787,8 +789,8 @@ fail:
 				      save_set.y, save_set.fb))
 		DRM_ERROR("failed to restore config after modeset failure\n");
 
-	kfree(save_connectors);
-	kfree(save_encoders);
+	kfree(save_connector_encoders);
+	kfree(save_encoder_crtcs);
 	return ret;
 }
 EXPORT_SYMBOL(drm_crtc_helper_set_config);
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index a13edf5de2d6..6537908050d7 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -2927,11 +2927,9 @@ static void drm_dp_destroy_connector_work(struct work_struct *work)
 		drm_dp_port_teardown_pdt(port, port->pdt);
 
 		if (!port->input && port->vcpi.vcpi > 0) {
-			if (mgr->mst_state) {
-				drm_dp_mst_reset_vcpi_slots(mgr, port);
-				drm_dp_update_payload_part1(mgr);
-				drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
-			}
+			drm_dp_mst_reset_vcpi_slots(mgr, port);
+			drm_dp_update_payload_part1(mgr);
+			drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
 		}
 
 		kref_put(&port->kref, drm_dp_free_mst_port);
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index 172cafe11c71..5075fae3c4e2 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -445,7 +445,7 @@ err_cma_destroy:
 err_fb_info_destroy:
 	drm_fb_helper_release_fbi(helper);
 err_gem_free_object:
-	dev->driver->gem_free_object(&obj->base);
+	drm_gem_object_unreference_unlocked(&obj->base);
 	return ret;
 }
 EXPORT_SYMBOL(drm_fbdev_cma_create_with_funcs);
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index e1ab008b3f08..1d6c335584ec 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -121,7 +121,7 @@ struct drm_gem_cma_object *drm_gem_cma_create(struct drm_device *drm,
 	return cma_obj;
 
 error:
-	drm->driver->gem_free_object(&cma_obj->base);
+	drm_gem_object_unreference_unlocked(&cma_obj->base);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(drm_gem_cma_create);
@@ -162,18 +162,12 @@ drm_gem_cma_create_with_handle(struct drm_file *file_priv,
 	 * and handle has the id what user can see.
 	 */
 	ret = drm_gem_handle_create(file_priv, gem_obj, handle);
-	if (ret)
-		goto err_handle_create;
-
 	/* drop reference from allocate - handle holds it now. */
 	drm_gem_object_unreference_unlocked(gem_obj);
+	if (ret)
+		return ERR_PTR(ret);
 
 	return cma_obj;
-
-err_handle_create:
-	drm->driver->gem_free_object(gem_obj);
-
-	return ERR_PTR(ret);
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 7def3d58da18..e5e6f504d8cc 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1518,6 +1518,8 @@ int drm_mode_convert_umode(struct drm_display_mode *out,
 	if (out->status != MODE_OK)
 		goto out;
 
+	drm_mode_set_crtcinfo(out, CRTC_INTERLACE_HALVE_V);
+
 	ret = 0;
 
 out:
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
index 522cfd447892..16353ee81651 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
@@ -225,6 +225,7 @@ struct iommu_domain *etnaviv_iommu_domain_alloc(struct etnaviv_gpu *gpu)
 
 	etnaviv_domain->domain.type = __IOMMU_DOMAIN_PAGING;
 	etnaviv_domain->domain.ops = &etnaviv_iommu_ops.ops;
+	etnaviv_domain->domain.pgsize_bitmap = SZ_4K;
 	etnaviv_domain->domain.geometry.aperture_start = GPU_MEM_START;
 	etnaviv_domain->domain.geometry.aperture_end = GPU_MEM_START + PT_ENTRIES * SZ_4K - 1;
 
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index f6223f907c15..7f9901b7777b 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -31,7 +31,6 @@
 #include "exynos_drm_plane.h"
 #include "exynos_drm_drv.h"
 #include "exynos_drm_fb.h"
-#include "exynos_drm_fbdev.h"
 #include "exynos_drm_iommu.h"
 
 /*
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 468498e3fec1..4c1fb3f8b5a6 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -34,7 +34,7 @@
 
 struct exynos_dp_device {
 	struct drm_encoder         encoder;
-	struct drm_connector       connector;
+	struct drm_connector       *connector;
 	struct drm_bridge          *ptn_bridge;
 	struct drm_device          *drm_dev;
 	struct device              *dev;
@@ -70,7 +70,7 @@ static int exynos_dp_poweroff(struct analogix_dp_plat_data *plat_data)
 static int exynos_dp_get_modes(struct analogix_dp_plat_data *plat_data)
 {
 	struct exynos_dp_device *dp = to_dp(plat_data);
-	struct drm_connector *connector = &dp->connector;
+	struct drm_connector *connector = dp->connector;
 	struct drm_display_mode *mode;
 	int num_modes = 0;
 
@@ -103,6 +103,7 @@ static int exynos_dp_bridge_attach(struct analogix_dp_plat_data *plat_data,
 	int ret;
 
 	drm_connector_register(connector);
+	dp->connector = connector;
 
 	/* Pre-empt DP connector creation if there's a bridge */
 	if (dp->ptn_bridge) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c
index 011211e4167d..edbd98ff293e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_core.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_core.c
@@ -15,7 +15,6 @@
 #include <drm/drmP.h>
 #include "exynos_drm_drv.h"
 #include "exynos_drm_crtc.h"
-#include "exynos_drm_fbdev.h"
 
 static LIST_HEAD(exynos_drm_subdrv_list);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 3efe1aa89416..d47216488985 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -30,7 +30,6 @@
 
 #include "exynos_drm_drv.h"
 #include "exynos_drm_fb.h"
-#include "exynos_drm_fbdev.h"
 #include "exynos_drm_crtc.h"
 #include "exynos_drm_plane.h"
 #include "exynos_drm_iommu.h"
@@ -120,7 +119,6 @@ static struct fimd_driver_data s3c64xx_fimd_driver_data = {
 	.timing_base = 0x0,
 	.has_clksel = 1,
 	.has_limited_fmt = 1,
-	.has_hw_trigger = 1,
 };
 
 static struct fimd_driver_data exynos3_fimd_driver_data = {
@@ -171,14 +169,11 @@ static struct fimd_driver_data exynos5420_fimd_driver_data = {
 	.lcdblk_vt_shift = 24,
 	.lcdblk_bypass_shift = 15,
 	.lcdblk_mic_bypass_shift = 11,
-	.trg_type = I80_HW_TRG,
 	.has_shadowcon = 1,
 	.has_vidoutcon = 1,
 	.has_vtsel = 1,
 	.has_mic_bypass = 1,
 	.has_dp_clk = 1,
-	.has_hw_trigger = 1,
-	.has_trigger_per_te = 1,
 };
 
 struct fimd_context {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 493552368295..8564c3da0d22 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -48,13 +48,13 @@
 
 /* registers for base address */
 #define G2D_SRC_BASE_ADDR		0x0304
-#define G2D_SRC_STRIDE_REG		0x0308
+#define G2D_SRC_STRIDE			0x0308
 #define G2D_SRC_COLOR_MODE		0x030C
 #define G2D_SRC_LEFT_TOP		0x0310
 #define G2D_SRC_RIGHT_BOTTOM		0x0314
 #define G2D_SRC_PLANE2_BASE_ADDR	0x0318
 #define G2D_DST_BASE_ADDR		0x0404
-#define G2D_DST_STRIDE_REG		0x0408
+#define G2D_DST_STRIDE			0x0408
 #define G2D_DST_COLOR_MODE		0x040C
 #define G2D_DST_LEFT_TOP		0x0410
 #define G2D_DST_RIGHT_BOTTOM		0x0414
@@ -563,7 +563,7 @@ static enum g2d_reg_type g2d_get_reg_type(int reg_offset)
 
 	switch (reg_offset) {
 	case G2D_SRC_BASE_ADDR:
-	case G2D_SRC_STRIDE_REG:
+	case G2D_SRC_STRIDE:
 	case G2D_SRC_COLOR_MODE:
 	case G2D_SRC_LEFT_TOP:
 	case G2D_SRC_RIGHT_BOTTOM:
@@ -573,7 +573,7 @@ static enum g2d_reg_type g2d_get_reg_type(int reg_offset)
 		reg_type = REG_TYPE_SRC_PLANE2;
 		break;
 	case G2D_DST_BASE_ADDR:
-	case G2D_DST_STRIDE_REG:
+	case G2D_DST_STRIDE:
 	case G2D_DST_COLOR_MODE:
 	case G2D_DST_LEFT_TOP:
 	case G2D_DST_RIGHT_BOTTOM:
@@ -968,8 +968,8 @@ static int g2d_check_reg_offset(struct device *dev,
 			} else
 				buf_info->types[reg_type] = BUF_TYPE_GEM;
 			break;
-		case G2D_SRC_STRIDE_REG:
-		case G2D_DST_STRIDE_REG:
+		case G2D_SRC_STRIDE:
+		case G2D_DST_STRIDE:
 			if (for_addr)
 				goto err;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index 55f1d37c666a..77f12c00abf9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -242,7 +242,7 @@ exynos_drm_plane_check_size(const struct exynos_drm_plane_config *config,
 	    state->v_ratio == (1 << 15))
 		height_ok = true;
 
-	if (width_ok & height_ok)
+	if (width_ok && height_ok)
 		return 0;
 
 	DRM_DEBUG_KMS("scaling mode is not supported");
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
index 0ec1ad961e0d..dc723f7ead7d 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
@@ -42,9 +42,10 @@ static const struct regmap_config fsl_dcu_regmap_config = {
 	.reg_bits = 32,
 	.reg_stride = 4,
 	.val_bits = 32,
-	.cache_type = REGCACHE_RBTREE,
+	.cache_type = REGCACHE_FLAT,
 
 	.volatile_reg = fsl_dcu_drm_is_volatile_reg,
+	.max_register = 0x11fc,
 };
 
 static int fsl_dcu_drm_irq_init(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 5faacc6e548d..7c334e902266 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3481,6 +3481,7 @@ int intel_bios_init(struct drm_i915_private *dev_priv);
 bool intel_bios_is_valid_vbt(const void *buf, size_t size);
 bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv);
 bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin);
+bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port);
 bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port);
 bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv, enum port port);
 bool intel_bios_is_dsi_present(struct drm_i915_private *dev_priv, enum port *port);
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index b235b6e88ead..b9022fa053d6 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -139,6 +139,11 @@ fill_detail_timing_data(struct drm_display_mode *panel_fixed_mode,
 	else
 		panel_fixed_mode->flags |= DRM_MODE_FLAG_NVSYNC;
 
+	panel_fixed_mode->width_mm = (dvo_timing->himage_hi << 8) |
+		dvo_timing->himage_lo;
+	panel_fixed_mode->height_mm = (dvo_timing->vimage_hi << 8) |
+		dvo_timing->vimage_lo;
+
 	/* Some VBTs have bogus h/vtotal values */
 	if (panel_fixed_mode->hsync_end > panel_fixed_mode->htotal)
 		panel_fixed_mode->htotal = panel_fixed_mode->hsync_end + 1;
@@ -1187,7 +1192,7 @@ parse_device_mapping(struct drm_i915_private *dev_priv,
 	}
 	if (bdb->version < 106) {
 		expected_size = 22;
-	} else if (bdb->version < 109) {
+	} else if (bdb->version < 111) {
 		expected_size = 27;
 	} else if (bdb->version < 195) {
 		BUILD_BUG_ON(sizeof(struct old_child_dev_config) != 33);
@@ -1546,6 +1551,45 @@ bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin)
 }
 
 /**
+ * intel_bios_is_port_present - is the specified digital port present
+ * @dev_priv:	i915 device instance
+ * @port:	port to check
+ *
+ * Return true if the device in %port is present.
+ */
+bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port)
+{
+	static const struct {
+		u16 dp, hdmi;
+	} port_mapping[] = {
+		[PORT_B] = { DVO_PORT_DPB, DVO_PORT_HDMIB, },
+		[PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, },
+		[PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, },
+		[PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, },
+	};
+	int i;
+
+	/* FIXME maybe deal with port A as well? */
+	if (WARN_ON(port == PORT_A) || port >= ARRAY_SIZE(port_mapping))
+		return false;
+
+	if (!dev_priv->vbt.child_dev_num)
+		return false;
+
+	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
+		const union child_device_config *p_child =
+			&dev_priv->vbt.child_dev[i];
+		if ((p_child->common.dvo_port == port_mapping[port].dp ||
+		     p_child->common.dvo_port == port_mapping[port].hdmi) &&
+		    (p_child->common.device_type & (DEVICE_TYPE_TMDS_DVI_SIGNALING |
+						    DEVICE_TYPE_DISPLAYPORT_OUTPUT)))
+			return true;
+	}
+
+	return false;
+}
+
+/**
  * intel_bios_is_port_edp - is the device in given port eDP
  * @dev_priv:	i915 device instance
  * @port:	port to check
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 2113f401f0ba..56a1637c864f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -8275,12 +8275,14 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_encoder *encoder;
+	int i;
 	u32 val, final;
 	bool has_lvds = false;
 	bool has_cpu_edp = false;
 	bool has_panel = false;
 	bool has_ck505 = false;
 	bool can_ssc = false;
+	bool using_ssc_source = false;
 
 	/* We need to take the global config into account */
 	for_each_intel_encoder(dev, encoder) {
@@ -8307,8 +8309,22 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		can_ssc = true;
 	}
 
-	DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d\n",
-		      has_panel, has_lvds, has_ck505);
+	/* Check if any DPLLs are using the SSC source */
+	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
+		u32 temp = I915_READ(PCH_DPLL(i));
+
+		if (!(temp & DPLL_VCO_ENABLE))
+			continue;
+
+		if ((temp & PLL_REF_INPUT_MASK) ==
+		    PLLB_REF_INPUT_SPREADSPECTRUMIN) {
+			using_ssc_source = true;
+			break;
+		}
+	}
+
+	DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d using_ssc_source %d\n",
+		      has_panel, has_lvds, has_ck505, using_ssc_source);
 
 	/* Ironlake: try to setup display ref clock before DPLL
 	 * enabling. This is only under driver's control after
@@ -8345,9 +8361,9 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 				final |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD;
 		} else
 			final |= DREF_CPU_SOURCE_OUTPUT_DISABLE;
-	} else {
-		final |= DREF_SSC_SOURCE_DISABLE;
-		final |= DREF_CPU_SOURCE_OUTPUT_DISABLE;
+	} else if (using_ssc_source) {
+		final |= DREF_SSC_SOURCE_ENABLE;
+		final |= DREF_SSC1_ENABLE;
 	}
 
 	if (final == val)
@@ -8393,7 +8409,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		POSTING_READ(PCH_DREF_CONTROL);
 		udelay(200);
 	} else {
-		DRM_DEBUG_KMS("Disabling SSC entirely\n");
+		DRM_DEBUG_KMS("Disabling CPU source output\n");
 
 		val &= ~DREF_CPU_SOURCE_OUTPUT_MASK;
 
@@ -8404,16 +8420,20 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		POSTING_READ(PCH_DREF_CONTROL);
 		udelay(200);
 
-		/* Turn off the SSC source */
-		val &= ~DREF_SSC_SOURCE_MASK;
-		val |= DREF_SSC_SOURCE_DISABLE;
+		if (!using_ssc_source) {
+			DRM_DEBUG_KMS("Disabling SSC source\n");
 
-		/* Turn off SSC1 */
-		val &= ~DREF_SSC1_ENABLE;
+			/* Turn off the SSC source */
+			val &= ~DREF_SSC_SOURCE_MASK;
+			val |= DREF_SSC_SOURCE_DISABLE;
 
-		I915_WRITE(PCH_DREF_CONTROL, val);
-		POSTING_READ(PCH_DREF_CONTROL);
-		udelay(200);
+			/* Turn off SSC1 */
+			val &= ~DREF_SSC1_ENABLE;
+
+			I915_WRITE(PCH_DREF_CONTROL, val);
+			POSTING_READ(PCH_DREF_CONTROL);
+			udelay(200);
+		}
 	}
 
 	BUG_ON(val != final);
@@ -14554,6 +14574,8 @@ static void intel_setup_outputs(struct drm_device *dev)
 		if (I915_READ(PCH_DP_D) & DP_DETECTED)
 			intel_dp_init(dev, PCH_DP_D, PORT_D);
 	} else if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
+		bool has_edp, has_port;
+
 		/*
 		 * The DP_DETECTED bit is the latched state of the DDC
 		 * SDA pin at boot. However since eDP doesn't require DDC
@@ -14562,27 +14584,37 @@ static void intel_setup_outputs(struct drm_device *dev)
 		 * Thus we can't rely on the DP_DETECTED bit alone to detect
 		 * eDP ports. Consult the VBT as well as DP_DETECTED to
 		 * detect eDP ports.
+		 *
+		 * Sadly the straps seem to be missing sometimes even for HDMI
+		 * ports (eg. on Voyo V3 - CHT x7-Z8700), so check both strap
+		 * and VBT for the presence of the port. Additionally we can't
+		 * trust the port type the VBT declares as we've seen at least
+		 * HDMI ports that the VBT claim are DP or eDP.
 		 */
-		if (I915_READ(VLV_HDMIB) & SDVO_DETECTED &&
-		    !intel_dp_is_edp(dev, PORT_B))
+		has_edp = intel_dp_is_edp(dev, PORT_B);
+		has_port = intel_bios_is_port_present(dev_priv, PORT_B);
+		if (I915_READ(VLV_DP_B) & DP_DETECTED || has_port)
+			has_edp &= intel_dp_init(dev, VLV_DP_B, PORT_B);
+		if ((I915_READ(VLV_HDMIB) & SDVO_DETECTED || has_port) && !has_edp)
 			intel_hdmi_init(dev, VLV_HDMIB, PORT_B);
-		if (I915_READ(VLV_DP_B) & DP_DETECTED ||
-		    intel_dp_is_edp(dev, PORT_B))
-			intel_dp_init(dev, VLV_DP_B, PORT_B);
 
-		if (I915_READ(VLV_HDMIC) & SDVO_DETECTED &&
-		    !intel_dp_is_edp(dev, PORT_C))
+		has_edp = intel_dp_is_edp(dev, PORT_C);
+		has_port = intel_bios_is_port_present(dev_priv, PORT_C);
+		if (I915_READ(VLV_DP_C) & DP_DETECTED || has_port)
+			has_edp &= intel_dp_init(dev, VLV_DP_C, PORT_C);
+		if ((I915_READ(VLV_HDMIC) & SDVO_DETECTED || has_port) && !has_edp)
 			intel_hdmi_init(dev, VLV_HDMIC, PORT_C);
-		if (I915_READ(VLV_DP_C) & DP_DETECTED ||
-		    intel_dp_is_edp(dev, PORT_C))
-			intel_dp_init(dev, VLV_DP_C, PORT_C);
 
 		if (IS_CHERRYVIEW(dev)) {
-			/* eDP not supported on port D, so don't check VBT */
-			if (I915_READ(CHV_HDMID) & SDVO_DETECTED)
-				intel_hdmi_init(dev, CHV_HDMID, PORT_D);
-			if (I915_READ(CHV_DP_D) & DP_DETECTED)
+			/*
+			 * eDP not supported on port D,
+			 * so no need to worry about it
+			 */
+			has_port = intel_bios_is_port_present(dev_priv, PORT_D);
+			if (I915_READ(CHV_DP_D) & DP_DETECTED || has_port)
 				intel_dp_init(dev, CHV_DP_D, PORT_D);
+			if (I915_READ(CHV_HDMID) & SDVO_DETECTED || has_port)
+				intel_hdmi_init(dev, CHV_HDMID, PORT_D);
 		}
 
 		intel_dsi_init(dev);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index f192f58708c2..79cf2d5f5a20 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -4977,9 +4977,6 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 	intel_display_power_get(dev_priv, power_domain);
 
 	if (long_hpd) {
-		/* indicate that we need to restart link training */
-		intel_dp->train_set_valid = false;
-
 		intel_dp_long_pulse(intel_dp->attached_connector);
 		if (intel_dp->is_mst)
 			ret = IRQ_HANDLED;
@@ -5725,8 +5722,11 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	if (!fixed_mode && dev_priv->vbt.lfp_lvds_vbt_mode) {
 		fixed_mode = drm_mode_duplicate(dev,
 					dev_priv->vbt.lfp_lvds_vbt_mode);
-		if (fixed_mode)
+		if (fixed_mode) {
 			fixed_mode->type |= DRM_MODE_TYPE_PREFERRED;
+			connector->display_info.width_mm = fixed_mode->width_mm;
+			connector->display_info.height_mm = fixed_mode->height_mm;
+		}
 	}
 	mutex_unlock(&dev->mode_config.mutex);
 
@@ -5923,9 +5923,9 @@ fail:
 	return false;
 }
 
-void
-intel_dp_init(struct drm_device *dev,
-	      i915_reg_t output_reg, enum port port)
+bool intel_dp_init(struct drm_device *dev,
+		   i915_reg_t output_reg,
+		   enum port port)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_digital_port *intel_dig_port;
@@ -5935,7 +5935,7 @@ intel_dp_init(struct drm_device *dev,
 
 	intel_dig_port = kzalloc(sizeof(*intel_dig_port), GFP_KERNEL);
 	if (!intel_dig_port)
-		return;
+		return false;
 
 	intel_connector = intel_connector_alloc();
 	if (!intel_connector)
@@ -5992,7 +5992,7 @@ intel_dp_init(struct drm_device *dev,
 	if (!intel_dp_init_connector(intel_dig_port, intel_connector))
 		goto err_init_connector;
 
-	return;
+	return true;
 
 err_init_connector:
 	drm_encoder_cleanup(encoder);
@@ -6000,8 +6000,7 @@ err_encoder_init:
 	kfree(intel_connector);
 err_connector_alloc:
 	kfree(intel_dig_port);
-
-	return;
+	return false;
 }
 
 void intel_dp_mst_suspend(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c
index 0b8eefc2acc5..60fb39cd220b 100644
--- a/drivers/gpu/drm/i915/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/intel_dp_link_training.c
@@ -85,8 +85,7 @@ static bool
 intel_dp_reset_link_train(struct intel_dp *intel_dp,
 			uint8_t dp_train_pat)
 {
-	if (!intel_dp->train_set_valid)
-		memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set));
+	memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set));
 	intel_dp_set_signal_levels(intel_dp);
 	return intel_dp_set_link_train(intel_dp, dp_train_pat);
 }
@@ -161,23 +160,6 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp)
 			break;
 		}
 
-		/*
-		 * if we used previously trained voltage and pre-emphasis values
-		 * and we don't get clock recovery, reset link training values
-		 */
-		if (intel_dp->train_set_valid) {
-			DRM_DEBUG_KMS("clock recovery not ok, reset");
-			/* clear the flag as we are not reusing train set */
-			intel_dp->train_set_valid = false;
-			if (!intel_dp_reset_link_train(intel_dp,
-						       DP_TRAINING_PATTERN_1 |
-						       DP_LINK_SCRAMBLING_DISABLE)) {
-				DRM_ERROR("failed to enable link training\n");
-				return;
-			}
-			continue;
-		}
-
 		/* Check to see if we've tried the max voltage */
 		for (i = 0; i < intel_dp->lane_count; i++)
 			if ((intel_dp->train_set[i] & DP_TRAIN_MAX_SWING_REACHED) == 0)
@@ -284,7 +266,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
 		/* Make sure clock is still ok */
 		if (!drm_dp_clock_recovery_ok(link_status,
 					      intel_dp->lane_count)) {
-			intel_dp->train_set_valid = false;
 			intel_dp_link_training_clock_recovery(intel_dp);
 			intel_dp_set_link_train(intel_dp,
 						training_pattern |
@@ -301,7 +282,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
 
 		/* Try 5 times, then try clock recovery if that fails */
 		if (tries > 5) {
-			intel_dp->train_set_valid = false;
 			intel_dp_link_training_clock_recovery(intel_dp);
 			intel_dp_set_link_train(intel_dp,
 						training_pattern |
@@ -322,10 +302,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
 
 	intel_dp_set_idle_link_train(intel_dp);
 
-	if (channel_eq) {
-		intel_dp->train_set_valid = true;
+	if (channel_eq)
 		DRM_DEBUG_KMS("Channel EQ done. DP Training successful\n");
-	}
 }
 
 void intel_dp_stop_link_train(struct intel_dp *intel_dp)
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 3ac705936b04..baf6f5584cbd 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -366,6 +366,9 @@ ibx_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 					     DPLL_ID_PCH_PLL_B);
 	}
 
+	if (!pll)
+		return NULL;
+
 	/* reference the pll */
 	intel_reference_shared_dpll(pll, crtc_state);
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index a28b4aac1e02..f7f0f01814f6 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -863,8 +863,6 @@ struct intel_dp {
 	/* This is called before a link training is starterd */
 	void (*prepare_link_retrain)(struct intel_dp *intel_dp);
 
-	bool train_set_valid;
-
 	/* Displayport compliance testing */
 	unsigned long compliance_test_type;
 	unsigned long compliance_test_data;
@@ -1284,7 +1282,7 @@ void intel_csr_ucode_suspend(struct drm_i915_private *);
 void intel_csr_ucode_resume(struct drm_i915_private *);
 
 /* intel_dp.c */
-void intel_dp_init(struct drm_device *dev, i915_reg_t output_reg, enum port port);
+bool intel_dp_init(struct drm_device *dev, i915_reg_t output_reg, enum port port);
 bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 			     struct intel_connector *intel_connector);
 void intel_dp_set_link_params(struct intel_dp *intel_dp,
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index 366ad6c67ce4..4756ef639648 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -1545,6 +1545,9 @@ void intel_dsi_init(struct drm_device *dev)
 		goto err;
 	}
 
+	connector->display_info.width_mm = fixed_mode->width_mm;
+	connector->display_info.height_mm = fixed_mode->height_mm;
+
 	intel_panel_init(&intel_connector->panel, fixed_mode, NULL);
 
 	intel_dsi_add_properties(intel_connector);
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index d5a7cfec589b..647127f3aaff 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -824,8 +824,7 @@ static bool intel_fbc_can_choose(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
 	struct intel_fbc *fbc = &dev_priv->fbc;
-	bool enable_by_default = IS_HASWELL(dev_priv) ||
-				 IS_BROADWELL(dev_priv);
+	bool enable_by_default = IS_BROADWELL(dev_priv);
 
 	if (intel_vgpu_active(dev_priv->dev)) {
 		fbc->no_fbc_reason = "VGPU is active";
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 2c3bd9c2573e..a8844702d11b 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -2142,6 +2142,9 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	enum port port = intel_dig_port->port;
 	uint8_t alternate_ddc_pin;
 
+	DRM_DEBUG_KMS("Adding HDMI connector on port %c\n",
+		      port_name(port));
+
 	if (WARN(intel_dig_port->max_lanes < 4,
 		 "Not enough lanes (%d) for HDMI on port %c\n",
 		 intel_dig_port->max_lanes, port_name(port)))
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index bc53c0dd34d0..96281e628d2a 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -1082,6 +1082,8 @@ void intel_lvds_init(struct drm_device *dev)
 		fixed_mode = drm_mode_duplicate(dev, dev_priv->vbt.lfp_lvds_vbt_mode);
 		if (fixed_mode) {
 			fixed_mode->type |= DRM_MODE_TYPE_PREFERRED;
+			connector->display_info.width_mm = fixed_mode->width_mm;
+			connector->display_info.height_mm = fixed_mode->height_mm;
 			goto out;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h
index c15051de8023..44fb0b35eed3 100644
--- a/drivers/gpu/drm/i915/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/intel_vbt_defs.h
@@ -403,9 +403,10 @@ struct lvds_dvo_timing {
 	u8 vsync_off:4;
 	u8 rsvd0:6;
 	u8 hsync_off_hi:2;
-	u8 h_image;
-	u8 v_image;
-	u8 max_hv;
+	u8 himage_lo;
+	u8 vimage_lo;
+	u8 vimage_hi:4;
+	u8 himage_hi:4;
 	u8 h_border;
 	u8 v_border;
 	u8 rsvd1:3;
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 1f14b602882b..82656654fb21 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -97,8 +97,8 @@ static struct imx_drm_crtc *imx_drm_find_crtc(struct drm_crtc *crtc)
 	return NULL;
 }
 
-int imx_drm_set_bus_format_pins(struct drm_encoder *encoder, u32 bus_format,
-		int hsync_pin, int vsync_pin)
+int imx_drm_set_bus_config(struct drm_encoder *encoder, u32 bus_format,
+		int hsync_pin, int vsync_pin, u32 bus_flags)
 {
 	struct imx_drm_crtc_helper_funcs *helper;
 	struct imx_drm_crtc *imx_crtc;
@@ -110,14 +110,17 @@ int imx_drm_set_bus_format_pins(struct drm_encoder *encoder, u32 bus_format,
 	helper = &imx_crtc->imx_drm_helper_funcs;
 	if (helper->set_interface_pix_fmt)
 		return helper->set_interface_pix_fmt(encoder->crtc,
-					bus_format, hsync_pin, vsync_pin);
+					bus_format, hsync_pin, vsync_pin,
+					bus_flags);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(imx_drm_set_bus_format_pins);
+EXPORT_SYMBOL_GPL(imx_drm_set_bus_config);
 
 int imx_drm_set_bus_format(struct drm_encoder *encoder, u32 bus_format)
 {
-	return imx_drm_set_bus_format_pins(encoder, bus_format, 2, 3);
+	return imx_drm_set_bus_config(encoder, bus_format, 2, 3,
+				      DRM_BUS_FLAG_DE_HIGH |
+				      DRM_BUS_FLAG_PIXDATA_NEGEDGE);
 }
 EXPORT_SYMBOL_GPL(imx_drm_set_bus_format);
 
diff --git a/drivers/gpu/drm/imx/imx-drm.h b/drivers/gpu/drm/imx/imx-drm.h
index b0241b9d1334..74320a1723b7 100644
--- a/drivers/gpu/drm/imx/imx-drm.h
+++ b/drivers/gpu/drm/imx/imx-drm.h
@@ -19,7 +19,8 @@ struct imx_drm_crtc_helper_funcs {
 	int (*enable_vblank)(struct drm_crtc *crtc);
 	void (*disable_vblank)(struct drm_crtc *crtc);
 	int (*set_interface_pix_fmt)(struct drm_crtc *crtc,
-			u32 bus_format, int hsync_pin, int vsync_pin);
+			u32 bus_format, int hsync_pin, int vsync_pin,
+			u32 bus_flags);
 	const struct drm_crtc_helper_funcs *crtc_helper_funcs;
 	const struct drm_crtc_funcs *crtc_funcs;
 };
@@ -41,8 +42,8 @@ void imx_drm_mode_config_init(struct drm_device *drm);
 
 struct drm_gem_cma_object *imx_drm_fb_get_obj(struct drm_framebuffer *fb);
 
-int imx_drm_set_bus_format_pins(struct drm_encoder *encoder,
-		u32 bus_format, int hsync_pin, int vsync_pin);
+int imx_drm_set_bus_config(struct drm_encoder *encoder, u32 bus_format,
+		int hsync_pin, int vsync_pin, u32 bus_flags);
 int imx_drm_set_bus_format(struct drm_encoder *encoder,
 		u32 bus_format);
 
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index a58eee59550a..beff793bb717 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -25,6 +25,7 @@
 #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
 #include <linux/of_device.h>
 #include <linux/of_graph.h>
+#include <video/of_display_timing.h>
 #include <video/of_videomode.h>
 #include <linux/regmap.h>
 #include <linux/videodev2.h>
@@ -59,6 +60,7 @@ struct imx_ldb_channel {
 	struct drm_encoder encoder;
 	struct drm_panel *panel;
 	struct device_node *child;
+	struct i2c_adapter *ddc;
 	int chno;
 	void *edid;
 	int edid_len;
@@ -107,6 +109,9 @@ static int imx_ldb_connector_get_modes(struct drm_connector *connector)
 			return num_modes;
 	}
 
+	if (!imx_ldb_ch->edid && imx_ldb_ch->ddc)
+		imx_ldb_ch->edid = drm_get_edid(connector, imx_ldb_ch->ddc);
+
 	if (imx_ldb_ch->edid) {
 		drm_mode_connector_update_edid_property(connector,
 							imx_ldb_ch->edid);
@@ -553,7 +558,8 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 
 	for_each_child_of_node(np, child) {
 		struct imx_ldb_channel *channel;
-		struct device_node *port;
+		struct device_node *ddc_node;
+		struct device_node *ep;
 
 		ret = of_property_read_u32(child, "reg", &i);
 		if (ret || i < 0 || i > 1)
@@ -576,33 +582,54 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 		 * The output port is port@4 with an external 4-port mux or
 		 * port@2 with the internal 2-port mux.
 		 */
-		port = of_graph_get_port_by_id(child, imx_ldb->lvds_mux ? 4 : 2);
-		if (port) {
-			struct device_node *endpoint, *remote;
-
-			endpoint = of_get_child_by_name(port, "endpoint");
-			if (endpoint) {
-				remote = of_graph_get_remote_port_parent(endpoint);
-				if (remote)
-					channel->panel = of_drm_find_panel(remote);
-				else
-					return -EPROBE_DEFER;
-				if (!channel->panel) {
-					dev_err(dev, "panel not found: %s\n",
-						remote->full_name);
-					return -EPROBE_DEFER;
-				}
+		ep = of_graph_get_endpoint_by_regs(child,
+						   imx_ldb->lvds_mux ? 4 : 2,
+						   -1);
+		if (ep) {
+			struct device_node *remote;
+
+			remote = of_graph_get_remote_port_parent(ep);
+			of_node_put(ep);
+			if (remote)
+				channel->panel = of_drm_find_panel(remote);
+			else
+				return -EPROBE_DEFER;
+			of_node_put(remote);
+			if (!channel->panel) {
+				dev_err(dev, "panel not found: %s\n",
+					remote->full_name);
+				return -EPROBE_DEFER;
 			}
 		}
 
-		edidp = of_get_property(child, "edid", &channel->edid_len);
-		if (edidp) {
-			channel->edid = kmemdup(edidp, channel->edid_len,
-						GFP_KERNEL);
-		} else if (!channel->panel) {
-			ret = of_get_drm_display_mode(child, &channel->mode, 0);
-			if (!ret)
-				channel->mode_valid = 1;
+		ddc_node = of_parse_phandle(child, "ddc-i2c-bus", 0);
+		if (ddc_node) {
+			channel->ddc = of_find_i2c_adapter_by_node(ddc_node);
+			of_node_put(ddc_node);
+			if (!channel->ddc) {
+				dev_warn(dev, "failed to get ddc i2c adapter\n");
+				return -EPROBE_DEFER;
+			}
+		}
+
+		if (!channel->ddc) {
+			/* if no DDC available, fallback to hardcoded EDID */
+			dev_dbg(dev, "no ddc available\n");
+
+			edidp = of_get_property(child, "edid",
+						&channel->edid_len);
+			if (edidp) {
+				channel->edid = kmemdup(edidp,
+							channel->edid_len,
+							GFP_KERNEL);
+			} else if (!channel->panel) {
+				/* fallback to display-timings node */
+				ret = of_get_drm_display_mode(child,
+							      &channel->mode,
+							      OF_USE_NATIVE_MODE);
+				if (!ret)
+					channel->mode_valid = 1;
+			}
 		}
 
 		channel->bus_format = of_get_bus_format(dev, child);
@@ -647,6 +674,7 @@ static void imx_ldb_unbind(struct device *dev, struct device *master,
 		channel->encoder.funcs->destroy(&channel->encoder);
 
 		kfree(channel->edid);
+		i2c_put_adapter(channel->ddc);
 	}
 }
 
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index ae7a9fb3b8a2..baf788121287 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -294,8 +294,10 @@ static void imx_tve_encoder_prepare(struct drm_encoder *encoder)
 
 	switch (tve->mode) {
 	case TVE_MODE_VGA:
-		imx_drm_set_bus_format_pins(encoder, MEDIA_BUS_FMT_GBR888_1X24,
-					    tve->hsync_pin, tve->vsync_pin);
+		imx_drm_set_bus_config(encoder, MEDIA_BUS_FMT_GBR888_1X24,
+				       tve->hsync_pin, tve->vsync_pin,
+				       DRM_BUS_FLAG_DE_HIGH |
+				       DRM_BUS_FLAG_PIXDATA_NEGEDGE);
 		break;
 	case TVE_MODE_TVOUT:
 		imx_drm_set_bus_format(encoder, MEDIA_BUS_FMT_YUV8_1X24);
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index b2c30b8d9816..fc040417e1e8 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -66,6 +66,7 @@ struct ipu_crtc {
 	struct ipu_flip_work	*flip_work;
 	int			irq;
 	u32			bus_format;
+	u32			bus_flags;
 	int			di_hsync_pin;
 	int			di_vsync_pin;
 };
@@ -271,8 +272,10 @@ static int ipu_crtc_mode_set(struct drm_crtc *crtc,
 	else
 		sig_cfg.clkflags = 0;
 
-	sig_cfg.enable_pol = 1;
-	sig_cfg.clk_pol = 0;
+	sig_cfg.enable_pol = !(ipu_crtc->bus_flags & DRM_BUS_FLAG_DE_LOW);
+	/* Default to driving pixel data on negative clock edges */
+	sig_cfg.clk_pol = !!(ipu_crtc->bus_flags &
+			     DRM_BUS_FLAG_PIXDATA_POSEDGE);
 	sig_cfg.bus_format = ipu_crtc->bus_format;
 	sig_cfg.v_to_h_sync = 0;
 	sig_cfg.hsync_pin = ipu_crtc->di_hsync_pin;
@@ -396,11 +399,12 @@ static void ipu_disable_vblank(struct drm_crtc *crtc)
 }
 
 static int ipu_set_interface_pix_fmt(struct drm_crtc *crtc,
-		u32 bus_format, int hsync_pin, int vsync_pin)
+		u32 bus_format, int hsync_pin, int vsync_pin, u32 bus_flags)
 {
 	struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
 
 	ipu_crtc->bus_format = bus_format;
+	ipu_crtc->bus_flags = bus_flags;
 	ipu_crtc->di_hsync_pin = hsync_pin;
 	ipu_crtc->di_vsync_pin = vsync_pin;
 
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index 681ec6eb77d9..a4bb44118d33 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -38,6 +38,8 @@ static const uint32_t ipu_plane_formats[] = {
 	DRM_FORMAT_RGBX8888,
 	DRM_FORMAT_BGRA8888,
 	DRM_FORMAT_BGRA8888,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_VYUY,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_YUV420,
@@ -428,7 +430,6 @@ static int ipu_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	if (crtc != plane->crtc)
 		dev_dbg(plane->dev->dev, "crtc change: %p -> %p\n",
 				plane->crtc, crtc);
-	plane->crtc = crtc;
 
 	if (!ipu_plane->enabled)
 		ipu_plane_enable(ipu_plane);
@@ -461,7 +462,7 @@ static void ipu_plane_destroy(struct drm_plane *plane)
 	kfree(ipu_plane);
 }
 
-static struct drm_plane_funcs ipu_plane_funcs = {
+static const struct drm_plane_funcs ipu_plane_funcs = {
 	.update_plane	= ipu_update_plane,
 	.disable_plane	= ipu_disable_plane,
 	.destroy	= ipu_plane_destroy,
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 363e2c7741e2..2d1fd02cd3d6 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -35,7 +35,6 @@ struct imx_parallel_display {
 	void *edid;
 	int edid_len;
 	u32 bus_format;
-	int mode_valid;
 	struct drm_display_mode mode;
 	struct drm_panel *panel;
 };
@@ -68,17 +67,6 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
 		num_modes = drm_add_edid_modes(connector, imxpd->edid);
 	}
 
-	if (imxpd->mode_valid) {
-		struct drm_display_mode *mode = drm_mode_create(connector->dev);
-
-		if (!mode)
-			return -EINVAL;
-		drm_mode_copy(mode, &imxpd->mode);
-		mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED,
-		drm_mode_probed_add(connector, mode);
-		num_modes++;
-	}
-
 	if (np) {
 		struct drm_display_mode *mode = drm_mode_create(connector->dev);
 
@@ -115,8 +103,8 @@ static void imx_pd_encoder_dpms(struct drm_encoder *encoder, int mode)
 static void imx_pd_encoder_prepare(struct drm_encoder *encoder)
 {
 	struct imx_parallel_display *imxpd = enc_to_imxpd(encoder);
-
-	imx_drm_set_bus_format(encoder, imxpd->bus_format);
+	imx_drm_set_bus_config(encoder, imxpd->bus_format, 2, 3,
+			       imxpd->connector.display_info.bus_flags);
 }
 
 static void imx_pd_encoder_commit(struct drm_encoder *encoder)
@@ -203,7 +191,7 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 {
 	struct drm_device *drm = data;
 	struct device_node *np = dev->of_node;
-	struct device_node *port;
+	struct device_node *ep;
 	const u8 *edidp;
 	struct imx_parallel_display *imxpd;
 	int ret;
@@ -230,18 +218,18 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 	}
 
 	/* port@1 is the output port */
-	port = of_graph_get_port_by_id(np, 1);
-	if (port) {
-		struct device_node *endpoint, *remote;
-
-		endpoint = of_get_child_by_name(port, "endpoint");
-		if (endpoint) {
-			remote = of_graph_get_remote_port_parent(endpoint);
-			if (remote)
-				imxpd->panel = of_drm_find_panel(remote);
-			if (!imxpd->panel)
-				return -EPROBE_DEFER;
+	ep = of_graph_get_endpoint_by_regs(np, 1, -1);
+	if (ep) {
+		struct device_node *remote;
+
+		remote = of_graph_get_remote_port_parent(ep);
+		of_node_put(ep);
+		if (remote) {
+			imxpd->panel = of_drm_find_panel(remote);
+			of_node_put(remote);
 		}
+		if (!imxpd->panel)
+			return -EPROBE_DEFER;
 	}
 
 	imxpd->dev = dev;
diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
index d05ca7901315..0186e500d2a5 100644
--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
@@ -432,11 +432,6 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi,
 	unsigned long pll_rate;
 	unsigned int factor;
 
-	if (!dpi) {
-		dev_err(dpi->dev, "invalid argument\n");
-		return -EINVAL;
-	}
-
 	pix_rate = 1000UL * mode->clock;
 	if (mode->clock <= 74000)
 		factor = 8 * 3;
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 2d808e59fefd..769559124562 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -695,10 +695,8 @@ static void mtk_dsi_destroy_conn_enc(struct mtk_dsi *dsi)
 {
 	drm_encoder_cleanup(&dsi->encoder);
 	/* Skip connector cleanup if creation was delegated to the bridge */
-	if (dsi->conn.dev) {
-		drm_connector_unregister(&dsi->conn);
+	if (dsi->conn.dev)
 		drm_connector_cleanup(&dsi->conn);
-	}
 }
 
 static void mtk_dsi_ddp_start(struct mtk_ddp_comp *comp)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 14e64e08909e..d347dca17267 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -182,7 +182,7 @@ static int mga_g200se_set_plls(struct mga_device *mdev, long clock)
 			}
 		}
 
-		fvv = pllreffreq * testn / testm;
+		fvv = pllreffreq * (n + 1) / (m + 1);
 		fvv = (fvv - 800000) / 50000;
 
 		if (fvv > 15)
@@ -202,6 +202,14 @@ static int mga_g200se_set_plls(struct mga_device *mdev, long clock)
 	WREG_DAC(MGA1064_PIX_PLLC_M, m);
 	WREG_DAC(MGA1064_PIX_PLLC_N, n);
 	WREG_DAC(MGA1064_PIX_PLLC_P, p);
+
+	if (mdev->unique_rev_id >= 0x04) {
+		WREG_DAC(0x1a, 0x09);
+		msleep(20);
+		WREG_DAC(0x1a, 0x01);
+
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index fbe304ee6c80..2aec27dbb5bb 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -408,7 +408,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	}
 
 	adreno_gpu->memptrs = msm_gem_vaddr(adreno_gpu->memptrs_bo);
-	if (!adreno_gpu->memptrs) {
+	if (IS_ERR(adreno_gpu->memptrs)) {
 		dev_err(drm->dev, "could not vmap memptrs\n");
 		return -ENOMEM;
 	}
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index d9759bf3482e..c6cf837c5193 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -159,6 +159,10 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
 	dev->mode_config.fb_base = paddr;
 
 	fbi->screen_base = msm_gem_vaddr_locked(fbdev->bo);
+	if (IS_ERR(fbi->screen_base)) {
+		ret = PTR_ERR(fbi->screen_base);
+		goto fail_unlock;
+	}
 	fbi->screen_size = fbdev->bo->size;
 	fbi->fix.smem_start = paddr;
 	fbi->fix.smem_len = fbdev->bo->size;
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 7daf4054dd2b..69836f5685b1 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -398,6 +398,8 @@ void *msm_gem_vaddr_locked(struct drm_gem_object *obj)
 			return ERR_CAST(pages);
 		msm_obj->vaddr = vmap(pages, obj->size >> PAGE_SHIFT,
 				VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+		if (msm_obj->vaddr == NULL)
+			return ERR_PTR(-ENOMEM);
 	}
 	return msm_obj->vaddr;
 }
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index b89ca5174863..eb4bb8b2f3a5 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -40,12 +40,14 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 
 	submit->dev = dev;
 	submit->gpu = gpu;
+	submit->fence = NULL;
 	submit->pid = get_pid(task_pid(current));
 
 	/* initially, until copy_from_user() and bo lookup succeeds: */
 	submit->nr_bos = 0;
 	submit->nr_cmds = 0;
 
+	INIT_LIST_HEAD(&submit->node);
 	INIT_LIST_HEAD(&submit->bo_list);
 	ww_acquire_init(&submit->ticket, &reservation_ww_class);
 
@@ -75,6 +77,11 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 		void __user *userptr =
 			u64_to_user_ptr(args->bos + (i * sizeof(submit_bo)));
 
+		/* make sure we don't have garbage flags, in case we hit
+		 * error path before flags is initialized:
+		 */
+		submit->bos[i].flags = 0;
+
 		ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
 		if (ret) {
 			ret = -EFAULT;
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index b48f73ac6389..0857710c2ff2 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -312,6 +312,9 @@ void msm_rd_dump_submit(struct msm_gem_submit *submit)
 		struct msm_gem_object *obj = submit->bos[idx].obj;
 		const char *buf = msm_gem_vaddr_locked(&obj->base);
 
+		if (IS_ERR(buf))
+			continue;
+
 		buf += iova - submit->bos[idx].iova;
 
 		rd_write_section(rd, RD_GPUADDR,
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 1f14b908b221..42f5359cf988 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -40,6 +40,10 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int size)
 	}
 
 	ring->start = msm_gem_vaddr_locked(ring->bo);
+	if (IS_ERR(ring->start)) {
+		ret = PTR_ERR(ring->start);
+		goto fail;
+	}
 	ring->end   = ring->start + (size / 4);
 	ring->cur   = ring->start;
 
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
index c612dc1f1eb4..126a85cc81bc 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
@@ -16,9 +16,9 @@ enum nvkm_devidx {
 	NVKM_SUBDEV_MC,
 	NVKM_SUBDEV_BUS,
 	NVKM_SUBDEV_TIMER,
+	NVKM_SUBDEV_INSTMEM,
 	NVKM_SUBDEV_FB,
 	NVKM_SUBDEV_LTC,
-	NVKM_SUBDEV_INSTMEM,
 	NVKM_SUBDEV_MMU,
 	NVKM_SUBDEV_BAR,
 	NVKM_SUBDEV_PMU,
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/disp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/disp.h
index db10c11f0595..c5a6ebd5a478 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/disp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/disp.h
@@ -25,7 +25,8 @@ u16 nvbios_outp_match(struct nvkm_bios *, u16 type, u16 mask,
 		      u8 *ver, u8 *hdr, u8 *cnt, u8 *len, struct nvbios_outp *);
 
 struct nvbios_ocfg {
-	u16 match;
+	u8  proto;
+	u8  flags;
 	u16 clkcmp[2];
 };
 
@@ -33,7 +34,7 @@ u16 nvbios_ocfg_entry(struct nvkm_bios *, u16 outp, u8 idx,
 		      u8 *ver, u8 *hdr, u8 *cnt, u8 *len);
 u16 nvbios_ocfg_parse(struct nvkm_bios *, u16 outp, u8 idx,
 		      u8 *ver, u8 *hdr, u8 *cnt, u8 *len, struct nvbios_ocfg *);
-u16 nvbios_ocfg_match(struct nvkm_bios *, u16 outp, u16 type,
+u16 nvbios_ocfg_match(struct nvkm_bios *, u16 outp, u8 proto, u8 flags,
 		      u8 *ver, u8 *hdr, u8 *cnt, u8 *len, struct nvbios_ocfg *);
 u16 nvbios_oclk_match(struct nvkm_bios *, u16 cmp, u32 khz);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 57aaf98a26f9..d1f248fd3506 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -552,6 +552,8 @@ nouveau_fbcon_init(struct drm_device *dev)
 	if (ret)
 		goto fini;
 
+	if (fbcon->helper.fbdev)
+		fbcon->helper.fbdev->pixmap.buf_align = 4;
 	return 0;
 
 fini:
diff --git a/drivers/gpu/drm/nouveau/nv04_fbcon.c b/drivers/gpu/drm/nouveau/nv04_fbcon.c
index 0f3e4bb411cc..7d9248b8c664 100644
--- a/drivers/gpu/drm/nouveau/nv04_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv04_fbcon.c
@@ -82,7 +82,6 @@ nv04_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	uint32_t fg;
 	uint32_t bg;
 	uint32_t dsize;
-	uint32_t width;
 	uint32_t *data = (uint32_t *)image->data;
 	int ret;
 
@@ -93,9 +92,6 @@ nv04_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	if (ret)
 		return ret;
 
-	width = ALIGN(image->width, 8);
-	dsize = ALIGN(width * image->height, 32) >> 5;
-
 	if (info->fix.visual == FB_VISUAL_TRUECOLOR ||
 	    info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
 		fg = ((uint32_t *) info->pseudo_palette)[image->fg_color];
@@ -111,10 +107,11 @@ nv04_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 			 ((image->dx + image->width) & 0xffff));
 	OUT_RING(chan, bg);
 	OUT_RING(chan, fg);
-	OUT_RING(chan, (image->height << 16) | width);
+	OUT_RING(chan, (image->height << 16) | image->width);
 	OUT_RING(chan, (image->height << 16) | image->width);
 	OUT_RING(chan, (image->dy << 16) | (image->dx & 0xffff));
 
+	dsize = ALIGN(image->width * image->height, 32) >> 5;
 	while (dsize) {
 		int iter_len = dsize > 128 ? 128 : dsize;
 
diff --git a/drivers/gpu/drm/nouveau/nv50_fbcon.c b/drivers/gpu/drm/nouveau/nv50_fbcon.c
index 33d9ee0fac40..1aeb698e9707 100644
--- a/drivers/gpu/drm/nouveau/nv50_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv50_fbcon.c
@@ -95,7 +95,7 @@ nv50_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	struct nouveau_fbdev *nfbdev = info->par;
 	struct nouveau_drm *drm = nouveau_drm(nfbdev->dev);
 	struct nouveau_channel *chan = drm->channel;
-	uint32_t width, dwords, *data = (uint32_t *)image->data;
+	uint32_t dwords, *data = (uint32_t *)image->data;
 	uint32_t mask = ~(~0 >> (32 - info->var.bits_per_pixel));
 	uint32_t *palette = info->pseudo_palette;
 	int ret;
@@ -107,9 +107,6 @@ nv50_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	if (ret)
 		return ret;
 
-	width = ALIGN(image->width, 32);
-	dwords = (width * image->height) >> 5;
-
 	BEGIN_NV04(chan, NvSub2D, 0x0814, 2);
 	if (info->fix.visual == FB_VISUAL_TRUECOLOR ||
 	    info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
@@ -128,6 +125,7 @@ nv50_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	OUT_RING(chan, 0);
 	OUT_RING(chan, image->dy);
 
+	dwords = ALIGN(image->width * image->height, 32) >> 5;
 	while (dwords) {
 		int push = dwords > 2047 ? 2047 : dwords;
 
diff --git a/drivers/gpu/drm/nouveau/nvc0_fbcon.c b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
index a0913359ac05..839f4c8c1805 100644
--- a/drivers/gpu/drm/nouveau/nvc0_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
@@ -95,7 +95,7 @@ nvc0_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	struct nouveau_fbdev *nfbdev = info->par;
 	struct nouveau_drm *drm = nouveau_drm(nfbdev->dev);
 	struct nouveau_channel *chan = drm->channel;
-	uint32_t width, dwords, *data = (uint32_t *)image->data;
+	uint32_t dwords, *data = (uint32_t *)image->data;
 	uint32_t mask = ~(~0 >> (32 - info->var.bits_per_pixel));
 	uint32_t *palette = info->pseudo_palette;
 	int ret;
@@ -107,9 +107,6 @@ nvc0_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	if (ret)
 		return ret;
 
-	width = ALIGN(image->width, 32);
-	dwords = (width * image->height) >> 5;
-
 	BEGIN_NVC0(chan, NvSub2D, 0x0814, 2);
 	if (info->fix.visual == FB_VISUAL_TRUECOLOR ||
 	    info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
@@ -128,6 +125,7 @@ nvc0_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	OUT_RING  (chan, 0);
 	OUT_RING  (chan, image->dy);
 
+	dwords = ALIGN(image->width * image->height, 32) >> 5;
 	while (dwords) {
 		int push = dwords > 2047 ? 2047 : dwords;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
index 18fab3973ce5..62ad0300cfa5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
@@ -1614,7 +1614,7 @@ nvkm_device_pci_func = {
 	.fini = nvkm_device_pci_fini,
 	.resource_addr = nvkm_device_pci_resource_addr,
 	.resource_size = nvkm_device_pci_resource_size,
-	.cpu_coherent = !IS_ENABLED(CONFIG_ARM) && !IS_ENABLED(CONFIG_ARM64),
+	.cpu_coherent = !IS_ENABLED(CONFIG_ARM),
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
index a74c5dd27dc0..e2a64ed14b22 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
@@ -18,6 +18,7 @@ nvkm-y += nvkm/engine/disp/piornv50.o
 nvkm-y += nvkm/engine/disp/sornv50.o
 nvkm-y += nvkm/engine/disp/sorg94.o
 nvkm-y += nvkm/engine/disp/sorgf119.o
+nvkm-y += nvkm/engine/disp/sorgm107.o
 nvkm-y += nvkm/engine/disp/sorgm200.o
 nvkm-y += nvkm/engine/disp/dport.o
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
index f0314664349c..5dd34382f55a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
@@ -76,6 +76,7 @@ exec_lookup(struct nv50_disp *disp, int head, int or, u32 ctrl,
 	mask |= 0x0001 << or;
 	mask |= 0x0100 << head;
 
+
 	list_for_each_entry(outp, &disp->base.outp, head) {
 		if ((outp->info.hasht & 0xff) == type &&
 		    (outp->info.hashm & mask) == mask) {
@@ -155,25 +156,21 @@ exec_clkcmp(struct nv50_disp *disp, int head, int id, u32 pclk, u32 *conf)
 	if (!outp)
 		return NULL;
 
+	*conf = (ctrl & 0x00000f00) >> 8;
 	switch (outp->info.type) {
 	case DCB_OUTPUT_TMDS:
-		*conf = (ctrl & 0x00000f00) >> 8;
 		if (*conf == 5)
 			*conf |= 0x0100;
 		break;
 	case DCB_OUTPUT_LVDS:
-		*conf = disp->sor.lvdsconf;
-		break;
-	case DCB_OUTPUT_DP:
-		*conf = (ctrl & 0x00000f00) >> 8;
+		*conf |= disp->sor.lvdsconf;
 		break;
-	case DCB_OUTPUT_ANALOG:
 	default:
-		*conf = 0x00ff;
 		break;
 	}
 
-	data = nvbios_ocfg_match(bios, data, *conf, &ver, &hdr, &cnt, &len, &info2);
+	data = nvbios_ocfg_match(bios, data, *conf & 0xff, *conf >> 8,
+				 &ver, &hdr, &cnt, &len, &info2);
 	if (data && id < 0xff) {
 		data = nvbios_oclk_match(bios, info2.clkcmp[id], pclk);
 		if (data) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
index b6944142d616..f4b9cf8574be 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
@@ -36,7 +36,7 @@ gm107_disp = {
 	.outp.internal.crt = nv50_dac_output_new,
 	.outp.internal.tmds = nv50_sor_output_new,
 	.outp.internal.lvds = nv50_sor_output_new,
-	.outp.internal.dp = gf119_sor_dp_new,
+	.outp.internal.dp = gm107_sor_dp_new,
 	.dac.nr = 3,
 	.dac.power = nv50_dac_power,
 	.dac.sense = nv50_dac_sense,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
index 4226d2153b9c..fcb1b0c46d64 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
@@ -387,22 +387,17 @@ exec_clkcmp(struct nv50_disp *disp, int head, int id, u32 pclk, u32 *conf)
 	if (!outp)
 		return NULL;
 
+	*conf = (ctrl & 0x00000f00) >> 8;
 	if (outp->info.location == 0) {
 		switch (outp->info.type) {
 		case DCB_OUTPUT_TMDS:
-			*conf = (ctrl & 0x00000f00) >> 8;
 			if (*conf == 5)
 				*conf |= 0x0100;
 			break;
 		case DCB_OUTPUT_LVDS:
-			*conf = disp->sor.lvdsconf;
+			*conf |= disp->sor.lvdsconf;
 			break;
-		case DCB_OUTPUT_DP:
-			*conf = (ctrl & 0x00000f00) >> 8;
-			break;
-		case DCB_OUTPUT_ANALOG:
 		default:
-			*conf = 0x00ff;
 			break;
 		}
 	} else {
@@ -410,7 +405,8 @@ exec_clkcmp(struct nv50_disp *disp, int head, int id, u32 pclk, u32 *conf)
 		pclk = pclk / 2;
 	}
 
-	data = nvbios_ocfg_match(bios, data, *conf, &ver, &hdr, &cnt, &len, &info2);
+	data = nvbios_ocfg_match(bios, data, *conf & 0xff, *conf >> 8,
+				 &ver, &hdr, &cnt, &len, &info2);
 	if (data && id < 0xff) {
 		data = nvbios_oclk_match(bios, info2.clkcmp[id], pclk);
 		if (data) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outpdp.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outpdp.h
index e9067ba4e179..4e983f6d7032 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outpdp.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outpdp.h
@@ -62,7 +62,12 @@ int g94_sor_dp_lnk_pwr(struct nvkm_output_dp *, int);
 int gf119_sor_dp_new(struct nvkm_disp *, int, struct dcb_output *,
 		     struct nvkm_output **);
 int gf119_sor_dp_lnk_ctl(struct nvkm_output_dp *, int, int, bool);
+int gf119_sor_dp_drv_ctl(struct nvkm_output_dp *, int, int, int, int);
 
-int  gm200_sor_dp_new(struct nvkm_disp *, int, struct dcb_output *,
-		      struct nvkm_output **);
+int gm107_sor_dp_new(struct nvkm_disp *, int, struct dcb_output *,
+		     struct nvkm_output **);
+int gm107_sor_dp_pattern(struct nvkm_output_dp *, int);
+
+int gm200_sor_dp_new(struct nvkm_disp *, int, struct dcb_output *,
+		     struct nvkm_output **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
index b4b41b135643..22706c0a54b5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
@@ -40,8 +40,7 @@ static int
 gf119_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
 {
 	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
-	const u32 loff = gf119_sor_loff(outp);
-	nvkm_mask(device, 0x61c110 + loff, 0x0f0f0f0f, 0x01010101 * pattern);
+	nvkm_mask(device, 0x61c110, 0x0f0f0f0f, 0x01010101 * pattern);
 	return 0;
 }
 
@@ -64,7 +63,7 @@ gf119_sor_dp_lnk_ctl(struct nvkm_output_dp *outp, int nr, int bw, bool ef)
 	return 0;
 }
 
-static int
+int
 gf119_sor_dp_drv_ctl(struct nvkm_output_dp *outp,
 		     int ln, int vs, int pe, int pc)
 {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm107.c
new file mode 100644
index 000000000000..37790b2617c5
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm107.c
@@ -0,0 +1,53 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <[email protected]>
+ */
+#include "nv50.h"
+#include "outpdp.h"
+
+int
+gm107_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
+{
+	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
+	const u32 soff = outp->base.or * 0x800;
+	const u32 data = 0x01010101 * pattern;
+	if (outp->base.info.sorconf.link & 1)
+		nvkm_mask(device, 0x61c110 + soff, 0x0f0f0f0f, data);
+	else
+		nvkm_mask(device, 0x61c12c + soff, 0x0f0f0f0f, data);
+	return 0;
+}
+
+static const struct nvkm_output_dp_func
+gm107_sor_dp_func = {
+	.pattern = gm107_sor_dp_pattern,
+	.lnk_pwr = g94_sor_dp_lnk_pwr,
+	.lnk_ctl = gf119_sor_dp_lnk_ctl,
+	.drv_ctl = gf119_sor_dp_drv_ctl,
+};
+
+int
+gm107_sor_dp_new(struct nvkm_disp *disp, int index,
+		 struct dcb_output *dcbE, struct nvkm_output **poutp)
+{
+	return nvkm_output_dp_new_(&gm107_sor_dp_func, disp, index, dcbE, poutp);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c
index 2cfbef9c344f..c44fa7ea672a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c
@@ -57,19 +57,6 @@ gm200_sor_dp_lane_map(struct nvkm_device *device, u8 lane)
 }
 
 static int
-gm200_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
-{
-	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
-	const u32 soff = gm200_sor_soff(outp);
-	const u32 data = 0x01010101 * pattern;
-	if (outp->base.info.sorconf.link & 1)
-		nvkm_mask(device, 0x61c110 + soff, 0x0f0f0f0f, data);
-	else
-		nvkm_mask(device, 0x61c12c + soff, 0x0f0f0f0f, data);
-	return 0;
-}
-
-static int
 gm200_sor_dp_lnk_pwr(struct nvkm_output_dp *outp, int nr)
 {
 	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
@@ -129,7 +116,7 @@ gm200_sor_dp_drv_ctl(struct nvkm_output_dp *outp,
 
 static const struct nvkm_output_dp_func
 gm200_sor_dp_func = {
-	.pattern = gm200_sor_dp_pattern,
+	.pattern = gm107_sor_dp_pattern,
 	.lnk_pwr = gm200_sor_dp_lnk_pwr,
 	.lnk_ctl = gf119_sor_dp_lnk_ctl,
 	.drv_ctl = gm200_sor_dp_drv_ctl,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index 9513badb8220..ae9ab5b1ab97 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -949,22 +949,41 @@ gf100_gr_trap_gpc_rop(struct gf100_gr *gr, int gpc)
 }
 
 static const struct nvkm_enum gf100_mp_warp_error[] = {
-	{ 0x00, "NO_ERROR" },
-	{ 0x01, "STACK_MISMATCH" },
+	{ 0x01, "STACK_ERROR" },
+	{ 0x02, "API_STACK_ERROR" },
+	{ 0x03, "RET_EMPTY_STACK_ERROR" },
+	{ 0x04, "PC_WRAP" },
 	{ 0x05, "MISALIGNED_PC" },
-	{ 0x08, "MISALIGNED_GPR" },
-	{ 0x09, "INVALID_OPCODE" },
-	{ 0x0d, "GPR_OUT_OF_BOUNDS" },
-	{ 0x0e, "MEM_OUT_OF_BOUNDS" },
-	{ 0x0f, "UNALIGNED_MEM_ACCESS" },
+	{ 0x06, "PC_OVERFLOW" },
+	{ 0x07, "MISALIGNED_IMMC_ADDR" },
+	{ 0x08, "MISALIGNED_REG" },
+	{ 0x09, "ILLEGAL_INSTR_ENCODING" },
+	{ 0x0a, "ILLEGAL_SPH_INSTR_COMBO" },
+	{ 0x0b, "ILLEGAL_INSTR_PARAM" },
+	{ 0x0c, "INVALID_CONST_ADDR" },
+	{ 0x0d, "OOR_REG" },
+	{ 0x0e, "OOR_ADDR" },
+	{ 0x0f, "MISALIGNED_ADDR" },
 	{ 0x10, "INVALID_ADDR_SPACE" },
-	{ 0x11, "INVALID_PARAM" },
+	{ 0x11, "ILLEGAL_INSTR_PARAM2" },
+	{ 0x12, "INVALID_CONST_ADDR_LDC" },
+	{ 0x13, "GEOMETRY_SM_ERROR" },
+	{ 0x14, "DIVERGENT" },
+	{ 0x15, "WARP_EXIT" },
 	{}
 };
 
 static const struct nvkm_bitfield gf100_mp_global_error[] = {
+	{ 0x00000001, "SM_TO_SM_FAULT" },
+	{ 0x00000002, "L1_ERROR" },
 	{ 0x00000004, "MULTIPLE_WARP_ERRORS" },
-	{ 0x00000008, "OUT_OF_STACK_SPACE" },
+	{ 0x00000008, "PHYSICAL_STACK_OVERFLOW" },
+	{ 0x00000010, "BPT_INT" },
+	{ 0x00000020, "BPT_PAUSE" },
+	{ 0x00000040, "SINGLE_STEP_COMPLETE" },
+	{ 0x20000000, "ECC_SEC_ERROR" },
+	{ 0x40000000, "ECC_DED_ERROR" },
+	{ 0x80000000, "TIMEOUT" },
 	{}
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/disp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/disp.c
index a5e92135cd77..9efb1b48cd54 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/disp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/disp.c
@@ -141,7 +141,8 @@ nvbios_ocfg_parse(struct nvkm_bios *bios, u16 outp, u8 idx,
 {
 	u16 data = nvbios_ocfg_entry(bios, outp, idx, ver, hdr, cnt, len);
 	if (data) {
-		info->match     = nvbios_rd16(bios, data + 0x00);
+		info->proto     = nvbios_rd08(bios, data + 0x00);
+		info->flags     = nvbios_rd16(bios, data + 0x01);
 		info->clkcmp[0] = nvbios_rd16(bios, data + 0x02);
 		info->clkcmp[1] = nvbios_rd16(bios, data + 0x04);
 	}
@@ -149,12 +150,13 @@ nvbios_ocfg_parse(struct nvkm_bios *bios, u16 outp, u8 idx,
 }
 
 u16
-nvbios_ocfg_match(struct nvkm_bios *bios, u16 outp, u16 type,
+nvbios_ocfg_match(struct nvkm_bios *bios, u16 outp, u8 proto, u8 flags,
 		  u8 *ver, u8 *hdr, u8 *cnt, u8 *len, struct nvbios_ocfg *info)
 {
 	u16 data, idx = 0;
 	while ((data = nvbios_ocfg_parse(bios, outp, idx++, ver, hdr, cnt, len, info))) {
-		if (info->match == type)
+		if ((info->proto == proto || info->proto == 0xff) &&
+		    (info->flags == flags))
 			break;
 	}
 	return data;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/base.c
index 323c79abe468..41bd5d0f7692 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/base.c
@@ -276,6 +276,8 @@ nvkm_iccsense_oneinit(struct nvkm_subdev *subdev)
 		struct pwr_rail_t *r = &stbl.rail[i];
 		struct nvkm_iccsense_rail *rail;
 		struct nvkm_iccsense_sensor *sensor;
+		int (*read)(struct nvkm_iccsense *,
+			    struct nvkm_iccsense_rail *);
 
 		if (!r->mode || r->resistor_mohm == 0)
 			continue;
@@ -284,31 +286,31 @@ nvkm_iccsense_oneinit(struct nvkm_subdev *subdev)
 		if (!sensor)
 			continue;
 
-		rail = kmalloc(sizeof(*rail), GFP_KERNEL);
-		if (!rail)
-			return -ENOMEM;
-
 		switch (sensor->type) {
 		case NVBIOS_EXTDEV_INA209:
 			if (r->rail != 0)
 				continue;
-			rail->read = nvkm_iccsense_ina209_read;
+			read = nvkm_iccsense_ina209_read;
 			break;
 		case NVBIOS_EXTDEV_INA219:
 			if (r->rail != 0)
 				continue;
-			rail->read = nvkm_iccsense_ina219_read;
+			read = nvkm_iccsense_ina219_read;
 			break;
 		case NVBIOS_EXTDEV_INA3221:
 			if (r->rail >= 3)
 				continue;
-			rail->read = nvkm_iccsense_ina3221_read;
+			read = nvkm_iccsense_ina3221_read;
 			break;
 		default:
 			continue;
 		}
 
+		rail = kmalloc(sizeof(*rail), GFP_KERNEL);
+		if (!rail)
+			return -ENOMEM;
 		sensor->rail_mask |= 1 << r->rail;
+		rail->read = read;
 		rail->sensor = sensor;
 		rail->idx = r->rail;
 		rail->mohm = r->resistor_mohm;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c
index e292f5679418..389fb13a1998 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c
@@ -69,11 +69,11 @@ gm107_ltc_zbc_clear_depth(struct nvkm_ltc *ltc, int i, const u32 depth)
 }
 
 static void
-gm107_ltc_lts_isr(struct nvkm_ltc *ltc, int c, int s)
+gm107_ltc_intr_lts(struct nvkm_ltc *ltc, int c, int s)
 {
 	struct nvkm_subdev *subdev = &ltc->subdev;
 	struct nvkm_device *device = subdev->device;
-	u32 base = 0x140000 + (c * 0x2000) + (s * 0x200);
+	u32 base = 0x140400 + (c * 0x2000) + (s * 0x200);
 	u32 stat = nvkm_rd32(device, base + 0x00c);
 
 	if (stat) {
@@ -92,7 +92,7 @@ gm107_ltc_intr(struct nvkm_ltc *ltc)
 	while (mask) {
 		u32 s, c = __ffs(mask);
 		for (s = 0; s < ltc->lts_nr; s++)
-			gm107_ltc_lts_isr(ltc, c, s);
+			gm107_ltc_intr_lts(ltc, c, s);
 		mask &= ~(1 << c);
 	}
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm200.c
index 2a29bfd5125a..e18e0dc19ec8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm200.c
@@ -46,7 +46,7 @@ static const struct nvkm_ltc_func
 gm200_ltc = {
 	.oneinit = gm200_ltc_oneinit,
 	.init = gm200_ltc_init,
-	.intr = gm107_ltc_intr, /*XXX: not validated */
+	.intr = gm107_ltc_intr,
 	.cbc_clear = gm107_ltc_cbc_clear,
 	.cbc_wait = gm107_ltc_cbc_wait,
 	.zbc = 16,
diff --git a/drivers/gpu/drm/omapdrm/Kconfig b/drivers/gpu/drm/omapdrm/Kconfig
index 73241c4eb7aa..336ad4de9981 100644
--- a/drivers/gpu/drm/omapdrm/Kconfig
+++ b/drivers/gpu/drm/omapdrm/Kconfig
@@ -2,6 +2,7 @@ config DRM_OMAP
 	tristate "OMAP DRM"
 	depends on DRM
 	depends on ARCH_OMAP2PLUS || ARCH_MULTIPLATFORM
+	select OMAP2_DSS
 	select DRM_KMS_HELPER
 	select DRM_KMS_FB_HELPER
 	select FB_SYS_FILLRECT
diff --git a/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c b/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
index 225fd8d6ab31..667ca4a24ece 100644
--- a/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
+++ b/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
@@ -9,6 +9,7 @@
  * the Free Software Foundation.
  */
 
+#include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c b/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
index 8c246c213e06..9594ff7a2b0c 100644
--- a/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
+++ b/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
@@ -14,7 +14,7 @@
  * the Free Software Foundation.
  */
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c b/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
index 2fd5602880a7..671806ca7d6a 100644
--- a/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
+++ b/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
@@ -9,7 +9,7 @@
  * the Free Software Foundation.
  */
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-dpi.c b/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
index e780fd4f8b46..7c2331be8d15 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
@@ -9,7 +9,7 @@
  * the Free Software Foundation.
  */
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c b/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
index 36485c2137ce..2b118071b5a1 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
@@ -14,7 +14,7 @@
 #include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/fb.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/jiffies.h>
 #include <linux/module.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c b/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
index 458f77bc473d..ac680e1de603 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
@@ -15,6 +15,7 @@
 #include <linux/spi/spi.h>
 #include <linux/mutex.h>
 #include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 #include <video/omapdss.h>
 #include <video/omap-panel-data.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c b/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
index 780cb263a318..38d2920a95e6 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
@@ -15,7 +15,7 @@
 #include <linux/delay.h>
 #include <linux/spi/spi.h>
 #include <linux/fb.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of_gpio.h>
 
 #include <video/omapdss.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c b/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
index 529a017602e4..4363fffc87e3 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
index 31efcca801bd..deb416736aad 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
@@ -29,7 +29,7 @@
 #include <linux/sched.h>
 #include <linux/backlight.h>
 #include <linux/fb.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
index 03e2beb7b4f0..d93175b03a12 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
@@ -14,7 +14,7 @@
 #include <linux/delay.h>
 #include <linux/spi/spi.h>
 #include <linux/regulator/consumer.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/of_gpio.h>
diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c
index 8730646a0cbb..56c43f355ce3 100644
--- a/drivers/gpu/drm/omapdrm/dss/dsi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dsi.c
@@ -1167,7 +1167,6 @@ static int dsi_regulator_init(struct platform_device *dsidev)
 {
 	struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
 	struct regulator *vdds_dsi;
-	int r;
 
 	if (dsi->vdds_dsi_reg != NULL)
 		return 0;
@@ -1180,15 +1179,6 @@ static int dsi_regulator_init(struct platform_device *dsidev)
 		return PTR_ERR(vdds_dsi);
 	}
 
-	if (regulator_can_change_voltage(vdds_dsi)) {
-		r = regulator_set_voltage(vdds_dsi, 1800000, 1800000);
-		if (r) {
-			devm_regulator_put(vdds_dsi);
-			DSSERR("can't set the DSI regulator voltage\n");
-			return r;
-		}
-	}
-
 	dsi->vdds_dsi_reg = vdds_dsi;
 
 	return 0;
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index f95ff319e68e..3303cfad4838 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -30,6 +30,7 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include <linux/clk.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/gfp.h>
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4.c b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
index f892ae157ff3..4d46cdf7a037 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
@@ -33,6 +33,7 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/component.h>
+#include <linux/of.h>
 #include <video/omapdss.h>
 #include <sound/omap-hdmi-audio.h>
 
@@ -100,7 +101,6 @@ static irqreturn_t hdmi_irq_handler(int irq, void *data)
 
 static int hdmi_init_regulator(void)
 {
-	int r;
 	struct regulator *reg;
 
 	if (hdmi.vdda_reg != NULL)
@@ -114,15 +114,6 @@ static int hdmi_init_regulator(void)
 		return PTR_ERR(reg);
 	}
 
-	if (regulator_can_change_voltage(reg)) {
-		r = regulator_set_voltage(reg, 1800000, 1800000);
-		if (r) {
-			devm_regulator_put(reg);
-			DSSWARN("can't set the regulator voltage\n");
-			return r;
-		}
-	}
-
 	hdmi.vdda_reg = reg;
 
 	return 0;
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
index fa72e735dad2..ef3afe99e487 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
@@ -211,7 +211,7 @@ static void hdmi_core_init(struct hdmi_core_video_config *video_cfg)
 static void hdmi_core_powerdown_disable(struct hdmi_core_data *core)
 {
 	DSSDBG("Enter hdmi_core_powerdown_disable\n");
-	REG_FLD_MOD(core->base, HDMI_CORE_SYS_SYS_CTRL1, 0x0, 0, 0);
+	REG_FLD_MOD(core->base, HDMI_CORE_SYS_SYS_CTRL1, 0x1, 0, 0);
 }
 
 static void hdmi_core_swreset_release(struct hdmi_core_data *core)
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5.c b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
index a43f7b10e113..9255c0e1e4a7 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi5.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
@@ -38,6 +38,7 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/component.h>
+#include <linux/of.h>
 #include <video/omapdss.h>
 #include <sound/omap-hdmi-audio.h>
 
@@ -119,7 +120,6 @@ static irqreturn_t hdmi_irq_handler(int irq, void *data)
 
 static int hdmi_init_regulator(void)
 {
-	int r;
 	struct regulator *reg;
 
 	if (hdmi.vdda_reg != NULL)
@@ -131,15 +131,6 @@ static int hdmi_init_regulator(void)
 		return PTR_ERR(reg);
 	}
 
-	if (regulator_can_change_voltage(reg)) {
-		r = regulator_set_voltage(reg, 1800000, 1800000);
-		if (r) {
-			devm_regulator_put(reg);
-			DSSWARN("can't set the regulator voltage\n");
-			return r;
-		}
-	}
-
 	hdmi.vdda_reg = reg;
 
 	return 0;
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c b/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c
index 6a397520cae5..8ab2093daa12 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c
@@ -51,8 +51,8 @@ static void hdmi_core_ddc_init(struct hdmi_core_data *core)
 {
 	void __iomem *base = core->base;
 	const unsigned long long iclk = 266000000;	/* DSS L3 ICLK */
-	const unsigned ss_scl_high = 4000;		/* ns */
-	const unsigned ss_scl_low = 4700;		/* ns */
+	const unsigned ss_scl_high = 4600;		/* ns */
+	const unsigned ss_scl_low = 5400;		/* ns */
 	const unsigned fs_scl_high = 600;		/* ns */
 	const unsigned fs_scl_low = 1300;		/* ns */
 	const unsigned sda_hold = 1000;			/* ns */
@@ -458,7 +458,7 @@ static void hdmi_core_write_avi_infoframe(struct hdmi_core_data *core,
 
 	c = (ptr[1] >> 6) & 0x3;
 	m = (ptr[1] >> 4) & 0x3;
-	r = (ptr[1] >> 0) & 0x3;
+	r = (ptr[1] >> 0) & 0xf;
 
 	itc = (ptr[2] >> 7) & 0x1;
 	ec = (ptr[2] >> 4) & 0x7;
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c b/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
index 1f5d19c119ce..f98b750fc499 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
@@ -13,6 +13,7 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/seq_file.h>
 #include <video/omapdss.h>
 
 #include "dss.h"
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c b/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
index 06e23a7c432c..f1015e8b8267 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/seq_file.h>
 
 #include <video/omapdss.h>
 
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c b/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
index 13442b9052d1..055f62fca5dc 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
@@ -14,6 +14,7 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/seq_file.h>
 #include <video/omapdss.h>
 
 #include "dss.h"
diff --git a/drivers/gpu/drm/omapdrm/omap_debugfs.c b/drivers/gpu/drm/omapdrm/omap_debugfs.c
index 6f5fc14fc015..479bf24050f8 100644
--- a/drivers/gpu/drm/omapdrm/omap_debugfs.c
+++ b/drivers/gpu/drm/omapdrm/omap_debugfs.c
@@ -17,6 +17,8 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/seq_file.h>
+
 #include <drm/drm_crtc.h>
 #include <drm/drm_fb_helper.h>
 
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index de275a5be1db..4ceed7a9762f 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h> /* platform_device() */
 #include <linux/sched.h>
+#include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index 94ec06d3d737..f84570d1636c 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -17,6 +17,8 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/seq_file.h>
+
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
 
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index b97afc281778..03698b6c806c 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -17,6 +17,7 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/seq_file.h>
 #include <linux/shmem_fs.h>
 #include <linux/spinlock.h>
 #include <linux/pfn_t.h>
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 2e216e2ea78c..259cd6e6d71c 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -589,7 +589,8 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 		if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE61(rdev) || ASIC_IS_DCE8(rdev))
 			radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
 		/* use frac fb div on RS780/RS880 */
-		if ((rdev->family == CHIP_RS780) || (rdev->family == CHIP_RS880))
+		if (((rdev->family == CHIP_RS780) || (rdev->family == CHIP_RS880))
+		    && !radeon_crtc->ss_enabled)
 			radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
 		if (ASIC_IS_DCE32(rdev) && mode->clock > 165000)
 			radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
@@ -626,7 +627,7 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 			if (radeon_crtc->ss.refdiv) {
 				radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV;
 				radeon_crtc->pll_reference_div = radeon_crtc->ss.refdiv;
-				if (ASIC_IS_AVIVO(rdev))
+				if (rdev->family >= CHIP_RV770)
 					radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
 			}
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index e721e6b2766e..21c44b2293bc 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -630,6 +630,23 @@ void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc)
 /*
  * GPU helpers function.
  */
+
+/**
+ * radeon_device_is_virtual - check if we are running is a virtual environment
+ *
+ * Check if the asic has been passed through to a VM (all asics).
+ * Used at driver startup.
+ * Returns true if virtual or false if not.
+ */
+static bool radeon_device_is_virtual(void)
+{
+#ifdef CONFIG_X86
+	return boot_cpu_has(X86_FEATURE_HYPERVISOR);
+#else
+	return false;
+#endif
+}
+
 /**
  * radeon_card_posted - check if the hw has already been initialized
  *
@@ -643,6 +660,10 @@ bool radeon_card_posted(struct radeon_device *rdev)
 {
 	uint32_t reg;
 
+	/* for pass through, always force asic_init */
+	if (radeon_device_is_virtual())
+		return false;
+
 	/* required for EFI mode on macbook2,1 which uses an r5xx asic */
 	if (efi_enabled(EFI_BOOT) &&
 	    (rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) &&
@@ -1631,7 +1652,7 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend,
 	radeon_agp_suspend(rdev);
 
 	pci_save_state(dev->pdev);
-	if (freeze && rdev->family >= CHIP_R600) {
+	if (freeze && rdev->family >= CHIP_CEDAR) {
 		rdev->asic->asic_reset(rdev, true);
 		pci_restore_state(dev->pdev);
 	} else if (suspend) {
diff --git a/drivers/gpu/drm/sti/sti_crtc.c b/drivers/gpu/drm/sti/sti_crtc.c
index 505620c7c2c8..e04deedabd4a 100644
--- a/drivers/gpu/drm/sti/sti_crtc.c
+++ b/drivers/gpu/drm/sti/sti_crtc.c
@@ -51,15 +51,6 @@ static void sti_crtc_disabling(struct drm_crtc *crtc)
 	mixer->status = STI_MIXER_DISABLING;
 }
 
-static bool sti_crtc_mode_fixup(struct drm_crtc *crtc,
-				const struct drm_display_mode *mode,
-				struct drm_display_mode *adjusted_mode)
-{
-	/* accept the provided drm_display_mode, do not fix it up */
-	drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V);
-	return true;
-}
-
 static int
 sti_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode)
 {
@@ -230,7 +221,6 @@ static void sti_crtc_atomic_flush(struct drm_crtc *crtc,
 static const struct drm_crtc_helper_funcs sti_crtc_helper_funcs = {
 	.enable = sti_crtc_enable,
 	.disable = sti_crtc_disabling,
-	.mode_fixup = sti_crtc_mode_fixup,
 	.mode_set = drm_helper_crtc_mode_set,
 	.mode_set_nofb = sti_crtc_mode_set_nofb,
 	.mode_set_base = drm_helper_crtc_mode_set_base,
diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index 99510e64e91a..a4b357db8856 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -1,6 +1,6 @@
 config DRM_SUN4I
 	tristate "DRM Support for Allwinner A10 Display Engine"
-	depends on DRM && ARM
+	depends on DRM && ARM && COMMON_CLK
 	depends on ARCH_SUNXI || COMPILE_TEST
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index f7a15c1a93bf..3ab560450a82 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -190,7 +190,7 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
 	/* Get the physical address of the buffer in memory */
 	gem = drm_fb_cma_get_gem_obj(fb, 0);
 
-	DRM_DEBUG_DRIVER("Using GEM @ 0x%x\n", gem->paddr);
+	DRM_DEBUG_DRIVER("Using GEM @ %pad\n", &gem->paddr);
 
 	/* Compute the start of the displayed memory */
 	bpp = drm_format_plane_cpp(fb->pixel_format, 0);
@@ -198,7 +198,7 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
 	paddr += (state->src_x >> 16) * bpp;
 	paddr += (state->src_y >> 16) * fb->pitches[0];
 
-	DRM_DEBUG_DRIVER("Setting buffer address to 0x%x\n", paddr);
+	DRM_DEBUG_DRIVER("Setting buffer address to %pad\n", &paddr);
 
 	/* Write the 32 lower bits of the address (in bits) */
 	lo_paddr = paddr << 3;
diff --git a/drivers/gpu/drm/sun4i/sun4i_dotclock.c b/drivers/gpu/drm/sun4i/sun4i_dotclock.c
index 3ff668cb463c..5b3463197c48 100644
--- a/drivers/gpu/drm/sun4i/sun4i_dotclock.c
+++ b/drivers/gpu/drm/sun4i/sun4i_dotclock.c
@@ -72,14 +72,40 @@ static unsigned long sun4i_dclk_recalc_rate(struct clk_hw *hw,
 static long sun4i_dclk_round_rate(struct clk_hw *hw, unsigned long rate,
 				  unsigned long *parent_rate)
 {
-	return *parent_rate / DIV_ROUND_CLOSEST(*parent_rate, rate);
+	unsigned long best_parent = 0;
+	u8 best_div = 1;
+	int i;
+
+	for (i = 6; i < 127; i++) {
+		unsigned long ideal = rate * i;
+		unsigned long rounded;
+
+		rounded = clk_hw_round_rate(clk_hw_get_parent(hw),
+					    ideal);
+
+		if (rounded == ideal) {
+			best_parent = rounded;
+			best_div = i;
+			goto out;
+		}
+
+		if ((rounded < ideal) && (rounded > best_parent)) {
+			best_parent = rounded;
+			best_div = i;
+		}
+	}
+
+out:
+	*parent_rate = best_parent;
+
+	return best_parent / best_div;
 }
 
 static int sun4i_dclk_set_rate(struct clk_hw *hw, unsigned long rate,
 			       unsigned long parent_rate)
 {
 	struct sun4i_dclk *dclk = hw_to_dclk(hw);
-	int div = DIV_ROUND_CLOSEST(parent_rate, rate);
+	u8 div = parent_rate / rate;
 
 	return regmap_update_bits(dclk->regmap, SUN4I_TCON0_DCLK_REG,
 				  GENMASK(6, 0), div);
@@ -127,10 +153,14 @@ int sun4i_dclk_create(struct device *dev, struct sun4i_tcon *tcon)
 	const char *clk_name, *parent_name;
 	struct clk_init_data init;
 	struct sun4i_dclk *dclk;
+	int ret;
 
 	parent_name = __clk_get_name(tcon->sclk0);
-	of_property_read_string_index(dev->of_node, "clock-output-names", 0,
-				      &clk_name);
+	ret = of_property_read_string_index(dev->of_node,
+					    "clock-output-names", 0,
+					    &clk_name);
+	if (ret)
+		return ret;
 
 	dclk = devm_kzalloc(dev, sizeof(*dclk), GFP_KERNEL);
 	if (!dclk)
@@ -140,6 +170,7 @@ int sun4i_dclk_create(struct device *dev, struct sun4i_tcon *tcon)
 	init.ops = &sun4i_dclk_ops;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
+	init.flags = CLK_SET_RATE_PARENT;
 
 	dclk->regmap = tcon->regs;
 	dclk->hw.init = &init;
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 76e922bb60e5..257d2b4f3645 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -24,34 +24,6 @@
 #include "sun4i_layer.h"
 #include "sun4i_tcon.h"
 
-static int sun4i_drv_connector_plug_all(struct drm_device *drm)
-{
-	struct drm_connector *connector, *failed;
-	int ret;
-
-	mutex_lock(&drm->mode_config.mutex);
-	list_for_each_entry(connector, &drm->mode_config.connector_list, head) {
-		ret = drm_connector_register(connector);
-		if (ret) {
-			failed = connector;
-			goto err;
-		}
-	}
-	mutex_unlock(&drm->mode_config.mutex);
-	return 0;
-
-err:
-	list_for_each_entry(connector, &drm->mode_config.connector_list, head) {
-		if (failed == connector)
-			break;
-
-		drm_connector_unregister(connector);
-	}
-	mutex_unlock(&drm->mode_config.mutex);
-
-	return ret;
-}
-
 static int sun4i_drv_enable_vblank(struct drm_device *drm, unsigned int pipe)
 {
 	struct sun4i_drv *drv = drm->dev_private;
@@ -125,6 +97,22 @@ static struct drm_driver sun4i_drv_driver = {
 	.disable_vblank		= sun4i_drv_disable_vblank,
 };
 
+static void sun4i_remove_framebuffers(void)
+{
+	struct apertures_struct *ap;
+
+	ap = alloc_apertures(1);
+	if (!ap)
+		return;
+
+	/* The framebuffer can be located anywhere in RAM */
+	ap->ranges[0].base = 0;
+	ap->ranges[0].size = ~0;
+
+	remove_conflicting_framebuffers(ap, "sun4i-drm-fb", false);
+	kfree(ap);
+}
+
 static int sun4i_drv_bind(struct device *dev)
 {
 	struct drm_device *drm;
@@ -172,6 +160,9 @@ static int sun4i_drv_bind(struct device *dev)
 	}
 	drm->irq_enabled = true;
 
+	/* Remove early framebuffers (ie. simplefb) */
+	sun4i_remove_framebuffers();
+
 	/* Create our framebuffer */
 	drv->fbdev = sun4i_framebuffer_init(drm);
 	if (IS_ERR(drv->fbdev)) {
@@ -187,7 +178,7 @@ static int sun4i_drv_bind(struct device *dev)
 	if (ret)
 		goto free_drm;
 
-	ret = sun4i_drv_connector_plug_all(drm);
+	ret = drm_connector_register_all(drm);
 	if (ret)
 		goto unregister_drm;
 
@@ -204,6 +195,7 @@ static void sun4i_drv_unbind(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
 
+	drm_connector_unregister_all(drm);
 	drm_dev_unregister(drm);
 	drm_kms_helper_poll_fini(drm);
 	sun4i_framebuffer_free(drm);
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index ab6494818050..aaffe9e64ffb 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -54,8 +54,13 @@ static int sun4i_rgb_get_modes(struct drm_connector *connector)
 static int sun4i_rgb_mode_valid(struct drm_connector *connector,
 				struct drm_display_mode *mode)
 {
+	struct sun4i_rgb *rgb = drm_connector_to_sun4i_rgb(connector);
+	struct sun4i_drv *drv = rgb->drv;
+	struct sun4i_tcon *tcon = drv->tcon;
 	u32 hsync = mode->hsync_end - mode->hsync_start;
 	u32 vsync = mode->vsync_end - mode->vsync_start;
+	unsigned long rate = mode->clock * 1000;
+	long rounded_rate;
 
 	DRM_DEBUG_DRIVER("Validating modes...\n");
 
@@ -87,6 +92,15 @@ static int sun4i_rgb_mode_valid(struct drm_connector *connector,
 
 	DRM_DEBUG_DRIVER("Vertical parameters OK\n");
 
+	rounded_rate = clk_round_rate(tcon->dclk, rate);
+	if (rounded_rate < rate)
+		return MODE_CLOCK_LOW;
+
+	if (rounded_rate > rate)
+		return MODE_CLOCK_HIGH;
+
+	DRM_DEBUG_DRIVER("Clock rate OK\n");
+
 	return MODE_OK;
 }
 
@@ -203,7 +217,7 @@ int sun4i_rgb_init(struct drm_device *drm)
 	int ret;
 
 	/* If we don't have a panel, there's no point in going on */
-	if (!tcon->panel)
+	if (IS_ERR(tcon->panel))
 		return -ENODEV;
 
 	rgb = devm_kzalloc(drm->dev, sizeof(*rgb), GFP_KERNEL);
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 9f19b0e08560..652385f09735 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -425,11 +425,11 @@ static struct drm_panel *sun4i_tcon_find_panel(struct device_node *node)
 
 	remote = of_graph_get_remote_port_parent(end_node);
 	if (!remote) {
-		DRM_DEBUG_DRIVER("Enable to parse remote node\n");
+		DRM_DEBUG_DRIVER("Unable to parse remote node\n");
 		return ERR_PTR(-EINVAL);
 	}
 
-	return of_drm_find_panel(remote);
+	return of_drm_find_panel(remote) ?: ERR_PTR(-EPROBE_DEFER);
 }
 
 static int sun4i_tcon_bind(struct device *dev, struct device *master,
@@ -490,7 +490,11 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master,
 		return 0;
 	}
 
-	return sun4i_rgb_init(drm);
+	ret = sun4i_rgb_init(drm);
+	if (ret < 0)
+		goto err_free_clocks;
+
+	return 0;
 
 err_free_clocks:
 	sun4i_tcon_free_clocks(tcon);
@@ -522,12 +526,13 @@ static int sun4i_tcon_probe(struct platform_device *pdev)
 	 * Defer the probe.
 	 */
 	panel = sun4i_tcon_find_panel(node);
-	if (IS_ERR(panel)) {
-		/*
-		 * If we don't have a panel endpoint, just go on
-		 */
-		if (PTR_ERR(panel) != -ENODEV)
-			return -EPROBE_DEFER;
+
+	/*
+	 * If we don't have a panel endpoint, just go on
+	 */
+	if (PTR_ERR(panel) == -EPROBE_DEFER) {
+		DRM_DEBUG_DRIVER("Still waiting for our panel. Deferring...\n");
+		return -EPROBE_DEFER;
 	}
 
 	return component_add(&pdev->dev, &sun4i_tcon_ops);
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 904d0754ad78..0f18b76c7906 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -456,14 +456,6 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc,
 
 	WARN_ON_ONCE(dlist_next - dlist_start != vc4_state->mm.size);
 
-	HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
-		  vc4_state->mm.start);
-
-	if (debug_dump_regs) {
-		DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc));
-		vc4_hvs_dump_state(dev);
-	}
-
 	if (crtc->state->event) {
 		unsigned long flags;
 
@@ -473,8 +465,20 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc,
 
 		spin_lock_irqsave(&dev->event_lock, flags);
 		vc4_crtc->event = crtc->state->event;
-		spin_unlock_irqrestore(&dev->event_lock, flags);
 		crtc->state->event = NULL;
+
+		HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
+			  vc4_state->mm.start);
+
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	} else {
+		HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
+			  vc4_state->mm.start);
+	}
+
+	if (debug_dump_regs) {
+		DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc));
+		vc4_hvs_dump_state(dev);
 	}
 }
 
@@ -500,12 +504,17 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
 {
 	struct drm_crtc *crtc = &vc4_crtc->base;
 	struct drm_device *dev = crtc->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+	u32 chan = vc4_crtc->channel;
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev->event_lock, flags);
-	if (vc4_crtc->event) {
+	if (vc4_crtc->event &&
+	    (vc4_state->mm.start == HVS_READ(SCALER_DISPLACTX(chan)))) {
 		drm_crtc_send_vblank_event(crtc, vc4_crtc->event);
 		vc4_crtc->event = NULL;
+		drm_crtc_vblank_put(crtc);
 	}
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
@@ -556,6 +565,7 @@ vc4_async_page_flip_complete(struct vc4_seqno_cb *cb)
 		spin_unlock_irqrestore(&dev->event_lock, flags);
 	}
 
+	drm_crtc_vblank_put(crtc);
 	drm_framebuffer_unreference(flip_state->fb);
 	kfree(flip_state);
 
@@ -598,6 +608,8 @@ static int vc4_async_page_flip(struct drm_crtc *crtc,
 		return ret;
 	}
 
+	WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+
 	/* Immediately update the plane's legacy fb pointer, so that later
 	 * modeset prep sees the state that will be present when the semaphore
 	 * is released.
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 3446ece21b4a..250ed7e3754c 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -66,12 +66,12 @@ static const struct file_operations vc4_drm_fops = {
 };
 
 static const struct drm_ioctl_desc vc4_drm_ioctls[] = {
-	DRM_IOCTL_DEF_DRV(VC4_SUBMIT_CL, vc4_submit_cl_ioctl, 0),
-	DRM_IOCTL_DEF_DRV(VC4_WAIT_SEQNO, vc4_wait_seqno_ioctl, 0),
-	DRM_IOCTL_DEF_DRV(VC4_WAIT_BO, vc4_wait_bo_ioctl, 0),
-	DRM_IOCTL_DEF_DRV(VC4_CREATE_BO, vc4_create_bo_ioctl, 0),
-	DRM_IOCTL_DEF_DRV(VC4_MMAP_BO, vc4_mmap_bo_ioctl, 0),
-	DRM_IOCTL_DEF_DRV(VC4_CREATE_SHADER_BO, vc4_create_shader_bo_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(VC4_SUBMIT_CL, vc4_submit_cl_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_WAIT_SEQNO, vc4_wait_seqno_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_WAIT_BO, vc4_wait_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_CREATE_BO, vc4_create_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_MMAP_BO, vc4_mmap_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_CREATE_SHADER_BO, vc4_create_shader_bo_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(VC4_GET_HANG_STATE, vc4_get_hang_state_ioctl,
 			  DRM_ROOT_ONLY),
 };
@@ -91,7 +91,7 @@ static struct drm_driver vc4_drm_driver = {
 
 	.enable_vblank = vc4_enable_vblank,
 	.disable_vblank = vc4_disable_vblank,
-	.get_vblank_counter = drm_vblank_count,
+	.get_vblank_counter = drm_vblank_no_hw_counter,
 
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = vc4_debugfs_init,
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index cb37751bc99f..861a623bc185 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -117,10 +117,18 @@ static int vc4_atomic_commit(struct drm_device *dev,
 		return -ENOMEM;
 
 	/* Make sure that any outstanding modesets have finished. */
-	ret = down_interruptible(&vc4->async_modeset);
-	if (ret) {
-		kfree(c);
-		return ret;
+	if (nonblock) {
+		ret = down_trylock(&vc4->async_modeset);
+		if (ret) {
+			kfree(c);
+			return -EBUSY;
+		}
+	} else {
+		ret = down_interruptible(&vc4->async_modeset);
+		if (ret) {
+			kfree(c);
+			return ret;
+		}
 	}
 
 	ret = drm_atomic_helper_prepare_planes(dev, state);
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index 6163b95c5411..f99eece4cc97 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -341,6 +341,10 @@
 #define SCALER_DISPLACT0                        0x00000030
 #define SCALER_DISPLACT1                        0x00000034
 #define SCALER_DISPLACT2                        0x00000038
+#define SCALER_DISPLACTX(x)			(SCALER_DISPLACT0 +	\
+						 (x) * (SCALER_DISPLACT1 - \
+							SCALER_DISPLACT0))
+
 #define SCALER_DISPCTRL0                        0x00000040
 # define SCALER_DISPCTRLX_ENABLE		BIT(31)
 # define SCALER_DISPCTRLX_RESET			BIT(30)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 6de283c8fa3e..f0374f9b56ca 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/frame.h>
 #include <asm/hypervisor.h>
 #include "drmP.h"
 #include "vmwgfx_msg.h"
@@ -194,7 +195,7 @@ static int vmw_send_msg(struct rpc_channel *channel, const char *msg)
 
 	return -EINVAL;
 }
-
+STACK_FRAME_NON_STANDARD(vmw_send_msg);
 
 
 /**
@@ -304,6 +305,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg,
 
 	return 0;
 }
+STACK_FRAME_NON_STANDARD(vmw_recv_msg);
 
 
 /**
diff --git a/drivers/hid/hid-elo.c b/drivers/hid/hid-elo.c
index aad8c162a825..0cd4f7216239 100644
--- a/drivers/hid/hid-elo.c
+++ b/drivers/hid/hid-elo.c
@@ -261,7 +261,7 @@ static void elo_remove(struct hid_device *hdev)
 	struct elo_priv *priv = hid_get_drvdata(hdev);
 
 	hid_hw_stop(hdev);
-	flush_workqueue(wq);
+	cancel_delayed_work_sync(&priv->work);
 	kfree(priv);
 }
 
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index c741f5e50a66..fb6f1f447279 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -61,6 +61,7 @@ MODULE_LICENSE("GPL");
 #define MT_QUIRK_ALWAYS_VALID		(1 << 4)
 #define MT_QUIRK_VALID_IS_INRANGE	(1 << 5)
 #define MT_QUIRK_VALID_IS_CONFIDENCE	(1 << 6)
+#define MT_QUIRK_CONFIDENCE		(1 << 7)
 #define MT_QUIRK_SLOT_IS_CONTACTID_MINUS_ONE	(1 << 8)
 #define MT_QUIRK_NO_AREA		(1 << 9)
 #define MT_QUIRK_IGNORE_DUPLICATES	(1 << 10)
@@ -78,6 +79,7 @@ struct mt_slot {
 	__s32 contactid;	/* the device ContactID assigned to this slot */
 	bool touch_state;	/* is the touch valid? */
 	bool inrange_state;	/* is the finger in proximity of the sensor? */
+	bool confidence_state;  /* is the touch made by a finger? */
 };
 
 struct mt_class {
@@ -503,10 +505,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 			return 1;
 		case HID_DG_CONFIDENCE:
 			if (cls->name == MT_CLS_WIN_8 &&
-				field->application == HID_DG_TOUCHPAD) {
-				cls->quirks &= ~MT_QUIRK_ALWAYS_VALID;
-				cls->quirks |= MT_QUIRK_VALID_IS_CONFIDENCE;
-			}
+				field->application == HID_DG_TOUCHPAD)
+				cls->quirks |= MT_QUIRK_CONFIDENCE;
 			mt_store_field(usage, td, hi);
 			return 1;
 		case HID_DG_TIPSWITCH:
@@ -619,6 +619,7 @@ static void mt_complete_slot(struct mt_device *td, struct input_dev *input)
 		return;
 
 	if (td->curvalid || (td->mtclass.quirks & MT_QUIRK_ALWAYS_VALID)) {
+		int active;
 		int slotnum = mt_compute_slot(td, input);
 		struct mt_slot *s = &td->curdata;
 		struct input_mt *mt = input->mt;
@@ -633,10 +634,14 @@ static void mt_complete_slot(struct mt_device *td, struct input_dev *input)
 				return;
 		}
 
+		if (!(td->mtclass.quirks & MT_QUIRK_CONFIDENCE))
+			s->confidence_state = 1;
+		active = (s->touch_state || s->inrange_state) &&
+							s->confidence_state;
+
 		input_mt_slot(input, slotnum);
-		input_mt_report_slot_state(input, MT_TOOL_FINGER,
-			s->touch_state || s->inrange_state);
-		if (s->touch_state || s->inrange_state) {
+		input_mt_report_slot_state(input, MT_TOOL_FINGER, active);
+		if (active) {
 			/* this finger is in proximity of the sensor */
 			int wide = (s->w > s->h);
 			/* divided by two to match visual scale of touch */
@@ -701,6 +706,8 @@ static void mt_process_mt_event(struct hid_device *hid, struct hid_field *field,
 			td->curdata.touch_state = value;
 			break;
 		case HID_DG_CONFIDENCE:
+			if (quirks & MT_QUIRK_CONFIDENCE)
+				td->curdata.confidence_state = value;
 			if (quirks & MT_QUIRK_VALID_IS_CONFIDENCE)
 				td->curvalid = value;
 			break;
@@ -1401,6 +1408,11 @@ static const struct hid_device_id mt_devices[] = {
 		MT_USB_DEVICE(USB_VENDOR_ID_NOVATEK,
 			USB_DEVICE_ID_NOVATEK_PCT) },
 
+	/* Ntrig Panel */
+	{ .driver_data = MT_CLS_NSMU,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_NTRIG, 0x1b05) },
+
 	/* PixArt optical touch screen */
 	{ .driver_data = MT_CLS_INRANGE_CONTACTNUMBER,
 		MT_USB_DEVICE(USB_VENDOR_ID_PIXART,
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 2f1ddca6f2e0..700145b15088 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -516,13 +516,13 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd,
 					goto inval;
 			} else if (uref->usage_index >= field->report_count)
 				goto inval;
-
-			else if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
-				 (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
-				  uref->usage_index + uref_multi->num_values > field->report_count))
-				goto inval;
 		}
 
+		if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
+		    (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
+		     uref->usage_index + uref_multi->num_values > field->report_count))
+			goto inval;
+
 		switch (cmd) {
 		case HIDIOCGUSAGE:
 			uref->value = field->value[uref->usage_index];
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index c43318d3416e..2ac87d553e22 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -35,6 +35,7 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/sched.h>
+#include <linux/ctype.h>
 
 #include <linux/i8k.h>
 
@@ -66,11 +67,13 @@
 
 static DEFINE_MUTEX(i8k_mutex);
 static char bios_version[4];
+static char bios_machineid[16];
 static struct device *i8k_hwmon_dev;
 static u32 i8k_hwmon_flags;
 static uint i8k_fan_mult = I8K_FAN_MULT;
 static uint i8k_pwm_mult;
 static uint i8k_fan_max = I8K_FAN_HIGH;
+static bool disallow_fan_type_call;
 
 #define I8K_HWMON_HAVE_TEMP1	(1 << 0)
 #define I8K_HWMON_HAVE_TEMP2	(1 << 1)
@@ -94,13 +97,13 @@ module_param(ignore_dmi, bool, 0);
 MODULE_PARM_DESC(ignore_dmi, "Continue probing hardware even if DMI data does not match");
 
 #if IS_ENABLED(CONFIG_I8K)
-static bool restricted;
+static bool restricted = true;
 module_param(restricted, bool, 0);
-MODULE_PARM_DESC(restricted, "Allow fan control if SYS_ADMIN capability set");
+MODULE_PARM_DESC(restricted, "Restrict fan control and serial number to CAP_SYS_ADMIN (default: 1)");
 
 static bool power_status;
 module_param(power_status, bool, 0600);
-MODULE_PARM_DESC(power_status, "Report power status in /proc/i8k");
+MODULE_PARM_DESC(power_status, "Report power status in /proc/i8k (default: 0)");
 #endif
 
 static uint fan_mult;
@@ -235,14 +238,28 @@ static int i8k_get_fan_speed(int fan)
 /*
  * Read the fan type.
  */
-static int i8k_get_fan_type(int fan)
+static int _i8k_get_fan_type(int fan)
 {
 	struct smm_regs regs = { .eax = I8K_SMM_GET_FAN_TYPE, };
 
+	if (disallow_fan_type_call)
+		return -EINVAL;
+
 	regs.ebx = fan & 0xff;
 	return i8k_smm(&regs) ? : regs.eax & 0xff;
 }
 
+static int i8k_get_fan_type(int fan)
+{
+	/* I8K_SMM_GET_FAN_TYPE SMM call is expensive, so cache values */
+	static int types[2] = { INT_MIN, INT_MIN };
+
+	if (types[fan] == INT_MIN)
+		types[fan] = _i8k_get_fan_type(fan);
+
+	return types[fan];
+}
+
 /*
  * Read the fan nominal rpm for specific fan speed.
  */
@@ -387,14 +404,20 @@ i8k_ioctl_unlocked(struct file *fp, unsigned int cmd, unsigned long arg)
 
 	switch (cmd) {
 	case I8K_BIOS_VERSION:
+		if (!isdigit(bios_version[0]) || !isdigit(bios_version[1]) ||
+		    !isdigit(bios_version[2]))
+			return -EINVAL;
+
 		val = (bios_version[0] << 16) |
 				(bios_version[1] << 8) | bios_version[2];
 		break;
 
 	case I8K_MACHINE_ID:
-		memset(buff, 0, 16);
-		strlcpy(buff, i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
-			sizeof(buff));
+		if (restricted && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		memset(buff, 0, sizeof(buff));
+		strlcpy(buff, bios_machineid, sizeof(buff));
 		break;
 
 	case I8K_FN_STATUS:
@@ -511,7 +534,7 @@ static int i8k_proc_show(struct seq_file *seq, void *offset)
 	seq_printf(seq, "%s %s %s %d %d %d %d %d %d %d\n",
 		   I8K_PROC_FMT,
 		   bios_version,
-		   i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
+		   (restricted && !capable(CAP_SYS_ADMIN)) ? "-1" : bios_machineid,
 		   cpu_temp,
 		   left_fan, right_fan, left_speed, right_speed,
 		   ac_power, fn_key);
@@ -718,6 +741,9 @@ static struct attribute *i8k_attrs[] = {
 static umode_t i8k_is_visible(struct kobject *kobj, struct attribute *attr,
 			      int index)
 {
+	if (disallow_fan_type_call &&
+	    (index == 9 || index == 12))
+		return 0;
 	if (index >= 0 && index <= 1 &&
 	    !(i8k_hwmon_flags & I8K_HWMON_HAVE_TEMP1))
 		return 0;
@@ -767,13 +793,17 @@ static int __init i8k_init_hwmon(void)
 	if (err >= 0)
 		i8k_hwmon_flags |= I8K_HWMON_HAVE_TEMP4;
 
-	/* First fan attributes, if fan type is OK */
-	err = i8k_get_fan_type(0);
+	/* First fan attributes, if fan status or type is OK */
+	err = i8k_get_fan_status(0);
+	if (err < 0)
+		err = i8k_get_fan_type(0);
 	if (err >= 0)
 		i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN1;
 
-	/* Second fan attributes, if fan type is OK */
-	err = i8k_get_fan_type(1);
+	/* Second fan attributes, if fan status or type is OK */
+	err = i8k_get_fan_status(1);
+	if (err < 0)
+		err = i8k_get_fan_type(1);
 	if (err >= 0)
 		i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN2;
 
@@ -929,12 +959,14 @@ static struct dmi_system_id i8k_dmi_table[] __initdata = {
 
 MODULE_DEVICE_TABLE(dmi, i8k_dmi_table);
 
-static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = {
+/*
+ * On some machines once I8K_SMM_GET_FAN_TYPE is issued then CPU fan speed
+ * randomly going up and down due to bug in Dell SMM or BIOS. Here is blacklist
+ * of affected Dell machines for which we disallow I8K_SMM_GET_FAN_TYPE call.
+ * See bug: https://bugzilla.kernel.org/show_bug.cgi?id=100121
+ */
+static struct dmi_system_id i8k_blacklist_fan_type_dmi_table[] __initdata = {
 	{
-		/*
-		 * CPU fan speed going up and down on Dell Studio XPS 8000
-		 * for unknown reasons.
-		 */
 		.ident = "Dell Studio XPS 8000",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
@@ -942,16 +974,19 @@ static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = {
 		},
 	},
 	{
-		/*
-		 * CPU fan speed going up and down on Dell Studio XPS 8100
-		 * for unknown reasons.
-		 */
 		.ident = "Dell Studio XPS 8100",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Studio XPS 8100"),
 		},
 	},
+	{
+		.ident = "Dell Inspiron 580",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Inspiron 580 "),
+		},
+	},
 	{ }
 };
 
@@ -966,8 +1001,7 @@ static int __init i8k_probe(void)
 	/*
 	 * Get DMI information
 	 */
-	if (!dmi_check_system(i8k_dmi_table) ||
-	    dmi_check_system(i8k_blacklist_dmi_table)) {
+	if (!dmi_check_system(i8k_dmi_table)) {
 		if (!ignore_dmi && !force)
 			return -ENODEV;
 
@@ -978,8 +1012,13 @@ static int __init i8k_probe(void)
 			i8k_get_dmi_data(DMI_BIOS_VERSION));
 	}
 
+	if (dmi_check_system(i8k_blacklist_fan_type_dmi_table))
+		disallow_fan_type_call = true;
+
 	strlcpy(bios_version, i8k_get_dmi_data(DMI_BIOS_VERSION),
 		sizeof(bios_version));
+	strlcpy(bios_machineid, i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
+		sizeof(bios_machineid));
 
 	/*
 	 * Get SMM Dell signature
diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c
index eb97a9241d17..15aa49d082c4 100644
--- a/drivers/hwmon/fam15h_power.c
+++ b/drivers/hwmon/fam15h_power.c
@@ -172,9 +172,9 @@ static void do_read_registers_on_cu(void *_data)
  */
 static int read_registers(struct fam15h_power_data *data)
 {
-	int this_cpu, ret, cpu;
 	int core, this_core;
 	cpumask_var_t mask;
+	int ret, cpu;
 
 	ret = zalloc_cpumask_var(&mask, GFP_KERNEL);
 	if (!ret)
@@ -183,7 +183,6 @@ static int read_registers(struct fam15h_power_data *data)
 	memset(data->cu_on, 0, sizeof(int) * MAX_CUS);
 
 	get_online_cpus();
-	this_cpu = smp_processor_id();
 
 	/*
 	 * Choose the first online core of each compute unit, and then
@@ -205,12 +204,9 @@ static int read_registers(struct fam15h_power_data *data)
 		cpumask_set_cpu(cpumask_any(topology_sibling_cpumask(cpu)), mask);
 	}
 
-	if (cpumask_test_cpu(this_cpu, mask))
-		do_read_registers_on_cu(data);
+	on_each_cpu_mask(mask, do_read_registers_on_cu, data, true);
 
-	smp_call_function_many(mask, do_read_registers_on_cu, data, true);
 	put_online_cpus();
-
 	free_cpumask_var(mask);
 
 	return 0;
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index c9ff08dbe10c..e30a5939dc0d 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -375,7 +375,7 @@ struct lm90_data {
 	int kind;
 	u32 flags;
 
-	int update_interval;	/* in milliseconds */
+	unsigned int update_interval; /* in milliseconds */
 
 	u8 config_orig;		/* Original configuration register value */
 	u8 convrate_orig;	/* Original conversion rate register value */
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index 847d1b5f2c13..688be9e060fc 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -300,13 +300,10 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata)
 	if (local_read(&drvdata->mode) == CS_MODE_SYSFS) {
 		/*
 		 * The trace run will continue with the same allocated trace
-		 * buffer. As such zero-out the buffer so that we don't end
-		 * up with stale data.
-		 *
-		 * Since the tracer is still enabled drvdata::buf
-		 * can't be NULL.
+		 * buffer. The trace buffer is cleared in tmc_etr_enable_hw(),
+		 * so we don't have to explicitly clear it. Also, since the
+		 * tracer is still enabled drvdata::buf can't be NULL.
 		 */
-		memset(drvdata->buf, 0, drvdata->size);
 		tmc_etr_enable_hw(drvdata);
 	} else {
 		/*
@@ -315,7 +312,7 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata)
 		 */
 		vaddr = drvdata->vaddr;
 		paddr = drvdata->paddr;
-		drvdata->buf = NULL;
+		drvdata->buf = drvdata->vaddr = NULL;
 	}
 
 	drvdata->reading = false;
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index 5443d03a1eec..d08d1ab9bba5 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -385,7 +385,6 @@ static int _coresight_build_path(struct coresight_device *csdev,
 	int i;
 	bool found = false;
 	struct coresight_node *node;
-	struct coresight_connection *conn;
 
 	/* An activated sink has been found.  Enqueue the element */
 	if ((csdev->type == CORESIGHT_DEV_TYPE_SINK ||
@@ -394,8 +393,9 @@ static int _coresight_build_path(struct coresight_device *csdev,
 
 	/* Not a sink - recursively explore each port found on this element */
 	for (i = 0; i < csdev->nr_outport; i++) {
-		conn = &csdev->conns[i];
-		if (_coresight_build_path(conn->child_dev, path) == 0) {
+		struct coresight_device *child_dev = csdev->conns[i].child_dev;
+
+		if (child_dev && _coresight_build_path(child_dev, path) == 0) {
 			found = true;
 			break;
 		}
@@ -425,6 +425,7 @@ out:
 struct list_head *coresight_build_path(struct coresight_device *csdev)
 {
 	struct list_head *path;
+	int rc;
 
 	path = kzalloc(sizeof(struct list_head), GFP_KERNEL);
 	if (!path)
@@ -432,9 +433,10 @@ struct list_head *coresight_build_path(struct coresight_device *csdev)
 
 	INIT_LIST_HEAD(path);
 
-	if (_coresight_build_path(csdev, path)) {
+	rc = _coresight_build_path(csdev, path);
+	if (rc) {
 		kfree(path);
-		path = NULL;
+		return ERR_PTR(rc);
 	}
 
 	return path;
@@ -507,8 +509,9 @@ int coresight_enable(struct coresight_device *csdev)
 		goto out;
 
 	path = coresight_build_path(csdev);
-	if (!path) {
+	if (IS_ERR(path)) {
 		pr_err("building path(s) failed\n");
+		ret = PTR_ERR(path);
 		goto out;
 	}
 
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 64b1208bca5e..4a60ad214747 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -245,6 +245,13 @@ struct i801_priv {
 	struct platform_device *mux_pdev;
 #endif
 	struct platform_device *tco_pdev;
+
+	/*
+	 * If set to true the host controller registers are reserved for
+	 * ACPI AML use. Protected by acpi_lock.
+	 */
+	bool acpi_reserved;
+	struct mutex acpi_lock;
 };
 
 #define FEATURE_SMBUS_PEC	(1 << 0)
@@ -718,6 +725,12 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
 	int ret = 0, xact = 0;
 	struct i801_priv *priv = i2c_get_adapdata(adap);
 
+	mutex_lock(&priv->acpi_lock);
+	if (priv->acpi_reserved) {
+		mutex_unlock(&priv->acpi_lock);
+		return -EBUSY;
+	}
+
 	pm_runtime_get_sync(&priv->pci_dev->dev);
 
 	hwpec = (priv->features & FEATURE_SMBUS_PEC) && (flags & I2C_CLIENT_PEC)
@@ -820,6 +833,7 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
 out:
 	pm_runtime_mark_last_busy(&priv->pci_dev->dev);
 	pm_runtime_put_autosuspend(&priv->pci_dev->dev);
+	mutex_unlock(&priv->acpi_lock);
 	return ret;
 }
 
@@ -1257,6 +1271,83 @@ static void i801_add_tco(struct i801_priv *priv)
 	priv->tco_pdev = pdev;
 }
 
+#ifdef CONFIG_ACPI
+static acpi_status
+i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits,
+		     u64 *value, void *handler_context, void *region_context)
+{
+	struct i801_priv *priv = handler_context;
+	struct pci_dev *pdev = priv->pci_dev;
+	acpi_status status;
+
+	/*
+	 * Once BIOS AML code touches the OpRegion we warn and inhibit any
+	 * further access from the driver itself. This device is now owned
+	 * by the system firmware.
+	 */
+	mutex_lock(&priv->acpi_lock);
+
+	if (!priv->acpi_reserved) {
+		priv->acpi_reserved = true;
+
+		dev_warn(&pdev->dev, "BIOS is accessing SMBus registers\n");
+		dev_warn(&pdev->dev, "Driver SMBus register access inhibited\n");
+
+		/*
+		 * BIOS is accessing the host controller so prevent it from
+		 * suspending automatically from now on.
+		 */
+		pm_runtime_get_sync(&pdev->dev);
+	}
+
+	if ((function & ACPI_IO_MASK) == ACPI_READ)
+		status = acpi_os_read_port(address, (u32 *)value, bits);
+	else
+		status = acpi_os_write_port(address, (u32)*value, bits);
+
+	mutex_unlock(&priv->acpi_lock);
+
+	return status;
+}
+
+static int i801_acpi_probe(struct i801_priv *priv)
+{
+	struct acpi_device *adev;
+	acpi_status status;
+
+	adev = ACPI_COMPANION(&priv->pci_dev->dev);
+	if (adev) {
+		status = acpi_install_address_space_handler(adev->handle,
+				ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler,
+				NULL, priv);
+		if (ACPI_SUCCESS(status))
+			return 0;
+	}
+
+	return acpi_check_resource_conflict(&priv->pci_dev->resource[SMBBAR]);
+}
+
+static void i801_acpi_remove(struct i801_priv *priv)
+{
+	struct acpi_device *adev;
+
+	adev = ACPI_COMPANION(&priv->pci_dev->dev);
+	if (!adev)
+		return;
+
+	acpi_remove_address_space_handler(adev->handle,
+		ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler);
+
+	mutex_lock(&priv->acpi_lock);
+	if (priv->acpi_reserved)
+		pm_runtime_put(&priv->pci_dev->dev);
+	mutex_unlock(&priv->acpi_lock);
+}
+#else
+static inline int i801_acpi_probe(struct i801_priv *priv) { return 0; }
+static inline void i801_acpi_remove(struct i801_priv *priv) { }
+#endif
+
 static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
 	unsigned char temp;
@@ -1274,6 +1365,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	priv->adapter.dev.parent = &dev->dev;
 	ACPI_COMPANION_SET(&priv->adapter.dev, ACPI_COMPANION(&dev->dev));
 	priv->adapter.retries = 3;
+	mutex_init(&priv->acpi_lock);
 
 	priv->pci_dev = dev;
 	switch (dev->device) {
@@ -1336,10 +1428,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		return -ENODEV;
 	}
 
-	err = acpi_check_resource_conflict(&dev->resource[SMBBAR]);
-	if (err) {
+	if (i801_acpi_probe(priv))
 		return -ENODEV;
-	}
 
 	err = pcim_iomap_regions(dev, 1 << SMBBAR,
 				 dev_driver_string(&dev->dev));
@@ -1348,6 +1438,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 			"Failed to request SMBus region 0x%lx-0x%Lx\n",
 			priv->smba,
 			(unsigned long long)pci_resource_end(dev, SMBBAR));
+		i801_acpi_remove(priv);
 		return err;
 	}
 
@@ -1412,6 +1503,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	err = i2c_add_adapter(&priv->adapter);
 	if (err) {
 		dev_err(&dev->dev, "Failed to add SMBus adapter\n");
+		i801_acpi_remove(priv);
 		return err;
 	}
 
@@ -1438,6 +1530,7 @@ static void i801_remove(struct pci_dev *dev)
 
 	i801_del_mux(priv);
 	i2c_del_adapter(&priv->adapter);
+	i801_acpi_remove(priv);
 	pci_write_config_byte(dev, SMBHSTCFG, priv->original_hstcfg);
 
 	platform_device_unregister(priv->tco_pdev);
diff --git a/drivers/i2c/busses/i2c-octeon.c b/drivers/i2c/busses/i2c-octeon.c
index aa5f01efd826..30ae35146723 100644
--- a/drivers/i2c/busses/i2c-octeon.c
+++ b/drivers/i2c/busses/i2c-octeon.c
@@ -934,8 +934,15 @@ static int octeon_i2c_read(struct octeon_i2c *i2c, int target,
 		return result;
 
 	for (i = 0; i < length; i++) {
-		/* for the last byte TWSI_CTL_AAK must not be set */
-		if (i + 1 == length)
+		/*
+		 * For the last byte to receive TWSI_CTL_AAK must not be set.
+		 *
+		 * A special case is I2C_M_RECV_LEN where we don't know the
+		 * additional length yet. If recv_len is set we assume we're
+		 * not reading the final byte and therefore need to set
+		 * TWSI_CTL_AAK.
+		 */
+		if ((i + 1 == length) && !(recv_len && i == 0))
 			final_read = true;
 
 		/* clear iflg to allow next event */
@@ -950,12 +957,8 @@ static int octeon_i2c_read(struct octeon_i2c *i2c, int target,
 
 		data[i] = octeon_i2c_data_read(i2c);
 		if (recv_len && i == 0) {
-			if (data[i] > I2C_SMBUS_BLOCK_MAX + 1) {
-				dev_err(i2c->dev,
-					"%s: read len > I2C_SMBUS_BLOCK_MAX %d\n",
-					__func__, data[i]);
+			if (data[i] > I2C_SMBUS_BLOCK_MAX + 1)
 				return -EPROTO;
-			}
 			length += data[i];
 		}
 
diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c
index 6773cadf7c9f..26e7c5187a58 100644
--- a/drivers/i2c/muxes/i2c-mux-reg.c
+++ b/drivers/i2c/muxes/i2c-mux-reg.c
@@ -260,6 +260,7 @@ static struct platform_driver i2c_mux_reg_driver = {
 	.remove	= i2c_mux_reg_remove,
 	.driver	= {
 		.name	= "i2c-mux-reg",
+		.of_match_table = of_match_ptr(i2c_mux_reg_of_match),
 	},
 };
 
diff --git a/drivers/iio/accel/st_accel_buffer.c b/drivers/iio/accel/st_accel_buffer.c
index a1e642ee13d6..7fddc137e91e 100644
--- a/drivers/iio/accel/st_accel_buffer.c
+++ b/drivers/iio/accel/st_accel_buffer.c
@@ -91,7 +91,7 @@ static const struct iio_buffer_setup_ops st_accel_buffer_setup_ops = {
 
 int st_accel_allocate_ring(struct iio_dev *indio_dev)
 {
-	return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+	return iio_triggered_buffer_setup(indio_dev, NULL,
 		&st_sensors_trigger_handler, &st_accel_buffer_setup_ops);
 }
 
diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c
index dc73f2d85e6d..4d95bfc4786c 100644
--- a/drivers/iio/accel/st_accel_core.c
+++ b/drivers/iio/accel/st_accel_core.c
@@ -741,6 +741,7 @@ static const struct iio_info accel_info = {
 static const struct iio_trigger_ops st_accel_trigger_ops = {
 	.owner = THIS_MODULE,
 	.set_trigger_state = ST_ACCEL_TRIGGER_SET_STATE,
+	.validate_device = st_sensors_validate_device,
 };
 #define ST_ACCEL_TRIGGER_OPS (&st_accel_trigger_ops)
 #else
diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c
index c55898543a47..f1693dbebb8a 100644
--- a/drivers/iio/common/st_sensors/st_sensors_buffer.c
+++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c
@@ -57,31 +57,20 @@ irqreturn_t st_sensors_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct st_sensor_data *sdata = iio_priv(indio_dev);
+	s64 timestamp;
 
-	/* If we have a status register, check if this IRQ came from us */
-	if (sdata->sensor_settings->drdy_irq.addr_stat_drdy) {
-		u8 status;
-
-		len = sdata->tf->read_byte(&sdata->tb, sdata->dev,
-			   sdata->sensor_settings->drdy_irq.addr_stat_drdy,
-			   &status);
-		if (len < 0)
-			dev_err(sdata->dev, "could not read channel status\n");
-
-		/*
-		 * If this was not caused by any channels on this sensor,
-		 * return IRQ_NONE
-		 */
-		if (!(status & (u8)indio_dev->active_scan_mask[0]))
-			return IRQ_NONE;
-	}
+	/* If we do timetamping here, do it before reading the values */
+	if (sdata->hw_irq_trigger)
+		timestamp = sdata->hw_timestamp;
+	else
+		timestamp = iio_get_time_ns();
 
 	len = st_sensors_get_buffer_element(indio_dev, sdata->buffer_data);
 	if (len < 0)
 		goto st_sensors_get_buffer_element_error;
 
 	iio_push_to_buffers_with_timestamp(indio_dev, sdata->buffer_data,
-		pf->timestamp);
+					   timestamp);
 
 st_sensors_get_buffer_element_error:
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c
index dffe00692169..9e59c90f6a8d 100644
--- a/drivers/iio/common/st_sensors/st_sensors_core.c
+++ b/drivers/iio/common/st_sensors/st_sensors_core.c
@@ -363,6 +363,11 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev,
 	if (err < 0)
 		return err;
 
+	/* Disable DRDY, this might be still be enabled after reboot. */
+	err = st_sensors_set_dataready_irq(indio_dev, false);
+	if (err < 0)
+		return err;
+
 	if (sdata->current_fullscale) {
 		err = st_sensors_set_fullscale(indio_dev,
 						sdata->current_fullscale->num);
@@ -424,6 +429,9 @@ int st_sensors_set_dataready_irq(struct iio_dev *indio_dev, bool enable)
 	else
 		drdy_mask = sdata->sensor_settings->drdy_irq.mask_int2;
 
+	/* Flag to the poll function that the hardware trigger is in use */
+	sdata->hw_irq_trigger = enable;
+
 	/* Enable/Disable the interrupt generator for data ready. */
 	err = st_sensors_write_data_with_mask(indio_dev,
 					sdata->sensor_settings->drdy_irq.addr,
diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c
index da72279fcf99..296e4ff19ae8 100644
--- a/drivers/iio/common/st_sensors/st_sensors_trigger.c
+++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c
@@ -17,6 +17,73 @@
 #include <linux/iio/common/st_sensors.h>
 #include "st_sensors_core.h"
 
+/**
+ * st_sensors_irq_handler() - top half of the IRQ-based triggers
+ * @irq: irq number
+ * @p: private handler data
+ */
+irqreturn_t st_sensors_irq_handler(int irq, void *p)
+{
+	struct iio_trigger *trig = p;
+	struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
+	struct st_sensor_data *sdata = iio_priv(indio_dev);
+
+	/* Get the time stamp as close in time as possible */
+	sdata->hw_timestamp = iio_get_time_ns();
+	return IRQ_WAKE_THREAD;
+}
+
+/**
+ * st_sensors_irq_thread() - bottom half of the IRQ-based triggers
+ * @irq: irq number
+ * @p: private handler data
+ */
+irqreturn_t st_sensors_irq_thread(int irq, void *p)
+{
+	struct iio_trigger *trig = p;
+	struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
+	struct st_sensor_data *sdata = iio_priv(indio_dev);
+	int ret;
+
+	/*
+	 * If this trigger is backed by a hardware interrupt and we have a
+	 * status register, check if this IRQ came from us
+	 */
+	if (sdata->sensor_settings->drdy_irq.addr_stat_drdy) {
+		u8 status;
+
+		ret = sdata->tf->read_byte(&sdata->tb, sdata->dev,
+			   sdata->sensor_settings->drdy_irq.addr_stat_drdy,
+			   &status);
+		if (ret < 0) {
+			dev_err(sdata->dev, "could not read channel status\n");
+			goto out_poll;
+		}
+		/*
+		 * the lower bits of .active_scan_mask[0] is directly mapped
+		 * to the channels on the sensor: either bit 0 for
+		 * one-dimensional sensors, or e.g. x,y,z for accelerometers,
+		 * gyroscopes or magnetometers. No sensor use more than 3
+		 * channels, so cut the other status bits here.
+		 */
+		status &= 0x07;
+
+		/*
+		 * If this was not caused by any channels on this sensor,
+		 * return IRQ_NONE
+		 */
+		if (!indio_dev->active_scan_mask)
+			return IRQ_NONE;
+		if (!(status & (u8)indio_dev->active_scan_mask[0]))
+			return IRQ_NONE;
+	}
+
+out_poll:
+	/* It's our IRQ: proceed to handle the register polling */
+	iio_trigger_poll_chained(p);
+	return IRQ_HANDLED;
+}
+
 int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 				const struct iio_trigger_ops *trigger_ops)
 {
@@ -30,6 +97,10 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 		return -ENOMEM;
 	}
 
+	iio_trigger_set_drvdata(sdata->trig, indio_dev);
+	sdata->trig->ops = trigger_ops;
+	sdata->trig->dev.parent = sdata->dev;
+
 	irq = sdata->get_irq_data_ready(indio_dev);
 	irq_trig = irqd_get_trigger_type(irq_get_irq_data(irq));
 	/*
@@ -77,9 +148,12 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 	    sdata->sensor_settings->drdy_irq.addr_stat_drdy)
 		irq_trig |= IRQF_SHARED;
 
-	err = request_threaded_irq(irq,
-			iio_trigger_generic_data_rdy_poll,
-			NULL,
+	/* Let's create an interrupt thread masking the hard IRQ here */
+	irq_trig |= IRQF_ONESHOT;
+
+	err = request_threaded_irq(sdata->get_irq_data_ready(indio_dev),
+			st_sensors_irq_handler,
+			st_sensors_irq_thread,
 			irq_trig,
 			sdata->trig->name,
 			sdata->trig);
@@ -88,10 +162,6 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 		goto iio_trigger_free;
 	}
 
-	iio_trigger_set_drvdata(sdata->trig, indio_dev);
-	sdata->trig->ops = trigger_ops;
-	sdata->trig->dev.parent = sdata->dev;
-
 	err = iio_trigger_register(sdata->trig);
 	if (err < 0) {
 		dev_err(&indio_dev->dev, "failed to register iio trigger.\n");
@@ -119,6 +189,18 @@ void st_sensors_deallocate_trigger(struct iio_dev *indio_dev)
 }
 EXPORT_SYMBOL(st_sensors_deallocate_trigger);
 
+int st_sensors_validate_device(struct iio_trigger *trig,
+			       struct iio_dev *indio_dev)
+{
+	struct iio_dev *indio = iio_trigger_get_drvdata(trig);
+
+	if (indio != indio_dev)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL(st_sensors_validate_device);
+
 MODULE_AUTHOR("Denis Ciocca <[email protected]>");
 MODULE_DESCRIPTION("STMicroelectronics ST-sensors trigger");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig
index e63b957c985f..f7c71da42f15 100644
--- a/drivers/iio/dac/Kconfig
+++ b/drivers/iio/dac/Kconfig
@@ -247,7 +247,7 @@ config MCP4922
 
 config STX104
 	tristate "Apex Embedded Systems STX104 DAC driver"
-	depends on X86 && ISA
+	depends on X86 && ISA_BUS_API
 	help
 	  Say yes here to build support for the 2-channel DAC on the Apex
 	  Embedded Systems STX104 integrated analog PC/104 card. The base port
diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c
index 948f600e7059..69bde5909854 100644
--- a/drivers/iio/dac/ad5592r-base.c
+++ b/drivers/iio/dac/ad5592r-base.c
@@ -525,7 +525,7 @@ static int ad5592r_alloc_channels(struct ad5592r_state *st)
 
 	device_for_each_child_node(st->dev, child) {
 		ret = fwnode_property_read_u32(child, "reg", &reg);
-		if (ret || reg > ARRAY_SIZE(st->channel_modes))
+		if (ret || reg >= ARRAY_SIZE(st->channel_modes))
 			continue;
 
 		ret = fwnode_property_read_u32(child, "adi,mode", &tmp);
diff --git a/drivers/iio/gyro/st_gyro_buffer.c b/drivers/iio/gyro/st_gyro_buffer.c
index d67b17b6a7aa..a5377044e42f 100644
--- a/drivers/iio/gyro/st_gyro_buffer.c
+++ b/drivers/iio/gyro/st_gyro_buffer.c
@@ -91,7 +91,7 @@ static const struct iio_buffer_setup_ops st_gyro_buffer_setup_ops = {
 
 int st_gyro_allocate_ring(struct iio_dev *indio_dev)
 {
-	return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+	return iio_triggered_buffer_setup(indio_dev, NULL,
 		&st_sensors_trigger_handler, &st_gyro_buffer_setup_ops);
 }
 
diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c
index 52a3c87c375c..a8012955a1f6 100644
--- a/drivers/iio/gyro/st_gyro_core.c
+++ b/drivers/iio/gyro/st_gyro_core.c
@@ -409,6 +409,7 @@ static const struct iio_info gyro_info = {
 static const struct iio_trigger_ops st_gyro_trigger_ops = {
 	.owner = THIS_MODULE,
 	.set_trigger_state = ST_GYRO_TRIGGER_SET_STATE,
+	.validate_device = st_sensors_validate_device,
 };
 #define ST_GYRO_TRIGGER_OPS (&st_gyro_trigger_ops)
 #else
diff --git a/drivers/iio/humidity/am2315.c b/drivers/iio/humidity/am2315.c
index 3be6d209a159..11535911a5c6 100644
--- a/drivers/iio/humidity/am2315.c
+++ b/drivers/iio/humidity/am2315.c
@@ -165,10 +165,8 @@ static irqreturn_t am2315_trigger_handler(int irq, void *p)
 	struct am2315_sensor_data sensor_data;
 
 	ret = am2315_read_data(data, &sensor_data);
-	if (ret < 0) {
-		mutex_unlock(&data->lock);
+	if (ret < 0)
 		goto err;
-	}
 
 	mutex_lock(&data->lock);
 	if (*(indio_dev->active_scan_mask) == AM2315_ALL_CHANNEL_MASK) {
diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c
index fa4767613173..a03832a5fc95 100644
--- a/drivers/iio/humidity/hdc100x.c
+++ b/drivers/iio/humidity/hdc100x.c
@@ -55,7 +55,7 @@ static const struct {
 	},
 	{ /* IIO_HUMIDITYRELATIVE channel */
 		.shift = 8,
-		.mask = 2,
+		.mask = 3,
 	},
 };
 
@@ -164,14 +164,14 @@ static int hdc100x_get_measurement(struct hdc100x_data *data,
 		dev_err(&client->dev, "cannot read high byte measurement");
 		return ret;
 	}
-	val = ret << 6;
+	val = ret << 8;
 
 	ret = i2c_smbus_read_byte(client);
 	if (ret < 0) {
 		dev_err(&client->dev, "cannot read low byte measurement");
 		return ret;
 	}
-	val |= ret >> 2;
+	val |= ret;
 
 	return val;
 }
@@ -211,18 +211,18 @@ static int hdc100x_read_raw(struct iio_dev *indio_dev,
 		return IIO_VAL_INT_PLUS_MICRO;
 	case IIO_CHAN_INFO_SCALE:
 		if (chan->type == IIO_TEMP) {
-			*val = 165;
-			*val2 = 65536 >> 2;
+			*val = 165000;
+			*val2 = 65536;
 			return IIO_VAL_FRACTIONAL;
 		} else {
-			*val = 0;
-			*val2 = 10000;
-			return IIO_VAL_INT_PLUS_MICRO;
+			*val = 100;
+			*val2 = 65536;
+			return IIO_VAL_FRACTIONAL;
 		}
 		break;
 	case IIO_CHAN_INFO_OFFSET:
-		*val = -3971;
-		*val2 = 879096;
+		*val = -15887;
+		*val2 = 515151;
 		return IIO_VAL_INT_PLUS_MICRO;
 	default:
 		return -EINVAL;
diff --git a/drivers/iio/imu/bmi160/bmi160_core.c b/drivers/iio/imu/bmi160/bmi160_core.c
index 0bf92b06d7d8..b8a290ec984e 100644
--- a/drivers/iio/imu/bmi160/bmi160_core.c
+++ b/drivers/iio/imu/bmi160/bmi160_core.c
@@ -209,11 +209,11 @@ static const struct  bmi160_scale_item bmi160_scale_table[] = {
 };
 
 static const struct bmi160_odr bmi160_accel_odr[] = {
-	{0x01, 0, 78125},
-	{0x02, 1, 5625},
-	{0x03, 3, 125},
-	{0x04, 6, 25},
-	{0x05, 12, 5},
+	{0x01, 0, 781250},
+	{0x02, 1, 562500},
+	{0x03, 3, 125000},
+	{0x04, 6, 250000},
+	{0x05, 12, 500000},
 	{0x06, 25, 0},
 	{0x07, 50, 0},
 	{0x08, 100, 0},
@@ -229,7 +229,7 @@ static const struct bmi160_odr bmi160_gyro_odr[] = {
 	{0x08, 100, 0},
 	{0x09, 200, 0},
 	{0x0A, 400, 0},
-	{0x0B, 8000, 0},
+	{0x0B, 800, 0},
 	{0x0C, 1600, 0},
 	{0x0D, 3200, 0},
 };
@@ -364,8 +364,8 @@ int bmi160_set_odr(struct bmi160_data *data, enum bmi160_sensor_type t,
 
 	return regmap_update_bits(data->regmap,
 				  bmi160_regs[t].config,
-				  bmi160_odr_table[t].tbl[i].bits,
-				  bmi160_regs[t].config_odr_mask);
+				  bmi160_regs[t].config_odr_mask,
+				  bmi160_odr_table[t].tbl[i].bits);
 }
 
 static int bmi160_get_odr(struct bmi160_data *data, enum bmi160_sensor_type t,
diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index ae2806aafb72..0c52dfe64977 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -210,22 +210,35 @@ static int iio_trigger_attach_poll_func(struct iio_trigger *trig,
 
 	/* Prevent the module from being removed whilst attached to a trigger */
 	__module_get(pf->indio_dev->info->driver_module);
+
+	/* Get irq number */
 	pf->irq = iio_trigger_get_irq(trig);
+	if (pf->irq < 0)
+		goto out_put_module;
+
+	/* Request irq */
 	ret = request_threaded_irq(pf->irq, pf->h, pf->thread,
 				   pf->type, pf->name,
 				   pf);
-	if (ret < 0) {
-		module_put(pf->indio_dev->info->driver_module);
-		return ret;
-	}
+	if (ret < 0)
+		goto out_put_irq;
 
+	/* Enable trigger in driver */
 	if (trig->ops && trig->ops->set_trigger_state && notinuse) {
 		ret = trig->ops->set_trigger_state(trig, true);
 		if (ret < 0)
-			module_put(pf->indio_dev->info->driver_module);
+			goto out_free_irq;
 	}
 
 	return ret;
+
+out_free_irq:
+	free_irq(pf->irq, pf);
+out_put_irq:
+	iio_trigger_put_irq(trig, pf->irq);
+out_put_module:
+	module_put(pf->indio_dev->info->driver_module);
+	return ret;
 }
 
 static int iio_trigger_detach_poll_func(struct iio_trigger *trig,
diff --git a/drivers/iio/light/apds9960.c b/drivers/iio/light/apds9960.c
index b4dbb3912977..651d57b8abbf 100644
--- a/drivers/iio/light/apds9960.c
+++ b/drivers/iio/light/apds9960.c
@@ -1011,6 +1011,7 @@ static int apds9960_probe(struct i2c_client *client,
 
 	iio_device_attach_buffer(indio_dev, buffer);
 
+	indio_dev->dev.parent = &client->dev;
 	indio_dev->info = &apds9960_info;
 	indio_dev->name = APDS9960_DRV_NAME;
 	indio_dev->channels = apds9960_channels;
diff --git a/drivers/iio/light/bh1780.c b/drivers/iio/light/bh1780.c
index 72b364e4aa72..b54dcba05a82 100644
--- a/drivers/iio/light/bh1780.c
+++ b/drivers/iio/light/bh1780.c
@@ -84,7 +84,7 @@ static int bh1780_debugfs_reg_access(struct iio_dev *indio_dev,
 	int ret;
 
 	if (!readval)
-		bh1780_write(bh1780, (u8)reg, (u8)writeval);
+		return bh1780_write(bh1780, (u8)reg, (u8)writeval);
 
 	ret = bh1780_read(bh1780, (u8)reg);
 	if (ret < 0)
@@ -187,7 +187,7 @@ static int bh1780_probe(struct i2c_client *client,
 
 	indio_dev->dev.parent = &client->dev;
 	indio_dev->info = &bh1780_info;
-	indio_dev->name = id->name;
+	indio_dev->name = "bh1780";
 	indio_dev->channels = bh1780_channels;
 	indio_dev->num_channels = ARRAY_SIZE(bh1780_channels);
 	indio_dev->modes = INDIO_DIRECT_MODE;
@@ -226,7 +226,8 @@ static int bh1780_remove(struct i2c_client *client)
 static int bh1780_runtime_suspend(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
-	struct bh1780_data *bh1780 = i2c_get_clientdata(client);
+	struct iio_dev *indio_dev = i2c_get_clientdata(client);
+	struct bh1780_data *bh1780 = iio_priv(indio_dev);
 	int ret;
 
 	ret = bh1780_write(bh1780, BH1780_REG_CONTROL, BH1780_POFF);
@@ -241,7 +242,8 @@ static int bh1780_runtime_suspend(struct device *dev)
 static int bh1780_runtime_resume(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
-	struct bh1780_data *bh1780 = i2c_get_clientdata(client);
+	struct iio_dev *indio_dev = i2c_get_clientdata(client);
+	struct bh1780_data *bh1780 = iio_priv(indio_dev);
 	int ret;
 
 	ret = bh1780_write(bh1780, BH1780_REG_CONTROL, BH1780_PON);
diff --git a/drivers/iio/light/max44000.c b/drivers/iio/light/max44000.c
index e01e58a9bd14..f17cb2ea18f5 100644
--- a/drivers/iio/light/max44000.c
+++ b/drivers/iio/light/max44000.c
@@ -147,7 +147,6 @@ static const struct iio_chan_spec max44000_channels[] = {
 	{
 		.type = IIO_PROXIMITY,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.scan_index = MAX44000_SCAN_INDEX_PRX,
 		.scan_type = {
 			.sign		= 'u',
diff --git a/drivers/iio/magnetometer/st_magn_buffer.c b/drivers/iio/magnetometer/st_magn_buffer.c
index ecd3bd0a9769..0a9e8fadfa9d 100644
--- a/drivers/iio/magnetometer/st_magn_buffer.c
+++ b/drivers/iio/magnetometer/st_magn_buffer.c
@@ -82,7 +82,7 @@ static const struct iio_buffer_setup_ops st_magn_buffer_setup_ops = {
 
 int st_magn_allocate_ring(struct iio_dev *indio_dev)
 {
-	return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+	return iio_triggered_buffer_setup(indio_dev, NULL,
 		&st_sensors_trigger_handler, &st_magn_buffer_setup_ops);
 }
 
diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c
index 62036d2a9956..8250fc322c56 100644
--- a/drivers/iio/magnetometer/st_magn_core.c
+++ b/drivers/iio/magnetometer/st_magn_core.c
@@ -572,6 +572,7 @@ static const struct iio_info magn_info = {
 static const struct iio_trigger_ops st_magn_trigger_ops = {
 	.owner = THIS_MODULE,
 	.set_trigger_state = ST_MAGN_TRIGGER_SET_STATE,
+	.validate_device = st_sensors_validate_device,
 };
 #define ST_MAGN_TRIGGER_OPS (&st_magn_trigger_ops)
 #else
diff --git a/drivers/iio/pressure/bmp280.c b/drivers/iio/pressure/bmp280.c
index 2f1498e12bb2..724452d61846 100644
--- a/drivers/iio/pressure/bmp280.c
+++ b/drivers/iio/pressure/bmp280.c
@@ -879,8 +879,8 @@ static int bmp280_probe(struct i2c_client *client,
 	if (ret < 0)
 		return ret;
 	if (chip_id != id->driver_data) {
-		dev_err(&client->dev, "bad chip id.  expected %x got %x\n",
-			BMP280_CHIP_ID, chip_id);
+		dev_err(&client->dev, "bad chip id.  expected %lx got %x\n",
+			id->driver_data, chip_id);
 		return -EINVAL;
 	}
 
diff --git a/drivers/iio/pressure/st_pressure_buffer.c b/drivers/iio/pressure/st_pressure_buffer.c
index 2ff53f222352..99468d0a64e7 100644
--- a/drivers/iio/pressure/st_pressure_buffer.c
+++ b/drivers/iio/pressure/st_pressure_buffer.c
@@ -82,7 +82,7 @@ static const struct iio_buffer_setup_ops st_press_buffer_setup_ops = {
 
 int st_press_allocate_ring(struct iio_dev *indio_dev)
 {
-	return iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+	return iio_triggered_buffer_setup(indio_dev, NULL,
 		&st_sensors_trigger_handler, &st_press_buffer_setup_ops);
 }
 
diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c
index 9e9b72a8f18f..92a118c3c4ac 100644
--- a/drivers/iio/pressure/st_pressure_core.c
+++ b/drivers/iio/pressure/st_pressure_core.c
@@ -28,15 +28,21 @@
 #include <linux/iio/common/st_sensors.h>
 #include "st_pressure.h"
 
+#define MCELSIUS_PER_CELSIUS			1000
+
+/* Default pressure sensitivity */
 #define ST_PRESS_LSB_PER_MBAR			4096UL
 #define ST_PRESS_KPASCAL_NANO_SCALE		(100000000UL / \
 						 ST_PRESS_LSB_PER_MBAR)
+
+/* Default temperature sensitivity */
 #define ST_PRESS_LSB_PER_CELSIUS		480UL
-#define ST_PRESS_CELSIUS_NANO_SCALE		(1000000000UL / \
-						 ST_PRESS_LSB_PER_CELSIUS)
+#define ST_PRESS_MILLI_CELSIUS_OFFSET		42500UL
+
 #define ST_PRESS_NUMBER_DATA_CHANNELS		1
 
 /* FULLSCALE */
+#define ST_PRESS_FS_AVL_1100MB			1100
 #define ST_PRESS_FS_AVL_1260MB			1260
 
 #define ST_PRESS_1_OUT_XL_ADDR			0x28
@@ -54,9 +60,6 @@
 #define ST_PRESS_LPS331AP_PW_MASK		0x80
 #define ST_PRESS_LPS331AP_FS_ADDR		0x23
 #define ST_PRESS_LPS331AP_FS_MASK		0x30
-#define ST_PRESS_LPS331AP_FS_AVL_1260_VAL	0x00
-#define ST_PRESS_LPS331AP_FS_AVL_1260_GAIN	ST_PRESS_KPASCAL_NANO_SCALE
-#define ST_PRESS_LPS331AP_FS_AVL_TEMP_GAIN	ST_PRESS_CELSIUS_NANO_SCALE
 #define ST_PRESS_LPS331AP_BDU_ADDR		0x20
 #define ST_PRESS_LPS331AP_BDU_MASK		0x04
 #define ST_PRESS_LPS331AP_DRDY_IRQ_ADDR		0x22
@@ -67,9 +70,14 @@
 #define ST_PRESS_LPS331AP_OD_IRQ_ADDR		0x22
 #define ST_PRESS_LPS331AP_OD_IRQ_MASK		0x40
 #define ST_PRESS_LPS331AP_MULTIREAD_BIT		true
-#define ST_PRESS_LPS331AP_TEMP_OFFSET		42500
 
 /* CUSTOM VALUES FOR LPS001WP SENSOR */
+
+/* LPS001WP pressure resolution */
+#define ST_PRESS_LPS001WP_LSB_PER_MBAR		16UL
+/* LPS001WP temperature resolution */
+#define ST_PRESS_LPS001WP_LSB_PER_CELSIUS	64UL
+
 #define ST_PRESS_LPS001WP_WAI_EXP		0xba
 #define ST_PRESS_LPS001WP_ODR_ADDR		0x20
 #define ST_PRESS_LPS001WP_ODR_MASK		0x30
@@ -78,6 +86,8 @@
 #define ST_PRESS_LPS001WP_ODR_AVL_13HZ_VAL	0x03
 #define ST_PRESS_LPS001WP_PW_ADDR		0x20
 #define ST_PRESS_LPS001WP_PW_MASK		0x40
+#define ST_PRESS_LPS001WP_FS_AVL_PRESS_GAIN \
+	(100000000UL / ST_PRESS_LPS001WP_LSB_PER_MBAR)
 #define ST_PRESS_LPS001WP_BDU_ADDR		0x20
 #define ST_PRESS_LPS001WP_BDU_MASK		0x04
 #define ST_PRESS_LPS001WP_MULTIREAD_BIT		true
@@ -94,11 +104,6 @@
 #define ST_PRESS_LPS25H_ODR_AVL_25HZ_VAL	0x04
 #define ST_PRESS_LPS25H_PW_ADDR			0x20
 #define ST_PRESS_LPS25H_PW_MASK			0x80
-#define ST_PRESS_LPS25H_FS_ADDR			0x00
-#define ST_PRESS_LPS25H_FS_MASK			0x00
-#define ST_PRESS_LPS25H_FS_AVL_1260_VAL		0x00
-#define ST_PRESS_LPS25H_FS_AVL_1260_GAIN	ST_PRESS_KPASCAL_NANO_SCALE
-#define ST_PRESS_LPS25H_FS_AVL_TEMP_GAIN	ST_PRESS_CELSIUS_NANO_SCALE
 #define ST_PRESS_LPS25H_BDU_ADDR		0x20
 #define ST_PRESS_LPS25H_BDU_MASK		0x04
 #define ST_PRESS_LPS25H_DRDY_IRQ_ADDR		0x23
@@ -109,7 +114,6 @@
 #define ST_PRESS_LPS25H_OD_IRQ_ADDR		0x22
 #define ST_PRESS_LPS25H_OD_IRQ_MASK		0x40
 #define ST_PRESS_LPS25H_MULTIREAD_BIT		true
-#define ST_PRESS_LPS25H_TEMP_OFFSET		42500
 #define ST_PRESS_LPS25H_OUT_XL_ADDR		0x28
 #define ST_TEMP_LPS25H_OUT_L_ADDR		0x2b
 
@@ -161,7 +165,9 @@ static const struct iio_chan_spec st_press_lps001wp_channels[] = {
 			.storagebits = 16,
 			.endianness = IIO_LE,
 		},
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+		.info_mask_separate =
+			BIT(IIO_CHAN_INFO_RAW) |
+			BIT(IIO_CHAN_INFO_SCALE),
 		.modified = 0,
 	},
 	{
@@ -177,7 +183,7 @@ static const struct iio_chan_spec st_press_lps001wp_channels[] = {
 		},
 		.info_mask_separate =
 			BIT(IIO_CHAN_INFO_RAW) |
-			BIT(IIO_CHAN_INFO_OFFSET),
+			BIT(IIO_CHAN_INFO_SCALE),
 		.modified = 0,
 	},
 	IIO_CHAN_SOFT_TIMESTAMP(1)
@@ -212,11 +218,14 @@ static const struct st_sensor_settings st_press_sensors_settings[] = {
 			.addr = ST_PRESS_LPS331AP_FS_ADDR,
 			.mask = ST_PRESS_LPS331AP_FS_MASK,
 			.fs_avl = {
+				/*
+				 * Pressure and temperature sensitivity values
+				 * as defined in table 3 of LPS331AP datasheet.
+				 */
 				[0] = {
 					.num = ST_PRESS_FS_AVL_1260MB,
-					.value = ST_PRESS_LPS331AP_FS_AVL_1260_VAL,
-					.gain = ST_PRESS_LPS331AP_FS_AVL_1260_GAIN,
-					.gain2 = ST_PRESS_LPS331AP_FS_AVL_TEMP_GAIN,
+					.gain = ST_PRESS_KPASCAL_NANO_SCALE,
+					.gain2 = ST_PRESS_LSB_PER_CELSIUS,
 				},
 			},
 		},
@@ -261,7 +270,17 @@ static const struct st_sensor_settings st_press_sensors_settings[] = {
 			.value_off = ST_SENSORS_DEFAULT_POWER_OFF_VALUE,
 		},
 		.fs = {
-			.addr = 0,
+			.fs_avl = {
+				/*
+				 * Pressure and temperature resolution values
+				 * as defined in table 3 of LPS001WP datasheet.
+				 */
+				[0] = {
+					.num = ST_PRESS_FS_AVL_1100MB,
+					.gain = ST_PRESS_LPS001WP_FS_AVL_PRESS_GAIN,
+					.gain2 = ST_PRESS_LPS001WP_LSB_PER_CELSIUS,
+				},
+			},
 		},
 		.bdu = {
 			.addr = ST_PRESS_LPS001WP_BDU_ADDR,
@@ -298,14 +317,15 @@ static const struct st_sensor_settings st_press_sensors_settings[] = {
 			.value_off = ST_SENSORS_DEFAULT_POWER_OFF_VALUE,
 		},
 		.fs = {
-			.addr = ST_PRESS_LPS25H_FS_ADDR,
-			.mask = ST_PRESS_LPS25H_FS_MASK,
 			.fs_avl = {
+				/*
+				 * Pressure and temperature sensitivity values
+				 * as defined in table 3 of LPS25H datasheet.
+				 */
 				[0] = {
 					.num = ST_PRESS_FS_AVL_1260MB,
-					.value = ST_PRESS_LPS25H_FS_AVL_1260_VAL,
-					.gain = ST_PRESS_LPS25H_FS_AVL_1260_GAIN,
-					.gain2 = ST_PRESS_LPS25H_FS_AVL_TEMP_GAIN,
+					.gain = ST_PRESS_KPASCAL_NANO_SCALE,
+					.gain2 = ST_PRESS_LSB_PER_CELSIUS,
 				},
 			},
 		},
@@ -364,26 +384,26 @@ static int st_press_read_raw(struct iio_dev *indio_dev,
 
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SCALE:
-		*val = 0;
-
 		switch (ch->type) {
 		case IIO_PRESSURE:
+			*val = 0;
 			*val2 = press_data->current_fullscale->gain;
-			break;
+			return IIO_VAL_INT_PLUS_NANO;
 		case IIO_TEMP:
+			*val = MCELSIUS_PER_CELSIUS;
 			*val2 = press_data->current_fullscale->gain2;
-			break;
+			return IIO_VAL_FRACTIONAL;
 		default:
 			err = -EINVAL;
 			goto read_error;
 		}
 
-		return IIO_VAL_INT_PLUS_NANO;
 	case IIO_CHAN_INFO_OFFSET:
 		switch (ch->type) {
 		case IIO_TEMP:
-			*val = 425;
-			*val2 = 10;
+			*val = ST_PRESS_MILLI_CELSIUS_OFFSET *
+			       press_data->current_fullscale->gain2;
+			*val2 = MCELSIUS_PER_CELSIUS;
 			break;
 		default:
 			err = -EINVAL;
@@ -425,6 +445,7 @@ static const struct iio_info press_info = {
 static const struct iio_trigger_ops st_press_trigger_ops = {
 	.owner = THIS_MODULE,
 	.set_trigger_state = ST_PRESS_TRIGGER_SET_STATE,
+	.validate_device = st_sensors_validate_device,
 };
 #define ST_PRESS_TRIGGER_OPS (&st_press_trigger_ops)
 #else
diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c
index f4d29d5dbd5f..e2f926cdcad2 100644
--- a/drivers/iio/proximity/as3935.c
+++ b/drivers/iio/proximity/as3935.c
@@ -64,6 +64,7 @@ struct as3935_state {
 	struct delayed_work work;
 
 	u32 tune_cap;
+	u8 buffer[16]; /* 8-bit data + 56-bit padding + 64-bit timestamp */
 	u8 buf[2] ____cacheline_aligned;
 };
 
@@ -72,7 +73,8 @@ static const struct iio_chan_spec as3935_channels[] = {
 		.type           = IIO_PROXIMITY,
 		.info_mask_separate =
 			BIT(IIO_CHAN_INFO_RAW) |
-			BIT(IIO_CHAN_INFO_PROCESSED),
+			BIT(IIO_CHAN_INFO_PROCESSED) |
+			BIT(IIO_CHAN_INFO_SCALE),
 		.scan_index     = 0,
 		.scan_type = {
 			.sign           = 'u',
@@ -181,7 +183,12 @@ static int as3935_read_raw(struct iio_dev *indio_dev,
 		/* storm out of range */
 		if (*val == AS3935_DATA_MASK)
 			return -EINVAL;
-		*val *= 1000;
+
+		if (m == IIO_CHAN_INFO_PROCESSED)
+			*val *= 1000;
+		break;
+	case IIO_CHAN_INFO_SCALE:
+		*val = 1000;
 		break;
 	default:
 		return -EINVAL;
@@ -206,10 +213,10 @@ static irqreturn_t as3935_trigger_handler(int irq, void *private)
 	ret = as3935_read(st, AS3935_DATA, &val);
 	if (ret)
 		goto err_read;
-	val &= AS3935_DATA_MASK;
-	val *= 1000;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, &val, pf->timestamp);
+	st->buffer[0] = val & AS3935_DATA_MASK;
+	iio_push_to_buffers_with_timestamp(indio_dev, &st->buffer,
+					   pf->timestamp);
 err_read:
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index c2e257d97eff..1a2984c28b95 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -178,6 +178,7 @@ static int write_gid(struct ib_device *ib_dev, u8 port,
 {
 	int ret = 0;
 	struct net_device *old_net_dev;
+	enum ib_gid_type old_gid_type;
 
 	/* in rdma_cap_roce_gid_table, this funciton should be protected by a
 	 * sleep-able lock.
@@ -199,6 +200,7 @@ static int write_gid(struct ib_device *ib_dev, u8 port,
 	}
 
 	old_net_dev = table->data_vec[ix].attr.ndev;
+	old_gid_type = table->data_vec[ix].attr.gid_type;
 	if (old_net_dev && old_net_dev != attr->ndev)
 		dev_put(old_net_dev);
 	/* if modify_gid failed, just delete the old gid */
@@ -207,10 +209,14 @@ static int write_gid(struct ib_device *ib_dev, u8 port,
 		attr = &zattr;
 		table->data_vec[ix].context = NULL;
 	}
-	if (default_gid)
-		table->data_vec[ix].props |= GID_TABLE_ENTRY_DEFAULT;
+
 	memcpy(&table->data_vec[ix].gid, gid, sizeof(*gid));
 	memcpy(&table->data_vec[ix].attr, attr, sizeof(*attr));
+	if (default_gid) {
+		table->data_vec[ix].props |= GID_TABLE_ENTRY_DEFAULT;
+		if (action == GID_TABLE_WRITE_ACTION_DEL)
+			table->data_vec[ix].attr.gid_type = old_gid_type;
+	}
 	if (table->data_vec[ix].attr.ndev &&
 	    table->data_vec[ix].attr.ndev != old_net_dev)
 		dev_hold(table->data_vec[ix].attr.ndev);
@@ -405,7 +411,9 @@ int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u8 port,
 
 	for (ix = 0; ix < table->sz; ix++)
 		if (table->data_vec[ix].attr.ndev == ndev)
-			if (!del_gid(ib_dev, port, table, ix, false))
+			if (!del_gid(ib_dev, port, table, ix,
+				     !!(table->data_vec[ix].props &
+					GID_TABLE_ENTRY_DEFAULT)))
 				deleted = true;
 
 	write_unlock_irq(&table->rwlock);
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 1d92e091e22e..c99525512b34 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -3452,14 +3452,14 @@ static int cm_establish(struct ib_cm_id *cm_id)
 	work->cm_event.event = IB_CM_USER_ESTABLISHED;
 
 	/* Check if the device started its remove_one */
-	spin_lock_irq(&cm.lock);
+	spin_lock_irqsave(&cm.lock, flags);
 	if (!cm_dev->going_down) {
 		queue_delayed_work(cm.wq, &work->work, 0);
 	} else {
 		kfree(work);
 		ret = -ENODEV;
 	}
-	spin_unlock_irq(&cm.lock);
+	spin_unlock_irqrestore(&cm.lock, flags);
 
 out:
 	return ret;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index f0c91ba3178a..ad1b1adcf6f0 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -708,17 +708,6 @@ static void cma_deref_id(struct rdma_id_private *id_priv)
 		complete(&id_priv->comp);
 }
 
-static int cma_disable_callback(struct rdma_id_private *id_priv,
-				enum rdma_cm_state state)
-{
-	mutex_lock(&id_priv->handler_mutex);
-	if (id_priv->state != state) {
-		mutex_unlock(&id_priv->handler_mutex);
-		return -EINVAL;
-	}
-	return 0;
-}
-
 struct rdma_cm_id *rdma_create_id(struct net *net,
 				  rdma_cm_event_handler event_handler,
 				  void *context, enum rdma_port_space ps,
@@ -1671,11 +1660,12 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 	struct rdma_cm_event event;
 	int ret = 0;
 
+	mutex_lock(&id_priv->handler_mutex);
 	if ((ib_event->event != IB_CM_TIMEWAIT_EXIT &&
-		cma_disable_callback(id_priv, RDMA_CM_CONNECT)) ||
+	     id_priv->state != RDMA_CM_CONNECT) ||
 	    (ib_event->event == IB_CM_TIMEWAIT_EXIT &&
-		cma_disable_callback(id_priv, RDMA_CM_DISCONNECT)))
-		return 0;
+	     id_priv->state != RDMA_CM_DISCONNECT))
+		goto out;
 
 	memset(&event, 0, sizeof event);
 	switch (ib_event->event) {
@@ -1870,7 +1860,7 @@ static int cma_check_req_qp_type(struct rdma_cm_id *id, struct ib_cm_event *ib_e
 
 static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 {
-	struct rdma_id_private *listen_id, *conn_id;
+	struct rdma_id_private *listen_id, *conn_id = NULL;
 	struct rdma_cm_event event;
 	struct net_device *net_dev;
 	int offset, ret;
@@ -1884,9 +1874,10 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 		goto net_dev_put;
 	}
 
-	if (cma_disable_callback(listen_id, RDMA_CM_LISTEN)) {
+	mutex_lock(&listen_id->handler_mutex);
+	if (listen_id->state != RDMA_CM_LISTEN) {
 		ret = -ECONNABORTED;
-		goto net_dev_put;
+		goto err1;
 	}
 
 	memset(&event, 0, sizeof event);
@@ -1976,8 +1967,9 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event)
 	struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr;
 	struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr;
 
-	if (cma_disable_callback(id_priv, RDMA_CM_CONNECT))
-		return 0;
+	mutex_lock(&id_priv->handler_mutex);
+	if (id_priv->state != RDMA_CM_CONNECT)
+		goto out;
 
 	memset(&event, 0, sizeof event);
 	switch (iw_event->event) {
@@ -2029,6 +2021,7 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event)
 		return ret;
 	}
 
+out:
 	mutex_unlock(&id_priv->handler_mutex);
 	return ret;
 }
@@ -2039,13 +2032,15 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
 	struct rdma_cm_id *new_cm_id;
 	struct rdma_id_private *listen_id, *conn_id;
 	struct rdma_cm_event event;
-	int ret;
+	int ret = -ECONNABORTED;
 	struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr;
 	struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr;
 
 	listen_id = cm_id->context;
-	if (cma_disable_callback(listen_id, RDMA_CM_LISTEN))
-		return -ECONNABORTED;
+
+	mutex_lock(&listen_id->handler_mutex);
+	if (listen_id->state != RDMA_CM_LISTEN)
+		goto out;
 
 	/* Create a new RDMA id for the new IW CM ID */
 	new_cm_id = rdma_create_id(listen_id->id.route.addr.dev_addr.net,
@@ -3216,8 +3211,9 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id,
 	struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd;
 	int ret = 0;
 
-	if (cma_disable_callback(id_priv, RDMA_CM_CONNECT))
-		return 0;
+	mutex_lock(&id_priv->handler_mutex);
+	if (id_priv->state != RDMA_CM_CONNECT)
+		goto out;
 
 	memset(&event, 0, sizeof event);
 	switch (ib_event->event) {
@@ -3673,12 +3669,13 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast)
 	struct rdma_id_private *id_priv;
 	struct cma_multicast *mc = multicast->context;
 	struct rdma_cm_event event;
-	int ret;
+	int ret = 0;
 
 	id_priv = mc->id_priv;
-	if (cma_disable_callback(id_priv, RDMA_CM_ADDR_BOUND) &&
-	    cma_disable_callback(id_priv, RDMA_CM_ADDR_RESOLVED))
-		return 0;
+	mutex_lock(&id_priv->handler_mutex);
+	if (id_priv->state != RDMA_CM_ADDR_BOUND &&
+	    id_priv->state != RDMA_CM_ADDR_RESOLVED)
+		goto out;
 
 	if (!status)
 		status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey));
@@ -3720,6 +3717,7 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast)
 		return 0;
 	}
 
+out:
 	mutex_unlock(&id_priv->handler_mutex);
 	return 0;
 }
@@ -3878,12 +3876,12 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv,
 	gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num -
 		   rdma_start_port(id_priv->cma_dev->device)];
 	if (addr->sa_family == AF_INET) {
-		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {
+			mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
 			err = cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid,
 					    true);
-		if (!err) {
-			mc->igmp_joined = true;
-			mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
+			if (!err)
+				mc->igmp_joined = true;
 		}
 	} else {
 		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 5516fb070344..5c155fa91eec 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -661,6 +661,9 @@ int ib_query_port(struct ib_device *device,
 	if (err || port_attr->subnet_prefix)
 		return err;
 
+	if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND)
+		return 0;
+
 	err = ib_query_gid(device, port_num, 0, &gid, NULL);
 	if (err)
 		return err;
@@ -1024,7 +1027,8 @@ static int __init ib_core_init(void)
 		goto err_mad;
 	}
 
-	if (ib_add_ibnl_clients()) {
+	ret = ib_add_ibnl_clients();
+	if (ret) {
 		pr_warn("Couldn't register ibnl clients\n");
 		goto err_sa;
 	}
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index 43e3fa27102b..1c41b95cefec 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -506,7 +506,7 @@ int iwpm_add_and_query_mapping_cb(struct sk_buff *skb,
 	if (!nlmsg_request) {
 		pr_info("%s: Could not find a matching request (seq = %u)\n",
 				 __func__, msg_seq);
-			return -EINVAL;
+		return -EINVAL;
 	}
 	pm_msg = nlmsg_request->req_buffer;
 	local_sockaddr = (struct sockaddr_storage *)
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 82fb511112da..2d49228f28b2 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -1638,9 +1638,9 @@ static void remove_mad_reg_req(struct ib_mad_agent_private *agent_priv)
 		/* Now, check to see if there are any methods still in use */
 		if (!check_method_table(method)) {
 			/* If not, release management method table */
-			 kfree(method);
-			 class->method_table[mgmt_class] = NULL;
-			 /* Any management classes left ? */
+			kfree(method);
+			class->method_table[mgmt_class] = NULL;
+			/* Any management classes left ? */
 			if (!check_class_table(class)) {
 				/* If not, release management class table */
 				kfree(class);
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 5e573bb18660..a5793c8f1590 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -889,9 +889,9 @@ static struct attribute *alloc_hsa_lifespan(char *name, u8 port_num)
 static void setup_hw_stats(struct ib_device *device, struct ib_port *port,
 			   u8 port_num)
 {
-	struct attribute_group *hsag = NULL;
+	struct attribute_group *hsag;
 	struct rdma_hw_stats *stats;
-	int i = 0, ret;
+	int i, ret;
 
 	stats = device->alloc_hw_stats(device, port_num);
 
@@ -899,19 +899,22 @@ static void setup_hw_stats(struct ib_device *device, struct ib_port *port,
 		return;
 
 	if (!stats->names || stats->num_counters <= 0)
-		goto err;
+		goto err_free_stats;
 
+	/*
+	 * Two extra attribue elements here, one for the lifespan entry and
+	 * one to NULL terminate the list for the sysfs core code
+	 */
 	hsag = kzalloc(sizeof(*hsag) +
-		       // 1 extra for the lifespan config entry
-		       sizeof(void *) * (stats->num_counters + 1),
+		       sizeof(void *) * (stats->num_counters + 2),
 		       GFP_KERNEL);
 	if (!hsag)
-		return;
+		goto err_free_stats;
 
 	ret = device->get_hw_stats(device, stats, port_num,
 				   stats->num_counters);
 	if (ret != stats->num_counters)
-		goto err;
+		goto err_free_hsag;
 
 	stats->timestamp = jiffies;
 
@@ -922,10 +925,13 @@ static void setup_hw_stats(struct ib_device *device, struct ib_port *port,
 		hsag->attrs[i] = alloc_hsa(i, port_num, stats->names[i]);
 		if (!hsag->attrs[i])
 			goto err;
+		sysfs_attr_init(hsag->attrs[i]);
 	}
 
 	/* treat an error here as non-fatal */
 	hsag->attrs[i] = alloc_hsa_lifespan("lifespan", port_num);
+	if (hsag->attrs[i])
+		sysfs_attr_init(hsag->attrs[i]);
 
 	if (port) {
 		struct kobject *kobj = &port->kobj;
@@ -946,10 +952,12 @@ static void setup_hw_stats(struct ib_device *device, struct ib_port *port,
 	return;
 
 err:
-	kfree(stats);
 	for (; i >= 0; i--)
 		kfree(hsag->attrs[i]);
+err_free_hsag:
 	kfree(hsag);
+err_free_stats:
+	kfree(stats);
 	return;
 }
 
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 1a8babb8ee3c..825021d1008b 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1747,7 +1747,7 @@ static int create_qp(struct ib_uverbs_file *file,
 	struct ib_srq			*srq = NULL;
 	struct ib_qp			*qp;
 	char				*buf;
-	struct ib_qp_init_attr		attr;
+	struct ib_qp_init_attr		attr = {};
 	struct ib_uverbs_ex_create_qp_resp resp;
 	int				ret;
 
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 1d7d4cf442e3..6298f54b4137 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -511,12 +511,16 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
 		ah_attr->grh.dgid = sgid;
 
 		if (!rdma_cap_eth_ah(device, port_num)) {
-			ret = ib_find_cached_gid_by_port(device, &dgid,
-							 IB_GID_TYPE_IB,
-							 port_num, NULL,
-							 &gid_index);
-			if (ret)
-				return ret;
+			if (dgid.global.interface_id != cpu_to_be64(IB_SA_WELL_KNOWN_GUID)) {
+				ret = ib_find_cached_gid_by_port(device, &dgid,
+								 IB_GID_TYPE_IB,
+								 port_num, NULL,
+								 &gid_index);
+				if (ret)
+					return ret;
+			} else {
+				gid_index = 0;
+			}
 		}
 
 		ah_attr->grh.sgid_index = (u8) gid_index;
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 6e7050ab9e16..14d7eeb09be6 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -300,16 +300,15 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node)
 	const struct cpumask *node_mask,
 		*proc_mask = tsk_cpus_allowed(current);
 	struct cpu_mask_set *set = &dd->affinity->proc;
-	char buf[1024];
 
 	/*
 	 * check whether process/context affinity has already
 	 * been set
 	 */
 	if (cpumask_weight(proc_mask) == 1) {
-		scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(proc_mask));
-		hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %s",
-			  current->pid, current->comm, buf);
+		hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %*pbl",
+			  current->pid, current->comm,
+			  cpumask_pr_args(proc_mask));
 		/*
 		 * Mark the pre-set CPU as used. This is atomic so we don't
 		 * need the lock
@@ -318,9 +317,9 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node)
 		cpumask_set_cpu(cpu, &set->used);
 		goto done;
 	} else if (cpumask_weight(proc_mask) < cpumask_weight(&set->mask)) {
-		scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(proc_mask));
-		hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %s",
-			  current->pid, current->comm, buf);
+		hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl",
+			  current->pid, current->comm,
+			  cpumask_pr_args(proc_mask));
 		goto done;
 	}
 
@@ -356,8 +355,8 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node)
 	cpumask_or(intrs, intrs, (dd->affinity->rcv_intr.gen ?
 				  &dd->affinity->rcv_intr.mask :
 				  &dd->affinity->rcv_intr.used));
-	scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(intrs));
-	hfi1_cdbg(PROC, "CPUs used by interrupts: %s", buf);
+	hfi1_cdbg(PROC, "CPUs used by interrupts: %*pbl",
+		  cpumask_pr_args(intrs));
 
 	/*
 	 * If we don't have a NUMA node requested, preference is towards
@@ -366,18 +365,16 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node)
 	if (node == -1)
 		node = dd->node;
 	node_mask = cpumask_of_node(node);
-	scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(node_mask));
-	hfi1_cdbg(PROC, "device on NUMA %u, CPUs %s", node, buf);
+	hfi1_cdbg(PROC, "device on NUMA %u, CPUs %*pbl", node,
+		  cpumask_pr_args(node_mask));
 
 	/* diff will hold all unused cpus */
 	cpumask_andnot(diff, &set->mask, &set->used);
-	scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(diff));
-	hfi1_cdbg(PROC, "unused CPUs (all) %s", buf);
+	hfi1_cdbg(PROC, "unused CPUs (all) %*pbl", cpumask_pr_args(diff));
 
 	/* get cpumask of available CPUs on preferred NUMA */
 	cpumask_and(mask, diff, node_mask);
-	scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(mask));
-	hfi1_cdbg(PROC, "available cpus on NUMA %s", buf);
+	hfi1_cdbg(PROC, "available cpus on NUMA %*pbl", cpumask_pr_args(mask));
 
 	/*
 	 * At first, we don't want to place processes on the same
@@ -395,8 +392,8 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node)
 		cpumask_andnot(diff, &set->mask, &set->used);
 		cpumask_andnot(mask, diff, node_mask);
 	}
-	scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(mask));
-	hfi1_cdbg(PROC, "possible CPUs for process %s", buf);
+	hfi1_cdbg(PROC, "possible CPUs for process %*pbl",
+		  cpumask_pr_args(mask));
 
 	cpu = cpumask_first(mask);
 	if (cpu >= nr_cpu_ids) /* empty */
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 3b876da745a1..f5de85178055 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1037,7 +1037,7 @@ static void dc_shutdown(struct hfi1_devdata *);
 static void dc_start(struct hfi1_devdata *);
 static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp,
 			   unsigned int *np);
-static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd);
+static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd);
 
 /*
  * Error interrupt table entry.  This is used as input to the interrupt
@@ -6962,8 +6962,6 @@ void handle_link_down(struct work_struct *work)
 	}
 
 	reset_neighbor_info(ppd);
-	if (ppd->mgmt_allowed)
-		remove_full_mgmt_pkey(ppd);
 
 	/* disable the port */
 	clear_rcvctrl(ppd->dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
@@ -7070,12 +7068,16 @@ static void add_full_mgmt_pkey(struct hfi1_pportdata *ppd)
 			    __func__, ppd->pkeys[2], FULL_MGMT_P_KEY);
 	ppd->pkeys[2] = FULL_MGMT_P_KEY;
 	(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+	hfi1_event_pkey_change(ppd->dd, ppd->port);
 }
 
-static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd)
+static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd)
 {
-	ppd->pkeys[2] = 0;
-	(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+	if (ppd->pkeys[2] != 0) {
+		ppd->pkeys[2] = 0;
+		(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+		hfi1_event_pkey_change(ppd->dd, ppd->port);
+	}
 }
 
 /*
@@ -7832,8 +7834,8 @@ static void handle_dcc_err(struct hfi1_devdata *dd, u32 unused, u64 reg)
 			 * save first 2 flits in the packet that caused
 			 * the error
 			 */
-			 dd->err_info_rcvport.packet_flit1 = hdr0;
-			 dd->err_info_rcvport.packet_flit2 = hdr1;
+			dd->err_info_rcvport.packet_flit1 = hdr0;
+			dd->err_info_rcvport.packet_flit2 = hdr1;
 		}
 		switch (info) {
 		case 1:
@@ -9168,6 +9170,13 @@ int start_link(struct hfi1_pportdata *ppd)
 		return 0;
 	}
 
+	/*
+	 * FULL_MGMT_P_KEY is cleared from the pkey table, so that the
+	 * pkey table can be configured properly if the HFI unit is connected
+	 * to switch port with MgmtAllowed=NO
+	 */
+	clear_full_mgmt_pkey(ppd);
+
 	return set_link_state(ppd, HLS_DN_POLL);
 }
 
@@ -9777,7 +9786,7 @@ static void set_send_length(struct hfi1_pportdata *ppd)
 	u64 len1 = 0, len2 = (((dd->vld[15].mtu + max_hb) >> 2)
 			      & SEND_LEN_CHECK1_LEN_VL15_MASK) <<
 		SEND_LEN_CHECK1_LEN_VL15_SHIFT;
-	int i;
+	int i, j;
 	u32 thres;
 
 	for (i = 0; i < ppd->vls_supported; i++) {
@@ -9801,7 +9810,10 @@ static void set_send_length(struct hfi1_pportdata *ppd)
 			    sc_mtu_to_threshold(dd->vld[i].sc,
 						dd->vld[i].mtu,
 						dd->rcd[0]->rcvhdrqentsize));
-		sc_set_cr_threshold(dd->vld[i].sc, thres);
+		for (j = 0; j < INIT_SC_PER_VL; j++)
+			sc_set_cr_threshold(
+					pio_select_send_context_vl(dd, j, i),
+					    thres);
 	}
 	thres = min(sc_percent_to_threshold(dd->vld[15].sc, 50),
 		    sc_mtu_to_threshold(dd->vld[15].sc,
@@ -11906,7 +11918,7 @@ static void update_synth_timer(unsigned long opaque)
 		hfi1_cdbg(CNTR, "[%d] No update necessary", dd->unit);
 	}
 
-mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME);
+	mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME);
 }
 
 #define C_MAX_NAME 13 /* 12 chars + one for /0 */
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 7a5b0e676cc7..c702a009608f 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -203,6 +203,9 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
 
 	switch (cmd) {
 	case HFI1_IOCTL_ASSIGN_CTXT:
+		if (uctxt)
+			return -EINVAL;
+
 		if (copy_from_user(&uinfo,
 				   (struct hfi1_user_info __user *)arg,
 				   sizeof(uinfo)))
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 5cc492e5776d..eed971ccd2a1 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1337,7 +1337,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd)
 		dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
 				  (void *)dd->rcvhdrtail_dummy_kvaddr,
 				  dd->rcvhdrtail_dummy_physaddr);
-				  dd->rcvhdrtail_dummy_kvaddr = NULL;
+		dd->rcvhdrtail_dummy_kvaddr = NULL;
 	}
 
 	for (ctxt = 0; tmp && ctxt < dd->num_rcv_contexts; ctxt++) {
@@ -1383,7 +1383,7 @@ static void postinit_cleanup(struct hfi1_devdata *dd)
 static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int ret = 0, j, pidx, initfail;
-	struct hfi1_devdata *dd = NULL;
+	struct hfi1_devdata *dd = ERR_PTR(-EINVAL);
 	struct hfi1_pportdata *ppd;
 
 	/* First, lock the non-writable module parameters */
diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c
index 219029576ba0..fca07a1d6c28 100644
--- a/drivers/infiniband/hw/hfi1/mad.c
+++ b/drivers/infiniband/hw/hfi1/mad.c
@@ -78,6 +78,16 @@ static inline void clear_opa_smp_data(struct opa_smp *smp)
 	memset(data, 0, size);
 }
 
+void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port)
+{
+	struct ib_event event;
+
+	event.event = IB_EVENT_PKEY_CHANGE;
+	event.device = &dd->verbs_dev.rdi.ibdev;
+	event.element.port_num = port;
+	ib_dispatch_event(&event);
+}
+
 static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len)
 {
 	struct ib_mad_send_buf *send_buf;
@@ -1418,15 +1428,10 @@ static int set_pkeys(struct hfi1_devdata *dd, u8 port, u16 *pkeys)
 	}
 
 	if (changed) {
-		struct ib_event event;
-
 		(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
-
-		event.event = IB_EVENT_PKEY_CHANGE;
-		event.device = &dd->verbs_dev.rdi.ibdev;
-		event.element.port_num = port;
-		ib_dispatch_event(&event);
+		hfi1_event_pkey_change(dd, port);
 	}
+
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/mad.h b/drivers/infiniband/hw/hfi1/mad.h
index 55ee08675333..8b734aaae88a 100644
--- a/drivers/infiniband/hw/hfi1/mad.h
+++ b/drivers/infiniband/hw/hfi1/mad.h
@@ -434,4 +434,6 @@ struct sc2vlnt {
 		    COUNTER_MASK(1, 3) | \
 		    COUNTER_MASK(1, 4))
 
+void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port);
+
 #endif				/* _HFI1_MAD_H */
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index d5edb1afbb8f..d4022450b73f 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -995,7 +995,7 @@ static void sc_wait_for_packet_egress(struct send_context *sc, int pause)
 		/* counter is reset if occupancy count changes */
 		if (reg != reg_prev)
 			loop = 0;
-		if (loop > 500) {
+		if (loop > 50000) {
 			/* timed out - bounce the link */
 			dd_dev_err(dd,
 				   "%s: context %u(%u) timeout waiting for packets to egress, remaining count %u, bouncing link\n",
@@ -1798,6 +1798,21 @@ static void pio_map_rcu_callback(struct rcu_head *list)
 }
 
 /*
+ * Set credit return threshold for the kernel send context
+ */
+static void set_threshold(struct hfi1_devdata *dd, int scontext, int i)
+{
+	u32 thres;
+
+	thres = min(sc_percent_to_threshold(dd->kernel_send_context[scontext],
+					    50),
+		    sc_mtu_to_threshold(dd->kernel_send_context[scontext],
+					dd->vld[i].mtu,
+					dd->rcd[0]->rcvhdrqentsize));
+	sc_set_cr_threshold(dd->kernel_send_context[scontext], thres);
+}
+
+/*
  * pio_map_init - called when #vls change
  * @dd: hfi1_devdata
  * @port: port number
@@ -1872,11 +1887,16 @@ int pio_map_init(struct hfi1_devdata *dd, u8 port, u8 num_vls, u8 *vl_scontexts)
 			if (!newmap->map[i])
 				goto bail;
 			newmap->map[i]->mask = (1 << ilog2(sz)) - 1;
-			/* assign send contexts */
+			/*
+			 * assign send contexts and
+			 * adjust credit return threshold
+			 */
 			for (j = 0; j < sz; j++) {
-				if (dd->kernel_send_context[scontext])
+				if (dd->kernel_send_context[scontext]) {
 					newmap->map[i]->ksc[j] =
 					dd->kernel_send_context[scontext];
+					set_threshold(dd, scontext, i);
+				}
 				if (++scontext >= first_scontext +
 						  vl_scontexts[i])
 					/* wrap back to first send context */
diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c
index 2441669f0817..9fb561682c66 100644
--- a/drivers/infiniband/hw/hfi1/qsfp.c
+++ b/drivers/infiniband/hw/hfi1/qsfp.c
@@ -579,7 +579,8 @@ int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len)
 
 	if (ppd->qsfp_info.cache_valid) {
 		if (QSFP_IS_CU(cache[QSFP_MOD_TECH_OFFS]))
-			sprintf(lenstr, "%dM ", cache[QSFP_MOD_LEN_OFFS]);
+			snprintf(lenstr, sizeof(lenstr), "%dM ",
+				 cache[QSFP_MOD_LEN_OFFS]);
 
 		power_byte = cache[QSFP_MOD_PWR_OFFS];
 		sofar += scnprintf(buf + sofar, len - sofar, "PWR:%.3sW\n",
diff --git a/drivers/infiniband/hw/hfi1/trace.c b/drivers/infiniband/hw/hfi1/trace.c
index 79b2952c0dfb..4cfb13771897 100644
--- a/drivers/infiniband/hw/hfi1/trace.c
+++ b/drivers/infiniband/hw/hfi1/trace.c
@@ -214,19 +214,6 @@ const char *print_u32_array(
 	return ret;
 }
 
-const char *print_u64_array(
-	struct trace_seq *p,
-	u64 *arr, int len)
-{
-	int i;
-	const char *ret = trace_seq_buffer_ptr(p);
-
-	for (i = 0; i < len; i++)
-		trace_seq_printf(p, "%s0x%016llx", i == 0 ? "" : " ", arr[i]);
-	trace_seq_putc(p, 0);
-	return ret;
-}
-
 __hfi1_trace_fn(PKT);
 __hfi1_trace_fn(PROC);
 __hfi1_trace_fn(SDMA);
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index 29f4795f866c..47ffd273ecbd 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -183,7 +183,7 @@ struct user_sdma_iovec {
 	struct sdma_mmu_node *node;
 };
 
-#define SDMA_CACHE_NODE_EVICT BIT(0)
+#define SDMA_CACHE_NODE_EVICT 0
 
 struct sdma_mmu_node {
 	struct mmu_rb_node rb;
@@ -1355,11 +1355,11 @@ static int set_txreq_header(struct user_sdma_request *req,
 		 */
 		SDMA_DBG(req, "TID offset %ubytes %uunits om%u",
 			 req->tidoffset, req->tidoffset / req->omfactor,
-			 !!(req->omfactor - KDETH_OM_SMALL));
+			 req->omfactor != KDETH_OM_SMALL);
 		KDETH_SET(hdr->kdeth.ver_tid_offset, OFFSET,
 			  req->tidoffset / req->omfactor);
 		KDETH_SET(hdr->kdeth.ver_tid_offset, OM,
-			  !!(req->omfactor - KDETH_OM_SMALL));
+			  req->omfactor != KDETH_OM_SMALL);
 	}
 done:
 	trace_hfi1_sdma_user_header(pq->dd, pq->ctxt, pq->subctxt,
diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.c b/drivers/infiniband/hw/hfi1/verbs_txreq.c
index bc95c4112c61..d8fb056526f8 100644
--- a/drivers/infiniband/hw/hfi1/verbs_txreq.c
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.c
@@ -92,11 +92,10 @@ void hfi1_put_txreq(struct verbs_txreq *tx)
 
 struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
 				struct rvt_qp *qp)
+	__must_hold(&qp->s_lock)
 {
 	struct verbs_txreq *tx = ERR_PTR(-EBUSY);
-	unsigned long flags;
 
-	spin_lock_irqsave(&qp->s_lock, flags);
 	write_seqlock(&dev->iowait_lock);
 	if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) {
 		struct hfi1_qp_priv *priv;
@@ -116,7 +115,6 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
 	}
 out:
 	write_sequnlock(&dev->iowait_lock);
-	spin_unlock_irqrestore(&qp->s_lock, flags);
 	return tx;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h
index 1cf69b2fe4a5..a1d6e0807f97 100644
--- a/drivers/infiniband/hw/hfi1/verbs_txreq.h
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h
@@ -73,6 +73,7 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
 
 static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev,
 					    struct rvt_qp *qp)
+	__must_hold(&qp->slock)
 {
 	struct verbs_txreq *tx;
 	struct hfi1_qp_priv *priv = qp->priv;
diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h
index 8b9532034558..b738acdb9b02 100644
--- a/drivers/infiniband/hw/i40iw/i40iw.h
+++ b/drivers/infiniband/hw/i40iw/i40iw.h
@@ -113,6 +113,8 @@
 
 #define IW_HMC_OBJ_TYPE_NUM ARRAY_SIZE(iw_hmc_obj_types)
 #define IW_CFG_FPM_QP_COUNT		32768
+#define I40IW_MAX_PAGES_PER_FMR		512
+#define I40IW_MIN_PAGES_PER_FMR		1
 
 #define I40IW_MTU_TO_MSS		40
 #define I40IW_DEFAULT_MSS		1460
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 02a735b64208..33959ed14563 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -79,6 +79,7 @@ static int i40iw_query_device(struct ib_device *ibdev,
 	props->max_qp_init_rd_atom = props->max_qp_rd_atom;
 	props->atomic_cap = IB_ATOMIC_NONE;
 	props->max_map_per_fmr = 1;
+	props->max_fast_reg_page_list_len = I40IW_MAX_PAGES_PER_FMR;
 	return 0;
 }
 
@@ -1527,7 +1528,7 @@ static struct ib_mr *i40iw_alloc_mr(struct ib_pd *pd,
 	mutex_lock(&iwdev->pbl_mutex);
 	status = i40iw_get_pble(&iwdev->sc_dev, iwdev->pble_rsrc, palloc, iwmr->page_cnt);
 	mutex_unlock(&iwdev->pbl_mutex);
-	if (!status)
+	if (status)
 		goto err1;
 
 	if (palloc->level != I40IW_LEVEL_1)
@@ -2149,6 +2150,7 @@ static int i40iw_post_send(struct ib_qp *ibqp,
 			struct i40iw_sc_dev *dev = &iwqp->iwdev->sc_dev;
 			struct i40iw_fast_reg_stag_info info;
 
+			memset(&info, 0, sizeof(info));
 			info.access_rights = I40IW_ACCESS_FLAGS_LOCALREAD;
 			info.access_rights |= i40iw_get_user_access(flags);
 			info.stag_key = reg_wr(ib_wr)->key & 0xff;
@@ -2158,10 +2160,14 @@ static int i40iw_post_send(struct ib_qp *ibqp,
 			info.addr_type = I40IW_ADDR_TYPE_VA_BASED;
 			info.va = (void *)(uintptr_t)iwmr->ibmr.iova;
 			info.total_len = iwmr->ibmr.length;
+			info.reg_addr_pa = *(u64 *)palloc->level1.addr;
 			info.first_pm_pbl_index = palloc->level1.idx;
 			info.local_fence = ib_wr->send_flags & IB_SEND_FENCE;
 			info.signaled = ib_wr->send_flags & IB_SEND_SIGNALED;
 
+			if (iwmr->npages > I40IW_MIN_PAGES_PER_FMR)
+				info.chunk_size = 1;
+
 			if (page_shift == 21)
 				info.page_size = 1; /* 2M page */
 
@@ -2327,13 +2333,16 @@ static int i40iw_req_notify_cq(struct ib_cq *ibcq,
 {
 	struct i40iw_cq *iwcq;
 	struct i40iw_cq_uk *ukcq;
-	enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_SOLICITED;
+	unsigned long flags;
+	enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_EVENT;
 
 	iwcq = (struct i40iw_cq *)ibcq;
 	ukcq = &iwcq->sc_cq.cq_uk;
-	if (notify_flags == IB_CQ_NEXT_COMP)
-		cq_notify = IW_CQ_COMPL_EVENT;
+	if (notify_flags == IB_CQ_SOLICITED)
+		cq_notify = IW_CQ_COMPL_SOLICITED;
+	spin_lock_irqsave(&iwcq->lock, flags);
 	ukcq->ops.iw_cq_request_notification(ukcq, cq_notify);
+	spin_unlock_irqrestore(&iwcq->lock, flags);
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 105246fba2e7..5fc623362731 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -47,6 +47,7 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
 
 	ah->av.ib.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
 	ah->av.ib.g_slid  = ah_attr->src_path_bits;
+	ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 	if (ah_attr->ah_flags & IB_AH_GRH) {
 		ah->av.ib.g_slid   |= 0x80;
 		ah->av.ib.gid_index = ah_attr->grh.sgid_index;
@@ -64,7 +65,6 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
 		       !(1 << ah->av.ib.stat_rate & dev->caps.stat_rate_support))
 			--ah->av.ib.stat_rate;
 	}
-	ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 
 	return &ah->ibah;
 }
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index d68f506c1922..9c2e53d28f98 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -527,7 +527,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 		tun_tx_ix = (++tun_qp->tx_ix_head) & (MLX4_NUM_TUNNEL_BUFS - 1);
 	spin_unlock(&tun_qp->tx_lock);
 	if (ret)
-		goto out;
+		goto end;
 
 	tun_mad = (struct mlx4_rcv_tunnel_mad *) (tun_qp->tx_ring[tun_tx_ix].buf.addr);
 	if (tun_qp->tx_ring[tun_tx_ix].ah)
@@ -596,9 +596,15 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 	wr.wr.send_flags = IB_SEND_SIGNALED;
 
 	ret = ib_post_send(src_qp, &wr.wr, &bad_wr);
-out:
-	if (ret)
-		ib_destroy_ah(ah);
+	if (!ret)
+		return 0;
+ out:
+	spin_lock(&tun_qp->tx_lock);
+	tun_qp->tx_ix_tail++;
+	spin_unlock(&tun_qp->tx_lock);
+	tun_qp->tx_ring[tun_tx_ix].ah = NULL;
+end:
+	ib_destroy_ah(ah);
 	return ret;
 }
 
@@ -1326,9 +1332,15 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
 
 
 	ret = ib_post_send(send_qp, &wr.wr, &bad_wr);
+	if (!ret)
+		return 0;
+
+	spin_lock(&sqp->tx_lock);
+	sqp->tx_ix_tail++;
+	spin_unlock(&sqp->tx_lock);
+	sqp->tx_ring[wire_tx_ix].ah = NULL;
 out:
-	if (ret)
-		ib_destroy_ah(ah);
+	ib_destroy_ah(ah);
 	return ret;
 }
 
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index b01ef6eee6e8..42a46078d7d5 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -505,9 +505,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
 		else
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
-	if (dev->steering_support ==  MLX4_STEERING_MODE_DEVICE_MANAGED)
-		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
 	}
+	if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED)
+		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
 
 	props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
 
@@ -1704,6 +1704,9 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 	struct mlx4_dev *dev = (to_mdev(qp->device))->dev;
 	int is_bonded = mlx4_is_bonded(dev);
 
+	if (flow_attr->port < 1 || flow_attr->port > qp->device->phys_port_cnt)
+		return ERR_PTR(-EINVAL);
+
 	if ((flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) &&
 	    (flow_attr->type != IB_FLOW_ATTR_NORMAL))
 		return ERR_PTR(-EOPNOTSUPP);
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 6c5ac5d8f32f..29acda249612 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -139,7 +139,7 @@ struct mlx4_ib_mr {
 	u32			max_pages;
 	struct mlx4_mr		mmr;
 	struct ib_umem	       *umem;
-	void			*pages_alloc;
+	size_t			page_map_size;
 };
 
 struct mlx4_ib_mw {
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 631272172a0b..5d73989d9771 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -277,20 +277,23 @@ mlx4_alloc_priv_pages(struct ib_device *device,
 		      struct mlx4_ib_mr *mr,
 		      int max_pages)
 {
-	int size = max_pages * sizeof(u64);
-	int add_size;
 	int ret;
 
-	add_size = max_t(int, MLX4_MR_PAGES_ALIGN - ARCH_KMALLOC_MINALIGN, 0);
+	/* Ensure that size is aligned to DMA cacheline
+	 * requirements.
+	 * max_pages is limited to MLX4_MAX_FAST_REG_PAGES
+	 * so page_map_size will never cross PAGE_SIZE.
+	 */
+	mr->page_map_size = roundup(max_pages * sizeof(u64),
+				    MLX4_MR_PAGES_ALIGN);
 
-	mr->pages_alloc = kzalloc(size + add_size, GFP_KERNEL);
-	if (!mr->pages_alloc)
+	/* Prevent cross page boundary allocation. */
+	mr->pages = (__be64 *)get_zeroed_page(GFP_KERNEL);
+	if (!mr->pages)
 		return -ENOMEM;
 
-	mr->pages = PTR_ALIGN(mr->pages_alloc, MLX4_MR_PAGES_ALIGN);
-
 	mr->page_map = dma_map_single(device->dma_device, mr->pages,
-				      size, DMA_TO_DEVICE);
+				      mr->page_map_size, DMA_TO_DEVICE);
 
 	if (dma_mapping_error(device->dma_device, mr->page_map)) {
 		ret = -ENOMEM;
@@ -298,9 +301,9 @@ mlx4_alloc_priv_pages(struct ib_device *device,
 	}
 
 	return 0;
-err:
-	kfree(mr->pages_alloc);
 
+err:
+	free_page((unsigned long)mr->pages);
 	return ret;
 }
 
@@ -309,11 +312,10 @@ mlx4_free_priv_pages(struct mlx4_ib_mr *mr)
 {
 	if (mr->pages) {
 		struct ib_device *device = mr->ibmr.device;
-		int size = mr->max_pages * sizeof(u64);
 
 		dma_unmap_single(device->dma_device, mr->page_map,
-				 size, DMA_TO_DEVICE);
-		kfree(mr->pages_alloc);
+				 mr->page_map_size, DMA_TO_DEVICE);
+		free_page((unsigned long)mr->pages);
 		mr->pages = NULL;
 	}
 }
@@ -537,14 +539,12 @@ int mlx4_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
 	mr->npages = 0;
 
 	ib_dma_sync_single_for_cpu(ibmr->device, mr->page_map,
-				   sizeof(u64) * mr->max_pages,
-				   DMA_TO_DEVICE);
+				   mr->page_map_size, DMA_TO_DEVICE);
 
 	rc = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, mlx4_set_page);
 
 	ib_dma_sync_single_for_device(ibmr->device, mr->page_map,
-				      sizeof(u64) * mr->max_pages,
-				      DMA_TO_DEVICE);
+				      mr->page_map_size, DMA_TO_DEVICE);
 
 	return rc;
 }
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 81b0e1fbec1d..8db8405c1e99 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -362,7 +362,7 @@ static int send_wqe_overhead(enum mlx4_ib_qp_type type, u32 flags)
 			sizeof (struct mlx4_wqe_raddr_seg);
 	case MLX4_IB_QPT_RC:
 		return sizeof (struct mlx4_wqe_ctrl_seg) +
-			sizeof (struct mlx4_wqe_atomic_seg) +
+			sizeof (struct mlx4_wqe_masked_atomic_seg) +
 			sizeof (struct mlx4_wqe_raddr_seg);
 	case MLX4_IB_QPT_SMI:
 	case MLX4_IB_QPT_GSI:
@@ -1191,8 +1191,10 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 	{
 		err = create_qp_common(to_mdev(pd->device), pd, init_attr,
 				       udata, 0, &qp, gfp);
-		if (err)
+		if (err) {
+			kfree(qp);
 			return ERR_PTR(err);
+		}
 
 		qp->ibqp.qp_num = qp->mqp.qpn;
 		qp->xrcdn = xrcdn;
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index dabcc65bd65e..9c0e67bd2ba7 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -822,7 +822,8 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
 	int eqn;
 	int err;
 
-	if (entries < 0)
+	if (entries < 0 ||
+	    (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))))
 		return ERR_PTR(-EINVAL);
 
 	if (check_cq_create_flags(attr->flags))
@@ -1168,11 +1169,16 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 		return -ENOSYS;
 	}
 
-	if (entries < 1)
+	if (entries < 1 ||
+	    entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))) {
+		mlx5_ib_warn(dev, "wrong entries number %d, max %d\n",
+			     entries,
+			     1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz));
 		return -EINVAL;
+	}
 
 	entries = roundup_pow_of_two(entries + 1);
-	if (entries >  (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1)
+	if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1)
 		return -EINVAL;
 
 	if (entries == ibcq->cqe + 1)
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 1534af113058..364aab9f3c9e 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -121,7 +121,7 @@ static void pma_cnt_ext_assign(struct ib_pma_portcounters_ext *pma_cnt_ext,
 	pma_cnt_ext->port_xmit_data =
 		cpu_to_be64(MLX5_SUM_CNT(out, transmitted_ib_unicast.octets,
 					 transmitted_ib_multicast.octets) >> 2);
-	pma_cnt_ext->port_xmit_data =
+	pma_cnt_ext->port_rcv_data =
 		cpu_to_be64(MLX5_SUM_CNT(out, received_ib_unicast.octets,
 					 received_ib_multicast.octets) >> 2);
 	pma_cnt_ext->port_xmit_packets =
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index c72797cd9e4f..dad63f038bb8 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -524,6 +524,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	    MLX5_CAP_ETH(dev->mdev, scatter_fcs))
 		props->device_cap_flags |= IB_DEVICE_RAW_SCATTER_FCS;
 
+	if (mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS))
+		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
+
 	props->vendor_part_id	   = mdev->pdev->device;
 	props->hw_ver		   = mdev->pdev->revision;
 
@@ -915,7 +918,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE;
 	gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE;
 	resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp);
-	resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
+	if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf))
+		resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
 	resp.cache_line_size = L1_CACHE_BYTES;
 	resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq);
 	resp.max_rq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq);
@@ -988,7 +992,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	if (field_avail(typeof(resp), cqe_version, udata->outlen))
 		resp.response_length += sizeof(resp.cqe_version);
 
-	if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
+	/*
+	 * We don't want to expose information from the PCI bar that is located
+	 * after 4096 bytes, so if the arch only supports larger pages, let's
+	 * pretend we don't support reading the HCA's core clock. This is also
+	 * forced by mmap function.
+	 */
+	if (PAGE_SIZE <= 4096 &&
+	    field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
 		resp.comp_mask |=
 			MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET;
 		resp.hca_core_clock_offset =
@@ -1517,21 +1528,18 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 {
 	struct mlx5_flow_table	*ft = ft_prio->flow_table;
 	struct mlx5_ib_flow_handler *handler;
+	struct mlx5_flow_spec *spec;
 	void *ib_flow = flow_attr + 1;
-	u8 match_criteria_enable = 0;
 	unsigned int spec_index;
-	u32 *match_c;
-	u32 *match_v;
 	u32 action;
 	int err = 0;
 
 	if (!is_valid_attr(flow_attr))
 		return ERR_PTR(-EINVAL);
 
-	match_c = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
-	match_v = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
+	spec = mlx5_vzalloc(sizeof(*spec));
 	handler = kzalloc(sizeof(*handler), GFP_KERNEL);
-	if (!handler || !match_c || !match_v) {
+	if (!handler || !spec) {
 		err = -ENOMEM;
 		goto free;
 	}
@@ -1539,7 +1547,8 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 	INIT_LIST_HEAD(&handler->list);
 
 	for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
-		err = parse_flow_attr(match_c, match_v, ib_flow);
+		err = parse_flow_attr(spec->match_criteria,
+				      spec->match_value, ib_flow);
 		if (err < 0)
 			goto free;
 
@@ -1547,11 +1556,11 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 	}
 
 	/* Outer header support only */
-	match_criteria_enable = (!outer_header_zero(match_c)) << 0;
+	spec->match_criteria_enable = (!outer_header_zero(spec->match_criteria))
+		<< 0;
 	action = dst ? MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
 		MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
-	handler->rule = mlx5_add_flow_rule(ft, match_criteria_enable,
-					   match_c, match_v,
+	handler->rule = mlx5_add_flow_rule(ft, spec,
 					   action,
 					   MLX5_FS_DEFAULT_FLOW_TAG,
 					   dst);
@@ -1567,8 +1576,7 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 free:
 	if (err)
 		kfree(handler);
-	kfree(match_c);
-	kfree(match_v);
+	kvfree(spec);
 	return err ? ERR_PTR(err) : handler;
 }
 
@@ -1798,7 +1806,7 @@ static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr,
 {
 	struct mlx5_ib_dev *dev =
 		container_of(device, struct mlx5_ib_dev, ib_dev.dev);
-	return sprintf(buf, "%d.%d.%d\n", fw_rev_maj(dev->mdev),
+	return sprintf(buf, "%d.%d.%04d\n", fw_rev_maj(dev->mdev),
 		       fw_rev_min(dev->mdev), fw_rev_sub(dev->mdev));
 }
 
@@ -1866,14 +1874,11 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 		break;
 
 	case MLX5_DEV_EVENT_PORT_DOWN:
+	case MLX5_DEV_EVENT_PORT_INITIALIZED:
 		ibev.event = IB_EVENT_PORT_ERR;
 		port = (u8)param;
 		break;
 
-	case MLX5_DEV_EVENT_PORT_INITIALIZED:
-		/* not used by ULPs */
-		return;
-
 	case MLX5_DEV_EVENT_LID_CHANGE:
 		ibev.event = IB_EVENT_LID_CHANGE;
 		port = (u8)param;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 504117657d41..ce0a7ab35a22 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -235,6 +235,8 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
 		qp->rq.max_gs = 0;
 		qp->rq.wqe_cnt = 0;
 		qp->rq.wqe_shift = 0;
+		cap->max_recv_wr = 0;
+		cap->max_recv_sge = 0;
 	} else {
 		if (ucmd) {
 			qp->rq.wqe_cnt = ucmd->rq_wqe_count;
@@ -1851,13 +1853,15 @@ static int modify_raw_packet_eth_prio(struct mlx5_core_dev *dev,
 static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 			 const struct ib_ah_attr *ah,
 			 struct mlx5_qp_path *path, u8 port, int attr_mask,
-			 u32 path_flags, const struct ib_qp_attr *attr)
+			 u32 path_flags, const struct ib_qp_attr *attr,
+			 bool alt)
 {
 	enum rdma_link_layer ll = rdma_port_get_link_layer(&dev->ib_dev, port);
 	int err;
 
 	if (attr_mask & IB_QP_PKEY_INDEX)
-		path->pkey_index = attr->pkey_index;
+		path->pkey_index = cpu_to_be16(alt ? attr->alt_pkey_index :
+						     attr->pkey_index);
 
 	if (ah->ah_flags & IB_AH_GRH) {
 		if (ah->grh.sgid_index >=
@@ -1877,9 +1881,9 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 							  ah->grh.sgid_index);
 		path->dci_cfi_prio_sl = (ah->sl & 0x7) << 4;
 	} else {
-		path->fl = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
-		path->free_ar = (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x80 :
-									0;
+		path->fl_free_ar = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
+		path->fl_free_ar |=
+			(path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x40 : 0;
 		path->rlid = cpu_to_be16(ah->dlid);
 		path->grh_mlid = ah->src_path_bits & 0x7f;
 		if (ah->ah_flags & IB_AH_GRH)
@@ -1903,7 +1907,7 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	path->port = port;
 
 	if (attr_mask & IB_QP_TIMEOUT)
-		path->ackto_lt = attr->timeout << 3;
+		path->ackto_lt = (alt ? attr->alt_timeout : attr->timeout) << 3;
 
 	if ((qp->ibqp.qp_type == IB_QPT_RAW_PACKET) && qp->sq.wqe_cnt)
 		return modify_raw_packet_eth_prio(dev->mdev,
@@ -2264,7 +2268,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 		context->log_pg_sz_remote_qpn = cpu_to_be32(attr->dest_qp_num);
 
 	if (attr_mask & IB_QP_PKEY_INDEX)
-		context->pri_path.pkey_index = attr->pkey_index;
+		context->pri_path.pkey_index = cpu_to_be16(attr->pkey_index);
 
 	/* todo implement counter_index functionality */
 
@@ -2277,7 +2281,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	if (attr_mask & IB_QP_AV) {
 		err = mlx5_set_path(dev, qp, &attr->ah_attr, &context->pri_path,
 				    attr_mask & IB_QP_PORT ? attr->port_num : qp->port,
-				    attr_mask, 0, attr);
+				    attr_mask, 0, attr, false);
 		if (err)
 			goto out;
 	}
@@ -2288,7 +2292,9 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	if (attr_mask & IB_QP_ALT_PATH) {
 		err = mlx5_set_path(dev, qp, &attr->alt_ah_attr,
 				    &context->alt_path,
-				    attr->alt_port_num, attr_mask, 0, attr);
+				    attr->alt_port_num,
+				    attr_mask | IB_QP_PKEY_INDEX | IB_QP_TIMEOUT,
+				    0, attr, true);
 		if (err)
 			goto out;
 	}
@@ -3326,10 +3332,11 @@ static u8 get_fence(u8 fence, struct ib_send_wr *wr)
 			return MLX5_FENCE_MODE_SMALL_AND_FENCE;
 		else
 			return fence;
-
-	} else {
-		return 0;
+	} else if (unlikely(wr->send_flags & IB_SEND_FENCE)) {
+		return MLX5_FENCE_MODE_FENCE;
 	}
+
+	return 0;
 }
 
 static int begin_wqe(struct mlx5_ib_qp *qp, void **seg,
@@ -4013,11 +4020,12 @@ static int query_qp_attr(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) {
 		to_ib_ah_attr(dev, &qp_attr->ah_attr, &context->pri_path);
 		to_ib_ah_attr(dev, &qp_attr->alt_ah_attr, &context->alt_path);
-		qp_attr->alt_pkey_index = context->alt_path.pkey_index & 0x7f;
+		qp_attr->alt_pkey_index =
+			be16_to_cpu(context->alt_path.pkey_index);
 		qp_attr->alt_port_num	= qp_attr->alt_ah_attr.port_num;
 	}
 
-	qp_attr->pkey_index = context->pri_path.pkey_index & 0x7f;
+	qp_attr->pkey_index = be16_to_cpu(context->pri_path.pkey_index);
 	qp_attr->port_num = context->pri_path.port;
 
 	/* qp_attr->en_sqd_async_notify is only applicable in modify qp */
@@ -4079,17 +4087,19 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
 	qp_attr->cap.max_recv_sge    = qp->rq.max_gs;
 
 	if (!ibqp->uobject) {
-		qp_attr->cap.max_send_wr  = qp->sq.wqe_cnt;
+		qp_attr->cap.max_send_wr  = qp->sq.max_post;
 		qp_attr->cap.max_send_sge = qp->sq.max_gs;
+		qp_init_attr->qp_context = ibqp->qp_context;
 	} else {
 		qp_attr->cap.max_send_wr  = 0;
 		qp_attr->cap.max_send_sge = 0;
 	}
 
-	/* We don't support inline sends for kernel QPs (yet), and we
-	 * don't know what userspace's value should be.
-	 */
-	qp_attr->cap.max_inline_data = 0;
+	qp_init_attr->qp_type = ibqp->qp_type;
+	qp_init_attr->recv_cq = ibqp->recv_cq;
+	qp_init_attr->send_cq = ibqp->send_cq;
+	qp_init_attr->srq = ibqp->srq;
+	qp_attr->cap.max_inline_data = qp->max_inline_data;
 
 	qp_init_attr->cap	     = qp_attr->cap;
 
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index ff946d5f59e4..382466a90da7 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -2178,6 +2178,11 @@ static ssize_t qib_write(struct file *fp, const char __user *data,
 
 	switch (cmd.type) {
 	case QIB_CMD_ASSIGN_CTXT:
+		if (rcd) {
+			ret = -EINVAL;
+			goto bail;
+		}
+
 		ret = qib_assign_ctxt(fp, &cmd.cmd.user_info);
 		if (ret)
 			goto bail;
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 7209fbc03ccb..a0b6ebee4d8a 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -36,7 +36,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/sched.h>
 #include <linux/hugetlb.h>
-#include <linux/dma-attrs.h>
 #include <linux/iommu.h>
 #include <linux/workqueue.h>
 #include <linux/list.h>
@@ -112,10 +111,6 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
 	int i;
 	int flags;
 	dma_addr_t pa;
-	DEFINE_DMA_ATTRS(attrs);
-
-	if (dmasync)
-		dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
 
 	if (!can_do_mlock())
 		return -EPERM;
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 5fa4d4d81ee0..41ba7e9cadaa 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -369,8 +369,8 @@ static int alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
 			/* wrap to first map page, invert bit 0 */
 			offset = qpt->incr | ((offset & 1) ^ 1);
 		}
-		/* there can be no bits at shift and below */
-		WARN_ON(offset & (rdi->dparms.qos_shift - 1));
+		/* there can be no set bits in low-order QoS bits */
+		WARN_ON(offset & (BIT(rdi->dparms.qos_shift) - 1));
 		qpn = mk_qpn(qpt, map, offset);
 	}
 
@@ -502,6 +502,12 @@ static void rvt_remove_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp)
  */
 static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 		  enum ib_qp_type type)
+	__releases(&qp->s_lock)
+	__releases(&qp->s_hlock)
+	__releases(&qp->r_lock)
+	__acquires(&qp->r_lock)
+	__acquires(&qp->s_hlock)
+	__acquires(&qp->s_lock)
 {
 	if (qp->state != IB_QPS_RESET) {
 		qp->state = IB_QPS_RESET;
@@ -570,12 +576,6 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 	qp->s_ssn = 1;
 	qp->s_lsn = 0;
 	qp->s_mig_state = IB_MIG_MIGRATED;
-	if (qp->s_ack_queue)
-		memset(
-			qp->s_ack_queue,
-			0,
-			rvt_max_atomic(rdi) *
-				sizeof(*qp->s_ack_queue));
 	qp->r_head_ack_queue = 0;
 	qp->s_tail_ack_queue = 0;
 	qp->s_num_rd_atomic = 0;
@@ -699,8 +699,10 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 		 * initialization that is needed.
 		 */
 		priv = rdi->driver_f.qp_priv_alloc(rdi, qp, gfp);
-		if (!priv)
+		if (IS_ERR(priv)) {
+			ret = priv;
 			goto bail_qp;
+		}
 		qp->priv = priv;
 		qp->timeout_jiffies =
 			usecs_to_jiffies((4096UL * (1UL << qp->timeout)) /
diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c
index e1cc2cc42f25..30c4fda7a05a 100644
--- a/drivers/infiniband/sw/rdmavt/vt.c
+++ b/drivers/infiniband/sw/rdmavt/vt.c
@@ -501,9 +501,7 @@ static noinline int check_support(struct rvt_dev_info *rdi, int verb)
 			    !rdi->driver_f.quiesce_qp ||
 			    !rdi->driver_f.notify_error_qp ||
 			    !rdi->driver_f.mtu_from_qp ||
-			    !rdi->driver_f.mtu_to_path_mtu ||
-			    !rdi->driver_f.shut_down_port ||
-			    !rdi->driver_f.cap_mask_chg)
+			    !rdi->driver_f.mtu_to_path_mtu)
 				return -EINVAL;
 		break;
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index bab7db6fa9ab..4f7d9b48df64 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -94,6 +94,7 @@ enum {
 	IPOIB_NEIGH_TBL_FLUSH	  = 12,
 	IPOIB_FLAG_DEV_ADDR_SET	  = 13,
 	IPOIB_FLAG_DEV_ADDR_CTRL  = 14,
+	IPOIB_FLAG_GOING_DOWN	  = 15,
 
 	IPOIB_MAX_BACKOFF_SECONDS = 16,
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index b2f42835d76d..951d9abcca8b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1486,6 +1486,10 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 {
 	struct net_device *dev = to_net_dev(d);
 	int ret;
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+	if (test_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags))
+		return -EPERM;
 
 	if (!rtnl_trylock())
 		return restart_syscall();
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 45c40a17d6a6..dc6d241b9406 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -1015,7 +1015,7 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv)
 	if (ib_query_gid(priv->ca, priv->port, 0, &gid0, NULL))
 		return false;
 
-	netif_addr_lock(priv->dev);
+	netif_addr_lock_bh(priv->dev);
 
 	/* The subnet prefix may have changed, update it now so we won't have
 	 * to do it later
@@ -1026,12 +1026,12 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv)
 
 	search_gid.global.interface_id = priv->local_gid.global.interface_id;
 
-	netif_addr_unlock(priv->dev);
+	netif_addr_unlock_bh(priv->dev);
 
 	err = ib_find_gid(priv->ca, &search_gid, IB_GID_TYPE_IB,
 			  priv->dev, &port, &index);
 
-	netif_addr_lock(priv->dev);
+	netif_addr_lock_bh(priv->dev);
 
 	if (search_gid.global.interface_id !=
 	    priv->local_gid.global.interface_id)
@@ -1092,7 +1092,7 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv)
 	}
 
 out:
-	netif_addr_unlock(priv->dev);
+	netif_addr_unlock_bh(priv->dev);
 
 	return ret;
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 2d7c16346648..5f58c41ef787 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1206,7 +1206,9 @@ struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr)
 				neigh = NULL;
 				goto out_unlock;
 			}
-			neigh->alive = jiffies;
+
+			if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE))
+				neigh->alive = jiffies;
 			goto out_unlock;
 		}
 	}
@@ -1851,7 +1853,7 @@ static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid)
 	struct ipoib_dev_priv *child_priv;
 	struct net_device *netdev = priv->dev;
 
-	netif_addr_lock(netdev);
+	netif_addr_lock_bh(netdev);
 
 	memcpy(&priv->local_gid.global.interface_id,
 	       &gid->global.interface_id,
@@ -1859,7 +1861,7 @@ static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid)
 	memcpy(netdev->dev_addr + 4, &priv->local_gid, sizeof(priv->local_gid));
 	clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
 
-	netif_addr_unlock(netdev);
+	netif_addr_unlock_bh(netdev);
 
 	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
 		down_read(&priv->vlan_rwsem);
@@ -1875,7 +1877,7 @@ static int ipoib_check_lladdr(struct net_device *dev,
 	union ib_gid *gid = (union ib_gid *)(ss->__data + 4);
 	int ret = 0;
 
-	netif_addr_lock(dev);
+	netif_addr_lock_bh(dev);
 
 	/* Make sure the QPN, reserved and subnet prefix match the current
 	 * lladdr, it also makes sure the lladdr is unicast.
@@ -1885,7 +1887,7 @@ static int ipoib_check_lladdr(struct net_device *dev,
 	    gid->global.interface_id == 0)
 		ret = -EINVAL;
 
-	netif_addr_unlock(dev);
+	netif_addr_unlock_bh(dev);
 
 	return ret;
 }
@@ -2141,6 +2143,9 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data)
 		ib_unregister_event_handler(&priv->event_handler);
 		flush_workqueue(ipoib_workqueue);
 
+		/* mark interface in the middle of destruction */
+		set_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags);
+
 		rtnl_lock();
 		dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP);
 		rtnl_unlock();
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 82fbc9442608..d3394b6add24 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -582,13 +582,13 @@ void ipoib_mcast_join_task(struct work_struct *work)
 		return;
 	}
 	priv->local_lid = port_attr.lid;
-	netif_addr_lock(dev);
+	netif_addr_lock_bh(dev);
 
 	if (!test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) {
-		netif_addr_unlock(dev);
+		netif_addr_unlock_bh(dev);
 		return;
 	}
-	netif_addr_unlock(dev);
+	netif_addr_unlock_bh(dev);
 
 	spin_lock_irq(&priv->lock);
 	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index 64a35595eab8..a2f9f29c6ab5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -131,6 +131,9 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 
 	ppriv = netdev_priv(pdev);
 
+	if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags))
+		return -EPERM;
+
 	snprintf(intf_name, sizeof intf_name, "%s.%04x",
 		 ppriv->dev->name, pkey);
 	priv = ipoib_intf_alloc(intf_name);
@@ -183,6 +186,9 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 
 	ppriv = netdev_priv(pdev);
 
+	if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags))
+		return -EPERM;
+
 	if (!rtnl_trylock())
 		return restart_syscall();
 
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 646de170ec12..3322ed750172 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1457,7 +1457,6 @@ static int srp_map_sg_fr(struct srp_map_state *state, struct srp_rdma_ch *ch,
 {
 	unsigned int sg_offset = 0;
 
-	state->desc = req->indirect_desc;
 	state->fr.next = req->fr_list;
 	state->fr.end = req->fr_list + ch->target->mr_per_cmd;
 	state->sg = scat;
@@ -1489,7 +1488,6 @@ static int srp_map_sg_dma(struct srp_map_state *state, struct srp_rdma_ch *ch,
 	struct scatterlist *sg;
 	int i;
 
-	state->desc = req->indirect_desc;
 	for_each_sg(scat, sg, count, i) {
 		srp_map_desc(state, ib_sg_dma_address(dev->dev, sg),
 			     ib_sg_dma_len(dev->dev, sg),
@@ -1655,6 +1653,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch,
 				   target->indirect_size, DMA_TO_DEVICE);
 
 	memset(&state, 0, sizeof(state));
+	state.desc = req->indirect_desc;
 	if (dev->use_fast_reg)
 		ret = srp_map_sg_fr(&state, ch, req, scat, count);
 	else if (dev->use_fmr)
@@ -3526,7 +3525,7 @@ static void srp_add_one(struct ib_device *device)
 	int mr_page_shift, p;
 	u64 max_pages_per_mr;
 
-	srp_dev = kmalloc(sizeof *srp_dev, GFP_KERNEL);
+	srp_dev = kzalloc(sizeof(*srp_dev), GFP_KERNEL);
 	if (!srp_dev)
 		return;
 
@@ -3586,8 +3585,6 @@ static void srp_add_one(struct ib_device *device)
 						   IB_ACCESS_REMOTE_WRITE);
 		if (IS_ERR(srp_dev->global_mr))
 			goto err_pd;
-	} else {
-		srp_dev->global_mr = NULL;
 	}
 
 	for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index e68b20cba70b..4a4155640d51 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1638,8 +1638,7 @@ retry:
 	 */
 	qp_init->cap.max_send_wr = srp_sq_size / 2;
 	qp_init->cap.max_rdma_ctxs = srp_sq_size / 2;
-	qp_init->cap.max_send_sge = max(sdev->device->attrs.max_sge_rd,
-					sdev->device->attrs.max_sge);
+	qp_init->cap.max_send_sge = SRPT_DEF_SG_PER_WQE;
 	qp_init->port_num = ch->sport->port;
 
 	ch->qp = ib_create_qp(sdev->pd, qp_init);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index fee6bfd7ca21..389030487da7 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -106,6 +106,7 @@ enum {
 	SRP_LOGIN_RSP_MULTICHAN_MAINTAINED = 0x2,
 
 	SRPT_DEF_SG_TABLESIZE = 128,
+	SRPT_DEF_SG_PER_WQE = 16,
 
 	MIN_SRPT_SQ_SIZE = 16,
 	DEF_SRPT_SQ_SIZE = 4096,
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 804dbcc37d3f..3438e98c145a 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -1031,17 +1031,17 @@ static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect
 
 	case XTYPE_XBOXONE:
 		packet->data[0] = 0x09; /* activate rumble */
-		packet->data[1] = 0x08;
+		packet->data[1] = 0x00;
 		packet->data[2] = xpad->odata_serial++;
-		packet->data[3] = 0x08; /* continuous effect */
-		packet->data[4] = 0x00; /* simple rumble mode */
-		packet->data[5] = 0x03; /* L and R actuator only */
-		packet->data[6] = 0x00; /* TODO: LT actuator */
-		packet->data[7] = 0x00; /* TODO: RT actuator */
+		packet->data[3] = 0x09;
+		packet->data[4] = 0x00;
+		packet->data[5] = 0x0F;
+		packet->data[6] = 0x00;
+		packet->data[7] = 0x00;
 		packet->data[8] = strong / 512;	/* left actuator */
 		packet->data[9] = weak / 512;	/* right actuator */
-		packet->data[10] = 0x80;	/* length of pulse */
-		packet->data[11] = 0x00;	/* stop period of pulse */
+		packet->data[10] = 0xFF;
+		packet->data[11] = 0x00;
 		packet->data[12] = 0x00;
 		packet->len = 13;
 		packet->pending = true;
@@ -1437,16 +1437,6 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
 			break;
 	}
 
-	if (xpad_device[i].xtype == XTYPE_XBOXONE &&
-	    intf->cur_altsetting->desc.bInterfaceNumber != 0) {
-		/*
-		 * The Xbox One controller lists three interfaces all with the
-		 * same interface class, subclass and protocol. Differentiate by
-		 * interface number.
-		 */
-		return -ENODEV;
-	}
-
 	xpad = kzalloc(sizeof(struct usb_xpad), GFP_KERNEL);
 	if (!xpad)
 		return -ENOMEM;
@@ -1478,6 +1468,8 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
 		if (intf->cur_altsetting->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC) {
 			if (intf->cur_altsetting->desc.bInterfaceProtocol == 129)
 				xpad->xtype = XTYPE_XBOX360W;
+			else if (intf->cur_altsetting->desc.bInterfaceProtocol == 208)
+				xpad->xtype = XTYPE_XBOXONE;
 			else
 				xpad->xtype = XTYPE_XBOX360;
 		} else {
@@ -1492,6 +1484,17 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
 			xpad->mapping |= MAP_STICKS_TO_NULL;
 	}
 
+	if (xpad->xtype == XTYPE_XBOXONE &&
+	    intf->cur_altsetting->desc.bInterfaceNumber != 0) {
+		/*
+		 * The Xbox One controller lists three interfaces all with the
+		 * same interface class, subclass and protocol. Differentiate by
+		 * interface number.
+		 */
+		error = -ENODEV;
+		goto err_free_in_urb;
+	}
+
 	error = xpad_init_output(intf, xpad);
 	if (error)
 		goto err_free_in_urb;
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 78f93cf68840..be5b399da5d3 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1568,13 +1568,7 @@ static int elantech_set_properties(struct elantech_data *etd)
 		case 5:
 			etd->hw_version = 3;
 			break;
-		case 6:
-		case 7:
-		case 8:
-		case 9:
-		case 10:
-		case 13:
-		case 14:
+		case 6 ... 14:
 			etd->hw_version = 4;
 			break;
 		default:
diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index a3f0f5a47490..0f586780ceb4 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -355,18 +355,11 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties)
 		return -ENXIO;
 	}
 
-	if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) {
-		psmouse_dbg(psmouse, "VMMouse port in use.\n");
-		return -EBUSY;
-	}
-
 	/* Check if the device is present */
 	response = ~VMMOUSE_PROTO_MAGIC;
 	VMMOUSE_CMD(GETVERSION, 0, version, response, dummy1, dummy2);
-	if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU) {
-		release_region(VMMOUSE_PROTO_PORT, 4);
+	if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU)
 		return -ENXIO;
-	}
 
 	if (set_properties) {
 		psmouse->vendor = VMMOUSE_VENDOR;
@@ -374,8 +367,6 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties)
 		psmouse->model = version;
 	}
 
-	release_region(VMMOUSE_PROTO_PORT, 4);
-
 	return 0;
 }
 
@@ -394,7 +385,6 @@ static void vmmouse_disconnect(struct psmouse *psmouse)
 	psmouse_reset(psmouse);
 	input_unregister_device(priv->abs_dev);
 	kfree(priv);
-	release_region(VMMOUSE_PROTO_PORT, 4);
 }
 
 /**
@@ -438,15 +428,10 @@ int vmmouse_init(struct psmouse *psmouse)
 	struct input_dev *rel_dev = psmouse->dev, *abs_dev;
 	int error;
 
-	if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) {
-		psmouse_dbg(psmouse, "VMMouse port in use.\n");
-		return -EBUSY;
-	}
-
 	psmouse_reset(psmouse);
 	error = vmmouse_enable(psmouse);
 	if (error)
-		goto release_region;
+		return error;
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	abs_dev = input_allocate_device();
@@ -502,8 +487,5 @@ init_fail:
 	kfree(priv);
 	psmouse->private = NULL;
 
-release_region:
-	release_region(VMMOUSE_PROTO_PORT, 4);
-
 	return error;
 }
diff --git a/drivers/input/touchscreen/wacom_w8001.c b/drivers/input/touchscreen/wacom_w8001.c
index bab3c6acf6a2..0c9191cf324d 100644
--- a/drivers/input/touchscreen/wacom_w8001.c
+++ b/drivers/input/touchscreen/wacom_w8001.c
@@ -27,7 +27,7 @@ MODULE_AUTHOR("Jaya Kumar <[email protected]>");
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 
-#define W8001_MAX_LENGTH	11
+#define W8001_MAX_LENGTH	13
 #define W8001_LEAD_MASK		0x80
 #define W8001_LEAD_BYTE		0x80
 #define W8001_TAB_MASK		0x40
@@ -339,6 +339,15 @@ static irqreturn_t w8001_interrupt(struct serio *serio,
 		w8001->idx = 0;
 		parse_multi_touch(w8001);
 		break;
+
+	default:
+		/*
+		 * ThinkPad X60 Tablet PC (pen only device) sometimes
+		 * sends invalid data packets that are larger than
+		 * W8001_PKTLEN_TPCPEN. Let's start over again.
+		 */
+		if (!w8001->touch_dev && w8001->idx > W8001_PKTLEN_TPCPEN - 1)
+			w8001->idx = 0;
 	}
 
 	return IRQ_HANDLED;
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 94b68213c50d..5f6b3bcab078 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1941,6 +1941,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.attach_dev		= arm_smmu_attach_dev,
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
+	.map_sg			= default_iommu_map_sg,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
 	.remove_device		= arm_smmu_remove_device,
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a644d0cec2d8..10700945994e 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3222,11 +3222,6 @@ static int __init init_dmars(void)
 			}
 		}
 
-		iommu_flush_write_buffer(iommu);
-		iommu_set_root_entry(iommu);
-		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
-		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
-
 		if (!ecap_pass_through(iommu->ecap))
 			hw_pass_through = 0;
 #ifdef CONFIG_INTEL_IOMMU_SVM
@@ -3235,6 +3230,18 @@ static int __init init_dmars(void)
 #endif
 	}
 
+	/*
+	 * Now that qi is enabled on all iommus, set the root entry and flush
+	 * caches. This is required on some Intel X58 chipsets, otherwise the
+	 * flush_context function will loop forever and the boot hangs.
+	 */
+	for_each_active_iommu(iommu, drhd) {
+		iommu_flush_write_buffer(iommu);
+		iommu_set_root_entry(iommu);
+		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+	}
+
 	if (iommu_pass_through)
 		iommu_identity_mapping |= IDENTMAP_ALL;
 
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index c7d6156ff536..25b4627cb57f 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -815,7 +815,7 @@ static int rk_iommu_attach_device(struct iommu_domain *domain,
 	dte_addr = virt_to_phys(rk_domain->dt);
 	for (i = 0; i < iommu->num_mmu; i++) {
 		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, dte_addr);
-		rk_iommu_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE);
+		rk_iommu_base_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE);
 		rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, RK_MMU_IRQ_MASK);
 	}
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 6bd881be24ea..5eb1f9e17a98 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -41,6 +41,7 @@
 
 #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING		(1ULL << 0)
 #define ITS_FLAGS_WORKAROUND_CAVIUM_22375	(1ULL << 1)
+#define ITS_FLAGS_WORKAROUND_CAVIUM_23144	(1ULL << 2)
 
 #define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING	(1 << 0)
 
@@ -82,6 +83,7 @@ struct its_node {
 	u64			flags;
 	u32			ite_size;
 	u32			device_ids;
+	int			numa_node;
 };
 
 #define ITS_ITT_ALIGN		SZ_256
@@ -613,11 +615,23 @@ static void its_unmask_irq(struct irq_data *d)
 static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
-	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	unsigned int cpu;
+	const struct cpumask *cpu_mask = cpu_online_mask;
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	struct its_collection *target_col;
 	u32 id = its_get_event_id(d);
 
+       /* lpi cannot be routed to a redistributor that is on a foreign node */
+	if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+		if (its_dev->its->numa_node >= 0) {
+			cpu_mask = cpumask_of_node(its_dev->its->numa_node);
+			if (!cpumask_intersects(mask_val, cpu_mask))
+				return -EINVAL;
+		}
+	}
+
+	cpu = cpumask_any_and(mask_val, cpu_mask);
+
 	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
@@ -1101,6 +1115,16 @@ static void its_cpu_init_collection(void)
 	list_for_each_entry(its, &its_nodes, entry) {
 		u64 target;
 
+		/* avoid cross node collections and its mapping */
+		if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+			struct device_node *cpu_node;
+
+			cpu_node = of_get_cpu_node(cpu, NULL);
+			if (its->numa_node != NUMA_NO_NODE &&
+				its->numa_node != of_node_to_nid(cpu_node))
+				continue;
+		}
+
 		/*
 		 * We now have to bind each collection to its target
 		 * redistributor.
@@ -1351,9 +1375,14 @@ static void its_irq_domain_activate(struct irq_domain *domain,
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
+	const struct cpumask *cpu_mask = cpu_online_mask;
+
+	/* get the cpu_mask of local node */
+	if (its_dev->its->numa_node >= 0)
+		cpu_mask = cpumask_of_node(its_dev->its->numa_node);
 
 	/* Bind the LPI to the first possible CPU */
-	its_dev->event_map.col_map[event] = cpumask_first(cpu_online_mask);
+	its_dev->event_map.col_map[event] = cpumask_first(cpu_mask);
 
 	/* Map the GIC IRQ and event to the device */
 	its_send_mapvi(its_dev, d->hwirq, event);
@@ -1443,6 +1472,13 @@ static void __maybe_unused its_enable_quirk_cavium_22375(void *data)
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375;
 }
 
+static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
+{
+	struct its_node *its = data;
+
+	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
 	{
@@ -1452,6 +1488,14 @@ static const struct gic_quirk its_quirks[] = {
 		.init	= its_enable_quirk_cavium_22375,
 	},
 #endif
+#ifdef CONFIG_CAVIUM_ERRATUM_23144
+	{
+		.desc	= "ITS: Cavium erratum 23144",
+		.iidr	= 0xa100034c,	/* ThunderX pass 1.x */
+		.mask	= 0xffff0fff,
+		.init	= its_enable_quirk_cavium_23144,
+	},
+#endif
 	{
 	}
 };
@@ -1514,6 +1558,7 @@ static int __init its_probe(struct device_node *node,
 	its->base = its_base;
 	its->phys_base = res.start;
 	its->ite_size = ((readl_relaxed(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
+	its->numa_node = of_node_to_nid(node);
 
 	its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
 	if (!its->cmd_base) {
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index fb042ba9a3db..2c5ba0e704bf 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -155,7 +155,7 @@ static void gic_enable_redist(bool enable)
 
 	while (count--) {
 		val = readl_relaxed(rbase + GICR_WAKER);
-		if (enable ^ (val & GICR_WAKER_ChildrenAsleep))
+		if (enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep))
 			break;
 		cpu_relax();
 		udelay(1);
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 3b5e10aa48ab..8a4adbeb2b8c 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -746,6 +746,12 @@ static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq,
 		/* verify that it doesn't conflict with an IPI irq */
 		if (test_bit(spec->hwirq, ipi_resrv))
 			return -EBUSY;
+
+		hwirq = GIC_SHARED_TO_HWIRQ(spec->hwirq);
+
+		return irq_domain_set_hwirq_and_chip(d, virq, hwirq,
+						     &gic_level_irq_controller,
+						     NULL);
 	} else {
 		base_hwirq = find_first_bit(ipi_resrv, gic_shared_intrs);
 		if (base_hwirq == gic_shared_intrs) {
@@ -867,10 +873,14 @@ static int gic_dev_domain_alloc(struct irq_domain *d, unsigned int virq,
 						    &gic_level_irq_controller,
 						    NULL);
 		if (ret)
-			return ret;
+			goto error;
 	}
 
 	return 0;
+
+error:
+	irq_domain_free_irqs_parent(d, virq, nr_irqs);
+	return ret;
 }
 
 void gic_dev_domain_free(struct irq_domain *d, unsigned int virq,
diff --git a/drivers/irqchip/irq-pic32-evic.c b/drivers/irqchip/irq-pic32-evic.c
index e7155db01d55..73addb4b625b 100644
--- a/drivers/irqchip/irq-pic32-evic.c
+++ b/drivers/irqchip/irq-pic32-evic.c
@@ -91,7 +91,7 @@ static int pic32_set_type_edge(struct irq_data *data,
 	/* set polarity for external interrupts only */
 	for (i = 0; i < ARRAY_SIZE(priv->ext_irqs); i++) {
 		if (priv->ext_irqs[i] == data->hwirq) {
-			ret = pic32_set_ext_polarity(i + 1, flow_type);
+			ret = pic32_set_ext_polarity(i, flow_type);
 			if (ret)
 				return ret;
 		}
diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c
index a2e0ed6c9a4d..32f34511c416 100644
--- a/drivers/isdn/hardware/eicon/divasmain.c
+++ b/drivers/isdn/hardware/eicon/divasmain.c
@@ -445,32 +445,32 @@ void divasa_unmap_pci_bar(void __iomem *bar)
 /*********************************************************
  ** I/O port access
  *********************************************************/
-byte __inline__ inpp(void __iomem *addr)
+inline byte inpp(void __iomem *addr)
 {
 	return (inb((unsigned long) addr));
 }
 
-word __inline__ inppw(void __iomem *addr)
+inline word inppw(void __iomem *addr)
 {
 	return (inw((unsigned long) addr));
 }
 
-void __inline__ inppw_buffer(void __iomem *addr, void *P, int length)
+inline void inppw_buffer(void __iomem *addr, void *P, int length)
 {
 	insw((unsigned long) addr, (word *) P, length >> 1);
 }
 
-void __inline__ outppw_buffer(void __iomem *addr, void *P, int length)
+inline void outppw_buffer(void __iomem *addr, void *P, int length)
 {
 	outsw((unsigned long) addr, (word *) P, length >> 1);
 }
 
-void __inline__ outppw(void __iomem *addr, word w)
+inline void outppw(void __iomem *addr, word w)
 {
 	outw(w, (unsigned long) addr);
 }
 
-void __inline__ outpp(void __iomem *addr, word p)
+inline void outpp(void __iomem *addr, word p)
 {
 	outb(p, (unsigned long) addr);
 }
diff --git a/drivers/isdn/hardware/eicon/platform.h b/drivers/isdn/hardware/eicon/platform.h
index b2edb7590dda..62e2073c3690 100644
--- a/drivers/isdn/hardware/eicon/platform.h
+++ b/drivers/isdn/hardware/eicon/platform.h
@@ -203,7 +203,7 @@ void PCIread(byte bus, byte func, int offset, void *data, int length, void *pci_
 /*
 **  I/O Port utilities
 */
-int diva_os_register_io_port(void *adapter, int register, unsigned long port,
+int diva_os_register_io_port(void *adapter, int reg, unsigned long port,
 			     unsigned long length, const char *name, int id);
 /*
 **  I/O port access abstraction
@@ -271,13 +271,13 @@ void diva_os_get_time(dword *sec, dword *usec);
 **  atomic operation, fake because we use threads
 */
 typedef int diva_os_atomic_t;
-static diva_os_atomic_t __inline__
+static inline diva_os_atomic_t
 diva_os_atomic_increment(diva_os_atomic_t *pv)
 {
 	*pv += 1;
 	return (*pv);
 }
-static diva_os_atomic_t __inline__
+static inline diva_os_atomic_t
 diva_os_atomic_decrement(diva_os_atomic_t *pv)
 {
 	*pv -= 1;
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index 3495d5d6547f..3bce44893021 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -53,11 +53,12 @@ static void led_timer_function(unsigned long data)
 
 	if (!led_cdev->blink_delay_on || !led_cdev->blink_delay_off) {
 		led_set_brightness_nosleep(led_cdev, LED_OFF);
+		led_cdev->flags &= ~LED_BLINK_SW;
 		return;
 	}
 
 	if (led_cdev->flags & LED_BLINK_ONESHOT_STOP) {
-		led_cdev->flags &= ~LED_BLINK_ONESHOT_STOP;
+		led_cdev->flags &=  ~(LED_BLINK_ONESHOT_STOP | LED_BLINK_SW);
 		return;
 	}
 
@@ -151,6 +152,7 @@ static void led_set_software_blink(struct led_classdev *led_cdev,
 		return;
 	}
 
+	led_cdev->flags |= LED_BLINK_SW;
 	mod_timer(&led_cdev->blink_timer, jiffies + 1);
 }
 
@@ -219,6 +221,7 @@ void led_stop_software_blink(struct led_classdev *led_cdev)
 	del_timer_sync(&led_cdev->blink_timer);
 	led_cdev->blink_delay_on = 0;
 	led_cdev->blink_delay_off = 0;
+	led_cdev->flags &= ~LED_BLINK_SW;
 }
 EXPORT_SYMBOL_GPL(led_stop_software_blink);
 
@@ -226,10 +229,10 @@ void led_set_brightness(struct led_classdev *led_cdev,
 			enum led_brightness brightness)
 {
 	/*
-	 * In case blinking is on delay brightness setting
+	 * If software blink is active, delay brightness setting
 	 * until the next timer tick.
 	 */
-	if (led_cdev->blink_delay_on || led_cdev->blink_delay_off) {
+	if (led_cdev->flags & LED_BLINK_SW) {
 		/*
 		 * If we need to disable soft blinking delegate this to the
 		 * work queue task to avoid problems in case we are called
diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index 410c39c62dc7..c9f386213e9e 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/leds.h>
 #include <linux/reboot.h>
+#include <linux/suspend.h>
 #include "../leds.h"
 
 static int panic_heartbeats;
@@ -154,6 +155,30 @@ static struct led_trigger heartbeat_led_trigger = {
 	.deactivate = heartbeat_trig_deactivate,
 };
 
+static int heartbeat_pm_notifier(struct notifier_block *nb,
+				 unsigned long pm_event, void *unused)
+{
+	int rc;
+
+	switch (pm_event) {
+	case PM_SUSPEND_PREPARE:
+	case PM_HIBERNATION_PREPARE:
+	case PM_RESTORE_PREPARE:
+		led_trigger_unregister(&heartbeat_led_trigger);
+		break;
+	case PM_POST_SUSPEND:
+	case PM_POST_HIBERNATION:
+	case PM_POST_RESTORE:
+		rc = led_trigger_register(&heartbeat_led_trigger);
+		if (rc)
+			pr_err("could not re-register heartbeat trigger\n");
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
 static int heartbeat_reboot_notifier(struct notifier_block *nb,
 				     unsigned long code, void *unused)
 {
@@ -168,6 +193,10 @@ static int heartbeat_panic_notifier(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
+static struct notifier_block heartbeat_pm_nb = {
+	.notifier_call = heartbeat_pm_notifier,
+};
+
 static struct notifier_block heartbeat_reboot_nb = {
 	.notifier_call = heartbeat_reboot_notifier,
 };
@@ -184,12 +213,14 @@ static int __init heartbeat_trig_init(void)
 		atomic_notifier_chain_register(&panic_notifier_list,
 					       &heartbeat_panic_nb);
 		register_reboot_notifier(&heartbeat_reboot_nb);
+		register_pm_notifier(&heartbeat_pm_nb);
 	}
 	return rc;
 }
 
 static void __exit heartbeat_trig_exit(void)
 {
+	unregister_pm_notifier(&heartbeat_pm_nb);
 	unregister_reboot_notifier(&heartbeat_reboot_nb);
 	atomic_notifier_chain_unregister(&panic_notifier_list,
 					 &heartbeat_panic_nb);
diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c
index b73c6e7d28e4..6f2c8522e14a 100644
--- a/drivers/mcb/mcb-core.c
+++ b/drivers/mcb/mcb-core.c
@@ -61,21 +61,36 @@ static int mcb_probe(struct device *dev)
 	struct mcb_driver *mdrv = to_mcb_driver(dev->driver);
 	struct mcb_device *mdev = to_mcb_device(dev);
 	const struct mcb_device_id *found_id;
+	struct module *carrier_mod;
+	int ret;
 
 	found_id = mcb_match_id(mdrv->id_table, mdev);
 	if (!found_id)
 		return -ENODEV;
 
-	return mdrv->probe(mdev, found_id);
+	carrier_mod = mdev->dev.parent->driver->owner;
+	if (!try_module_get(carrier_mod))
+		return -EINVAL;
+
+	get_device(dev);
+	ret = mdrv->probe(mdev, found_id);
+	if (ret)
+		module_put(carrier_mod);
+
+	return ret;
 }
 
 static int mcb_remove(struct device *dev)
 {
 	struct mcb_driver *mdrv = to_mcb_driver(dev->driver);
 	struct mcb_device *mdev = to_mcb_device(dev);
+	struct module *carrier_mod;
 
 	mdrv->remove(mdev);
 
+	carrier_mod = mdev->dev.parent->driver->owner;
+	module_put(carrier_mod);
+
 	put_device(&mdev->dev);
 
 	return 0;
diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c
index d7723ce772b3..c04bc6afb965 100644
--- a/drivers/media/usb/uvc/uvc_v4l2.c
+++ b/drivers/media/usb/uvc/uvc_v4l2.c
@@ -1274,8 +1274,6 @@ struct uvc_xu_control_mapping32 {
 static int uvc_v4l2_get_xu_mapping(struct uvc_xu_control_mapping *kp,
 			const struct uvc_xu_control_mapping32 __user *up)
 {
-	struct uvc_menu_info __user *umenus;
-	struct uvc_menu_info __user *kmenus;
 	compat_caddr_t p;
 
 	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
@@ -1292,17 +1290,7 @@ static int uvc_v4l2_get_xu_mapping(struct uvc_xu_control_mapping *kp,
 
 	if (__get_user(p, &up->menu_info))
 		return -EFAULT;
-	umenus = compat_ptr(p);
-	if (!access_ok(VERIFY_READ, umenus, kp->menu_count * sizeof(*umenus)))
-		return -EFAULT;
-
-	kmenus = compat_alloc_user_space(kp->menu_count * sizeof(*kmenus));
-	if (kmenus == NULL)
-		return -EFAULT;
-	kp->menu_info = kmenus;
-
-	if (copy_in_user(kmenus, umenus, kp->menu_count * sizeof(*umenus)))
-		return -EFAULT;
+	kp->menu_info = compat_ptr(p);
 
 	return 0;
 }
@@ -1310,10 +1298,6 @@ static int uvc_v4l2_get_xu_mapping(struct uvc_xu_control_mapping *kp,
 static int uvc_v4l2_put_xu_mapping(const struct uvc_xu_control_mapping *kp,
 			struct uvc_xu_control_mapping32 __user *up)
 {
-	struct uvc_menu_info __user *umenus;
-	struct uvc_menu_info __user *kmenus = kp->menu_info;
-	compat_caddr_t p;
-
 	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
 	    __copy_to_user(up, kp, offsetof(typeof(*up), menu_info)) ||
 	    __put_user(kp->menu_count, &up->menu_count))
@@ -1322,16 +1306,6 @@ static int uvc_v4l2_put_xu_mapping(const struct uvc_xu_control_mapping *kp,
 	if (__clear_user(up->reserved, sizeof(up->reserved)))
 		return -EFAULT;
 
-	if (kp->menu_count == 0)
-		return 0;
-
-	if (get_user(p, &up->menu_info))
-		return -EFAULT;
-	umenus = compat_ptr(p);
-
-	if (copy_in_user(umenus, kmenus, kp->menu_count * sizeof(*umenus)))
-		return -EFAULT;
-
 	return 0;
 }
 
@@ -1346,8 +1320,6 @@ struct uvc_xu_control_query32 {
 static int uvc_v4l2_get_xu_query(struct uvc_xu_control_query *kp,
 			const struct uvc_xu_control_query32 __user *up)
 {
-	u8 __user *udata;
-	u8 __user *kdata;
 	compat_caddr_t p;
 
 	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
@@ -1361,17 +1333,7 @@ static int uvc_v4l2_get_xu_query(struct uvc_xu_control_query *kp,
 
 	if (__get_user(p, &up->data))
 		return -EFAULT;
-	udata = compat_ptr(p);
-	if (!access_ok(VERIFY_READ, udata, kp->size))
-		return -EFAULT;
-
-	kdata = compat_alloc_user_space(kp->size);
-	if (kdata == NULL)
-		return -EFAULT;
-	kp->data = kdata;
-
-	if (copy_in_user(kdata, udata, kp->size))
-		return -EFAULT;
+	kp->data = compat_ptr(p);
 
 	return 0;
 }
@@ -1379,26 +1341,10 @@ static int uvc_v4l2_get_xu_query(struct uvc_xu_control_query *kp,
 static int uvc_v4l2_put_xu_query(const struct uvc_xu_control_query *kp,
 			struct uvc_xu_control_query32 __user *up)
 {
-	u8 __user *udata;
-	u8 __user *kdata = kp->data;
-	compat_caddr_t p;
-
 	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
 	    __copy_to_user(up, kp, offsetof(typeof(*up), data)))
 		return -EFAULT;
 
-	if (kp->size == 0)
-		return 0;
-
-	if (get_user(p, &up->data))
-		return -EFAULT;
-	udata = compat_ptr(p);
-	if (!access_ok(VERIFY_READ, udata, kp->size))
-		return -EFAULT;
-
-	if (copy_in_user(udata, kdata, kp->size))
-		return -EFAULT;
-
 	return 0;
 }
 
@@ -1408,47 +1354,44 @@ static int uvc_v4l2_put_xu_query(const struct uvc_xu_control_query *kp,
 static long uvc_v4l2_compat_ioctl32(struct file *file,
 		     unsigned int cmd, unsigned long arg)
 {
+	struct uvc_fh *handle = file->private_data;
 	union {
 		struct uvc_xu_control_mapping xmap;
 		struct uvc_xu_control_query xqry;
 	} karg;
 	void __user *up = compat_ptr(arg);
-	mm_segment_t old_fs;
 	long ret;
 
 	switch (cmd) {
 	case UVCIOC_CTRL_MAP32:
-		cmd = UVCIOC_CTRL_MAP;
 		ret = uvc_v4l2_get_xu_mapping(&karg.xmap, up);
+		if (ret)
+			return ret;
+		ret = uvc_ioctl_ctrl_map(handle->chain, &karg.xmap);
+		if (ret)
+			return ret;
+		ret = uvc_v4l2_put_xu_mapping(&karg.xmap, up);
+		if (ret)
+			return ret;
+
 		break;
 
 	case UVCIOC_CTRL_QUERY32:
-		cmd = UVCIOC_CTRL_QUERY;
 		ret = uvc_v4l2_get_xu_query(&karg.xqry, up);
+		if (ret)
+			return ret;
+		ret = uvc_xu_ctrl_query(handle->chain, &karg.xqry);
+		if (ret)
+			return ret;
+		ret = uvc_v4l2_put_xu_query(&karg.xqry, up);
+		if (ret)
+			return ret;
 		break;
 
 	default:
 		return -ENOIOCTLCMD;
 	}
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	ret = video_ioctl2(file, cmd, (unsigned long)&karg);
-	set_fs(old_fs);
-
-	if (ret < 0)
-		return ret;
-
-	switch (cmd) {
-	case UVCIOC_CTRL_MAP:
-		ret = uvc_v4l2_put_xu_mapping(&karg.xmap, up);
-		break;
-
-	case UVCIOC_CTRL_QUERY:
-		ret = uvc_v4l2_put_xu_query(&karg.xqry, up);
-		break;
-	}
-
 	return ret;
 }
 #endif
diff --git a/drivers/media/v4l2-core/v4l2-mc.c b/drivers/media/v4l2-core/v4l2-mc.c
index ca94bded3386..8bef4331bd51 100644
--- a/drivers/media/v4l2-core/v4l2-mc.c
+++ b/drivers/media/v4l2-core/v4l2-mc.c
@@ -1,7 +1,7 @@
 /*
  * Media Controller ancillary functions
  *
- * Copyright (c) 2016 Mauro Carvalho Chehab <[email protected]>
+ * Copyright (c) 2016 Mauro Carvalho Chehab <[email protected]>
  * Copyright (C) 2016 Shuah Khan <[email protected]>
  * Copyright (C) 2006-2010 Nokia Corporation
  * Copyright (c) 2016 Intel Corporation.
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index af4884ba6b7c..15508df24e5d 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -398,7 +398,7 @@ static void gpmc_cs_bool_timings(int cs, const struct gpmc_bool_timings *p)
 	gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG4,
 			   GPMC_CONFIG4_OEEXTRADELAY, p->oe_extra_delay);
 	gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG4,
-			   GPMC_CONFIG4_OEEXTRADELAY, p->we_extra_delay);
+			   GPMC_CONFIG4_WEEXTRADELAY, p->we_extra_delay);
 	gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG6,
 			   GPMC_CONFIG6_CYCLE2CYCLESAMECSEN,
 			   p->cycle2cyclesamecsen);
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index eed254da63a8..641c1a566687 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -730,7 +730,7 @@ static void mei_cl_wake_all(struct mei_cl *cl)
 	/* synchronized under device mutex */
 	if (waitqueue_active(&cl->wait)) {
 		cl_dbg(dev, cl, "Waking up ctrl write clients!\n");
-		wake_up_interruptible(&cl->wait);
+		wake_up(&cl->wait);
 	}
 }
 
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index c984321d1881..5d438ad3ee32 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1276,7 +1276,7 @@ static int mmc_select_hs200(struct mmc_card *card)
 	 * switch to HS200 mode if bus width is set successfully.
 	 */
 	err = mmc_select_bus_width(card);
-	if (!err) {
+	if (err >= 0) {
 		val = EXT_CSD_TIMING_HS200 |
 		      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 		err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
@@ -1583,7 +1583,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	} else if (mmc_card_hs(card)) {
 		/* Select the desired bus width optionally */
 		err = mmc_select_bus_width(card);
-		if (!err) {
+		if (err >= 0) {
 			err = mmc_select_hs_ddr(card);
 			if (err)
 				goto free_card;
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index 7fc8b7aa83f0..2ee4c21ec55e 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -970,8 +970,8 @@ static const struct sunxi_mmc_clk_delay sun9i_mmc_clk_delays[] = {
 	[SDXC_CLK_400K]		= { .output = 180, .sample = 180 },
 	[SDXC_CLK_25M]		= { .output = 180, .sample =  75 },
 	[SDXC_CLK_50M]		= { .output = 150, .sample = 120 },
-	[SDXC_CLK_50M_DDR]	= { .output =  90, .sample = 120 },
-	[SDXC_CLK_50M_DDR_8BIT]	= { .output =  90, .sample = 120 },
+	[SDXC_CLK_50M_DDR]	= { .output =  54, .sample =  36 },
+	[SDXC_CLK_50M_DDR_8BIT]	= { .output =  72, .sample =  72 },
 };
 
 static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host,
@@ -1129,11 +1129,6 @@ static int sunxi_mmc_probe(struct platform_device *pdev)
 				  MMC_CAP_1_8V_DDR |
 				  MMC_CAP_ERASE | MMC_CAP_SDIO_IRQ;
 
-	/* TODO MMC DDR is not working on A80 */
-	if (of_device_is_compatible(pdev->dev.of_node,
-				    "allwinner,sun9i-a80-mmc"))
-		mmc->caps &= ~MMC_CAP_1_8V_DDR;
-
 	ret = mmc_of_parse(mmc);
 	if (ret)
 		goto error_free_dma;
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index 16baeb51b2bd..ef3618299494 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -1147,11 +1147,17 @@ int ubi_detach_mtd_dev(int ubi_num, int anyway)
  */
 static struct mtd_info * __init open_mtd_by_chdev(const char *mtd_dev)
 {
-	struct kstat stat;
 	int err, minor;
+	struct path path;
+	struct kstat stat;
 
 	/* Probably this is an MTD character device node path */
-	err = vfs_stat(mtd_dev, &stat);
+	err = kern_path(mtd_dev, LOOKUP_FOLLOW, &path);
+	if (err)
+		return ERR_PTR(err);
+
+	err = vfs_getattr(&path, &stat);
+	path_put(&path);
 	if (err)
 		return ERR_PTR(err);
 
@@ -1160,6 +1166,7 @@ static struct mtd_info * __init open_mtd_by_chdev(const char *mtd_dev)
 		return ERR_PTR(-EINVAL);
 
 	minor = MINOR(stat.rdev);
+
 	if (minor & 1)
 		/*
 		 * Just do not think the "/dev/mtdrX" devices support is need,
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index 5780dd1ba79d..ebf517271d29 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -575,6 +575,7 @@ static int recover_peb(struct ubi_device *ubi, int pnum, int vol_id, int lnum,
 	int err, idx = vol_id2idx(ubi, vol_id), new_pnum, data_size, tries = 0;
 	struct ubi_volume *vol = ubi->volumes[idx];
 	struct ubi_vid_hdr *vid_hdr;
+	uint32_t crc;
 
 	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
 	if (!vid_hdr)
@@ -599,14 +600,8 @@ retry:
 		goto out_put;
 	}
 
-	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
-	err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr);
-	if (err) {
-		up_read(&ubi->fm_eba_sem);
-		goto write_error;
-	}
+	ubi_assert(vid_hdr->vol_type == UBI_VID_DYNAMIC);
 
-	data_size = offset + len;
 	mutex_lock(&ubi->buf_mutex);
 	memset(ubi->peb_buf + offset, 0xFF, len);
 
@@ -621,6 +616,19 @@ retry:
 
 	memcpy(ubi->peb_buf + offset, buf, len);
 
+	data_size = offset + len;
+	crc = crc32(UBI_CRC32_INIT, ubi->peb_buf, data_size);
+	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
+	vid_hdr->copy_flag = 1;
+	vid_hdr->data_size = cpu_to_be32(data_size);
+	vid_hdr->data_crc = cpu_to_be32(crc);
+	err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr);
+	if (err) {
+		mutex_unlock(&ubi->buf_mutex);
+		up_read(&ubi->fm_eba_sem);
+		goto write_error;
+	}
+
 	err = ubi_io_write_data(ubi, ubi->peb_buf, new_pnum, 0, data_size);
 	if (err) {
 		mutex_unlock(&ubi->buf_mutex);
diff --git a/drivers/mtd/ubi/kapi.c b/drivers/mtd/ubi/kapi.c
index 348dbbcbedc8..a9e2cef7c95c 100644
--- a/drivers/mtd/ubi/kapi.c
+++ b/drivers/mtd/ubi/kapi.c
@@ -302,6 +302,7 @@ EXPORT_SYMBOL_GPL(ubi_open_volume_nm);
 struct ubi_volume_desc *ubi_open_volume_path(const char *pathname, int mode)
 {
 	int error, ubi_num, vol_id;
+	struct path path;
 	struct kstat stat;
 
 	dbg_gen("open volume %s, mode %d", pathname, mode);
@@ -309,7 +310,12 @@ struct ubi_volume_desc *ubi_open_volume_path(const char *pathname, int mode)
 	if (!pathname || !*pathname)
 		return ERR_PTR(-EINVAL);
 
-	error = vfs_stat(pathname, &stat);
+	error = kern_path(pathname, LOOKUP_FOLLOW, &path);
+	if (error)
+		return ERR_PTR(error);
+
+	error = vfs_getattr(&path, &stat);
+	path_put(&path);
 	if (error)
 		return ERR_PTR(error);
 
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index b9304a295f86..ca81f46ea1aa 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -657,6 +657,20 @@ static void __set_agg_ports_ready(struct aggregator *aggregator, int val)
 	}
 }
 
+static int __agg_active_ports(struct aggregator *agg)
+{
+	struct port *port;
+	int active = 0;
+
+	for (port = agg->lag_ports; port;
+	     port = port->next_port_in_aggregator) {
+		if (port->is_enabled)
+			active++;
+	}
+
+	return active;
+}
+
 /**
  * __get_agg_bandwidth - get the total bandwidth of an aggregator
  * @aggregator: the aggregator we're looking at
@@ -664,39 +678,40 @@ static void __set_agg_ports_ready(struct aggregator *aggregator, int val)
  */
 static u32 __get_agg_bandwidth(struct aggregator *aggregator)
 {
+	int nports = __agg_active_ports(aggregator);
 	u32 bandwidth = 0;
 
-	if (aggregator->num_of_ports) {
+	if (nports) {
 		switch (__get_link_speed(aggregator->lag_ports)) {
 		case AD_LINK_SPEED_1MBPS:
-			bandwidth = aggregator->num_of_ports;
+			bandwidth = nports;
 			break;
 		case AD_LINK_SPEED_10MBPS:
-			bandwidth = aggregator->num_of_ports * 10;
+			bandwidth = nports * 10;
 			break;
 		case AD_LINK_SPEED_100MBPS:
-			bandwidth = aggregator->num_of_ports * 100;
+			bandwidth = nports * 100;
 			break;
 		case AD_LINK_SPEED_1000MBPS:
-			bandwidth = aggregator->num_of_ports * 1000;
+			bandwidth = nports * 1000;
 			break;
 		case AD_LINK_SPEED_2500MBPS:
-			bandwidth = aggregator->num_of_ports * 2500;
+			bandwidth = nports * 2500;
 			break;
 		case AD_LINK_SPEED_10000MBPS:
-			bandwidth = aggregator->num_of_ports * 10000;
+			bandwidth = nports * 10000;
 			break;
 		case AD_LINK_SPEED_20000MBPS:
-			bandwidth = aggregator->num_of_ports * 20000;
+			bandwidth = nports * 20000;
 			break;
 		case AD_LINK_SPEED_40000MBPS:
-			bandwidth = aggregator->num_of_ports * 40000;
+			bandwidth = nports * 40000;
 			break;
 		case AD_LINK_SPEED_56000MBPS:
-			bandwidth = aggregator->num_of_ports * 56000;
+			bandwidth = nports * 56000;
 			break;
 		case AD_LINK_SPEED_100000MBPS:
-			bandwidth = aggregator->num_of_ports * 100000;
+			bandwidth = nports * 100000;
 			break;
 		default:
 			bandwidth = 0; /* to silence the compiler */
@@ -1530,10 +1545,10 @@ static struct aggregator *ad_agg_selection_test(struct aggregator *best,
 
 	switch (__get_agg_selection_mode(curr->lag_ports)) {
 	case BOND_AD_COUNT:
-		if (curr->num_of_ports > best->num_of_ports)
+		if (__agg_active_ports(curr) > __agg_active_ports(best))
 			return curr;
 
-		if (curr->num_of_ports < best->num_of_ports)
+		if (__agg_active_ports(curr) < __agg_active_ports(best))
 			return best;
 
 		/*FALLTHROUGH*/
@@ -1561,8 +1576,14 @@ static int agg_device_up(const struct aggregator *agg)
 	if (!port)
 		return 0;
 
-	return netif_running(port->slave->dev) &&
-	       netif_carrier_ok(port->slave->dev);
+	for (port = agg->lag_ports; port;
+	     port = port->next_port_in_aggregator) {
+		if (netif_running(port->slave->dev) &&
+		    netif_carrier_ok(port->slave->dev))
+			return 1;
+	}
+
+	return 0;
 }
 
 /**
@@ -1610,7 +1631,7 @@ static void ad_agg_selection_logic(struct aggregator *agg,
 
 		agg->is_active = 0;
 
-		if (agg->num_of_ports && agg_device_up(agg))
+		if (__agg_active_ports(agg) && agg_device_up(agg))
 			best = ad_agg_selection_test(best, agg);
 	}
 
@@ -1622,7 +1643,7 @@ static void ad_agg_selection_logic(struct aggregator *agg,
 		 * answering partner.
 		 */
 		if (active && active->lag_ports &&
-		    active->lag_ports->is_enabled &&
+		    __agg_active_ports(active) &&
 		    (__agg_has_partner(active) ||
 		     (!__agg_has_partner(active) &&
 		     !__agg_has_partner(best)))) {
@@ -2133,7 +2154,7 @@ void bond_3ad_unbind_slave(struct slave *slave)
 				else
 					temp_aggregator->lag_ports = temp_port->next_port_in_aggregator;
 				temp_aggregator->num_of_ports--;
-				if (temp_aggregator->num_of_ports == 0) {
+				if (__agg_active_ports(temp_aggregator) == 0) {
 					select_new_active_agg = temp_aggregator->is_active;
 					ad_clear_agg(temp_aggregator);
 					if (select_new_active_agg) {
@@ -2432,7 +2453,9 @@ void bond_3ad_adapter_speed_duplex_changed(struct slave *slave)
  */
 void bond_3ad_handle_link_change(struct slave *slave, char link)
 {
+	struct aggregator *agg;
 	struct port *port;
+	bool dummy;
 
 	port = &(SLAVE_AD_INFO(slave)->port);
 
@@ -2459,6 +2482,9 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
 		port->is_enabled = false;
 		ad_update_actor_keys(port, true);
 	}
+	agg = __get_first_agg(port);
+	ad_agg_selection_logic(agg, &dummy);
+
 	netdev_dbg(slave->bond->dev, "Port %d changed link status to %s\n",
 		   port->actor_port_number,
 		   link == BOND_LINK_UP ? "UP" : "DOWN");
@@ -2499,7 +2525,7 @@ int bond_3ad_set_carrier(struct bonding *bond)
 	active = __get_active_agg(&(SLAVE_AD_INFO(first_slave)->aggregator));
 	if (active) {
 		/* are enough slaves available to consider link up? */
-		if (active->num_of_ports < bond->params.min_links) {
+		if (__agg_active_ports(active) < bond->params.min_links) {
 			if (netif_carrier_ok(bond->dev)) {
 				netif_carrier_off(bond->dev);
 				goto out;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 941ec99cd3b6..480d73ac7d1b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4137,6 +4137,8 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_add_slave		= bond_enslave,
 	.ndo_del_slave		= bond_release,
 	.ndo_fix_features	= bond_fix_features,
+	.ndo_neigh_construct	= netdev_default_l2upper_neigh_construct,
+	.ndo_neigh_destroy	= netdev_default_l2upper_neigh_destroy,
 	.ndo_bridge_setlink	= switchdev_port_bridge_setlink,
 	.ndo_bridge_getlink	= switchdev_port_bridge_getlink,
 	.ndo_bridge_dellink	= switchdev_port_bridge_dellink,
@@ -4607,26 +4609,6 @@ static int bond_check_params(struct bond_params *params)
 	return 0;
 }
 
-static struct lock_class_key bonding_netdev_xmit_lock_key;
-static struct lock_class_key bonding_netdev_addr_lock_key;
-static struct lock_class_key bonding_tx_busylock_key;
-
-static void bond_set_lockdep_class_one(struct net_device *dev,
-				       struct netdev_queue *txq,
-				       void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock,
-			  &bonding_netdev_xmit_lock_key);
-}
-
-static void bond_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock,
-			  &bonding_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, bond_set_lockdep_class_one, NULL);
-	dev->qdisc_tx_busylock = &bonding_tx_busylock_key;
-}
-
 /* Called from registration process */
 static int bond_init(struct net_device *bond_dev)
 {
@@ -4639,7 +4621,7 @@ static int bond_init(struct net_device *bond_dev)
 	if (!bond->wq)
 		return -ENOMEM;
 
-	bond_set_lockdep_class(bond_dev);
+	netdev_lockdep_set_classes(bond_dev);
 
 	list_add_tail(&bond->bond_list, &bn->dev_list);
 
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 0d40aef928e2..22570ea3a8d2 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -104,16 +104,6 @@ config CAN_JANZ_ICAN3
 	  This driver can also be built as a module. If so, the module will be
 	  called janz-ican3.ko.
 
-config CAN_RCAR
-	tristate "Renesas R-Car CAN controller"
-	depends on ARCH_RENESAS || ARM
-	---help---
-	  Say Y here if you want to use CAN controller found on Renesas R-Car
-	  SoCs.
-
-	  To compile this driver as a module, choose M here: the module will
-	  be called rcar_can.
-
 config CAN_SUN4I
 	tristate "Allwinner A10 CAN controller"
 	depends on MACH_SUN4I || MACH_SUN7I || COMPILE_TEST
@@ -152,6 +142,7 @@ source "drivers/net/can/cc770/Kconfig"
 source "drivers/net/can/ifi_canfd/Kconfig"
 source "drivers/net/can/m_can/Kconfig"
 source "drivers/net/can/mscan/Kconfig"
+source "drivers/net/can/rcar/Kconfig"
 source "drivers/net/can/sja1000/Kconfig"
 source "drivers/net/can/softing/Kconfig"
 source "drivers/net/can/spi/Kconfig"
diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile
index e3db0c807f55..26ba4b794a0b 100644
--- a/drivers/net/can/Makefile
+++ b/drivers/net/can/Makefile
@@ -10,6 +10,7 @@ can-dev-y			:= dev.o
 
 can-dev-$(CONFIG_CAN_LEDS)	+= led.o
 
+obj-y				+= rcar/
 obj-y				+= spi/
 obj-y				+= usb/
 obj-y				+= softing/
@@ -24,7 +25,6 @@ obj-$(CONFIG_CAN_IFI_CANFD)	+= ifi_canfd/
 obj-$(CONFIG_CAN_JANZ_ICAN3)	+= janz-ican3.o
 obj-$(CONFIG_CAN_MSCAN)		+= mscan/
 obj-$(CONFIG_CAN_M_CAN)		+= m_can/
-obj-$(CONFIG_CAN_RCAR)		+= rcar_can.o
 obj-$(CONFIG_CAN_SJA1000)	+= sja1000/
 obj-$(CONFIG_CAN_SUN4I)		+= sun4i_can.o
 obj-$(CONFIG_CAN_TI_HECC)	+= ti_hecc.o
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 8b3275d7792a..8f5e93cb7975 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -712,9 +712,10 @@ static int at91_poll_rx(struct net_device *dev, int quota)
 
 	/* upper group completed, look again in lower */
 	if (priv->rx_next > get_mb_rx_low_last(priv) &&
-	    quota > 0 && mb > get_mb_rx_last(priv)) {
+	    mb > get_mb_rx_last(priv)) {
 		priv->rx_next = get_mb_rx_first(priv);
-		goto again;
+		if (quota > 0)
+			goto again;
 	}
 
 	return received;
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index f91b094288da..e3dccd3200d5 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -332,9 +332,23 @@ static void c_can_setup_tx_object(struct net_device *dev, int iface,
 
 	priv->write_reg(priv, C_CAN_IFACE(MSGCTRL_REG, iface), ctrl);
 
-	for (i = 0; i < frame->can_dlc; i += 2) {
-		priv->write_reg(priv, C_CAN_IFACE(DATA1_REG, iface) + i / 2,
-				frame->data[i] | (frame->data[i + 1] << 8));
+	if (priv->type == BOSCH_D_CAN) {
+		u32 data = 0, dreg = C_CAN_IFACE(DATA1_REG, iface);
+
+		for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+			data = (u32)frame->data[i];
+			data |= (u32)frame->data[i + 1] << 8;
+			data |= (u32)frame->data[i + 2] << 16;
+			data |= (u32)frame->data[i + 3] << 24;
+			priv->write_reg32(priv, dreg, data);
+		}
+	} else {
+		for (i = 0; i < frame->can_dlc; i += 2) {
+			priv->write_reg(priv,
+					C_CAN_IFACE(DATA1_REG, iface) + i / 2,
+					frame->data[i] |
+					(frame->data[i + 1] << 8));
+		}
 	}
 }
 
@@ -402,10 +416,20 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl)
 	} else {
 		int i, dreg = C_CAN_IFACE(DATA1_REG, iface);
 
-		for (i = 0; i < frame->can_dlc; i += 2, dreg ++) {
-			data = priv->read_reg(priv, dreg);
-			frame->data[i] = data;
-			frame->data[i + 1] = data >> 8;
+		if (priv->type == BOSCH_D_CAN) {
+			for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+				data = priv->read_reg32(priv, dreg);
+				frame->data[i] = data;
+				frame->data[i + 1] = data >> 8;
+				frame->data[i + 2] = data >> 16;
+				frame->data[i + 3] = data >> 24;
+			}
+		} else {
+			for (i = 0; i < frame->can_dlc; i += 2, dreg++) {
+				data = priv->read_reg(priv, dreg);
+				frame->data[i] = data;
+				frame->data[i + 1] = data >> 8;
+			}
 		}
 	}
 
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 910c12e2638e..e21f7cc5ae4d 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -69,6 +69,7 @@ EXPORT_SYMBOL_GPL(can_len2dlc);
 
 #ifdef CONFIG_CAN_CALC_BITTIMING
 #define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */
+#define CAN_CALC_SYNC_SEG 1
 
 /*
  * Bit-timing calculation derived from:
@@ -83,98 +84,126 @@ EXPORT_SYMBOL_GPL(can_len2dlc);
  * registers of the CAN controller. You can find more information
  * in the header file linux/can/netlink.h.
  */
-static int can_update_spt(const struct can_bittiming_const *btc,
-			  int sampl_pt, int tseg, int *tseg1, int *tseg2)
+static int can_update_sample_point(const struct can_bittiming_const *btc,
+			  unsigned int sample_point_nominal, unsigned int tseg,
+			  unsigned int *tseg1_ptr, unsigned int *tseg2_ptr,
+			  unsigned int *sample_point_error_ptr)
 {
-	*tseg2 = tseg + 1 - (sampl_pt * (tseg + 1)) / 1000;
-	if (*tseg2 < btc->tseg2_min)
-		*tseg2 = btc->tseg2_min;
-	if (*tseg2 > btc->tseg2_max)
-		*tseg2 = btc->tseg2_max;
-	*tseg1 = tseg - *tseg2;
-	if (*tseg1 > btc->tseg1_max) {
-		*tseg1 = btc->tseg1_max;
-		*tseg2 = tseg - *tseg1;
+	unsigned int sample_point_error, best_sample_point_error = UINT_MAX;
+	unsigned int sample_point, best_sample_point = 0;
+	unsigned int tseg1, tseg2;
+	int i;
+
+	for (i = 0; i <= 1; i++) {
+		tseg2 = tseg + CAN_CALC_SYNC_SEG - (sample_point_nominal * (tseg + CAN_CALC_SYNC_SEG)) / 1000 - i;
+		tseg2 = clamp(tseg2, btc->tseg2_min, btc->tseg2_max);
+		tseg1 = tseg - tseg2;
+		if (tseg1 > btc->tseg1_max) {
+			tseg1 = btc->tseg1_max;
+			tseg2 = tseg - tseg1;
+		}
+
+		sample_point = 1000 * (tseg + CAN_CALC_SYNC_SEG - tseg2) / (tseg + CAN_CALC_SYNC_SEG);
+		sample_point_error = abs(sample_point_nominal - sample_point);
+
+		if ((sample_point <= sample_point_nominal) && (sample_point_error < best_sample_point_error)) {
+			best_sample_point = sample_point;
+			best_sample_point_error = sample_point_error;
+			*tseg1_ptr = tseg1;
+			*tseg2_ptr = tseg2;
+		}
 	}
-	return 1000 * (tseg + 1 - *tseg2) / (tseg + 1);
+
+	if (sample_point_error_ptr)
+		*sample_point_error_ptr = best_sample_point_error;
+
+	return best_sample_point;
 }
 
 static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt,
 			      const struct can_bittiming_const *btc)
 {
 	struct can_priv *priv = netdev_priv(dev);
-	long best_error = 1000000000, error = 0;
-	int best_tseg = 0, best_brp = 0, brp = 0;
-	int tsegall, tseg = 0, tseg1 = 0, tseg2 = 0;
-	int spt_error = 1000, spt = 0, sampl_pt;
-	long rate;
+	unsigned int bitrate;			/* current bitrate */
+	unsigned int bitrate_error;		/* difference between current and nominal value */
+	unsigned int best_bitrate_error = UINT_MAX;
+	unsigned int sample_point_error;	/* difference between current and nominal value */
+	unsigned int best_sample_point_error = UINT_MAX;
+	unsigned int sample_point_nominal;	/* nominal sample point */
+	unsigned int best_tseg = 0;		/* current best value for tseg */
+	unsigned int best_brp = 0;		/* current best value for brp */
+	unsigned int brp, tsegall, tseg, tseg1 = 0, tseg2 = 0;
 	u64 v64;
 
 	/* Use CiA recommended sample points */
 	if (bt->sample_point) {
-		sampl_pt = bt->sample_point;
+		sample_point_nominal = bt->sample_point;
 	} else {
 		if (bt->bitrate > 800000)
-			sampl_pt = 750;
+			sample_point_nominal = 750;
 		else if (bt->bitrate > 500000)
-			sampl_pt = 800;
+			sample_point_nominal = 800;
 		else
-			sampl_pt = 875;
+			sample_point_nominal = 875;
 	}
 
 	/* tseg even = round down, odd = round up */
 	for (tseg = (btc->tseg1_max + btc->tseg2_max) * 2 + 1;
 	     tseg >= (btc->tseg1_min + btc->tseg2_min) * 2; tseg--) {
-		tsegall = 1 + tseg / 2;
+		tsegall = CAN_CALC_SYNC_SEG + tseg / 2;
+
 		/* Compute all possible tseg choices (tseg=tseg1+tseg2) */
 		brp = priv->clock.freq / (tsegall * bt->bitrate) + tseg % 2;
-		/* chose brp step which is possible in system */
+
+		/* choose brp step which is possible in system */
 		brp = (brp / btc->brp_inc) * btc->brp_inc;
 		if ((brp < btc->brp_min) || (brp > btc->brp_max))
 			continue;
-		rate = priv->clock.freq / (brp * tsegall);
-		error = bt->bitrate - rate;
+
+		bitrate = priv->clock.freq / (brp * tsegall);
+		bitrate_error = abs(bt->bitrate - bitrate);
+
 		/* tseg brp biterror */
-		if (error < 0)
-			error = -error;
-		if (error > best_error)
+		if (bitrate_error > best_bitrate_error)
 			continue;
-		best_error = error;
-		if (error == 0) {
-			spt = can_update_spt(btc, sampl_pt, tseg / 2,
-					     &tseg1, &tseg2);
-			error = sampl_pt - spt;
-			if (error < 0)
-				error = -error;
-			if (error > spt_error)
-				continue;
-			spt_error = error;
-		}
+
+		/* reset sample point error if we have a better bitrate */
+		if (bitrate_error < best_bitrate_error)
+			best_sample_point_error = UINT_MAX;
+
+		can_update_sample_point(btc, sample_point_nominal, tseg / 2, &tseg1, &tseg2, &sample_point_error);
+		if (sample_point_error > best_sample_point_error)
+			continue;
+
+		best_sample_point_error = sample_point_error;
+		best_bitrate_error = bitrate_error;
 		best_tseg = tseg / 2;
 		best_brp = brp;
-		if (error == 0)
+
+		if (bitrate_error == 0 && sample_point_error == 0)
 			break;
 	}
 
-	if (best_error) {
+	if (best_bitrate_error) {
 		/* Error in one-tenth of a percent */
-		error = (best_error * 1000) / bt->bitrate;
-		if (error > CAN_CALC_MAX_ERROR) {
+		v64 = (u64)best_bitrate_error * 1000;
+		do_div(v64, bt->bitrate);
+		bitrate_error = (u32)v64;
+		if (bitrate_error > CAN_CALC_MAX_ERROR) {
 			netdev_err(dev,
-				   "bitrate error %ld.%ld%% too high\n",
-				   error / 10, error % 10);
+				   "bitrate error %d.%d%% too high\n",
+				   bitrate_error / 10, bitrate_error % 10);
 			return -EDOM;
-		} else {
-			netdev_warn(dev, "bitrate error %ld.%ld%%\n",
-				    error / 10, error % 10);
 		}
+		netdev_warn(dev, "bitrate error %d.%d%%\n",
+			    bitrate_error / 10, bitrate_error % 10);
 	}
 
 	/* real sample point */
-	bt->sample_point = can_update_spt(btc, sampl_pt, best_tseg,
-					  &tseg1, &tseg2);
+	bt->sample_point = can_update_sample_point(btc, sample_point_nominal, best_tseg,
+					  &tseg1, &tseg2, NULL);
 
-	v64 = (u64)best_brp * 1000000000UL;
+	v64 = (u64)best_brp * 1000 * 1000 * 1000;
 	do_div(v64, priv->clock.freq);
 	bt->tq = (u32)v64;
 	bt->prop_seg = tseg1 / 2;
@@ -182,9 +211,9 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt,
 	bt->phase_seg2 = tseg2;
 
 	/* check for sjw user settings */
-	if (!bt->sjw || !btc->sjw_max)
+	if (!bt->sjw || !btc->sjw_max) {
 		bt->sjw = 1;
-	else {
+	} else {
 		/* bt->sjw is at least 1 -> sanitize upper bound to sjw_max */
 		if (bt->sjw > btc->sjw_max)
 			bt->sjw = btc->sjw_max;
@@ -194,8 +223,9 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt,
 	}
 
 	bt->brp = best_brp;
-	/* real bit-rate */
-	bt->bitrate = priv->clock.freq / (bt->brp * (tseg1 + tseg2 + 1));
+
+	/* real bitrate */
+	bt->bitrate = priv->clock.freq / (bt->brp * (CAN_CALC_SYNC_SEG + tseg1 + tseg2));
 
 	return 0;
 }
@@ -798,6 +828,9 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[])
 	 * - control mode with CAN_CTRLMODE_FD set
 	 */
 
+	if (!data)
+		return 0;
+
 	if (data[IFLA_CAN_CTRLMODE]) {
 		struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]);
 
@@ -1008,6 +1041,11 @@ static int can_newlink(struct net *src_net, struct net_device *dev,
 	return -EOPNOTSUPP;
 }
 
+static void can_dellink(struct net_device *dev, struct list_head *head)
+{
+	return;
+}
+
 static struct rtnl_link_ops can_link_ops __read_mostly = {
 	.kind		= "can",
 	.maxtype	= IFLA_CAN_MAX,
@@ -1016,6 +1054,7 @@ static struct rtnl_link_ops can_link_ops __read_mostly = {
 	.validate	= can_validate,
 	.newlink	= can_newlink,
 	.changelink	= can_changelink,
+	.dellink	= can_dellink,
 	.get_size	= can_get_size,
 	.fill_info	= can_fill_info,
 	.get_xstats_size = can_get_xstats_size,
diff --git a/drivers/net/can/rcar/Kconfig b/drivers/net/can/rcar/Kconfig
new file mode 100644
index 000000000000..7b03a3a37db7
--- /dev/null
+++ b/drivers/net/can/rcar/Kconfig
@@ -0,0 +1,21 @@
+config CAN_RCAR
+	tristate "Renesas R-Car CAN controller"
+	depends on ARCH_RENESAS || ARM
+	---help---
+	  Say Y here if you want to use CAN controller found on Renesas R-Car
+	  SoCs.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called rcar_can.
+
+config CAN_RCAR_CANFD
+	tristate "Renesas R-Car CAN FD controller"
+	depends on ARCH_RENESAS || ARM
+	---help---
+	  Say Y here if you want to use CAN FD controller found on
+	  Renesas R-Car SoCs. The driver puts the controller in CAN FD only
+	  mode, which can interoperate with CAN2.0 nodes but does not support
+	  dedicated CAN 2.0 mode.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called rcar_canfd.
diff --git a/drivers/net/can/rcar/Makefile b/drivers/net/can/rcar/Makefile
new file mode 100644
index 000000000000..08de36a4cfcc
--- /dev/null
+++ b/drivers/net/can/rcar/Makefile
@@ -0,0 +1,6 @@
+#
+#  Makefile for the Renesas R-Car CAN & CAN FD controller drivers
+#
+
+obj-$(CONFIG_CAN_RCAR)		+= rcar_can.o
+obj-$(CONFIG_CAN_RCAR_CANFD)	+= rcar_canfd.o
diff --git a/drivers/net/can/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index 788459f6bf5c..788459f6bf5c 100644
--- a/drivers/net/can/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
new file mode 100644
index 000000000000..43cdd5544b0c
--- /dev/null
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -0,0 +1,1858 @@
+/* Renesas R-Car CAN FD device driver
+ *
+ * Copyright (C) 2015 Renesas Electronics Corp.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/* The R-Car CAN FD controller can operate in either one of the below two modes
+ *  - CAN FD only mode
+ *  - Classical CAN (CAN 2.0) only mode
+ *
+ * This driver puts the controller in CAN FD only mode by default. In this
+ * mode, the controller acts as a CAN FD node that can also interoperate with
+ * CAN 2.0 nodes.
+ *
+ * To switch the controller to Classical CAN (CAN 2.0) only mode, add
+ * "renesas,no-can-fd" optional property to the device tree node. A h/w reset is
+ * also required to switch modes.
+ *
+ * Note: The h/w manual register naming convention is clumsy and not acceptable
+ * to use as it is in the driver. However, those names are added as comments
+ * wherever it is modified to a readable name.
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/platform_device.h>
+#include <linux/can/led.h>
+#include <linux/can/dev.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/iopoll.h>
+
+#define RCANFD_DRV_NAME			"rcar_canfd"
+
+/* Global register bits */
+
+/* RSCFDnCFDGRMCFG */
+#define RCANFD_GRMCFG_RCMC		BIT(0)
+
+/* RSCFDnCFDGCFG / RSCFDnGCFG */
+#define RCANFD_GCFG_EEFE		BIT(6)
+#define RCANFD_GCFG_CMPOC		BIT(5)	/* CAN FD only */
+#define RCANFD_GCFG_DCS			BIT(4)
+#define RCANFD_GCFG_DCE			BIT(1)
+#define RCANFD_GCFG_TPRI		BIT(0)
+
+/* RSCFDnCFDGCTR / RSCFDnGCTR */
+#define RCANFD_GCTR_TSRST		BIT(16)
+#define RCANFD_GCTR_CFMPOFIE		BIT(11)	/* CAN FD only */
+#define RCANFD_GCTR_THLEIE		BIT(10)
+#define RCANFD_GCTR_MEIE		BIT(9)
+#define RCANFD_GCTR_DEIE		BIT(8)
+#define RCANFD_GCTR_GSLPR		BIT(2)
+#define RCANFD_GCTR_GMDC_MASK		(0x3)
+#define RCANFD_GCTR_GMDC_GOPM		(0x0)
+#define RCANFD_GCTR_GMDC_GRESET		(0x1)
+#define RCANFD_GCTR_GMDC_GTEST		(0x2)
+
+/* RSCFDnCFDGSTS / RSCFDnGSTS */
+#define RCANFD_GSTS_GRAMINIT		BIT(3)
+#define RCANFD_GSTS_GSLPSTS		BIT(2)
+#define RCANFD_GSTS_GHLTSTS		BIT(1)
+#define RCANFD_GSTS_GRSTSTS		BIT(0)
+/* Non-operational status */
+#define RCANFD_GSTS_GNOPM		(BIT(0) | BIT(1) | BIT(2) | BIT(3))
+
+/* RSCFDnCFDGERFL / RSCFDnGERFL */
+#define RCANFD_GERFL_EEF1		BIT(17)
+#define RCANFD_GERFL_EEF0		BIT(16)
+#define RCANFD_GERFL_CMPOF		BIT(3)	/* CAN FD only */
+#define RCANFD_GERFL_THLES		BIT(2)
+#define RCANFD_GERFL_MES		BIT(1)
+#define RCANFD_GERFL_DEF		BIT(0)
+
+#define RCANFD_GERFL_ERR(gpriv, x)	((x) & (RCANFD_GERFL_EEF1 |\
+					RCANFD_GERFL_EEF0 | RCANFD_GERFL_MES |\
+					(gpriv->fdmode ?\
+					 RCANFD_GERFL_CMPOF : 0)))
+
+/* AFL Rx rules registers */
+
+/* RSCFDnCFDGAFLCFG0 / RSCFDnGAFLCFG0 */
+#define RCANFD_GAFLCFG_SETRNC(n, x)	(((x) & 0xff) << (24 - n * 8))
+#define RCANFD_GAFLCFG_GETRNC(n, x)	(((x) >> (24 - n * 8)) & 0xff)
+
+/* RSCFDnCFDGAFLECTR / RSCFDnGAFLECTR */
+#define RCANFD_GAFLECTR_AFLDAE		BIT(8)
+#define RCANFD_GAFLECTR_AFLPN(x)	((x) & 0x1f)
+
+/* RSCFDnCFDGAFLIDj / RSCFDnGAFLIDj */
+#define RCANFD_GAFLID_GAFLLB		BIT(29)
+
+/* RSCFDnCFDGAFLP1_j / RSCFDnGAFLP1_j */
+#define RCANFD_GAFLP1_GAFLFDP(x)	(1 << (x))
+
+/* Channel register bits */
+
+/* RSCFDnCmCFG - Classical CAN only */
+#define RCANFD_CFG_SJW(x)		(((x) & 0x3) << 24)
+#define RCANFD_CFG_TSEG2(x)		(((x) & 0x7) << 20)
+#define RCANFD_CFG_TSEG1(x)		(((x) & 0xf) << 16)
+#define RCANFD_CFG_BRP(x)		(((x) & 0x3ff) << 0)
+
+/* RSCFDnCFDCmNCFG - CAN FD only */
+#define RCANFD_NCFG_NTSEG2(x)		(((x) & 0x1f) << 24)
+#define RCANFD_NCFG_NTSEG1(x)		(((x) & 0x7f) << 16)
+#define RCANFD_NCFG_NSJW(x)		(((x) & 0x1f) << 11)
+#define RCANFD_NCFG_NBRP(x)		(((x) & 0x3ff) << 0)
+
+/* RSCFDnCFDCmCTR / RSCFDnCmCTR */
+#define RCANFD_CCTR_CTME		BIT(24)
+#define RCANFD_CCTR_ERRD		BIT(23)
+#define RCANFD_CCTR_BOM_MASK		(0x3 << 21)
+#define RCANFD_CCTR_BOM_ISO		(0x0 << 21)
+#define RCANFD_CCTR_BOM_BENTRY		(0x1 << 21)
+#define RCANFD_CCTR_BOM_BEND		(0x2 << 21)
+#define RCANFD_CCTR_TDCVFIE		BIT(19)
+#define RCANFD_CCTR_SOCOIE		BIT(18)
+#define RCANFD_CCTR_EOCOIE		BIT(17)
+#define RCANFD_CCTR_TAIE		BIT(16)
+#define RCANFD_CCTR_ALIE		BIT(15)
+#define RCANFD_CCTR_BLIE		BIT(14)
+#define RCANFD_CCTR_OLIE		BIT(13)
+#define RCANFD_CCTR_BORIE		BIT(12)
+#define RCANFD_CCTR_BOEIE		BIT(11)
+#define RCANFD_CCTR_EPIE		BIT(10)
+#define RCANFD_CCTR_EWIE		BIT(9)
+#define RCANFD_CCTR_BEIE		BIT(8)
+#define RCANFD_CCTR_CSLPR		BIT(2)
+#define RCANFD_CCTR_CHMDC_MASK		(0x3)
+#define RCANFD_CCTR_CHDMC_COPM		(0x0)
+#define RCANFD_CCTR_CHDMC_CRESET	(0x1)
+#define RCANFD_CCTR_CHDMC_CHLT		(0x2)
+
+/* RSCFDnCFDCmSTS / RSCFDnCmSTS */
+#define RCANFD_CSTS_COMSTS		BIT(7)
+#define RCANFD_CSTS_RECSTS		BIT(6)
+#define RCANFD_CSTS_TRMSTS		BIT(5)
+#define RCANFD_CSTS_BOSTS		BIT(4)
+#define RCANFD_CSTS_EPSTS		BIT(3)
+#define RCANFD_CSTS_SLPSTS		BIT(2)
+#define RCANFD_CSTS_HLTSTS		BIT(1)
+#define RCANFD_CSTS_CRSTSTS		BIT(0)
+
+#define RCANFD_CSTS_TECCNT(x)		(((x) >> 24) & 0xff)
+#define RCANFD_CSTS_RECCNT(x)		(((x) >> 16) & 0xff)
+
+/* RSCFDnCFDCmERFL / RSCFDnCmERFL */
+#define RCANFD_CERFL_ADERR		BIT(14)
+#define RCANFD_CERFL_B0ERR		BIT(13)
+#define RCANFD_CERFL_B1ERR		BIT(12)
+#define RCANFD_CERFL_CERR		BIT(11)
+#define RCANFD_CERFL_AERR		BIT(10)
+#define RCANFD_CERFL_FERR		BIT(9)
+#define RCANFD_CERFL_SERR		BIT(8)
+#define RCANFD_CERFL_ALF		BIT(7)
+#define RCANFD_CERFL_BLF		BIT(6)
+#define RCANFD_CERFL_OVLF		BIT(5)
+#define RCANFD_CERFL_BORF		BIT(4)
+#define RCANFD_CERFL_BOEF		BIT(3)
+#define RCANFD_CERFL_EPF		BIT(2)
+#define RCANFD_CERFL_EWF		BIT(1)
+#define RCANFD_CERFL_BEF		BIT(0)
+
+#define RCANFD_CERFL_ERR(x)		((x) & (0x7fff)) /* above bits 14:0 */
+
+/* RSCFDnCFDCmDCFG */
+#define RCANFD_DCFG_DSJW(x)		(((x) & 0x7) << 24)
+#define RCANFD_DCFG_DTSEG2(x)		(((x) & 0x7) << 20)
+#define RCANFD_DCFG_DTSEG1(x)		(((x) & 0xf) << 16)
+#define RCANFD_DCFG_DBRP(x)		(((x) & 0xff) << 0)
+
+/* RSCFDnCFDCmFDCFG */
+#define RCANFD_FDCFG_TDCE		BIT(9)
+#define RCANFD_FDCFG_TDCOC		BIT(8)
+#define RCANFD_FDCFG_TDCO(x)		(((x) & 0x7f) >> 16)
+
+/* RSCFDnCFDRFCCx */
+#define RCANFD_RFCC_RFIM		BIT(12)
+#define RCANFD_RFCC_RFDC(x)		(((x) & 0x7) << 8)
+#define RCANFD_RFCC_RFPLS(x)		(((x) & 0x7) << 4)
+#define RCANFD_RFCC_RFIE		BIT(1)
+#define RCANFD_RFCC_RFE			BIT(0)
+
+/* RSCFDnCFDRFSTSx */
+#define RCANFD_RFSTS_RFIF		BIT(3)
+#define RCANFD_RFSTS_RFMLT		BIT(2)
+#define RCANFD_RFSTS_RFFLL		BIT(1)
+#define RCANFD_RFSTS_RFEMP		BIT(0)
+
+/* RSCFDnCFDRFIDx */
+#define RCANFD_RFID_RFIDE		BIT(31)
+#define RCANFD_RFID_RFRTR		BIT(30)
+
+/* RSCFDnCFDRFPTRx */
+#define RCANFD_RFPTR_RFDLC(x)		(((x) >> 28) & 0xf)
+#define RCANFD_RFPTR_RFPTR(x)		(((x) >> 16) & 0xfff)
+#define RCANFD_RFPTR_RFTS(x)		(((x) >> 0) & 0xffff)
+
+/* RSCFDnCFDRFFDSTSx */
+#define RCANFD_RFFDSTS_RFFDF		BIT(2)
+#define RCANFD_RFFDSTS_RFBRS		BIT(1)
+#define RCANFD_RFFDSTS_RFESI		BIT(0)
+
+/* Common FIFO bits */
+
+/* RSCFDnCFDCFCCk */
+#define RCANFD_CFCC_CFTML(x)		(((x) & 0xf) << 20)
+#define RCANFD_CFCC_CFM(x)		(((x) & 0x3) << 16)
+#define RCANFD_CFCC_CFIM		BIT(12)
+#define RCANFD_CFCC_CFDC(x)		(((x) & 0x7) << 8)
+#define RCANFD_CFCC_CFPLS(x)		(((x) & 0x7) << 4)
+#define RCANFD_CFCC_CFTXIE		BIT(2)
+#define RCANFD_CFCC_CFE			BIT(0)
+
+/* RSCFDnCFDCFSTSk */
+#define RCANFD_CFSTS_CFMC(x)		(((x) >> 8) & 0xff)
+#define RCANFD_CFSTS_CFTXIF		BIT(4)
+#define RCANFD_CFSTS_CFMLT		BIT(2)
+#define RCANFD_CFSTS_CFFLL		BIT(1)
+#define RCANFD_CFSTS_CFEMP		BIT(0)
+
+/* RSCFDnCFDCFIDk */
+#define RCANFD_CFID_CFIDE		BIT(31)
+#define RCANFD_CFID_CFRTR		BIT(30)
+#define RCANFD_CFID_CFID_MASK(x)	((x) & 0x1fffffff)
+
+/* RSCFDnCFDCFPTRk */
+#define RCANFD_CFPTR_CFDLC(x)		(((x) & 0xf) << 28)
+#define RCANFD_CFPTR_CFPTR(x)		(((x) & 0xfff) << 16)
+#define RCANFD_CFPTR_CFTS(x)		(((x) & 0xff) << 0)
+
+/* RSCFDnCFDCFFDCSTSk */
+#define RCANFD_CFFDCSTS_CFFDF		BIT(2)
+#define RCANFD_CFFDCSTS_CFBRS		BIT(1)
+#define RCANFD_CFFDCSTS_CFESI		BIT(0)
+
+/* This controller supports either Classical CAN only mode or CAN FD only mode.
+ * These modes are supported in two separate set of register maps & names.
+ * However, some of the register offsets are common for both modes. Those
+ * offsets are listed below as Common registers.
+ *
+ * The CAN FD only mode specific registers & Classical CAN only mode specific
+ * registers are listed separately. Their register names starts with
+ * RCANFD_F_xxx & RCANFD_C_xxx respectively.
+ */
+
+/* Common registers */
+
+/* RSCFDnCFDCmNCFG / RSCFDnCmCFG */
+#define RCANFD_CCFG(m)			(0x0000 + (0x10 * (m)))
+/* RSCFDnCFDCmCTR / RSCFDnCmCTR */
+#define RCANFD_CCTR(m)			(0x0004 + (0x10 * (m)))
+/* RSCFDnCFDCmSTS / RSCFDnCmSTS */
+#define RCANFD_CSTS(m)			(0x0008 + (0x10 * (m)))
+/* RSCFDnCFDCmERFL / RSCFDnCmERFL */
+#define RCANFD_CERFL(m)			(0x000C + (0x10 * (m)))
+
+/* RSCFDnCFDGCFG / RSCFDnGCFG */
+#define RCANFD_GCFG			(0x0084)
+/* RSCFDnCFDGCTR / RSCFDnGCTR */
+#define RCANFD_GCTR			(0x0088)
+/* RSCFDnCFDGCTS / RSCFDnGCTS */
+#define RCANFD_GSTS			(0x008c)
+/* RSCFDnCFDGERFL / RSCFDnGERFL */
+#define RCANFD_GERFL			(0x0090)
+/* RSCFDnCFDGTSC / RSCFDnGTSC */
+#define RCANFD_GTSC			(0x0094)
+/* RSCFDnCFDGAFLECTR / RSCFDnGAFLECTR */
+#define RCANFD_GAFLECTR			(0x0098)
+/* RSCFDnCFDGAFLCFG0 / RSCFDnGAFLCFG0 */
+#define RCANFD_GAFLCFG0			(0x009c)
+/* RSCFDnCFDGAFLCFG1 / RSCFDnGAFLCFG1 */
+#define RCANFD_GAFLCFG1			(0x00a0)
+/* RSCFDnCFDRMNB / RSCFDnRMNB */
+#define RCANFD_RMNB			(0x00a4)
+/* RSCFDnCFDRMND / RSCFDnRMND */
+#define RCANFD_RMND(y)			(0x00a8 + (0x04 * (y)))
+
+/* RSCFDnCFDRFCCx / RSCFDnRFCCx */
+#define RCANFD_RFCC(x)			(0x00b8 + (0x04 * (x)))
+/* RSCFDnCFDRFSTSx / RSCFDnRFSTSx */
+#define RCANFD_RFSTS(x)			(0x00d8 + (0x04 * (x)))
+/* RSCFDnCFDRFPCTRx / RSCFDnRFPCTRx */
+#define RCANFD_RFPCTR(x)		(0x00f8 + (0x04 * (x)))
+
+/* Common FIFO Control registers */
+
+/* RSCFDnCFDCFCCx / RSCFDnCFCCx */
+#define RCANFD_CFCC(ch, idx)		(0x0118 + (0x0c * (ch)) + \
+					 (0x04 * (idx)))
+/* RSCFDnCFDCFSTSx / RSCFDnCFSTSx */
+#define RCANFD_CFSTS(ch, idx)		(0x0178 + (0x0c * (ch)) + \
+					 (0x04 * (idx)))
+/* RSCFDnCFDCFPCTRx / RSCFDnCFPCTRx */
+#define RCANFD_CFPCTR(ch, idx)		(0x01d8 + (0x0c * (ch)) + \
+					 (0x04 * (idx)))
+
+/* RSCFDnCFDFESTS / RSCFDnFESTS */
+#define RCANFD_FESTS			(0x0238)
+/* RSCFDnCFDFFSTS / RSCFDnFFSTS */
+#define RCANFD_FFSTS			(0x023c)
+/* RSCFDnCFDFMSTS / RSCFDnFMSTS */
+#define RCANFD_FMSTS			(0x0240)
+/* RSCFDnCFDRFISTS / RSCFDnRFISTS */
+#define RCANFD_RFISTS			(0x0244)
+/* RSCFDnCFDCFRISTS / RSCFDnCFRISTS */
+#define RCANFD_CFRISTS			(0x0248)
+/* RSCFDnCFDCFTISTS / RSCFDnCFTISTS */
+#define RCANFD_CFTISTS			(0x024c)
+
+/* RSCFDnCFDTMCp / RSCFDnTMCp */
+#define RCANFD_TMC(p)			(0x0250 + (0x01 * (p)))
+/* RSCFDnCFDTMSTSp / RSCFDnTMSTSp */
+#define RCANFD_TMSTS(p)			(0x02d0 + (0x01 * (p)))
+
+/* RSCFDnCFDTMTRSTSp / RSCFDnTMTRSTSp */
+#define RCANFD_TMTRSTS(y)		(0x0350 + (0x04 * (y)))
+/* RSCFDnCFDTMTARSTSp / RSCFDnTMTARSTSp */
+#define RCANFD_TMTARSTS(y)		(0x0360 + (0x04 * (y)))
+/* RSCFDnCFDTMTCSTSp / RSCFDnTMTCSTSp */
+#define RCANFD_TMTCSTS(y)		(0x0370 + (0x04 * (y)))
+/* RSCFDnCFDTMTASTSp / RSCFDnTMTASTSp */
+#define RCANFD_TMTASTS(y)		(0x0380 + (0x04 * (y)))
+/* RSCFDnCFDTMIECy / RSCFDnTMIECy */
+#define RCANFD_TMIEC(y)			(0x0390 + (0x04 * (y)))
+
+/* RSCFDnCFDTXQCCm / RSCFDnTXQCCm */
+#define RCANFD_TXQCC(m)			(0x03a0 + (0x04 * (m)))
+/* RSCFDnCFDTXQSTSm / RSCFDnTXQSTSm */
+#define RCANFD_TXQSTS(m)		(0x03c0 + (0x04 * (m)))
+/* RSCFDnCFDTXQPCTRm / RSCFDnTXQPCTRm */
+#define RCANFD_TXQPCTR(m)		(0x03e0 + (0x04 * (m)))
+
+/* RSCFDnCFDTHLCCm / RSCFDnTHLCCm */
+#define RCANFD_THLCC(m)			(0x0400 + (0x04 * (m)))
+/* RSCFDnCFDTHLSTSm / RSCFDnTHLSTSm */
+#define RCANFD_THLSTS(m)		(0x0420 + (0x04 * (m)))
+/* RSCFDnCFDTHLPCTRm / RSCFDnTHLPCTRm */
+#define RCANFD_THLPCTR(m)		(0x0440 + (0x04 * (m)))
+
+/* RSCFDnCFDGTINTSTS0 / RSCFDnGTINTSTS0 */
+#define RCANFD_GTINTSTS0		(0x0460)
+/* RSCFDnCFDGTINTSTS1 / RSCFDnGTINTSTS1 */
+#define RCANFD_GTINTSTS1		(0x0464)
+/* RSCFDnCFDGTSTCFG / RSCFDnGTSTCFG */
+#define RCANFD_GTSTCFG			(0x0468)
+/* RSCFDnCFDGTSTCTR / RSCFDnGTSTCTR */
+#define RCANFD_GTSTCTR			(0x046c)
+/* RSCFDnCFDGLOCKK / RSCFDnGLOCKK */
+#define RCANFD_GLOCKK			(0x047c)
+/* RSCFDnCFDGRMCFG */
+#define RCANFD_GRMCFG			(0x04fc)
+
+/* RSCFDnCFDGAFLIDj / RSCFDnGAFLIDj */
+#define RCANFD_GAFLID(offset, j)	((offset) + (0x10 * (j)))
+/* RSCFDnCFDGAFLMj / RSCFDnGAFLMj */
+#define RCANFD_GAFLM(offset, j)		((offset) + 0x04 + (0x10 * (j)))
+/* RSCFDnCFDGAFLP0j / RSCFDnGAFLP0j */
+#define RCANFD_GAFLP0(offset, j)	((offset) + 0x08 + (0x10 * (j)))
+/* RSCFDnCFDGAFLP1j / RSCFDnGAFLP1j */
+#define RCANFD_GAFLP1(offset, j)	((offset) + 0x0c + (0x10 * (j)))
+
+/* Classical CAN only mode register map */
+
+/* RSCFDnGAFLXXXj offset */
+#define RCANFD_C_GAFL_OFFSET		(0x0500)
+
+/* RSCFDnRMXXXq -> RCANFD_C_RMXXX(q) */
+#define RCANFD_C_RMID(q)		(0x0600 + (0x10 * (q)))
+#define RCANFD_C_RMPTR(q)		(0x0604 + (0x10 * (q)))
+#define RCANFD_C_RMDF0(q)		(0x0608 + (0x10 * (q)))
+#define RCANFD_C_RMDF1(q)		(0x060c + (0x10 * (q)))
+
+/* RSCFDnRFXXx -> RCANFD_C_RFXX(x) */
+#define RCANFD_C_RFOFFSET		(0x0e00)
+#define RCANFD_C_RFID(x)		(RCANFD_C_RFOFFSET + (0x10 * (x)))
+#define RCANFD_C_RFPTR(x)		(RCANFD_C_RFOFFSET + 0x04 + \
+					 (0x10 * (x)))
+#define RCANFD_C_RFDF(x, df)		(RCANFD_C_RFOFFSET + 0x08 + \
+					 (0x10 * (x)) + (0x04 * (df)))
+
+/* RSCFDnCFXXk -> RCANFD_C_CFXX(ch, k) */
+#define RCANFD_C_CFOFFSET		(0x0e80)
+#define RCANFD_C_CFID(ch, idx)		(RCANFD_C_CFOFFSET + (0x30 * (ch)) + \
+					 (0x10 * (idx)))
+#define RCANFD_C_CFPTR(ch, idx)		(RCANFD_C_CFOFFSET + 0x04 + \
+					 (0x30 * (ch)) + (0x10 * (idx)))
+#define RCANFD_C_CFDF(ch, idx, df)	(RCANFD_C_CFOFFSET + 0x08 + \
+					 (0x30 * (ch)) + (0x10 * (idx)) + \
+					 (0x04 * (df)))
+
+/* RSCFDnTMXXp -> RCANFD_C_TMXX(p) */
+#define RCANFD_C_TMID(p)		(0x1000 + (0x10 * (p)))
+#define RCANFD_C_TMPTR(p)		(0x1004 + (0x10 * (p)))
+#define RCANFD_C_TMDF0(p)		(0x1008 + (0x10 * (p)))
+#define RCANFD_C_TMDF1(p)		(0x100c + (0x10 * (p)))
+
+/* RSCFDnTHLACCm */
+#define RCANFD_C_THLACC(m)		(0x1800 + (0x04 * (m)))
+/* RSCFDnRPGACCr */
+#define RCANFD_C_RPGACC(r)		(0x1900 + (0x04 * (r)))
+
+/* CAN FD mode specific regsiter map */
+
+/* RSCFDnCFDCmXXX -> RCANFD_F_XXX(m) */
+#define RCANFD_F_DCFG(m)		(0x0500 + (0x20 * (m)))
+#define RCANFD_F_CFDCFG(m)		(0x0504 + (0x20 * (m)))
+#define RCANFD_F_CFDCTR(m)		(0x0508 + (0x20 * (m)))
+#define RCANFD_F_CFDSTS(m)		(0x050c + (0x20 * (m)))
+#define RCANFD_F_CFDCRC(m)		(0x0510 + (0x20 * (m)))
+
+/* RSCFDnCFDGAFLXXXj offset */
+#define RCANFD_F_GAFL_OFFSET		(0x1000)
+
+/* RSCFDnCFDRMXXXq -> RCANFD_F_RMXXX(q) */
+#define RCANFD_F_RMID(q)		(0x2000 + (0x20 * (q)))
+#define RCANFD_F_RMPTR(q)		(0x2004 + (0x20 * (q)))
+#define RCANFD_F_RMFDSTS(q)		(0x2008 + (0x20 * (q)))
+#define RCANFD_F_RMDF(q, b)		(0x200c + (0x04 * (b)) + (0x20 * (q)))
+
+/* RSCFDnCFDRFXXx -> RCANFD_F_RFXX(x) */
+#define RCANFD_F_RFOFFSET		(0x3000)
+#define RCANFD_F_RFID(x)		(RCANFD_F_RFOFFSET + (0x80 * (x)))
+#define RCANFD_F_RFPTR(x)		(RCANFD_F_RFOFFSET + 0x04 + \
+					 (0x80 * (x)))
+#define RCANFD_F_RFFDSTS(x)		(RCANFD_F_RFOFFSET + 0x08 + \
+					 (0x80 * (x)))
+#define RCANFD_F_RFDF(x, df)		(RCANFD_F_RFOFFSET + 0x0c + \
+					 (0x80 * (x)) + (0x04 * (df)))
+
+/* RSCFDnCFDCFXXk -> RCANFD_F_CFXX(ch, k) */
+#define RCANFD_F_CFOFFSET		(0x3400)
+#define RCANFD_F_CFID(ch, idx)		(RCANFD_F_CFOFFSET + (0x180 * (ch)) + \
+					 (0x80 * (idx)))
+#define RCANFD_F_CFPTR(ch, idx)		(RCANFD_F_CFOFFSET + 0x04 + \
+					 (0x180 * (ch)) + (0x80 * (idx)))
+#define RCANFD_F_CFFDCSTS(ch, idx)	(RCANFD_F_CFOFFSET + 0x08 + \
+					 (0x180 * (ch)) + (0x80 * (idx)))
+#define RCANFD_F_CFDF(ch, idx, df)	(RCANFD_F_CFOFFSET + 0x0c + \
+					 (0x180 * (ch)) + (0x80 * (idx)) + \
+					 (0x04 * (df)))
+
+/* RSCFDnCFDTMXXp -> RCANFD_F_TMXX(p) */
+#define RCANFD_F_TMID(p)		(0x4000 + (0x20 * (p)))
+#define RCANFD_F_TMPTR(p)		(0x4004 + (0x20 * (p)))
+#define RCANFD_F_TMFDCTR(p)		(0x4008 + (0x20 * (p)))
+#define RCANFD_F_TMDF(p, b)		(0x400c + (0x20 * (p)) + (0x04 * (b)))
+
+/* RSCFDnCFDTHLACCm */
+#define RCANFD_F_THLACC(m)		(0x6000 + (0x04 * (m)))
+/* RSCFDnCFDRPGACCr */
+#define RCANFD_F_RPGACC(r)		(0x6400 + (0x04 * (r)))
+
+/* Constants */
+#define RCANFD_FIFO_DEPTH		8	/* Tx FIFO depth */
+#define RCANFD_NAPI_WEIGHT		8	/* Rx poll quota */
+
+#define RCANFD_NUM_CHANNELS		2	/* Two channels max */
+#define RCANFD_CHANNELS_MASK		BIT((RCANFD_NUM_CHANNELS) - 1)
+
+#define RCANFD_GAFL_PAGENUM(entry)	((entry) / 16)
+#define RCANFD_CHANNEL_NUMRULES		1	/* only one rule per channel */
+
+/* Rx FIFO is a global resource of the controller. There are 8 such FIFOs
+ * available. Each channel gets a dedicated Rx FIFO (i.e.) the channel
+ * number is added to RFFIFO index.
+ */
+#define RCANFD_RFFIFO_IDX		0
+
+/* Tx/Rx or Common FIFO is a per channel resource. Each channel has 3 Common
+ * FIFOs dedicated to them. Use the first (index 0) FIFO out of the 3 for Tx.
+ */
+#define RCANFD_CFFIFO_IDX		0
+
+/* fCAN clock select register settings */
+enum rcar_canfd_fcanclk {
+	RCANFD_CANFDCLK = 0,		/* CANFD clock */
+	RCANFD_EXTCLK,			/* Externally input clock */
+};
+
+struct rcar_canfd_global;
+
+/* Channel priv data */
+struct rcar_canfd_channel {
+	struct can_priv can;			/* Must be the first member */
+	struct net_device *ndev;
+	struct rcar_canfd_global *gpriv;	/* Controller reference */
+	void __iomem *base;			/* Register base address */
+	struct napi_struct napi;
+	u8  tx_len[RCANFD_FIFO_DEPTH];		/* For net stats */
+	u32 tx_head;				/* Incremented on xmit */
+	u32 tx_tail;				/* Incremented on xmit done */
+	u32 channel;				/* Channel number */
+	spinlock_t tx_lock;			/* To protect tx path */
+};
+
+/* Global priv data */
+struct rcar_canfd_global {
+	struct rcar_canfd_channel *ch[RCANFD_NUM_CHANNELS];
+	void __iomem *base;		/* Register base address */
+	struct platform_device *pdev;	/* Respective platform device */
+	struct clk *clkp;		/* Peripheral clock */
+	struct clk *can_clk;		/* fCAN clock */
+	enum rcar_canfd_fcanclk fcan;	/* CANFD or Ext clock */
+	unsigned long channels_mask;	/* Enabled channels mask */
+	bool fdmode;			/* CAN FD or Classical CAN only mode */
+};
+
+/* CAN FD mode nominal rate constants */
+static const struct can_bittiming_const rcar_canfd_nom_bittiming_const = {
+	.name = RCANFD_DRV_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 128,
+	.tseg2_min = 2,
+	.tseg2_max = 32,
+	.sjw_max = 32,
+	.brp_min = 1,
+	.brp_max = 1024,
+	.brp_inc = 1,
+};
+
+/* CAN FD mode data rate constants */
+static const struct can_bittiming_const rcar_canfd_data_bittiming_const = {
+	.name = RCANFD_DRV_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 16,
+	.tseg2_min = 2,
+	.tseg2_max = 8,
+	.sjw_max = 8,
+	.brp_min = 1,
+	.brp_max = 256,
+	.brp_inc = 1,
+};
+
+/* Classical CAN mode bitrate constants */
+static const struct can_bittiming_const rcar_canfd_bittiming_const = {
+	.name = RCANFD_DRV_NAME,
+	.tseg1_min = 4,
+	.tseg1_max = 16,
+	.tseg2_min = 2,
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 1,
+	.brp_max = 1024,
+	.brp_inc = 1,
+};
+
+/* Helper functions */
+static inline void rcar_canfd_update(u32 mask, u32 val, u32 __iomem *reg)
+{
+	u32 data = readl(reg);
+
+	data &= ~mask;
+	data |= (val & mask);
+	writel(data, reg);
+}
+
+static inline u32 rcar_canfd_read(void __iomem *base, u32 offset)
+{
+	return readl(base + (offset));
+}
+
+static inline void rcar_canfd_write(void __iomem *base, u32 offset, u32 val)
+{
+	writel(val, base + (offset));
+}
+
+static void rcar_canfd_set_bit(void __iomem *base, u32 reg, u32 val)
+{
+	rcar_canfd_update(val, val, base + (reg));
+}
+
+static void rcar_canfd_clear_bit(void __iomem *base, u32 reg, u32 val)
+{
+	rcar_canfd_update(val, 0, base + (reg));
+}
+
+static void rcar_canfd_update_bit(void __iomem *base, u32 reg,
+				  u32 mask, u32 val)
+{
+	rcar_canfd_update(mask, val, base + (reg));
+}
+
+static void rcar_canfd_get_data(struct rcar_canfd_channel *priv,
+				struct canfd_frame *cf, u32 off)
+{
+	u32 i, lwords;
+
+	lwords = DIV_ROUND_UP(cf->len, sizeof(u32));
+	for (i = 0; i < lwords; i++)
+		*((u32 *)cf->data + i) =
+			rcar_canfd_read(priv->base, off + (i * sizeof(u32)));
+}
+
+static void rcar_canfd_put_data(struct rcar_canfd_channel *priv,
+				struct canfd_frame *cf, u32 off)
+{
+	u32 i, lwords;
+
+	lwords = DIV_ROUND_UP(cf->len, sizeof(u32));
+	for (i = 0; i < lwords; i++)
+		rcar_canfd_write(priv->base, off + (i * sizeof(u32)),
+				 *((u32 *)cf->data + i));
+}
+
+static void rcar_canfd_tx_failure_cleanup(struct net_device *ndev)
+{
+	u32 i;
+
+	for (i = 0; i < RCANFD_FIFO_DEPTH; i++)
+		can_free_echo_skb(ndev, i);
+}
+
+static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv)
+{
+	u32 sts, ch;
+	int err;
+
+	/* Check RAMINIT flag as CAN RAM initialization takes place
+	 * after the MCU reset
+	 */
+	err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts,
+				 !(sts & RCANFD_GSTS_GRAMINIT), 2, 500000);
+	if (err) {
+		dev_dbg(&gpriv->pdev->dev, "global raminit failed\n");
+		return err;
+	}
+
+	/* Transition to Global Reset mode */
+	rcar_canfd_clear_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GSLPR);
+	rcar_canfd_update_bit(gpriv->base, RCANFD_GCTR,
+			      RCANFD_GCTR_GMDC_MASK, RCANFD_GCTR_GMDC_GRESET);
+
+	/* Ensure Global reset mode */
+	err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts,
+				 (sts & RCANFD_GSTS_GRSTSTS), 2, 500000);
+	if (err) {
+		dev_dbg(&gpriv->pdev->dev, "global reset failed\n");
+		return err;
+	}
+
+	/* Reset Global error flags */
+	rcar_canfd_write(gpriv->base, RCANFD_GERFL, 0x0);
+
+	/* Set the controller into appropriate mode */
+	if (gpriv->fdmode)
+		rcar_canfd_set_bit(gpriv->base, RCANFD_GRMCFG,
+				   RCANFD_GRMCFG_RCMC);
+	else
+		rcar_canfd_clear_bit(gpriv->base, RCANFD_GRMCFG,
+				     RCANFD_GRMCFG_RCMC);
+
+	/* Transition all Channels to reset mode */
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		rcar_canfd_clear_bit(gpriv->base,
+				     RCANFD_CCTR(ch), RCANFD_CCTR_CSLPR);
+
+		rcar_canfd_update_bit(gpriv->base, RCANFD_CCTR(ch),
+				      RCANFD_CCTR_CHMDC_MASK,
+				      RCANFD_CCTR_CHDMC_CRESET);
+
+		/* Ensure Channel reset mode */
+		err = readl_poll_timeout((gpriv->base + RCANFD_CSTS(ch)), sts,
+					 (sts & RCANFD_CSTS_CRSTSTS),
+					 2, 500000);
+		if (err) {
+			dev_dbg(&gpriv->pdev->dev,
+				"channel %u reset failed\n", ch);
+			return err;
+		}
+	}
+	return 0;
+}
+
+static void rcar_canfd_configure_controller(struct rcar_canfd_global *gpriv)
+{
+	u32 cfg, ch;
+
+	/* Global configuration settings */
+
+	/* ECC Error flag Enable */
+	cfg = RCANFD_GCFG_EEFE;
+
+	if (gpriv->fdmode)
+		/* Truncate payload to configured message size RFPLS */
+		cfg |= RCANFD_GCFG_CMPOC;
+
+	/* Set External Clock if selected */
+	if (gpriv->fcan != RCANFD_CANFDCLK)
+		cfg |= RCANFD_GCFG_DCS;
+
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GCFG, cfg);
+
+	/* Channel configuration settings */
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		rcar_canfd_set_bit(gpriv->base, RCANFD_CCTR(ch),
+				   RCANFD_CCTR_ERRD);
+		rcar_canfd_update_bit(gpriv->base, RCANFD_CCTR(ch),
+				      RCANFD_CCTR_BOM_MASK,
+				      RCANFD_CCTR_BOM_BENTRY);
+	}
+}
+
+static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv,
+					   u32 ch)
+{
+	u32 cfg;
+	int offset, start, page, num_rules = RCANFD_CHANNEL_NUMRULES;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	if (ch == 0) {
+		start = 0; /* Channel 0 always starts from 0th rule */
+	} else {
+		/* Get number of Channel 0 rules and adjust */
+		cfg = rcar_canfd_read(gpriv->base, RCANFD_GAFLCFG0);
+		start = RCANFD_GAFLCFG_GETRNC(0, cfg);
+	}
+
+	/* Enable write access to entry */
+	page = RCANFD_GAFL_PAGENUM(start);
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLECTR,
+			   (RCANFD_GAFLECTR_AFLPN(page) |
+			    RCANFD_GAFLECTR_AFLDAE));
+
+	/* Write number of rules for channel */
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLCFG0,
+			   RCANFD_GAFLCFG_SETRNC(ch, num_rules));
+	if (gpriv->fdmode)
+		offset = RCANFD_F_GAFL_OFFSET;
+	else
+		offset = RCANFD_C_GAFL_OFFSET;
+
+	/* Accept all IDs */
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLID(offset, start), 0);
+	/* IDE or RTR is not considered for matching */
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLM(offset, start), 0);
+	/* Any data length accepted */
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLP0(offset, start), 0);
+	/* Place the msg in corresponding Rx FIFO entry */
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLP1(offset, start),
+			 RCANFD_GAFLP1_GAFLFDP(ridx));
+
+	/* Disable write access to page */
+	rcar_canfd_clear_bit(gpriv->base,
+			     RCANFD_GAFLECTR, RCANFD_GAFLECTR_AFLDAE);
+}
+
+static void rcar_canfd_configure_rx(struct rcar_canfd_global *gpriv, u32 ch)
+{
+	/* Rx FIFO is used for reception */
+	u32 cfg;
+	u16 rfdc, rfpls;
+
+	/* Select Rx FIFO based on channel */
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	rfdc = 2;		/* b010 - 8 messages Rx FIFO depth */
+	if (gpriv->fdmode)
+		rfpls = 7;	/* b111 - Max 64 bytes payload */
+	else
+		rfpls = 0;	/* b000 - Max 8 bytes payload */
+
+	cfg = (RCANFD_RFCC_RFIM | RCANFD_RFCC_RFDC(rfdc) |
+		RCANFD_RFCC_RFPLS(rfpls) | RCANFD_RFCC_RFIE);
+	rcar_canfd_write(gpriv->base, RCANFD_RFCC(ridx), cfg);
+}
+
+static void rcar_canfd_configure_tx(struct rcar_canfd_global *gpriv, u32 ch)
+{
+	/* Tx/Rx(Common) FIFO configured in Tx mode is
+	 * used for transmission
+	 *
+	 * Each channel has 3 Common FIFO dedicated to them.
+	 * Use the 1st (index 0) out of 3
+	 */
+	u32 cfg;
+	u16 cftml, cfm, cfdc, cfpls;
+
+	cftml = 0;		/* 0th buffer */
+	cfm = 1;		/* b01 - Transmit mode */
+	cfdc = 2;		/* b010 - 8 messages Tx FIFO depth */
+	if (gpriv->fdmode)
+		cfpls = 7;	/* b111 - Max 64 bytes payload */
+	else
+		cfpls = 0;	/* b000 - Max 8 bytes payload */
+
+	cfg = (RCANFD_CFCC_CFTML(cftml) | RCANFD_CFCC_CFM(cfm) |
+		RCANFD_CFCC_CFIM | RCANFD_CFCC_CFDC(cfdc) |
+		RCANFD_CFCC_CFPLS(cfpls) | RCANFD_CFCC_CFTXIE);
+	rcar_canfd_write(gpriv->base, RCANFD_CFCC(ch, RCANFD_CFFIFO_IDX), cfg);
+
+	if (gpriv->fdmode)
+		/* Clear FD mode specific control/status register */
+		rcar_canfd_write(gpriv->base,
+				 RCANFD_F_CFFDCSTS(ch, RCANFD_CFFIFO_IDX), 0);
+}
+
+static void rcar_canfd_enable_global_interrupts(struct rcar_canfd_global *gpriv)
+{
+	u32 ctr;
+
+	/* Clear any stray error interrupt flags */
+	rcar_canfd_write(gpriv->base, RCANFD_GERFL, 0);
+
+	/* Global interrupts setup */
+	ctr = RCANFD_GCTR_MEIE;
+	if (gpriv->fdmode)
+		ctr |= RCANFD_GCTR_CFMPOFIE;
+
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GCTR, ctr);
+}
+
+static void rcar_canfd_disable_global_interrupts(struct rcar_canfd_global
+						 *gpriv)
+{
+	/* Disable all interrupts */
+	rcar_canfd_write(gpriv->base, RCANFD_GCTR, 0);
+
+	/* Clear any stray error interrupt flags */
+	rcar_canfd_write(gpriv->base, RCANFD_GERFL, 0);
+}
+
+static void rcar_canfd_enable_channel_interrupts(struct rcar_canfd_channel
+						 *priv)
+{
+	u32 ctr, ch = priv->channel;
+
+	/* Clear any stray error flags */
+	rcar_canfd_write(priv->base, RCANFD_CERFL(ch), 0);
+
+	/* Channel interrupts setup */
+	ctr = (RCANFD_CCTR_TAIE |
+	       RCANFD_CCTR_ALIE | RCANFD_CCTR_BLIE |
+	       RCANFD_CCTR_OLIE | RCANFD_CCTR_BORIE |
+	       RCANFD_CCTR_BOEIE | RCANFD_CCTR_EPIE |
+	       RCANFD_CCTR_EWIE | RCANFD_CCTR_BEIE);
+	rcar_canfd_set_bit(priv->base, RCANFD_CCTR(ch), ctr);
+}
+
+static void rcar_canfd_disable_channel_interrupts(struct rcar_canfd_channel
+						  *priv)
+{
+	u32 ctr, ch = priv->channel;
+
+	ctr = (RCANFD_CCTR_TAIE |
+	       RCANFD_CCTR_ALIE | RCANFD_CCTR_BLIE |
+	       RCANFD_CCTR_OLIE | RCANFD_CCTR_BORIE |
+	       RCANFD_CCTR_BOEIE | RCANFD_CCTR_EPIE |
+	       RCANFD_CCTR_EWIE | RCANFD_CCTR_BEIE);
+	rcar_canfd_clear_bit(priv->base, RCANFD_CCTR(ch), ctr);
+
+	/* Clear any stray error flags */
+	rcar_canfd_write(priv->base, RCANFD_CERFL(ch), 0);
+}
+
+static void rcar_canfd_global_error(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct rcar_canfd_global *gpriv = priv->gpriv;
+	struct net_device_stats *stats = &ndev->stats;
+	u32 ch = priv->channel;
+	u32 gerfl, sts;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	gerfl = rcar_canfd_read(priv->base, RCANFD_GERFL);
+	if ((gerfl & RCANFD_GERFL_EEF0) && (ch == 0)) {
+		netdev_dbg(ndev, "Ch0: ECC Error flag\n");
+		stats->tx_dropped++;
+	}
+	if ((gerfl & RCANFD_GERFL_EEF1) && (ch == 1)) {
+		netdev_dbg(ndev, "Ch1: ECC Error flag\n");
+		stats->tx_dropped++;
+	}
+	if (gerfl & RCANFD_GERFL_MES) {
+		sts = rcar_canfd_read(priv->base,
+				      RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX));
+		if (sts & RCANFD_CFSTS_CFMLT) {
+			netdev_dbg(ndev, "Tx Message Lost flag\n");
+			stats->tx_dropped++;
+			rcar_canfd_write(priv->base,
+					 RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX),
+					 sts & ~RCANFD_CFSTS_CFMLT);
+		}
+
+		sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx));
+		if (sts & RCANFD_RFSTS_RFMLT) {
+			netdev_dbg(ndev, "Rx Message Lost flag\n");
+			stats->rx_dropped++;
+			rcar_canfd_write(priv->base, RCANFD_RFSTS(ridx),
+					 sts & ~RCANFD_RFSTS_RFMLT);
+		}
+	}
+	if (gpriv->fdmode && gerfl & RCANFD_GERFL_CMPOF) {
+		/* Message Lost flag will be set for respective channel
+		 * when this condition happens with counters and flags
+		 * already updated.
+		 */
+		netdev_dbg(ndev, "global payload overflow interrupt\n");
+	}
+
+	/* Clear all global error interrupts. Only affected channels bits
+	 * get cleared
+	 */
+	rcar_canfd_write(priv->base, RCANFD_GERFL, 0);
+}
+
+static void rcar_canfd_error(struct net_device *ndev, u32 cerfl,
+			     u16 txerr, u16 rxerr)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u32 ch = priv->channel;
+
+	netdev_dbg(ndev, "ch erfl %x txerr %u rxerr %u\n", cerfl, txerr, rxerr);
+
+	/* Propagate the error condition to the CAN stack */
+	skb = alloc_can_err_skb(ndev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+
+	/* Channel error interrupts */
+	if (cerfl & RCANFD_CERFL_BEF) {
+		netdev_dbg(ndev, "Bus error\n");
+		cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
+		cf->data[2] = CAN_ERR_PROT_UNSPEC;
+		priv->can.can_stats.bus_error++;
+	}
+	if (cerfl & RCANFD_CERFL_ADERR) {
+		netdev_dbg(ndev, "ACK Delimiter Error\n");
+		stats->tx_errors++;
+		cf->data[3] |= CAN_ERR_PROT_LOC_ACK_DEL;
+	}
+	if (cerfl & RCANFD_CERFL_B0ERR) {
+		netdev_dbg(ndev, "Bit Error (dominant)\n");
+		stats->tx_errors++;
+		cf->data[2] |= CAN_ERR_PROT_BIT0;
+	}
+	if (cerfl & RCANFD_CERFL_B1ERR) {
+		netdev_dbg(ndev, "Bit Error (recessive)\n");
+		stats->tx_errors++;
+		cf->data[2] |= CAN_ERR_PROT_BIT1;
+	}
+	if (cerfl & RCANFD_CERFL_CERR) {
+		netdev_dbg(ndev, "CRC Error\n");
+		stats->rx_errors++;
+		cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+	}
+	if (cerfl & RCANFD_CERFL_AERR) {
+		netdev_dbg(ndev, "ACK Error\n");
+		stats->tx_errors++;
+		cf->can_id |= CAN_ERR_ACK;
+		cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+	}
+	if (cerfl & RCANFD_CERFL_FERR) {
+		netdev_dbg(ndev, "Form Error\n");
+		stats->rx_errors++;
+		cf->data[2] |= CAN_ERR_PROT_FORM;
+	}
+	if (cerfl & RCANFD_CERFL_SERR) {
+		netdev_dbg(ndev, "Stuff Error\n");
+		stats->rx_errors++;
+		cf->data[2] |= CAN_ERR_PROT_STUFF;
+	}
+	if (cerfl & RCANFD_CERFL_ALF) {
+		netdev_dbg(ndev, "Arbitration lost Error\n");
+		priv->can.can_stats.arbitration_lost++;
+		cf->can_id |= CAN_ERR_LOSTARB;
+		cf->data[0] |= CAN_ERR_LOSTARB_UNSPEC;
+	}
+	if (cerfl & RCANFD_CERFL_BLF) {
+		netdev_dbg(ndev, "Bus Lock Error\n");
+		stats->rx_errors++;
+		cf->can_id |= CAN_ERR_BUSERROR;
+	}
+	if (cerfl & RCANFD_CERFL_EWF) {
+		netdev_dbg(ndev, "Error warning interrupt\n");
+		priv->can.state = CAN_STATE_ERROR_WARNING;
+		priv->can.can_stats.error_warning++;
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->data[1] = txerr > rxerr ? CAN_ERR_CRTL_TX_WARNING :
+			CAN_ERR_CRTL_RX_WARNING;
+		cf->data[6] = txerr;
+		cf->data[7] = rxerr;
+	}
+	if (cerfl & RCANFD_CERFL_EPF) {
+		netdev_dbg(ndev, "Error passive interrupt\n");
+		priv->can.state = CAN_STATE_ERROR_PASSIVE;
+		priv->can.can_stats.error_passive++;
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->data[1] = txerr > rxerr ? CAN_ERR_CRTL_TX_PASSIVE :
+			CAN_ERR_CRTL_RX_PASSIVE;
+		cf->data[6] = txerr;
+		cf->data[7] = rxerr;
+	}
+	if (cerfl & RCANFD_CERFL_BOEF) {
+		netdev_dbg(ndev, "Bus-off entry interrupt\n");
+		rcar_canfd_tx_failure_cleanup(ndev);
+		priv->can.state = CAN_STATE_BUS_OFF;
+		priv->can.can_stats.bus_off++;
+		can_bus_off(ndev);
+		cf->can_id |= CAN_ERR_BUSOFF;
+	}
+	if (cerfl & RCANFD_CERFL_OVLF) {
+		netdev_dbg(ndev,
+			   "Overload Frame Transmission error interrupt\n");
+		stats->tx_errors++;
+		cf->can_id |= CAN_ERR_PROT;
+		cf->data[2] |= CAN_ERR_PROT_OVERLOAD;
+	}
+
+	/* Clear channel error interrupts that are handled */
+	rcar_canfd_write(priv->base, RCANFD_CERFL(ch),
+			 RCANFD_CERFL_ERR(~cerfl));
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+static void rcar_canfd_tx_done(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	u32 sts;
+	unsigned long flags;
+	u32 ch = priv->channel;
+
+	do {
+		u8 unsent, sent;
+
+		sent = priv->tx_tail % RCANFD_FIFO_DEPTH;
+		stats->tx_packets++;
+		stats->tx_bytes += priv->tx_len[sent];
+		priv->tx_len[sent] = 0;
+		can_get_echo_skb(ndev, sent);
+
+		spin_lock_irqsave(&priv->tx_lock, flags);
+		priv->tx_tail++;
+		sts = rcar_canfd_read(priv->base,
+				      RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX));
+		unsent = RCANFD_CFSTS_CFMC(sts);
+
+		/* Wake producer only when there is room */
+		if (unsent != RCANFD_FIFO_DEPTH)
+			netif_wake_queue(ndev);
+
+		if (priv->tx_head - priv->tx_tail <= unsent) {
+			spin_unlock_irqrestore(&priv->tx_lock, flags);
+			break;
+		}
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+	} while (1);
+
+	/* Clear interrupt */
+	rcar_canfd_write(priv->base, RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX),
+			 sts & ~RCANFD_CFSTS_CFTXIF);
+	can_led_event(ndev, CAN_LED_EVENT_TX);
+}
+
+static irqreturn_t rcar_canfd_global_interrupt(int irq, void *dev_id)
+{
+	struct rcar_canfd_global *gpriv = dev_id;
+	struct net_device *ndev;
+	struct rcar_canfd_channel *priv;
+	u32 sts, gerfl;
+	u32 ch, ridx;
+
+	/* Global error interrupts still indicate a condition specific
+	 * to a channel. RxFIFO interrupt is a global interrupt.
+	 */
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		priv = gpriv->ch[ch];
+		ndev = priv->ndev;
+		ridx = ch + RCANFD_RFFIFO_IDX;
+
+		/* Global error interrupts */
+		gerfl = rcar_canfd_read(priv->base, RCANFD_GERFL);
+		if (unlikely(RCANFD_GERFL_ERR(gpriv, gerfl)))
+			rcar_canfd_global_error(ndev);
+
+		/* Handle Rx interrupts */
+		sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx));
+		if (likely(sts & RCANFD_RFSTS_RFIF)) {
+			if (napi_schedule_prep(&priv->napi)) {
+				/* Disable Rx FIFO interrupts */
+				rcar_canfd_clear_bit(priv->base,
+						     RCANFD_RFCC(ridx),
+						     RCANFD_RFCC_RFIE);
+				__napi_schedule(&priv->napi);
+			}
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+static void rcar_canfd_state_change(struct net_device *ndev,
+				    u16 txerr, u16 rxerr)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	enum can_state rx_state, tx_state, state = priv->can.state;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+
+	/* Handle transition from error to normal states */
+	if (txerr < 96 && rxerr < 96)
+		state = CAN_STATE_ERROR_ACTIVE;
+	else if (txerr < 128 && rxerr < 128)
+		state = CAN_STATE_ERROR_WARNING;
+
+	if (state != priv->can.state) {
+		netdev_dbg(ndev, "state: new %d, old %d: txerr %u, rxerr %u\n",
+			   state, priv->can.state, txerr, rxerr);
+		skb = alloc_can_err_skb(ndev, &cf);
+		if (!skb) {
+			stats->rx_dropped++;
+			return;
+		}
+		tx_state = txerr >= rxerr ? state : 0;
+		rx_state = txerr <= rxerr ? state : 0;
+
+		can_change_state(ndev, cf, tx_state, rx_state);
+		stats->rx_packets++;
+		stats->rx_bytes += cf->can_dlc;
+		netif_rx(skb);
+	}
+}
+
+static irqreturn_t rcar_canfd_channel_interrupt(int irq, void *dev_id)
+{
+	struct rcar_canfd_global *gpriv = dev_id;
+	struct net_device *ndev;
+	struct rcar_canfd_channel *priv;
+	u32 sts, ch, cerfl;
+	u16 txerr, rxerr;
+
+	/* Common FIFO is a per channel resource */
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		priv = gpriv->ch[ch];
+		ndev = priv->ndev;
+
+		/* Channel error interrupts */
+		cerfl = rcar_canfd_read(priv->base, RCANFD_CERFL(ch));
+		sts = rcar_canfd_read(priv->base, RCANFD_CSTS(ch));
+		txerr = RCANFD_CSTS_TECCNT(sts);
+		rxerr = RCANFD_CSTS_RECCNT(sts);
+		if (unlikely(RCANFD_CERFL_ERR(cerfl)))
+			rcar_canfd_error(ndev, cerfl, txerr, rxerr);
+
+		/* Handle state change to lower states */
+		if (unlikely((priv->can.state != CAN_STATE_ERROR_ACTIVE) &&
+			     (priv->can.state != CAN_STATE_BUS_OFF)))
+			rcar_canfd_state_change(ndev, txerr, rxerr);
+
+		/* Handle Tx interrupts */
+		sts = rcar_canfd_read(priv->base,
+				      RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX));
+		if (likely(sts & RCANFD_CFSTS_CFTXIF))
+			rcar_canfd_tx_done(ndev);
+	}
+	return IRQ_HANDLED;
+}
+
+static void rcar_canfd_set_bittiming(struct net_device *dev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(dev);
+	const struct can_bittiming *bt = &priv->can.bittiming;
+	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	u16 brp, sjw, tseg1, tseg2;
+	u32 cfg;
+	u32 ch = priv->channel;
+
+	/* Nominal bit timing settings */
+	brp = bt->brp - 1;
+	sjw = bt->sjw - 1;
+	tseg1 = bt->prop_seg + bt->phase_seg1 - 1;
+	tseg2 = bt->phase_seg2 - 1;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+		/* CAN FD only mode */
+		cfg = (RCANFD_NCFG_NTSEG1(tseg1) | RCANFD_NCFG_NBRP(brp) |
+		       RCANFD_NCFG_NSJW(sjw) | RCANFD_NCFG_NTSEG2(tseg2));
+
+		rcar_canfd_write(priv->base, RCANFD_CCFG(ch), cfg);
+		netdev_dbg(priv->ndev, "nrate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n",
+			   brp, sjw, tseg1, tseg2);
+
+		/* Data bit timing settings */
+		brp = dbt->brp - 1;
+		sjw = dbt->sjw - 1;
+		tseg1 = dbt->prop_seg + dbt->phase_seg1 - 1;
+		tseg2 = dbt->phase_seg2 - 1;
+
+		cfg = (RCANFD_DCFG_DTSEG1(tseg1) | RCANFD_DCFG_DBRP(brp) |
+		       RCANFD_DCFG_DSJW(sjw) | RCANFD_DCFG_DTSEG2(tseg2));
+
+		rcar_canfd_write(priv->base, RCANFD_F_DCFG(ch), cfg);
+		netdev_dbg(priv->ndev, "drate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n",
+			   brp, sjw, tseg1, tseg2);
+	} else {
+		/* Classical CAN only mode */
+		cfg = (RCANFD_CFG_TSEG1(tseg1) | RCANFD_CFG_BRP(brp) |
+			RCANFD_CFG_SJW(sjw) | RCANFD_CFG_TSEG2(tseg2));
+
+		rcar_canfd_write(priv->base, RCANFD_CCFG(ch), cfg);
+		netdev_dbg(priv->ndev,
+			   "rate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n",
+			   brp, sjw, tseg1, tseg2);
+	}
+}
+
+static int rcar_canfd_start(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	int err = -EOPNOTSUPP;
+	u32 sts, ch = priv->channel;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	rcar_canfd_set_bittiming(ndev);
+
+	rcar_canfd_enable_channel_interrupts(priv);
+
+	/* Set channel to Operational mode */
+	rcar_canfd_update_bit(priv->base, RCANFD_CCTR(ch),
+			      RCANFD_CCTR_CHMDC_MASK, RCANFD_CCTR_CHDMC_COPM);
+
+	/* Verify channel mode change */
+	err = readl_poll_timeout((priv->base + RCANFD_CSTS(ch)), sts,
+				 (sts & RCANFD_CSTS_COMSTS), 2, 500000);
+	if (err) {
+		netdev_err(ndev, "channel %u communication state failed\n", ch);
+		goto fail_mode_change;
+	}
+
+	/* Enable Common & Rx FIFO */
+	rcar_canfd_set_bit(priv->base, RCANFD_CFCC(ch, RCANFD_CFFIFO_IDX),
+			   RCANFD_CFCC_CFE);
+	rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx), RCANFD_RFCC_RFE);
+
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+	return 0;
+
+fail_mode_change:
+	rcar_canfd_disable_channel_interrupts(priv);
+	return err;
+}
+
+static int rcar_canfd_open(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct rcar_canfd_global *gpriv = priv->gpriv;
+	int err;
+
+	/* Peripheral clock is already enabled in probe */
+	err = clk_prepare_enable(gpriv->can_clk);
+	if (err) {
+		netdev_err(ndev, "failed to enable CAN clock, error %d\n", err);
+		goto out_clock;
+	}
+
+	err = open_candev(ndev);
+	if (err) {
+		netdev_err(ndev, "open_candev() failed, error %d\n", err);
+		goto out_can_clock;
+	}
+
+	napi_enable(&priv->napi);
+	err = rcar_canfd_start(ndev);
+	if (err)
+		goto out_close;
+	netif_start_queue(ndev);
+	can_led_event(ndev, CAN_LED_EVENT_OPEN);
+	return 0;
+out_close:
+	napi_disable(&priv->napi);
+	close_candev(ndev);
+out_can_clock:
+	clk_disable_unprepare(gpriv->can_clk);
+out_clock:
+	return err;
+}
+
+static void rcar_canfd_stop(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	int err;
+	u32 sts, ch = priv->channel;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	/* Transition to channel reset mode  */
+	rcar_canfd_update_bit(priv->base, RCANFD_CCTR(ch),
+			      RCANFD_CCTR_CHMDC_MASK, RCANFD_CCTR_CHDMC_CRESET);
+
+	/* Check Channel reset mode */
+	err = readl_poll_timeout((priv->base + RCANFD_CSTS(ch)), sts,
+				 (sts & RCANFD_CSTS_CRSTSTS), 2, 500000);
+	if (err)
+		netdev_err(ndev, "channel %u reset failed\n", ch);
+
+	rcar_canfd_disable_channel_interrupts(priv);
+
+	/* Disable Common & Rx FIFO */
+	rcar_canfd_clear_bit(priv->base, RCANFD_CFCC(ch, RCANFD_CFFIFO_IDX),
+			     RCANFD_CFCC_CFE);
+	rcar_canfd_clear_bit(priv->base, RCANFD_RFCC(ridx), RCANFD_RFCC_RFE);
+
+	/* Set the state as STOPPED */
+	priv->can.state = CAN_STATE_STOPPED;
+}
+
+static int rcar_canfd_close(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct rcar_canfd_global *gpriv = priv->gpriv;
+
+	netif_stop_queue(ndev);
+	rcar_canfd_stop(ndev);
+	napi_disable(&priv->napi);
+	clk_disable_unprepare(gpriv->can_clk);
+	close_candev(ndev);
+	can_led_event(ndev, CAN_LED_EVENT_STOP);
+	return 0;
+}
+
+static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb,
+					 struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
+	u32 sts = 0, id, dlc;
+	unsigned long flags;
+	u32 ch = priv->channel;
+
+	if (can_dropped_invalid_skb(ndev, skb))
+		return NETDEV_TX_OK;
+
+	if (cf->can_id & CAN_EFF_FLAG) {
+		id = cf->can_id & CAN_EFF_MASK;
+		id |= RCANFD_CFID_CFIDE;
+	} else {
+		id = cf->can_id & CAN_SFF_MASK;
+	}
+
+	if (cf->can_id & CAN_RTR_FLAG)
+		id |= RCANFD_CFID_CFRTR;
+
+	dlc = RCANFD_CFPTR_CFDLC(can_len2dlc(cf->len));
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+		rcar_canfd_write(priv->base,
+				 RCANFD_F_CFID(ch, RCANFD_CFFIFO_IDX), id);
+		rcar_canfd_write(priv->base,
+				 RCANFD_F_CFPTR(ch, RCANFD_CFFIFO_IDX), dlc);
+
+		if (can_is_canfd_skb(skb)) {
+			/* CAN FD frame format */
+			sts |= RCANFD_CFFDCSTS_CFFDF;
+			if (cf->flags & CANFD_BRS)
+				sts |= RCANFD_CFFDCSTS_CFBRS;
+
+			if (priv->can.state == CAN_STATE_ERROR_PASSIVE)
+				sts |= RCANFD_CFFDCSTS_CFESI;
+		}
+
+		rcar_canfd_write(priv->base,
+				 RCANFD_F_CFFDCSTS(ch, RCANFD_CFFIFO_IDX), sts);
+
+		rcar_canfd_put_data(priv, cf,
+				    RCANFD_F_CFDF(ch, RCANFD_CFFIFO_IDX, 0));
+	} else {
+		rcar_canfd_write(priv->base,
+				 RCANFD_C_CFID(ch, RCANFD_CFFIFO_IDX), id);
+		rcar_canfd_write(priv->base,
+				 RCANFD_C_CFPTR(ch, RCANFD_CFFIFO_IDX), dlc);
+		rcar_canfd_put_data(priv, cf,
+				    RCANFD_C_CFDF(ch, RCANFD_CFFIFO_IDX, 0));
+	}
+
+	priv->tx_len[priv->tx_head % RCANFD_FIFO_DEPTH] = cf->len;
+	can_put_echo_skb(skb, ndev, priv->tx_head % RCANFD_FIFO_DEPTH);
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+	priv->tx_head++;
+
+	/* Stop the queue if we've filled all FIFO entries */
+	if (priv->tx_head - priv->tx_tail >= RCANFD_FIFO_DEPTH)
+		netif_stop_queue(ndev);
+
+	/* Start Tx: Write 0xff to CFPC to increment the CPU-side
+	 * pointer for the Common FIFO
+	 */
+	rcar_canfd_write(priv->base,
+			 RCANFD_CFPCTR(ch, RCANFD_CFFIFO_IDX), 0xff);
+
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+	return NETDEV_TX_OK;
+}
+
+static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
+{
+	struct net_device_stats *stats = &priv->ndev->stats;
+	struct canfd_frame *cf;
+	struct sk_buff *skb;
+	u32 sts = 0, id, dlc;
+	u32 ch = priv->channel;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+		id = rcar_canfd_read(priv->base, RCANFD_F_RFID(ridx));
+		dlc = rcar_canfd_read(priv->base, RCANFD_F_RFPTR(ridx));
+
+		sts = rcar_canfd_read(priv->base, RCANFD_F_RFFDSTS(ridx));
+		if (sts & RCANFD_RFFDSTS_RFFDF)
+			skb = alloc_canfd_skb(priv->ndev, &cf);
+		else
+			skb = alloc_can_skb(priv->ndev,
+					    (struct can_frame **)&cf);
+	} else {
+		id = rcar_canfd_read(priv->base, RCANFD_C_RFID(ridx));
+		dlc = rcar_canfd_read(priv->base, RCANFD_C_RFPTR(ridx));
+		skb = alloc_can_skb(priv->ndev, (struct can_frame **)&cf);
+	}
+
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+
+	if (id & RCANFD_RFID_RFIDE)
+		cf->can_id = (id & CAN_EFF_MASK) | CAN_EFF_FLAG;
+	else
+		cf->can_id = id & CAN_SFF_MASK;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+		if (sts & RCANFD_RFFDSTS_RFFDF)
+			cf->len = can_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
+		else
+			cf->len = get_can_dlc(RCANFD_RFPTR_RFDLC(dlc));
+
+		if (sts & RCANFD_RFFDSTS_RFESI) {
+			cf->flags |= CANFD_ESI;
+			netdev_dbg(priv->ndev, "ESI Error\n");
+		}
+
+		if (!(sts & RCANFD_RFFDSTS_RFFDF) && (id & RCANFD_RFID_RFRTR)) {
+			cf->can_id |= CAN_RTR_FLAG;
+		} else {
+			if (sts & RCANFD_RFFDSTS_RFBRS)
+				cf->flags |= CANFD_BRS;
+
+			rcar_canfd_get_data(priv, cf, RCANFD_F_RFDF(ridx, 0));
+		}
+	} else {
+		cf->len = get_can_dlc(RCANFD_RFPTR_RFDLC(dlc));
+		if (id & RCANFD_RFID_RFRTR)
+			cf->can_id |= CAN_RTR_FLAG;
+		else
+			rcar_canfd_get_data(priv, cf, RCANFD_C_RFDF(ridx, 0));
+	}
+
+	/* Write 0xff to RFPC to increment the CPU-side
+	 * pointer of the Rx FIFO
+	 */
+	rcar_canfd_write(priv->base, RCANFD_RFPCTR(ridx), 0xff);
+
+	can_led_event(priv->ndev, CAN_LED_EVENT_RX);
+
+	stats->rx_bytes += cf->len;
+	stats->rx_packets++;
+	netif_receive_skb(skb);
+}
+
+static int rcar_canfd_rx_poll(struct napi_struct *napi, int quota)
+{
+	struct rcar_canfd_channel *priv =
+		container_of(napi, struct rcar_canfd_channel, napi);
+	int num_pkts;
+	u32 sts;
+	u32 ch = priv->channel;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	for (num_pkts = 0; num_pkts < quota; num_pkts++) {
+		sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx));
+		/* Check FIFO empty condition */
+		if (sts & RCANFD_RFSTS_RFEMP)
+			break;
+
+		rcar_canfd_rx_pkt(priv);
+
+		/* Clear interrupt bit */
+		if (sts & RCANFD_RFSTS_RFIF)
+			rcar_canfd_write(priv->base, RCANFD_RFSTS(ridx),
+					 sts & ~RCANFD_RFSTS_RFIF);
+	}
+
+	/* All packets processed */
+	if (num_pkts < quota) {
+		napi_complete(napi);
+		/* Enable Rx FIFO interrupts */
+		rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx),
+				   RCANFD_RFCC_RFIE);
+	}
+	return num_pkts;
+}
+
+static int rcar_canfd_do_set_mode(struct net_device *ndev, enum can_mode mode)
+{
+	int err;
+
+	switch (mode) {
+	case CAN_MODE_START:
+		err = rcar_canfd_start(ndev);
+		if (err)
+			return err;
+		netif_wake_queue(ndev);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int rcar_canfd_get_berr_counter(const struct net_device *dev,
+				       struct can_berr_counter *bec)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(dev);
+	u32 val, ch = priv->channel;
+
+	/* Peripheral clock is already enabled in probe */
+	val = rcar_canfd_read(priv->base, RCANFD_CSTS(ch));
+	bec->txerr = RCANFD_CSTS_TECCNT(val);
+	bec->rxerr = RCANFD_CSTS_RECCNT(val);
+	return 0;
+}
+
+static const struct net_device_ops rcar_canfd_netdev_ops = {
+	.ndo_open = rcar_canfd_open,
+	.ndo_stop = rcar_canfd_close,
+	.ndo_start_xmit = rcar_canfd_start_xmit,
+	.ndo_change_mtu = can_change_mtu,
+};
+
+static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
+				    u32 fcan_freq)
+{
+	struct platform_device *pdev = gpriv->pdev;
+	struct rcar_canfd_channel *priv;
+	struct net_device *ndev;
+	int err = -ENODEV;
+
+	ndev = alloc_candev(sizeof(*priv), RCANFD_FIFO_DEPTH);
+	if (!ndev) {
+		dev_err(&pdev->dev, "alloc_candev() failed\n");
+		err = -ENOMEM;
+		goto fail;
+	}
+	priv = netdev_priv(ndev);
+
+	ndev->netdev_ops = &rcar_canfd_netdev_ops;
+	ndev->flags |= IFF_ECHO;
+	priv->ndev = ndev;
+	priv->base = gpriv->base;
+	priv->channel = ch;
+	priv->can.clock.freq = fcan_freq;
+	dev_info(&pdev->dev, "can_clk rate is %u\n", priv->can.clock.freq);
+
+	if (gpriv->fdmode) {
+		priv->can.bittiming_const = &rcar_canfd_nom_bittiming_const;
+		priv->can.data_bittiming_const =
+			&rcar_canfd_data_bittiming_const;
+
+		/* Controller starts in CAN FD only mode */
+		can_set_static_ctrlmode(ndev, CAN_CTRLMODE_FD);
+		priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING;
+	} else {
+		/* Controller starts in Classical CAN only mode */
+		priv->can.bittiming_const = &rcar_canfd_bittiming_const;
+		priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING;
+	}
+
+	priv->can.do_set_mode = rcar_canfd_do_set_mode;
+	priv->can.do_get_berr_counter = rcar_canfd_get_berr_counter;
+	priv->gpriv = gpriv;
+	SET_NETDEV_DEV(ndev, &pdev->dev);
+
+	netif_napi_add(ndev, &priv->napi, rcar_canfd_rx_poll,
+		       RCANFD_NAPI_WEIGHT);
+	err = register_candev(ndev);
+	if (err) {
+		dev_err(&pdev->dev,
+			"register_candev() failed, error %d\n", err);
+		goto fail_candev;
+	}
+	spin_lock_init(&priv->tx_lock);
+	devm_can_led_init(ndev);
+	gpriv->ch[priv->channel] = priv;
+	dev_info(&pdev->dev, "device registered (channel %u)\n", priv->channel);
+	return 0;
+
+fail_candev:
+	netif_napi_del(&priv->napi);
+	free_candev(ndev);
+fail:
+	return err;
+}
+
+static void rcar_canfd_channel_remove(struct rcar_canfd_global *gpriv, u32 ch)
+{
+	struct rcar_canfd_channel *priv = gpriv->ch[ch];
+
+	if (priv) {
+		unregister_candev(priv->ndev);
+		netif_napi_del(&priv->napi);
+		free_candev(priv->ndev);
+	}
+}
+
+static int rcar_canfd_probe(struct platform_device *pdev)
+{
+	struct resource *mem;
+	void __iomem *addr;
+	u32 sts, ch, fcan_freq;
+	struct rcar_canfd_global *gpriv;
+	struct device_node *of_child;
+	unsigned long channels_mask = 0;
+	int err, ch_irq, g_irq;
+	bool fdmode = true;			/* CAN FD only mode - default */
+
+	if (of_property_read_bool(pdev->dev.of_node, "renesas,no-can-fd"))
+		fdmode = false;			/* Classical CAN only mode */
+
+	of_child = of_get_child_by_name(pdev->dev.of_node, "channel0");
+	if (of_child && of_device_is_available(of_child))
+		channels_mask |= BIT(0);	/* Channel 0 */
+
+	of_child = of_get_child_by_name(pdev->dev.of_node, "channel1");
+	if (of_child && of_device_is_available(of_child))
+		channels_mask |= BIT(1);	/* Channel 1 */
+
+	ch_irq = platform_get_irq(pdev, 0);
+	if (ch_irq < 0) {
+		dev_err(&pdev->dev, "no Channel IRQ resource\n");
+		err = ch_irq;
+		goto fail_dev;
+	}
+
+	g_irq = platform_get_irq(pdev, 1);
+	if (g_irq < 0) {
+		dev_err(&pdev->dev, "no Global IRQ resource\n");
+		err = g_irq;
+		goto fail_dev;
+	}
+
+	/* Global controller context */
+	gpriv = devm_kzalloc(&pdev->dev, sizeof(*gpriv), GFP_KERNEL);
+	if (!gpriv) {
+		err = -ENOMEM;
+		goto fail_dev;
+	}
+	gpriv->pdev = pdev;
+	gpriv->channels_mask = channels_mask;
+	gpriv->fdmode = fdmode;
+
+	/* Peripheral clock */
+	gpriv->clkp = devm_clk_get(&pdev->dev, "fck");
+	if (IS_ERR(gpriv->clkp)) {
+		err = PTR_ERR(gpriv->clkp);
+		dev_err(&pdev->dev, "cannot get peripheral clock, error %d\n",
+			err);
+		goto fail_dev;
+	}
+
+	/* fCAN clock: Pick External clock. If not available fallback to
+	 * CANFD clock
+	 */
+	gpriv->can_clk = devm_clk_get(&pdev->dev, "can_clk");
+	if (IS_ERR(gpriv->can_clk) || (clk_get_rate(gpriv->can_clk) == 0)) {
+		gpriv->can_clk = devm_clk_get(&pdev->dev, "canfd");
+		if (IS_ERR(gpriv->can_clk)) {
+			err = PTR_ERR(gpriv->can_clk);
+			dev_err(&pdev->dev,
+				"cannot get canfd clock, error %d\n", err);
+			goto fail_dev;
+		}
+		gpriv->fcan = RCANFD_CANFDCLK;
+
+	} else {
+		gpriv->fcan = RCANFD_EXTCLK;
+	}
+	fcan_freq = clk_get_rate(gpriv->can_clk);
+
+	if (gpriv->fcan == RCANFD_CANFDCLK)
+		/* CANFD clock is further divided by (1/2) within the IP */
+		fcan_freq /= 2;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	addr = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(addr)) {
+		err = PTR_ERR(addr);
+		goto fail_dev;
+	}
+	gpriv->base = addr;
+
+	/* Request IRQ that's common for both channels */
+	err = devm_request_irq(&pdev->dev, ch_irq,
+			       rcar_canfd_channel_interrupt, 0,
+			       "canfd.chn", gpriv);
+	if (err) {
+		dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n",
+			ch_irq, err);
+		goto fail_dev;
+	}
+	err = devm_request_irq(&pdev->dev, g_irq,
+			       rcar_canfd_global_interrupt, 0,
+			       "canfd.gbl", gpriv);
+	if (err) {
+		dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n",
+			g_irq, err);
+		goto fail_dev;
+	}
+
+	/* Enable peripheral clock for register access */
+	err = clk_prepare_enable(gpriv->clkp);
+	if (err) {
+		dev_err(&pdev->dev,
+			"failed to enable peripheral clock, error %d\n", err);
+		goto fail_dev;
+	}
+
+	err = rcar_canfd_reset_controller(gpriv);
+	if (err) {
+		dev_err(&pdev->dev, "reset controller failed\n");
+		goto fail_clk;
+	}
+
+	/* Controller in Global reset & Channel reset mode */
+	rcar_canfd_configure_controller(gpriv);
+
+	/* Configure per channel attributes */
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		/* Configure Channel's Rx fifo */
+		rcar_canfd_configure_rx(gpriv, ch);
+
+		/* Configure Channel's Tx (Common) fifo */
+		rcar_canfd_configure_tx(gpriv, ch);
+
+		/* Configure receive rules */
+		rcar_canfd_configure_afl_rules(gpriv, ch);
+	}
+
+	/* Configure common interrupts */
+	rcar_canfd_enable_global_interrupts(gpriv);
+
+	/* Start Global operation mode */
+	rcar_canfd_update_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GMDC_MASK,
+			      RCANFD_GCTR_GMDC_GOPM);
+
+	/* Verify mode change */
+	err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts,
+				 !(sts & RCANFD_GSTS_GNOPM), 2, 500000);
+	if (err) {
+		dev_err(&pdev->dev, "global operational mode failed\n");
+		goto fail_mode;
+	}
+
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		err = rcar_canfd_channel_probe(gpriv, ch, fcan_freq);
+		if (err)
+			goto fail_channel;
+	}
+
+	platform_set_drvdata(pdev, gpriv);
+	dev_info(&pdev->dev, "global operational state (clk %d, fdmode %d)\n",
+		 gpriv->fcan, gpriv->fdmode);
+	return 0;
+
+fail_channel:
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS)
+		rcar_canfd_channel_remove(gpriv, ch);
+fail_mode:
+	rcar_canfd_disable_global_interrupts(gpriv);
+fail_clk:
+	clk_disable_unprepare(gpriv->clkp);
+fail_dev:
+	return err;
+}
+
+static int rcar_canfd_remove(struct platform_device *pdev)
+{
+	struct rcar_canfd_global *gpriv = platform_get_drvdata(pdev);
+	u32 ch;
+
+	rcar_canfd_reset_controller(gpriv);
+	rcar_canfd_disable_global_interrupts(gpriv);
+
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		rcar_canfd_disable_channel_interrupts(gpriv->ch[ch]);
+		rcar_canfd_channel_remove(gpriv, ch);
+	}
+
+	/* Enter global sleep mode */
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GSLPR);
+	clk_disable_unprepare(gpriv->clkp);
+	return 0;
+}
+
+static int __maybe_unused rcar_canfd_suspend(struct device *dev)
+{
+	return 0;
+}
+
+static int __maybe_unused rcar_canfd_resume(struct device *dev)
+{
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(rcar_canfd_pm_ops, rcar_canfd_suspend,
+			 rcar_canfd_resume);
+
+static const struct of_device_id rcar_canfd_of_table[] = {
+	{ .compatible = "renesas,rcar-gen3-canfd" },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, rcar_canfd_of_table);
+
+static struct platform_driver rcar_canfd_driver = {
+	.driver = {
+		.name = RCANFD_DRV_NAME,
+		.of_match_table = of_match_ptr(rcar_canfd_of_table),
+		.pm = &rcar_canfd_pm_ops,
+	},
+	.probe = rcar_canfd_probe,
+	.remove = rcar_canfd_remove,
+};
+
+module_platform_driver(rcar_canfd_driver);
+
+MODULE_AUTHOR("Ramesh Shanmugasundaram <[email protected]>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("CAN FD driver for Renesas R-Car SoC");
+MODULE_ALIAS("platform:" RCANFD_DRV_NAME);
diff --git a/drivers/net/can/sja1000/tscan1.c b/drivers/net/can/sja1000/tscan1.c
index 76513dd780c7..79572457a2d6 100644
--- a/drivers/net/can/sja1000/tscan1.c
+++ b/drivers/net/can/sja1000/tscan1.c
@@ -203,14 +203,4 @@ static struct isa_driver tscan1_isa_driver = {
 	},
 };
 
-static int __init tscan1_init(void)
-{
-	return isa_register_driver(&tscan1_isa_driver, TSCAN1_MAXDEV);
-}
-module_init(tscan1_init);
-
-static void __exit tscan1_exit(void)
-{
-	isa_unregister_driver(&tscan1_isa_driver);
-}
-module_exit(tscan1_exit);
+module_isa_driver(tscan1_isa_driver, TSCAN1_MAXDEV);
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 9a3f15cb7ef4..eb7173713bbc 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -354,7 +354,7 @@ static netdev_tx_t slc_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct slcan *sl = netdev_priv(dev);
 
-	if (skb->len != sizeof(struct can_frame))
+	if (skb->len != CAN_MTU)
 		goto out;
 
 	spin_lock(&sl->lock);
@@ -442,7 +442,7 @@ static void slc_setup(struct net_device *dev)
 	dev->addr_len		= 0;
 	dev->tx_queue_len	= 10;
 
-	dev->mtu		= sizeof(struct can_frame);
+	dev->mtu		= CAN_MTU;
 	dev->type		= ARPHRD_CAN;
 
 	/* New-style flags. */
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index cf36d26ef002..f3f05fea8e1f 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -1145,8 +1145,11 @@ static int mcp251x_can_probe(struct spi_device *spi)
 
 	/* Here is OK to not lock the MCP, no one knows about it yet */
 	ret = mcp251x_hw_probe(spi);
-	if (ret)
+	if (ret) {
+		if (ret == -ENODEV)
+			dev_err(&spi->dev, "Cannot initialize MCP%x. Wrong wiring?\n", priv->model);
 		goto error_probe;
+	}
 
 	mcp251x_hw_sleep(spi);
 
@@ -1156,6 +1159,7 @@ static int mcp251x_can_probe(struct spi_device *spi)
 
 	devm_can_led_init(net);
 
+	netdev_info(net, "MCP%x successfully initialized.\n", priv->model);
 	return 0;
 
 error_probe:
@@ -1168,6 +1172,7 @@ out_clk:
 out_free:
 	free_candev(net);
 
+	dev_err(&spi->dev, "Probe failed, err=%d\n", -ret);
 	return ret;
 }
 
diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index bcb272f6c68a..8483a40e7e9e 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -16,7 +16,8 @@ config CAN_ESD_USB2
 config CAN_GS_USB
 	tristate "Geschwister Schneider UG interfaces"
 	---help---
-	  This driver supports the Geschwister Schneider USB/CAN devices.
+	  This driver supports the Geschwister Schneider and bytewerk.org
+	  candleLight USB CAN interfaces USB/CAN devices
 	  If unsure choose N,
 	  choose Y for built in support,
 	  M to compile as module (module will be named: gs_usb).
@@ -46,6 +47,8 @@ config CAN_KVASER_USB
 	    - Kvaser USBcan R
 	    - Kvaser Leaf Light v2
 	    - Kvaser Mini PCI Express HS
+	    - Kvaser Mini PCI Express 2xHS
+	    - Kvaser USBcan Light 2xHS
 	    - Kvaser USBcan II HS/HS
 	    - Kvaser USBcan II HS/LS
 	    - Kvaser USBcan Rugged ("USBcan Rev B")
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 1556d4286235..6f0cbc38782e 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -1,7 +1,9 @@
-/* CAN driver for Geschwister Schneider USB/CAN devices.
+/* CAN driver for Geschwister Schneider USB/CAN devices
+ * and bytewerk.org candleLight USB CAN interfaces.
  *
- * Copyright (C) 2013 Geschwister Schneider Technologie-,
+ * Copyright (C) 2013-2016 Geschwister Schneider Technologie-,
  * Entwicklungs- und Vertriebs UG (Haftungsbeschränkt).
+ * Copyright (C) 2016 Hubert Denkmair
  *
  * Many thanks to all socketcan devs!
  *
@@ -29,6 +31,9 @@
 #define USB_GSUSB_1_VENDOR_ID      0x1d50
 #define USB_GSUSB_1_PRODUCT_ID     0x606f
 
+#define USB_CANDLELIGHT_VENDOR_ID  0x1209
+#define USB_CANDLELIGHT_PRODUCT_ID 0x2323
+
 #define GSUSB_ENDPOINT_IN          1
 #define GSUSB_ENDPOINT_OUT         2
 
@@ -39,7 +44,9 @@ enum gs_usb_breq {
 	GS_USB_BREQ_MODE,
 	GS_USB_BREQ_BERR,
 	GS_USB_BREQ_BT_CONST,
-	GS_USB_BREQ_DEVICE_CONFIG
+	GS_USB_BREQ_DEVICE_CONFIG,
+	GS_USB_BREQ_TIMESTAMP,
+	GS_USB_BREQ_IDENTIFY,
 };
 
 enum gs_can_mode {
@@ -58,6 +65,11 @@ enum gs_can_state {
 	GS_CAN_STATE_SLEEPING
 };
 
+enum gs_can_identify_mode {
+	GS_CAN_IDENTIFY_OFF = 0,
+	GS_CAN_IDENTIFY_ON
+};
+
 /* data types passed between host and device */
 struct gs_host_config {
 	u32 byte_order;
@@ -77,10 +89,10 @@ struct gs_device_config {
 } __packed;
 
 #define GS_CAN_MODE_NORMAL               0
-#define GS_CAN_MODE_LISTEN_ONLY          (1<<0)
-#define GS_CAN_MODE_LOOP_BACK            (1<<1)
-#define GS_CAN_MODE_TRIPLE_SAMPLE        (1<<2)
-#define GS_CAN_MODE_ONE_SHOT             (1<<3)
+#define GS_CAN_MODE_LISTEN_ONLY          BIT(0)
+#define GS_CAN_MODE_LOOP_BACK            BIT(1)
+#define GS_CAN_MODE_TRIPLE_SAMPLE        BIT(2)
+#define GS_CAN_MODE_ONE_SHOT             BIT(3)
 
 struct gs_device_mode {
 	u32 mode;
@@ -101,10 +113,16 @@ struct gs_device_bittiming {
 	u32 brp;
 } __packed;
 
-#define GS_CAN_FEATURE_LISTEN_ONLY      (1<<0)
-#define GS_CAN_FEATURE_LOOP_BACK        (1<<1)
-#define GS_CAN_FEATURE_TRIPLE_SAMPLE    (1<<2)
-#define GS_CAN_FEATURE_ONE_SHOT         (1<<3)
+struct gs_identify_mode {
+	u32 mode;
+} __packed;
+
+#define GS_CAN_FEATURE_LISTEN_ONLY      BIT(0)
+#define GS_CAN_FEATURE_LOOP_BACK        BIT(1)
+#define GS_CAN_FEATURE_TRIPLE_SAMPLE    BIT(2)
+#define GS_CAN_FEATURE_ONE_SHOT         BIT(3)
+#define GS_CAN_FEATURE_HW_TIMESTAMP     BIT(4)
+#define GS_CAN_FEATURE_IDENTIFY         BIT(5)
 
 struct gs_device_bt_const {
 	u32 feature;
@@ -209,7 +227,8 @@ static void gs_free_tx_context(struct gs_tx_context *txc)
 
 /* Get a tx context by id.
  */
-static struct gs_tx_context *gs_get_tx_context(struct gs_can *dev, unsigned int id)
+static struct gs_tx_context *gs_get_tx_context(struct gs_can *dev,
+					       unsigned int id)
 {
 	unsigned long flags;
 
@@ -452,7 +471,8 @@ static void gs_usb_xmit_callback(struct urb *urb)
 		netif_wake_queue(netdev);
 }
 
-static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb,
+				     struct net_device *netdev)
 {
 	struct gs_can *dev = netdev_priv(netdev);
 	struct net_device_stats *stats = &dev->netdev->stats;
@@ -658,7 +678,8 @@ static int gs_can_open(struct net_device *netdev)
 	rc = usb_control_msg(interface_to_usbdev(dev->iface),
 			     usb_sndctrlpipe(interface_to_usbdev(dev->iface), 0),
 			     GS_USB_BREQ_MODE,
-			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     USB_DIR_OUT | USB_TYPE_VENDOR |
+			     USB_RECIP_INTERFACE,
 			     dev->channel,
 			     0,
 			     dm,
@@ -721,7 +742,59 @@ static const struct net_device_ops gs_usb_netdev_ops = {
 	.ndo_change_mtu = can_change_mtu,
 };
 
-static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface *intf)
+static int gs_usb_set_identify(struct net_device *netdev, bool do_identify)
+{
+	struct gs_can *dev = netdev_priv(netdev);
+	struct gs_identify_mode imode;
+	int rc;
+
+	if (do_identify)
+		imode.mode = GS_CAN_IDENTIFY_ON;
+	else
+		imode.mode = GS_CAN_IDENTIFY_OFF;
+
+	rc = usb_control_msg(interface_to_usbdev(dev->iface),
+			     usb_sndctrlpipe(interface_to_usbdev(dev->iface),
+					     0),
+			     GS_USB_BREQ_IDENTIFY,
+			     USB_DIR_OUT | USB_TYPE_VENDOR |
+			     USB_RECIP_INTERFACE,
+			     dev->channel,
+			     0,
+			     &imode,
+			     sizeof(imode),
+			     100);
+
+	return (rc > 0) ? 0 : rc;
+}
+
+/* blink LED's for finding the this interface */
+static int gs_usb_set_phys_id(struct net_device *dev,
+			      enum ethtool_phys_id_state state)
+{
+	int rc = 0;
+
+	switch (state) {
+	case ETHTOOL_ID_ACTIVE:
+		rc = gs_usb_set_identify(dev, GS_CAN_IDENTIFY_ON);
+		break;
+	case ETHTOOL_ID_INACTIVE:
+		rc = gs_usb_set_identify(dev, GS_CAN_IDENTIFY_OFF);
+		break;
+	default:
+		break;
+	}
+
+	return rc;
+}
+
+static const struct ethtool_ops gs_usb_ethtool_ops = {
+	.set_phys_id = gs_usb_set_phys_id,
+};
+
+static struct gs_can *gs_make_candev(unsigned int channel,
+				     struct usb_interface *intf,
+				     struct gs_device_config *dconf)
 {
 	struct gs_can *dev;
 	struct net_device *netdev;
@@ -809,10 +882,14 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface
 	if (bt_const->feature & GS_CAN_FEATURE_ONE_SHOT)
 		dev->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT;
 
-	kfree(bt_const);
-
 	SET_NETDEV_DEV(netdev, &intf->dev);
 
+	if (dconf->sw_version > 1)
+		if (bt_const->feature & GS_CAN_FEATURE_IDENTIFY)
+			netdev->ethtool_ops = &gs_usb_ethtool_ops;
+
+	kfree(bt_const);
+
 	rc = register_candev(dev->netdev);
 	if (rc) {
 		free_candev(dev->netdev);
@@ -830,19 +907,16 @@ static void gs_destroy_candev(struct gs_can *dev)
 	free_candev(dev->netdev);
 }
 
-static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
+static int gs_usb_probe(struct usb_interface *intf,
+			const struct usb_device_id *id)
 {
 	struct gs_usb *dev;
 	int rc = -ENOMEM;
 	unsigned int icount, i;
-	struct gs_host_config *hconf;
-	struct gs_device_config *dconf;
-
-	hconf = kmalloc(sizeof(*hconf), GFP_KERNEL);
-	if (!hconf)
-		return -ENOMEM;
-
-	hconf->byte_order = 0x0000beef;
+	struct gs_host_config hconf = {
+		.byte_order = 0x0000beef,
+	};
+	struct gs_device_config dconf;
 
 	/* send host config */
 	rc = usb_control_msg(interface_to_usbdev(intf),
@@ -851,22 +925,16 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *
 			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
 			     1,
 			     intf->altsetting[0].desc.bInterfaceNumber,
-			     hconf,
-			     sizeof(*hconf),
+			     &hconf,
+			     sizeof(hconf),
 			     1000);
 
-	kfree(hconf);
-
 	if (rc < 0) {
 		dev_err(&intf->dev, "Couldn't send data format (err=%d)\n",
 			rc);
 		return rc;
 	}
 
-	dconf = kmalloc(sizeof(*dconf), GFP_KERNEL);
-	if (!dconf)
-		return -ENOMEM;
-
 	/* read device config */
 	rc = usb_control_msg(interface_to_usbdev(intf),
 			     usb_rcvctrlpipe(interface_to_usbdev(intf), 0),
@@ -874,22 +942,16 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *
 			     USB_DIR_IN|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
 			     1,
 			     intf->altsetting[0].desc.bInterfaceNumber,
-			     dconf,
-			     sizeof(*dconf),
+			     &dconf,
+			     sizeof(dconf),
 			     1000);
 	if (rc < 0) {
 		dev_err(&intf->dev, "Couldn't get device config: (err=%d)\n",
 			rc);
-
-		kfree(dconf);
-
 		return rc;
 	}
 
-	icount = dconf->icount+1;
-
-	kfree(dconf);
-
+	icount = dconf.icount + 1;
 	dev_info(&intf->dev, "Configuring for %d interfaces\n", icount);
 
 	if (icount > GS_MAX_INTF) {
@@ -910,7 +972,7 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *
 	dev->udev = interface_to_usbdev(intf);
 
 	for (i = 0; i < icount; i++) {
-		dev->canch[i] = gs_make_candev(i, intf);
+		dev->canch[i] = gs_make_candev(i, intf, &dconf);
 		if (IS_ERR_OR_NULL(dev->canch[i])) {
 			/* save error code to return later */
 			rc = PTR_ERR(dev->canch[i]);
@@ -952,6 +1014,8 @@ static void gs_usb_disconnect(struct usb_interface *intf)
 static const struct usb_device_id gs_usb_table[] = {
 	{ USB_DEVICE_INTERFACE_NUMBER(USB_GSUSB_1_VENDOR_ID,
 				      USB_GSUSB_1_PRODUCT_ID, 0) },
+	{ USB_DEVICE_INTERFACE_NUMBER(USB_CANDLELIGHT_VENDOR_ID,
+				      USB_CANDLELIGHT_PRODUCT_ID, 0) },
 	{} /* Terminating entry */
 };
 
@@ -969,5 +1033,6 @@ module_usb_driver(gs_usb_driver);
 MODULE_AUTHOR("Maximilian Schneider <[email protected]>");
 MODULE_DESCRIPTION(
 "Socket CAN device driver for Geschwister Schneider Technologie-, "
-"Entwicklungs- und Vertriebs UG. USB2.0 to CAN interfaces.");
+"Entwicklungs- und Vertriebs UG. USB2.0 to CAN interfaces\n"
+"and bytewerk.org candleLight USB CAN interfaces.");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 022bfa13ebfa..6f1f3b675ff5 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -59,11 +59,14 @@
 #define USB_CAN_R_PRODUCT_ID		39
 #define USB_LEAF_LITE_V2_PRODUCT_ID	288
 #define USB_MINI_PCIE_HS_PRODUCT_ID	289
+#define USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID 290
+#define USB_USBCAN_LIGHT_2HS_PRODUCT_ID	291
+#define USB_MINI_PCIE_2HS_PRODUCT_ID	292
 
 static inline bool kvaser_is_leaf(const struct usb_device_id *id)
 {
 	return id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID &&
-	       id->idProduct <= USB_MINI_PCIE_HS_PRODUCT_ID;
+	       id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID;
 }
 
 /* Kvaser USBCan-II devices */
@@ -537,6 +540,9 @@ static const struct usb_device_id kvaser_usb_table[] = {
 		.driver_info = KVASER_HAS_TXRX_ERRORS },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) },
 
 	/* USBCANII family IDs */
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID),
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 200663c43ce9..8f4544394f44 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -9,14 +9,6 @@ config NET_DSA_MV88E6060
 	  This enables support for the Marvell 88E6060 ethernet switch
 	  chip.
 
-config NET_DSA_MV88E6XXX
-	tristate "Marvell 88E6xxx Ethernet switch chip support"
-	depends on NET_DSA
-	select NET_DSA_TAG_EDSA
-	---help---
-	  This enables support for most of the Marvell 88E6xxx models of
-	  Ethernet switch chips, except 88E6060.
-
 config NET_DSA_BCM_SF2
 	tristate "Broadcom Starfighter 2 Ethernet switch support"
 	depends on HAS_IOMEM && NET_DSA
@@ -28,4 +20,8 @@ config NET_DSA_BCM_SF2
 	  This enables support for the Broadcom Starfighter 2 Ethernet
 	  switch chips.
 
+source "drivers/net/dsa/b53/Kconfig"
+
+source "drivers/net/dsa/mv88e6xxx/Kconfig"
+
 endmenu
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index 76b751dd9efd..ca1e71b853a6 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -1,3 +1,5 @@
 obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
-obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx.o
 obj-$(CONFIG_NET_DSA_BCM_SF2)	+= bcm_sf2.o
+
+obj-y				+= b53/
+obj-y				+= mv88e6xxx/
diff --git a/drivers/net/dsa/b53/Kconfig b/drivers/net/dsa/b53/Kconfig
new file mode 100644
index 000000000000..27f32a50df57
--- /dev/null
+++ b/drivers/net/dsa/b53/Kconfig
@@ -0,0 +1,33 @@
+menuconfig B53
+	tristate "Broadcom BCM53xx managed switch support"
+	depends on NET_DSA
+	help
+	  This driver adds support for Broadcom managed switch chips. It supports
+	  BCM5325E, BCM5365, BCM539x, BCM53115 and BCM53125 as well as BCM63XX
+	  integrated switches.
+
+config B53_SPI_DRIVER
+	tristate "B53 SPI connected switch driver"
+	depends on B53 && SPI
+	help
+	  Select to enable support for registering switches configured through SPI.
+
+config B53_MDIO_DRIVER
+	tristate "B53 MDIO connected switch driver"
+	depends on B53
+	help
+	  Select to enable support for registering switches configured through MDIO.
+
+config B53_MMAP_DRIVER
+	tristate "B53 MMAP connected switch driver"
+	depends on B53 && HAS_IOMEM
+	help
+	  Select to enable support for memory-mapped switches like the BCM63XX
+	  integrated switches.
+
+config B53_SRAB_DRIVER
+	tristate "B53 SRAB connected switch driver"
+	depends on B53 && HAS_IOMEM
+	help
+	  Select to enable support for memory-mapped Switch Register Access
+	  Bridge Registers (SRAB) like it is found on the BCM53010
diff --git a/drivers/net/dsa/b53/Makefile b/drivers/net/dsa/b53/Makefile
new file mode 100644
index 000000000000..7e6f9a8bfd75
--- /dev/null
+++ b/drivers/net/dsa/b53/Makefile
@@ -0,0 +1,6 @@
+obj-$(CONFIG_B53)		+= b53_common.o
+
+obj-$(CONFIG_B53_SPI_DRIVER)	+= b53_spi.o
+obj-$(CONFIG_B53_MDIO_DRIVER)	+= b53_mdio.o
+obj-$(CONFIG_B53_MMAP_DRIVER)	+= b53_mmap.o
+obj-$(CONFIG_B53_SRAB_DRIVER)	+= b53_srab.o
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
new file mode 100644
index 000000000000..444de66667b9
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -0,0 +1,1787 @@
+/*
+ * B53 switch driver main logic
+ *
+ * Copyright (C) 2011-2013 Jonas Gorski <[email protected]>
+ * Copyright (C) 2016 Florian Fainelli <[email protected]>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/gpio.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_data/b53.h>
+#include <linux/phy.h>
+#include <linux/etherdevice.h>
+#include <linux/if_bridge.h>
+#include <net/dsa.h>
+#include <net/switchdev.h>
+
+#include "b53_regs.h"
+#include "b53_priv.h"
+
+struct b53_mib_desc {
+	u8 size;
+	u8 offset;
+	const char *name;
+};
+
+/* BCM5365 MIB counters */
+static const struct b53_mib_desc b53_mibs_65[] = {
+	{ 8, 0x00, "TxOctets" },
+	{ 4, 0x08, "TxDropPkts" },
+	{ 4, 0x10, "TxBroadcastPkts" },
+	{ 4, 0x14, "TxMulticastPkts" },
+	{ 4, 0x18, "TxUnicastPkts" },
+	{ 4, 0x1c, "TxCollisions" },
+	{ 4, 0x20, "TxSingleCollision" },
+	{ 4, 0x24, "TxMultipleCollision" },
+	{ 4, 0x28, "TxDeferredTransmit" },
+	{ 4, 0x2c, "TxLateCollision" },
+	{ 4, 0x30, "TxExcessiveCollision" },
+	{ 4, 0x38, "TxPausePkts" },
+	{ 8, 0x44, "RxOctets" },
+	{ 4, 0x4c, "RxUndersizePkts" },
+	{ 4, 0x50, "RxPausePkts" },
+	{ 4, 0x54, "Pkts64Octets" },
+	{ 4, 0x58, "Pkts65to127Octets" },
+	{ 4, 0x5c, "Pkts128to255Octets" },
+	{ 4, 0x60, "Pkts256to511Octets" },
+	{ 4, 0x64, "Pkts512to1023Octets" },
+	{ 4, 0x68, "Pkts1024to1522Octets" },
+	{ 4, 0x6c, "RxOversizePkts" },
+	{ 4, 0x70, "RxJabbers" },
+	{ 4, 0x74, "RxAlignmentErrors" },
+	{ 4, 0x78, "RxFCSErrors" },
+	{ 8, 0x7c, "RxGoodOctets" },
+	{ 4, 0x84, "RxDropPkts" },
+	{ 4, 0x88, "RxUnicastPkts" },
+	{ 4, 0x8c, "RxMulticastPkts" },
+	{ 4, 0x90, "RxBroadcastPkts" },
+	{ 4, 0x94, "RxSAChanges" },
+	{ 4, 0x98, "RxFragments" },
+};
+
+#define B53_MIBS_65_SIZE	ARRAY_SIZE(b53_mibs_65)
+
+/* BCM63xx MIB counters */
+static const struct b53_mib_desc b53_mibs_63xx[] = {
+	{ 8, 0x00, "TxOctets" },
+	{ 4, 0x08, "TxDropPkts" },
+	{ 4, 0x0c, "TxQoSPkts" },
+	{ 4, 0x10, "TxBroadcastPkts" },
+	{ 4, 0x14, "TxMulticastPkts" },
+	{ 4, 0x18, "TxUnicastPkts" },
+	{ 4, 0x1c, "TxCollisions" },
+	{ 4, 0x20, "TxSingleCollision" },
+	{ 4, 0x24, "TxMultipleCollision" },
+	{ 4, 0x28, "TxDeferredTransmit" },
+	{ 4, 0x2c, "TxLateCollision" },
+	{ 4, 0x30, "TxExcessiveCollision" },
+	{ 4, 0x38, "TxPausePkts" },
+	{ 8, 0x3c, "TxQoSOctets" },
+	{ 8, 0x44, "RxOctets" },
+	{ 4, 0x4c, "RxUndersizePkts" },
+	{ 4, 0x50, "RxPausePkts" },
+	{ 4, 0x54, "Pkts64Octets" },
+	{ 4, 0x58, "Pkts65to127Octets" },
+	{ 4, 0x5c, "Pkts128to255Octets" },
+	{ 4, 0x60, "Pkts256to511Octets" },
+	{ 4, 0x64, "Pkts512to1023Octets" },
+	{ 4, 0x68, "Pkts1024to1522Octets" },
+	{ 4, 0x6c, "RxOversizePkts" },
+	{ 4, 0x70, "RxJabbers" },
+	{ 4, 0x74, "RxAlignmentErrors" },
+	{ 4, 0x78, "RxFCSErrors" },
+	{ 8, 0x7c, "RxGoodOctets" },
+	{ 4, 0x84, "RxDropPkts" },
+	{ 4, 0x88, "RxUnicastPkts" },
+	{ 4, 0x8c, "RxMulticastPkts" },
+	{ 4, 0x90, "RxBroadcastPkts" },
+	{ 4, 0x94, "RxSAChanges" },
+	{ 4, 0x98, "RxFragments" },
+	{ 4, 0xa0, "RxSymbolErrors" },
+	{ 4, 0xa4, "RxQoSPkts" },
+	{ 8, 0xa8, "RxQoSOctets" },
+	{ 4, 0xb0, "Pkts1523to2047Octets" },
+	{ 4, 0xb4, "Pkts2048to4095Octets" },
+	{ 4, 0xb8, "Pkts4096to8191Octets" },
+	{ 4, 0xbc, "Pkts8192to9728Octets" },
+	{ 4, 0xc0, "RxDiscarded" },
+};
+
+#define B53_MIBS_63XX_SIZE	ARRAY_SIZE(b53_mibs_63xx)
+
+/* MIB counters */
+static const struct b53_mib_desc b53_mibs[] = {
+	{ 8, 0x00, "TxOctets" },
+	{ 4, 0x08, "TxDropPkts" },
+	{ 4, 0x10, "TxBroadcastPkts" },
+	{ 4, 0x14, "TxMulticastPkts" },
+	{ 4, 0x18, "TxUnicastPkts" },
+	{ 4, 0x1c, "TxCollisions" },
+	{ 4, 0x20, "TxSingleCollision" },
+	{ 4, 0x24, "TxMultipleCollision" },
+	{ 4, 0x28, "TxDeferredTransmit" },
+	{ 4, 0x2c, "TxLateCollision" },
+	{ 4, 0x30, "TxExcessiveCollision" },
+	{ 4, 0x38, "TxPausePkts" },
+	{ 8, 0x50, "RxOctets" },
+	{ 4, 0x58, "RxUndersizePkts" },
+	{ 4, 0x5c, "RxPausePkts" },
+	{ 4, 0x60, "Pkts64Octets" },
+	{ 4, 0x64, "Pkts65to127Octets" },
+	{ 4, 0x68, "Pkts128to255Octets" },
+	{ 4, 0x6c, "Pkts256to511Octets" },
+	{ 4, 0x70, "Pkts512to1023Octets" },
+	{ 4, 0x74, "Pkts1024to1522Octets" },
+	{ 4, 0x78, "RxOversizePkts" },
+	{ 4, 0x7c, "RxJabbers" },
+	{ 4, 0x80, "RxAlignmentErrors" },
+	{ 4, 0x84, "RxFCSErrors" },
+	{ 8, 0x88, "RxGoodOctets" },
+	{ 4, 0x90, "RxDropPkts" },
+	{ 4, 0x94, "RxUnicastPkts" },
+	{ 4, 0x98, "RxMulticastPkts" },
+	{ 4, 0x9c, "RxBroadcastPkts" },
+	{ 4, 0xa0, "RxSAChanges" },
+	{ 4, 0xa4, "RxFragments" },
+	{ 4, 0xa8, "RxJumboPkts" },
+	{ 4, 0xac, "RxSymbolErrors" },
+	{ 4, 0xc0, "RxDiscarded" },
+};
+
+#define B53_MIBS_SIZE	ARRAY_SIZE(b53_mibs)
+
+static int b53_do_vlan_op(struct b53_device *dev, u8 op)
+{
+	unsigned int i;
+
+	b53_write8(dev, B53_ARLIO_PAGE, dev->vta_regs[0], VTA_START_CMD | op);
+
+	for (i = 0; i < 10; i++) {
+		u8 vta;
+
+		b53_read8(dev, B53_ARLIO_PAGE, dev->vta_regs[0], &vta);
+		if (!(vta & VTA_START_CMD))
+			return 0;
+
+		usleep_range(100, 200);
+	}
+
+	return -EIO;
+}
+
+static void b53_set_vlan_entry(struct b53_device *dev, u16 vid,
+			       struct b53_vlan *vlan)
+{
+	if (is5325(dev)) {
+		u32 entry = 0;
+
+		if (vlan->members) {
+			entry = ((vlan->untag & VA_UNTAG_MASK_25) <<
+				 VA_UNTAG_S_25) | vlan->members;
+			if (dev->core_rev >= 3)
+				entry |= VA_VALID_25_R4 | vid << VA_VID_HIGH_S;
+			else
+				entry |= VA_VALID_25;
+		}
+
+		b53_write32(dev, B53_VLAN_PAGE, B53_VLAN_WRITE_25, entry);
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, vid |
+			    VTA_RW_STATE_WR | VTA_RW_OP_EN);
+	} else if (is5365(dev)) {
+		u16 entry = 0;
+
+		if (vlan->members)
+			entry = ((vlan->untag & VA_UNTAG_MASK_65) <<
+				 VA_UNTAG_S_65) | vlan->members | VA_VALID_65;
+
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_WRITE_65, entry);
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_65, vid |
+			    VTA_RW_STATE_WR | VTA_RW_OP_EN);
+	} else {
+		b53_write16(dev, B53_ARLIO_PAGE, dev->vta_regs[1], vid);
+		b53_write32(dev, B53_ARLIO_PAGE, dev->vta_regs[2],
+			    (vlan->untag << VTE_UNTAG_S) | vlan->members);
+
+		b53_do_vlan_op(dev, VTA_CMD_WRITE);
+	}
+
+	dev_dbg(dev->ds->dev, "VID: %d, members: 0x%04x, untag: 0x%04x\n",
+		vid, vlan->members, vlan->untag);
+}
+
+static void b53_get_vlan_entry(struct b53_device *dev, u16 vid,
+			       struct b53_vlan *vlan)
+{
+	if (is5325(dev)) {
+		u32 entry = 0;
+
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, vid |
+			    VTA_RW_STATE_RD | VTA_RW_OP_EN);
+		b53_read32(dev, B53_VLAN_PAGE, B53_VLAN_WRITE_25, &entry);
+
+		if (dev->core_rev >= 3)
+			vlan->valid = !!(entry & VA_VALID_25_R4);
+		else
+			vlan->valid = !!(entry & VA_VALID_25);
+		vlan->members = entry & VA_MEMBER_MASK;
+		vlan->untag = (entry >> VA_UNTAG_S_25) & VA_UNTAG_MASK_25;
+
+	} else if (is5365(dev)) {
+		u16 entry = 0;
+
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_65, vid |
+			    VTA_RW_STATE_WR | VTA_RW_OP_EN);
+		b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_WRITE_65, &entry);
+
+		vlan->valid = !!(entry & VA_VALID_65);
+		vlan->members = entry & VA_MEMBER_MASK;
+		vlan->untag = (entry >> VA_UNTAG_S_65) & VA_UNTAG_MASK_65;
+	} else {
+		u32 entry = 0;
+
+		b53_write16(dev, B53_ARLIO_PAGE, dev->vta_regs[1], vid);
+		b53_do_vlan_op(dev, VTA_CMD_READ);
+		b53_read32(dev, B53_ARLIO_PAGE, dev->vta_regs[2], &entry);
+		vlan->members = entry & VTE_MEMBERS;
+		vlan->untag = (entry >> VTE_UNTAG_S) & VTE_MEMBERS;
+		vlan->valid = true;
+	}
+}
+
+static void b53_set_forwarding(struct b53_device *dev, int enable)
+{
+	u8 mgmt;
+
+	b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
+
+	if (enable)
+		mgmt |= SM_SW_FWD_EN;
+	else
+		mgmt &= ~SM_SW_FWD_EN;
+
+	b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt);
+}
+
+static void b53_enable_vlan(struct b53_device *dev, bool enable)
+{
+	u8 mgmt, vc0, vc1, vc4 = 0, vc5;
+
+	b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
+	b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL0, &vc0);
+	b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL1, &vc1);
+
+	if (is5325(dev) || is5365(dev)) {
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4_25, &vc4);
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5_25, &vc5);
+	} else if (is63xx(dev)) {
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4_63XX, &vc4);
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5_63XX, &vc5);
+	} else {
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4, &vc4);
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, &vc5);
+	}
+
+	mgmt &= ~SM_SW_FWD_MODE;
+
+	if (enable) {
+		vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID;
+		vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN;
+		vc4 &= ~VC4_ING_VID_CHECK_MASK;
+		vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S;
+		vc5 |= VC5_DROP_VTABLE_MISS;
+
+		if (is5325(dev))
+			vc0 &= ~VC0_RESERVED_1;
+
+		if (is5325(dev) || is5365(dev))
+			vc1 |= VC1_RX_MCST_TAG_EN;
+
+	} else {
+		vc0 &= ~(VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID);
+		vc1 &= ~(VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN);
+		vc4 &= ~VC4_ING_VID_CHECK_MASK;
+		vc5 &= ~VC5_DROP_VTABLE_MISS;
+
+		if (is5325(dev) || is5365(dev))
+			vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S;
+		else
+			vc4 |= VC4_ING_VID_VIO_TO_IMP << VC4_ING_VID_CHECK_S;
+
+		if (is5325(dev) || is5365(dev))
+			vc1 &= ~VC1_RX_MCST_TAG_EN;
+	}
+
+	if (!is5325(dev) && !is5365(dev))
+		vc5 &= ~VC5_VID_FFF_EN;
+
+	b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL0, vc0);
+	b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL1, vc1);
+
+	if (is5325(dev) || is5365(dev)) {
+		/* enable the high 8 bit vid check on 5325 */
+		if (is5325(dev) && enable)
+			b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL3,
+				   VC3_HIGH_8BIT_EN);
+		else
+			b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL3, 0);
+
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4_25, vc4);
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5_25, vc5);
+	} else if (is63xx(dev)) {
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_CTRL3_63XX, 0);
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4_63XX, vc4);
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5_63XX, vc5);
+	} else {
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_CTRL3, 0);
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4, vc4);
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, vc5);
+	}
+
+	b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt);
+}
+
+static int b53_set_jumbo(struct b53_device *dev, bool enable, bool allow_10_100)
+{
+	u32 port_mask = 0;
+	u16 max_size = JMS_MIN_SIZE;
+
+	if (is5325(dev) || is5365(dev))
+		return -EINVAL;
+
+	if (enable) {
+		port_mask = dev->enabled_ports;
+		max_size = JMS_MAX_SIZE;
+		if (allow_10_100)
+			port_mask |= JPM_10_100_JUMBO_EN;
+	}
+
+	b53_write32(dev, B53_JUMBO_PAGE, dev->jumbo_pm_reg, port_mask);
+	return b53_write16(dev, B53_JUMBO_PAGE, dev->jumbo_size_reg, max_size);
+}
+
+static int b53_flush_arl(struct b53_device *dev, u8 mask)
+{
+	unsigned int i;
+
+	b53_write8(dev, B53_CTRL_PAGE, B53_FAST_AGE_CTRL,
+		   FAST_AGE_DONE | FAST_AGE_DYNAMIC | mask);
+
+	for (i = 0; i < 10; i++) {
+		u8 fast_age_ctrl;
+
+		b53_read8(dev, B53_CTRL_PAGE, B53_FAST_AGE_CTRL,
+			  &fast_age_ctrl);
+
+		if (!(fast_age_ctrl & FAST_AGE_DONE))
+			goto out;
+
+		msleep(1);
+	}
+
+	return -ETIMEDOUT;
+out:
+	/* Only age dynamic entries (default behavior) */
+	b53_write8(dev, B53_CTRL_PAGE, B53_FAST_AGE_CTRL, FAST_AGE_DYNAMIC);
+	return 0;
+}
+
+static int b53_fast_age_port(struct b53_device *dev, int port)
+{
+	b53_write8(dev, B53_CTRL_PAGE, B53_FAST_AGE_PORT_CTRL, port);
+
+	return b53_flush_arl(dev, FAST_AGE_PORT);
+}
+
+static int b53_fast_age_vlan(struct b53_device *dev, u16 vid)
+{
+	b53_write16(dev, B53_CTRL_PAGE, B53_FAST_AGE_VID_CTRL, vid);
+
+	return b53_flush_arl(dev, FAST_AGE_VLAN);
+}
+
+static void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	unsigned int i;
+	u16 pvlan;
+
+	/* Enable the IMP port to be in the same VLAN as the other ports
+	 * on a per-port basis such that we only have Port i and IMP in
+	 * the same VLAN.
+	 */
+	b53_for_each_port(dev, i) {
+		b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), &pvlan);
+		pvlan |= BIT(cpu_port);
+		b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), pvlan);
+	}
+}
+
+static int b53_enable_port(struct dsa_switch *ds, int port,
+			   struct phy_device *phy)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	unsigned int cpu_port = dev->cpu_port;
+	u16 pvlan;
+
+	/* Clear the Rx and Tx disable bits and set to no spanning tree */
+	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), 0);
+
+	/* Set this port, and only this one to be in the default VLAN,
+	 * if member of a bridge, restore its membership prior to
+	 * bringing down this port.
+	 */
+	b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
+	pvlan &= ~0x1ff;
+	pvlan |= BIT(port);
+	pvlan |= dev->ports[port].vlan_ctl_mask;
+	b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan);
+
+	b53_imp_vlan_setup(ds, cpu_port);
+
+	return 0;
+}
+
+static void b53_disable_port(struct dsa_switch *ds, int port,
+			     struct phy_device *phy)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	u8 reg;
+
+	/* Disable Tx/Rx for the port */
+	b53_read8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), &reg);
+	reg |= PORT_CTRL_RX_DISABLE | PORT_CTRL_TX_DISABLE;
+	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), reg);
+}
+
+static void b53_enable_cpu_port(struct b53_device *dev)
+{
+	unsigned int cpu_port = dev->cpu_port;
+	u8 port_ctrl;
+
+	/* BCM5325 CPU port is at 8 */
+	if ((is5325(dev) || is5365(dev)) && cpu_port == B53_CPU_PORT_25)
+		cpu_port = B53_CPU_PORT;
+
+	port_ctrl = PORT_CTRL_RX_BCST_EN |
+		    PORT_CTRL_RX_MCST_EN |
+		    PORT_CTRL_RX_UCST_EN;
+	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(cpu_port), port_ctrl);
+}
+
+static void b53_enable_mib(struct b53_device *dev)
+{
+	u8 gc;
+
+	b53_read8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, &gc);
+	gc &= ~(GC_RESET_MIB | GC_MIB_AC_EN);
+	b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc);
+}
+
+static int b53_configure_vlan(struct b53_device *dev)
+{
+	struct b53_vlan vl = { 0 };
+	int i;
+
+	/* clear all vlan entries */
+	if (is5325(dev) || is5365(dev)) {
+		for (i = 1; i < dev->num_vlans; i++)
+			b53_set_vlan_entry(dev, i, &vl);
+	} else {
+		b53_do_vlan_op(dev, VTA_CMD_CLEAR);
+	}
+
+	b53_enable_vlan(dev, false);
+
+	b53_for_each_port(dev, i)
+		b53_write16(dev, B53_VLAN_PAGE,
+			    B53_VLAN_PORT_DEF_TAG(i), 1);
+
+	if (!is5325(dev) && !is5365(dev))
+		b53_set_jumbo(dev, dev->enable_jumbo, false);
+
+	return 0;
+}
+
+static void b53_switch_reset_gpio(struct b53_device *dev)
+{
+	int gpio = dev->reset_gpio;
+
+	if (gpio < 0)
+		return;
+
+	/* Reset sequence: RESET low(50ms)->high(20ms)
+	 */
+	gpio_set_value(gpio, 0);
+	mdelay(50);
+
+	gpio_set_value(gpio, 1);
+	mdelay(20);
+
+	dev->current_page = 0xff;
+}
+
+static int b53_switch_reset(struct b53_device *dev)
+{
+	u8 mgmt;
+
+	b53_switch_reset_gpio(dev);
+
+	if (is539x(dev)) {
+		b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, 0x83);
+		b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, 0x00);
+	}
+
+	b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
+
+	if (!(mgmt & SM_SW_FWD_EN)) {
+		mgmt &= ~SM_SW_FWD_MODE;
+		mgmt |= SM_SW_FWD_EN;
+
+		b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt);
+		b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
+
+		if (!(mgmt & SM_SW_FWD_EN)) {
+			dev_err(dev->dev, "Failed to enable switch!\n");
+			return -EINVAL;
+		}
+	}
+
+	b53_enable_mib(dev);
+
+	return b53_flush_arl(dev, FAST_AGE_STATIC);
+}
+
+static int b53_phy_read16(struct dsa_switch *ds, int addr, int reg)
+{
+	struct b53_device *priv = ds_to_priv(ds);
+	u16 value = 0;
+	int ret;
+
+	if (priv->ops->phy_read16)
+		ret = priv->ops->phy_read16(priv, addr, reg, &value);
+	else
+		ret = b53_read16(priv, B53_PORT_MII_PAGE(addr),
+				 reg * 2, &value);
+
+	return ret ? ret : value;
+}
+
+static int b53_phy_write16(struct dsa_switch *ds, int addr, int reg, u16 val)
+{
+	struct b53_device *priv = ds_to_priv(ds);
+
+	if (priv->ops->phy_write16)
+		return priv->ops->phy_write16(priv, addr, reg, val);
+
+	return b53_write16(priv, B53_PORT_MII_PAGE(addr), reg * 2, val);
+}
+
+static int b53_reset_switch(struct b53_device *priv)
+{
+	/* reset vlans */
+	priv->enable_jumbo = false;
+
+	memset(priv->vlans, 0, sizeof(*priv->vlans) * priv->num_vlans);
+	memset(priv->ports, 0, sizeof(*priv->ports) * priv->num_ports);
+
+	return b53_switch_reset(priv);
+}
+
+static int b53_apply_config(struct b53_device *priv)
+{
+	/* disable switching */
+	b53_set_forwarding(priv, 0);
+
+	b53_configure_vlan(priv);
+
+	/* enable switching */
+	b53_set_forwarding(priv, 1);
+
+	return 0;
+}
+
+static void b53_reset_mib(struct b53_device *priv)
+{
+	u8 gc;
+
+	b53_read8(priv, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, &gc);
+
+	b53_write8(priv, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc | GC_RESET_MIB);
+	msleep(1);
+	b53_write8(priv, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc & ~GC_RESET_MIB);
+	msleep(1);
+}
+
+static const struct b53_mib_desc *b53_get_mib(struct b53_device *dev)
+{
+	if (is5365(dev))
+		return b53_mibs_65;
+	else if (is63xx(dev))
+		return b53_mibs_63xx;
+	else
+		return b53_mibs;
+}
+
+static unsigned int b53_get_mib_size(struct b53_device *dev)
+{
+	if (is5365(dev))
+		return B53_MIBS_65_SIZE;
+	else if (is63xx(dev))
+		return B53_MIBS_63XX_SIZE;
+	else
+		return B53_MIBS_SIZE;
+}
+
+static void b53_get_strings(struct dsa_switch *ds, int port, uint8_t *data)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	const struct b53_mib_desc *mibs = b53_get_mib(dev);
+	unsigned int mib_size = b53_get_mib_size(dev);
+	unsigned int i;
+
+	for (i = 0; i < mib_size; i++)
+		memcpy(data + i * ETH_GSTRING_LEN,
+		       mibs[i].name, ETH_GSTRING_LEN);
+}
+
+static void b53_get_ethtool_stats(struct dsa_switch *ds, int port,
+				  uint64_t *data)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	const struct b53_mib_desc *mibs = b53_get_mib(dev);
+	unsigned int mib_size = b53_get_mib_size(dev);
+	const struct b53_mib_desc *s;
+	unsigned int i;
+	u64 val = 0;
+
+	if (is5365(dev) && port == 5)
+		port = 8;
+
+	mutex_lock(&dev->stats_mutex);
+
+	for (i = 0; i < mib_size; i++) {
+		s = &mibs[i];
+
+		if (s->size == 8) {
+			b53_read64(dev, B53_MIB_PAGE(port), s->offset, &val);
+		} else {
+			u32 val32;
+
+			b53_read32(dev, B53_MIB_PAGE(port), s->offset,
+				   &val32);
+			val = val32;
+		}
+		data[i] = (u64)val;
+	}
+
+	mutex_unlock(&dev->stats_mutex);
+}
+
+static int b53_get_sset_count(struct dsa_switch *ds)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+
+	return b53_get_mib_size(dev);
+}
+
+static int b53_set_addr(struct dsa_switch *ds, u8 *addr)
+{
+	return 0;
+}
+
+static int b53_setup(struct dsa_switch *ds)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	unsigned int port;
+	int ret;
+
+	ret = b53_reset_switch(dev);
+	if (ret) {
+		dev_err(ds->dev, "failed to reset switch\n");
+		return ret;
+	}
+
+	b53_reset_mib(dev);
+
+	ret = b53_apply_config(dev);
+	if (ret)
+		dev_err(ds->dev, "failed to apply configuration\n");
+
+	for (port = 0; port < dev->num_ports; port++) {
+		if (BIT(port) & ds->enabled_port_mask)
+			b53_enable_port(ds, port, NULL);
+		else if (dsa_is_cpu_port(ds, port))
+			b53_enable_cpu_port(dev);
+		else
+			b53_disable_port(ds, port, NULL);
+	}
+
+	return ret;
+}
+
+static void b53_adjust_link(struct dsa_switch *ds, int port,
+			    struct phy_device *phydev)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	u8 rgmii_ctrl = 0, reg = 0, off;
+
+	if (!phy_is_pseudo_fixed_link(phydev))
+		return;
+
+	/* Override the port settings */
+	if (port == dev->cpu_port) {
+		off = B53_PORT_OVERRIDE_CTRL;
+		reg = PORT_OVERRIDE_EN;
+	} else {
+		off = B53_GMII_PORT_OVERRIDE_CTRL(port);
+		reg = GMII_PO_EN;
+	}
+
+	/* Set the link UP */
+	if (phydev->link)
+		reg |= PORT_OVERRIDE_LINK;
+
+	if (phydev->duplex == DUPLEX_FULL)
+		reg |= PORT_OVERRIDE_FULL_DUPLEX;
+
+	switch (phydev->speed) {
+	case 2000:
+		reg |= PORT_OVERRIDE_SPEED_2000M;
+		/* fallthrough */
+	case SPEED_1000:
+		reg |= PORT_OVERRIDE_SPEED_1000M;
+		break;
+	case SPEED_100:
+		reg |= PORT_OVERRIDE_SPEED_100M;
+		break;
+	case SPEED_10:
+		reg |= PORT_OVERRIDE_SPEED_10M;
+		break;
+	default:
+		dev_err(ds->dev, "unknown speed: %d\n", phydev->speed);
+		return;
+	}
+
+	/* Enable flow control on BCM5301x's CPU port */
+	if (is5301x(dev) && port == dev->cpu_port)
+		reg |= PORT_OVERRIDE_RX_FLOW | PORT_OVERRIDE_TX_FLOW;
+
+	if (phydev->pause) {
+		if (phydev->asym_pause)
+			reg |= PORT_OVERRIDE_TX_FLOW;
+		reg |= PORT_OVERRIDE_RX_FLOW;
+	}
+
+	b53_write8(dev, B53_CTRL_PAGE, off, reg);
+
+	if (is531x5(dev) && phy_interface_is_rgmii(phydev)) {
+		if (port == 8)
+			off = B53_RGMII_CTRL_IMP;
+		else
+			off = B53_RGMII_CTRL_P(port);
+
+		/* Configure the port RGMII clock delay by DLL disabled and
+		 * tx_clk aligned timing (restoring to reset defaults)
+		 */
+		b53_read8(dev, B53_CTRL_PAGE, off, &rgmii_ctrl);
+		rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC |
+				RGMII_CTRL_TIMING_SEL);
+
+		/* PHY_INTERFACE_MODE_RGMII_TXID means TX internal delay, make
+		 * sure that we enable the port TX clock internal delay to
+		 * account for this internal delay that is inserted, otherwise
+		 * the switch won't be able to receive correctly.
+		 *
+		 * PHY_INTERFACE_MODE_RGMII means that we are not introducing
+		 * any delay neither on transmission nor reception, so the
+		 * BCM53125 must also be configured accordingly to account for
+		 * the lack of delay and introduce
+		 *
+		 * The BCM53125 switch has its RX clock and TX clock control
+		 * swapped, hence the reason why we modify the TX clock path in
+		 * the "RGMII" case
+		 */
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
+			rgmii_ctrl |= RGMII_CTRL_DLL_TXC;
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
+			rgmii_ctrl |= RGMII_CTRL_DLL_TXC | RGMII_CTRL_DLL_RXC;
+		rgmii_ctrl |= RGMII_CTRL_TIMING_SEL;
+		b53_write8(dev, B53_CTRL_PAGE, off, rgmii_ctrl);
+
+		dev_info(ds->dev, "Configured port %d for %s\n", port,
+			 phy_modes(phydev->interface));
+	}
+
+	/* configure MII port if necessary */
+	if (is5325(dev)) {
+		b53_read8(dev, B53_CTRL_PAGE, B53_PORT_OVERRIDE_CTRL,
+			  &reg);
+
+		/* reverse mii needs to be enabled */
+		if (!(reg & PORT_OVERRIDE_RV_MII_25)) {
+			b53_write8(dev, B53_CTRL_PAGE, B53_PORT_OVERRIDE_CTRL,
+				   reg | PORT_OVERRIDE_RV_MII_25);
+			b53_read8(dev, B53_CTRL_PAGE, B53_PORT_OVERRIDE_CTRL,
+				  &reg);
+
+			if (!(reg & PORT_OVERRIDE_RV_MII_25)) {
+				dev_err(ds->dev,
+					"Failed to enable reverse MII mode\n");
+				return;
+			}
+		}
+	} else if (is5301x(dev)) {
+		if (port != dev->cpu_port) {
+			u8 po_reg = B53_GMII_PORT_OVERRIDE_CTRL(dev->cpu_port);
+			u8 gmii_po;
+
+			b53_read8(dev, B53_CTRL_PAGE, po_reg, &gmii_po);
+			gmii_po |= GMII_PO_LINK |
+				   GMII_PO_RX_FLOW |
+				   GMII_PO_TX_FLOW |
+				   GMII_PO_EN |
+				   GMII_PO_SPEED_2000M;
+			b53_write8(dev, B53_CTRL_PAGE, po_reg, gmii_po);
+		}
+	}
+}
+
+static int b53_vlan_filtering(struct dsa_switch *ds, int port,
+			      bool vlan_filtering)
+{
+	return 0;
+}
+
+static int b53_vlan_prepare(struct dsa_switch *ds, int port,
+			    const struct switchdev_obj_port_vlan *vlan,
+			    struct switchdev_trans *trans)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+
+	if ((is5325(dev) || is5365(dev)) && vlan->vid_begin == 0)
+		return -EOPNOTSUPP;
+
+	if (vlan->vid_end > dev->num_vlans)
+		return -ERANGE;
+
+	b53_enable_vlan(dev, true);
+
+	return 0;
+}
+
+static void b53_vlan_add(struct dsa_switch *ds, int port,
+			 const struct switchdev_obj_port_vlan *vlan,
+			 struct switchdev_trans *trans)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+	unsigned int cpu_port = dev->cpu_port;
+	struct b53_vlan *vl;
+	u16 vid;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &dev->vlans[vid];
+
+		b53_get_vlan_entry(dev, vid, vl);
+
+		vl->members |= BIT(port) | BIT(cpu_port);
+		if (untagged)
+			vl->untag |= BIT(port) | BIT(cpu_port);
+		else
+			vl->untag &= ~(BIT(port) | BIT(cpu_port));
+
+		b53_set_vlan_entry(dev, vid, vl);
+		b53_fast_age_vlan(dev, vid);
+	}
+
+	if (pvid) {
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port),
+			    vlan->vid_end);
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port),
+			    vlan->vid_end);
+		b53_fast_age_vlan(dev, vid);
+	}
+}
+
+static int b53_vlan_del(struct dsa_switch *ds, int port,
+			const struct switchdev_obj_port_vlan *vlan)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	unsigned int cpu_port = dev->cpu_port;
+	struct b53_vlan *vl;
+	u16 vid;
+	u16 pvid;
+
+	b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid);
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &dev->vlans[vid];
+
+		b53_get_vlan_entry(dev, vid, vl);
+
+		vl->members &= ~BIT(port);
+		if ((vl->members & BIT(cpu_port)) == BIT(cpu_port))
+			vl->members = 0;
+
+		if (pvid == vid) {
+			if (is5325(dev) || is5365(dev))
+				pvid = 1;
+			else
+				pvid = 0;
+		}
+
+		if (untagged) {
+			vl->untag &= ~(BIT(port));
+			if ((vl->untag & BIT(cpu_port)) == BIT(cpu_port))
+				vl->untag = 0;
+		}
+
+		b53_set_vlan_entry(dev, vid, vl);
+		b53_fast_age_vlan(dev, vid);
+	}
+
+	b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), pvid);
+	b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port), pvid);
+	b53_fast_age_vlan(dev, pvid);
+
+	return 0;
+}
+
+static int b53_vlan_dump(struct dsa_switch *ds, int port,
+			 struct switchdev_obj_port_vlan *vlan,
+			 int (*cb)(struct switchdev_obj *obj))
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	u16 vid, vid_start = 0, pvid;
+	struct b53_vlan *vl;
+	int err = 0;
+
+	if (is5325(dev) || is5365(dev))
+		vid_start = 1;
+
+	b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid);
+
+	/* Use our software cache for dumps, since we do not have any HW
+	 * operation returning only the used/valid VLANs
+	 */
+	for (vid = vid_start; vid < dev->num_vlans; vid++) {
+		vl = &dev->vlans[vid];
+
+		if (!vl->valid)
+			continue;
+
+		if (!(vl->members & BIT(port)))
+			continue;
+
+		vlan->vid_begin = vlan->vid_end = vid;
+		vlan->flags = 0;
+
+		if (vl->untag & BIT(port))
+			vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+		if (pvid == vid)
+			vlan->flags |= BRIDGE_VLAN_INFO_PVID;
+
+		err = cb(&vlan->obj);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+/* Address Resolution Logic routines */
+static int b53_arl_op_wait(struct b53_device *dev)
+{
+	unsigned int timeout = 10;
+	u8 reg;
+
+	do {
+		b53_read8(dev, B53_ARLIO_PAGE, B53_ARLTBL_RW_CTRL, &reg);
+		if (!(reg & ARLTBL_START_DONE))
+			return 0;
+
+		usleep_range(1000, 2000);
+	} while (timeout--);
+
+	dev_warn(dev->dev, "timeout waiting for ARL to finish: 0x%02x\n", reg);
+
+	return -ETIMEDOUT;
+}
+
+static int b53_arl_rw_op(struct b53_device *dev, unsigned int op)
+{
+	u8 reg;
+
+	if (op > ARLTBL_RW)
+		return -EINVAL;
+
+	b53_read8(dev, B53_ARLIO_PAGE, B53_ARLTBL_RW_CTRL, &reg);
+	reg |= ARLTBL_START_DONE;
+	if (op)
+		reg |= ARLTBL_RW;
+	else
+		reg &= ~ARLTBL_RW;
+	b53_write8(dev, B53_ARLIO_PAGE, B53_ARLTBL_RW_CTRL, reg);
+
+	return b53_arl_op_wait(dev);
+}
+
+static int b53_arl_read(struct b53_device *dev, u64 mac,
+			u16 vid, struct b53_arl_entry *ent, u8 *idx,
+			bool is_valid)
+{
+	unsigned int i;
+	int ret;
+
+	ret = b53_arl_op_wait(dev);
+	if (ret)
+		return ret;
+
+	/* Read the bins */
+	for (i = 0; i < dev->num_arl_entries; i++) {
+		u64 mac_vid;
+		u32 fwd_entry;
+
+		b53_read64(dev, B53_ARLIO_PAGE,
+			   B53_ARLTBL_MAC_VID_ENTRY(i), &mac_vid);
+		b53_read32(dev, B53_ARLIO_PAGE,
+			   B53_ARLTBL_DATA_ENTRY(i), &fwd_entry);
+		b53_arl_to_entry(ent, mac_vid, fwd_entry);
+
+		if (!(fwd_entry & ARLTBL_VALID))
+			continue;
+		if ((mac_vid & ARLTBL_MAC_MASK) != mac)
+			continue;
+		*idx = i;
+	}
+
+	return -ENOENT;
+}
+
+static int b53_arl_op(struct b53_device *dev, int op, int port,
+		      const unsigned char *addr, u16 vid, bool is_valid)
+{
+	struct b53_arl_entry ent;
+	u32 fwd_entry;
+	u64 mac, mac_vid = 0;
+	u8 idx = 0;
+	int ret;
+
+	/* Convert the array into a 64-bit MAC */
+	mac = b53_mac_to_u64(addr);
+
+	/* Perform a read for the given MAC and VID */
+	b53_write48(dev, B53_ARLIO_PAGE, B53_MAC_ADDR_IDX, mac);
+	b53_write16(dev, B53_ARLIO_PAGE, B53_VLAN_ID_IDX, vid);
+
+	/* Issue a read operation for this MAC */
+	ret = b53_arl_rw_op(dev, 1);
+	if (ret)
+		return ret;
+
+	ret = b53_arl_read(dev, mac, vid, &ent, &idx, is_valid);
+	/* If this is a read, just finish now */
+	if (op)
+		return ret;
+
+	/* We could not find a matching MAC, so reset to a new entry */
+	if (ret) {
+		fwd_entry = 0;
+		idx = 1;
+	}
+
+	memset(&ent, 0, sizeof(ent));
+	ent.port = port;
+	ent.is_valid = is_valid;
+	ent.vid = vid;
+	ent.is_static = true;
+	memcpy(ent.mac, addr, ETH_ALEN);
+	b53_arl_from_entry(&mac_vid, &fwd_entry, &ent);
+
+	b53_write64(dev, B53_ARLIO_PAGE,
+		    B53_ARLTBL_MAC_VID_ENTRY(idx), mac_vid);
+	b53_write32(dev, B53_ARLIO_PAGE,
+		    B53_ARLTBL_DATA_ENTRY(idx), fwd_entry);
+
+	return b53_arl_rw_op(dev, 0);
+}
+
+static int b53_fdb_prepare(struct dsa_switch *ds, int port,
+			   const struct switchdev_obj_port_fdb *fdb,
+			   struct switchdev_trans *trans)
+{
+	struct b53_device *priv = ds_to_priv(ds);
+
+	/* 5325 and 5365 require some more massaging, but could
+	 * be supported eventually
+	 */
+	if (is5325(priv) || is5365(priv))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static void b53_fdb_add(struct dsa_switch *ds, int port,
+			const struct switchdev_obj_port_fdb *fdb,
+			struct switchdev_trans *trans)
+{
+	struct b53_device *priv = ds_to_priv(ds);
+
+	if (b53_arl_op(priv, 0, port, fdb->addr, fdb->vid, true))
+		pr_err("%s: failed to add MAC address\n", __func__);
+}
+
+static int b53_fdb_del(struct dsa_switch *ds, int port,
+		       const struct switchdev_obj_port_fdb *fdb)
+{
+	struct b53_device *priv = ds_to_priv(ds);
+
+	return b53_arl_op(priv, 0, port, fdb->addr, fdb->vid, false);
+}
+
+static int b53_arl_search_wait(struct b53_device *dev)
+{
+	unsigned int timeout = 1000;
+	u8 reg;
+
+	do {
+		b53_read8(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_CTL, &reg);
+		if (!(reg & ARL_SRCH_STDN))
+			return 0;
+
+		if (reg & ARL_SRCH_VLID)
+			return 0;
+
+		usleep_range(1000, 2000);
+	} while (timeout--);
+
+	return -ETIMEDOUT;
+}
+
+static void b53_arl_search_rd(struct b53_device *dev, u8 idx,
+			      struct b53_arl_entry *ent)
+{
+	u64 mac_vid;
+	u32 fwd_entry;
+
+	b53_read64(dev, B53_ARLIO_PAGE,
+		   B53_ARL_SRCH_RSTL_MACVID(idx), &mac_vid);
+	b53_read32(dev, B53_ARLIO_PAGE,
+		   B53_ARL_SRCH_RSTL(idx), &fwd_entry);
+	b53_arl_to_entry(ent, mac_vid, fwd_entry);
+}
+
+static int b53_fdb_copy(struct net_device *dev, int port,
+			const struct b53_arl_entry *ent,
+			struct switchdev_obj_port_fdb *fdb,
+			int (*cb)(struct switchdev_obj *obj))
+{
+	if (!ent->is_valid)
+		return 0;
+
+	if (port != ent->port)
+		return 0;
+
+	ether_addr_copy(fdb->addr, ent->mac);
+	fdb->vid = ent->vid;
+	fdb->ndm_state = ent->is_static ? NUD_NOARP : NUD_REACHABLE;
+
+	return cb(&fdb->obj);
+}
+
+static int b53_fdb_dump(struct dsa_switch *ds, int port,
+			struct switchdev_obj_port_fdb *fdb,
+			int (*cb)(struct switchdev_obj *obj))
+{
+	struct b53_device *priv = ds_to_priv(ds);
+	struct net_device *dev = ds->ports[port].netdev;
+	struct b53_arl_entry results[2];
+	unsigned int count = 0;
+	int ret;
+	u8 reg;
+
+	/* Start search operation */
+	reg = ARL_SRCH_STDN;
+	b53_write8(priv, B53_ARLIO_PAGE, B53_ARL_SRCH_CTL, reg);
+
+	do {
+		ret = b53_arl_search_wait(priv);
+		if (ret)
+			return ret;
+
+		b53_arl_search_rd(priv, 0, &results[0]);
+		ret = b53_fdb_copy(dev, port, &results[0], fdb, cb);
+		if (ret)
+			return ret;
+
+		if (priv->num_arl_entries > 2) {
+			b53_arl_search_rd(priv, 1, &results[1]);
+			ret = b53_fdb_copy(dev, port, &results[1], fdb, cb);
+			if (ret)
+				return ret;
+
+			if (!results[0].is_valid && !results[1].is_valid)
+				break;
+		}
+
+	} while (count++ < 1024);
+
+	return 0;
+}
+
+static int b53_br_join(struct dsa_switch *ds, int port,
+		       struct net_device *bridge)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	u16 pvlan, reg;
+	unsigned int i;
+
+	dev->ports[port].bridge_dev = bridge;
+	b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
+
+	b53_for_each_port(dev, i) {
+		if (dev->ports[i].bridge_dev != bridge)
+			continue;
+
+		/* Add this local port to the remote port VLAN control
+		 * membership and update the remote port bitmask
+		 */
+		b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), &reg);
+		reg |= BIT(port);
+		b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), reg);
+		dev->ports[i].vlan_ctl_mask = reg;
+
+		pvlan |= BIT(i);
+	}
+
+	/* Configure the local port VLAN control membership to include
+	 * remote ports and update the local port bitmask
+	 */
+	b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan);
+	dev->ports[port].vlan_ctl_mask = pvlan;
+
+	return 0;
+}
+
+static void b53_br_leave(struct dsa_switch *ds, int port)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	struct net_device *bridge = dev->ports[port].bridge_dev;
+	struct b53_vlan *vl = &dev->vlans[0];
+	unsigned int i;
+	u16 pvlan, reg, pvid;
+
+	b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
+
+	b53_for_each_port(dev, i) {
+		/* Don't touch the remaining ports */
+		if (dev->ports[i].bridge_dev != bridge)
+			continue;
+
+		b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), &reg);
+		reg &= ~BIT(port);
+		b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), reg);
+		dev->ports[port].vlan_ctl_mask = reg;
+
+		/* Prevent self removal to preserve isolation */
+		if (port != i)
+			pvlan &= ~BIT(i);
+	}
+
+	b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan);
+	dev->ports[port].vlan_ctl_mask = pvlan;
+	dev->ports[port].bridge_dev = NULL;
+
+	if (is5325(dev) || is5365(dev))
+		pvid = 1;
+	else
+		pvid = 0;
+
+	b53_get_vlan_entry(dev, pvid, vl);
+	vl->members |= BIT(port) | BIT(dev->cpu_port);
+	vl->untag |= BIT(port) | BIT(dev->cpu_port);
+	b53_set_vlan_entry(dev, pvid, vl);
+}
+
+static void b53_br_set_stp_state(struct dsa_switch *ds, int port,
+				 u8 state)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	u8 hw_state, cur_hw_state;
+	u8 reg;
+
+	b53_read8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), &reg);
+	cur_hw_state = reg & PORT_CTRL_STP_STATE_MASK;
+
+	switch (state) {
+	case BR_STATE_DISABLED:
+		hw_state = PORT_CTRL_DIS_STATE;
+		break;
+	case BR_STATE_LISTENING:
+		hw_state = PORT_CTRL_LISTEN_STATE;
+		break;
+	case BR_STATE_LEARNING:
+		hw_state = PORT_CTRL_LEARN_STATE;
+		break;
+	case BR_STATE_FORWARDING:
+		hw_state = PORT_CTRL_FWD_STATE;
+		break;
+	case BR_STATE_BLOCKING:
+		hw_state = PORT_CTRL_BLOCK_STATE;
+		break;
+	default:
+		dev_err(ds->dev, "invalid STP state: %d\n", state);
+		return;
+	}
+
+	/* Fast-age ARL entries if we are moving a port from Learning or
+	 * Forwarding (cur_hw_state) state to Disabled, Blocking or Listening
+	 * state (hw_state)
+	 */
+	if (cur_hw_state != hw_state) {
+		if (cur_hw_state >= PORT_CTRL_LEARN_STATE &&
+		    hw_state <= PORT_CTRL_LISTEN_STATE) {
+			if (b53_fast_age_port(dev, port)) {
+				dev_err(ds->dev, "fast ageing failed\n");
+				return;
+			}
+		}
+	}
+
+	b53_read8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), &reg);
+	reg &= ~PORT_CTRL_STP_STATE_MASK;
+	reg |= hw_state;
+	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), reg);
+}
+
+static struct dsa_switch_driver b53_switch_ops = {
+	.tag_protocol		= DSA_TAG_PROTO_NONE,
+	.setup			= b53_setup,
+	.set_addr		= b53_set_addr,
+	.get_strings		= b53_get_strings,
+	.get_ethtool_stats	= b53_get_ethtool_stats,
+	.get_sset_count		= b53_get_sset_count,
+	.phy_read		= b53_phy_read16,
+	.phy_write		= b53_phy_write16,
+	.adjust_link		= b53_adjust_link,
+	.port_enable		= b53_enable_port,
+	.port_disable		= b53_disable_port,
+	.port_bridge_join	= b53_br_join,
+	.port_bridge_leave	= b53_br_leave,
+	.port_stp_state_set	= b53_br_set_stp_state,
+	.port_vlan_filtering	= b53_vlan_filtering,
+	.port_vlan_prepare	= b53_vlan_prepare,
+	.port_vlan_add		= b53_vlan_add,
+	.port_vlan_del		= b53_vlan_del,
+	.port_vlan_dump		= b53_vlan_dump,
+	.port_fdb_prepare	= b53_fdb_prepare,
+	.port_fdb_dump		= b53_fdb_dump,
+	.port_fdb_add		= b53_fdb_add,
+	.port_fdb_del		= b53_fdb_del,
+};
+
+struct b53_chip_data {
+	u32 chip_id;
+	const char *dev_name;
+	u16 vlans;
+	u16 enabled_ports;
+	u8 cpu_port;
+	u8 vta_regs[3];
+	u8 arl_entries;
+	u8 duplex_reg;
+	u8 jumbo_pm_reg;
+	u8 jumbo_size_reg;
+};
+
+#define B53_VTA_REGS	\
+	{ B53_VT_ACCESS, B53_VT_INDEX, B53_VT_ENTRY }
+#define B53_VTA_REGS_9798 \
+	{ B53_VT_ACCESS_9798, B53_VT_INDEX_9798, B53_VT_ENTRY_9798 }
+#define B53_VTA_REGS_63XX \
+	{ B53_VT_ACCESS_63XX, B53_VT_INDEX_63XX, B53_VT_ENTRY_63XX }
+
+static const struct b53_chip_data b53_switch_chips[] = {
+	{
+		.chip_id = BCM5325_DEVICE_ID,
+		.dev_name = "BCM5325",
+		.vlans = 16,
+		.enabled_ports = 0x1f,
+		.arl_entries = 2,
+		.cpu_port = B53_CPU_PORT_25,
+		.duplex_reg = B53_DUPLEX_STAT_FE,
+	},
+	{
+		.chip_id = BCM5365_DEVICE_ID,
+		.dev_name = "BCM5365",
+		.vlans = 256,
+		.enabled_ports = 0x1f,
+		.arl_entries = 2,
+		.cpu_port = B53_CPU_PORT_25,
+		.duplex_reg = B53_DUPLEX_STAT_FE,
+	},
+	{
+		.chip_id = BCM5395_DEVICE_ID,
+		.dev_name = "BCM5395",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM5397_DEVICE_ID,
+		.dev_name = "BCM5397",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS_9798,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM5398_DEVICE_ID,
+		.dev_name = "BCM5398",
+		.vlans = 4096,
+		.enabled_ports = 0x7f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS_9798,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53115_DEVICE_ID,
+		.dev_name = "BCM53115",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.vta_regs = B53_VTA_REGS,
+		.cpu_port = B53_CPU_PORT,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53125_DEVICE_ID,
+		.dev_name = "BCM53125",
+		.vlans = 4096,
+		.enabled_ports = 0xff,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53128_DEVICE_ID,
+		.dev_name = "BCM53128",
+		.vlans = 4096,
+		.enabled_ports = 0x1ff,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM63XX_DEVICE_ID,
+		.dev_name = "BCM63xx",
+		.vlans = 4096,
+		.enabled_ports = 0, /* pdata must provide them */
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS_63XX,
+		.duplex_reg = B53_DUPLEX_STAT_63XX,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK_63XX,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE_63XX,
+	},
+	{
+		.chip_id = BCM53010_DEVICE_ID,
+		.dev_name = "BCM53010",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53011_DEVICE_ID,
+		.dev_name = "BCM53011",
+		.vlans = 4096,
+		.enabled_ports = 0x1bf,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53012_DEVICE_ID,
+		.dev_name = "BCM53012",
+		.vlans = 4096,
+		.enabled_ports = 0x1bf,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53018_DEVICE_ID,
+		.dev_name = "BCM53018",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53019_DEVICE_ID,
+		.dev_name = "BCM53019",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+};
+
+static int b53_switch_init(struct b53_device *dev)
+{
+	struct dsa_switch *ds = dev->ds;
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(b53_switch_chips); i++) {
+		const struct b53_chip_data *chip = &b53_switch_chips[i];
+
+		if (chip->chip_id == dev->chip_id) {
+			if (!dev->enabled_ports)
+				dev->enabled_ports = chip->enabled_ports;
+			dev->name = chip->dev_name;
+			dev->duplex_reg = chip->duplex_reg;
+			dev->vta_regs[0] = chip->vta_regs[0];
+			dev->vta_regs[1] = chip->vta_regs[1];
+			dev->vta_regs[2] = chip->vta_regs[2];
+			dev->jumbo_pm_reg = chip->jumbo_pm_reg;
+			ds->drv = &b53_switch_ops;
+			dev->cpu_port = chip->cpu_port;
+			dev->num_vlans = chip->vlans;
+			dev->num_arl_entries = chip->arl_entries;
+			break;
+		}
+	}
+
+	/* check which BCM5325x version we have */
+	if (is5325(dev)) {
+		u8 vc4;
+
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4_25, &vc4);
+
+		/* check reserved bits */
+		switch (vc4 & 3) {
+		case 1:
+			/* BCM5325E */
+			break;
+		case 3:
+			/* BCM5325F - do not use port 4 */
+			dev->enabled_ports &= ~BIT(4);
+			break;
+		default:
+/* On the BCM47XX SoCs this is the supported internal switch.*/
+#ifndef CONFIG_BCM47XX
+			/* BCM5325M */
+			return -EINVAL;
+#else
+			break;
+#endif
+		}
+	} else if (dev->chip_id == BCM53115_DEVICE_ID) {
+		u64 strap_value;
+
+		b53_read48(dev, B53_STAT_PAGE, B53_STRAP_VALUE, &strap_value);
+		/* use second IMP port if GMII is enabled */
+		if (strap_value & SV_GMII_CTRL_115)
+			dev->cpu_port = 5;
+	}
+
+	/* cpu port is always last */
+	dev->num_ports = dev->cpu_port + 1;
+	dev->enabled_ports |= BIT(dev->cpu_port);
+
+	dev->ports = devm_kzalloc(dev->dev,
+				  sizeof(struct b53_port) * dev->num_ports,
+				  GFP_KERNEL);
+	if (!dev->ports)
+		return -ENOMEM;
+
+	dev->vlans = devm_kzalloc(dev->dev,
+				  sizeof(struct b53_vlan) * dev->num_vlans,
+				  GFP_KERNEL);
+	if (!dev->vlans)
+		return -ENOMEM;
+
+	dev->reset_gpio = b53_switch_get_reset_gpio(dev);
+	if (dev->reset_gpio >= 0) {
+		ret = devm_gpio_request_one(dev->dev, dev->reset_gpio,
+					    GPIOF_OUT_INIT_HIGH, "robo_reset");
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+struct b53_device *b53_switch_alloc(struct device *base, struct b53_io_ops *ops,
+				    void *priv)
+{
+	struct dsa_switch *ds;
+	struct b53_device *dev;
+
+	ds = devm_kzalloc(base, sizeof(*ds) + sizeof(*dev), GFP_KERNEL);
+	if (!ds)
+		return NULL;
+
+	dev = (struct b53_device *)(ds + 1);
+
+	ds->priv = dev;
+	ds->dev = base;
+	dev->dev = base;
+
+	dev->ds = ds;
+	dev->priv = priv;
+	dev->ops = ops;
+	mutex_init(&dev->reg_mutex);
+	mutex_init(&dev->stats_mutex);
+
+	return dev;
+}
+EXPORT_SYMBOL(b53_switch_alloc);
+
+int b53_switch_detect(struct b53_device *dev)
+{
+	u32 id32;
+	u16 tmp;
+	u8 id8;
+	int ret;
+
+	ret = b53_read8(dev, B53_MGMT_PAGE, B53_DEVICE_ID, &id8);
+	if (ret)
+		return ret;
+
+	switch (id8) {
+	case 0:
+		/* BCM5325 and BCM5365 do not have this register so reads
+		 * return 0. But the read operation did succeed, so assume this
+		 * is one of them.
+		 *
+		 * Next check if we can write to the 5325's VTA register; for
+		 * 5365 it is read only.
+		 */
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, 0xf);
+		b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, &tmp);
+
+		if (tmp == 0xf)
+			dev->chip_id = BCM5325_DEVICE_ID;
+		else
+			dev->chip_id = BCM5365_DEVICE_ID;
+		break;
+	case BCM5395_DEVICE_ID:
+	case BCM5397_DEVICE_ID:
+	case BCM5398_DEVICE_ID:
+		dev->chip_id = id8;
+		break;
+	default:
+		ret = b53_read32(dev, B53_MGMT_PAGE, B53_DEVICE_ID, &id32);
+		if (ret)
+			return ret;
+
+		switch (id32) {
+		case BCM53115_DEVICE_ID:
+		case BCM53125_DEVICE_ID:
+		case BCM53128_DEVICE_ID:
+		case BCM53010_DEVICE_ID:
+		case BCM53011_DEVICE_ID:
+		case BCM53012_DEVICE_ID:
+		case BCM53018_DEVICE_ID:
+		case BCM53019_DEVICE_ID:
+			dev->chip_id = id32;
+			break;
+		default:
+			pr_err("unsupported switch detected (BCM53%02x/BCM%x)\n",
+			       id8, id32);
+			return -ENODEV;
+		}
+	}
+
+	if (dev->chip_id == BCM5325_DEVICE_ID)
+		return b53_read8(dev, B53_STAT_PAGE, B53_REV_ID_25,
+				 &dev->core_rev);
+	else
+		return b53_read8(dev, B53_MGMT_PAGE, B53_REV_ID,
+				 &dev->core_rev);
+}
+EXPORT_SYMBOL(b53_switch_detect);
+
+int b53_switch_register(struct b53_device *dev)
+{
+	int ret;
+
+	if (dev->pdata) {
+		dev->chip_id = dev->pdata->chip_id;
+		dev->enabled_ports = dev->pdata->enabled_ports;
+	}
+
+	if (!dev->chip_id && b53_switch_detect(dev))
+		return -EINVAL;
+
+	ret = b53_switch_init(dev);
+	if (ret)
+		return ret;
+
+	pr_info("found switch: %s, rev %i\n", dev->name, dev->core_rev);
+
+	return dsa_register_switch(dev->ds, dev->ds->dev->of_node);
+}
+EXPORT_SYMBOL(b53_switch_register);
+
+MODULE_AUTHOR("Jonas Gorski <[email protected]>");
+MODULE_DESCRIPTION("B53 switch library");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c
new file mode 100644
index 000000000000..aa87c3fffdac
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_mdio.c
@@ -0,0 +1,392 @@
+/*
+ * B53 register access through MII registers
+ *
+ * Copyright (C) 2011-2013 Jonas Gorski <[email protected]>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/phy.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/brcmphy.h>
+#include <linux/rtnetlink.h>
+#include <net/dsa.h>
+
+#include "b53_priv.h"
+
+/* MII registers */
+#define REG_MII_PAGE    0x10    /* MII Page register */
+#define REG_MII_ADDR    0x11    /* MII Address register */
+#define REG_MII_DATA0   0x18    /* MII Data register 0 */
+#define REG_MII_DATA1   0x19    /* MII Data register 1 */
+#define REG_MII_DATA2   0x1a    /* MII Data register 2 */
+#define REG_MII_DATA3   0x1b    /* MII Data register 3 */
+
+#define REG_MII_PAGE_ENABLE     BIT(0)
+#define REG_MII_ADDR_WRITE      BIT(0)
+#define REG_MII_ADDR_READ       BIT(1)
+
+static int b53_mdio_op(struct b53_device *dev, u8 page, u8 reg, u16 op)
+{
+	int i;
+	u16 v;
+	int ret;
+	struct mii_bus *bus = dev->priv;
+
+	if (dev->current_page != page) {
+		/* set page number */
+		v = (page << 8) | REG_MII_PAGE_ENABLE;
+		ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					   REG_MII_PAGE, v);
+		if (ret)
+			return ret;
+		dev->current_page = page;
+	}
+
+	/* set register address */
+	v = (reg << 8) | op;
+	ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR, REG_MII_ADDR, v);
+	if (ret)
+		return ret;
+
+	/* check if operation completed */
+	for (i = 0; i < 5; ++i) {
+		v = mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					REG_MII_ADDR);
+		if (!(v & (REG_MII_ADDR_WRITE | REG_MII_ADDR_READ)))
+			break;
+		usleep_range(10, 100);
+	}
+
+	if (WARN_ON(i == 5))
+		return -EIO;
+
+	return 0;
+}
+
+static int b53_mdio_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
+{
+	struct mii_bus *bus = dev->priv;
+	int ret;
+
+	ret = b53_mdio_op(dev, page, reg, REG_MII_ADDR_READ);
+	if (ret)
+		return ret;
+
+	*val = mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+				   REG_MII_DATA0) & 0xff;
+
+	return 0;
+}
+
+static int b53_mdio_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
+{
+	struct mii_bus *bus = dev->priv;
+	int ret;
+
+	ret = b53_mdio_op(dev, page, reg, REG_MII_ADDR_READ);
+	if (ret)
+		return ret;
+
+	*val = mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR, REG_MII_DATA0);
+
+	return 0;
+}
+
+static int b53_mdio_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
+{
+	struct mii_bus *bus = dev->priv;
+	int ret;
+
+	ret = b53_mdio_op(dev, page, reg, REG_MII_ADDR_READ);
+	if (ret)
+		return ret;
+
+	*val = mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR, REG_MII_DATA0);
+	*val |= mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+				    REG_MII_DATA1) << 16;
+
+	return 0;
+}
+
+static int b53_mdio_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	struct mii_bus *bus = dev->priv;
+	u64 temp = 0;
+	int i;
+	int ret;
+
+	ret = b53_mdio_op(dev, page, reg, REG_MII_ADDR_READ);
+	if (ret)
+		return ret;
+
+	for (i = 2; i >= 0; i--) {
+		temp <<= 16;
+		temp |= mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+				     REG_MII_DATA0 + i);
+	}
+
+	*val = temp;
+
+	return 0;
+}
+
+static int b53_mdio_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	struct mii_bus *bus = dev->priv;
+	u64 temp = 0;
+	int i;
+	int ret;
+
+	ret = b53_mdio_op(dev, page, reg, REG_MII_ADDR_READ);
+	if (ret)
+		return ret;
+
+	for (i = 3; i >= 0; i--) {
+		temp <<= 16;
+		temp |= mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					    REG_MII_DATA0 + i);
+	}
+
+	*val = temp;
+
+	return 0;
+}
+
+static int b53_mdio_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
+{
+	struct mii_bus *bus = dev->priv;
+	int ret;
+
+	ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+				   REG_MII_DATA0, value);
+	if (ret)
+		return ret;
+
+	return b53_mdio_op(dev, page, reg, REG_MII_ADDR_WRITE);
+}
+
+static int b53_mdio_write16(struct b53_device *dev, u8 page, u8 reg,
+			    u16 value)
+{
+	struct mii_bus *bus = dev->priv;
+	int ret;
+
+	ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+				   REG_MII_DATA0, value);
+	if (ret)
+		return ret;
+
+	return b53_mdio_op(dev, page, reg, REG_MII_ADDR_WRITE);
+}
+
+static int b53_mdio_write32(struct b53_device *dev, u8 page, u8 reg,
+			    u32 value)
+{
+	struct mii_bus *bus = dev->priv;
+	unsigned int i;
+	u32 temp = value;
+
+	for (i = 0; i < 2; i++) {
+		int ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					       REG_MII_DATA0 + i,
+					       temp & 0xffff);
+		if (ret)
+			return ret;
+		temp >>= 16;
+	}
+
+	return b53_mdio_op(dev, page, reg, REG_MII_ADDR_WRITE);
+}
+
+static int b53_mdio_write48(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	struct mii_bus *bus = dev->priv;
+	unsigned int i;
+	u64 temp = value;
+
+	for (i = 0; i < 3; i++) {
+		int ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					       REG_MII_DATA0 + i,
+					       temp & 0xffff);
+		if (ret)
+			return ret;
+		temp >>= 16;
+	}
+
+	return b53_mdio_op(dev, page, reg, REG_MII_ADDR_WRITE);
+}
+
+static int b53_mdio_write64(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	struct mii_bus *bus = dev->priv;
+	unsigned int i;
+	u64 temp = value;
+
+	for (i = 0; i < 4; i++) {
+		int ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					       REG_MII_DATA0 + i,
+					       temp & 0xffff);
+		if (ret)
+			return ret;
+		temp >>= 16;
+	}
+
+	return b53_mdio_op(dev, page, reg, REG_MII_ADDR_WRITE);
+}
+
+static int b53_mdio_phy_read16(struct b53_device *dev, int addr, int reg,
+			       u16 *value)
+{
+	struct mii_bus *bus = dev->priv;
+
+	*value = mdiobus_read_nested(bus, addr, reg);
+
+	return 0;
+}
+
+static int b53_mdio_phy_write16(struct b53_device *dev, int addr, int reg,
+				u16 value)
+{
+	struct mii_bus *bus = dev->bus;
+
+	return mdiobus_write_nested(bus, addr, reg, value);
+}
+
+static struct b53_io_ops b53_mdio_ops = {
+	.read8 = b53_mdio_read8,
+	.read16 = b53_mdio_read16,
+	.read32 = b53_mdio_read32,
+	.read48 = b53_mdio_read48,
+	.read64 = b53_mdio_read64,
+	.write8 = b53_mdio_write8,
+	.write16 = b53_mdio_write16,
+	.write32 = b53_mdio_write32,
+	.write48 = b53_mdio_write48,
+	.write64 = b53_mdio_write64,
+	.phy_read16 = b53_mdio_phy_read16,
+	.phy_write16 = b53_mdio_phy_write16,
+};
+
+#define B53_BRCM_OUI_1	0x0143bc00
+#define B53_BRCM_OUI_2	0x03625c00
+#define B53_BRCM_OUI_3	0x00406000
+
+static int b53_mdio_probe(struct mdio_device *mdiodev)
+{
+	struct b53_device *dev;
+	u32 phy_id;
+	int ret;
+
+	/* allow the generic PHY driver to take over the non-management MDIO
+	 * addresses
+	 */
+	if (mdiodev->addr != BRCM_PSEUDO_PHY_ADDR && mdiodev->addr != 0) {
+		dev_err(&mdiodev->dev, "leaving address %d to PHY\n",
+			mdiodev->addr);
+		return -ENODEV;
+	}
+
+	/* read the first port's id */
+	phy_id = mdiobus_read(mdiodev->bus, 0, 2) << 16;
+	phy_id |= mdiobus_read(mdiodev->bus, 0, 3);
+
+	/* BCM5325, BCM539x (OUI_1)
+	 * BCM53125, BCM53128 (OUI_2)
+	 * BCM5365 (OUI_3)
+	 */
+	if ((phy_id & 0xfffffc00) != B53_BRCM_OUI_1 &&
+	    (phy_id & 0xfffffc00) != B53_BRCM_OUI_2 &&
+	    (phy_id & 0xfffffc00) != B53_BRCM_OUI_3) {
+		dev_err(&mdiodev->dev, "Unsupported device: 0x%08x\n", phy_id);
+		return -ENODEV;
+	}
+
+	/* First probe will come from SWITCH_MDIO controller on the 7445D0
+	 * switch, which will conflict with the 7445 integrated switch
+	 * pseudo-phy (we end-up programming both). In that case, we return
+	 * -EPROBE_DEFER for the first time we get here, and wait until we come
+	 * back with the slave MDIO bus which has the correct indirection
+	 * layer setup
+	 */
+	if (of_machine_is_compatible("brcm,bcm7445d0") &&
+	    strcmp(mdiodev->bus->name, "sf2 slave mii"))
+		return -EPROBE_DEFER;
+
+	dev = b53_switch_alloc(&mdiodev->dev, &b53_mdio_ops, mdiodev->bus);
+	if (!dev)
+		return -ENOMEM;
+
+	/* we don't use page 0xff, so force a page set */
+	dev->current_page = 0xff;
+	dev->bus = mdiodev->bus;
+
+	dev_set_drvdata(&mdiodev->dev, dev);
+
+	ret = b53_switch_register(dev);
+	if (ret) {
+		dev_err(&mdiodev->dev, "failed to register switch: %i\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static void b53_mdio_remove(struct mdio_device *mdiodev)
+{
+	struct b53_device *dev = dev_get_drvdata(&mdiodev->dev);
+	struct dsa_switch *ds = dev->ds;
+
+	dsa_unregister_switch(ds);
+}
+
+static const struct of_device_id b53_of_match[] = {
+	{ .compatible = "brcm,bcm5325" },
+	{ .compatible = "brcm,bcm53115" },
+	{ .compatible = "brcm,bcm53125" },
+	{ .compatible = "brcm,bcm53128" },
+	{ .compatible = "brcm,bcm5365" },
+	{ .compatible = "brcm,bcm5395" },
+	{ .compatible = "brcm,bcm5397" },
+	{ .compatible = "brcm,bcm5398" },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, b53_of_match);
+
+static struct mdio_driver b53_mdio_driver = {
+	.probe	= b53_mdio_probe,
+	.remove	= b53_mdio_remove,
+	.mdiodrv.driver = {
+		.name = "bcm53xx",
+		.of_match_table = b53_of_match,
+	},
+};
+
+static int __init b53_mdio_driver_register(void)
+{
+	return mdio_driver_register(&b53_mdio_driver);
+}
+module_init(b53_mdio_driver_register);
+
+static void __exit b53_mdio_driver_unregister(void)
+{
+	mdio_driver_unregister(&b53_mdio_driver);
+}
+module_exit(b53_mdio_driver_unregister);
+
+MODULE_DESCRIPTION("B53 MDIO access driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c
new file mode 100644
index 000000000000..21f1068b0804
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_mmap.c
@@ -0,0 +1,274 @@
+/*
+ * B53 register access through memory mapped registers
+ *
+ * Copyright (C) 2012-2013 Jonas Gorski <[email protected]>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kconfig.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/b53.h>
+
+#include "b53_priv.h"
+
+struct b53_mmap_priv {
+	void __iomem *regs;
+};
+
+static int b53_mmap_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
+{
+	u8 __iomem *regs = dev->priv;
+
+	*val = readb(regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
+{
+	u8 __iomem *regs = dev->priv;
+
+	if (WARN_ON(reg % 2))
+		return -EINVAL;
+
+	if (dev->pdata && dev->pdata->big_endian)
+		*val = ioread16be(regs + (page << 8) + reg);
+	else
+		*val = readw(regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
+{
+	u8 __iomem *regs = dev->priv;
+
+	if (WARN_ON(reg % 4))
+		return -EINVAL;
+
+	if (dev->pdata && dev->pdata->big_endian)
+		*val = ioread32be(regs + (page << 8) + reg);
+	else
+		*val = readl(regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	u8 __iomem *regs = dev->priv;
+
+	if (WARN_ON(reg % 2))
+		return -EINVAL;
+
+	if (reg % 4) {
+		u16 lo;
+		u32 hi;
+
+		if (dev->pdata && dev->pdata->big_endian) {
+			lo = ioread16be(regs + (page << 8) + reg);
+			hi = ioread32be(regs + (page << 8) + reg + 2);
+		} else {
+			lo = readw(regs + (page << 8) + reg);
+			hi = readl(regs + (page << 8) + reg + 2);
+		}
+
+		*val = ((u64)hi << 16) | lo;
+	} else {
+		u32 lo;
+		u16 hi;
+
+		if (dev->pdata && dev->pdata->big_endian) {
+			lo = ioread32be(regs + (page << 8) + reg);
+			hi = ioread16be(regs + (page << 8) + reg + 4);
+		} else {
+			lo = readl(regs + (page << 8) + reg);
+			hi = readw(regs + (page << 8) + reg + 4);
+		}
+
+		*val = ((u64)hi << 32) | lo;
+	}
+
+	return 0;
+}
+
+static int b53_mmap_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	u8 __iomem *regs = dev->priv;
+	u32 hi, lo;
+
+	if (WARN_ON(reg % 4))
+		return -EINVAL;
+
+	if (dev->pdata && dev->pdata->big_endian) {
+		lo = ioread32be(regs + (page << 8) + reg);
+		hi = ioread32be(regs + (page << 8) + reg + 4);
+	} else {
+		lo = readl(regs + (page << 8) + reg);
+		hi = readl(regs + (page << 8) + reg + 4);
+	}
+
+	*val = ((u64)hi << 32) | lo;
+
+	return 0;
+}
+
+static int b53_mmap_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
+{
+	u8 __iomem *regs = dev->priv;
+
+	writeb(value, regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_write16(struct b53_device *dev, u8 page, u8 reg,
+			    u16 value)
+{
+	u8 __iomem *regs = dev->priv;
+
+	if (WARN_ON(reg % 2))
+		return -EINVAL;
+
+	if (dev->pdata && dev->pdata->big_endian)
+		iowrite16be(value, regs + (page << 8) + reg);
+	else
+		writew(value, regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_write32(struct b53_device *dev, u8 page, u8 reg,
+			    u32 value)
+{
+	u8 __iomem *regs = dev->priv;
+
+	if (WARN_ON(reg % 4))
+		return -EINVAL;
+
+	if (dev->pdata && dev->pdata->big_endian)
+		iowrite32be(value, regs + (page << 8) + reg);
+	else
+		writel(value, regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_write48(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	if (WARN_ON(reg % 2))
+		return -EINVAL;
+
+	if (reg % 4) {
+		u32 hi = (u32)(value >> 16);
+		u16 lo = (u16)value;
+
+		b53_mmap_write16(dev, page, reg, lo);
+		b53_mmap_write32(dev, page, reg + 2, hi);
+	} else {
+		u16 hi = (u16)(value >> 32);
+		u32 lo = (u32)value;
+
+		b53_mmap_write32(dev, page, reg, lo);
+		b53_mmap_write16(dev, page, reg + 4, hi);
+	}
+
+	return 0;
+}
+
+static int b53_mmap_write64(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	u32 hi, lo;
+
+	hi = upper_32_bits(value);
+	lo = lower_32_bits(value);
+
+	if (WARN_ON(reg % 4))
+		return -EINVAL;
+
+	b53_mmap_write32(dev, page, reg, lo);
+	b53_mmap_write32(dev, page, reg + 4, hi);
+
+	return 0;
+}
+
+static struct b53_io_ops b53_mmap_ops = {
+	.read8 = b53_mmap_read8,
+	.read16 = b53_mmap_read16,
+	.read32 = b53_mmap_read32,
+	.read48 = b53_mmap_read48,
+	.read64 = b53_mmap_read64,
+	.write8 = b53_mmap_write8,
+	.write16 = b53_mmap_write16,
+	.write32 = b53_mmap_write32,
+	.write48 = b53_mmap_write48,
+	.write64 = b53_mmap_write64,
+};
+
+static int b53_mmap_probe(struct platform_device *pdev)
+{
+	struct b53_platform_data *pdata = pdev->dev.platform_data;
+	struct b53_device *dev;
+
+	if (!pdata)
+		return -EINVAL;
+
+	dev = b53_switch_alloc(&pdev->dev, &b53_mmap_ops, pdata->regs);
+	if (!dev)
+		return -ENOMEM;
+
+	if (pdata)
+		dev->pdata = pdata;
+
+	platform_set_drvdata(pdev, dev);
+
+	return b53_switch_register(dev);
+}
+
+static int b53_mmap_remove(struct platform_device *pdev)
+{
+	struct b53_device *dev = platform_get_drvdata(pdev);
+
+	if (dev)
+		b53_switch_remove(dev);
+
+	return 0;
+}
+
+static const struct of_device_id b53_mmap_of_table[] = {
+	{ .compatible = "brcm,bcm3384-switch" },
+	{ .compatible = "brcm,bcm6328-switch" },
+	{ .compatible = "brcm,bcm6368-switch" },
+	{ .compatible = "brcm,bcm63xx-switch" },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver b53_mmap_driver = {
+	.probe = b53_mmap_probe,
+	.remove = b53_mmap_remove,
+	.driver = {
+		.name = "b53-switch",
+		.of_match_table = b53_mmap_of_table,
+	},
+};
+
+module_platform_driver(b53_mmap_driver);
+MODULE_AUTHOR("Jonas Gorski <[email protected]>");
+MODULE_DESCRIPTION("B53 MMAP access driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
new file mode 100644
index 000000000000..5d8c602fb877
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -0,0 +1,387 @@
+/*
+ * B53 common definitions
+ *
+ * Copyright (C) 2011-2013 Jonas Gorski <[email protected]>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef __B53_PRIV_H
+#define __B53_PRIV_H
+
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/phy.h>
+#include <net/dsa.h>
+
+#include "b53_regs.h"
+
+struct b53_device;
+struct net_device;
+
+struct b53_io_ops {
+	int (*read8)(struct b53_device *dev, u8 page, u8 reg, u8 *value);
+	int (*read16)(struct b53_device *dev, u8 page, u8 reg, u16 *value);
+	int (*read32)(struct b53_device *dev, u8 page, u8 reg, u32 *value);
+	int (*read48)(struct b53_device *dev, u8 page, u8 reg, u64 *value);
+	int (*read64)(struct b53_device *dev, u8 page, u8 reg, u64 *value);
+	int (*write8)(struct b53_device *dev, u8 page, u8 reg, u8 value);
+	int (*write16)(struct b53_device *dev, u8 page, u8 reg, u16 value);
+	int (*write32)(struct b53_device *dev, u8 page, u8 reg, u32 value);
+	int (*write48)(struct b53_device *dev, u8 page, u8 reg, u64 value);
+	int (*write64)(struct b53_device *dev, u8 page, u8 reg, u64 value);
+	int (*phy_read16)(struct b53_device *dev, int addr, int reg, u16 *value);
+	int (*phy_write16)(struct b53_device *dev, int addr, int reg, u16 value);
+};
+
+enum {
+	BCM5325_DEVICE_ID = 0x25,
+	BCM5365_DEVICE_ID = 0x65,
+	BCM5395_DEVICE_ID = 0x95,
+	BCM5397_DEVICE_ID = 0x97,
+	BCM5398_DEVICE_ID = 0x98,
+	BCM53115_DEVICE_ID = 0x53115,
+	BCM53125_DEVICE_ID = 0x53125,
+	BCM53128_DEVICE_ID = 0x53128,
+	BCM63XX_DEVICE_ID = 0x6300,
+	BCM53010_DEVICE_ID = 0x53010,
+	BCM53011_DEVICE_ID = 0x53011,
+	BCM53012_DEVICE_ID = 0x53012,
+	BCM53018_DEVICE_ID = 0x53018,
+	BCM53019_DEVICE_ID = 0x53019,
+};
+
+#define B53_N_PORTS	9
+#define B53_N_PORTS_25	6
+
+struct b53_port {
+	u16		vlan_ctl_mask;
+	struct net_device *bridge_dev;
+};
+
+struct b53_vlan {
+	u16 members;
+	u16 untag;
+	bool valid;
+};
+
+struct b53_device {
+	struct dsa_switch *ds;
+	struct b53_platform_data *pdata;
+	const char *name;
+
+	struct mutex reg_mutex;
+	struct mutex stats_mutex;
+	const struct b53_io_ops *ops;
+
+	/* chip specific data */
+	u32 chip_id;
+	u8 core_rev;
+	u8 vta_regs[3];
+	u8 duplex_reg;
+	u8 jumbo_pm_reg;
+	u8 jumbo_size_reg;
+	int reset_gpio;
+	u8 num_arl_entries;
+
+	/* used ports mask */
+	u16 enabled_ports;
+	unsigned int cpu_port;
+
+	/* connect specific data */
+	u8 current_page;
+	struct device *dev;
+
+	/* Master MDIO bus we got probed from */
+	struct mii_bus *bus;
+
+	void *priv;
+
+	/* run time configuration */
+	bool enable_jumbo;
+
+	unsigned int num_vlans;
+	struct b53_vlan *vlans;
+	unsigned int num_ports;
+	struct b53_port *ports;
+};
+
+#define b53_for_each_port(dev, i) \
+	for (i = 0; i < B53_N_PORTS; i++) \
+		if (dev->enabled_ports & BIT(i))
+
+
+static inline int is5325(struct b53_device *dev)
+{
+	return dev->chip_id == BCM5325_DEVICE_ID;
+}
+
+static inline int is5365(struct b53_device *dev)
+{
+#ifdef CONFIG_BCM47XX
+	return dev->chip_id == BCM5365_DEVICE_ID;
+#else
+	return 0;
+#endif
+}
+
+static inline int is5397_98(struct b53_device *dev)
+{
+	return dev->chip_id == BCM5397_DEVICE_ID ||
+		dev->chip_id == BCM5398_DEVICE_ID;
+}
+
+static inline int is539x(struct b53_device *dev)
+{
+	return dev->chip_id == BCM5395_DEVICE_ID ||
+		dev->chip_id == BCM5397_DEVICE_ID ||
+		dev->chip_id == BCM5398_DEVICE_ID;
+}
+
+static inline int is531x5(struct b53_device *dev)
+{
+	return dev->chip_id == BCM53115_DEVICE_ID ||
+		dev->chip_id == BCM53125_DEVICE_ID ||
+		dev->chip_id == BCM53128_DEVICE_ID;
+}
+
+static inline int is63xx(struct b53_device *dev)
+{
+#ifdef CONFIG_BCM63XX
+	return dev->chip_id == BCM63XX_DEVICE_ID;
+#else
+	return 0;
+#endif
+}
+
+static inline int is5301x(struct b53_device *dev)
+{
+	return dev->chip_id == BCM53010_DEVICE_ID ||
+		dev->chip_id == BCM53011_DEVICE_ID ||
+		dev->chip_id == BCM53012_DEVICE_ID ||
+		dev->chip_id == BCM53018_DEVICE_ID ||
+		dev->chip_id == BCM53019_DEVICE_ID;
+}
+
+#define B53_CPU_PORT_25	5
+#define B53_CPU_PORT	8
+
+static inline int is_cpu_port(struct b53_device *dev, int port)
+{
+	return dev->cpu_port;
+}
+
+struct b53_device *b53_switch_alloc(struct device *base, struct b53_io_ops *ops,
+				    void *priv);
+
+int b53_switch_detect(struct b53_device *dev);
+
+int b53_switch_register(struct b53_device *dev);
+
+static inline void b53_switch_remove(struct b53_device *dev)
+{
+	dsa_unregister_switch(dev->ds);
+}
+
+static inline int b53_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read8(dev, page, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read16(dev, page, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read32(dev, page, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read48(dev, page, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read64(dev, page, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write8(dev, page, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_write16(struct b53_device *dev, u8 page, u8 reg,
+			      u16 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write16(dev, page, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_write32(struct b53_device *dev, u8 page, u8 reg,
+			      u32 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write32(dev, page, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_write48(struct b53_device *dev, u8 page, u8 reg,
+			      u64 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write48(dev, page, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_write64(struct b53_device *dev, u8 page, u8 reg,
+			       u64 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write64(dev, page, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+struct b53_arl_entry {
+	u8 port;
+	u8 mac[ETH_ALEN];
+	u16 vid;
+	u8 is_valid:1;
+	u8 is_age:1;
+	u8 is_static:1;
+};
+
+static inline void b53_mac_from_u64(u64 src, u8 *dst)
+{
+	unsigned int i;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		dst[ETH_ALEN - 1 - i] = (src >> (8 * i)) & 0xff;
+}
+
+static inline u64 b53_mac_to_u64(const u8 *src)
+{
+	unsigned int i;
+	u64 dst = 0;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		dst |= (u64)src[ETH_ALEN - 1 - i] << (8 * i);
+
+	return dst;
+}
+
+static inline void b53_arl_to_entry(struct b53_arl_entry *ent,
+				    u64 mac_vid, u32 fwd_entry)
+{
+	memset(ent, 0, sizeof(*ent));
+	ent->port = fwd_entry & ARLTBL_DATA_PORT_ID_MASK;
+	ent->is_valid = !!(fwd_entry & ARLTBL_VALID);
+	ent->is_age = !!(fwd_entry & ARLTBL_AGE);
+	ent->is_static = !!(fwd_entry & ARLTBL_STATIC);
+	b53_mac_from_u64(mac_vid, ent->mac);
+	ent->vid = mac_vid >> ARLTBL_VID_S;
+}
+
+static inline void b53_arl_from_entry(u64 *mac_vid, u32 *fwd_entry,
+				      const struct b53_arl_entry *ent)
+{
+	*mac_vid = b53_mac_to_u64(ent->mac);
+	*mac_vid |= (u64)(ent->vid & ARLTBL_VID_MASK) << ARLTBL_VID_S;
+	*fwd_entry = ent->port & ARLTBL_DATA_PORT_ID_MASK;
+	if (ent->is_valid)
+		*fwd_entry |= ARLTBL_VALID;
+	if (ent->is_static)
+		*fwd_entry |= ARLTBL_STATIC;
+	if (ent->is_age)
+		*fwd_entry |= ARLTBL_AGE;
+}
+
+#ifdef CONFIG_BCM47XX
+
+#include <linux/version.h>
+#include <linux/bcm47xx_nvram.h>
+#include <bcm47xx_board.h>
+static inline int b53_switch_get_reset_gpio(struct b53_device *dev)
+{
+	enum bcm47xx_board board = bcm47xx_board_get();
+
+	switch (board) {
+	case BCM47XX_BOARD_LINKSYS_WRT300NV11:
+	case BCM47XX_BOARD_LINKSYS_WRT310NV1:
+		return 8;
+	default:
+		return bcm47xx_nvram_gpio_pin("robo_reset");
+	}
+}
+#else
+static inline int b53_switch_get_reset_gpio(struct b53_device *dev)
+{
+	return -ENOENT;
+}
+#endif
+#endif
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
new file mode 100644
index 000000000000..8f12bddd5dc9
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -0,0 +1,434 @@
+/*
+ * B53 register definitions
+ *
+ * Copyright (C) 2004 Broadcom Corporation
+ * Copyright (C) 2011-2013 Jonas Gorski <[email protected]>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef __B53_REGS_H
+#define __B53_REGS_H
+
+/* Management Port (SMP) Page offsets */
+#define B53_CTRL_PAGE			0x00 /* Control */
+#define B53_STAT_PAGE			0x01 /* Status */
+#define B53_MGMT_PAGE			0x02 /* Management Mode */
+#define B53_MIB_AC_PAGE			0x03 /* MIB Autocast */
+#define B53_ARLCTRL_PAGE		0x04 /* ARL Control */
+#define B53_ARLIO_PAGE			0x05 /* ARL Access */
+#define B53_FRAMEBUF_PAGE		0x06 /* Management frame access */
+#define B53_MEM_ACCESS_PAGE		0x08 /* Memory access */
+
+/* PHY Registers */
+#define B53_PORT_MII_PAGE(i)		(0x10 + (i)) /* Port i MII Registers */
+#define B53_IM_PORT_PAGE		0x18 /* Inverse MII Port (to EMAC) */
+#define B53_ALL_PORT_PAGE		0x19 /* All ports MII (broadcast) */
+
+/* MIB registers */
+#define B53_MIB_PAGE(i)			(0x20 + (i))
+
+/* Quality of Service (QoS) Registers */
+#define B53_QOS_PAGE			0x30
+
+/* Port VLAN Page */
+#define B53_PVLAN_PAGE			0x31
+
+/* VLAN Registers */
+#define B53_VLAN_PAGE			0x34
+
+/* Jumbo Frame Registers */
+#define B53_JUMBO_PAGE			0x40
+
+/* CFP Configuration Registers Page */
+#define B53_CFP_PAGE			0xa1
+
+/*************************************************************************
+ * Control Page registers
+ *************************************************************************/
+
+/* Port Control Register (8 bit) */
+#define B53_PORT_CTRL(i)		(0x00 + (i))
+#define   PORT_CTRL_RX_DISABLE		BIT(0)
+#define   PORT_CTRL_TX_DISABLE		BIT(1)
+#define   PORT_CTRL_RX_BCST_EN		BIT(2) /* Broadcast RX (P8 only) */
+#define   PORT_CTRL_RX_MCST_EN		BIT(3) /* Multicast RX (P8 only) */
+#define   PORT_CTRL_RX_UCST_EN		BIT(4) /* Unicast RX (P8 only) */
+#define	  PORT_CTRL_STP_STATE_S		5
+#define   PORT_CTRL_NO_STP		(0 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_DIS_STATE		(1 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_BLOCK_STATE		(2 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_LISTEN_STATE	(3 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_LEARN_STATE		(4 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_FWD_STATE		(5 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_STP_STATE_MASK	(0x7 << PORT_CTRL_STP_STATE_S)
+
+/* SMP Control Register (8 bit) */
+#define B53_SMP_CTRL			0x0a
+
+/* Switch Mode Control Register (8 bit) */
+#define B53_SWITCH_MODE			0x0b
+#define   SM_SW_FWD_MODE		BIT(0)	/* 1 = Managed Mode */
+#define   SM_SW_FWD_EN			BIT(1)	/* Forwarding Enable */
+
+/* IMP Port state override register (8 bit) */
+#define B53_PORT_OVERRIDE_CTRL		0x0e
+#define   PORT_OVERRIDE_LINK		BIT(0)
+#define   PORT_OVERRIDE_FULL_DUPLEX	BIT(1) /* 0 = Half Duplex */
+#define   PORT_OVERRIDE_SPEED_S		2
+#define   PORT_OVERRIDE_SPEED_10M	(0 << PORT_OVERRIDE_SPEED_S)
+#define   PORT_OVERRIDE_SPEED_100M	(1 << PORT_OVERRIDE_SPEED_S)
+#define   PORT_OVERRIDE_SPEED_1000M	(2 << PORT_OVERRIDE_SPEED_S)
+#define   PORT_OVERRIDE_RV_MII_25	BIT(4) /* BCM5325 only */
+#define   PORT_OVERRIDE_RX_FLOW		BIT(4)
+#define   PORT_OVERRIDE_TX_FLOW		BIT(5)
+#define   PORT_OVERRIDE_SPEED_2000M	BIT(6) /* BCM5301X only, requires setting 1000M */
+#define   PORT_OVERRIDE_EN		BIT(7) /* Use the register contents */
+
+/* Power-down mode control */
+#define B53_PD_MODE_CTRL_25		0x0f
+
+/* IP Multicast control (8 bit) */
+#define B53_IP_MULTICAST_CTRL		0x21
+#define  B53_IPMC_FWD_EN		BIT(1)
+#define  B53_UC_FWD_EN			BIT(6)
+#define  B53_MC_FWD_EN			BIT(7)
+
+/* (16 bit) */
+#define B53_UC_FLOOD_MASK		0x32
+#define B53_MC_FLOOD_MASK		0x34
+#define B53_IPMC_FLOOD_MASK		0x36
+
+/*
+ * Override Ports 0-7 State on devices with xMII interfaces (8 bit)
+ *
+ * For port 8 still use B53_PORT_OVERRIDE_CTRL
+ * Please note that not all ports are available on every hardware, e.g. BCM5301X
+ * don't include overriding port 6, BCM63xx also have some limitations.
+ */
+#define B53_GMII_PORT_OVERRIDE_CTRL(i)	(0x58 + (i))
+#define   GMII_PO_LINK			BIT(0)
+#define   GMII_PO_FULL_DUPLEX		BIT(1) /* 0 = Half Duplex */
+#define   GMII_PO_SPEED_S		2
+#define   GMII_PO_SPEED_10M		(0 << GMII_PO_SPEED_S)
+#define   GMII_PO_SPEED_100M		(1 << GMII_PO_SPEED_S)
+#define   GMII_PO_SPEED_1000M		(2 << GMII_PO_SPEED_S)
+#define   GMII_PO_RX_FLOW		BIT(4)
+#define   GMII_PO_TX_FLOW		BIT(5)
+#define   GMII_PO_EN			BIT(6) /* Use the register contents */
+#define   GMII_PO_SPEED_2000M		BIT(7) /* BCM5301X only, requires setting 1000M */
+
+#define B53_RGMII_CTRL_IMP		0x60
+#define   RGMII_CTRL_ENABLE_GMII	BIT(7)
+#define   RGMII_CTRL_TIMING_SEL		BIT(2)
+#define   RGMII_CTRL_DLL_RXC		BIT(1)
+#define   RGMII_CTRL_DLL_TXC		BIT(0)
+
+#define B53_RGMII_CTRL_P(i)		(B53_RGMII_CTRL_IMP + (i))
+
+/* Software reset register (8 bit) */
+#define B53_SOFTRESET			0x79
+#define   SW_RST			BIT(7)
+#define   EN_SW_RST			BIT(4)
+
+/* Fast Aging Control register (8 bit) */
+#define B53_FAST_AGE_CTRL		0x88
+#define   FAST_AGE_STATIC		BIT(0)
+#define   FAST_AGE_DYNAMIC		BIT(1)
+#define   FAST_AGE_PORT			BIT(2)
+#define   FAST_AGE_VLAN			BIT(3)
+#define   FAST_AGE_STP			BIT(4)
+#define   FAST_AGE_MC			BIT(5)
+#define   FAST_AGE_DONE			BIT(7)
+
+/* Fast Aging Port Control register (8 bit) */
+#define B53_FAST_AGE_PORT_CTRL		0x89
+
+/* Fast Aging VID Control register (16 bit) */
+#define B53_FAST_AGE_VID_CTRL		0x8a
+
+/*************************************************************************
+ * Status Page registers
+ *************************************************************************/
+
+/* Link Status Summary Register (16bit) */
+#define B53_LINK_STAT			0x00
+
+/* Link Status Change Register (16 bit) */
+#define B53_LINK_STAT_CHANGE		0x02
+
+/* Port Speed Summary Register (16 bit for FE, 32 bit for GE) */
+#define B53_SPEED_STAT			0x04
+#define  SPEED_PORT_FE(reg, port)	(((reg) >> (port)) & 1)
+#define  SPEED_PORT_GE(reg, port)	(((reg) >> 2 * (port)) & 3)
+#define  SPEED_STAT_10M			0
+#define  SPEED_STAT_100M		1
+#define  SPEED_STAT_1000M		2
+
+/* Duplex Status Summary (16 bit) */
+#define B53_DUPLEX_STAT_FE		0x06
+#define B53_DUPLEX_STAT_GE		0x08
+#define B53_DUPLEX_STAT_63XX		0x0c
+
+/* Revision ID register for BCM5325 */
+#define B53_REV_ID_25			0x50
+
+/* Strap Value (48 bit) */
+#define B53_STRAP_VALUE			0x70
+#define   SV_GMII_CTRL_115		BIT(27)
+
+/*************************************************************************
+ * Management Mode Page Registers
+ *************************************************************************/
+
+/* Global Management Config Register (8 bit) */
+#define B53_GLOBAL_CONFIG		0x00
+#define   GC_RESET_MIB			0x01
+#define   GC_RX_BPDU_EN			0x02
+#define   GC_MIB_AC_HDR_EN		0x10
+#define   GC_MIB_AC_EN			0x20
+#define   GC_FRM_MGMT_PORT_M		0xC0
+#define   GC_FRM_MGMT_PORT_04		0x00
+#define   GC_FRM_MGMT_PORT_MII		0x80
+
+/* Broadcom Header control register (8 bit) */
+#define B53_BRCM_HDR			0x03
+#define   BRCM_HDR_P8_EN		BIT(0) /* Enable tagging on port 8 */
+#define   BRCM_HDR_P5_EN		BIT(1) /* Enable tagging on port 5 */
+
+/* Device ID register (8 or 32 bit) */
+#define B53_DEVICE_ID			0x30
+
+/* Revision ID register (8 bit) */
+#define B53_REV_ID			0x40
+
+/*************************************************************************
+ * ARL Access Page Registers
+ *************************************************************************/
+
+/* VLAN Table Access Register (8 bit) */
+#define B53_VT_ACCESS			0x80
+#define B53_VT_ACCESS_9798		0x60 /* for BCM5397/BCM5398 */
+#define B53_VT_ACCESS_63XX		0x60 /* for BCM6328/62/68 */
+#define   VTA_CMD_WRITE			0
+#define   VTA_CMD_READ			1
+#define   VTA_CMD_CLEAR			2
+#define   VTA_START_CMD			BIT(7)
+
+/* VLAN Table Index Register (16 bit) */
+#define B53_VT_INDEX			0x81
+#define B53_VT_INDEX_9798		0x61
+#define B53_VT_INDEX_63XX		0x62
+
+/* VLAN Table Entry Register (32 bit) */
+#define B53_VT_ENTRY			0x83
+#define B53_VT_ENTRY_9798		0x63
+#define B53_VT_ENTRY_63XX		0x64
+#define   VTE_MEMBERS			0x1ff
+#define   VTE_UNTAG_S			9
+#define   VTE_UNTAG			(0x1ff << 9)
+
+/*************************************************************************
+ * ARL I/O Registers
+ *************************************************************************/
+
+/* ARL Table Read/Write Register (8 bit) */
+#define B53_ARLTBL_RW_CTRL		0x00
+#define    ARLTBL_RW			BIT(0)
+#define    ARLTBL_START_DONE		BIT(7)
+
+/* MAC Address Index Register (48 bit) */
+#define B53_MAC_ADDR_IDX		0x02
+
+/* VLAN ID Index Register (16 bit) */
+#define B53_VLAN_ID_IDX			0x08
+
+/* ARL Table MAC/VID Entry N Registers (64 bit)
+ *
+ * BCM5325 and BCM5365 share most definitions below
+ */
+#define B53_ARLTBL_MAC_VID_ENTRY(n)	(0x10 * (n))
+#define   ARLTBL_MAC_MASK		0xffffffffffff
+#define   ARLTBL_VID_S			48
+#define   ARLTBL_VID_MASK_25		0xff
+#define   ARLTBL_VID_MASK		0xfff
+#define   ARLTBL_DATA_PORT_ID_S_25	48
+#define   ARLTBL_DATA_PORT_ID_MASK_25	0xf
+#define   ARLTBL_AGE_25			BIT(61)
+#define   ARLTBL_STATIC_25		BIT(62)
+#define   ARLTBL_VALID_25		BIT(63)
+
+/* ARL Table Data Entry N Registers (32 bit) */
+#define B53_ARLTBL_DATA_ENTRY(n)	((0x10 * (n)) + 0x08)
+#define   ARLTBL_DATA_PORT_ID_MASK	0x1ff
+#define   ARLTBL_TC(tc)			((3 & tc) << 11)
+#define   ARLTBL_AGE			BIT(14)
+#define   ARLTBL_STATIC			BIT(15)
+#define   ARLTBL_VALID			BIT(16)
+
+/* ARL Search Control Register (8 bit) */
+#define B53_ARL_SRCH_CTL		0x50
+#define B53_ARL_SRCH_CTL_25		0x20
+#define   ARL_SRCH_VLID			BIT(0)
+#define   ARL_SRCH_STDN			BIT(7)
+
+/* ARL Search Address Register (16 bit) */
+#define B53_ARL_SRCH_ADDR		0x51
+#define B53_ARL_SRCH_ADDR_25		0x22
+#define B53_ARL_SRCH_ADDR_65		0x24
+#define  ARL_ADDR_MASK			GENMASK(14, 0)
+
+/* ARL Search MAC/VID Result (64 bit) */
+#define B53_ARL_SRCH_RSTL_0_MACVID	0x60
+
+/* Single register search result on 5325 */
+#define B53_ARL_SRCH_RSTL_0_MACVID_25	0x24
+/* Single register search result on 5365 */
+#define B53_ARL_SRCH_RSTL_0_MACVID_65	0x30
+
+/* ARL Search Data Result (32 bit) */
+#define B53_ARL_SRCH_RSTL_0		0x68
+
+#define B53_ARL_SRCH_RSTL_MACVID(x)	(B53_ARL_SRCH_RSTL_0_MACVID + ((x) * 0x10))
+#define B53_ARL_SRCH_RSTL(x)		(B53_ARL_SRCH_RSTL_0 + ((x) * 0x10))
+
+/*************************************************************************
+ * Port VLAN Registers
+ *************************************************************************/
+
+/* Port VLAN mask (16 bit) IMP port is always 8, also on 5325 & co */
+#define B53_PVLAN_PORT_MASK(i)		((i) * 2)
+
+/*************************************************************************
+ * 802.1Q Page Registers
+ *************************************************************************/
+
+/* Global QoS Control (8 bit) */
+#define B53_QOS_GLOBAL_CTL		0x00
+
+/* Enable 802.1Q for individual Ports (16 bit) */
+#define B53_802_1P_EN			0x04
+
+/*************************************************************************
+ * VLAN Page Registers
+ *************************************************************************/
+
+/* VLAN Control 0 (8 bit) */
+#define B53_VLAN_CTRL0			0x00
+#define   VC0_8021PF_CTRL_MASK		0x3
+#define   VC0_8021PF_CTRL_NONE		0x0
+#define   VC0_8021PF_CTRL_CHANGE_PRI	0x1
+#define   VC0_8021PF_CTRL_CHANGE_VID	0x2
+#define   VC0_8021PF_CTRL_CHANGE_BOTH	0x3
+#define   VC0_8021QF_CTRL_MASK		0xc
+#define   VC0_8021QF_CTRL_CHANGE_PRI	0x1
+#define   VC0_8021QF_CTRL_CHANGE_VID	0x2
+#define   VC0_8021QF_CTRL_CHANGE_BOTH	0x3
+#define   VC0_RESERVED_1		BIT(1)
+#define   VC0_DROP_VID_MISS		BIT(4)
+#define   VC0_VID_HASH_VID		BIT(5)
+#define   VC0_VID_CHK_EN		BIT(6)	/* Use VID,DA or VID,SA */
+#define   VC0_VLAN_EN			BIT(7)	/* 802.1Q VLAN Enabled */
+
+/* VLAN Control 1 (8 bit) */
+#define B53_VLAN_CTRL1			0x01
+#define   VC1_RX_MCST_TAG_EN		BIT(1)
+#define   VC1_RX_MCST_FWD_EN		BIT(2)
+#define   VC1_RX_MCST_UNTAG_EN		BIT(3)
+
+/* VLAN Control 2 (8 bit) */
+#define B53_VLAN_CTRL2			0x02
+
+/* VLAN Control 3 (8 bit when BCM5325, 16 bit else) */
+#define B53_VLAN_CTRL3			0x03
+#define B53_VLAN_CTRL3_63XX		0x04
+#define   VC3_MAXSIZE_1532		BIT(6) /* 5325 only */
+#define   VC3_HIGH_8BIT_EN		BIT(7) /* 5325 only */
+
+/* VLAN Control 4 (8 bit) */
+#define B53_VLAN_CTRL4			0x05
+#define B53_VLAN_CTRL4_25		0x04
+#define B53_VLAN_CTRL4_63XX		0x06
+#define   VC4_ING_VID_CHECK_S		6
+#define   VC4_ING_VID_CHECK_MASK	(0x3 << VC4_ING_VID_CHECK_S)
+#define   VC4_ING_VID_VIO_FWD		0 /* forward, but do not learn */
+#define   VC4_ING_VID_VIO_DROP		1 /* drop VID violations */
+#define   VC4_NO_ING_VID_CHK		2 /* do not check */
+#define   VC4_ING_VID_VIO_TO_IMP	3 /* redirect to MII port */
+
+/* VLAN Control 5 (8 bit) */
+#define B53_VLAN_CTRL5			0x06
+#define B53_VLAN_CTRL5_25		0x05
+#define B53_VLAN_CTRL5_63XX		0x07
+#define   VC5_VID_FFF_EN		BIT(2)
+#define   VC5_DROP_VTABLE_MISS		BIT(3)
+
+/* VLAN Control 6 (8 bit) */
+#define B53_VLAN_CTRL6			0x07
+#define B53_VLAN_CTRL6_63XX		0x08
+
+/* VLAN Table Access Register (16 bit) */
+#define B53_VLAN_TABLE_ACCESS_25	0x06	/* BCM5325E/5350 */
+#define B53_VLAN_TABLE_ACCESS_65	0x08	/* BCM5365 */
+#define   VTA_VID_LOW_MASK_25		0xf
+#define   VTA_VID_LOW_MASK_65		0xff
+#define   VTA_VID_HIGH_S_25		4
+#define   VTA_VID_HIGH_S_65		8
+#define   VTA_VID_HIGH_MASK_25		(0xff << VTA_VID_HIGH_S_25E)
+#define   VTA_VID_HIGH_MASK_65		(0xf << VTA_VID_HIGH_S_65)
+#define   VTA_RW_STATE			BIT(12)
+#define   VTA_RW_STATE_RD		0
+#define   VTA_RW_STATE_WR		BIT(12)
+#define   VTA_RW_OP_EN			BIT(13)
+
+/* VLAN Read/Write Registers for (16/32 bit) */
+#define B53_VLAN_WRITE_25		0x08
+#define B53_VLAN_WRITE_65		0x0a
+#define B53_VLAN_READ			0x0c
+#define   VA_MEMBER_MASK		0x3f
+#define   VA_UNTAG_S_25			6
+#define   VA_UNTAG_MASK_25		0x3f
+#define   VA_UNTAG_S_65			7
+#define   VA_UNTAG_MASK_65		0x1f
+#define   VA_VID_HIGH_S			12
+#define   VA_VID_HIGH_MASK		(0xffff << VA_VID_HIGH_S)
+#define   VA_VALID_25			BIT(20)
+#define   VA_VALID_25_R4		BIT(24)
+#define   VA_VALID_65			BIT(14)
+
+/* VLAN Port Default Tag (16 bit) */
+#define B53_VLAN_PORT_DEF_TAG(i)	(0x10 + 2 * (i))
+
+/*************************************************************************
+ * Jumbo Frame Page Registers
+ *************************************************************************/
+
+/* Jumbo Enable Port Mask (bit i == port i enabled) (32 bit) */
+#define B53_JUMBO_PORT_MASK		0x01
+#define B53_JUMBO_PORT_MASK_63XX	0x04
+#define   JPM_10_100_JUMBO_EN		BIT(24) /* GigE always enabled */
+
+/* Good Frame Max Size without 802.1Q TAG (16 bit) */
+#define B53_JUMBO_MAX_SIZE		0x05
+#define B53_JUMBO_MAX_SIZE_63XX		0x08
+#define   JMS_MIN_SIZE			1518
+#define   JMS_MAX_SIZE			9724
+
+/*************************************************************************
+ * CFP Configuration Page Registers
+ *************************************************************************/
+
+/* CFP Control Register with ports map (8 bit) */
+#define B53_CFP_CTRL			0x00
+
+#endif /* !__B53_REGS_H */
diff --git a/drivers/net/dsa/b53/b53_spi.c b/drivers/net/dsa/b53/b53_spi.c
new file mode 100644
index 000000000000..2bda0b5f1578
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_spi.c
@@ -0,0 +1,331 @@
+/*
+ * B53 register access through SPI
+ *
+ * Copyright (C) 2011-2013 Jonas Gorski <[email protected]>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <asm/unaligned.h>
+
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/spi/spi.h>
+#include <linux/platform_data/b53.h>
+
+#include "b53_priv.h"
+
+#define B53_SPI_DATA		0xf0
+
+#define B53_SPI_STATUS		0xfe
+#define B53_SPI_CMD_SPIF	BIT(7)
+#define B53_SPI_CMD_RACK	BIT(5)
+
+#define B53_SPI_CMD_READ	0x00
+#define B53_SPI_CMD_WRITE	0x01
+#define B53_SPI_CMD_NORMAL	0x60
+#define B53_SPI_CMD_FAST	0x10
+
+#define B53_SPI_PAGE_SELECT	0xff
+
+static inline int b53_spi_read_reg(struct spi_device *spi, u8 reg, u8 *val,
+				   unsigned int len)
+{
+	u8 txbuf[2];
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_READ;
+	txbuf[1] = reg;
+
+	return spi_write_then_read(spi, txbuf, 2, val, len);
+}
+
+static inline int b53_spi_clear_status(struct spi_device *spi)
+{
+	unsigned int i;
+	u8 rxbuf;
+	int ret;
+
+	for (i = 0; i < 10; i++) {
+		ret = b53_spi_read_reg(spi, B53_SPI_STATUS, &rxbuf, 1);
+		if (ret)
+			return ret;
+
+		if (!(rxbuf & B53_SPI_CMD_SPIF))
+			break;
+
+		mdelay(1);
+	}
+
+	if (i == 10)
+		return -EIO;
+
+	return 0;
+}
+
+static inline int b53_spi_set_page(struct spi_device *spi, u8 page)
+{
+	u8 txbuf[3];
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = B53_SPI_PAGE_SELECT;
+	txbuf[2] = page;
+
+	return spi_write(spi, txbuf, sizeof(txbuf));
+}
+
+static inline int b53_prepare_reg_access(struct spi_device *spi, u8 page)
+{
+	int ret = b53_spi_clear_status(spi);
+
+	if (ret)
+		return ret;
+
+	return b53_spi_set_page(spi, page);
+}
+
+static int b53_spi_prepare_reg_read(struct spi_device *spi, u8 reg)
+{
+	u8 rxbuf;
+	int retry_count;
+	int ret;
+
+	ret = b53_spi_read_reg(spi, reg, &rxbuf, 1);
+	if (ret)
+		return ret;
+
+	for (retry_count = 0; retry_count < 10; retry_count++) {
+		ret = b53_spi_read_reg(spi, B53_SPI_STATUS, &rxbuf, 1);
+		if (ret)
+			return ret;
+
+		if (rxbuf & B53_SPI_CMD_RACK)
+			break;
+
+		mdelay(1);
+	}
+
+	if (retry_count == 10)
+		return -EIO;
+
+	return 0;
+}
+
+static int b53_spi_read(struct b53_device *dev, u8 page, u8 reg, u8 *data,
+			unsigned int len)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	ret = b53_spi_prepare_reg_read(spi, reg);
+	if (ret)
+		return ret;
+
+	return b53_spi_read_reg(spi, B53_SPI_DATA, data, len);
+}
+
+static int b53_spi_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
+{
+	return b53_spi_read(dev, page, reg, val, 1);
+}
+
+static int b53_spi_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
+{
+	int ret = b53_spi_read(dev, page, reg, (u8 *)val, 2);
+
+	if (!ret)
+		*val = le16_to_cpu(*val);
+
+	return ret;
+}
+
+static int b53_spi_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
+{
+	int ret = b53_spi_read(dev, page, reg, (u8 *)val, 4);
+
+	if (!ret)
+		*val = le32_to_cpu(*val);
+
+	return ret;
+}
+
+static int b53_spi_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	int ret;
+
+	*val = 0;
+	ret = b53_spi_read(dev, page, reg, (u8 *)val, 6);
+	if (!ret)
+		*val = le64_to_cpu(*val);
+
+	return ret;
+}
+
+static int b53_spi_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	int ret = b53_spi_read(dev, page, reg, (u8 *)val, 8);
+
+	if (!ret)
+		*val = le64_to_cpu(*val);
+
+	return ret;
+}
+
+static int b53_spi_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+	u8 txbuf[3];
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = reg;
+	txbuf[2] = value;
+
+	return spi_write(spi, txbuf, sizeof(txbuf));
+}
+
+static int b53_spi_write16(struct b53_device *dev, u8 page, u8 reg, u16 value)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+	u8 txbuf[4];
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = reg;
+	put_unaligned_le16(value, &txbuf[2]);
+
+	return spi_write(spi, txbuf, sizeof(txbuf));
+}
+
+static int b53_spi_write32(struct b53_device *dev, u8 page, u8 reg, u32 value)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+	u8 txbuf[6];
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = reg;
+	put_unaligned_le32(value, &txbuf[2]);
+
+	return spi_write(spi, txbuf, sizeof(txbuf));
+}
+
+static int b53_spi_write48(struct b53_device *dev, u8 page, u8 reg, u64 value)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+	u8 txbuf[10];
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = reg;
+	put_unaligned_le64(value, &txbuf[2]);
+
+	return spi_write(spi, txbuf, sizeof(txbuf) - 2);
+}
+
+static int b53_spi_write64(struct b53_device *dev, u8 page, u8 reg, u64 value)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+	u8 txbuf[10];
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = reg;
+	put_unaligned_le64(value, &txbuf[2]);
+
+	return spi_write(spi, txbuf, sizeof(txbuf));
+}
+
+static struct b53_io_ops b53_spi_ops = {
+	.read8 = b53_spi_read8,
+	.read16 = b53_spi_read16,
+	.read32 = b53_spi_read32,
+	.read48 = b53_spi_read48,
+	.read64 = b53_spi_read64,
+	.write8 = b53_spi_write8,
+	.write16 = b53_spi_write16,
+	.write32 = b53_spi_write32,
+	.write48 = b53_spi_write48,
+	.write64 = b53_spi_write64,
+};
+
+static int b53_spi_probe(struct spi_device *spi)
+{
+	struct b53_device *dev;
+	int ret;
+
+	dev = b53_switch_alloc(&spi->dev, &b53_spi_ops, spi);
+	if (!dev)
+		return -ENOMEM;
+
+	if (spi->dev.platform_data)
+		dev->pdata = spi->dev.platform_data;
+
+	ret = b53_switch_register(dev);
+	if (ret)
+		return ret;
+
+	spi_set_drvdata(spi, dev);
+
+	return 0;
+}
+
+static int b53_spi_remove(struct spi_device *spi)
+{
+	struct b53_device *dev = spi_get_drvdata(spi);
+
+	if (dev)
+		b53_switch_remove(dev);
+
+	return 0;
+}
+
+static struct spi_driver b53_spi_driver = {
+	.driver = {
+		.name	= "b53-switch",
+		.bus	= &spi_bus_type,
+		.owner	= THIS_MODULE,
+	},
+	.probe	= b53_spi_probe,
+	.remove	= b53_spi_remove,
+};
+
+module_spi_driver(b53_spi_driver);
+
+MODULE_AUTHOR("Jonas Gorski <[email protected]>");
+MODULE_DESCRIPTION("B53 SPI access driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c
new file mode 100644
index 000000000000..70fd47284535
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_srab.c
@@ -0,0 +1,415 @@
+/*
+ * B53 register access through Switch Register Access Bridge Registers
+ *
+ * Copyright (C) 2013 Hauke Mehrtens <[email protected]>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/b53.h>
+
+#include "b53_priv.h"
+
+/* command and status register of the SRAB */
+#define B53_SRAB_CMDSTAT		0x2c
+#define  B53_SRAB_CMDSTAT_RST		BIT(2)
+#define  B53_SRAB_CMDSTAT_WRITE		BIT(1)
+#define  B53_SRAB_CMDSTAT_GORDYN	BIT(0)
+#define  B53_SRAB_CMDSTAT_PAGE		24
+#define  B53_SRAB_CMDSTAT_REG		16
+
+/* high order word of write data to switch registe */
+#define B53_SRAB_WD_H			0x30
+
+/* low order word of write data to switch registe */
+#define B53_SRAB_WD_L			0x34
+
+/* high order word of read data from switch register */
+#define B53_SRAB_RD_H			0x38
+
+/* low order word of read data from switch register */
+#define B53_SRAB_RD_L			0x3c
+
+/* command and status register of the SRAB */
+#define B53_SRAB_CTRLS			0x40
+#define  B53_SRAB_CTRLS_RCAREQ		BIT(3)
+#define  B53_SRAB_CTRLS_RCAGNT		BIT(4)
+#define  B53_SRAB_CTRLS_SW_INIT_DONE	BIT(6)
+
+/* the register captures interrupt pulses from the switch */
+#define B53_SRAB_INTR			0x44
+#define  B53_SRAB_INTR_P(x)		BIT(x)
+#define  B53_SRAB_SWITCH_PHY		BIT(8)
+#define  B53_SRAB_1588_SYNC		BIT(9)
+#define  B53_SRAB_IMP1_SLEEP_TIMER	BIT(10)
+#define  B53_SRAB_P7_SLEEP_TIMER	BIT(11)
+#define  B53_SRAB_IMP0_SLEEP_TIMER	BIT(12)
+
+struct b53_srab_priv {
+	void __iomem *regs;
+};
+
+static int b53_srab_request_grant(struct b53_device *dev)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	u32 ctrls;
+	int i;
+
+	ctrls = readl(regs + B53_SRAB_CTRLS);
+	ctrls |= B53_SRAB_CTRLS_RCAREQ;
+	writel(ctrls, regs + B53_SRAB_CTRLS);
+
+	for (i = 0; i < 20; i++) {
+		ctrls = readl(regs + B53_SRAB_CTRLS);
+		if (ctrls & B53_SRAB_CTRLS_RCAGNT)
+			break;
+		usleep_range(10, 100);
+	}
+	if (WARN_ON(i == 5))
+		return -EIO;
+
+	return 0;
+}
+
+static void b53_srab_release_grant(struct b53_device *dev)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	u32 ctrls;
+
+	ctrls = readl(regs + B53_SRAB_CTRLS);
+	ctrls &= ~B53_SRAB_CTRLS_RCAREQ;
+	writel(ctrls, regs + B53_SRAB_CTRLS);
+}
+
+static int b53_srab_op(struct b53_device *dev, u8 page, u8 reg, u32 op)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int i;
+	u32 cmdstat;
+
+	/* set register address */
+	cmdstat = (page << B53_SRAB_CMDSTAT_PAGE) |
+		  (reg << B53_SRAB_CMDSTAT_REG) |
+		  B53_SRAB_CMDSTAT_GORDYN |
+		  op;
+	writel(cmdstat, regs + B53_SRAB_CMDSTAT);
+
+	/* check if operation completed */
+	for (i = 0; i < 5; ++i) {
+		cmdstat = readl(regs + B53_SRAB_CMDSTAT);
+		if (!(cmdstat & B53_SRAB_CMDSTAT_GORDYN))
+			break;
+		usleep_range(10, 100);
+	}
+
+	if (WARN_ON(i == 5))
+		return -EIO;
+
+	return 0;
+}
+
+static int b53_srab_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	ret = b53_srab_op(dev, page, reg, 0);
+	if (ret)
+		goto err;
+
+	*val = readl(regs + B53_SRAB_RD_L) & 0xff;
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	ret = b53_srab_op(dev, page, reg, 0);
+	if (ret)
+		goto err;
+
+	*val = readl(regs + B53_SRAB_RD_L) & 0xffff;
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	ret = b53_srab_op(dev, page, reg, 0);
+	if (ret)
+		goto err;
+
+	*val = readl(regs + B53_SRAB_RD_L);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	ret = b53_srab_op(dev, page, reg, 0);
+	if (ret)
+		goto err;
+
+	*val = readl(regs + B53_SRAB_RD_L);
+	*val += ((u64)readl(regs + B53_SRAB_RD_H) & 0xffff) << 32;
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	ret = b53_srab_op(dev, page, reg, 0);
+	if (ret)
+		goto err;
+
+	*val = readl(regs + B53_SRAB_RD_L);
+	*val += (u64)readl(regs + B53_SRAB_RD_H) << 32;
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	writel(value, regs + B53_SRAB_WD_L);
+
+	ret = b53_srab_op(dev, page, reg, B53_SRAB_CMDSTAT_WRITE);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_write16(struct b53_device *dev, u8 page, u8 reg,
+			    u16 value)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	writel(value, regs + B53_SRAB_WD_L);
+
+	ret = b53_srab_op(dev, page, reg, B53_SRAB_CMDSTAT_WRITE);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_write32(struct b53_device *dev, u8 page, u8 reg,
+			    u32 value)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	writel(value, regs + B53_SRAB_WD_L);
+
+	ret = b53_srab_op(dev, page, reg, B53_SRAB_CMDSTAT_WRITE);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_write48(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	writel((u32)value, regs + B53_SRAB_WD_L);
+	writel((u16)(value >> 32), regs + B53_SRAB_WD_H);
+
+	ret = b53_srab_op(dev, page, reg, B53_SRAB_CMDSTAT_WRITE);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_write64(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	writel((u32)value, regs + B53_SRAB_WD_L);
+	writel((u32)(value >> 32), regs + B53_SRAB_WD_H);
+
+	ret = b53_srab_op(dev, page, reg, B53_SRAB_CMDSTAT_WRITE);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static struct b53_io_ops b53_srab_ops = {
+	.read8 = b53_srab_read8,
+	.read16 = b53_srab_read16,
+	.read32 = b53_srab_read32,
+	.read48 = b53_srab_read48,
+	.read64 = b53_srab_read64,
+	.write8 = b53_srab_write8,
+	.write16 = b53_srab_write16,
+	.write32 = b53_srab_write32,
+	.write48 = b53_srab_write48,
+	.write64 = b53_srab_write64,
+};
+
+static int b53_srab_probe(struct platform_device *pdev)
+{
+	struct b53_srab_priv *priv;
+	struct b53_device *dev;
+	struct resource *r;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->regs = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(priv->regs))
+		return -ENOMEM;
+
+	dev = b53_switch_alloc(&pdev->dev, &b53_srab_ops, priv);
+	if (!dev)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, dev);
+
+	return b53_switch_register(dev);
+}
+
+static int b53_srab_remove(struct platform_device *pdev)
+{
+	struct b53_device *dev = platform_get_drvdata(pdev);
+
+	if (dev)
+		b53_switch_remove(dev);
+
+	return 0;
+}
+
+static const struct of_device_id b53_srab_of_match[] = {
+	{ .compatible = "brcm,bcm53010-srab" },
+	{ .compatible = "brcm,bcm53011-srab" },
+	{ .compatible = "brcm,bcm53012-srab" },
+	{ .compatible = "brcm,bcm53018-srab" },
+	{ .compatible = "brcm,bcm53019-srab" },
+	{ .compatible = "brcm,bcm5301x-srab" },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver b53_srab_driver = {
+	.probe = b53_srab_probe,
+	.remove = b53_srab_remove,
+	.driver = {
+		.name = "b53-srab-switch",
+		.of_match_table = b53_srab_of_match,
+	},
+};
+
+module_platform_driver(b53_srab_driver);
+MODULE_AUTHOR("Hauke Mehrtens <[email protected]>");
+MODULE_DESCRIPTION("B53 Switch Register Access Bridge Registers (SRAB) access driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 73df91bb0466..cd1d630ae3a9 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -22,6 +22,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 #include <linux/of_net.h>
+#include <linux/of_mdio.h>
 #include <net/dsa.h>
 #include <linux/ethtool.h>
 #include <linux/if_bridge.h>
@@ -460,19 +461,13 @@ static int bcm_sf2_sw_set_eee(struct dsa_switch *ds, int port,
 	return 0;
 }
 
-/* Fast-ageing of ARL entries for a given port, equivalent to an ARL
- * flush for that port.
- */
-static int bcm_sf2_sw_fast_age_port(struct dsa_switch  *ds, int port)
+static int bcm_sf2_fast_age_op(struct bcm_sf2_priv *priv)
 {
-	struct bcm_sf2_priv *priv = ds_to_priv(ds);
 	unsigned int timeout = 1000;
 	u32 reg;
 
-	core_writel(priv, port, CORE_FAST_AGE_PORT);
-
 	reg = core_readl(priv, CORE_FAST_AGE_CTRL);
-	reg |= EN_AGE_PORT | EN_AGE_DYNAMIC | FAST_AGE_STR_DONE;
+	reg |= EN_AGE_PORT | EN_AGE_VLAN | EN_AGE_DYNAMIC | FAST_AGE_STR_DONE;
 	core_writel(priv, reg, CORE_FAST_AGE_CTRL);
 
 	do {
@@ -491,13 +486,98 @@ static int bcm_sf2_sw_fast_age_port(struct dsa_switch  *ds, int port)
 	return 0;
 }
 
+/* Fast-ageing of ARL entries for a given port, equivalent to an ARL
+ * flush for that port.
+ */
+static int bcm_sf2_sw_fast_age_port(struct dsa_switch *ds, int port)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+
+	core_writel(priv, port, CORE_FAST_AGE_PORT);
+
+	return bcm_sf2_fast_age_op(priv);
+}
+
+static int bcm_sf2_sw_fast_age_vlan(struct bcm_sf2_priv *priv, u16 vid)
+{
+	core_writel(priv, vid, CORE_FAST_AGE_VID);
+
+	return bcm_sf2_fast_age_op(priv);
+}
+
+static int bcm_sf2_vlan_op_wait(struct bcm_sf2_priv *priv)
+{
+	unsigned int timeout = 10;
+	u32 reg;
+
+	do {
+		reg = core_readl(priv, CORE_ARLA_VTBL_RWCTRL);
+		if (!(reg & ARLA_VTBL_STDN))
+			return 0;
+
+		usleep_range(1000, 2000);
+	} while (timeout--);
+
+	return -ETIMEDOUT;
+}
+
+static int bcm_sf2_vlan_op(struct bcm_sf2_priv *priv, u8 op)
+{
+	core_writel(priv, ARLA_VTBL_STDN | op, CORE_ARLA_VTBL_RWCTRL);
+
+	return bcm_sf2_vlan_op_wait(priv);
+}
+
+static void bcm_sf2_set_vlan_entry(struct bcm_sf2_priv *priv, u16 vid,
+				   struct bcm_sf2_vlan *vlan)
+{
+	int ret;
+
+	core_writel(priv, vid & VTBL_ADDR_INDEX_MASK, CORE_ARLA_VTBL_ADDR);
+	core_writel(priv, vlan->untag << UNTAG_MAP_SHIFT | vlan->members,
+		    CORE_ARLA_VTBL_ENTRY);
+
+	ret = bcm_sf2_vlan_op(priv, ARLA_VTBL_CMD_WRITE);
+	if (ret)
+		pr_err("failed to write VLAN entry\n");
+}
+
+static int bcm_sf2_get_vlan_entry(struct bcm_sf2_priv *priv, u16 vid,
+				  struct bcm_sf2_vlan *vlan)
+{
+	u32 entry;
+	int ret;
+
+	core_writel(priv, vid & VTBL_ADDR_INDEX_MASK, CORE_ARLA_VTBL_ADDR);
+
+	ret = bcm_sf2_vlan_op(priv, ARLA_VTBL_CMD_READ);
+	if (ret)
+		return ret;
+
+	entry = core_readl(priv, CORE_ARLA_VTBL_ENTRY);
+	vlan->members = entry & FWD_MAP_MASK;
+	vlan->untag = (entry >> UNTAG_MAP_SHIFT) & UNTAG_MAP_MASK;
+
+	return 0;
+}
+
 static int bcm_sf2_sw_br_join(struct dsa_switch *ds, int port,
 			      struct net_device *bridge)
 {
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	s8 cpu_port = ds->dst->cpu_port;
 	unsigned int i;
 	u32 reg, p_ctl;
 
+	/* Make this port leave the all VLANs join since we will have proper
+	 * VLAN entries from now on
+	 */
+	reg = core_readl(priv, CORE_JOIN_ALL_VLAN_EN);
+	reg &= ~BIT(port);
+	if ((reg & BIT(cpu_port)) == BIT(cpu_port))
+		reg &= ~BIT(cpu_port);
+	core_writel(priv, reg, CORE_JOIN_ALL_VLAN_EN);
+
 	priv->port_sts[port].bridge_dev = bridge;
 	p_ctl = core_readl(priv, CORE_PORT_VLAN_CTL_PORT(port));
 
@@ -529,6 +609,7 @@ static void bcm_sf2_sw_br_leave(struct dsa_switch *ds, int port)
 {
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
 	struct net_device *bridge = priv->port_sts[port].bridge_dev;
+	s8 cpu_port = ds->dst->cpu_port;
 	unsigned int i;
 	u32 reg, p_ctl;
 
@@ -552,6 +633,13 @@ static void bcm_sf2_sw_br_leave(struct dsa_switch *ds, int port)
 	core_writel(priv, p_ctl, CORE_PORT_VLAN_CTL_PORT(port));
 	priv->port_sts[port].vlan_ctl_mask = p_ctl;
 	priv->port_sts[port].bridge_dev = NULL;
+
+	/* Make this port join all VLANs without VLAN entries */
+	reg = core_readl(priv, CORE_JOIN_ALL_VLAN_EN);
+	reg |= BIT(port);
+	if (!(reg & BIT(cpu_port)))
+		reg |= BIT(cpu_port);
+	core_writel(priv, reg, CORE_JOIN_ALL_VLAN_EN);
 }
 
 static void bcm_sf2_sw_br_set_stp_state(struct dsa_switch *ds, int port,
@@ -836,6 +924,66 @@ static int bcm_sf2_sw_fdb_dump(struct dsa_switch *ds, int port,
 	return 0;
 }
 
+static int bcm_sf2_sw_indir_rw(struct bcm_sf2_priv *priv, int op, int addr,
+			       int regnum, u16 val)
+{
+	int ret = 0;
+	u32 reg;
+
+	reg = reg_readl(priv, REG_SWITCH_CNTRL);
+	reg |= MDIO_MASTER_SEL;
+	reg_writel(priv, reg, REG_SWITCH_CNTRL);
+
+	/* Page << 8 | offset */
+	reg = 0x70;
+	reg <<= 2;
+	core_writel(priv, addr, reg);
+
+	/* Page << 8 | offset */
+	reg = 0x80 << 8 | regnum << 1;
+	reg <<= 2;
+
+	if (op)
+		ret = core_readl(priv, reg);
+	else
+		core_writel(priv, val, reg);
+
+	reg = reg_readl(priv, REG_SWITCH_CNTRL);
+	reg &= ~MDIO_MASTER_SEL;
+	reg_writel(priv, reg, REG_SWITCH_CNTRL);
+
+	return ret & 0xffff;
+}
+
+static int bcm_sf2_sw_mdio_read(struct mii_bus *bus, int addr, int regnum)
+{
+	struct bcm_sf2_priv *priv = bus->priv;
+
+	/* Intercept reads from Broadcom pseudo-PHY address, else, send
+	 * them to our master MDIO bus controller
+	 */
+	if (addr == BRCM_PSEUDO_PHY_ADDR && priv->indir_phy_mask & BIT(addr))
+		return bcm_sf2_sw_indir_rw(priv, 1, addr, regnum, 0);
+	else
+		return mdiobus_read(priv->master_mii_bus, addr, regnum);
+}
+
+static int bcm_sf2_sw_mdio_write(struct mii_bus *bus, int addr, int regnum,
+				 u16 val)
+{
+	struct bcm_sf2_priv *priv = bus->priv;
+
+	/* Intercept writes to the Broadcom pseudo-PHY address, else,
+	 * send them to our master MDIO bus controller
+	 */
+	if (addr == BRCM_PSEUDO_PHY_ADDR && priv->indir_phy_mask & BIT(addr))
+		bcm_sf2_sw_indir_rw(priv, 0, addr, regnum, val);
+	else
+		mdiobus_write(priv->master_mii_bus, addr, regnum, val);
+
+	return 0;
+}
+
 static irqreturn_t bcm_sf2_switch_0_isr(int irq, void *dev_id)
 {
 	struct bcm_sf2_priv *priv = dev_id;
@@ -932,133 +1080,70 @@ static void bcm_sf2_identify_ports(struct bcm_sf2_priv *priv,
 	}
 }
 
-static int bcm_sf2_sw_setup(struct dsa_switch *ds)
+static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 {
-	const char *reg_names[BCM_SF2_REGS_NUM] = BCM_SF2_REGS_NAME;
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
 	struct device_node *dn;
-	void __iomem **base;
-	unsigned int port;
-	unsigned int i;
-	u32 reg, rev;
-	int ret;
-
-	spin_lock_init(&priv->indir_lock);
-	mutex_init(&priv->stats_mutex);
-
-	/* All the interesting properties are at the parent device_node
-	 * level
-	 */
-	dn = ds->cd->of_node->parent;
-	bcm_sf2_identify_ports(priv, ds->cd->of_node);
-
-	priv->irq0 = irq_of_parse_and_map(dn, 0);
-	priv->irq1 = irq_of_parse_and_map(dn, 1);
-
-	base = &priv->core;
-	for (i = 0; i < BCM_SF2_REGS_NUM; i++) {
-		*base = of_iomap(dn, i);
-		if (*base == NULL) {
-			pr_err("unable to find register: %s\n", reg_names[i]);
-			ret = -ENOMEM;
-			goto out_unmap;
-		}
-		base++;
-	}
-
-	ret = bcm_sf2_sw_rst(priv);
-	if (ret) {
-		pr_err("unable to software reset switch: %d\n", ret);
-		goto out_unmap;
-	}
-
-	/* Disable all interrupts and request them */
-	bcm_sf2_intr_disable(priv);
-
-	ret = request_irq(priv->irq0, bcm_sf2_switch_0_isr, 0,
-			  "switch_0", priv);
-	if (ret < 0) {
-		pr_err("failed to request switch_0 IRQ\n");
-		goto out_unmap;
-	}
-
-	ret = request_irq(priv->irq1, bcm_sf2_switch_1_isr, 0,
-			  "switch_1", priv);
-	if (ret < 0) {
-		pr_err("failed to request switch_1 IRQ\n");
-		goto out_free_irq0;
-	}
-
-	/* Reset the MIB counters */
-	reg = core_readl(priv, CORE_GMNCFGCFG);
-	reg |= RST_MIB_CNT;
-	core_writel(priv, reg, CORE_GMNCFGCFG);
-	reg &= ~RST_MIB_CNT;
-	core_writel(priv, reg, CORE_GMNCFGCFG);
-
-	/* Get the maximum number of ports for this switch */
-	priv->hw_params.num_ports = core_readl(priv, CORE_IMP0_PRT_ID) + 1;
-	if (priv->hw_params.num_ports > DSA_MAX_PORTS)
-		priv->hw_params.num_ports = DSA_MAX_PORTS;
-
-	/* Assume a single GPHY setup if we can't read that property */
-	if (of_property_read_u32(dn, "brcm,num-gphy",
-				 &priv->hw_params.num_gphy))
-		priv->hw_params.num_gphy = 1;
-
-	/* Enable all valid ports and disable those unused */
-	for (port = 0; port < priv->hw_params.num_ports; port++) {
-		/* IMP port receives special treatment */
-		if ((1 << port) & ds->enabled_port_mask)
-			bcm_sf2_port_setup(ds, port, NULL);
-		else if (dsa_is_cpu_port(ds, port))
-			bcm_sf2_imp_setup(ds, port);
-		else
-			bcm_sf2_port_disable(ds, port, NULL);
-	}
-
-	/* Include the pseudo-PHY address and the broadcast PHY address to
-	 * divert reads towards our workaround. This is only required for
-	 * 7445D0, since 7445E0 disconnects the internal switch pseudo-PHY such
-	 * that we can use the regular SWITCH_MDIO master controller instead.
+	static int index;
+	int err;
+
+	/* Find our integrated MDIO bus node */
+	dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio");
+	priv->master_mii_bus = of_mdio_find_bus(dn);
+	if (!priv->master_mii_bus)
+		return -EPROBE_DEFER;
+
+	get_device(&priv->master_mii_bus->dev);
+	priv->master_mii_dn = dn;
+
+	priv->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
+	if (!priv->slave_mii_bus)
+		return -ENOMEM;
+
+	priv->slave_mii_bus->priv = priv;
+	priv->slave_mii_bus->name = "sf2 slave mii";
+	priv->slave_mii_bus->read = bcm_sf2_sw_mdio_read;
+	priv->slave_mii_bus->write = bcm_sf2_sw_mdio_write;
+	snprintf(priv->slave_mii_bus->id, MII_BUS_ID_SIZE, "sf2-%d",
+		 index++);
+	priv->slave_mii_bus->dev.of_node = dn;
+
+	/* Include the pseudo-PHY address to divert reads towards our
+	 * workaround. This is only required for 7445D0, since 7445E0
+	 * disconnects the internal switch pseudo-PHY such that we can use the
+	 * regular SWITCH_MDIO master controller instead.
 	 *
-	 * By default, DSA initializes ds->phys_mii_mask to
-	 * ds->enabled_port_mask to have a 1:1 mapping between Port address
-	 * and PHY address in order to utilize the slave_mii_bus instance to
-	 * read from Port PHYs. This is not what we want here, so we
-	 * initialize phys_mii_mask 0 to always utilize the "master" MDIO
-	 * bus backed by the "mdio-unimac" driver.
+	 * Here we flag the pseudo PHY as needing special treatment and would
+	 * otherwise make all other PHY read/writes go to the master MDIO bus
+	 * controller that comes with this switch backed by the "mdio-unimac"
+	 * driver.
 	 */
 	if (of_machine_is_compatible("brcm,bcm7445d0"))
-		ds->phys_mii_mask |= ((1 << BRCM_PSEUDO_PHY_ADDR) | (1 << 0));
+		priv->indir_phy_mask |= (1 << BRCM_PSEUDO_PHY_ADDR);
 	else
-		ds->phys_mii_mask = 0;
+		priv->indir_phy_mask = 0;
 
-	rev = reg_readl(priv, REG_SWITCH_REVISION);
-	priv->hw_params.top_rev = (rev >> SWITCH_TOP_REV_SHIFT) &
-					SWITCH_TOP_REV_MASK;
-	priv->hw_params.core_rev = (rev & SF2_REV_MASK);
+	ds->phys_mii_mask = priv->indir_phy_mask;
+	ds->slave_mii_bus = priv->slave_mii_bus;
+	priv->slave_mii_bus->parent = ds->dev->parent;
+	priv->slave_mii_bus->phy_mask = ~priv->indir_phy_mask;
 
-	rev = reg_readl(priv, REG_PHY_REVISION);
-	priv->hw_params.gphy_rev = rev & PHY_REVISION_MASK;
+	if (dn)
+		err = of_mdiobus_register(priv->slave_mii_bus, dn);
+	else
+		err = mdiobus_register(priv->slave_mii_bus);
 
-	pr_info("Starfighter 2 top: %x.%02x, core: %x.%02x base: 0x%p, IRQs: %d, %d\n",
-		priv->hw_params.top_rev >> 8, priv->hw_params.top_rev & 0xff,
-		priv->hw_params.core_rev >> 8, priv->hw_params.core_rev & 0xff,
-		priv->core, priv->irq0, priv->irq1);
+	if (err)
+		of_node_put(dn);
 
-	return 0;
+	return err;
+}
 
-out_free_irq0:
-	free_irq(priv->irq0, priv);
-out_unmap:
-	base = &priv->core;
-	for (i = 0; i < BCM_SF2_REGS_NUM; i++) {
-		if (*base)
-			iounmap(*base);
-		base++;
-	}
-	return ret;
+static void bcm_sf2_mdio_unregister(struct bcm_sf2_priv *priv)
+{
+	mdiobus_unregister(priv->slave_mii_bus);
+	if (priv->master_mii_dn)
+		of_node_put(priv->master_mii_dn);
 }
 
 static int bcm_sf2_sw_set_addr(struct dsa_switch *ds, u8 *addr)
@@ -1078,68 +1163,6 @@ static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port)
 	return priv->hw_params.gphy_rev;
 }
 
-static int bcm_sf2_sw_indir_rw(struct dsa_switch *ds, int op, int addr,
-			       int regnum, u16 val)
-{
-	struct bcm_sf2_priv *priv = ds_to_priv(ds);
-	int ret = 0;
-	u32 reg;
-
-	reg = reg_readl(priv, REG_SWITCH_CNTRL);
-	reg |= MDIO_MASTER_SEL;
-	reg_writel(priv, reg, REG_SWITCH_CNTRL);
-
-	/* Page << 8 | offset */
-	reg = 0x70;
-	reg <<= 2;
-	core_writel(priv, addr, reg);
-
-	/* Page << 8 | offset */
-	reg = 0x80 << 8 | regnum << 1;
-	reg <<= 2;
-
-	if (op)
-		ret = core_readl(priv, reg);
-	else
-		core_writel(priv, val, reg);
-
-	reg = reg_readl(priv, REG_SWITCH_CNTRL);
-	reg &= ~MDIO_MASTER_SEL;
-	reg_writel(priv, reg, REG_SWITCH_CNTRL);
-
-	return ret & 0xffff;
-}
-
-static int bcm_sf2_sw_phy_read(struct dsa_switch *ds, int addr, int regnum)
-{
-	/* Intercept reads from the MDIO broadcast address or Broadcom
-	 * pseudo-PHY address
-	 */
-	switch (addr) {
-	case 0:
-	case BRCM_PSEUDO_PHY_ADDR:
-		return bcm_sf2_sw_indir_rw(ds, 1, addr, regnum, 0);
-	default:
-		return 0xffff;
-	}
-}
-
-static int bcm_sf2_sw_phy_write(struct dsa_switch *ds, int addr, int regnum,
-				u16 val)
-{
-	/* Intercept writes to the MDIO broadcast address or Broadcom
-	 * pseudo-PHY address
-	 */
-	switch (addr) {
-	case 0:
-	case BRCM_PSEUDO_PHY_ADDR:
-		bcm_sf2_sw_indir_rw(ds, 0, addr, regnum, val);
-		break;
-	}
-
-	return 0;
-}
-
 static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port,
 				   struct phy_device *phydev)
 {
@@ -1370,14 +1393,309 @@ static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port,
 	return p->ethtool_ops->set_wol(p, wol);
 }
 
+static void bcm_sf2_enable_vlan(struct bcm_sf2_priv *priv, bool enable)
+{
+	u32 mgmt, vc0, vc1, vc4, vc5;
+
+	mgmt = core_readl(priv, CORE_SWMODE);
+	vc0 = core_readl(priv, CORE_VLAN_CTRL0);
+	vc1 = core_readl(priv, CORE_VLAN_CTRL1);
+	vc4 = core_readl(priv, CORE_VLAN_CTRL4);
+	vc5 = core_readl(priv, CORE_VLAN_CTRL5);
+
+	mgmt &= ~SW_FWDG_MODE;
+
+	if (enable) {
+		vc0 |= VLAN_EN | VLAN_LEARN_MODE_IVL;
+		vc1 |= EN_RSV_MCAST_UNTAG | EN_RSV_MCAST_FWDMAP;
+		vc4 &= ~(INGR_VID_CHK_MASK << INGR_VID_CHK_SHIFT);
+		vc4 |= INGR_VID_CHK_DROP;
+		vc5 |= DROP_VTABLE_MISS | EN_VID_FFF_FWD;
+	} else {
+		vc0 &= ~(VLAN_EN | VLAN_LEARN_MODE_IVL);
+		vc1 &= ~(EN_RSV_MCAST_UNTAG | EN_RSV_MCAST_FWDMAP);
+		vc4 &= ~(INGR_VID_CHK_MASK << INGR_VID_CHK_SHIFT);
+		vc5 &= ~(DROP_VTABLE_MISS | EN_VID_FFF_FWD);
+		vc4 |= INGR_VID_CHK_VID_VIOL_IMP;
+	}
+
+	core_writel(priv, vc0, CORE_VLAN_CTRL0);
+	core_writel(priv, vc1, CORE_VLAN_CTRL1);
+	core_writel(priv, 0, CORE_VLAN_CTRL3);
+	core_writel(priv, vc4, CORE_VLAN_CTRL4);
+	core_writel(priv, vc5, CORE_VLAN_CTRL5);
+	core_writel(priv, mgmt, CORE_SWMODE);
+}
+
+static void bcm_sf2_sw_configure_vlan(struct dsa_switch *ds)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	unsigned int port;
+
+	/* Clear all VLANs */
+	bcm_sf2_vlan_op(priv, ARLA_VTBL_CMD_CLEAR);
+
+	for (port = 0; port < priv->hw_params.num_ports; port++) {
+		if (!((1 << port) & ds->enabled_port_mask))
+			continue;
+
+		core_writel(priv, 1, CORE_DEFAULT_1Q_TAG_P(port));
+	}
+}
+
+static int bcm_sf2_sw_vlan_filtering(struct dsa_switch *ds, int port,
+				     bool vlan_filtering)
+{
+	return 0;
+}
+
+static int bcm_sf2_sw_vlan_prepare(struct dsa_switch *ds, int port,
+				   const struct switchdev_obj_port_vlan *vlan,
+				   struct switchdev_trans *trans)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+
+	bcm_sf2_enable_vlan(priv, true);
+
+	return 0;
+}
+
+static void bcm_sf2_sw_vlan_add(struct dsa_switch *ds, int port,
+				const struct switchdev_obj_port_vlan *vlan,
+				struct switchdev_trans *trans)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+	s8 cpu_port = ds->dst->cpu_port;
+	struct bcm_sf2_vlan *vl;
+	u16 vid;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &priv->vlans[vid];
+
+		bcm_sf2_get_vlan_entry(priv, vid, vl);
+
+		vl->members |= BIT(port) | BIT(cpu_port);
+		if (untagged)
+			vl->untag |= BIT(port) | BIT(cpu_port);
+		else
+			vl->untag &= ~(BIT(port) | BIT(cpu_port));
+
+		bcm_sf2_set_vlan_entry(priv, vid, vl);
+		bcm_sf2_sw_fast_age_vlan(priv, vid);
+	}
+
+	if (pvid) {
+		core_writel(priv, vlan->vid_end, CORE_DEFAULT_1Q_TAG_P(port));
+		core_writel(priv, vlan->vid_end,
+			    CORE_DEFAULT_1Q_TAG_P(cpu_port));
+		bcm_sf2_sw_fast_age_vlan(priv, vid);
+	}
+}
+
+static int bcm_sf2_sw_vlan_del(struct dsa_switch *ds, int port,
+			       const struct switchdev_obj_port_vlan *vlan)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	s8 cpu_port = ds->dst->cpu_port;
+	struct bcm_sf2_vlan *vl;
+	u16 vid, pvid;
+	int ret;
+
+	pvid = core_readl(priv, CORE_DEFAULT_1Q_TAG_P(port));
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &priv->vlans[vid];
+
+		ret = bcm_sf2_get_vlan_entry(priv, vid, vl);
+		if (ret)
+			return ret;
+
+		vl->members &= ~BIT(port);
+		if ((vl->members & BIT(cpu_port)) == BIT(cpu_port))
+			vl->members = 0;
+		if (pvid == vid)
+			pvid = 0;
+		if (untagged) {
+			vl->untag &= ~BIT(port);
+			if ((vl->untag & BIT(port)) == BIT(cpu_port))
+				vl->untag = 0;
+		}
+
+		bcm_sf2_set_vlan_entry(priv, vid, vl);
+		bcm_sf2_sw_fast_age_vlan(priv, vid);
+	}
+
+	core_writel(priv, pvid, CORE_DEFAULT_1Q_TAG_P(port));
+	core_writel(priv, pvid, CORE_DEFAULT_1Q_TAG_P(cpu_port));
+	bcm_sf2_sw_fast_age_vlan(priv, vid);
+
+	return 0;
+}
+
+static int bcm_sf2_sw_vlan_dump(struct dsa_switch *ds, int port,
+				struct switchdev_obj_port_vlan *vlan,
+				int (*cb)(struct switchdev_obj *obj))
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	struct bcm_sf2_port_status *p = &priv->port_sts[port];
+	struct bcm_sf2_vlan *vl;
+	u16 vid, pvid;
+	int err = 0;
+
+	pvid = core_readl(priv, CORE_DEFAULT_1Q_TAG_P(port));
+
+	for (vid = 0; vid < VLAN_N_VID; vid++) {
+		vl = &priv->vlans[vid];
+
+		if (!(vl->members & BIT(port)))
+			continue;
+
+		vlan->vid_begin = vlan->vid_end = vid;
+		vlan->flags = 0;
+
+		if (vl->untag & BIT(port))
+			vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+		if (p->pvid == vid)
+			vlan->flags |= BRIDGE_VLAN_INFO_PVID;
+
+		err = cb(&vlan->obj);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+static int bcm_sf2_sw_setup(struct dsa_switch *ds)
+{
+	const char *reg_names[BCM_SF2_REGS_NUM] = BCM_SF2_REGS_NAME;
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	struct device_node *dn;
+	void __iomem **base;
+	unsigned int port;
+	unsigned int i;
+	u32 reg, rev;
+	int ret;
+
+	spin_lock_init(&priv->indir_lock);
+	mutex_init(&priv->stats_mutex);
+
+	/* All the interesting properties are at the parent device_node
+	 * level
+	 */
+	dn = ds->cd->of_node->parent;
+	bcm_sf2_identify_ports(priv, ds->cd->of_node);
+
+	priv->irq0 = irq_of_parse_and_map(dn, 0);
+	priv->irq1 = irq_of_parse_and_map(dn, 1);
+
+	base = &priv->core;
+	for (i = 0; i < BCM_SF2_REGS_NUM; i++) {
+		*base = of_iomap(dn, i);
+		if (*base == NULL) {
+			pr_err("unable to find register: %s\n", reg_names[i]);
+			ret = -ENOMEM;
+			goto out_unmap;
+		}
+		base++;
+	}
+
+	ret = bcm_sf2_sw_rst(priv);
+	if (ret) {
+		pr_err("unable to software reset switch: %d\n", ret);
+		goto out_unmap;
+	}
+
+	ret = bcm_sf2_mdio_register(ds);
+	if (ret) {
+		pr_err("failed to register MDIO bus\n");
+		goto out_unmap;
+	}
+
+	/* Disable all interrupts and request them */
+	bcm_sf2_intr_disable(priv);
+
+	ret = request_irq(priv->irq0, bcm_sf2_switch_0_isr, 0,
+			  "switch_0", priv);
+	if (ret < 0) {
+		pr_err("failed to request switch_0 IRQ\n");
+		goto out_unmap;
+	}
+
+	ret = request_irq(priv->irq1, bcm_sf2_switch_1_isr, 0,
+			  "switch_1", priv);
+	if (ret < 0) {
+		pr_err("failed to request switch_1 IRQ\n");
+		goto out_free_irq0;
+	}
+
+	/* Reset the MIB counters */
+	reg = core_readl(priv, CORE_GMNCFGCFG);
+	reg |= RST_MIB_CNT;
+	core_writel(priv, reg, CORE_GMNCFGCFG);
+	reg &= ~RST_MIB_CNT;
+	core_writel(priv, reg, CORE_GMNCFGCFG);
+
+	/* Get the maximum number of ports for this switch */
+	priv->hw_params.num_ports = core_readl(priv, CORE_IMP0_PRT_ID) + 1;
+	if (priv->hw_params.num_ports > DSA_MAX_PORTS)
+		priv->hw_params.num_ports = DSA_MAX_PORTS;
+
+	/* Assume a single GPHY setup if we can't read that property */
+	if (of_property_read_u32(dn, "brcm,num-gphy",
+				 &priv->hw_params.num_gphy))
+		priv->hw_params.num_gphy = 1;
+
+	/* Enable all valid ports and disable those unused */
+	for (port = 0; port < priv->hw_params.num_ports; port++) {
+		/* IMP port receives special treatment */
+		if ((1 << port) & ds->enabled_port_mask)
+			bcm_sf2_port_setup(ds, port, NULL);
+		else if (dsa_is_cpu_port(ds, port))
+			bcm_sf2_imp_setup(ds, port);
+		else
+			bcm_sf2_port_disable(ds, port, NULL);
+	}
+
+	bcm_sf2_sw_configure_vlan(ds);
+
+	rev = reg_readl(priv, REG_SWITCH_REVISION);
+	priv->hw_params.top_rev = (rev >> SWITCH_TOP_REV_SHIFT) &
+					SWITCH_TOP_REV_MASK;
+	priv->hw_params.core_rev = (rev & SF2_REV_MASK);
+
+	rev = reg_readl(priv, REG_PHY_REVISION);
+	priv->hw_params.gphy_rev = rev & PHY_REVISION_MASK;
+
+	pr_info("Starfighter 2 top: %x.%02x, core: %x.%02x base: 0x%p, IRQs: %d, %d\n",
+		priv->hw_params.top_rev >> 8, priv->hw_params.top_rev & 0xff,
+		priv->hw_params.core_rev >> 8, priv->hw_params.core_rev & 0xff,
+		priv->core, priv->irq0, priv->irq1);
+
+	return 0;
+
+out_free_irq0:
+	free_irq(priv->irq0, priv);
+out_unmap:
+	base = &priv->core;
+	for (i = 0; i < BCM_SF2_REGS_NUM; i++) {
+		if (*base)
+			iounmap(*base);
+		base++;
+	}
+	bcm_sf2_mdio_unregister(priv);
+	return ret;
+}
+
 static struct dsa_switch_driver bcm_sf2_switch_driver = {
 	.tag_protocol		= DSA_TAG_PROTO_BRCM,
 	.probe			= bcm_sf2_sw_drv_probe,
 	.setup			= bcm_sf2_sw_setup,
 	.set_addr		= bcm_sf2_sw_set_addr,
 	.get_phy_flags		= bcm_sf2_sw_get_phy_flags,
-	.phy_read		= bcm_sf2_sw_phy_read,
-	.phy_write		= bcm_sf2_sw_phy_write,
 	.get_strings		= bcm_sf2_sw_get_strings,
 	.get_ethtool_stats	= bcm_sf2_sw_get_ethtool_stats,
 	.get_sset_count		= bcm_sf2_sw_get_sset_count,
@@ -1398,6 +1716,11 @@ static struct dsa_switch_driver bcm_sf2_switch_driver = {
 	.port_fdb_add		= bcm_sf2_sw_fdb_add,
 	.port_fdb_del		= bcm_sf2_sw_fdb_del,
 	.port_fdb_dump		= bcm_sf2_sw_fdb_dump,
+	.port_vlan_filtering	= bcm_sf2_sw_vlan_filtering,
+	.port_vlan_prepare	= bcm_sf2_sw_vlan_prepare,
+	.port_vlan_add		= bcm_sf2_sw_vlan_add,
+	.port_vlan_del		= bcm_sf2_sw_vlan_del,
+	.port_vlan_dump		= bcm_sf2_sw_vlan_dump,
 };
 
 static int __init bcm_sf2_init(void)
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 200b1f5fdb56..463bed8cbe4c 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -21,6 +21,7 @@
 #include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/bitops.h>
+#include <linux/if_vlan.h>
 
 #include <net/dsa.h>
 
@@ -50,6 +51,7 @@ struct bcm_sf2_port_status {
 	struct ethtool_eee eee;
 
 	u32 vlan_ctl_mask;
+	u16 pvid;
 
 	struct net_device *bridge_dev;
 };
@@ -63,6 +65,11 @@ struct bcm_sf2_arl_entry {
 	u8 is_static:1;
 };
 
+struct bcm_sf2_vlan {
+	u16 members;
+	u16 untag;
+};
+
 static inline void bcm_sf2_mac_from_u64(u64 src, u8 *dst)
 {
 	unsigned int i;
@@ -142,6 +149,15 @@ struct bcm_sf2_priv {
 
 	/* Bitmask of ports having an integrated PHY */
 	unsigned int			int_phy_mask;
+
+	/* Master and slave MDIO bus controller */
+	unsigned int			indir_phy_mask;
+	struct device_node		*master_mii_dn;
+	struct mii_bus			*slave_mii_bus;
+	struct mii_bus			*master_mii_bus;
+
+	/* Cache of programmed VLANs */
+	struct bcm_sf2_vlan		vlans[VLAN_N_VID];
 };
 
 struct bcm_sf2_hw_stats {
diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h
index 97780d43b5c0..9f2a9cb42074 100644
--- a/drivers/net/dsa/bcm_sf2_regs.h
+++ b/drivers/net/dsa/bcm_sf2_regs.h
@@ -274,6 +274,23 @@
 #define CORE_ARLA_SRCH_RSLT_MACVID(x)	(CORE_ARLA_SRCH_RSLT_0_MACVID + ((x) * 0x40))
 #define CORE_ARLA_SRCH_RSLT(x)		(CORE_ARLA_SRCH_RSLT_0 + ((x) * 0x40))
 
+#define CORE_ARLA_VTBL_RWCTRL		0x1600
+#define  ARLA_VTBL_CMD_WRITE		0
+#define  ARLA_VTBL_CMD_READ		1
+#define  ARLA_VTBL_CMD_CLEAR		2
+#define  ARLA_VTBL_STDN			(1 << 7)
+
+#define CORE_ARLA_VTBL_ADDR		0x1604
+#define  VTBL_ADDR_INDEX_MASK		0xfff
+
+#define CORE_ARLA_VTBL_ENTRY		0x160c
+#define  FWD_MAP_MASK			0x1ff
+#define  UNTAG_MAP_MASK			0x1ff
+#define  UNTAG_MAP_SHIFT		9
+#define  MSTP_INDEX_MASK		0x7
+#define  MSTP_INDEX_SHIFT		18
+#define  FWD_MODE			(1 << 21)
+
 #define CORE_MEM_PSM_VDD_CTRL		0x2380
 #define  P_TXQ_PSM_VDD_SHIFT		2
 #define  P_TXQ_PSM_VDD_MASK		0x3
@@ -287,6 +304,59 @@
 #define CORE_PORT_VLAN_CTL_PORT(x)	(0xc400 + ((x) * 0x8))
 #define  PORT_VLAN_CTRL_MASK		0x1ff
 
+#define CORE_VLAN_CTRL0			0xd000
+#define  CHANGE_1P_VID_INNER		(1 << 0)
+#define  CHANGE_1P_VID_OUTER		(1 << 1)
+#define  CHANGE_1Q_VID			(1 << 3)
+#define  VLAN_LEARN_MODE_SVL		(0 << 5)
+#define  VLAN_LEARN_MODE_IVL		(3 << 5)
+#define  VLAN_EN			(1 << 7)
+
+#define CORE_VLAN_CTRL1			0xd004
+#define  EN_RSV_MCAST_FWDMAP		(1 << 2)
+#define  EN_RSV_MCAST_UNTAG		(1 << 3)
+#define  EN_IPMC_BYPASS_FWDMAP		(1 << 5)
+#define  EN_IPMC_BYPASS_UNTAG		(1 << 6)
+
+#define CORE_VLAN_CTRL2			0xd008
+#define  EN_MIIM_BYPASS_V_FWDMAP	(1 << 2)
+#define  EN_GMRP_GVRP_V_FWDMAP		(1 << 5)
+#define  EN_GMRP_GVRP_UNTAG_MAP		(1 << 6)
+
+#define CORE_VLAN_CTRL3			0xd00c
+#define  EN_DROP_NON1Q_MASK		0x1ff
+
+#define CORE_VLAN_CTRL4			0xd014
+#define  RESV_MCAST_FLOOD		(1 << 1)
+#define  EN_DOUBLE_TAG_MASK		0x3
+#define  EN_DOUBLE_TAG_SHIFT		2
+#define  EN_MGE_REV_GMRP		(1 << 4)
+#define  EN_MGE_REV_GVRP		(1 << 5)
+#define  INGR_VID_CHK_SHIFT		6
+#define  INGR_VID_CHK_MASK		0x3
+#define  INGR_VID_CHK_FWD		(0 << INGR_VID_CHK_SHIFT)
+#define  INGR_VID_CHK_DROP		(1 << INGR_VID_CHK_SHIFT)
+#define  INGR_VID_CHK_NO_CHK		(2 << INGR_VID_CHK_SHIFT)
+#define  INGR_VID_CHK_VID_VIOL_IMP	(3 << INGR_VID_CHK_SHIFT)
+
+#define CORE_VLAN_CTRL5			0xd018
+#define  EN_CPU_RX_BYP_INNER_CRCCHCK	(1 << 0)
+#define  EN_VID_FFF_FWD			(1 << 2)
+#define  DROP_VTABLE_MISS		(1 << 3)
+#define  EGRESS_DIR_FRM_BYP_TRUNK_EN	(1 << 4)
+#define  PRESV_NON1Q			(1 << 6)
+
+#define CORE_VLAN_CTRL6			0xd01c
+#define  STRICT_SFD_DETECT		(1 << 0)
+#define  DIS_ARL_BUST_LMIT		(1 << 4)
+
+#define CORE_DEFAULT_1Q_TAG_P(x)	(0xd040 + ((x) * 8))
+#define  CFI_SHIFT			12
+#define  PRI_SHIFT			13
+#define  PRI_MASK			0x7
+
+#define CORE_JOIN_ALL_VLAN_EN		0xd140
+
 #define CORE_EEE_EN_CTRL		0x24800
 #define CORE_EEE_LPI_INDICATE		0x24810
 
diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig
new file mode 100644
index 000000000000..490bc06f993e
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/Kconfig
@@ -0,0 +1,7 @@
+config NET_DSA_MV88E6XXX
+	tristate "Marvell 88E6xxx Ethernet switch fabric support"
+	depends on NET_DSA
+	select NET_DSA_TAG_EDSA
+	help
+	  This driver adds support for most of the Marvell 88E6xxx models of
+	  Ethernet switch chips, except 88E6060.
diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile
new file mode 100644
index 000000000000..6e29a75ee2f7
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_NET_DSA_MV88E6XXX) += chip.o
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx/chip.c
index ee06055444f9..5cb06f7673af 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -1,5 +1,6 @@
 /*
- * net/dsa/mv88e6xxx.c - Marvell 88e6xxx switch chip support
+ * Marvell 88e6xxx Ethernet switch single-chip support
+ *
  * Copyright (c) 2008 Marvell Semiconductor
  *
  * Copyright (c) 2015 CMC Electronics, Inc.
@@ -21,6 +22,7 @@
 #include <linux/list.h>
 #include <linux/mdio.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/of_mdio.h>
 #include <linux/netdevice.h>
 #include <linux/gpio/consumer.h>
@@ -29,29 +31,82 @@
 #include <net/switchdev.h>
 #include "mv88e6xxx.h"
 
-static void assert_smi_lock(struct mv88e6xxx_priv_state *ps)
+static void assert_reg_lock(struct mv88e6xxx_chip *chip)
 {
-	if (unlikely(!mutex_is_locked(&ps->smi_mutex))) {
-		dev_err(ps->dev, "SMI lock not held!\n");
+	if (unlikely(!mutex_is_locked(&chip->reg_lock))) {
+		dev_err(chip->dev, "Switch registers lock not held!\n");
 		dump_stack();
 	}
 }
 
-/* If the switch's ADDR[4:0] strap pins are strapped to zero, it will
- * use all 32 SMI bus addresses on its SMI bus, and all switch registers
- * will be directly accessible on some {device address,register address}
- * pair.  If the ADDR[4:0] pins are not strapped to zero, the switch
- * will only respond to SMI transactions to that specific address, and
- * an indirect addressing mechanism needs to be used to access its
- * registers.
+/* The switch ADDR[4:1] configuration pins define the chip SMI device address
+ * (ADDR[0] is always zero, thus only even SMI addresses can be strapped).
+ *
+ * When ADDR is all zero, the chip uses Single-chip Addressing Mode, assuming it
+ * is the only device connected to the SMI master. In this mode it responds to
+ * all 32 possible SMI addresses, and thus maps directly the internal devices.
+ *
+ * When ADDR is non-zero, the chip uses Multi-chip Addressing Mode, allowing
+ * multiple devices to share the SMI interface. In this mode it responds to only
+ * 2 registers, used to indirectly access the internal SMI devices.
  */
-static int mv88e6xxx_reg_wait_ready(struct mii_bus *bus, int sw_addr)
+
+static int mv88e6xxx_smi_read(struct mv88e6xxx_chip *chip,
+			      int addr, int reg, u16 *val)
+{
+	if (!chip->smi_ops)
+		return -EOPNOTSUPP;
+
+	return chip->smi_ops->read(chip, addr, reg, val);
+}
+
+static int mv88e6xxx_smi_write(struct mv88e6xxx_chip *chip,
+			       int addr, int reg, u16 val)
+{
+	if (!chip->smi_ops)
+		return -EOPNOTSUPP;
+
+	return chip->smi_ops->write(chip, addr, reg, val);
+}
+
+static int mv88e6xxx_smi_single_chip_read(struct mv88e6xxx_chip *chip,
+					  int addr, int reg, u16 *val)
+{
+	int ret;
+
+	ret = mdiobus_read_nested(chip->bus, addr, reg);
+	if (ret < 0)
+		return ret;
+
+	*val = ret & 0xffff;
+
+	return 0;
+}
+
+static int mv88e6xxx_smi_single_chip_write(struct mv88e6xxx_chip *chip,
+					   int addr, int reg, u16 val)
+{
+	int ret;
+
+	ret = mdiobus_write_nested(chip->bus, addr, reg, val);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static const struct mv88e6xxx_ops mv88e6xxx_smi_single_chip_ops = {
+	.read = mv88e6xxx_smi_single_chip_read,
+	.write = mv88e6xxx_smi_single_chip_write,
+};
+
+static int mv88e6xxx_smi_multi_chip_wait(struct mv88e6xxx_chip *chip)
 {
 	int ret;
 	int i;
 
 	for (i = 0; i < 16; i++) {
-		ret = mdiobus_read_nested(bus, sw_addr, SMI_CMD);
+		ret = mdiobus_read_nested(chip->bus, chip->sw_addr, SMI_CMD);
 		if (ret < 0)
 			return ret;
 
@@ -62,143 +117,168 @@ static int mv88e6xxx_reg_wait_ready(struct mii_bus *bus, int sw_addr)
 	return -ETIMEDOUT;
 }
 
-static int __mv88e6xxx_reg_read(struct mii_bus *bus, int sw_addr, int addr,
-				int reg)
+static int mv88e6xxx_smi_multi_chip_read(struct mv88e6xxx_chip *chip,
+					 int addr, int reg, u16 *val)
 {
 	int ret;
 
-	if (sw_addr == 0)
-		return mdiobus_read_nested(bus, addr, reg);
-
 	/* Wait for the bus to become free. */
-	ret = mv88e6xxx_reg_wait_ready(bus, sw_addr);
+	ret = mv88e6xxx_smi_multi_chip_wait(chip);
 	if (ret < 0)
 		return ret;
 
 	/* Transmit the read command. */
-	ret = mdiobus_write_nested(bus, sw_addr, SMI_CMD,
+	ret = mdiobus_write_nested(chip->bus, chip->sw_addr, SMI_CMD,
 				   SMI_CMD_OP_22_READ | (addr << 5) | reg);
 	if (ret < 0)
 		return ret;
 
 	/* Wait for the read command to complete. */
-	ret = mv88e6xxx_reg_wait_ready(bus, sw_addr);
+	ret = mv88e6xxx_smi_multi_chip_wait(chip);
 	if (ret < 0)
 		return ret;
 
 	/* Read the data. */
-	ret = mdiobus_read_nested(bus, sw_addr, SMI_DATA);
-	if (ret < 0)
-		return ret;
-
-	return ret & 0xffff;
-}
-
-static int _mv88e6xxx_reg_read(struct mv88e6xxx_priv_state *ps,
-			       int addr, int reg)
-{
-	int ret;
-
-	assert_smi_lock(ps);
-
-	ret = __mv88e6xxx_reg_read(ps->bus, ps->sw_addr, addr, reg);
+	ret = mdiobus_read_nested(chip->bus, chip->sw_addr, SMI_DATA);
 	if (ret < 0)
 		return ret;
 
-	dev_dbg(ps->dev, "<- addr: 0x%.2x reg: 0x%.2x val: 0x%.4x\n",
-		addr, reg, ret);
+	*val = ret & 0xffff;
 
-	return ret;
-}
-
-int mv88e6xxx_reg_read(struct mv88e6xxx_priv_state *ps, int addr, int reg)
-{
-	int ret;
-
-	mutex_lock(&ps->smi_mutex);
-	ret = _mv88e6xxx_reg_read(ps, addr, reg);
-	mutex_unlock(&ps->smi_mutex);
-
-	return ret;
+	return 0;
 }
 
-static int __mv88e6xxx_reg_write(struct mii_bus *bus, int sw_addr, int addr,
-				 int reg, u16 val)
+static int mv88e6xxx_smi_multi_chip_write(struct mv88e6xxx_chip *chip,
+					  int addr, int reg, u16 val)
 {
 	int ret;
 
-	if (sw_addr == 0)
-		return mdiobus_write_nested(bus, addr, reg, val);
-
 	/* Wait for the bus to become free. */
-	ret = mv88e6xxx_reg_wait_ready(bus, sw_addr);
+	ret = mv88e6xxx_smi_multi_chip_wait(chip);
 	if (ret < 0)
 		return ret;
 
 	/* Transmit the data to write. */
-	ret = mdiobus_write_nested(bus, sw_addr, SMI_DATA, val);
+	ret = mdiobus_write_nested(chip->bus, chip->sw_addr, SMI_DATA, val);
 	if (ret < 0)
 		return ret;
 
 	/* Transmit the write command. */
-	ret = mdiobus_write_nested(bus, sw_addr, SMI_CMD,
+	ret = mdiobus_write_nested(chip->bus, chip->sw_addr, SMI_CMD,
 				   SMI_CMD_OP_22_WRITE | (addr << 5) | reg);
 	if (ret < 0)
 		return ret;
 
 	/* Wait for the write command to complete. */
-	ret = mv88e6xxx_reg_wait_ready(bus, sw_addr);
+	ret = mv88e6xxx_smi_multi_chip_wait(chip);
 	if (ret < 0)
 		return ret;
 
 	return 0;
 }
 
-static int _mv88e6xxx_reg_write(struct mv88e6xxx_priv_state *ps, int addr,
-				int reg, u16 val)
+static const struct mv88e6xxx_ops mv88e6xxx_smi_multi_chip_ops = {
+	.read = mv88e6xxx_smi_multi_chip_read,
+	.write = mv88e6xxx_smi_multi_chip_write,
+};
+
+static int mv88e6xxx_read(struct mv88e6xxx_chip *chip,
+			  int addr, int reg, u16 *val)
 {
-	assert_smi_lock(ps);
+	int err;
+
+	assert_reg_lock(chip);
+
+	err = mv88e6xxx_smi_read(chip, addr, reg, val);
+	if (err)
+		return err;
+
+	dev_dbg(chip->dev, "<- addr: 0x%.2x reg: 0x%.2x val: 0x%.4x\n",
+		addr, reg, *val);
+
+	return 0;
+}
+
+static int mv88e6xxx_write(struct mv88e6xxx_chip *chip,
+			   int addr, int reg, u16 val)
+{
+	int err;
 
-	dev_dbg(ps->dev, "-> addr: 0x%.2x reg: 0x%.2x val: 0x%.4x\n",
+	assert_reg_lock(chip);
+
+	err = mv88e6xxx_smi_write(chip, addr, reg, val);
+	if (err)
+		return err;
+
+	dev_dbg(chip->dev, "-> addr: 0x%.2x reg: 0x%.2x val: 0x%.4x\n",
 		addr, reg, val);
 
-	return __mv88e6xxx_reg_write(ps->bus, ps->sw_addr, addr, reg, val);
+	return 0;
 }
 
-int mv88e6xxx_reg_write(struct mv88e6xxx_priv_state *ps, int addr,
-			int reg, u16 val)
+static int _mv88e6xxx_reg_read(struct mv88e6xxx_chip *chip, int addr, int reg)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_read(chip, addr, reg, &val);
+	if (err)
+		return err;
+
+	return val;
+}
+
+static int mv88e6xxx_reg_read(struct mv88e6xxx_chip *chip, int addr, int reg)
 {
 	int ret;
 
-	mutex_lock(&ps->smi_mutex);
-	ret = _mv88e6xxx_reg_write(ps, addr, reg, val);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
+	ret = _mv88e6xxx_reg_read(chip, addr, reg);
+	mutex_unlock(&chip->reg_lock);
+
+	return ret;
+}
+
+static int _mv88e6xxx_reg_write(struct mv88e6xxx_chip *chip, int addr,
+				int reg, u16 val)
+{
+	return mv88e6xxx_write(chip, addr, reg, val);
+}
+
+static int mv88e6xxx_reg_write(struct mv88e6xxx_chip *chip, int addr,
+			       int reg, u16 val)
+{
+	int ret;
+
+	mutex_lock(&chip->reg_lock);
+	ret = _mv88e6xxx_reg_write(chip, addr, reg, val);
+	mutex_unlock(&chip->reg_lock);
 
 	return ret;
 }
 
 static int mv88e6xxx_set_addr_direct(struct dsa_switch *ds, u8 *addr)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int err;
 
-	err = mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_MAC_01,
+	err = mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_MAC_01,
 				  (addr[0] << 8) | addr[1]);
 	if (err)
 		return err;
 
-	err = mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_MAC_23,
+	err = mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_MAC_23,
 				  (addr[2] << 8) | addr[3]);
 	if (err)
 		return err;
 
-	return mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_MAC_45,
+	return mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_MAC_45,
 				   (addr[4] << 8) | addr[5]);
 }
 
 static int mv88e6xxx_set_addr_indirect(struct dsa_switch *ds, u8 *addr)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int ret;
 	int i;
 
@@ -206,7 +286,7 @@ static int mv88e6xxx_set_addr_indirect(struct dsa_switch *ds, u8 *addr)
 		int j;
 
 		/* Write the MAC address byte. */
-		ret = mv88e6xxx_reg_write(ps, REG_GLOBAL2, GLOBAL2_SWITCH_MAC,
+		ret = mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_SWITCH_MAC,
 					  GLOBAL2_SWITCH_MAC_BUSY |
 					  (i << 8) | addr[i]);
 		if (ret)
@@ -214,7 +294,7 @@ static int mv88e6xxx_set_addr_indirect(struct dsa_switch *ds, u8 *addr)
 
 		/* Wait for the write to complete. */
 		for (j = 0; j < 16; j++) {
-			ret = mv88e6xxx_reg_read(ps, REG_GLOBAL2,
+			ret = mv88e6xxx_reg_read(chip, REG_GLOBAL2,
 						 GLOBAL2_SWITCH_MAC);
 			if (ret < 0)
 				return ret;
@@ -229,49 +309,49 @@ static int mv88e6xxx_set_addr_indirect(struct dsa_switch *ds, u8 *addr)
 	return 0;
 }
 
-int mv88e6xxx_set_addr(struct dsa_switch *ds, u8 *addr)
+static int mv88e6xxx_set_addr(struct dsa_switch *ds, u8 *addr)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 
-	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_SWITCH_MAC))
+	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_SWITCH_MAC))
 		return mv88e6xxx_set_addr_indirect(ds, addr);
 	else
 		return mv88e6xxx_set_addr_direct(ds, addr);
 }
 
-static int mv88e6xxx_mdio_read_direct(struct mv88e6xxx_priv_state *ps,
+static int mv88e6xxx_mdio_read_direct(struct mv88e6xxx_chip *chip,
 				      int addr, int regnum)
 {
 	if (addr >= 0)
-		return _mv88e6xxx_reg_read(ps, addr, regnum);
+		return _mv88e6xxx_reg_read(chip, addr, regnum);
 	return 0xffff;
 }
 
-static int mv88e6xxx_mdio_write_direct(struct mv88e6xxx_priv_state *ps,
+static int mv88e6xxx_mdio_write_direct(struct mv88e6xxx_chip *chip,
 				       int addr, int regnum, u16 val)
 {
 	if (addr >= 0)
-		return _mv88e6xxx_reg_write(ps, addr, regnum, val);
+		return _mv88e6xxx_reg_write(chip, addr, regnum, val);
 	return 0;
 }
 
-static int mv88e6xxx_ppu_disable(struct mv88e6xxx_priv_state *ps)
+static int mv88e6xxx_ppu_disable(struct mv88e6xxx_chip *chip)
 {
 	int ret;
 	unsigned long timeout;
 
-	ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_CONTROL);
+	ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_CONTROL);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_CONTROL,
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_CONTROL,
 				   ret & ~GLOBAL_CONTROL_PPU_ENABLE);
 	if (ret)
 		return ret;
 
 	timeout = jiffies + 1 * HZ;
 	while (time_before(jiffies, timeout)) {
-		ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_STATUS);
+		ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_STATUS);
 		if (ret < 0)
 			return ret;
 
@@ -284,23 +364,23 @@ static int mv88e6xxx_ppu_disable(struct mv88e6xxx_priv_state *ps)
 	return -ETIMEDOUT;
 }
 
-static int mv88e6xxx_ppu_enable(struct mv88e6xxx_priv_state *ps)
+static int mv88e6xxx_ppu_enable(struct mv88e6xxx_chip *chip)
 {
 	int ret, err;
 	unsigned long timeout;
 
-	ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_CONTROL);
+	ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_CONTROL);
 	if (ret < 0)
 		return ret;
 
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_CONTROL,
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_CONTROL,
 				   ret | GLOBAL_CONTROL_PPU_ENABLE);
 	if (err)
 		return err;
 
 	timeout = jiffies + 1 * HZ;
 	while (time_before(jiffies, timeout)) {
-		ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_STATUS);
+		ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_STATUS);
 		if (ret < 0)
 			return ret;
 
@@ -315,148 +395,148 @@ static int mv88e6xxx_ppu_enable(struct mv88e6xxx_priv_state *ps)
 
 static void mv88e6xxx_ppu_reenable_work(struct work_struct *ugly)
 {
-	struct mv88e6xxx_priv_state *ps;
+	struct mv88e6xxx_chip *chip;
 
-	ps = container_of(ugly, struct mv88e6xxx_priv_state, ppu_work);
+	chip = container_of(ugly, struct mv88e6xxx_chip, ppu_work);
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	if (mutex_trylock(&ps->ppu_mutex)) {
-		if (mv88e6xxx_ppu_enable(ps) == 0)
-			ps->ppu_disabled = 0;
-		mutex_unlock(&ps->ppu_mutex);
+	if (mutex_trylock(&chip->ppu_mutex)) {
+		if (mv88e6xxx_ppu_enable(chip) == 0)
+			chip->ppu_disabled = 0;
+		mutex_unlock(&chip->ppu_mutex);
 	}
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 }
 
 static void mv88e6xxx_ppu_reenable_timer(unsigned long _ps)
 {
-	struct mv88e6xxx_priv_state *ps = (void *)_ps;
+	struct mv88e6xxx_chip *chip = (void *)_ps;
 
-	schedule_work(&ps->ppu_work);
+	schedule_work(&chip->ppu_work);
 }
 
-static int mv88e6xxx_ppu_access_get(struct mv88e6xxx_priv_state *ps)
+static int mv88e6xxx_ppu_access_get(struct mv88e6xxx_chip *chip)
 {
 	int ret;
 
-	mutex_lock(&ps->ppu_mutex);
+	mutex_lock(&chip->ppu_mutex);
 
 	/* If the PHY polling unit is enabled, disable it so that
 	 * we can access the PHY registers.  If it was already
 	 * disabled, cancel the timer that is going to re-enable
 	 * it.
 	 */
-	if (!ps->ppu_disabled) {
-		ret = mv88e6xxx_ppu_disable(ps);
+	if (!chip->ppu_disabled) {
+		ret = mv88e6xxx_ppu_disable(chip);
 		if (ret < 0) {
-			mutex_unlock(&ps->ppu_mutex);
+			mutex_unlock(&chip->ppu_mutex);
 			return ret;
 		}
-		ps->ppu_disabled = 1;
+		chip->ppu_disabled = 1;
 	} else {
-		del_timer(&ps->ppu_timer);
+		del_timer(&chip->ppu_timer);
 		ret = 0;
 	}
 
 	return ret;
 }
 
-static void mv88e6xxx_ppu_access_put(struct mv88e6xxx_priv_state *ps)
+static void mv88e6xxx_ppu_access_put(struct mv88e6xxx_chip *chip)
 {
 	/* Schedule a timer to re-enable the PHY polling unit. */
-	mod_timer(&ps->ppu_timer, jiffies + msecs_to_jiffies(10));
-	mutex_unlock(&ps->ppu_mutex);
+	mod_timer(&chip->ppu_timer, jiffies + msecs_to_jiffies(10));
+	mutex_unlock(&chip->ppu_mutex);
 }
 
-void mv88e6xxx_ppu_state_init(struct mv88e6xxx_priv_state *ps)
+static void mv88e6xxx_ppu_state_init(struct mv88e6xxx_chip *chip)
 {
-	mutex_init(&ps->ppu_mutex);
-	INIT_WORK(&ps->ppu_work, mv88e6xxx_ppu_reenable_work);
-	init_timer(&ps->ppu_timer);
-	ps->ppu_timer.data = (unsigned long)ps;
-	ps->ppu_timer.function = mv88e6xxx_ppu_reenable_timer;
+	mutex_init(&chip->ppu_mutex);
+	INIT_WORK(&chip->ppu_work, mv88e6xxx_ppu_reenable_work);
+	init_timer(&chip->ppu_timer);
+	chip->ppu_timer.data = (unsigned long)chip;
+	chip->ppu_timer.function = mv88e6xxx_ppu_reenable_timer;
 }
 
-static int mv88e6xxx_mdio_read_ppu(struct mv88e6xxx_priv_state *ps, int addr,
+static int mv88e6xxx_mdio_read_ppu(struct mv88e6xxx_chip *chip, int addr,
 				   int regnum)
 {
 	int ret;
 
-	ret = mv88e6xxx_ppu_access_get(ps);
+	ret = mv88e6xxx_ppu_access_get(chip);
 	if (ret >= 0) {
-		ret = _mv88e6xxx_reg_read(ps, addr, regnum);
-		mv88e6xxx_ppu_access_put(ps);
+		ret = _mv88e6xxx_reg_read(chip, addr, regnum);
+		mv88e6xxx_ppu_access_put(chip);
 	}
 
 	return ret;
 }
 
-static int mv88e6xxx_mdio_write_ppu(struct mv88e6xxx_priv_state *ps, int addr,
+static int mv88e6xxx_mdio_write_ppu(struct mv88e6xxx_chip *chip, int addr,
 				    int regnum, u16 val)
 {
 	int ret;
 
-	ret = mv88e6xxx_ppu_access_get(ps);
+	ret = mv88e6xxx_ppu_access_get(chip);
 	if (ret >= 0) {
-		ret = _mv88e6xxx_reg_write(ps, addr, regnum, val);
-		mv88e6xxx_ppu_access_put(ps);
+		ret = _mv88e6xxx_reg_write(chip, addr, regnum, val);
+		mv88e6xxx_ppu_access_put(chip);
 	}
 
 	return ret;
 }
 
-static bool mv88e6xxx_6065_family(struct mv88e6xxx_priv_state *ps)
+static bool mv88e6xxx_6065_family(struct mv88e6xxx_chip *chip)
 {
-	return ps->info->family == MV88E6XXX_FAMILY_6065;
+	return chip->info->family == MV88E6XXX_FAMILY_6065;
 }
 
-static bool mv88e6xxx_6095_family(struct mv88e6xxx_priv_state *ps)
+static bool mv88e6xxx_6095_family(struct mv88e6xxx_chip *chip)
 {
-	return ps->info->family == MV88E6XXX_FAMILY_6095;
+	return chip->info->family == MV88E6XXX_FAMILY_6095;
 }
 
-static bool mv88e6xxx_6097_family(struct mv88e6xxx_priv_state *ps)
+static bool mv88e6xxx_6097_family(struct mv88e6xxx_chip *chip)
 {
-	return ps->info->family == MV88E6XXX_FAMILY_6097;
+	return chip->info->family == MV88E6XXX_FAMILY_6097;
 }
 
-static bool mv88e6xxx_6165_family(struct mv88e6xxx_priv_state *ps)
+static bool mv88e6xxx_6165_family(struct mv88e6xxx_chip *chip)
 {
-	return ps->info->family == MV88E6XXX_FAMILY_6165;
+	return chip->info->family == MV88E6XXX_FAMILY_6165;
 }
 
-static bool mv88e6xxx_6185_family(struct mv88e6xxx_priv_state *ps)
+static bool mv88e6xxx_6185_family(struct mv88e6xxx_chip *chip)
 {
-	return ps->info->family == MV88E6XXX_FAMILY_6185;
+	return chip->info->family == MV88E6XXX_FAMILY_6185;
 }
 
-static bool mv88e6xxx_6320_family(struct mv88e6xxx_priv_state *ps)
+static bool mv88e6xxx_6320_family(struct mv88e6xxx_chip *chip)
 {
-	return ps->info->family == MV88E6XXX_FAMILY_6320;
+	return chip->info->family == MV88E6XXX_FAMILY_6320;
 }
 
-static bool mv88e6xxx_6351_family(struct mv88e6xxx_priv_state *ps)
+static bool mv88e6xxx_6351_family(struct mv88e6xxx_chip *chip)
 {
-	return ps->info->family == MV88E6XXX_FAMILY_6351;
+	return chip->info->family == MV88E6XXX_FAMILY_6351;
 }
 
-static bool mv88e6xxx_6352_family(struct mv88e6xxx_priv_state *ps)
+static bool mv88e6xxx_6352_family(struct mv88e6xxx_chip *chip)
 {
-	return ps->info->family == MV88E6XXX_FAMILY_6352;
+	return chip->info->family == MV88E6XXX_FAMILY_6352;
 }
 
-static unsigned int mv88e6xxx_num_databases(struct mv88e6xxx_priv_state *ps)
+static unsigned int mv88e6xxx_num_databases(struct mv88e6xxx_chip *chip)
 {
-	return ps->info->num_databases;
+	return chip->info->num_databases;
 }
 
-static bool mv88e6xxx_has_fid_reg(struct mv88e6xxx_priv_state *ps)
+static bool mv88e6xxx_has_fid_reg(struct mv88e6xxx_chip *chip)
 {
 	/* Does the device have dedicated FID registers for ATU and VTU ops? */
-	if (mv88e6xxx_6097_family(ps) || mv88e6xxx_6165_family(ps) ||
-	    mv88e6xxx_6351_family(ps) || mv88e6xxx_6352_family(ps))
+	if (mv88e6xxx_6097_family(chip) || mv88e6xxx_6165_family(chip) ||
+	    mv88e6xxx_6351_family(chip) || mv88e6xxx_6352_family(chip))
 		return true;
 
 	return false;
@@ -469,16 +549,16 @@ static bool mv88e6xxx_has_fid_reg(struct mv88e6xxx_priv_state *ps)
 static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port,
 				  struct phy_device *phydev)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	u32 reg;
 	int ret;
 
 	if (!phy_is_pseudo_fixed_link(phydev))
 		return;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	ret = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_PCS_CTRL);
+	ret = _mv88e6xxx_reg_read(chip, REG_PORT(port), PORT_PCS_CTRL);
 	if (ret < 0)
 		goto out;
 
@@ -490,9 +570,9 @@ static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port,
 
 	reg |= PORT_PCS_CTRL_FORCE_LINK;
 	if (phydev->link)
-			reg |= PORT_PCS_CTRL_LINK_UP;
+		reg |= PORT_PCS_CTRL_LINK_UP;
 
-	if (mv88e6xxx_6065_family(ps) && phydev->speed > SPEED_100)
+	if (mv88e6xxx_6065_family(chip) && phydev->speed > SPEED_100)
 		goto out;
 
 	switch (phydev->speed) {
@@ -514,8 +594,8 @@ static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port,
 	if (phydev->duplex == DUPLEX_FULL)
 		reg |= PORT_PCS_CTRL_DUPLEX_FULL;
 
-	if ((mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps)) &&
-	    (port >= ps->info->num_ports - 2)) {
+	if ((mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip)) &&
+	    (port >= chip->info->num_ports - 2)) {
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
 			reg |= PORT_PCS_CTRL_RGMII_DELAY_RXCLK;
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
@@ -524,19 +604,19 @@ static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port,
 			reg |= (PORT_PCS_CTRL_RGMII_DELAY_RXCLK |
 				PORT_PCS_CTRL_RGMII_DELAY_TXCLK);
 	}
-	_mv88e6xxx_reg_write(ps, REG_PORT(port), PORT_PCS_CTRL, reg);
+	_mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_PCS_CTRL, reg);
 
 out:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 }
 
-static int _mv88e6xxx_stats_wait(struct mv88e6xxx_priv_state *ps)
+static int _mv88e6xxx_stats_wait(struct mv88e6xxx_chip *chip)
 {
 	int ret;
 	int i;
 
 	for (i = 0; i < 10; i++) {
-		ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_STATS_OP);
+		ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_STATS_OP);
 		if ((ret & GLOBAL_STATS_OP_BUSY) == 0)
 			return 0;
 	}
@@ -544,30 +624,29 @@ static int _mv88e6xxx_stats_wait(struct mv88e6xxx_priv_state *ps)
 	return -ETIMEDOUT;
 }
 
-static int _mv88e6xxx_stats_snapshot(struct mv88e6xxx_priv_state *ps,
-				     int port)
+static int _mv88e6xxx_stats_snapshot(struct mv88e6xxx_chip *chip, int port)
 {
 	int ret;
 
-	if (mv88e6xxx_6320_family(ps) || mv88e6xxx_6352_family(ps))
+	if (mv88e6xxx_6320_family(chip) || mv88e6xxx_6352_family(chip))
 		port = (port + 1) << 5;
 
 	/* Snapshot the hardware statistics counters for this port. */
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_STATS_OP,
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_STATS_OP,
 				   GLOBAL_STATS_OP_CAPTURE_PORT |
 				   GLOBAL_STATS_OP_HIST_RX_TX | port);
 	if (ret < 0)
 		return ret;
 
 	/* Wait for the snapshotting to complete. */
-	ret = _mv88e6xxx_stats_wait(ps);
+	ret = _mv88e6xxx_stats_wait(chip);
 	if (ret < 0)
 		return ret;
 
 	return 0;
 }
 
-static void _mv88e6xxx_stats_read(struct mv88e6xxx_priv_state *ps,
+static void _mv88e6xxx_stats_read(struct mv88e6xxx_chip *chip,
 				  int stat, u32 *val)
 {
 	u32 _val;
@@ -575,23 +654,23 @@ static void _mv88e6xxx_stats_read(struct mv88e6xxx_priv_state *ps,
 
 	*val = 0;
 
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_STATS_OP,
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_STATS_OP,
 				   GLOBAL_STATS_OP_READ_CAPTURED |
 				   GLOBAL_STATS_OP_HIST_RX_TX | stat);
 	if (ret < 0)
 		return;
 
-	ret = _mv88e6xxx_stats_wait(ps);
+	ret = _mv88e6xxx_stats_wait(chip);
 	if (ret < 0)
 		return;
 
-	ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_STATS_COUNTER_32);
+	ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_STATS_COUNTER_32);
 	if (ret < 0)
 		return;
 
 	_val = ret << 16;
 
-	ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_STATS_COUNTER_01);
+	ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_STATS_COUNTER_01);
 	if (ret < 0)
 		return;
 
@@ -660,26 +739,26 @@ static struct mv88e6xxx_hw_stat mv88e6xxx_hw_stats[] = {
 	{ "out_management",	4, 0x1f | GLOBAL_STATS_OP_BANK_1, BANK1, },
 };
 
-static bool mv88e6xxx_has_stat(struct mv88e6xxx_priv_state *ps,
+static bool mv88e6xxx_has_stat(struct mv88e6xxx_chip *chip,
 			       struct mv88e6xxx_hw_stat *stat)
 {
 	switch (stat->type) {
 	case BANK0:
 		return true;
 	case BANK1:
-		return mv88e6xxx_6320_family(ps);
+		return mv88e6xxx_6320_family(chip);
 	case PORT:
-		return mv88e6xxx_6095_family(ps) ||
-			mv88e6xxx_6185_family(ps) ||
-			mv88e6xxx_6097_family(ps) ||
-			mv88e6xxx_6165_family(ps) ||
-			mv88e6xxx_6351_family(ps) ||
-			mv88e6xxx_6352_family(ps);
+		return mv88e6xxx_6095_family(chip) ||
+			mv88e6xxx_6185_family(chip) ||
+			mv88e6xxx_6097_family(chip) ||
+			mv88e6xxx_6165_family(chip) ||
+			mv88e6xxx_6351_family(chip) ||
+			mv88e6xxx_6352_family(chip);
 	}
 	return false;
 }
 
-static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_priv_state *ps,
+static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip,
 					    struct mv88e6xxx_hw_stat *s,
 					    int port)
 {
@@ -690,13 +769,13 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_priv_state *ps,
 
 	switch (s->type) {
 	case PORT:
-		ret = _mv88e6xxx_reg_read(ps, REG_PORT(port), s->reg);
+		ret = _mv88e6xxx_reg_read(chip, REG_PORT(port), s->reg);
 		if (ret < 0)
 			return UINT64_MAX;
 
 		low = ret;
 		if (s->sizeof_stat == 4) {
-			ret = _mv88e6xxx_reg_read(ps, REG_PORT(port),
+			ret = _mv88e6xxx_reg_read(chip, REG_PORT(port),
 						  s->reg + 1);
 			if (ret < 0)
 				return UINT64_MAX;
@@ -705,9 +784,9 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_priv_state *ps,
 		break;
 	case BANK0:
 	case BANK1:
-		_mv88e6xxx_stats_read(ps, s->reg, &low);
+		_mv88e6xxx_stats_read(chip, s->reg, &low);
 		if (s->sizeof_stat == 8)
-			_mv88e6xxx_stats_read(ps, s->reg + 1, &high);
+			_mv88e6xxx_stats_read(chip, s->reg + 1, &high);
 	}
 	value = (((u64)high) << 16) | low;
 	return value;
@@ -716,13 +795,13 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_priv_state *ps,
 static void mv88e6xxx_get_strings(struct dsa_switch *ds, int port,
 				  uint8_t *data)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	struct mv88e6xxx_hw_stat *stat;
 	int i, j;
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) {
 		stat = &mv88e6xxx_hw_stats[i];
-		if (mv88e6xxx_has_stat(ps, stat)) {
+		if (mv88e6xxx_has_stat(chip, stat)) {
 			memcpy(data + j * ETH_GSTRING_LEN, stat->string,
 			       ETH_GSTRING_LEN);
 			j++;
@@ -732,13 +811,13 @@ static void mv88e6xxx_get_strings(struct dsa_switch *ds, int port,
 
 static int mv88e6xxx_get_sset_count(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	struct mv88e6xxx_hw_stat *stat;
 	int i, j;
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) {
 		stat = &mv88e6xxx_hw_stats[i];
-		if (mv88e6xxx_has_stat(ps, stat))
+		if (mv88e6xxx_has_stat(chip, stat))
 			j++;
 	}
 	return j;
@@ -747,27 +826,27 @@ static int mv88e6xxx_get_sset_count(struct dsa_switch *ds)
 static void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds, int port,
 					uint64_t *data)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	struct mv88e6xxx_hw_stat *stat;
 	int ret;
 	int i, j;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	ret = _mv88e6xxx_stats_snapshot(ps, port);
+	ret = _mv88e6xxx_stats_snapshot(chip, port);
 	if (ret < 0) {
-		mutex_unlock(&ps->smi_mutex);
+		mutex_unlock(&chip->reg_lock);
 		return;
 	}
 	for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) {
 		stat = &mv88e6xxx_hw_stats[i];
-		if (mv88e6xxx_has_stat(ps, stat)) {
-			data[j] = _mv88e6xxx_get_ethtool_stat(ps, stat, port);
+		if (mv88e6xxx_has_stat(chip, stat)) {
+			data[j] = _mv88e6xxx_get_ethtool_stat(chip, stat, port);
 			j++;
 		}
 	}
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 }
 
 static int mv88e6xxx_get_regs_len(struct dsa_switch *ds, int port)
@@ -778,7 +857,7 @@ static int mv88e6xxx_get_regs_len(struct dsa_switch *ds, int port)
 static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port,
 			       struct ethtool_regs *regs, void *_p)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	u16 *p = _p;
 	int i;
 
@@ -786,20 +865,20 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port,
 
 	memset(p, 0xff, 32 * sizeof(u16));
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
 	for (i = 0; i < 32; i++) {
 		int ret;
 
-		ret = _mv88e6xxx_reg_read(ps, REG_PORT(port), i);
+		ret = _mv88e6xxx_reg_read(chip, REG_PORT(port), i);
 		if (ret >= 0)
 			p[i] = ret;
 	}
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 }
 
-static int _mv88e6xxx_wait(struct mv88e6xxx_priv_state *ps, int reg, int offset,
+static int _mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int reg, int offset,
 			   u16 mask)
 {
 	unsigned long timeout = jiffies + HZ / 10;
@@ -807,7 +886,7 @@ static int _mv88e6xxx_wait(struct mv88e6xxx_priv_state *ps, int reg, int offset,
 	while (time_before(jiffies, timeout)) {
 		int ret;
 
-		ret = _mv88e6xxx_reg_read(ps, reg, offset);
+		ret = _mv88e6xxx_reg_read(chip, reg, offset);
 		if (ret < 0)
 			return ret;
 		if (!(ret & mask))
@@ -818,48 +897,48 @@ static int _mv88e6xxx_wait(struct mv88e6xxx_priv_state *ps, int reg, int offset,
 	return -ETIMEDOUT;
 }
 
-static int mv88e6xxx_wait(struct mv88e6xxx_priv_state *ps, int reg,
+static int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int reg,
 			  int offset, u16 mask)
 {
 	int ret;
 
-	mutex_lock(&ps->smi_mutex);
-	ret = _mv88e6xxx_wait(ps, reg, offset, mask);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
+	ret = _mv88e6xxx_wait(chip, reg, offset, mask);
+	mutex_unlock(&chip->reg_lock);
 
 	return ret;
 }
 
-static int mv88e6xxx_mdio_wait(struct mv88e6xxx_priv_state *ps)
+static int mv88e6xxx_mdio_wait(struct mv88e6xxx_chip *chip)
 {
-	return _mv88e6xxx_wait(ps, REG_GLOBAL2, GLOBAL2_SMI_OP,
+	return _mv88e6xxx_wait(chip, REG_GLOBAL2, GLOBAL2_SMI_OP,
 			       GLOBAL2_SMI_OP_BUSY);
 }
 
 static int mv88e6xxx_eeprom_load_wait(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 
-	return mv88e6xxx_wait(ps, REG_GLOBAL2, GLOBAL2_EEPROM_OP,
+	return mv88e6xxx_wait(chip, REG_GLOBAL2, GLOBAL2_EEPROM_OP,
 			      GLOBAL2_EEPROM_OP_LOAD);
 }
 
 static int mv88e6xxx_eeprom_busy_wait(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 
-	return mv88e6xxx_wait(ps, REG_GLOBAL2, GLOBAL2_EEPROM_OP,
+	return mv88e6xxx_wait(chip, REG_GLOBAL2, GLOBAL2_EEPROM_OP,
 			      GLOBAL2_EEPROM_OP_BUSY);
 }
 
 static int mv88e6xxx_read_eeprom_word(struct dsa_switch *ds, int addr)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int ret;
 
-	mutex_lock(&ps->eeprom_mutex);
+	mutex_lock(&chip->eeprom_mutex);
 
-	ret = mv88e6xxx_reg_write(ps, REG_GLOBAL2, GLOBAL2_EEPROM_OP,
+	ret = mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_EEPROM_OP,
 				  GLOBAL2_EEPROM_OP_READ |
 				  (addr & GLOBAL2_EEPROM_OP_ADDR_MASK));
 	if (ret < 0)
@@ -869,18 +948,18 @@ static int mv88e6xxx_read_eeprom_word(struct dsa_switch *ds, int addr)
 	if (ret < 0)
 		goto error;
 
-	ret = mv88e6xxx_reg_read(ps, REG_GLOBAL2, GLOBAL2_EEPROM_DATA);
+	ret = mv88e6xxx_reg_read(chip, REG_GLOBAL2, GLOBAL2_EEPROM_DATA);
 error:
-	mutex_unlock(&ps->eeprom_mutex);
+	mutex_unlock(&chip->eeprom_mutex);
 	return ret;
 }
 
 static int mv88e6xxx_get_eeprom_len(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 
-	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_EEPROM))
-		return ps->eeprom_len;
+	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEPROM))
+		return chip->eeprom_len;
 
 	return 0;
 }
@@ -888,12 +967,12 @@ static int mv88e6xxx_get_eeprom_len(struct dsa_switch *ds)
 static int mv88e6xxx_get_eeprom(struct dsa_switch *ds,
 				struct ethtool_eeprom *eeprom, u8 *data)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int offset;
 	int len;
 	int ret;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_EEPROM))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEPROM))
 		return -EOPNOTSUPP;
 
 	offset = eeprom->offset;
@@ -954,10 +1033,10 @@ static int mv88e6xxx_get_eeprom(struct dsa_switch *ds,
 
 static int mv88e6xxx_eeprom_is_readonly(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int ret;
 
-	ret = mv88e6xxx_reg_read(ps, REG_GLOBAL2, GLOBAL2_EEPROM_OP);
+	ret = mv88e6xxx_reg_read(chip, REG_GLOBAL2, GLOBAL2_EEPROM_OP);
 	if (ret < 0)
 		return ret;
 
@@ -970,16 +1049,16 @@ static int mv88e6xxx_eeprom_is_readonly(struct dsa_switch *ds)
 static int mv88e6xxx_write_eeprom_word(struct dsa_switch *ds, int addr,
 				       u16 data)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int ret;
 
-	mutex_lock(&ps->eeprom_mutex);
+	mutex_lock(&chip->eeprom_mutex);
 
-	ret = mv88e6xxx_reg_write(ps, REG_GLOBAL2, GLOBAL2_EEPROM_DATA, data);
+	ret = mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_EEPROM_DATA, data);
 	if (ret < 0)
 		goto error;
 
-	ret = mv88e6xxx_reg_write(ps, REG_GLOBAL2, GLOBAL2_EEPROM_OP,
+	ret = mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_EEPROM_OP,
 				  GLOBAL2_EEPROM_OP_WRITE |
 				  (addr & GLOBAL2_EEPROM_OP_ADDR_MASK));
 	if (ret < 0)
@@ -987,19 +1066,19 @@ static int mv88e6xxx_write_eeprom_word(struct dsa_switch *ds, int addr,
 
 	ret = mv88e6xxx_eeprom_busy_wait(ds);
 error:
-	mutex_unlock(&ps->eeprom_mutex);
+	mutex_unlock(&chip->eeprom_mutex);
 	return ret;
 }
 
 static int mv88e6xxx_set_eeprom(struct dsa_switch *ds,
 				struct ethtool_eeprom *eeprom, u8 *data)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int offset;
 	int ret;
 	int len;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_EEPROM))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEPROM))
 		return -EOPNOTSUPP;
 
 	if (eeprom->magic != 0xc3ec4951)
@@ -1071,67 +1150,67 @@ static int mv88e6xxx_set_eeprom(struct dsa_switch *ds,
 	return 0;
 }
 
-static int _mv88e6xxx_atu_wait(struct mv88e6xxx_priv_state *ps)
+static int _mv88e6xxx_atu_wait(struct mv88e6xxx_chip *chip)
 {
-	return _mv88e6xxx_wait(ps, REG_GLOBAL, GLOBAL_ATU_OP,
+	return _mv88e6xxx_wait(chip, REG_GLOBAL, GLOBAL_ATU_OP,
 			       GLOBAL_ATU_OP_BUSY);
 }
 
-static int mv88e6xxx_mdio_read_indirect(struct mv88e6xxx_priv_state *ps,
+static int mv88e6xxx_mdio_read_indirect(struct mv88e6xxx_chip *chip,
 					int addr, int regnum)
 {
 	int ret;
 
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL2, GLOBAL2_SMI_OP,
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_SMI_OP,
 				   GLOBAL2_SMI_OP_22_READ | (addr << 5) |
 				   regnum);
 	if (ret < 0)
 		return ret;
 
-	ret = mv88e6xxx_mdio_wait(ps);
+	ret = mv88e6xxx_mdio_wait(chip);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL2, GLOBAL2_SMI_DATA);
+	ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL2, GLOBAL2_SMI_DATA);
 
 	return ret;
 }
 
-static int mv88e6xxx_mdio_write_indirect(struct mv88e6xxx_priv_state *ps,
+static int mv88e6xxx_mdio_write_indirect(struct mv88e6xxx_chip *chip,
 					 int addr, int regnum, u16 val)
 {
 	int ret;
 
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL2, GLOBAL2_SMI_DATA, val);
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_SMI_DATA, val);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL2, GLOBAL2_SMI_OP,
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_SMI_OP,
 				   GLOBAL2_SMI_OP_22_WRITE | (addr << 5) |
 				   regnum);
 
-	return mv88e6xxx_mdio_wait(ps);
+	return mv88e6xxx_mdio_wait(chip);
 }
 
 static int mv88e6xxx_get_eee(struct dsa_switch *ds, int port,
 			     struct ethtool_eee *e)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int reg;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_EEE))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEE))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	reg = mv88e6xxx_mdio_read_indirect(ps, port, 16);
+	reg = mv88e6xxx_mdio_read_indirect(chip, port, 16);
 	if (reg < 0)
 		goto out;
 
 	e->eee_enabled = !!(reg & 0x0200);
 	e->tx_lpi_enabled = !!(reg & 0x0100);
 
-	reg = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_STATUS);
+	reg = _mv88e6xxx_reg_read(chip, REG_PORT(port), PORT_STATUS);
 	if (reg < 0)
 		goto out;
 
@@ -1139,23 +1218,23 @@ static int mv88e6xxx_get_eee(struct dsa_switch *ds, int port,
 	reg = 0;
 
 out:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 	return reg;
 }
 
 static int mv88e6xxx_set_eee(struct dsa_switch *ds, int port,
 			     struct phy_device *phydev, struct ethtool_eee *e)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int reg;
 	int ret;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_EEE))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEE))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	ret = mv88e6xxx_mdio_read_indirect(ps, port, 16);
+	ret = mv88e6xxx_mdio_read_indirect(chip, port, 16);
 	if (ret < 0)
 		goto out;
 
@@ -1165,28 +1244,29 @@ static int mv88e6xxx_set_eee(struct dsa_switch *ds, int port,
 	if (e->tx_lpi_enabled)
 		reg |= 0x0100;
 
-	ret = mv88e6xxx_mdio_write_indirect(ps, port, 16, reg);
+	ret = mv88e6xxx_mdio_write_indirect(chip, port, 16, reg);
 out:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 
 	return ret;
 }
 
-static int _mv88e6xxx_atu_cmd(struct mv88e6xxx_priv_state *ps, u16 fid, u16 cmd)
+static int _mv88e6xxx_atu_cmd(struct mv88e6xxx_chip *chip, u16 fid, u16 cmd)
 {
 	int ret;
 
-	if (mv88e6xxx_has_fid_reg(ps)) {
-		ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_ATU_FID, fid);
+	if (mv88e6xxx_has_fid_reg(chip)) {
+		ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_ATU_FID,
+					   fid);
 		if (ret < 0)
 			return ret;
-	} else if (mv88e6xxx_num_databases(ps) == 256) {
+	} else if (mv88e6xxx_num_databases(chip) == 256) {
 		/* ATU DBNum[7:4] are located in ATU Control 15:12 */
-		ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_ATU_CONTROL);
+		ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_ATU_CONTROL);
 		if (ret < 0)
 			return ret;
 
-		ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_ATU_CONTROL,
+		ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_ATU_CONTROL,
 					   (ret & 0xfff) |
 					   ((fid << 8) & 0xf000));
 		if (ret < 0)
@@ -1196,14 +1276,14 @@ static int _mv88e6xxx_atu_cmd(struct mv88e6xxx_priv_state *ps, u16 fid, u16 cmd)
 		cmd |= fid & 0xf;
 	}
 
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_ATU_OP, cmd);
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_ATU_OP, cmd);
 	if (ret < 0)
 		return ret;
 
-	return _mv88e6xxx_atu_wait(ps);
+	return _mv88e6xxx_atu_wait(chip);
 }
 
-static int _mv88e6xxx_atu_data_write(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_atu_data_write(struct mv88e6xxx_chip *chip,
 				     struct mv88e6xxx_atu_entry *entry)
 {
 	u16 data = entry->state & GLOBAL_ATU_DATA_STATE_MASK;
@@ -1223,21 +1303,21 @@ static int _mv88e6xxx_atu_data_write(struct mv88e6xxx_priv_state *ps,
 		data |= (entry->portv_trunkid << shift) & mask;
 	}
 
-	return _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_ATU_DATA, data);
+	return _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_ATU_DATA, data);
 }
 
-static int _mv88e6xxx_atu_flush_move(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_atu_flush_move(struct mv88e6xxx_chip *chip,
 				     struct mv88e6xxx_atu_entry *entry,
 				     bool static_too)
 {
 	int op;
 	int err;
 
-	err = _mv88e6xxx_atu_wait(ps);
+	err = _mv88e6xxx_atu_wait(chip);
 	if (err)
 		return err;
 
-	err = _mv88e6xxx_atu_data_write(ps, entry);
+	err = _mv88e6xxx_atu_data_write(chip, entry);
 	if (err)
 		return err;
 
@@ -1249,10 +1329,10 @@ static int _mv88e6xxx_atu_flush_move(struct mv88e6xxx_priv_state *ps,
 			GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC;
 	}
 
-	return _mv88e6xxx_atu_cmd(ps, entry->fid, op);
+	return _mv88e6xxx_atu_cmd(chip, entry->fid, op);
 }
 
-static int _mv88e6xxx_atu_flush(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_atu_flush(struct mv88e6xxx_chip *chip,
 				u16 fid, bool static_too)
 {
 	struct mv88e6xxx_atu_entry entry = {
@@ -1260,10 +1340,10 @@ static int _mv88e6xxx_atu_flush(struct mv88e6xxx_priv_state *ps,
 		.state = 0, /* EntryState bits must be 0 */
 	};
 
-	return _mv88e6xxx_atu_flush_move(ps, &entry, static_too);
+	return _mv88e6xxx_atu_flush_move(chip, &entry, static_too);
 }
 
-static int _mv88e6xxx_atu_move(struct mv88e6xxx_priv_state *ps, u16 fid,
+static int _mv88e6xxx_atu_move(struct mv88e6xxx_chip *chip, u16 fid,
 			       int from_port, int to_port, bool static_too)
 {
 	struct mv88e6xxx_atu_entry entry = {
@@ -1278,14 +1358,14 @@ static int _mv88e6xxx_atu_move(struct mv88e6xxx_priv_state *ps, u16 fid,
 	entry.portv_trunkid = (to_port & 0x0f) << 4;
 	entry.portv_trunkid |= from_port & 0x0f;
 
-	return _mv88e6xxx_atu_flush_move(ps, &entry, static_too);
+	return _mv88e6xxx_atu_flush_move(chip, &entry, static_too);
 }
 
-static int _mv88e6xxx_atu_remove(struct mv88e6xxx_priv_state *ps, u16 fid,
+static int _mv88e6xxx_atu_remove(struct mv88e6xxx_chip *chip, u16 fid,
 				 int port, bool static_too)
 {
 	/* Destination port 0xF means remove the entries */
-	return _mv88e6xxx_atu_move(ps, fid, port, 0x0f, static_too);
+	return _mv88e6xxx_atu_move(chip, fid, port, 0x0f, static_too);
 }
 
 static const char * const mv88e6xxx_port_state_names[] = {
@@ -1295,14 +1375,14 @@ static const char * const mv88e6xxx_port_state_names[] = {
 	[PORT_CONTROL_STATE_FORWARDING] = "Forwarding",
 };
 
-static int _mv88e6xxx_port_state(struct mv88e6xxx_priv_state *ps, int port,
+static int _mv88e6xxx_port_state(struct mv88e6xxx_chip *chip, int port,
 				 u8 state)
 {
-	struct dsa_switch *ds = ps->ds;
+	struct dsa_switch *ds = chip->ds;
 	int reg, ret = 0;
 	u8 oldstate;
 
-	reg = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_CONTROL);
+	reg = _mv88e6xxx_reg_read(chip, REG_PORT(port), PORT_CONTROL);
 	if (reg < 0)
 		return reg;
 
@@ -1314,16 +1394,16 @@ static int _mv88e6xxx_port_state(struct mv88e6xxx_priv_state *ps, int port,
 		 * Blocking or Listening state.
 		 */
 		if ((oldstate == PORT_CONTROL_STATE_LEARNING ||
-		     oldstate == PORT_CONTROL_STATE_FORWARDING)
-		    && (state == PORT_CONTROL_STATE_DISABLED ||
-			state == PORT_CONTROL_STATE_BLOCKING)) {
-			ret = _mv88e6xxx_atu_remove(ps, 0, port, false);
+		     oldstate == PORT_CONTROL_STATE_FORWARDING) &&
+		    (state == PORT_CONTROL_STATE_DISABLED ||
+		     state == PORT_CONTROL_STATE_BLOCKING)) {
+			ret = _mv88e6xxx_atu_remove(chip, 0, port, false);
 			if (ret)
 				return ret;
 		}
 
 		reg = (reg & ~PORT_CONTROL_STATE_MASK) | state;
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port), PORT_CONTROL,
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_CONTROL,
 					   reg);
 		if (ret)
 			return ret;
@@ -1336,12 +1416,11 @@ static int _mv88e6xxx_port_state(struct mv88e6xxx_priv_state *ps, int port,
 	return ret;
 }
 
-static int _mv88e6xxx_port_based_vlan_map(struct mv88e6xxx_priv_state *ps,
-					  int port)
+static int _mv88e6xxx_port_based_vlan_map(struct mv88e6xxx_chip *chip, int port)
 {
-	struct net_device *bridge = ps->ports[port].bridge_dev;
-	const u16 mask = (1 << ps->info->num_ports) - 1;
-	struct dsa_switch *ds = ps->ds;
+	struct net_device *bridge = chip->ports[port].bridge_dev;
+	const u16 mask = (1 << chip->info->num_ports) - 1;
+	struct dsa_switch *ds = chip->ds;
 	u16 output_ports = 0;
 	int reg;
 	int i;
@@ -1350,9 +1429,9 @@ static int _mv88e6xxx_port_based_vlan_map(struct mv88e6xxx_priv_state *ps,
 	if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) {
 		output_ports = mask;
 	} else {
-		for (i = 0; i < ps->info->num_ports; ++i) {
+		for (i = 0; i < chip->info->num_ports; ++i) {
 			/* allow sending frames to every group member */
-			if (bridge && ps->ports[i].bridge_dev == bridge)
+			if (bridge && chip->ports[i].bridge_dev == bridge)
 				output_ports |= BIT(i);
 
 			/* allow sending frames to CPU port and DSA link(s) */
@@ -1364,24 +1443,24 @@ static int _mv88e6xxx_port_based_vlan_map(struct mv88e6xxx_priv_state *ps,
 	/* prevent frames from going back out of the port they came in on */
 	output_ports &= ~BIT(port);
 
-	reg = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_BASE_VLAN);
+	reg = _mv88e6xxx_reg_read(chip, REG_PORT(port), PORT_BASE_VLAN);
 	if (reg < 0)
 		return reg;
 
 	reg &= ~mask;
 	reg |= output_ports & mask;
 
-	return _mv88e6xxx_reg_write(ps, REG_PORT(port), PORT_BASE_VLAN, reg);
+	return _mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_BASE_VLAN, reg);
 }
 
 static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port,
 					 u8 state)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int stp_state;
 	int err;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_PORTSTATE))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_PORTSTATE))
 		return;
 
 	switch (state) {
@@ -1401,9 +1480,9 @@ static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port,
 		break;
 	}
 
-	mutex_lock(&ps->smi_mutex);
-	err = _mv88e6xxx_port_state(ps, port, stp_state);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
+	err = _mv88e6xxx_port_state(chip, port, stp_state);
+	mutex_unlock(&chip->reg_lock);
 
 	if (err)
 		netdev_err(ds->ports[port].netdev,
@@ -1411,14 +1490,14 @@ static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port,
 			   mv88e6xxx_port_state_names[stp_state]);
 }
 
-static int _mv88e6xxx_port_pvid(struct mv88e6xxx_priv_state *ps, int port,
+static int _mv88e6xxx_port_pvid(struct mv88e6xxx_chip *chip, int port,
 				u16 *new, u16 *old)
 {
-	struct dsa_switch *ds = ps->ds;
+	struct dsa_switch *ds = chip->ds;
 	u16 pvid;
 	int ret;
 
-	ret = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_DEFAULT_VLAN);
+	ret = _mv88e6xxx_reg_read(chip, REG_PORT(port), PORT_DEFAULT_VLAN);
 	if (ret < 0)
 		return ret;
 
@@ -1428,7 +1507,7 @@ static int _mv88e6xxx_port_pvid(struct mv88e6xxx_priv_state *ps, int port,
 		ret &= ~PORT_DEFAULT_VLAN_MASK;
 		ret |= *new & PORT_DEFAULT_VLAN_MASK;
 
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port),
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_DEFAULT_VLAN, ret);
 		if (ret < 0)
 			return ret;
@@ -1443,47 +1522,47 @@ static int _mv88e6xxx_port_pvid(struct mv88e6xxx_priv_state *ps, int port,
 	return 0;
 }
 
-static int _mv88e6xxx_port_pvid_get(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_port_pvid_get(struct mv88e6xxx_chip *chip,
 				    int port, u16 *pvid)
 {
-	return _mv88e6xxx_port_pvid(ps, port, NULL, pvid);
+	return _mv88e6xxx_port_pvid(chip, port, NULL, pvid);
 }
 
-static int _mv88e6xxx_port_pvid_set(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_port_pvid_set(struct mv88e6xxx_chip *chip,
 				    int port, u16 pvid)
 {
-	return _mv88e6xxx_port_pvid(ps, port, &pvid, NULL);
+	return _mv88e6xxx_port_pvid(chip, port, &pvid, NULL);
 }
 
-static int _mv88e6xxx_vtu_wait(struct mv88e6xxx_priv_state *ps)
+static int _mv88e6xxx_vtu_wait(struct mv88e6xxx_chip *chip)
 {
-	return _mv88e6xxx_wait(ps, REG_GLOBAL, GLOBAL_VTU_OP,
+	return _mv88e6xxx_wait(chip, REG_GLOBAL, GLOBAL_VTU_OP,
 			       GLOBAL_VTU_OP_BUSY);
 }
 
-static int _mv88e6xxx_vtu_cmd(struct mv88e6xxx_priv_state *ps, u16 op)
+static int _mv88e6xxx_vtu_cmd(struct mv88e6xxx_chip *chip, u16 op)
 {
 	int ret;
 
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_VTU_OP, op);
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_VTU_OP, op);
 	if (ret < 0)
 		return ret;
 
-	return _mv88e6xxx_vtu_wait(ps);
+	return _mv88e6xxx_vtu_wait(chip);
 }
 
-static int _mv88e6xxx_vtu_stu_flush(struct mv88e6xxx_priv_state *ps)
+static int _mv88e6xxx_vtu_stu_flush(struct mv88e6xxx_chip *chip)
 {
 	int ret;
 
-	ret = _mv88e6xxx_vtu_wait(ps);
+	ret = _mv88e6xxx_vtu_wait(chip);
 	if (ret < 0)
 		return ret;
 
-	return _mv88e6xxx_vtu_cmd(ps, GLOBAL_VTU_OP_FLUSH_ALL);
+	return _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_FLUSH_ALL);
 }
 
-static int _mv88e6xxx_vtu_stu_data_read(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_vtu_stu_data_read(struct mv88e6xxx_chip *chip,
 					struct mv88e6xxx_vtu_stu_entry *entry,
 					unsigned int nibble_offset)
 {
@@ -1492,7 +1571,7 @@ static int _mv88e6xxx_vtu_stu_data_read(struct mv88e6xxx_priv_state *ps,
 	int ret;
 
 	for (i = 0; i < 3; ++i) {
-		ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL,
+		ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL,
 					  GLOBAL_VTU_DATA_0_3 + i);
 		if (ret < 0)
 			return ret;
@@ -1500,7 +1579,7 @@ static int _mv88e6xxx_vtu_stu_data_read(struct mv88e6xxx_priv_state *ps,
 		regs[i] = ret;
 	}
 
-	for (i = 0; i < ps->info->num_ports; ++i) {
+	for (i = 0; i < chip->info->num_ports; ++i) {
 		unsigned int shift = (i % 4) * 4 + nibble_offset;
 		u16 reg = regs[i / 4];
 
@@ -1510,19 +1589,19 @@ static int _mv88e6xxx_vtu_stu_data_read(struct mv88e6xxx_priv_state *ps,
 	return 0;
 }
 
-static int mv88e6xxx_vtu_data_read(struct mv88e6xxx_priv_state *ps,
+static int mv88e6xxx_vtu_data_read(struct mv88e6xxx_chip *chip,
 				   struct mv88e6xxx_vtu_stu_entry *entry)
 {
-	return _mv88e6xxx_vtu_stu_data_read(ps, entry, 0);
+	return _mv88e6xxx_vtu_stu_data_read(chip, entry, 0);
 }
 
-static int mv88e6xxx_stu_data_read(struct mv88e6xxx_priv_state *ps,
+static int mv88e6xxx_stu_data_read(struct mv88e6xxx_chip *chip,
 				   struct mv88e6xxx_vtu_stu_entry *entry)
 {
-	return _mv88e6xxx_vtu_stu_data_read(ps, entry, 2);
+	return _mv88e6xxx_vtu_stu_data_read(chip, entry, 2);
 }
 
-static int _mv88e6xxx_vtu_stu_data_write(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_vtu_stu_data_write(struct mv88e6xxx_chip *chip,
 					 struct mv88e6xxx_vtu_stu_entry *entry,
 					 unsigned int nibble_offset)
 {
@@ -1530,7 +1609,7 @@ static int _mv88e6xxx_vtu_stu_data_write(struct mv88e6xxx_priv_state *ps,
 	int i;
 	int ret;
 
-	for (i = 0; i < ps->info->num_ports; ++i) {
+	for (i = 0; i < chip->info->num_ports; ++i) {
 		unsigned int shift = (i % 4) * 4 + nibble_offset;
 		u8 data = entry->data[i];
 
@@ -1538,7 +1617,7 @@ static int _mv88e6xxx_vtu_stu_data_write(struct mv88e6xxx_priv_state *ps,
 	}
 
 	for (i = 0; i < 3; ++i) {
-		ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL,
+		ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL,
 					   GLOBAL_VTU_DATA_0_3 + i, regs[i]);
 		if (ret < 0)
 			return ret;
@@ -1547,39 +1626,39 @@ static int _mv88e6xxx_vtu_stu_data_write(struct mv88e6xxx_priv_state *ps,
 	return 0;
 }
 
-static int mv88e6xxx_vtu_data_write(struct mv88e6xxx_priv_state *ps,
+static int mv88e6xxx_vtu_data_write(struct mv88e6xxx_chip *chip,
 				    struct mv88e6xxx_vtu_stu_entry *entry)
 {
-	return _mv88e6xxx_vtu_stu_data_write(ps, entry, 0);
+	return _mv88e6xxx_vtu_stu_data_write(chip, entry, 0);
 }
 
-static int mv88e6xxx_stu_data_write(struct mv88e6xxx_priv_state *ps,
+static int mv88e6xxx_stu_data_write(struct mv88e6xxx_chip *chip,
 				    struct mv88e6xxx_vtu_stu_entry *entry)
 {
-	return _mv88e6xxx_vtu_stu_data_write(ps, entry, 2);
+	return _mv88e6xxx_vtu_stu_data_write(chip, entry, 2);
 }
 
-static int _mv88e6xxx_vtu_vid_write(struct mv88e6xxx_priv_state *ps, u16 vid)
+static int _mv88e6xxx_vtu_vid_write(struct mv88e6xxx_chip *chip, u16 vid)
 {
-	return _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_VTU_VID,
+	return _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_VTU_VID,
 				    vid & GLOBAL_VTU_VID_MASK);
 }
 
-static int _mv88e6xxx_vtu_getnext(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_vtu_getnext(struct mv88e6xxx_chip *chip,
 				  struct mv88e6xxx_vtu_stu_entry *entry)
 {
 	struct mv88e6xxx_vtu_stu_entry next = { 0 };
 	int ret;
 
-	ret = _mv88e6xxx_vtu_wait(ps);
+	ret = _mv88e6xxx_vtu_wait(chip);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_vtu_cmd(ps, GLOBAL_VTU_OP_VTU_GET_NEXT);
+	ret = _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_VTU_GET_NEXT);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_VTU_VID);
+	ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_VTU_VID);
 	if (ret < 0)
 		return ret;
 
@@ -1587,22 +1666,22 @@ static int _mv88e6xxx_vtu_getnext(struct mv88e6xxx_priv_state *ps,
 	next.valid = !!(ret & GLOBAL_VTU_VID_VALID);
 
 	if (next.valid) {
-		ret = mv88e6xxx_vtu_data_read(ps, &next);
+		ret = mv88e6xxx_vtu_data_read(chip, &next);
 		if (ret < 0)
 			return ret;
 
-		if (mv88e6xxx_has_fid_reg(ps)) {
-			ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL,
+		if (mv88e6xxx_has_fid_reg(chip)) {
+			ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL,
 						  GLOBAL_VTU_FID);
 			if (ret < 0)
 				return ret;
 
 			next.fid = ret & GLOBAL_VTU_FID_MASK;
-		} else if (mv88e6xxx_num_databases(ps) == 256) {
+		} else if (mv88e6xxx_num_databases(chip) == 256) {
 			/* VTU DBNum[7:4] are located in VTU Operation 11:8, and
 			 * VTU DBNum[3:0] are located in VTU Operation 3:0
 			 */
-			ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL,
+			ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL,
 						  GLOBAL_VTU_OP);
 			if (ret < 0)
 				return ret;
@@ -1611,8 +1690,8 @@ static int _mv88e6xxx_vtu_getnext(struct mv88e6xxx_priv_state *ps,
 			next.fid |= ret & 0xf;
 		}
 
-		if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_STU)) {
-			ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL,
+		if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_STU)) {
+			ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL,
 						  GLOBAL_VTU_SID);
 			if (ret < 0)
 				return ret;
@@ -1629,26 +1708,26 @@ static int mv88e6xxx_port_vlan_dump(struct dsa_switch *ds, int port,
 				    struct switchdev_obj_port_vlan *vlan,
 				    int (*cb)(struct switchdev_obj *obj))
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	struct mv88e6xxx_vtu_stu_entry next;
 	u16 pvid;
 	int err;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VTU))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VTU))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	err = _mv88e6xxx_port_pvid_get(ps, port, &pvid);
+	err = _mv88e6xxx_port_pvid_get(chip, port, &pvid);
 	if (err)
 		goto unlock;
 
-	err = _mv88e6xxx_vtu_vid_write(ps, GLOBAL_VTU_VID_MASK);
+	err = _mv88e6xxx_vtu_vid_write(chip, GLOBAL_VTU_VID_MASK);
 	if (err)
 		goto unlock;
 
 	do {
-		err = _mv88e6xxx_vtu_getnext(ps, &next);
+		err = _mv88e6xxx_vtu_getnext(chip, &next);
 		if (err)
 			break;
 
@@ -1659,7 +1738,8 @@ static int mv88e6xxx_port_vlan_dump(struct dsa_switch *ds, int port,
 			continue;
 
 		/* reinit and dump this VLAN obj */
-		vlan->vid_begin = vlan->vid_end = next.vid;
+		vlan->vid_begin = next.vid;
+		vlan->vid_end = next.vid;
 		vlan->flags = 0;
 
 		if (next.data[port] == GLOBAL_VTU_DATA_MEMBER_TAG_UNTAGGED)
@@ -1674,19 +1754,19 @@ static int mv88e6xxx_port_vlan_dump(struct dsa_switch *ds, int port,
 	} while (next.vid < GLOBAL_VTU_VID_MASK);
 
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 
 	return err;
 }
 
-static int _mv88e6xxx_vtu_loadpurge(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_vtu_loadpurge(struct mv88e6xxx_chip *chip,
 				    struct mv88e6xxx_vtu_stu_entry *entry)
 {
 	u16 op = GLOBAL_VTU_OP_VTU_LOAD_PURGE;
 	u16 reg = 0;
 	int ret;
 
-	ret = _mv88e6xxx_vtu_wait(ps);
+	ret = _mv88e6xxx_vtu_wait(chip);
 	if (ret < 0)
 		return ret;
 
@@ -1694,23 +1774,25 @@ static int _mv88e6xxx_vtu_loadpurge(struct mv88e6xxx_priv_state *ps,
 		goto loadpurge;
 
 	/* Write port member tags */
-	ret = mv88e6xxx_vtu_data_write(ps, entry);
+	ret = mv88e6xxx_vtu_data_write(chip, entry);
 	if (ret < 0)
 		return ret;
 
-	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_STU)) {
+	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_STU)) {
 		reg = entry->sid & GLOBAL_VTU_SID_MASK;
-		ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_VTU_SID, reg);
+		ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_VTU_SID,
+					   reg);
 		if (ret < 0)
 			return ret;
 	}
 
-	if (mv88e6xxx_has_fid_reg(ps)) {
+	if (mv88e6xxx_has_fid_reg(chip)) {
 		reg = entry->fid & GLOBAL_VTU_FID_MASK;
-		ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_VTU_FID, reg);
+		ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_VTU_FID,
+					   reg);
 		if (ret < 0)
 			return ret;
-	} else if (mv88e6xxx_num_databases(ps) == 256) {
+	} else if (mv88e6xxx_num_databases(chip) == 256) {
 		/* VTU DBNum[7:4] are located in VTU Operation 11:8, and
 		 * VTU DBNum[3:0] are located in VTU Operation 3:0
 		 */
@@ -1721,46 +1803,46 @@ static int _mv88e6xxx_vtu_loadpurge(struct mv88e6xxx_priv_state *ps,
 	reg = GLOBAL_VTU_VID_VALID;
 loadpurge:
 	reg |= entry->vid & GLOBAL_VTU_VID_MASK;
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_VTU_VID, reg);
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_VTU_VID, reg);
 	if (ret < 0)
 		return ret;
 
-	return _mv88e6xxx_vtu_cmd(ps, op);
+	return _mv88e6xxx_vtu_cmd(chip, op);
 }
 
-static int _mv88e6xxx_stu_getnext(struct mv88e6xxx_priv_state *ps, u8 sid,
+static int _mv88e6xxx_stu_getnext(struct mv88e6xxx_chip *chip, u8 sid,
 				  struct mv88e6xxx_vtu_stu_entry *entry)
 {
 	struct mv88e6xxx_vtu_stu_entry next = { 0 };
 	int ret;
 
-	ret = _mv88e6xxx_vtu_wait(ps);
+	ret = _mv88e6xxx_vtu_wait(chip);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_VTU_SID,
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_VTU_SID,
 				   sid & GLOBAL_VTU_SID_MASK);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_vtu_cmd(ps, GLOBAL_VTU_OP_STU_GET_NEXT);
+	ret = _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_STU_GET_NEXT);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_VTU_SID);
+	ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_VTU_SID);
 	if (ret < 0)
 		return ret;
 
 	next.sid = ret & GLOBAL_VTU_SID_MASK;
 
-	ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_VTU_VID);
+	ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_VTU_VID);
 	if (ret < 0)
 		return ret;
 
 	next.valid = !!(ret & GLOBAL_VTU_VID_VALID);
 
 	if (next.valid) {
-		ret = mv88e6xxx_stu_data_read(ps, &next);
+		ret = mv88e6xxx_stu_data_read(chip, &next);
 		if (ret < 0)
 			return ret;
 	}
@@ -1769,13 +1851,13 @@ static int _mv88e6xxx_stu_getnext(struct mv88e6xxx_priv_state *ps, u8 sid,
 	return 0;
 }
 
-static int _mv88e6xxx_stu_loadpurge(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_stu_loadpurge(struct mv88e6xxx_chip *chip,
 				    struct mv88e6xxx_vtu_stu_entry *entry)
 {
 	u16 reg = 0;
 	int ret;
 
-	ret = _mv88e6xxx_vtu_wait(ps);
+	ret = _mv88e6xxx_vtu_wait(chip);
 	if (ret < 0)
 		return ret;
 
@@ -1783,41 +1865,41 @@ static int _mv88e6xxx_stu_loadpurge(struct mv88e6xxx_priv_state *ps,
 		goto loadpurge;
 
 	/* Write port states */
-	ret = mv88e6xxx_stu_data_write(ps, entry);
+	ret = mv88e6xxx_stu_data_write(chip, entry);
 	if (ret < 0)
 		return ret;
 
 	reg = GLOBAL_VTU_VID_VALID;
 loadpurge:
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_VTU_VID, reg);
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_VTU_VID, reg);
 	if (ret < 0)
 		return ret;
 
 	reg = entry->sid & GLOBAL_VTU_SID_MASK;
-	ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_VTU_SID, reg);
+	ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_VTU_SID, reg);
 	if (ret < 0)
 		return ret;
 
-	return _mv88e6xxx_vtu_cmd(ps, GLOBAL_VTU_OP_STU_LOAD_PURGE);
+	return _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_STU_LOAD_PURGE);
 }
 
-static int _mv88e6xxx_port_fid(struct mv88e6xxx_priv_state *ps, int port,
+static int _mv88e6xxx_port_fid(struct mv88e6xxx_chip *chip, int port,
 			       u16 *new, u16 *old)
 {
-	struct dsa_switch *ds = ps->ds;
+	struct dsa_switch *ds = chip->ds;
 	u16 upper_mask;
 	u16 fid;
 	int ret;
 
-	if (mv88e6xxx_num_databases(ps) == 4096)
+	if (mv88e6xxx_num_databases(chip) == 4096)
 		upper_mask = 0xff;
-	else if (mv88e6xxx_num_databases(ps) == 256)
+	else if (mv88e6xxx_num_databases(chip) == 256)
 		upper_mask = 0xf;
 	else
 		return -EOPNOTSUPP;
 
 	/* Port's default FID bits 3:0 are located in reg 0x06, offset 12 */
-	ret = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_BASE_VLAN);
+	ret = _mv88e6xxx_reg_read(chip, REG_PORT(port), PORT_BASE_VLAN);
 	if (ret < 0)
 		return ret;
 
@@ -1827,14 +1909,14 @@ static int _mv88e6xxx_port_fid(struct mv88e6xxx_priv_state *ps, int port,
 		ret &= ~PORT_BASE_VLAN_FID_3_0_MASK;
 		ret |= (*new << 12) & PORT_BASE_VLAN_FID_3_0_MASK;
 
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port), PORT_BASE_VLAN,
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_BASE_VLAN,
 					   ret);
 		if (ret < 0)
 			return ret;
 	}
 
 	/* Port's default FID bits 11:4 are located in reg 0x05, offset 0 */
-	ret = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_CONTROL_1);
+	ret = _mv88e6xxx_reg_read(chip, REG_PORT(port), PORT_CONTROL_1);
 	if (ret < 0)
 		return ret;
 
@@ -1844,7 +1926,7 @@ static int _mv88e6xxx_port_fid(struct mv88e6xxx_priv_state *ps, int port,
 		ret &= ~upper_mask;
 		ret |= (*new >> 4) & upper_mask;
 
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port), PORT_CONTROL_1,
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_CONTROL_1,
 					   ret);
 		if (ret < 0)
 			return ret;
@@ -1859,19 +1941,19 @@ static int _mv88e6xxx_port_fid(struct mv88e6xxx_priv_state *ps, int port,
 	return 0;
 }
 
-static int _mv88e6xxx_port_fid_get(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_port_fid_get(struct mv88e6xxx_chip *chip,
 				   int port, u16 *fid)
 {
-	return _mv88e6xxx_port_fid(ps, port, NULL, fid);
+	return _mv88e6xxx_port_fid(chip, port, NULL, fid);
 }
 
-static int _mv88e6xxx_port_fid_set(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_port_fid_set(struct mv88e6xxx_chip *chip,
 				   int port, u16 fid)
 {
-	return _mv88e6xxx_port_fid(ps, port, &fid, NULL);
+	return _mv88e6xxx_port_fid(chip, port, &fid, NULL);
 }
 
-static int _mv88e6xxx_fid_new(struct mv88e6xxx_priv_state *ps, u16 *fid)
+static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid)
 {
 	DECLARE_BITMAP(fid_bitmap, MV88E6XXX_N_FID);
 	struct mv88e6xxx_vtu_stu_entry vlan;
@@ -1880,8 +1962,8 @@ static int _mv88e6xxx_fid_new(struct mv88e6xxx_priv_state *ps, u16 *fid)
 	bitmap_zero(fid_bitmap, MV88E6XXX_N_FID);
 
 	/* Set every FID bit used by the (un)bridged ports */
-	for (i = 0; i < ps->info->num_ports; ++i) {
-		err = _mv88e6xxx_port_fid_get(ps, i, fid);
+	for (i = 0; i < chip->info->num_ports; ++i) {
+		err = _mv88e6xxx_port_fid_get(chip, i, fid);
 		if (err)
 			return err;
 
@@ -1889,12 +1971,12 @@ static int _mv88e6xxx_fid_new(struct mv88e6xxx_priv_state *ps, u16 *fid)
 	}
 
 	/* Set every FID bit used by the VLAN entries */
-	err = _mv88e6xxx_vtu_vid_write(ps, GLOBAL_VTU_VID_MASK);
+	err = _mv88e6xxx_vtu_vid_write(chip, GLOBAL_VTU_VID_MASK);
 	if (err)
 		return err;
 
 	do {
-		err = _mv88e6xxx_vtu_getnext(ps, &vlan);
+		err = _mv88e6xxx_vtu_getnext(chip, &vlan);
 		if (err)
 			return err;
 
@@ -1908,35 +1990,35 @@ static int _mv88e6xxx_fid_new(struct mv88e6xxx_priv_state *ps, u16 *fid)
 	 * databases are not needed. Return the next positive available.
 	 */
 	*fid = find_next_zero_bit(fid_bitmap, MV88E6XXX_N_FID, 1);
-	if (unlikely(*fid >= mv88e6xxx_num_databases(ps)))
+	if (unlikely(*fid >= mv88e6xxx_num_databases(chip)))
 		return -ENOSPC;
 
 	/* Clear the database */
-	return _mv88e6xxx_atu_flush(ps, *fid, true);
+	return _mv88e6xxx_atu_flush(chip, *fid, true);
 }
 
-static int _mv88e6xxx_vtu_new(struct mv88e6xxx_priv_state *ps, u16 vid,
+static int _mv88e6xxx_vtu_new(struct mv88e6xxx_chip *chip, u16 vid,
 			      struct mv88e6xxx_vtu_stu_entry *entry)
 {
-	struct dsa_switch *ds = ps->ds;
+	struct dsa_switch *ds = chip->ds;
 	struct mv88e6xxx_vtu_stu_entry vlan = {
 		.valid = true,
 		.vid = vid,
 	};
 	int i, err;
 
-	err = _mv88e6xxx_fid_new(ps, &vlan.fid);
+	err = _mv88e6xxx_fid_new(chip, &vlan.fid);
 	if (err)
 		return err;
 
 	/* exclude all ports except the CPU and DSA ports */
-	for (i = 0; i < ps->info->num_ports; ++i)
+	for (i = 0; i < chip->info->num_ports; ++i)
 		vlan.data[i] = dsa_is_cpu_port(ds, i) || dsa_is_dsa_port(ds, i)
 			? GLOBAL_VTU_DATA_MEMBER_TAG_UNMODIFIED
 			: GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER;
 
-	if (mv88e6xxx_6097_family(ps) || mv88e6xxx_6165_family(ps) ||
-	    mv88e6xxx_6351_family(ps) || mv88e6xxx_6352_family(ps)) {
+	if (mv88e6xxx_6097_family(chip) || mv88e6xxx_6165_family(chip) ||
+	    mv88e6xxx_6351_family(chip) || mv88e6xxx_6352_family(chip)) {
 		struct mv88e6xxx_vtu_stu_entry vstp;
 
 		/* Adding a VTU entry requires a valid STU entry. As VSTP is not
@@ -1944,7 +2026,7 @@ static int _mv88e6xxx_vtu_new(struct mv88e6xxx_priv_state *ps, u16 vid,
 		 * entries. Thus, validate the SID 0.
 		 */
 		vlan.sid = 0;
-		err = _mv88e6xxx_stu_getnext(ps, GLOBAL_VTU_SID_MASK, &vstp);
+		err = _mv88e6xxx_stu_getnext(chip, GLOBAL_VTU_SID_MASK, &vstp);
 		if (err)
 			return err;
 
@@ -1953,7 +2035,7 @@ static int _mv88e6xxx_vtu_new(struct mv88e6xxx_priv_state *ps, u16 vid,
 			vstp.valid = true;
 			vstp.sid = vlan.sid;
 
-			err = _mv88e6xxx_stu_loadpurge(ps, &vstp);
+			err = _mv88e6xxx_stu_loadpurge(chip, &vstp);
 			if (err)
 				return err;
 		}
@@ -1963,7 +2045,7 @@ static int _mv88e6xxx_vtu_new(struct mv88e6xxx_priv_state *ps, u16 vid,
 	return 0;
 }
 
-static int _mv88e6xxx_vtu_get(struct mv88e6xxx_priv_state *ps, u16 vid,
+static int _mv88e6xxx_vtu_get(struct mv88e6xxx_chip *chip, u16 vid,
 			      struct mv88e6xxx_vtu_stu_entry *entry, bool creat)
 {
 	int err;
@@ -1971,11 +2053,11 @@ static int _mv88e6xxx_vtu_get(struct mv88e6xxx_priv_state *ps, u16 vid,
 	if (!vid)
 		return -EINVAL;
 
-	err = _mv88e6xxx_vtu_vid_write(ps, vid - 1);
+	err = _mv88e6xxx_vtu_vid_write(chip, vid - 1);
 	if (err)
 		return err;
 
-	err = _mv88e6xxx_vtu_getnext(ps, entry);
+	err = _mv88e6xxx_vtu_getnext(chip, entry);
 	if (err)
 		return err;
 
@@ -1986,7 +2068,7 @@ static int _mv88e6xxx_vtu_get(struct mv88e6xxx_priv_state *ps, u16 vid,
 		 * -EOPNOTSUPP to inform bridge about an eventual software VLAN.
 		 */
 
-		err = _mv88e6xxx_vtu_new(ps, vid, entry);
+		err = _mv88e6xxx_vtu_new(chip, vid, entry);
 	}
 
 	return err;
@@ -1995,21 +2077,21 @@ static int _mv88e6xxx_vtu_get(struct mv88e6xxx_priv_state *ps, u16 vid,
 static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port,
 					u16 vid_begin, u16 vid_end)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	struct mv88e6xxx_vtu_stu_entry vlan;
 	int i, err;
 
 	if (!vid_begin)
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	err = _mv88e6xxx_vtu_vid_write(ps, vid_begin - 1);
+	err = _mv88e6xxx_vtu_vid_write(chip, vid_begin - 1);
 	if (err)
 		goto unlock;
 
 	do {
-		err = _mv88e6xxx_vtu_getnext(ps, &vlan);
+		err = _mv88e6xxx_vtu_getnext(chip, &vlan);
 		if (err)
 			goto unlock;
 
@@ -2019,7 +2101,7 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port,
 		if (vlan.vid > vid_end)
 			break;
 
-		for (i = 0; i < ps->info->num_ports; ++i) {
+		for (i = 0; i < chip->info->num_ports; ++i) {
 			if (dsa_is_dsa_port(ds, i) || dsa_is_cpu_port(ds, i))
 				continue;
 
@@ -2027,21 +2109,21 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port,
 			    GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER)
 				continue;
 
-			if (ps->ports[i].bridge_dev ==
-			    ps->ports[port].bridge_dev)
+			if (chip->ports[i].bridge_dev ==
+			    chip->ports[port].bridge_dev)
 				break; /* same bridge, check next VLAN */
 
 			netdev_warn(ds->ports[port].netdev,
 				    "hardware VLAN %d already used by %s\n",
 				    vlan.vid,
-				    netdev_name(ps->ports[i].bridge_dev));
+				    netdev_name(chip->ports[i].bridge_dev));
 			err = -EOPNOTSUPP;
 			goto unlock;
 		}
 	} while (vlan.vid < vid_end);
 
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 
 	return err;
 }
@@ -2056,17 +2138,17 @@ static const char * const mv88e6xxx_port_8021q_mode_names[] = {
 static int mv88e6xxx_port_vlan_filtering(struct dsa_switch *ds, int port,
 					 bool vlan_filtering)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	u16 old, new = vlan_filtering ? PORT_CONTROL_2_8021Q_SECURE :
 		PORT_CONTROL_2_8021Q_DISABLED;
 	int ret;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VTU))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VTU))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	ret = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_CONTROL_2);
+	ret = _mv88e6xxx_reg_read(chip, REG_PORT(port), PORT_CONTROL_2);
 	if (ret < 0)
 		goto unlock;
 
@@ -2076,7 +2158,7 @@ static int mv88e6xxx_port_vlan_filtering(struct dsa_switch *ds, int port,
 		ret &= ~PORT_CONTROL_2_8021Q_MASK;
 		ret |= new & PORT_CONTROL_2_8021Q_MASK;
 
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port), PORT_CONTROL_2,
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_CONTROL_2,
 					   ret);
 		if (ret < 0)
 			goto unlock;
@@ -2088,19 +2170,20 @@ static int mv88e6xxx_port_vlan_filtering(struct dsa_switch *ds, int port,
 
 	ret = 0;
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 
 	return ret;
 }
 
-static int mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port,
-				       const struct switchdev_obj_port_vlan *vlan,
-				       struct switchdev_trans *trans)
+static int
+mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port,
+			    const struct switchdev_obj_port_vlan *vlan,
+			    struct switchdev_trans *trans)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int err;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VTU))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VTU))
 		return -EOPNOTSUPP;
 
 	/* If the requested port doesn't belong to the same bridge as the VLAN
@@ -2117,13 +2200,13 @@ static int mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port,
 	return 0;
 }
 
-static int _mv88e6xxx_port_vlan_add(struct mv88e6xxx_priv_state *ps, int port,
+static int _mv88e6xxx_port_vlan_add(struct mv88e6xxx_chip *chip, int port,
 				    u16 vid, bool untagged)
 {
 	struct mv88e6xxx_vtu_stu_entry vlan;
 	int err;
 
-	err = _mv88e6xxx_vtu_get(ps, vid, &vlan, true);
+	err = _mv88e6xxx_vtu_get(chip, vid, &vlan, true);
 	if (err)
 		return err;
 
@@ -2131,44 +2214,44 @@ static int _mv88e6xxx_port_vlan_add(struct mv88e6xxx_priv_state *ps, int port,
 		GLOBAL_VTU_DATA_MEMBER_TAG_UNTAGGED :
 		GLOBAL_VTU_DATA_MEMBER_TAG_TAGGED;
 
-	return _mv88e6xxx_vtu_loadpurge(ps, &vlan);
+	return _mv88e6xxx_vtu_loadpurge(chip, &vlan);
 }
 
 static void mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port,
 				    const struct switchdev_obj_port_vlan *vlan,
 				    struct switchdev_trans *trans)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
 	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
 	u16 vid;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VTU))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VTU))
 		return;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
 	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid)
-		if (_mv88e6xxx_port_vlan_add(ps, port, vid, untagged))
+		if (_mv88e6xxx_port_vlan_add(chip, port, vid, untagged))
 			netdev_err(ds->ports[port].netdev,
 				   "failed to add VLAN %d%c\n",
 				   vid, untagged ? 'u' : 't');
 
-	if (pvid && _mv88e6xxx_port_pvid_set(ps, port, vlan->vid_end))
+	if (pvid && _mv88e6xxx_port_pvid_set(chip, port, vlan->vid_end))
 		netdev_err(ds->ports[port].netdev, "failed to set PVID %d\n",
 			   vlan->vid_end);
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 }
 
-static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_chip *chip,
 				    int port, u16 vid)
 {
-	struct dsa_switch *ds = ps->ds;
+	struct dsa_switch *ds = chip->ds;
 	struct mv88e6xxx_vtu_stu_entry vlan;
 	int i, err;
 
-	err = _mv88e6xxx_vtu_get(ps, vid, &vlan, false);
+	err = _mv88e6xxx_vtu_get(chip, vid, &vlan, false);
 	if (err)
 		return err;
 
@@ -2180,7 +2263,7 @@ static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_priv_state *ps,
 
 	/* keep the VLAN unless all ports are excluded */
 	vlan.valid = false;
-	for (i = 0; i < ps->info->num_ports; ++i) {
+	for (i = 0; i < chip->info->num_ports; ++i) {
 		if (dsa_is_cpu_port(ds, i) || dsa_is_dsa_port(ds, i))
 			continue;
 
@@ -2190,55 +2273,55 @@ static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_priv_state *ps,
 		}
 	}
 
-	err = _mv88e6xxx_vtu_loadpurge(ps, &vlan);
+	err = _mv88e6xxx_vtu_loadpurge(chip, &vlan);
 	if (err)
 		return err;
 
-	return _mv88e6xxx_atu_remove(ps, vlan.fid, port, false);
+	return _mv88e6xxx_atu_remove(chip, vlan.fid, port, false);
 }
 
 static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
 				   const struct switchdev_obj_port_vlan *vlan)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	u16 pvid, vid;
 	int err = 0;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VTU))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VTU))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	err = _mv88e6xxx_port_pvid_get(ps, port, &pvid);
+	err = _mv88e6xxx_port_pvid_get(chip, port, &pvid);
 	if (err)
 		goto unlock;
 
 	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
-		err = _mv88e6xxx_port_vlan_del(ps, port, vid);
+		err = _mv88e6xxx_port_vlan_del(chip, port, vid);
 		if (err)
 			goto unlock;
 
 		if (vid == pvid) {
-			err = _mv88e6xxx_port_pvid_set(ps, port, 0);
+			err = _mv88e6xxx_port_pvid_set(chip, port, 0);
 			if (err)
 				goto unlock;
 		}
 	}
 
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 
 	return err;
 }
 
-static int _mv88e6xxx_atu_mac_write(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_atu_mac_write(struct mv88e6xxx_chip *chip,
 				    const unsigned char *addr)
 {
 	int i, ret;
 
 	for (i = 0; i < 3; i++) {
 		ret = _mv88e6xxx_reg_write(
-			ps, REG_GLOBAL, GLOBAL_ATU_MAC_01 + i,
+			chip, REG_GLOBAL, GLOBAL_ATU_MAC_01 + i,
 			(addr[i * 2] << 8) | addr[i * 2 + 1]);
 		if (ret < 0)
 			return ret;
@@ -2247,13 +2330,13 @@ static int _mv88e6xxx_atu_mac_write(struct mv88e6xxx_priv_state *ps,
 	return 0;
 }
 
-static int _mv88e6xxx_atu_mac_read(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_atu_mac_read(struct mv88e6xxx_chip *chip,
 				   unsigned char *addr)
 {
 	int i, ret;
 
 	for (i = 0; i < 3; i++) {
-		ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL,
+		ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL,
 					  GLOBAL_ATU_MAC_01 + i);
 		if (ret < 0)
 			return ret;
@@ -2264,27 +2347,27 @@ static int _mv88e6xxx_atu_mac_read(struct mv88e6xxx_priv_state *ps,
 	return 0;
 }
 
-static int _mv88e6xxx_atu_load(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_atu_load(struct mv88e6xxx_chip *chip,
 			       struct mv88e6xxx_atu_entry *entry)
 {
 	int ret;
 
-	ret = _mv88e6xxx_atu_wait(ps);
+	ret = _mv88e6xxx_atu_wait(chip);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_atu_mac_write(ps, entry->mac);
+	ret = _mv88e6xxx_atu_mac_write(chip, entry->mac);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_atu_data_write(ps, entry);
+	ret = _mv88e6xxx_atu_data_write(chip, entry);
 	if (ret < 0)
 		return ret;
 
-	return _mv88e6xxx_atu_cmd(ps, entry->fid, GLOBAL_ATU_OP_LOAD_DB);
+	return _mv88e6xxx_atu_cmd(chip, entry->fid, GLOBAL_ATU_OP_LOAD_DB);
 }
 
-static int _mv88e6xxx_port_fdb_load(struct mv88e6xxx_priv_state *ps, int port,
+static int _mv88e6xxx_port_fdb_load(struct mv88e6xxx_chip *chip, int port,
 				    const unsigned char *addr, u16 vid,
 				    u8 state)
 {
@@ -2294,9 +2377,9 @@ static int _mv88e6xxx_port_fdb_load(struct mv88e6xxx_priv_state *ps, int port,
 
 	/* Null VLAN ID corresponds to the port private database */
 	if (vid == 0)
-		err = _mv88e6xxx_port_fid_get(ps, port, &vlan.fid);
+		err = _mv88e6xxx_port_fid_get(chip, port, &vlan.fid);
 	else
-		err = _mv88e6xxx_vtu_get(ps, vid, &vlan, false);
+		err = _mv88e6xxx_vtu_get(chip, vid, &vlan, false);
 	if (err)
 		return err;
 
@@ -2308,16 +2391,16 @@ static int _mv88e6xxx_port_fdb_load(struct mv88e6xxx_priv_state *ps, int port,
 		entry.portv_trunkid = BIT(port);
 	}
 
-	return _mv88e6xxx_atu_load(ps, &entry);
+	return _mv88e6xxx_atu_load(chip, &entry);
 }
 
 static int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port,
 				      const struct switchdev_obj_port_fdb *fdb,
 				      struct switchdev_trans *trans)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_ATU))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_ATU))
 		return -EOPNOTSUPP;
 
 	/* We don't need any dynamic resource from the kernel (yet),
@@ -2333,36 +2416,36 @@ static void mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port,
 	int state = is_multicast_ether_addr(fdb->addr) ?
 		GLOBAL_ATU_DATA_STATE_MC_STATIC :
 		GLOBAL_ATU_DATA_STATE_UC_STATIC;
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_ATU))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_ATU))
 		return;
 
-	mutex_lock(&ps->smi_mutex);
-	if (_mv88e6xxx_port_fdb_load(ps, port, fdb->addr, fdb->vid, state))
+	mutex_lock(&chip->reg_lock);
+	if (_mv88e6xxx_port_fdb_load(chip, port, fdb->addr, fdb->vid, state))
 		netdev_err(ds->ports[port].netdev,
 			   "failed to load MAC address\n");
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 }
 
 static int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port,
 				  const struct switchdev_obj_port_fdb *fdb)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int ret;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_ATU))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_ATU))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
-	ret = _mv88e6xxx_port_fdb_load(ps, port, fdb->addr, fdb->vid,
+	mutex_lock(&chip->reg_lock);
+	ret = _mv88e6xxx_port_fdb_load(chip, port, fdb->addr, fdb->vid,
 				       GLOBAL_ATU_DATA_STATE_UNUSED);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 
 	return ret;
 }
 
-static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_priv_state *ps, u16 fid,
+static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
 				  struct mv88e6xxx_atu_entry *entry)
 {
 	struct mv88e6xxx_atu_entry next = { 0 };
@@ -2370,19 +2453,19 @@ static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_priv_state *ps, u16 fid,
 
 	next.fid = fid;
 
-	ret = _mv88e6xxx_atu_wait(ps);
+	ret = _mv88e6xxx_atu_wait(chip);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_atu_cmd(ps, fid, GLOBAL_ATU_OP_GET_NEXT_DB);
+	ret = _mv88e6xxx_atu_cmd(chip, fid, GLOBAL_ATU_OP_GET_NEXT_DB);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_atu_mac_read(ps, next.mac);
+	ret = _mv88e6xxx_atu_mac_read(chip, next.mac);
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_ATU_DATA);
+	ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, GLOBAL_ATU_DATA);
 	if (ret < 0)
 		return ret;
 
@@ -2407,7 +2490,7 @@ static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_priv_state *ps, u16 fid,
 	return 0;
 }
 
-static int _mv88e6xxx_port_fdb_dump_one(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_port_fdb_dump_one(struct mv88e6xxx_chip *chip,
 					u16 fid, u16 vid, int port,
 					struct switchdev_obj_port_fdb *fdb,
 					int (*cb)(struct switchdev_obj *obj))
@@ -2417,12 +2500,12 @@ static int _mv88e6xxx_port_fdb_dump_one(struct mv88e6xxx_priv_state *ps,
 	};
 	int err;
 
-	err = _mv88e6xxx_atu_mac_write(ps, addr.mac);
+	err = _mv88e6xxx_atu_mac_write(chip, addr.mac);
 	if (err)
 		return err;
 
 	do {
-		err = _mv88e6xxx_atu_getnext(ps, fid, &addr);
+		err = _mv88e6xxx_atu_getnext(chip, fid, &addr);
 		if (err)
 			break;
 
@@ -2452,48 +2535,48 @@ static int mv88e6xxx_port_fdb_dump(struct dsa_switch *ds, int port,
 				   struct switchdev_obj_port_fdb *fdb,
 				   int (*cb)(struct switchdev_obj *obj))
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	struct mv88e6xxx_vtu_stu_entry vlan = {
 		.vid = GLOBAL_VTU_VID_MASK, /* all ones */
 	};
 	u16 fid;
 	int err;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_ATU))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_ATU))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
 	/* Dump port's default Filtering Information Database (VLAN ID 0) */
-	err = _mv88e6xxx_port_fid_get(ps, port, &fid);
+	err = _mv88e6xxx_port_fid_get(chip, port, &fid);
 	if (err)
 		goto unlock;
 
-	err = _mv88e6xxx_port_fdb_dump_one(ps, fid, 0, port, fdb, cb);
+	err = _mv88e6xxx_port_fdb_dump_one(chip, fid, 0, port, fdb, cb);
 	if (err)
 		goto unlock;
 
 	/* Dump VLANs' Filtering Information Databases */
-	err = _mv88e6xxx_vtu_vid_write(ps, vlan.vid);
+	err = _mv88e6xxx_vtu_vid_write(chip, vlan.vid);
 	if (err)
 		goto unlock;
 
 	do {
-		err = _mv88e6xxx_vtu_getnext(ps, &vlan);
+		err = _mv88e6xxx_vtu_getnext(chip, &vlan);
 		if (err)
 			break;
 
 		if (!vlan.valid)
 			break;
 
-		err = _mv88e6xxx_port_fdb_dump_one(ps, vlan.fid, vlan.vid, port,
-						   fdb, cb);
+		err = _mv88e6xxx_port_fdb_dump_one(chip, vlan.fid, vlan.vid,
+						   port, fdb, cb);
 		if (err)
 			break;
 	} while (vlan.vid < GLOBAL_VTU_VID_MASK);
 
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 
 	return err;
 }
@@ -2501,101 +2584,101 @@ unlock:
 static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port,
 				      struct net_device *bridge)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int i, err = 0;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VLANTABLE))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VLANTABLE))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
 	/* Assign the bridge and remap each port's VLANTable */
-	ps->ports[port].bridge_dev = bridge;
+	chip->ports[port].bridge_dev = bridge;
 
-	for (i = 0; i < ps->info->num_ports; ++i) {
-		if (ps->ports[i].bridge_dev == bridge) {
-			err = _mv88e6xxx_port_based_vlan_map(ps, i);
+	for (i = 0; i < chip->info->num_ports; ++i) {
+		if (chip->ports[i].bridge_dev == bridge) {
+			err = _mv88e6xxx_port_based_vlan_map(chip, i);
 			if (err)
 				break;
 		}
 	}
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 
 	return err;
 }
 
 static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	struct net_device *bridge = ps->ports[port].bridge_dev;
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
+	struct net_device *bridge = chip->ports[port].bridge_dev;
 	int i;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VLANTABLE))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VLANTABLE))
 		return;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
 	/* Unassign the bridge and remap each port's VLANTable */
-	ps->ports[port].bridge_dev = NULL;
+	chip->ports[port].bridge_dev = NULL;
 
-	for (i = 0; i < ps->info->num_ports; ++i)
-		if (i == port || ps->ports[i].bridge_dev == bridge)
-			if (_mv88e6xxx_port_based_vlan_map(ps, i))
+	for (i = 0; i < chip->info->num_ports; ++i)
+		if (i == port || chip->ports[i].bridge_dev == bridge)
+			if (_mv88e6xxx_port_based_vlan_map(chip, i))
 				netdev_warn(ds->ports[i].netdev,
 					    "failed to remap\n");
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 }
 
-static int _mv88e6xxx_mdio_page_write(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_mdio_page_write(struct mv88e6xxx_chip *chip,
 				      int port, int page, int reg, int val)
 {
 	int ret;
 
-	ret = mv88e6xxx_mdio_write_indirect(ps, port, 0x16, page);
+	ret = mv88e6xxx_mdio_write_indirect(chip, port, 0x16, page);
 	if (ret < 0)
 		goto restore_page_0;
 
-	ret = mv88e6xxx_mdio_write_indirect(ps, port, reg, val);
+	ret = mv88e6xxx_mdio_write_indirect(chip, port, reg, val);
 restore_page_0:
-	mv88e6xxx_mdio_write_indirect(ps, port, 0x16, 0x0);
+	mv88e6xxx_mdio_write_indirect(chip, port, 0x16, 0x0);
 
 	return ret;
 }
 
-static int _mv88e6xxx_mdio_page_read(struct mv88e6xxx_priv_state *ps,
+static int _mv88e6xxx_mdio_page_read(struct mv88e6xxx_chip *chip,
 				     int port, int page, int reg)
 {
 	int ret;
 
-	ret = mv88e6xxx_mdio_write_indirect(ps, port, 0x16, page);
+	ret = mv88e6xxx_mdio_write_indirect(chip, port, 0x16, page);
 	if (ret < 0)
 		goto restore_page_0;
 
-	ret = mv88e6xxx_mdio_read_indirect(ps, port, reg);
+	ret = mv88e6xxx_mdio_read_indirect(chip, port, reg);
 restore_page_0:
-	mv88e6xxx_mdio_write_indirect(ps, port, 0x16, 0x0);
+	mv88e6xxx_mdio_write_indirect(chip, port, 0x16, 0x0);
 
 	return ret;
 }
 
-static int mv88e6xxx_switch_reset(struct mv88e6xxx_priv_state *ps)
+static int mv88e6xxx_switch_reset(struct mv88e6xxx_chip *chip)
 {
-	bool ppu_active = mv88e6xxx_has(ps, MV88E6XXX_FLAG_PPU_ACTIVE);
+	bool ppu_active = mv88e6xxx_has(chip, MV88E6XXX_FLAG_PPU_ACTIVE);
 	u16 is_reset = (ppu_active ? 0x8800 : 0xc800);
-	struct gpio_desc *gpiod = ps->reset;
+	struct gpio_desc *gpiod = chip->reset;
 	unsigned long timeout;
 	int ret;
 	int i;
 
 	/* Set all ports to the disabled state. */
-	for (i = 0; i < ps->info->num_ports; i++) {
-		ret = _mv88e6xxx_reg_read(ps, REG_PORT(i), PORT_CONTROL);
+	for (i = 0; i < chip->info->num_ports; i++) {
+		ret = _mv88e6xxx_reg_read(chip, REG_PORT(i), PORT_CONTROL);
 		if (ret < 0)
 			return ret;
 
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(i), PORT_CONTROL,
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(i), PORT_CONTROL,
 					   ret & 0xfffc);
 		if (ret)
 			return ret;
@@ -2617,16 +2700,16 @@ static int mv88e6xxx_switch_reset(struct mv88e6xxx_priv_state *ps)
 	 * through global registers 0x18 and 0x19.
 	 */
 	if (ppu_active)
-		ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, 0x04, 0xc000);
+		ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, 0x04, 0xc000);
 	else
-		ret = _mv88e6xxx_reg_write(ps, REG_GLOBAL, 0x04, 0xc400);
+		ret = _mv88e6xxx_reg_write(chip, REG_GLOBAL, 0x04, 0xc400);
 	if (ret)
 		return ret;
 
 	/* Wait up to one second for reset to complete. */
 	timeout = jiffies + 1 * HZ;
 	while (time_before(jiffies, timeout)) {
-		ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, 0x00);
+		ret = _mv88e6xxx_reg_read(chip, REG_GLOBAL, 0x00);
 		if (ret < 0)
 			return ret;
 
@@ -2642,18 +2725,18 @@ static int mv88e6xxx_switch_reset(struct mv88e6xxx_priv_state *ps)
 	return ret;
 }
 
-static int mv88e6xxx_power_on_serdes(struct mv88e6xxx_priv_state *ps)
+static int mv88e6xxx_power_on_serdes(struct mv88e6xxx_chip *chip)
 {
 	int ret;
 
-	ret = _mv88e6xxx_mdio_page_read(ps, REG_FIBER_SERDES,
+	ret = _mv88e6xxx_mdio_page_read(chip, REG_FIBER_SERDES,
 					PAGE_FIBER_SERDES, MII_BMCR);
 	if (ret < 0)
 		return ret;
 
 	if (ret & BMCR_PDOWN) {
 		ret &= ~BMCR_PDOWN;
-		ret = _mv88e6xxx_mdio_page_write(ps, REG_FIBER_SERDES,
+		ret = _mv88e6xxx_mdio_page_write(chip, REG_FIBER_SERDES,
 						 PAGE_FIBER_SERDES, MII_BMCR,
 						 ret);
 	}
@@ -2661,30 +2744,30 @@ static int mv88e6xxx_power_on_serdes(struct mv88e6xxx_priv_state *ps)
 	return ret;
 }
 
-static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
+static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 {
-	struct dsa_switch *ds = ps->ds;
+	struct dsa_switch *ds = chip->ds;
 	int ret;
 	u16 reg;
 
-	if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
-	    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
-	    mv88e6xxx_6185_family(ps) || mv88e6xxx_6095_family(ps) ||
-	    mv88e6xxx_6065_family(ps) || mv88e6xxx_6320_family(ps)) {
+	if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
+	    mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
+	    mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip) ||
+	    mv88e6xxx_6065_family(chip) || mv88e6xxx_6320_family(chip)) {
 		/* MAC Forcing register: don't force link, speed,
 		 * duplex or flow control state to any particular
 		 * values on physical ports, but force the CPU port
 		 * and all DSA ports to their maximum bandwidth and
 		 * full duplex.
 		 */
-		reg = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_PCS_CTRL);
+		reg = _mv88e6xxx_reg_read(chip, REG_PORT(port), PORT_PCS_CTRL);
 		if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) {
 			reg &= ~PORT_PCS_CTRL_UNFORCED;
 			reg |= PORT_PCS_CTRL_FORCE_LINK |
 				PORT_PCS_CTRL_LINK_UP |
 				PORT_PCS_CTRL_DUPLEX_FULL |
 				PORT_PCS_CTRL_FORCE_DUPLEX;
-			if (mv88e6xxx_6065_family(ps))
+			if (mv88e6xxx_6065_family(chip))
 				reg |= PORT_PCS_CTRL_100;
 			else
 				reg |= PORT_PCS_CTRL_1000;
@@ -2692,7 +2775,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 			reg |= PORT_PCS_CTRL_UNFORCED;
 		}
 
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port),
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_PCS_CTRL, reg);
 		if (ret)
 			return ret;
@@ -2713,37 +2796,46 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 	 * forwarding of unknown unicasts and multicasts.
 	 */
 	reg = 0;
-	if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
-	    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
-	    mv88e6xxx_6095_family(ps) || mv88e6xxx_6065_family(ps) ||
-	    mv88e6xxx_6185_family(ps) || mv88e6xxx_6320_family(ps))
+	if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
+	    mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
+	    mv88e6xxx_6095_family(chip) || mv88e6xxx_6065_family(chip) ||
+	    mv88e6xxx_6185_family(chip) || mv88e6xxx_6320_family(chip))
 		reg = PORT_CONTROL_IGMP_MLD_SNOOP |
 		PORT_CONTROL_USE_TAG | PORT_CONTROL_USE_IP |
 		PORT_CONTROL_STATE_FORWARDING;
 	if (dsa_is_cpu_port(ds, port)) {
-		if (mv88e6xxx_6095_family(ps) || mv88e6xxx_6185_family(ps))
+		if (mv88e6xxx_6095_family(chip) || mv88e6xxx_6185_family(chip))
 			reg |= PORT_CONTROL_DSA_TAG;
-		if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
-		    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
-		    mv88e6xxx_6320_family(ps)) {
+		if (mv88e6xxx_6352_family(chip) ||
+		    mv88e6xxx_6351_family(chip) ||
+		    mv88e6xxx_6165_family(chip) ||
+		    mv88e6xxx_6097_family(chip) ||
+		    mv88e6xxx_6320_family(chip)) {
 			reg |= PORT_CONTROL_FRAME_ETHER_TYPE_DSA |
 				PORT_CONTROL_FORWARD_UNKNOWN |
 				PORT_CONTROL_FORWARD_UNKNOWN_MC;
 		}
 
-		if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
-		    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
-		    mv88e6xxx_6095_family(ps) || mv88e6xxx_6065_family(ps) ||
-		    mv88e6xxx_6185_family(ps) || mv88e6xxx_6320_family(ps)) {
-				reg |= PORT_CONTROL_EGRESS_ADD_TAG;
+		if (mv88e6xxx_6352_family(chip) ||
+		    mv88e6xxx_6351_family(chip) ||
+		    mv88e6xxx_6165_family(chip) ||
+		    mv88e6xxx_6097_family(chip) ||
+		    mv88e6xxx_6095_family(chip) ||
+		    mv88e6xxx_6065_family(chip) ||
+		    mv88e6xxx_6185_family(chip) ||
+		    mv88e6xxx_6320_family(chip)) {
+			reg |= PORT_CONTROL_EGRESS_ADD_TAG;
 		}
 	}
 	if (dsa_is_dsa_port(ds, port)) {
-		if (mv88e6xxx_6095_family(ps) || mv88e6xxx_6185_family(ps))
+		if (mv88e6xxx_6095_family(chip) ||
+		    mv88e6xxx_6185_family(chip))
 			reg |= PORT_CONTROL_DSA_TAG;
-		if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
-		    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
-		    mv88e6xxx_6320_family(ps)) {
+		if (mv88e6xxx_6352_family(chip) ||
+		    mv88e6xxx_6351_family(chip) ||
+		    mv88e6xxx_6165_family(chip) ||
+		    mv88e6xxx_6097_family(chip) ||
+		    mv88e6xxx_6320_family(chip)) {
 			reg |= PORT_CONTROL_FRAME_MODE_DSA;
 		}
 
@@ -2752,7 +2844,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 				PORT_CONTROL_FORWARD_UNKNOWN_MC;
 	}
 	if (reg) {
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port),
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_CONTROL, reg);
 		if (ret)
 			return ret;
@@ -2761,15 +2853,15 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 	/* If this port is connected to a SerDes, make sure the SerDes is not
 	 * powered down.
 	 */
-	if (mv88e6xxx_6352_family(ps)) {
-		ret = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_STATUS);
+	if (mv88e6xxx_6352_family(chip)) {
+		ret = _mv88e6xxx_reg_read(chip, REG_PORT(port), PORT_STATUS);
 		if (ret < 0)
 			return ret;
 		ret &= PORT_STATUS_CMODE_MASK;
 		if ((ret == PORT_STATUS_CMODE_100BASE_X) ||
 		    (ret == PORT_STATUS_CMODE_1000BASE_X) ||
 		    (ret == PORT_STATUS_CMODE_SGMII)) {
-			ret = mv88e6xxx_power_on_serdes(ps);
+			ret = mv88e6xxx_power_on_serdes(chip);
 			if (ret < 0)
 				return ret;
 		}
@@ -2782,17 +2874,17 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 	 * copy of all transmitted/received frames on this port to the CPU.
 	 */
 	reg = 0;
-	if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
-	    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
-	    mv88e6xxx_6095_family(ps) || mv88e6xxx_6320_family(ps) ||
-	    mv88e6xxx_6185_family(ps))
+	if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
+	    mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
+	    mv88e6xxx_6095_family(chip) || mv88e6xxx_6320_family(chip) ||
+	    mv88e6xxx_6185_family(chip))
 		reg = PORT_CONTROL_2_MAP_DA;
 
-	if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
-	    mv88e6xxx_6165_family(ps) || mv88e6xxx_6320_family(ps))
+	if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
+	    mv88e6xxx_6165_family(chip) || mv88e6xxx_6320_family(chip))
 		reg |= PORT_CONTROL_2_JUMBO_10240;
 
-	if (mv88e6xxx_6095_family(ps) || mv88e6xxx_6185_family(ps)) {
+	if (mv88e6xxx_6095_family(chip) || mv88e6xxx_6185_family(chip)) {
 		/* Set the upstream port this port should use */
 		reg |= dsa_upstream_port(ds);
 		/* enable forwarding of unknown multicast addresses to
@@ -2805,7 +2897,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 	reg |= PORT_CONTROL_2_8021Q_DISABLED;
 
 	if (reg) {
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port),
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_CONTROL_2, reg);
 		if (ret)
 			return ret;
@@ -2821,24 +2913,25 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 	if (dsa_is_cpu_port(ds, port))
 		reg = 0;
 
-	ret = _mv88e6xxx_reg_write(ps, REG_PORT(port), PORT_ASSOC_VECTOR, reg);
+	ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_ASSOC_VECTOR,
+				   reg);
 	if (ret)
 		return ret;
 
 	/* Egress rate control 2: disable egress rate control. */
-	ret = _mv88e6xxx_reg_write(ps, REG_PORT(port), PORT_RATE_CONTROL_2,
+	ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_RATE_CONTROL_2,
 				   0x0000);
 	if (ret)
 		return ret;
 
-	if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
-	    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
-	    mv88e6xxx_6320_family(ps)) {
+	if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
+	    mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
+	    mv88e6xxx_6320_family(chip)) {
 		/* Do not limit the period of time that this port can
 		 * be paused for by the remote end or the period of
 		 * time that this port can pause the remote end.
 		 */
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port),
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_PAUSE_CTRL, 0x0000);
 		if (ret)
 			return ret;
@@ -2847,12 +2940,12 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 		 * address database entries that this port is allowed
 		 * to use.
 		 */
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port),
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_ATU_CONTROL, 0x0000);
 		/* Priority Override: disable DA, SA and VTU priority
 		 * override.
 		 */
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port),
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_PRI_OVERRIDE, 0x0000);
 		if (ret)
 			return ret;
@@ -2860,14 +2953,14 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 		/* Port Ethertype: use the Ethertype DSA Ethertype
 		 * value.
 		 */
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port),
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_ETH_TYPE, ETH_P_EDSA);
 		if (ret)
 			return ret;
 		/* Tag Remap: use an identity 802.1p prio -> switch
 		 * prio mapping.
 		 */
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port),
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_TAG_REGMAP_0123, 0x3210);
 		if (ret)
 			return ret;
@@ -2875,18 +2968,18 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 		/* Tag Remap 2: use an identity 802.1p prio -> switch
 		 * prio mapping.
 		 */
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port),
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_TAG_REGMAP_4567, 0x7654);
 		if (ret)
 			return ret;
 	}
 
-	if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
-	    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
-	    mv88e6xxx_6185_family(ps) || mv88e6xxx_6095_family(ps) ||
-	    mv88e6xxx_6320_family(ps)) {
+	if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
+	    mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
+	    mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip) ||
+	    mv88e6xxx_6320_family(chip)) {
 		/* Rate Control: disable ingress rate limiting. */
-		ret = _mv88e6xxx_reg_write(ps, REG_PORT(port),
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_RATE_CONTROL, 0x0001);
 		if (ret)
 			return ret;
@@ -2895,7 +2988,8 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 	/* Port Control 1: disable trunking, disable sending
 	 * learning messages to this port.
 	 */
-	ret = _mv88e6xxx_reg_write(ps, REG_PORT(port), PORT_CONTROL_1, 0x0000);
+	ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_CONTROL_1,
+				   0x0000);
 	if (ret)
 		return ret;
 
@@ -2903,18 +2997,18 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 	 * database, and allow bidirectional communication between the
 	 * CPU and DSA port(s), and the other ports.
 	 */
-	ret = _mv88e6xxx_port_fid_set(ps, port, 0);
+	ret = _mv88e6xxx_port_fid_set(chip, port, 0);
 	if (ret)
 		return ret;
 
-	ret = _mv88e6xxx_port_based_vlan_map(ps, port);
+	ret = _mv88e6xxx_port_based_vlan_map(chip, port);
 	if (ret)
 		return ret;
 
 	/* Default VLAN ID and priority: don't set a default VLAN
 	 * ID, and set the default packet priority to zero.
 	 */
-	ret = _mv88e6xxx_reg_write(ps, REG_PORT(port), PORT_DEFAULT_VLAN,
+	ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_DEFAULT_VLAN,
 				   0x0000);
 	if (ret)
 		return ret;
@@ -2922,9 +3016,9 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_priv_state *ps, int port)
 	return 0;
 }
 
-static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
+static int mv88e6xxx_setup_global(struct mv88e6xxx_chip *chip)
 {
-	struct dsa_switch *ds = ps->ds;
+	struct dsa_switch *ds = chip->ds;
 	u32 upstream_port = dsa_upstream_port(ds);
 	u16 reg;
 	int err;
@@ -2934,11 +3028,11 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 	 * and mask all interrupt sources.
 	 */
 	reg = 0;
-	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_PPU) ||
-	    mv88e6xxx_has(ps, MV88E6XXX_FLAG_PPU_ACTIVE))
+	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_PPU) ||
+	    mv88e6xxx_has(chip, MV88E6XXX_FLAG_PPU_ACTIVE))
 		reg |= GLOBAL_CONTROL_PPU_ENABLE;
 
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_CONTROL, reg);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_CONTROL, reg);
 	if (err)
 		return err;
 
@@ -2948,12 +3042,13 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 	reg = upstream_port << GLOBAL_MONITOR_CONTROL_INGRESS_SHIFT |
 		upstream_port << GLOBAL_MONITOR_CONTROL_EGRESS_SHIFT |
 		upstream_port << GLOBAL_MONITOR_CONTROL_ARP_SHIFT;
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_MONITOR_CONTROL, reg);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_MONITOR_CONTROL,
+				   reg);
 	if (err)
 		return err;
 
 	/* Disable remote management, and set the switch's DSA device number. */
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_CONTROL_2,
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_CONTROL_2,
 				   GLOBAL_CONTROL_2_MULTIPLE_CASCADE |
 				   (ds->index & 0x1f));
 	if (err)
@@ -2963,46 +3058,47 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 	 * enable address learn messages to be sent to all message
 	 * ports.
 	 */
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_ATU_CONTROL,
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_ATU_CONTROL,
 				   0x0140 | GLOBAL_ATU_CONTROL_LEARN2ALL);
 	if (err)
 		return err;
 
 	/* Configure the IP ToS mapping registers. */
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_IP_PRI_0, 0x0000);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_IP_PRI_0, 0x0000);
 	if (err)
 		return err;
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_IP_PRI_1, 0x0000);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_IP_PRI_1, 0x0000);
 	if (err)
 		return err;
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_IP_PRI_2, 0x5555);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_IP_PRI_2, 0x5555);
 	if (err)
 		return err;
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_IP_PRI_3, 0x5555);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_IP_PRI_3, 0x5555);
 	if (err)
 		return err;
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_IP_PRI_4, 0xaaaa);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_IP_PRI_4, 0xaaaa);
 	if (err)
 		return err;
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_IP_PRI_5, 0xaaaa);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_IP_PRI_5, 0xaaaa);
 	if (err)
 		return err;
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_IP_PRI_6, 0xffff);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_IP_PRI_6, 0xffff);
 	if (err)
 		return err;
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_IP_PRI_7, 0xffff);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_IP_PRI_7, 0xffff);
 	if (err)
 		return err;
 
 	/* Configure the IEEE 802.1p priority mapping register. */
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_IEEE_PRI, 0xfa41);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_IEEE_PRI, 0xfa41);
 	if (err)
 		return err;
 
 	/* Send all frames with destination addresses matching
 	 * 01:80:c2:00:00:0x to the CPU port.
 	 */
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL2, GLOBAL2_MGMT_EN_0X, 0xffff);
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_MGMT_EN_0X,
+				   0xffff);
 	if (err)
 		return err;
 
@@ -3011,7 +3107,7 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 	 * highest, and send all special multicast frames to the CPU
 	 * port at the highest priority.
 	 */
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL2, GLOBAL2_SWITCH_MGMT,
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2, GLOBAL2_SWITCH_MGMT,
 				   0x7 | GLOBAL2_SWITCH_MGMT_RSVD2CPU | 0x70 |
 				   GLOBAL2_SWITCH_MGMT_FORCE_FLOW_CTRL_PRI);
 	if (err)
@@ -3025,7 +3121,7 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 			nexthop = ds->rtable[i] & 0x1f;
 
 		err = _mv88e6xxx_reg_write(
-			ps, REG_GLOBAL2,
+			chip, REG_GLOBAL2,
 			GLOBAL2_DEVICE_MAPPING,
 			GLOBAL2_DEVICE_MAPPING_UPDATE |
 			(i << GLOBAL2_DEVICE_MAPPING_TARGET_SHIFT) | nexthop);
@@ -3035,10 +3131,11 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 
 	/* Clear all trunk masks. */
 	for (i = 0; i < 8; i++) {
-		err = _mv88e6xxx_reg_write(ps, REG_GLOBAL2, GLOBAL2_TRUNK_MASK,
+		err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2,
+					   GLOBAL2_TRUNK_MASK,
 					   0x8000 |
 					   (i << GLOBAL2_TRUNK_MASK_NUM_SHIFT) |
-					   ((1 << ps->info->num_ports) - 1));
+					   ((1 << chip->info->num_ports) - 1));
 		if (err)
 			return err;
 	}
@@ -3046,7 +3143,7 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 	/* Clear all trunk mappings. */
 	for (i = 0; i < 16; i++) {
 		err = _mv88e6xxx_reg_write(
-			ps, REG_GLOBAL2,
+			chip, REG_GLOBAL2,
 			GLOBAL2_TRUNK_MAPPING,
 			GLOBAL2_TRUNK_MAPPING_UPDATE |
 			(i << GLOBAL2_TRUNK_MAPPING_ID_SHIFT));
@@ -3054,13 +3151,13 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 			return err;
 	}
 
-	if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
-	    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
-	    mv88e6xxx_6320_family(ps)) {
+	if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
+	    mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
+	    mv88e6xxx_6320_family(chip)) {
 		/* Send all frames with destination addresses matching
 		 * 01:80:c2:00:00:2x to the CPU port.
 		 */
-		err = _mv88e6xxx_reg_write(ps, REG_GLOBAL2,
+		err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2,
 					   GLOBAL2_MGMT_EN_2X, 0xffff);
 		if (err)
 			return err;
@@ -3068,14 +3165,14 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 		/* Initialise cross-chip port VLAN table to reset
 		 * defaults.
 		 */
-		err = _mv88e6xxx_reg_write(ps, REG_GLOBAL2,
+		err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2,
 					   GLOBAL2_PVT_ADDR, 0x9000);
 		if (err)
 			return err;
 
 		/* Clear the priority override table. */
 		for (i = 0; i < 16; i++) {
-			err = _mv88e6xxx_reg_write(ps, REG_GLOBAL2,
+			err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2,
 						   GLOBAL2_PRIO_OVERRIDE,
 						   0x8000 | (i << 8));
 			if (err)
@@ -3083,16 +3180,16 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 		}
 	}
 
-	if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
-	    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
-	    mv88e6xxx_6185_family(ps) || mv88e6xxx_6095_family(ps) ||
-	    mv88e6xxx_6320_family(ps)) {
+	if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
+	    mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
+	    mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip) ||
+	    mv88e6xxx_6320_family(chip)) {
 		/* Disable ingress rate limiting by resetting all
 		 * ingress rate limit registers to their initial
 		 * state.
 		 */
-		for (i = 0; i < ps->info->num_ports; i++) {
-			err = _mv88e6xxx_reg_write(ps, REG_GLOBAL2,
+		for (i = 0; i < chip->info->num_ports; i++) {
+			err = _mv88e6xxx_reg_write(chip, REG_GLOBAL2,
 						   GLOBAL2_INGRESS_OP,
 						   0x9000 | (i << 8));
 			if (err)
@@ -3101,23 +3198,23 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 	}
 
 	/* Clear the statistics counters for all ports */
-	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_STATS_OP,
+	err = _mv88e6xxx_reg_write(chip, REG_GLOBAL, GLOBAL_STATS_OP,
 				   GLOBAL_STATS_OP_FLUSH_ALL);
 	if (err)
 		return err;
 
 	/* Wait for the flush to complete. */
-	err = _mv88e6xxx_stats_wait(ps);
+	err = _mv88e6xxx_stats_wait(chip);
 	if (err)
 		return err;
 
 	/* Clear all ATU entries */
-	err = _mv88e6xxx_atu_flush(ps, 0, true);
+	err = _mv88e6xxx_atu_flush(chip, 0, true);
 	if (err)
 		return err;
 
 	/* Clear all the VTU and STU entries */
-	err = _mv88e6xxx_vtu_stu_flush(ps);
+	err = _mv88e6xxx_vtu_stu_flush(chip);
 	if (err < 0)
 		return err;
 
@@ -3126,134 +3223,134 @@ static int mv88e6xxx_setup_global(struct mv88e6xxx_priv_state *ps)
 
 static int mv88e6xxx_setup(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int err;
 	int i;
 
-	ps->ds = ds;
-	ds->slave_mii_bus = ps->mdio_bus;
+	chip->ds = ds;
+	ds->slave_mii_bus = chip->mdio_bus;
 
-	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_EEPROM))
-		mutex_init(&ps->eeprom_mutex);
+	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEPROM))
+		mutex_init(&chip->eeprom_mutex);
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	err = mv88e6xxx_switch_reset(ps);
+	err = mv88e6xxx_switch_reset(chip);
 	if (err)
 		goto unlock;
 
-	err = mv88e6xxx_setup_global(ps);
+	err = mv88e6xxx_setup_global(chip);
 	if (err)
 		goto unlock;
 
-	for (i = 0; i < ps->info->num_ports; i++) {
-		err = mv88e6xxx_setup_port(ps, i);
+	for (i = 0; i < chip->info->num_ports; i++) {
+		err = mv88e6xxx_setup_port(chip, i);
 		if (err)
 			goto unlock;
 	}
 
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 
 	return err;
 }
 
-int mv88e6xxx_mdio_page_read(struct dsa_switch *ds, int port, int page, int reg)
+static int mv88e6xxx_mdio_page_read(struct dsa_switch *ds, int port, int page,
+				    int reg)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int ret;
 
-	mutex_lock(&ps->smi_mutex);
-	ret = _mv88e6xxx_mdio_page_read(ps, port, page, reg);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
+	ret = _mv88e6xxx_mdio_page_read(chip, port, page, reg);
+	mutex_unlock(&chip->reg_lock);
 
 	return ret;
 }
 
-int mv88e6xxx_mdio_page_write(struct dsa_switch *ds, int port, int page,
-			      int reg, int val)
+static int mv88e6xxx_mdio_page_write(struct dsa_switch *ds, int port, int page,
+				     int reg, int val)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int ret;
 
-	mutex_lock(&ps->smi_mutex);
-	ret = _mv88e6xxx_mdio_page_write(ps, port, page, reg, val);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
+	ret = _mv88e6xxx_mdio_page_write(chip, port, page, reg, val);
+	mutex_unlock(&chip->reg_lock);
 
 	return ret;
 }
 
-static int mv88e6xxx_port_to_mdio_addr(struct mv88e6xxx_priv_state *ps,
-				       int port)
+static int mv88e6xxx_port_to_mdio_addr(struct mv88e6xxx_chip *chip, int port)
 {
-	if (port >= 0 && port < ps->info->num_ports)
+	if (port >= 0 && port < chip->info->num_ports)
 		return port;
 	return -EINVAL;
 }
 
 static int mv88e6xxx_mdio_read(struct mii_bus *bus, int port, int regnum)
 {
-	struct mv88e6xxx_priv_state *ps = bus->priv;
-	int addr = mv88e6xxx_port_to_mdio_addr(ps, port);
+	struct mv88e6xxx_chip *chip = bus->priv;
+	int addr = mv88e6xxx_port_to_mdio_addr(chip, port);
 	int ret;
 
 	if (addr < 0)
 		return 0xffff;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_PPU))
-		ret = mv88e6xxx_mdio_read_ppu(ps, addr, regnum);
-	else if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_SMI_PHY))
-		ret = mv88e6xxx_mdio_read_indirect(ps, addr, regnum);
+	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_PPU))
+		ret = mv88e6xxx_mdio_read_ppu(chip, addr, regnum);
+	else if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_SMI_PHY))
+		ret = mv88e6xxx_mdio_read_indirect(chip, addr, regnum);
 	else
-		ret = mv88e6xxx_mdio_read_direct(ps, addr, regnum);
+		ret = mv88e6xxx_mdio_read_direct(chip, addr, regnum);
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 	return ret;
 }
 
 static int mv88e6xxx_mdio_write(struct mii_bus *bus, int port, int regnum,
 				u16 val)
 {
-	struct mv88e6xxx_priv_state *ps = bus->priv;
-	int addr = mv88e6xxx_port_to_mdio_addr(ps, port);
+	struct mv88e6xxx_chip *chip = bus->priv;
+	int addr = mv88e6xxx_port_to_mdio_addr(chip, port);
 	int ret;
 
 	if (addr < 0)
 		return 0xffff;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_PPU))
-		ret = mv88e6xxx_mdio_write_ppu(ps, addr, regnum, val);
-	else if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_SMI_PHY))
-		ret = mv88e6xxx_mdio_write_indirect(ps, addr, regnum, val);
+	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_PPU))
+		ret = mv88e6xxx_mdio_write_ppu(chip, addr, regnum, val);
+	else if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_SMI_PHY))
+		ret = mv88e6xxx_mdio_write_indirect(chip, addr, regnum, val);
 	else
-		ret = mv88e6xxx_mdio_write_direct(ps, addr, regnum, val);
+		ret = mv88e6xxx_mdio_write_direct(chip, addr, regnum, val);
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&chip->reg_lock);
 	return ret;
 }
 
-static int mv88e6xxx_mdio_register(struct mv88e6xxx_priv_state *ps,
+static int mv88e6xxx_mdio_register(struct mv88e6xxx_chip *chip,
 				   struct device_node *np)
 {
 	static int index;
 	struct mii_bus *bus;
 	int err;
 
-	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_PPU))
-		mv88e6xxx_ppu_state_init(ps);
+	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_PPU))
+		mv88e6xxx_ppu_state_init(chip);
 
 	if (np)
-		ps->mdio_np = of_get_child_by_name(np, "mdio");
+		chip->mdio_np = of_get_child_by_name(np, "mdio");
 
-	bus = devm_mdiobus_alloc(ps->dev);
+	bus = devm_mdiobus_alloc(chip->dev);
 	if (!bus)
 		return -ENOMEM;
 
-	bus->priv = (void *)ps;
+	bus->priv = (void *)chip;
 	if (np) {
 		bus->name = np->full_name;
 		snprintf(bus->id, MII_BUS_ID_SIZE, "%s", np->full_name);
@@ -3264,89 +3361,89 @@ static int mv88e6xxx_mdio_register(struct mv88e6xxx_priv_state *ps,
 
 	bus->read = mv88e6xxx_mdio_read;
 	bus->write = mv88e6xxx_mdio_write;
-	bus->parent = ps->dev;
+	bus->parent = chip->dev;
 
-	if (ps->mdio_np)
-		err = of_mdiobus_register(bus, ps->mdio_np);
+	if (chip->mdio_np)
+		err = of_mdiobus_register(bus, chip->mdio_np);
 	else
 		err = mdiobus_register(bus);
 	if (err) {
-		dev_err(ps->dev, "Cannot register MDIO bus (%d)\n", err);
+		dev_err(chip->dev, "Cannot register MDIO bus (%d)\n", err);
 		goto out;
 	}
-	ps->mdio_bus = bus;
+	chip->mdio_bus = bus;
 
 	return 0;
 
 out:
-	if (ps->mdio_np)
-		of_node_put(ps->mdio_np);
+	if (chip->mdio_np)
+		of_node_put(chip->mdio_np);
 
 	return err;
 }
 
-static void mv88e6xxx_mdio_unregister(struct mv88e6xxx_priv_state *ps)
+static void mv88e6xxx_mdio_unregister(struct mv88e6xxx_chip *chip)
 
 {
-	struct mii_bus *bus = ps->mdio_bus;
+	struct mii_bus *bus = chip->mdio_bus;
 
 	mdiobus_unregister(bus);
 
-	if (ps->mdio_np)
-		of_node_put(ps->mdio_np);
+	if (chip->mdio_np)
+		of_node_put(chip->mdio_np);
 }
 
 #ifdef CONFIG_NET_DSA_HWMON
 
 static int mv88e61xx_get_temp(struct dsa_switch *ds, int *temp)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 	int ret;
 	int val;
 
 	*temp = 0;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&chip->reg_lock);
 
-	ret = mv88e6xxx_mdio_write_direct(ps, 0x0, 0x16, 0x6);
+	ret = mv88e6xxx_mdio_write_direct(chip, 0x0, 0x16, 0x6);
 	if (ret < 0)
 		goto error;
 
 	/* Enable temperature sensor */
-	ret = mv88e6xxx_mdio_read_direct(ps, 0x0, 0x1a);
+	ret = mv88e6xxx_mdio_read_direct(chip, 0x0, 0x1a);
 	if (ret < 0)
 		goto error;
 
-	ret = mv88e6xxx_mdio_write_direct(ps, 0x0, 0x1a, ret | (1 << 5));
+	ret = mv88e6xxx_mdio_write_direct(chip, 0x0, 0x1a, ret | (1 << 5));
 	if (ret < 0)
 		goto error;
 
 	/* Wait for temperature to stabilize */
 	usleep_range(10000, 12000);
 
-	val = mv88e6xxx_mdio_read_direct(ps, 0x0, 0x1a);
+	val = mv88e6xxx_mdio_read_direct(chip, 0x0, 0x1a);
 	if (val < 0) {
 		ret = val;
 		goto error;
 	}
 
 	/* Disable temperature sensor */
-	ret = mv88e6xxx_mdio_write_direct(ps, 0x0, 0x1a, ret & ~(1 << 5));
+	ret = mv88e6xxx_mdio_write_direct(chip, 0x0, 0x1a, ret & ~(1 << 5));
 	if (ret < 0)
 		goto error;
 
 	*temp = ((val & 0x1f) - 5) * 5;
 
 error:
-	mv88e6xxx_mdio_write_direct(ps, 0x0, 0x16, 0x0);
-	mutex_unlock(&ps->smi_mutex);
+	mv88e6xxx_mdio_write_direct(chip, 0x0, 0x16, 0x0);
+	mutex_unlock(&chip->reg_lock);
 	return ret;
 }
 
 static int mv88e63xx_get_temp(struct dsa_switch *ds, int *temp)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	int phy = mv88e6xxx_6320_family(ps) ? 3 : 0;
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
+	int phy = mv88e6xxx_6320_family(chip) ? 3 : 0;
 	int ret;
 
 	*temp = 0;
@@ -3362,12 +3459,12 @@ static int mv88e63xx_get_temp(struct dsa_switch *ds, int *temp)
 
 static int mv88e6xxx_get_temp(struct dsa_switch *ds, int *temp)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_TEMP))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_TEMP))
 		return -EOPNOTSUPP;
 
-	if (mv88e6xxx_6320_family(ps) || mv88e6xxx_6352_family(ps))
+	if (mv88e6xxx_6320_family(chip) || mv88e6xxx_6352_family(chip))
 		return mv88e63xx_get_temp(ds, temp);
 
 	return mv88e61xx_get_temp(ds, temp);
@@ -3375,11 +3472,11 @@ static int mv88e6xxx_get_temp(struct dsa_switch *ds, int *temp)
 
 static int mv88e6xxx_get_temp_limit(struct dsa_switch *ds, int *temp)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	int phy = mv88e6xxx_6320_family(ps) ? 3 : 0;
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
+	int phy = mv88e6xxx_6320_family(chip) ? 3 : 0;
 	int ret;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_TEMP_LIMIT))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_TEMP_LIMIT))
 		return -EOPNOTSUPP;
 
 	*temp = 0;
@@ -3395,11 +3492,11 @@ static int mv88e6xxx_get_temp_limit(struct dsa_switch *ds, int *temp)
 
 static int mv88e6xxx_set_temp_limit(struct dsa_switch *ds, int temp)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	int phy = mv88e6xxx_6320_family(ps) ? 3 : 0;
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
+	int phy = mv88e6xxx_6320_family(chip) ? 3 : 0;
 	int ret;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_TEMP_LIMIT))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_TEMP_LIMIT))
 		return -EOPNOTSUPP;
 
 	ret = mv88e6xxx_mdio_page_read(ds, phy, 6, 26);
@@ -3412,11 +3509,11 @@ static int mv88e6xxx_set_temp_limit(struct dsa_switch *ds, int temp)
 
 static int mv88e6xxx_get_temp_alarm(struct dsa_switch *ds, bool *alarm)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	int phy = mv88e6xxx_6320_family(ps) ? 3 : 0;
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
+	int phy = mv88e6xxx_6320_family(chip) ? 3 : 0;
 	int ret;
 
-	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_TEMP_LIMIT))
+	if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_TEMP_LIMIT))
 		return -EOPNOTSUPP;
 
 	*alarm = false;
@@ -3438,6 +3535,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6085",
 		.num_databases = 4096,
 		.num_ports = 10,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6097,
 	},
 
@@ -3447,6 +3545,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6095/88E6095F",
 		.num_databases = 256,
 		.num_ports = 11,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6095,
 	},
 
@@ -3456,6 +3555,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6123",
 		.num_databases = 4096,
 		.num_ports = 3,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 	},
 
@@ -3465,6 +3565,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6131",
 		.num_databases = 256,
 		.num_ports = 8,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6185,
 	},
 
@@ -3474,6 +3575,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6161",
 		.num_databases = 4096,
 		.num_ports = 6,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 	},
 
@@ -3483,6 +3585,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6165",
 		.num_databases = 4096,
 		.num_ports = 6,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 	},
 
@@ -3492,6 +3595,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6171",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 	},
 
@@ -3501,6 +3605,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6172",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 	},
 
@@ -3510,6 +3615,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6175",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 	},
 
@@ -3519,6 +3625,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6176",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 	},
 
@@ -3528,6 +3635,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6185",
 		.num_databases = 256,
 		.num_ports = 10,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6185,
 	},
 
@@ -3537,6 +3645,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6240",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 	},
 
@@ -3546,6 +3655,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6320",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6320,
 	},
 
@@ -3555,6 +3665,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6321",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6320,
 	},
 
@@ -3564,6 +3675,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6350",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 	},
 
@@ -3573,6 +3685,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6351",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 	},
 
@@ -3582,75 +3695,124 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6352",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 	},
 };
 
-static const struct mv88e6xxx_info *
-mv88e6xxx_lookup_info(unsigned int prod_num, const struct mv88e6xxx_info *table,
-		      unsigned int num)
+static const struct mv88e6xxx_info *mv88e6xxx_lookup_info(unsigned int prod_num)
 {
 	int i;
 
-	for (i = 0; i < num; ++i)
-		if (table[i].prod_num == prod_num)
-			return &table[i];
+	for (i = 0; i < ARRAY_SIZE(mv88e6xxx_table); ++i)
+		if (mv88e6xxx_table[i].prod_num == prod_num)
+			return &mv88e6xxx_table[i];
 
 	return NULL;
 }
 
-static const char *mv88e6xxx_drv_probe(struct device *dsa_dev,
-				       struct device *host_dev, int sw_addr,
-				       void **priv)
+static int mv88e6xxx_detect(struct mv88e6xxx_chip *chip)
 {
 	const struct mv88e6xxx_info *info;
-	struct mv88e6xxx_priv_state *ps;
-	struct mii_bus *bus;
-	const char *name;
 	int id, prod_num, rev;
-	int err;
-
-	bus = dsa_host_dev_to_mii_bus(host_dev);
-	if (!bus)
-		return NULL;
 
-	id = __mv88e6xxx_reg_read(bus, sw_addr, REG_PORT(0), PORT_SWITCH_ID);
+	id = mv88e6xxx_reg_read(chip, chip->info->port_base_addr,
+				PORT_SWITCH_ID);
 	if (id < 0)
-		return NULL;
+		return id;
 
 	prod_num = (id & 0xfff0) >> 4;
 	rev = id & 0x000f;
 
-	info = mv88e6xxx_lookup_info(prod_num, mv88e6xxx_table,
-				     ARRAY_SIZE(mv88e6xxx_table));
+	info = mv88e6xxx_lookup_info(prod_num);
 	if (!info)
+		return -ENODEV;
+
+	/* Update the compatible info with the probed one */
+	chip->info = info;
+
+	dev_info(chip->dev, "switch 0x%x detected: %s, revision %u\n",
+		 chip->info->prod_num, chip->info->name, rev);
+
+	return 0;
+}
+
+static struct mv88e6xxx_chip *mv88e6xxx_alloc_chip(struct device *dev)
+{
+	struct mv88e6xxx_chip *chip;
+
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
 		return NULL;
 
-	name = info->name;
+	chip->dev = dev;
+
+	mutex_init(&chip->reg_lock);
+
+	return chip;
+}
+
+static int mv88e6xxx_smi_init(struct mv88e6xxx_chip *chip,
+			      struct mii_bus *bus, int sw_addr)
+{
+	/* ADDR[0] pin is unavailable externally and considered zero */
+	if (sw_addr & 0x1)
+		return -EINVAL;
+
+	if (sw_addr == 0)
+		chip->smi_ops = &mv88e6xxx_smi_single_chip_ops;
+	else if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_MULTI_CHIP))
+		chip->smi_ops = &mv88e6xxx_smi_multi_chip_ops;
+	else
+		return -EINVAL;
+
+	chip->bus = bus;
+	chip->sw_addr = sw_addr;
+
+	return 0;
+}
+
+static const char *mv88e6xxx_drv_probe(struct device *dsa_dev,
+				       struct device *host_dev, int sw_addr,
+				       void **priv)
+{
+	struct mv88e6xxx_chip *chip;
+	struct mii_bus *bus;
+	int err;
+
+	bus = dsa_host_dev_to_mii_bus(host_dev);
+	if (!bus)
+		return NULL;
 
-	ps = devm_kzalloc(dsa_dev, sizeof(*ps), GFP_KERNEL);
-	if (!ps)
+	chip = mv88e6xxx_alloc_chip(dsa_dev);
+	if (!chip)
 		return NULL;
 
-	ps->bus = bus;
-	ps->sw_addr = sw_addr;
-	ps->info = info;
-	ps->dev = dsa_dev;
-	mutex_init(&ps->smi_mutex);
+	/* Legacy SMI probing will only support chips similar to 88E6085 */
+	chip->info = &mv88e6xxx_table[MV88E6085];
 
-	err = mv88e6xxx_mdio_register(ps, NULL);
+	err = mv88e6xxx_smi_init(chip, bus, sw_addr);
 	if (err)
-		return NULL;
+		goto free;
+
+	err = mv88e6xxx_detect(chip);
+	if (err)
+		goto free;
+
+	err = mv88e6xxx_mdio_register(chip, NULL);
+	if (err)
+		goto free;
 
-	*priv = ps;
+	*priv = chip;
 
-	dev_info(&ps->bus->dev, "switch 0x%x probed: %s, revision %u\n",
-		 prod_num, name, rev);
+	return chip->info->name;
+free:
+	devm_kfree(dsa_dev, chip);
 
-	return name;
+	return NULL;
 }
 
-struct dsa_switch_driver mv88e6xxx_switch_driver = {
+static struct dsa_switch_driver mv88e6xxx_switch_driver = {
 	.tag_protocol		= DSA_TAG_PROTO_EDSA,
 	.probe			= mv88e6xxx_drv_probe,
 	.setup			= mv88e6xxx_setup,
@@ -3686,93 +3848,92 @@ struct dsa_switch_driver mv88e6xxx_switch_driver = {
 	.port_fdb_dump          = mv88e6xxx_port_fdb_dump,
 };
 
-int mv88e6xxx_probe(struct mdio_device *mdiodev)
+static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip,
+				     struct device_node *np)
 {
-	struct device *dev = &mdiodev->dev;
-	struct device_node *np = dev->of_node;
-	struct mv88e6xxx_priv_state *ps;
-	int id, prod_num, rev;
+	struct device *dev = chip->dev;
 	struct dsa_switch *ds;
-	u32 eeprom_len;
-	int err;
 
-	ds = devm_kzalloc(dev, sizeof(*ds) + sizeof(*ps), GFP_KERNEL);
+	ds = devm_kzalloc(dev, sizeof(*ds), GFP_KERNEL);
 	if (!ds)
 		return -ENOMEM;
 
-	ps = (struct mv88e6xxx_priv_state *)(ds + 1);
-	ds->priv = ps;
 	ds->dev = dev;
-	ps->dev = dev;
-	ps->ds = ds;
-	ps->bus = mdiodev->bus;
-	ps->sw_addr = mdiodev->addr;
-	mutex_init(&ps->smi_mutex);
+	ds->priv = chip;
+	ds->drv = &mv88e6xxx_switch_driver;
 
-	get_device(&ps->bus->dev);
+	dev_set_drvdata(dev, ds);
 
-	ds->drv = &mv88e6xxx_switch_driver;
+	return dsa_register_switch(ds, np);
+}
 
-	id = mv88e6xxx_reg_read(ps, REG_PORT(0), PORT_SWITCH_ID);
-	if (id < 0)
-		return id;
+static void mv88e6xxx_unregister_switch(struct mv88e6xxx_chip *chip)
+{
+	dsa_unregister_switch(chip->ds);
+}
 
-	prod_num = (id & 0xfff0) >> 4;
-	rev = id & 0x000f;
+static int mv88e6xxx_probe(struct mdio_device *mdiodev)
+{
+	struct device *dev = &mdiodev->dev;
+	struct device_node *np = dev->of_node;
+	const struct mv88e6xxx_info *compat_info;
+	struct mv88e6xxx_chip *chip;
+	u32 eeprom_len;
+	int err;
 
-	ps->info = mv88e6xxx_lookup_info(prod_num, mv88e6xxx_table,
-					 ARRAY_SIZE(mv88e6xxx_table));
-	if (!ps->info)
-		return -ENODEV;
+	compat_info = of_device_get_match_data(dev);
+	if (!compat_info)
+		return -EINVAL;
 
-	ps->reset = devm_gpiod_get(&mdiodev->dev, "reset", GPIOD_ASIS);
-	if (IS_ERR(ps->reset)) {
-		err = PTR_ERR(ps->reset);
-		if (err == -ENOENT) {
-			/* Optional, so not an error */
-			ps->reset = NULL;
-		} else {
-			return err;
-		}
-	}
+	chip = mv88e6xxx_alloc_chip(dev);
+	if (!chip)
+		return -ENOMEM;
 
-	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_EEPROM) &&
-	    !of_property_read_u32(np, "eeprom-length", &eeprom_len))
-		ps->eeprom_len = eeprom_len;
+	chip->info = compat_info;
 
-	err = mv88e6xxx_mdio_register(ps, mdiodev->dev.of_node);
+	err = mv88e6xxx_smi_init(chip, mdiodev->bus, mdiodev->addr);
 	if (err)
 		return err;
 
-	ds->slave_mii_bus = ps->mdio_bus;
+	err = mv88e6xxx_detect(chip);
+	if (err)
+		return err;
 
-	dev_set_drvdata(dev, ds);
+	chip->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_ASIS);
+	if (IS_ERR(chip->reset))
+		return PTR_ERR(chip->reset);
 
-	err = dsa_register_switch(ds, mdiodev->dev.of_node);
+	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_EEPROM) &&
+	    !of_property_read_u32(np, "eeprom-length", &eeprom_len))
+		chip->eeprom_len = eeprom_len;
+
+	err = mv88e6xxx_mdio_register(chip, np);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_register_switch(chip, np);
 	if (err) {
-		mv88e6xxx_mdio_unregister(ps);
+		mv88e6xxx_mdio_unregister(chip);
 		return err;
 	}
 
-	dev_info(dev, "switch 0x%x probed: %s, revision %u\n",
-		 prod_num, ps->info->name, rev);
-
 	return 0;
 }
 
 static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 {
 	struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev);
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_chip *chip = ds_to_priv(ds);
 
-	dsa_unregister_switch(ds);
-	put_device(&ps->bus->dev);
-
-	mv88e6xxx_mdio_unregister(ps);
+	mv88e6xxx_unregister_switch(chip);
+	mv88e6xxx_mdio_unregister(chip);
 }
 
 static const struct of_device_id mv88e6xxx_of_match[] = {
-	{ .compatible = "marvell,mv88e6085" },
+	{
+		.compatible = "marvell,mv88e6085",
+		.data = &mv88e6xxx_table[MV88E6085],
+	},
 	{ /* sentinel */ },
 };
 
diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
index 8221c3c7ec5a..83f06620133d 100644
--- a/drivers/net/dsa/mv88e6xxx.h
+++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
@@ -1,5 +1,6 @@
 /*
- * net/dsa/mv88e6xxx.h - Marvell 88e6xxx switch chip support
+ * Marvell 88e6xxx common definitions
+ *
  * Copyright (c) 2008 Marvell Semiconductor
  *
  * This program is free software; you can redistribute it and/or modify
@@ -387,6 +388,12 @@ enum mv88e6xxx_cap {
 	 */
 	MV88E6XXX_CAP_EEPROM,
 
+	/* Multi-chip Addressing Mode.
+	 * Some chips require an indirect SMI access when their SMI device
+	 * address is not zero. See SMI_CMD and SMI_DATA.
+	 */
+	MV88E6XXX_CAP_MULTI_CHIP,
+
 	/* Port State Filtering for 802.1D Spanning Tree.
 	 * See PORT_CONTROL_STATE_* values in the PORT_CONTROL register.
 	 */
@@ -439,6 +446,7 @@ enum mv88e6xxx_cap {
 #define MV88E6XXX_FLAG_ATU		BIT(MV88E6XXX_CAP_ATU)
 #define MV88E6XXX_FLAG_EEE		BIT(MV88E6XXX_CAP_EEE)
 #define MV88E6XXX_FLAG_EEPROM		BIT(MV88E6XXX_CAP_EEPROM)
+#define MV88E6XXX_FLAG_MULTI_CHIP	BIT(MV88E6XXX_CAP_MULTI_CHIP)
 #define MV88E6XXX_FLAG_PORTSTATE	BIT(MV88E6XXX_CAP_PORTSTATE)
 #define MV88E6XXX_FLAG_PPU		BIT(MV88E6XXX_CAP_PPU)
 #define MV88E6XXX_FLAG_PPU_ACTIVE	BIT(MV88E6XXX_CAP_PPU_ACTIVE)
@@ -452,25 +460,29 @@ enum mv88e6xxx_cap {
 
 #define MV88E6XXX_FLAGS_FAMILY_6095	\
 	(MV88E6XXX_FLAG_ATU |		\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PPU |		\
 	 MV88E6XXX_FLAG_VLANTABLE |	\
 	 MV88E6XXX_FLAG_VTU)
 
 #define MV88E6XXX_FLAGS_FAMILY_6097	\
 	(MV88E6XXX_FLAG_ATU |		\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PPU |		\
 	 MV88E6XXX_FLAG_STU |		\
 	 MV88E6XXX_FLAG_VLANTABLE |	\
 	 MV88E6XXX_FLAG_VTU)
 
 #define MV88E6XXX_FLAGS_FAMILY_6165	\
-	(MV88E6XXX_FLAG_STU |		\
+	(MV88E6XXX_FLAG_MULTI_CHIP |	\
+	 MV88E6XXX_FLAG_STU |		\
 	 MV88E6XXX_FLAG_SWITCH_MAC |	\
 	 MV88E6XXX_FLAG_TEMP |		\
 	 MV88E6XXX_FLAG_VTU)
 
 #define MV88E6XXX_FLAGS_FAMILY_6185	\
 	(MV88E6XXX_FLAG_ATU |		\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PPU |		\
 	 MV88E6XXX_FLAG_VLANTABLE |	\
 	 MV88E6XXX_FLAG_VTU)
@@ -479,6 +491,7 @@ enum mv88e6xxx_cap {
 	(MV88E6XXX_FLAG_ATU |		\
 	 MV88E6XXX_FLAG_EEE |		\
 	 MV88E6XXX_FLAG_EEPROM |	\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PORTSTATE |	\
 	 MV88E6XXX_FLAG_PPU_ACTIVE |	\
 	 MV88E6XXX_FLAG_SMI_PHY |	\
@@ -490,6 +503,7 @@ enum mv88e6xxx_cap {
 
 #define MV88E6XXX_FLAGS_FAMILY_6351	\
 	(MV88E6XXX_FLAG_ATU |		\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PORTSTATE |	\
 	 MV88E6XXX_FLAG_PPU_ACTIVE |	\
 	 MV88E6XXX_FLAG_SMI_PHY |	\
@@ -503,6 +517,7 @@ enum mv88e6xxx_cap {
 	(MV88E6XXX_FLAG_ATU |		\
 	 MV88E6XXX_FLAG_EEE |		\
 	 MV88E6XXX_FLAG_EEPROM |	\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PORTSTATE |	\
 	 MV88E6XXX_FLAG_PPU_ACTIVE |	\
 	 MV88E6XXX_FLAG_SMI_PHY |	\
@@ -519,6 +534,7 @@ struct mv88e6xxx_info {
 	const char *name;
 	unsigned int num_databases;
 	unsigned int num_ports;
+	unsigned int port_base_addr;
 	unsigned long flags;
 };
 
@@ -541,11 +557,13 @@ struct mv88e6xxx_vtu_stu_entry {
 	u8	data[DSA_MAX_PORTS];
 };
 
+struct mv88e6xxx_ops;
+
 struct mv88e6xxx_priv_port {
 	struct net_device *bridge_dev;
 };
 
-struct mv88e6xxx_priv_state {
+struct mv88e6xxx_chip {
 	const struct mv88e6xxx_info *info;
 
 	/* The dsa_switch this private structure is related to */
@@ -554,15 +572,13 @@ struct mv88e6xxx_priv_state {
 	/* The device this structure is associated to */
 	struct device *dev;
 
-	/* When using multi-chip addressing, this mutex protects
-	 * access to the indirect access registers.  (In single-chip
-	 * mode, this mutex is effectively useless.)
-	 */
-	struct mutex	smi_mutex;
+	/* This mutex protects the access to the switch registers */
+	struct mutex reg_lock;
 
 	/* The MII bus and the address on the bus that is used to
 	 * communication with the switch
 	 */
+	const struct mv88e6xxx_ops *smi_ops;
 	struct mii_bus *bus;
 	int sw_addr;
 
@@ -608,6 +624,11 @@ struct mv88e6xxx_priv_state {
 	struct mii_bus *mdio_bus;
 };
 
+struct mv88e6xxx_ops {
+	int (*read)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val);
+	int (*write)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val);
+};
+
 enum stat_type {
 	BANK0,
 	BANK1,
@@ -621,10 +642,10 @@ struct mv88e6xxx_hw_stat {
 	enum stat_type type;
 };
 
-static inline bool mv88e6xxx_has(struct mv88e6xxx_priv_state *ps,
+static inline bool mv88e6xxx_has(struct mv88e6xxx_chip *chip,
 				 unsigned long flags)
 {
-	return (ps->info->flags & flags) == flags;
+	return (chip->info->flags & flags) == flags;
 }
 
 #endif
diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c
index c89b9aeeceb6..5698f5354c0b 100644
--- a/drivers/net/ethernet/8390/ax88796.c
+++ b/drivers/net/ethernet/8390/ax88796.c
@@ -84,7 +84,6 @@ static u32 ax_msg_enable;
 struct ax_device {
 	struct mii_bus *mii_bus;
 	struct mdiobb_ctrl bb_ctrl;
-	struct phy_device *phy_dev;
 	void __iomem *addr_memr;
 	u8 reg_memr;
 	int link;
@@ -320,7 +319,7 @@ static void ax_block_output(struct net_device *dev, int count,
 static void ax_handle_link_change(struct net_device *dev)
 {
 	struct ax_device  *ax = to_ax_dev(dev);
-	struct phy_device *phy_dev = ax->phy_dev;
+	struct phy_device *phy_dev = dev->phydev;
 	int status_change = 0;
 
 	if (phy_dev->link && ((ax->speed != phy_dev->speed) ||
@@ -369,8 +368,6 @@ static int ax_mii_probe(struct net_device *dev)
 	phy_dev->supported &= PHY_BASIC_FEATURES;
 	phy_dev->advertising = phy_dev->supported;
 
-	ax->phy_dev = phy_dev;
-
 	netdev_info(dev, "PHY driver [%s] (mii_bus:phy_addr=%s, irq=%d)\n",
 		    phy_dev->drv->name, phydev_name(phy_dev), phy_dev->irq);
 
@@ -410,7 +407,7 @@ static int ax_open(struct net_device *dev)
 	ret = ax_mii_probe(dev);
 	if (ret)
 		goto failed_mii_probe;
-	phy_start(ax->phy_dev);
+	phy_start(dev->phydev);
 
 	ret = ax_ei_open(dev);
 	if (ret)
@@ -421,7 +418,7 @@ static int ax_open(struct net_device *dev)
 	return 0;
 
  failed_ax_ei_open:
-	phy_disconnect(ax->phy_dev);
+	phy_disconnect(dev->phydev);
  failed_mii_probe:
 	ax_phy_switch(dev, 0);
 	free_irq(dev->irq, dev);
@@ -442,7 +439,7 @@ static int ax_close(struct net_device *dev)
 
 	/* turn the phy off */
 	ax_phy_switch(dev, 0);
-	phy_disconnect(ax->phy_dev);
+	phy_disconnect(dev->phydev);
 
 	free_irq(dev->irq, dev);
 	return 0;
@@ -450,8 +447,7 @@ static int ax_close(struct net_device *dev)
 
 static int ax_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 {
-	struct ax_device *ax = to_ax_dev(dev);
-	struct phy_device *phy_dev = ax->phy_dev;
+	struct phy_device *phy_dev = dev->phydev;
 
 	if (!netif_running(dev))
 		return -EINVAL;
@@ -474,28 +470,6 @@ static void ax_get_drvinfo(struct net_device *dev,
 	strlcpy(info->bus_info, pdev->name, sizeof(info->bus_info));
 }
 
-static int ax_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct ax_device *ax = to_ax_dev(dev);
-	struct phy_device *phy_dev = ax->phy_dev;
-
-	if (!phy_dev)
-		return -ENODEV;
-
-	return phy_ethtool_gset(phy_dev, cmd);
-}
-
-static int ax_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct ax_device *ax = to_ax_dev(dev);
-	struct phy_device *phy_dev = ax->phy_dev;
-
-	if (!phy_dev)
-		return -ENODEV;
-
-	return phy_ethtool_sset(phy_dev, cmd);
-}
-
 static u32 ax_get_msglevel(struct net_device *dev)
 {
 	struct ei_device *ei_local = netdev_priv(dev);
@@ -512,12 +486,12 @@ static void ax_set_msglevel(struct net_device *dev, u32 v)
 
 static const struct ethtool_ops ax_ethtool_ops = {
 	.get_drvinfo		= ax_get_drvinfo,
-	.get_settings		= ax_get_settings,
-	.set_settings		= ax_set_settings,
 	.get_link		= ethtool_op_get_link,
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.get_msglevel		= ax_get_msglevel,
 	.set_msglevel		= ax_set_msglevel,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
 #ifdef CONFIG_AX88796_93CX6
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 30defe6c81f2..cd7e2e5f496b 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -440,7 +440,6 @@ struct et131x_adapter {
 	struct net_device *netdev;
 	struct pci_dev *pdev;
 	struct mii_bus *mii_bus;
-	struct phy_device *phydev;
 	struct napi_struct napi;
 
 	/* Flags that indicate current state of the adapter */
@@ -864,7 +863,7 @@ static void et1310_config_mac_regs2(struct et131x_adapter *adapter)
 {
 	int32_t delay = 0;
 	struct mac_regs __iomem *mac = &adapter->regs->mac;
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 	u32 cfg1;
 	u32 cfg2;
 	u32 ifctrl;
@@ -1035,7 +1034,7 @@ static void et1310_setup_device_for_unicast(struct et131x_adapter *adapter)
 static void et1310_config_rxmac_regs(struct et131x_adapter *adapter)
 {
 	struct rxmac_regs __iomem *rxmac = &adapter->regs->rxmac;
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 	u32 sa_lo;
 	u32 sa_hi = 0;
 	u32 pf_ctrl = 0;
@@ -1230,7 +1229,7 @@ out:
 
 static int et131x_mii_read(struct et131x_adapter *adapter, u8 reg, u16 *value)
 {
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 
 	if (!phydev)
 		return -EIO;
@@ -1311,7 +1310,7 @@ static void et1310_phy_read_mii_bit(struct et131x_adapter *adapter,
 
 static void et1310_config_flow_control(struct et131x_adapter *adapter)
 {
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 
 	if (phydev->duplex == DUPLEX_HALF) {
 		adapter->flow = FLOW_NONE;
@@ -1456,7 +1455,7 @@ static int et131x_mdio_write(struct mii_bus *bus, int phy_addr,
 static void et1310_phy_power_switch(struct et131x_adapter *adapter, bool down)
 {
 	u16 data;
-	struct  phy_device *phydev = adapter->phydev;
+	struct  phy_device *phydev = adapter->netdev->phydev;
 
 	et131x_mii_read(adapter, MII_BMCR, &data);
 	data &= ~BMCR_PDOWN;
@@ -1469,7 +1468,7 @@ static void et1310_phy_power_switch(struct et131x_adapter *adapter, bool down)
 static void et131x_xcvr_init(struct et131x_adapter *adapter)
 {
 	u16 lcr2;
-	struct  phy_device *phydev = adapter->phydev;
+	struct  phy_device *phydev = adapter->netdev->phydev;
 
 	/* Set the LED behavior such that LED 1 indicates speed (off =
 	 * 10Mbits, blink = 100Mbits, on = 1000Mbits) and LED 2 indicates
@@ -2111,7 +2110,7 @@ static int et131x_init_recv(struct et131x_adapter *adapter)
 /* et131x_set_rx_dma_timer - Set the heartbeat timer according to line rate */
 static void et131x_set_rx_dma_timer(struct et131x_adapter *adapter)
 {
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 
 	/* For version B silicon, we do not use the RxDMA timer for 10 and 100
 	 * Mbits/s line rates. We do not enable and RxDMA interrupt coalescing.
@@ -2426,7 +2425,7 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 	struct sk_buff *skb = tcb->skb;
 	u32 nr_frags = skb_shinfo(skb)->nr_frags + 1;
 	struct skb_frag_struct *frags = &skb_shinfo(skb)->frags[0];
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 	dma_addr_t dma_addr;
 	struct tx_ring *tx_ring = &adapter->tx_ring;
 
@@ -2791,22 +2790,6 @@ static void et131x_handle_send_pkts(struct et131x_adapter *adapter)
 	spin_unlock_irqrestore(&adapter->tcb_send_qlock, flags);
 }
 
-static int et131x_get_settings(struct net_device *netdev,
-			       struct ethtool_cmd *cmd)
-{
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
-	return phy_ethtool_gset(adapter->phydev, cmd);
-}
-
-static int et131x_set_settings(struct net_device *netdev,
-			       struct ethtool_cmd *cmd)
-{
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
-	return phy_ethtool_sset(adapter->phydev, cmd);
-}
-
 static int et131x_get_regs_len(struct net_device *netdev)
 {
 #define ET131X_REGS_LEN 256
@@ -2979,12 +2962,12 @@ static void et131x_get_drvinfo(struct net_device *netdev,
 }
 
 static struct ethtool_ops et131x_ethtool_ops = {
-	.get_settings	= et131x_get_settings,
-	.set_settings	= et131x_set_settings,
 	.get_drvinfo	= et131x_get_drvinfo,
 	.get_regs_len	= et131x_get_regs_len,
 	.get_regs	= et131x_get_regs,
 	.get_link	= ethtool_op_get_link,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 /* et131x_hwaddr_init - set up the MAC Address */
@@ -3098,7 +3081,7 @@ err_out:
 static void et131x_error_timer_handler(unsigned long data)
 {
 	struct et131x_adapter *adapter = (struct et131x_adapter *)data;
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 
 	if (et1310_in_phy_coma(adapter)) {
 		/* Bring the device immediately out of coma, to
@@ -3168,7 +3151,7 @@ static int et131x_adapter_memory_alloc(struct et131x_adapter *adapter)
 static void et131x_adjust_link(struct net_device *netdev)
 {
 	struct et131x_adapter *adapter = netdev_priv(netdev);
-	struct  phy_device *phydev = adapter->phydev;
+	struct  phy_device *phydev = netdev->phydev;
 
 	if (!phydev)
 		return;
@@ -3287,7 +3270,6 @@ static int et131x_mii_probe(struct net_device *netdev)
 
 	phydev->advertising = phydev->supported;
 	phydev->autoneg = AUTONEG_ENABLE;
-	adapter->phydev = phydev;
 
 	phy_attached_info(phydev);
 
@@ -3323,7 +3305,7 @@ static void et131x_pci_remove(struct pci_dev *pdev)
 
 	unregister_netdev(netdev);
 	netif_napi_del(&adapter->napi);
-	phy_disconnect(adapter->phydev);
+	phy_disconnect(netdev->phydev);
 	mdiobus_unregister(adapter->mii_bus);
 	mdiobus_free(adapter->mii_bus);
 
@@ -3338,20 +3320,16 @@ static void et131x_pci_remove(struct pci_dev *pdev)
 
 static void et131x_up(struct net_device *netdev)
 {
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
 	et131x_enable_txrx(netdev);
-	phy_start(adapter->phydev);
+	phy_start(netdev->phydev);
 }
 
 static void et131x_down(struct net_device *netdev)
 {
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
 	/* Save the timestamp for the TX watchdog, prevent a timeout */
 	netif_trans_update(netdev);
 
-	phy_stop(adapter->phydev);
+	phy_stop(netdev->phydev);
 	et131x_disable_txrx(netdev);
 }
 
@@ -3684,12 +3662,10 @@ static int et131x_close(struct net_device *netdev)
 static int et131x_ioctl(struct net_device *netdev, struct ifreq *reqbuf,
 			int cmd)
 {
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
-	if (!adapter->phydev)
+	if (!netdev->phydev)
 		return -EINVAL;
 
-	return phy_mii_ioctl(adapter->phydev, reqbuf, cmd);
+	return phy_mii_ioctl(netdev->phydev, reqbuf, cmd);
 }
 
 /* et131x_set_packet_filter - Configures the Rx Packet filtering */
@@ -4073,7 +4049,7 @@ out:
 	return rc;
 
 err_phy_disconnect:
-	phy_disconnect(adapter->phydev);
+	phy_disconnect(netdev->phydev);
 err_mdio_unregister:
 	mdiobus_unregister(adapter->mii_bus);
 err_mdio_free:
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index de2c4bf5fac4..6ffdff68bfc4 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -77,7 +77,6 @@ struct emac_board_info {
 
 	int			emacrx_completed_flag;
 
-	struct phy_device	*phy_dev;
 	struct device_node	*phy_node;
 	unsigned int		link;
 	unsigned int		speed;
@@ -115,7 +114,7 @@ static void emac_update_duplex(struct net_device *dev)
 static void emac_handle_link_change(struct net_device *dev)
 {
 	struct emac_board_info *db = netdev_priv(dev);
-	struct phy_device *phydev = db->phy_dev;
+	struct phy_device *phydev = dev->phydev;
 	unsigned long flags;
 	int status_change = 0;
 
@@ -154,21 +153,22 @@ static void emac_handle_link_change(struct net_device *dev)
 static int emac_mdio_probe(struct net_device *dev)
 {
 	struct emac_board_info *db = netdev_priv(dev);
+	struct phy_device *phydev;
 
 	/* to-do: PHY interrupts are currently not supported */
 
 	/* attach the mac to the phy */
-	db->phy_dev = of_phy_connect(db->ndev, db->phy_node,
-				     &emac_handle_link_change, 0,
-				     db->phy_interface);
-	if (!db->phy_dev) {
+	phydev = of_phy_connect(db->ndev, db->phy_node,
+				&emac_handle_link_change, 0,
+				db->phy_interface);
+	if (!phydev) {
 		netdev_err(db->ndev, "could not find the PHY\n");
 		return -ENODEV;
 	}
 
 	/* mask with MAC supported features */
-	db->phy_dev->supported &= PHY_BASIC_FEATURES;
-	db->phy_dev->advertising = db->phy_dev->supported;
+	phydev->supported &= PHY_BASIC_FEATURES;
+	phydev->advertising = phydev->supported;
 
 	db->link = 0;
 	db->speed = 0;
@@ -179,10 +179,7 @@ static int emac_mdio_probe(struct net_device *dev)
 
 static void emac_mdio_remove(struct net_device *dev)
 {
-	struct emac_board_info *db = netdev_priv(dev);
-
-	phy_disconnect(db->phy_dev);
-	db->phy_dev = NULL;
+	phy_disconnect(dev->phydev);
 }
 
 static void emac_reset(struct emac_board_info *db)
@@ -208,8 +205,7 @@ static void emac_inblk_32bit(void __iomem *reg, void *data, int count)
 
 static int emac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct emac_board_info *dm = netdev_priv(dev);
-	struct phy_device *phydev = dm->phy_dev;
+	struct phy_device *phydev = dev->phydev;
 
 	if (!netif_running(dev))
 		return -EINVAL;
@@ -229,33 +225,11 @@ static void emac_get_drvinfo(struct net_device *dev,
 	strlcpy(info->bus_info, dev_name(&dev->dev), sizeof(info->bus_info));
 }
 
-static int emac_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct emac_board_info *dm = netdev_priv(dev);
-	struct phy_device *phydev = dm->phy_dev;
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_ethtool_gset(phydev, cmd);
-}
-
-static int emac_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct emac_board_info *dm = netdev_priv(dev);
-	struct phy_device *phydev = dm->phy_dev;
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_ethtool_sset(phydev, cmd);
-}
-
 static const struct ethtool_ops emac_ethtool_ops = {
 	.get_drvinfo	= emac_get_drvinfo,
-	.get_settings	= emac_get_settings,
-	.set_settings	= emac_set_settings,
 	.get_link	= ethtool_op_get_link,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 static unsigned int emac_setup(struct net_device *ndev)
@@ -744,7 +718,7 @@ static int emac_open(struct net_device *dev)
 		return ret;
 	}
 
-	phy_start(db->phy_dev);
+	phy_start(dev->phydev);
 	netif_start_queue(dev);
 
 	return 0;
@@ -781,7 +755,7 @@ static int emac_stop(struct net_device *ndev)
 	netif_stop_queue(ndev);
 	netif_carrier_off(ndev);
 
-	phy_stop(db->phy_dev);
+	phy_stop(ndev->phydev);
 
 	emac_mdio_remove(ndev);
 
diff --git a/drivers/net/ethernet/altera/altera_tse.h b/drivers/net/ethernet/altera/altera_tse.h
index 103c30ddddf7..e0052003d16f 100644
--- a/drivers/net/ethernet/altera/altera_tse.h
+++ b/drivers/net/ethernet/altera/altera_tse.h
@@ -473,7 +473,6 @@ struct altera_tse_private {
 	int phy_addr;		/* PHY's MDIO address, -1 for autodetection */
 	phy_interface_t phy_iface;
 	struct mii_bus *mdio;
-	struct phy_device *phydev;
 	int oldspeed;
 	int oldduplex;
 	int oldlink;
diff --git a/drivers/net/ethernet/altera/altera_tse_ethtool.c b/drivers/net/ethernet/altera/altera_tse_ethtool.c
index be72e1e64525..7c367713c3e6 100644
--- a/drivers/net/ethernet/altera/altera_tse_ethtool.c
+++ b/drivers/net/ethernet/altera/altera_tse_ethtool.c
@@ -233,40 +233,18 @@ static void tse_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 		buf[i] = csrrd32(priv->mac_dev, i * 4);
 }
 
-static int tse_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct altera_tse_private *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
-
-	if (phydev == NULL)
-		return -ENODEV;
-
-	return phy_ethtool_gset(phydev, cmd);
-}
-
-static int tse_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct altera_tse_private *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
-
-	if (phydev == NULL)
-		return -ENODEV;
-
-	return phy_ethtool_sset(phydev, cmd);
-}
-
 static const struct ethtool_ops tse_ethtool_ops = {
 	.get_drvinfo = tse_get_drvinfo,
 	.get_regs_len = tse_reglen,
 	.get_regs = tse_get_regs,
 	.get_link = ethtool_op_get_link,
-	.get_settings = tse_get_settings,
-	.set_settings = tse_set_settings,
 	.get_strings = tse_gstrings,
 	.get_sset_count = tse_sset_count,
 	.get_ethtool_stats = tse_fill_stats,
 	.get_msglevel = tse_get_msglevel,
 	.set_msglevel = tse_set_msglevel,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 void altera_tse_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index f749e4d389eb..49025e99fb0e 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -625,7 +625,7 @@ out:
 static void altera_tse_adjust_link(struct net_device *dev)
 {
 	struct altera_tse_private *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	int new_state = 0;
 
 	/* only change config if there is a link */
@@ -845,7 +845,6 @@ static int init_phy(struct net_device *dev)
 	netdev_dbg(dev, "attached to PHY %d UID 0x%08x Link = %d\n",
 		   phydev->mdio.addr, phydev->phy_id, phydev->link);
 
-	priv->phydev = phydev;
 	return 0;
 }
 
@@ -1172,8 +1171,8 @@ static int tse_open(struct net_device *dev)
 
 	spin_unlock_irqrestore(&priv->rxdma_irq_lock, flags);
 
-	if (priv->phydev)
-		phy_start(priv->phydev);
+	if (dev->phydev)
+		phy_start(dev->phydev);
 
 	napi_enable(&priv->napi);
 	netif_start_queue(dev);
@@ -1205,8 +1204,8 @@ static int tse_shutdown(struct net_device *dev)
 	unsigned long int flags;
 
 	/* Stop the PHY */
-	if (priv->phydev)
-		phy_stop(priv->phydev);
+	if (dev->phydev)
+		phy_stop(dev->phydev);
 
 	netif_stop_queue(dev);
 	napi_disable(&priv->napi);
@@ -1545,10 +1544,9 @@ err_free_netdev:
 static int altera_tse_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct altera_tse_private *priv = netdev_priv(ndev);
 
-	if (priv->phydev)
-		phy_disconnect(priv->phydev);
+	if (ndev->phydev)
+		phy_disconnect(ndev->phydev);
 
 	platform_set_drvdata(pdev, NULL);
 	altera_tse_mdio_destroy(ndev);
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index e0fb0f1122db..20760e10211a 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -509,8 +509,8 @@ static int au1000_mii_probe(struct net_device *dev)
 	 * on the current MAC's MII bus
 	 */
 	for (phy_addr = 0; phy_addr < PHY_MAX_ADDR; phy_addr++)
-		if (mdiobus_get_phy(aup->mii_bus, aup->phy_addr)) {
-			phydev = mdiobus_get_phy(aup->mii_bus, aup->phy_addr);
+		if (mdiobus_get_phy(aup->mii_bus, phy_addr)) {
+			phydev = mdiobus_get_phy(aup->mii_bus, phy_addr);
 			if (!aup->phy_search_highest_addr)
 				/* break out with first one found */
 				break;
diff --git a/drivers/net/ethernet/arc/emac.h b/drivers/net/ethernet/arc/emac.h
index ca562bc034c3..e4feb712d4f2 100644
--- a/drivers/net/ethernet/arc/emac.h
+++ b/drivers/net/ethernet/arc/emac.h
@@ -134,7 +134,6 @@ struct arc_emac_priv {
 
 	/* Devices */
 	struct device *dev;
-	struct phy_device *phy_dev;
 	struct mii_bus *bus;
 	struct arc_emac_mdio_bus_data bus_data;
 
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index a3a9392a4954..586bedac457d 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -47,7 +47,7 @@ static inline int arc_emac_tx_avail(struct arc_emac_priv *priv)
 static void arc_emac_adjust_link(struct net_device *ndev)
 {
 	struct arc_emac_priv *priv = netdev_priv(ndev);
-	struct phy_device *phy_dev = priv->phy_dev;
+	struct phy_device *phy_dev = ndev->phydev;
 	unsigned int reg, state_changed = 0;
 
 	if (priv->link != phy_dev->link) {
@@ -80,46 +80,6 @@ static void arc_emac_adjust_link(struct net_device *ndev)
 }
 
 /**
- * arc_emac_get_settings - Get PHY settings.
- * @ndev:	Pointer to net_device structure.
- * @cmd:	Pointer to ethtool_cmd structure.
- *
- * This implements ethtool command for getting PHY settings. If PHY could
- * not be found, the function returns -ENODEV. This function calls the
- * relevant PHY ethtool API to get the PHY settings.
- * Issue "ethtool ethX" under linux prompt to execute this function.
- */
-static int arc_emac_get_settings(struct net_device *ndev,
-				 struct ethtool_cmd *cmd)
-{
-	struct arc_emac_priv *priv = netdev_priv(ndev);
-
-	return phy_ethtool_gset(priv->phy_dev, cmd);
-}
-
-/**
- * arc_emac_set_settings - Set PHY settings as passed in the argument.
- * @ndev:	Pointer to net_device structure.
- * @cmd:	Pointer to ethtool_cmd structure.
- *
- * This implements ethtool command for setting various PHY settings. If PHY
- * could not be found, the function returns -ENODEV. This function calls the
- * relevant PHY ethtool API to set the PHY.
- * Issue e.g. "ethtool -s ethX speed 1000" under linux prompt to execute this
- * function.
- */
-static int arc_emac_set_settings(struct net_device *ndev,
-				 struct ethtool_cmd *cmd)
-{
-	struct arc_emac_priv *priv = netdev_priv(ndev);
-
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	return phy_ethtool_sset(priv->phy_dev, cmd);
-}
-
-/**
  * arc_emac_get_drvinfo - Get EMAC driver information.
  * @ndev:	Pointer to net_device structure.
  * @info:	Pointer to ethtool_drvinfo structure.
@@ -137,10 +97,10 @@ static void arc_emac_get_drvinfo(struct net_device *ndev,
 }
 
 static const struct ethtool_ops arc_emac_ethtool_ops = {
-	.get_settings	= arc_emac_get_settings,
-	.set_settings	= arc_emac_set_settings,
 	.get_drvinfo	= arc_emac_get_drvinfo,
 	.get_link	= ethtool_op_get_link,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 #define FIRST_OR_LAST_MASK	(FIRST_MASK | LAST_MASK)
@@ -403,7 +363,7 @@ static void arc_emac_poll_controller(struct net_device *dev)
 static int arc_emac_open(struct net_device *ndev)
 {
 	struct arc_emac_priv *priv = netdev_priv(ndev);
-	struct phy_device *phy_dev = priv->phy_dev;
+	struct phy_device *phy_dev = ndev->phydev;
 	int i;
 
 	phy_dev->autoneg = AUTONEG_ENABLE;
@@ -474,7 +434,7 @@ static int arc_emac_open(struct net_device *ndev)
 	/* Enable EMAC */
 	arc_reg_or(priv, R_CTRL, EN_MASK);
 
-	phy_start_aneg(priv->phy_dev);
+	phy_start_aneg(ndev->phydev);
 
 	netif_start_queue(ndev);
 
@@ -772,6 +732,7 @@ int arc_emac_probe(struct net_device *ndev, int interface)
 	struct device *dev = ndev->dev.parent;
 	struct resource res_regs;
 	struct device_node *phy_node;
+	struct phy_device *phydev = NULL;
 	struct arc_emac_priv *priv;
 	const char *mac_addr;
 	unsigned int id, clock_frequency, irq;
@@ -887,16 +848,16 @@ int arc_emac_probe(struct net_device *ndev, int interface)
 		goto out_clken;
 	}
 
-	priv->phy_dev = of_phy_connect(ndev, phy_node, arc_emac_adjust_link, 0,
-				       interface);
-	if (!priv->phy_dev) {
+	phydev = of_phy_connect(ndev, phy_node, arc_emac_adjust_link, 0,
+				interface);
+	if (!phydev) {
 		dev_err(dev, "of_phy_connect() failed\n");
 		err = -ENODEV;
 		goto out_mdio;
 	}
 
 	dev_info(dev, "connected to %s phy with id 0x%x\n",
-		 priv->phy_dev->drv->name, priv->phy_dev->phy_id);
+		 phydev->drv->name, phydev->phy_id);
 
 	netif_napi_add(ndev, &priv->napi, arc_emac_poll, ARC_EMAC_NAPI_WEIGHT);
 
@@ -910,8 +871,7 @@ int arc_emac_probe(struct net_device *ndev, int interface)
 
 out_netif_api:
 	netif_napi_del(&priv->napi);
-	phy_disconnect(priv->phy_dev);
-	priv->phy_dev = NULL;
+	phy_disconnect(phydev);
 out_mdio:
 	arc_mdio_remove(priv);
 out_clken:
@@ -925,8 +885,7 @@ int arc_emac_remove(struct net_device *ndev)
 {
 	struct arc_emac_priv *priv = netdev_priv(ndev);
 
-	phy_disconnect(priv->phy_dev);
-	priv->phy_dev = NULL;
+	phy_disconnect(ndev->phydev);
 	arc_mdio_remove(priv);
 	unregister_netdev(ndev);
 	netif_napi_del(&priv->napi);
diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h
index d02c4240b7df..8fc93c5f6abc 100644
--- a/drivers/net/ethernet/atheros/alx/alx.h
+++ b/drivers/net/ethernet/atheros/alx/alx.h
@@ -96,10 +96,6 @@ struct alx_priv {
 	unsigned int rx_ringsz;
 	unsigned int rxbuf_size;
 
-	struct page  *rx_page;
-	unsigned int rx_page_offset;
-	unsigned int rx_frag_size;
-
 	struct napi_struct napi;
 	struct alx_tx_queue txq;
 	struct alx_rx_queue rxq;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index c98acdc0d14f..e708e360a9e3 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -70,35 +70,6 @@ static void alx_free_txbuf(struct alx_priv *alx, int entry)
 	}
 }
 
-static struct sk_buff *alx_alloc_skb(struct alx_priv *alx, gfp_t gfp)
-{
-	struct sk_buff *skb;
-	struct page *page;
-
-	if (alx->rx_frag_size > PAGE_SIZE)
-		return __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp);
-
-	page = alx->rx_page;
-	if (!page) {
-		alx->rx_page = page = alloc_page(gfp);
-		if (unlikely(!page))
-			return NULL;
-		alx->rx_page_offset = 0;
-	}
-
-	skb = build_skb(page_address(page) + alx->rx_page_offset,
-			alx->rx_frag_size);
-	if (likely(skb)) {
-		alx->rx_page_offset += alx->rx_frag_size;
-		if (alx->rx_page_offset >= PAGE_SIZE)
-			alx->rx_page = NULL;
-		else
-			get_page(page);
-	}
-	return skb;
-}
-
-
 static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 {
 	struct alx_rx_queue *rxq = &alx->rxq;
@@ -115,9 +86,22 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 	while (!cur_buf->skb && next != rxq->read_idx) {
 		struct alx_rfd *rfd = &rxq->rfd[cur];
 
-		skb = alx_alloc_skb(alx, gfp);
+		/*
+		 * When DMA RX address is set to something like
+		 * 0x....fc0, it will be very likely to cause DMA
+		 * RFD overflow issue.
+		 *
+		 * To work around it, we apply rx skb with 64 bytes
+		 * longer space, and offset the address whenever
+		 * 0x....fc0 is detected.
+		 */
+		skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size + 64, gfp);
 		if (!skb)
 			break;
+
+		if (((unsigned long)skb->data & 0xfff) == 0xfc0)
+			skb_reserve(skb, 64);
+
 		dma = dma_map_single(&alx->hw.pdev->dev,
 				     skb->data, alx->rxbuf_size,
 				     DMA_FROM_DEVICE);
@@ -153,7 +137,6 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 		alx_write_mem16(&alx->hw, ALX_RFD_PIDX, cur);
 	}
 
-
 	return count;
 }
 
@@ -622,11 +605,6 @@ static void alx_free_rings(struct alx_priv *alx)
 	kfree(alx->txq.bufs);
 	kfree(alx->rxq.bufs);
 
-	if (alx->rx_page) {
-		put_page(alx->rx_page);
-		alx->rx_page = NULL;
-	}
-
 	dma_free_coherent(&alx->hw.pdev->dev,
 			  alx->descmem.size,
 			  alx->descmem.virt,
@@ -681,7 +659,6 @@ static int alx_request_irq(struct alx_priv *alx)
 				  alx->dev->name, alx);
 		if (!err)
 			goto out;
-
 		/* fall back to legacy interrupt */
 		pci_disable_msi(alx->hw.pdev);
 	}
@@ -725,7 +702,6 @@ static int alx_init_sw(struct alx_priv *alx)
 	struct pci_dev *pdev = alx->hw.pdev;
 	struct alx_hw *hw = &alx->hw;
 	int err;
-	unsigned int head_size;
 
 	err = alx_identify_hw(alx);
 	if (err) {
@@ -741,12 +717,7 @@ static int alx_init_sw(struct alx_priv *alx)
 
 	hw->smb_timer = 400;
 	hw->mtu = alx->dev->mtu;
-
 	alx->rxbuf_size = ALX_MAX_FRAME_LEN(hw->mtu);
-	head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) +
-		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	alx->rx_frag_size = roundup_pow_of_two(head_size);
-
 	alx->tx_ringsz = 256;
 	alx->rx_ringsz = 512;
 	hw->imt = 200;
@@ -848,7 +819,6 @@ static int alx_change_mtu(struct net_device *netdev, int mtu)
 {
 	struct alx_priv *alx = netdev_priv(netdev);
 	int max_frame = ALX_MAX_FRAME_LEN(mtu);
-	unsigned int head_size;
 
 	if ((max_frame < ALX_MIN_FRAME_SIZE) ||
 	    (max_frame > ALX_MAX_FRAME_SIZE))
@@ -860,9 +830,6 @@ static int alx_change_mtu(struct net_device *netdev, int mtu)
 	netdev->mtu = mtu;
 	alx->hw.mtu = mtu;
 	alx->rxbuf_size = max(max_frame, ALX_DEF_RXBUF_SIZE);
-	head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) +
-		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	alx->rx_frag_size = roundup_pow_of_two(head_size);
 	netdev_update_features(netdev);
 	if (netif_running(netdev))
 		alx_reinit(alx);
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index 08a23e6b60e9..dc2c35dce216 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -631,7 +631,7 @@ static void nb8800_mac_config(struct net_device *dev)
 static void nb8800_pause_config(struct net_device *dev)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	u32 rxcr;
 
 	if (priv->pause_aneg) {
@@ -664,7 +664,7 @@ static void nb8800_pause_config(struct net_device *dev)
 static void nb8800_link_reconfigure(struct net_device *dev)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	int change = 0;
 
 	if (phydev->link) {
@@ -690,7 +690,7 @@ static void nb8800_link_reconfigure(struct net_device *dev)
 	}
 
 	if (change)
-		phy_print_status(priv->phydev);
+		phy_print_status(phydev);
 }
 
 static void nb8800_update_mac_addr(struct net_device *dev)
@@ -935,9 +935,10 @@ static int nb8800_dma_stop(struct net_device *dev)
 static void nb8800_pause_adv(struct net_device *dev)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = dev->phydev;
 	u32 adv = 0;
 
-	if (!priv->phydev)
+	if (!phydev)
 		return;
 
 	if (priv->pause_rx)
@@ -945,13 +946,14 @@ static void nb8800_pause_adv(struct net_device *dev)
 	if (priv->pause_tx)
 		adv ^= ADVERTISED_Asym_Pause;
 
-	priv->phydev->supported |= adv;
-	priv->phydev->advertising |= adv;
+	phydev->supported |= adv;
+	phydev->advertising |= adv;
 }
 
 static int nb8800_open(struct net_device *dev)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev;
 	int err;
 
 	/* clear any pending interrupts */
@@ -969,10 +971,10 @@ static int nb8800_open(struct net_device *dev)
 	nb8800_mac_rx(dev, true);
 	nb8800_mac_tx(dev, true);
 
-	priv->phydev = of_phy_connect(dev, priv->phy_node,
-				      nb8800_link_reconfigure, 0,
-				      priv->phy_mode);
-	if (!priv->phydev)
+	phydev = of_phy_connect(dev, priv->phy_node,
+				nb8800_link_reconfigure, 0,
+				priv->phy_mode);
+	if (!phydev)
 		goto err_free_irq;
 
 	nb8800_pause_adv(dev);
@@ -982,7 +984,7 @@ static int nb8800_open(struct net_device *dev)
 	netif_start_queue(dev);
 
 	nb8800_start_rx(dev);
-	phy_start(priv->phydev);
+	phy_start(phydev);
 
 	return 0;
 
@@ -997,8 +999,9 @@ err_free_dma:
 static int nb8800_stop(struct net_device *dev)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = dev->phydev;
 
-	phy_stop(priv->phydev);
+	phy_stop(phydev);
 
 	netif_stop_queue(dev);
 	napi_disable(&priv->napi);
@@ -1007,8 +1010,7 @@ static int nb8800_stop(struct net_device *dev)
 	nb8800_mac_rx(dev, false);
 	nb8800_mac_tx(dev, false);
 
-	phy_disconnect(priv->phydev);
-	priv->phydev = NULL;
+	phy_disconnect(phydev);
 
 	free_irq(dev->irq, dev);
 
@@ -1019,9 +1021,7 @@ static int nb8800_stop(struct net_device *dev)
 
 static int nb8800_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct nb8800_priv *priv = netdev_priv(dev);
-
-	return phy_mii_ioctl(priv->phydev, rq, cmd);
+	return phy_mii_ioctl(dev->phydev, rq, cmd);
 }
 
 static const struct net_device_ops nb8800_netdev_ops = {
@@ -1035,34 +1035,14 @@ static const struct net_device_ops nb8800_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-static int nb8800_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct nb8800_priv *priv = netdev_priv(dev);
-
-	if (!priv->phydev)
-		return -ENODEV;
-
-	return phy_ethtool_gset(priv->phydev, cmd);
-}
-
-static int nb8800_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct nb8800_priv *priv = netdev_priv(dev);
-
-	if (!priv->phydev)
-		return -ENODEV;
-
-	return phy_ethtool_sset(priv->phydev, cmd);
-}
-
 static int nb8800_nway_reset(struct net_device *dev)
 {
-	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = dev->phydev;
 
-	if (!priv->phydev)
+	if (!phydev)
 		return -ENODEV;
 
-	return genphy_restart_aneg(priv->phydev);
+	return genphy_restart_aneg(phydev);
 }
 
 static void nb8800_get_pauseparam(struct net_device *dev,
@@ -1079,6 +1059,7 @@ static int nb8800_set_pauseparam(struct net_device *dev,
 				 struct ethtool_pauseparam *pp)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = dev->phydev;
 
 	priv->pause_aneg = pp->autoneg;
 	priv->pause_rx = pp->rx_pause;
@@ -1088,8 +1069,8 @@ static int nb8800_set_pauseparam(struct net_device *dev,
 
 	if (!priv->pause_aneg)
 		nb8800_pause_config(dev);
-	else if (priv->phydev)
-		phy_start_aneg(priv->phydev);
+	else if (phydev)
+		phy_start_aneg(phydev);
 
 	return 0;
 }
@@ -1182,8 +1163,6 @@ static void nb8800_get_ethtool_stats(struct net_device *dev,
 }
 
 static const struct ethtool_ops nb8800_ethtool_ops = {
-	.get_settings		= nb8800_get_settings,
-	.set_settings		= nb8800_set_settings,
 	.nway_reset		= nb8800_nway_reset,
 	.get_link		= ethtool_op_get_link,
 	.get_pauseparam		= nb8800_get_pauseparam,
@@ -1191,6 +1170,8 @@ static const struct ethtool_ops nb8800_ethtool_ops = {
 	.get_sset_count		= nb8800_get_sset_count,
 	.get_strings		= nb8800_get_strings,
 	.get_ethtool_stats	= nb8800_get_ethtool_stats,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
 static int nb8800_hw_init(struct net_device *dev)
diff --git a/drivers/net/ethernet/aurora/nb8800.h b/drivers/net/ethernet/aurora/nb8800.h
index e5adbc2aac9f..6ec4a956e1e5 100644
--- a/drivers/net/ethernet/aurora/nb8800.h
+++ b/drivers/net/ethernet/aurora/nb8800.h
@@ -284,7 +284,6 @@ struct nb8800_priv {
 
 	struct mii_bus			*mii_bus;
 	struct device_node		*phy_node;
-	struct phy_device		*phydev;
 
 	/* PHY connection type from DT */
 	int				phy_mode;
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 18042c2460bd..d74a92e1c27d 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -139,26 +139,6 @@ config BNX2X_SRIOV
 	  Virtualization support in the 578xx and 57712 products. This
 	  allows for virtual function acceleration in virtual environments.
 
-config BNX2X_VXLAN
-	bool "Virtual eXtensible Local Area Network support"
-	default n
-	depends on BNX2X && VXLAN && !(BNX2X=y && VXLAN=m)
-	---help---
-	  This enables hardward offload support for VXLAN protocol over the
-	  NetXtremeII series adapters.
-	  Say Y here if you want to enable hardware offload support for
-	  Virtual eXtensible Local Area Network (VXLAN) in the driver.
-
-config BNX2X_GENEVE
-	bool "Generic Network Virtualization Encapsulation (GENEVE) support"
-	depends on BNX2X && GENEVE && !(BNX2X=y && GENEVE=m)
-	---help---
-          This allows one to create GENEVE virtual interfaces that provide
-          Layer 2 Networks over Layer 3 Networks. GENEVE is often used
-          to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to enable hardware offload support for
-	  Generic Network Virtualization Encapsulation (GENEVE) in the driver.
-
 config BGMAC
 	tristate "BCMA bus GBit core support"
 	depends on BCMA && BCMA_HOST_SOC
@@ -186,7 +166,6 @@ config SYSTEMPORT
 config BNXT
 	tristate "Broadcom NetXtreme-C/E support"
 	depends on PCI
-	depends on VXLAN || VXLAN=n
 	select FW_LOADER
 	select LIBCRC32C
 	---help---
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 543bf38105c9..834afbb51aff 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -96,28 +96,6 @@ static inline void tdma_port_write_desc_addr(struct bcm_sysport_priv *priv,
 }
 
 /* Ethtool operations */
-static int bcm_sysport_set_settings(struct net_device *dev,
-				    struct ethtool_cmd *cmd)
-{
-	struct bcm_sysport_priv *priv = netdev_priv(dev);
-
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	return phy_ethtool_sset(priv->phydev, cmd);
-}
-
-static int bcm_sysport_get_settings(struct net_device *dev,
-				    struct ethtool_cmd *cmd)
-{
-	struct bcm_sysport_priv *priv = netdev_priv(dev);
-
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	return phy_ethtool_gset(priv->phydev, cmd);
-}
-
 static int bcm_sysport_set_rx_csum(struct net_device *dev,
 				   netdev_features_t wanted)
 {
@@ -1127,7 +1105,7 @@ static void bcm_sysport_tx_timeout(struct net_device *dev)
 static void bcm_sysport_adj_link(struct net_device *dev)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	unsigned int changed = 0;
 	u32 cmd_bits = 0, reg;
 
@@ -1182,7 +1160,7 @@ static void bcm_sysport_adj_link(struct net_device *dev)
 		umac_writel(priv, reg, UMAC_CMD);
 	}
 
-	phy_print_status(priv->phydev);
+	phy_print_status(phydev);
 }
 
 static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
@@ -1525,7 +1503,7 @@ static void bcm_sysport_netif_start(struct net_device *dev)
 	/* Enable RX interrupt and TX ring full interrupt */
 	intrl2_0_mask_clear(priv, INTRL2_0_RDMA_MBDONE | INTRL2_0_TX_RING_FULL);
 
-	phy_start(priv->phydev);
+	phy_start(dev->phydev);
 
 	/* Enable TX interrupts for the 32 TXQs */
 	intrl2_1_mask_clear(priv, 0xffffffff);
@@ -1546,6 +1524,7 @@ static void rbuf_init(struct bcm_sysport_priv *priv)
 static int bcm_sysport_open(struct net_device *dev)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev;
 	unsigned int i;
 	int ret;
 
@@ -1570,9 +1549,9 @@ static int bcm_sysport_open(struct net_device *dev)
 	/* Read CRC forward */
 	priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD);
 
-	priv->phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link,
-					0, priv->phy_interface);
-	if (!priv->phydev) {
+	phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link,
+				0, priv->phy_interface);
+	if (!phydev) {
 		netdev_err(dev, "could not attach to PHY\n");
 		return -ENODEV;
 	}
@@ -1650,7 +1629,7 @@ out_free_tx_ring:
 out_free_irq0:
 	free_irq(priv->irq0, dev);
 out_phy_disconnect:
-	phy_disconnect(priv->phydev);
+	phy_disconnect(phydev);
 	return ret;
 }
 
@@ -1661,7 +1640,7 @@ static void bcm_sysport_netif_stop(struct net_device *dev)
 	/* stop all software from updating hardware */
 	netif_tx_stop_all_queues(dev);
 	napi_disable(&priv->napi);
-	phy_stop(priv->phydev);
+	phy_stop(dev->phydev);
 
 	/* mask all interrupts */
 	intrl2_0_mask_set(priv, 0xffffffff);
@@ -1708,14 +1687,12 @@ static int bcm_sysport_stop(struct net_device *dev)
 	free_irq(priv->irq1, dev);
 
 	/* Disconnect from PHY */
-	phy_disconnect(priv->phydev);
+	phy_disconnect(dev->phydev);
 
 	return 0;
 }
 
 static struct ethtool_ops bcm_sysport_ethtool_ops = {
-	.get_settings		= bcm_sysport_get_settings,
-	.set_settings		= bcm_sysport_set_settings,
 	.get_drvinfo		= bcm_sysport_get_drvinfo,
 	.get_msglevel		= bcm_sysport_get_msglvl,
 	.set_msglevel		= bcm_sysport_set_msglvl,
@@ -1727,6 +1704,8 @@ static struct ethtool_ops bcm_sysport_ethtool_ops = {
 	.set_wol		= bcm_sysport_set_wol,
 	.get_coalesce		= bcm_sysport_get_coalesce,
 	.set_coalesce		= bcm_sysport_set_coalesce,
+	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
 static const struct net_device_ops bcm_sysport_netdev_ops = {
@@ -1929,7 +1908,7 @@ static int bcm_sysport_suspend(struct device *d)
 
 	bcm_sysport_netif_stop(dev);
 
-	phy_suspend(priv->phydev);
+	phy_suspend(dev->phydev);
 
 	netif_device_detach(dev);
 
@@ -2055,7 +2034,7 @@ static int bcm_sysport_resume(struct device *d)
 		goto out_free_rx_ring;
 	}
 
-	phy_resume(priv->phydev);
+	phy_resume(dev->phydev);
 
 	bcm_sysport_netif_start(dev);
 
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index f28bf545d7f4..1c82e3da69a7 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -670,7 +670,6 @@ struct bcm_sysport_priv {
 
 	/* PHY device */
 	struct device_node	*phy_dn;
-	struct phy_device	*phydev;
 	phy_interface_t		phy_interface;
 	int			old_pause;
 	int			old_link;
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index ee5f431ab32a..b045dc072c40 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -246,6 +246,8 @@ err_dma_head:
 
 err_drop:
 	dev_kfree_skb(skb);
+	net_dev->stats.tx_dropped++;
+	net_dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
 }
 
@@ -267,15 +269,16 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring)
 	while (ring->start != ring->end) {
 		int slot_idx = ring->start % BGMAC_TX_RING_SLOTS;
 		struct bgmac_slot_info *slot = &ring->slots[slot_idx];
-		u32 ctl1;
+		u32 ctl0, ctl1;
 		int len;
 
 		if (slot_idx == empty_slot)
 			break;
 
+		ctl0 = le32_to_cpu(ring->cpu_base[slot_idx].ctl0);
 		ctl1 = le32_to_cpu(ring->cpu_base[slot_idx].ctl1);
 		len = ctl1 & BGMAC_DESC_CTL1_LEN;
-		if (ctl1 & BGMAC_DESC_CTL0_SOF)
+		if (ctl0 & BGMAC_DESC_CTL0_SOF)
 			/* Unmap no longer used buffer */
 			dma_unmap_single(dma_dev, slot->dma_addr, len,
 					 DMA_TO_DEVICE);
@@ -284,6 +287,8 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring)
 				       DMA_TO_DEVICE);
 
 		if (slot->skb) {
+			bgmac->net_dev->stats.tx_bytes += slot->skb->len;
+			bgmac->net_dev->stats.tx_packets++;
 			bytes_compl += slot->skb->len;
 			pkts_compl++;
 
@@ -464,6 +469,7 @@ static int bgmac_dma_rx_read(struct bgmac *bgmac, struct bgmac_dma_ring *ring,
 				bgmac_err(bgmac, "Found poisoned packet at slot %d, DMA issue!\n",
 					  ring->start);
 				put_page(virt_to_head_page(buf));
+				bgmac->net_dev->stats.rx_errors++;
 				break;
 			}
 
@@ -471,6 +477,8 @@ static int bgmac_dma_rx_read(struct bgmac *bgmac, struct bgmac_dma_ring *ring,
 				bgmac_err(bgmac, "Found oversized packet at slot %d, DMA issue!\n",
 					  ring->start);
 				put_page(virt_to_head_page(buf));
+				bgmac->net_dev->stats.rx_length_errors++;
+				bgmac->net_dev->stats.rx_errors++;
 				break;
 			}
 
@@ -481,6 +489,7 @@ static int bgmac_dma_rx_read(struct bgmac *bgmac, struct bgmac_dma_ring *ring,
 			if (unlikely(!skb)) {
 				bgmac_err(bgmac, "build_skb failed\n");
 				put_page(virt_to_head_page(buf));
+				bgmac->net_dev->stats.rx_errors++;
 				break;
 			}
 			skb_put(skb, BGMAC_RX_FRAME_OFFSET +
@@ -490,6 +499,8 @@ static int bgmac_dma_rx_read(struct bgmac *bgmac, struct bgmac_dma_ring *ring,
 
 			skb_checksum_none_assert(skb);
 			skb->protocol = eth_type_trans(skb, bgmac->net_dev);
+			bgmac->net_dev->stats.rx_bytes += len;
+			bgmac->net_dev->stats.rx_packets++;
 			napi_gro_receive(&bgmac->napi, skb);
 			handled++;
 		} while (0);
@@ -1310,9 +1321,10 @@ static int bgmac_open(struct net_device *net_dev)
 	}
 	napi_enable(&bgmac->napi);
 
-	phy_start(bgmac->phy_dev);
+	phy_start(net_dev->phydev);
+
+	netif_start_queue(net_dev);
 
-	netif_carrier_on(net_dev);
 	return 0;
 }
 
@@ -1322,7 +1334,7 @@ static int bgmac_stop(struct net_device *net_dev)
 
 	netif_carrier_off(net_dev);
 
-	phy_stop(bgmac->phy_dev);
+	phy_stop(net_dev->phydev);
 
 	napi_disable(&bgmac->napi);
 	bgmac_chip_intrs_off(bgmac);
@@ -1360,12 +1372,10 @@ static int bgmac_set_mac_address(struct net_device *net_dev, void *addr)
 
 static int bgmac_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
 {
-	struct bgmac *bgmac = netdev_priv(net_dev);
-
 	if (!netif_running(net_dev))
 		return -EINVAL;
 
-	return phy_mii_ioctl(bgmac->phy_dev, ifr, cmd);
+	return phy_mii_ioctl(net_dev->phydev, ifr, cmd);
 }
 
 static const struct net_device_ops bgmac_netdev_ops = {
@@ -1382,20 +1392,125 @@ static const struct net_device_ops bgmac_netdev_ops = {
  * ethtool_ops
  **************************************************/
 
-static int bgmac_get_settings(struct net_device *net_dev,
-			      struct ethtool_cmd *cmd)
+struct bgmac_stat {
+	u8 size;
+	u32 offset;
+	const char *name;
+};
+
+static struct bgmac_stat bgmac_get_strings_stats[] = {
+	{ 8, BGMAC_TX_GOOD_OCTETS, "tx_good_octets" },
+	{ 4, BGMAC_TX_GOOD_PKTS, "tx_good" },
+	{ 8, BGMAC_TX_OCTETS, "tx_octets" },
+	{ 4, BGMAC_TX_PKTS, "tx_pkts" },
+	{ 4, BGMAC_TX_BROADCAST_PKTS, "tx_broadcast" },
+	{ 4, BGMAC_TX_MULTICAST_PKTS, "tx_multicast" },
+	{ 4, BGMAC_TX_LEN_64, "tx_64" },
+	{ 4, BGMAC_TX_LEN_65_TO_127, "tx_65_127" },
+	{ 4, BGMAC_TX_LEN_128_TO_255, "tx_128_255" },
+	{ 4, BGMAC_TX_LEN_256_TO_511, "tx_256_511" },
+	{ 4, BGMAC_TX_LEN_512_TO_1023, "tx_512_1023" },
+	{ 4, BGMAC_TX_LEN_1024_TO_1522, "tx_1024_1522" },
+	{ 4, BGMAC_TX_LEN_1523_TO_2047, "tx_1523_2047" },
+	{ 4, BGMAC_TX_LEN_2048_TO_4095, "tx_2048_4095" },
+	{ 4, BGMAC_TX_LEN_4096_TO_8191, "tx_4096_8191" },
+	{ 4, BGMAC_TX_LEN_8192_TO_MAX, "tx_8192_max" },
+	{ 4, BGMAC_TX_JABBER_PKTS, "tx_jabber" },
+	{ 4, BGMAC_TX_OVERSIZE_PKTS, "tx_oversize" },
+	{ 4, BGMAC_TX_FRAGMENT_PKTS, "tx_fragment" },
+	{ 4, BGMAC_TX_UNDERRUNS, "tx_underruns" },
+	{ 4, BGMAC_TX_TOTAL_COLS, "tx_total_cols" },
+	{ 4, BGMAC_TX_SINGLE_COLS, "tx_single_cols" },
+	{ 4, BGMAC_TX_MULTIPLE_COLS, "tx_multiple_cols" },
+	{ 4, BGMAC_TX_EXCESSIVE_COLS, "tx_excessive_cols" },
+	{ 4, BGMAC_TX_LATE_COLS, "tx_late_cols" },
+	{ 4, BGMAC_TX_DEFERED, "tx_defered" },
+	{ 4, BGMAC_TX_CARRIER_LOST, "tx_carrier_lost" },
+	{ 4, BGMAC_TX_PAUSE_PKTS, "tx_pause" },
+	{ 4, BGMAC_TX_UNI_PKTS, "tx_unicast" },
+	{ 4, BGMAC_TX_Q0_PKTS, "tx_q0" },
+	{ 8, BGMAC_TX_Q0_OCTETS, "tx_q0_octets" },
+	{ 4, BGMAC_TX_Q1_PKTS, "tx_q1" },
+	{ 8, BGMAC_TX_Q1_OCTETS, "tx_q1_octets" },
+	{ 4, BGMAC_TX_Q2_PKTS, "tx_q2" },
+	{ 8, BGMAC_TX_Q2_OCTETS, "tx_q2_octets" },
+	{ 4, BGMAC_TX_Q3_PKTS, "tx_q3" },
+	{ 8, BGMAC_TX_Q3_OCTETS, "tx_q3_octets" },
+	{ 8, BGMAC_RX_GOOD_OCTETS, "rx_good_octets" },
+	{ 4, BGMAC_RX_GOOD_PKTS, "rx_good" },
+	{ 8, BGMAC_RX_OCTETS, "rx_octets" },
+	{ 4, BGMAC_RX_PKTS, "rx_pkts" },
+	{ 4, BGMAC_RX_BROADCAST_PKTS, "rx_broadcast" },
+	{ 4, BGMAC_RX_MULTICAST_PKTS, "rx_multicast" },
+	{ 4, BGMAC_RX_LEN_64, "rx_64" },
+	{ 4, BGMAC_RX_LEN_65_TO_127, "rx_65_127" },
+	{ 4, BGMAC_RX_LEN_128_TO_255, "rx_128_255" },
+	{ 4, BGMAC_RX_LEN_256_TO_511, "rx_256_511" },
+	{ 4, BGMAC_RX_LEN_512_TO_1023, "rx_512_1023" },
+	{ 4, BGMAC_RX_LEN_1024_TO_1522, "rx_1024_1522" },
+	{ 4, BGMAC_RX_LEN_1523_TO_2047, "rx_1523_2047" },
+	{ 4, BGMAC_RX_LEN_2048_TO_4095, "rx_2048_4095" },
+	{ 4, BGMAC_RX_LEN_4096_TO_8191, "rx_4096_8191" },
+	{ 4, BGMAC_RX_LEN_8192_TO_MAX, "rx_8192_max" },
+	{ 4, BGMAC_RX_JABBER_PKTS, "rx_jabber" },
+	{ 4, BGMAC_RX_OVERSIZE_PKTS, "rx_oversize" },
+	{ 4, BGMAC_RX_FRAGMENT_PKTS, "rx_fragment" },
+	{ 4, BGMAC_RX_MISSED_PKTS, "rx_missed" },
+	{ 4, BGMAC_RX_CRC_ALIGN_ERRS, "rx_crc_align" },
+	{ 4, BGMAC_RX_UNDERSIZE, "rx_undersize" },
+	{ 4, BGMAC_RX_CRC_ERRS, "rx_crc" },
+	{ 4, BGMAC_RX_ALIGN_ERRS, "rx_align" },
+	{ 4, BGMAC_RX_SYMBOL_ERRS, "rx_symbol" },
+	{ 4, BGMAC_RX_PAUSE_PKTS, "rx_pause" },
+	{ 4, BGMAC_RX_NONPAUSE_PKTS, "rx_nonpause" },
+	{ 4, BGMAC_RX_SACHANGES, "rx_sa_changes" },
+	{ 4, BGMAC_RX_UNI_PKTS, "rx_unicast" },
+};
+
+#define BGMAC_STATS_LEN	ARRAY_SIZE(bgmac_get_strings_stats)
+
+static int bgmac_get_sset_count(struct net_device *dev, int string_set)
 {
-	struct bgmac *bgmac = netdev_priv(net_dev);
+	switch (string_set) {
+	case ETH_SS_STATS:
+		return BGMAC_STATS_LEN;
+	}
 
-	return phy_ethtool_gset(bgmac->phy_dev, cmd);
+	return -EOPNOTSUPP;
 }
 
-static int bgmac_set_settings(struct net_device *net_dev,
-			      struct ethtool_cmd *cmd)
+static void bgmac_get_strings(struct net_device *dev, u32 stringset,
+			      u8 *data)
 {
-	struct bgmac *bgmac = netdev_priv(net_dev);
+	int i;
+
+	if (stringset != ETH_SS_STATS)
+		return;
 
-	return phy_ethtool_sset(bgmac->phy_dev, cmd);
+	for (i = 0; i < BGMAC_STATS_LEN; i++)
+		strlcpy(data + i * ETH_GSTRING_LEN,
+			bgmac_get_strings_stats[i].name, ETH_GSTRING_LEN);
+}
+
+static void bgmac_get_ethtool_stats(struct net_device *dev,
+				    struct ethtool_stats *ss, uint64_t *data)
+{
+	struct bgmac *bgmac = netdev_priv(dev);
+	const struct bgmac_stat *s;
+	unsigned int i;
+	u64 val;
+
+	if (!netif_running(dev))
+		return;
+
+	for (i = 0; i < BGMAC_STATS_LEN; i++) {
+		s = &bgmac_get_strings_stats[i];
+		val = 0;
+		if (s->size == 8)
+			val = (u64)bgmac_read(bgmac, s->offset + 4) << 32;
+		val |= bgmac_read(bgmac, s->offset);
+		data[i] = val;
+	}
 }
 
 static void bgmac_get_drvinfo(struct net_device *net_dev,
@@ -1406,9 +1521,12 @@ static void bgmac_get_drvinfo(struct net_device *net_dev,
 }
 
 static const struct ethtool_ops bgmac_ethtool_ops = {
-	.get_settings		= bgmac_get_settings,
-	.set_settings		= bgmac_set_settings,
+	.get_strings		= bgmac_get_strings,
+	.get_sset_count		= bgmac_get_sset_count,
+	.get_ethtool_stats	= bgmac_get_ethtool_stats,
 	.get_drvinfo		= bgmac_get_drvinfo,
+	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
 /**************************************************
@@ -1429,7 +1547,7 @@ static int bgmac_mii_write(struct mii_bus *bus, int mii_id, int regnum,
 static void bgmac_adjust_link(struct net_device *net_dev)
 {
 	struct bgmac *bgmac = netdev_priv(net_dev);
-	struct phy_device *phy_dev = bgmac->phy_dev;
+	struct phy_device *phy_dev = net_dev->phydev;
 	bool update = false;
 
 	if (phy_dev->link) {
@@ -1473,8 +1591,6 @@ static int bgmac_fixed_phy_register(struct bgmac *bgmac)
 		return err;
 	}
 
-	bgmac->phy_dev = phy_dev;
-
 	return err;
 }
 
@@ -1519,7 +1635,6 @@ static int bgmac_mii_register(struct bgmac *bgmac)
 		err = PTR_ERR(phy_dev);
 		goto err_unregister_bus;
 	}
-	bgmac->phy_dev = phy_dev;
 
 	return err;
 
@@ -1588,6 +1703,7 @@ static int bgmac_probe(struct bcma_device *core)
 	bgmac->net_dev = net_dev;
 	bgmac->core = core;
 	bcma_set_drvdata(core, bgmac);
+	SET_NETDEV_DEV(net_dev, &core->dev);
 
 	/* Defaults */
 	memcpy(bgmac->net_dev->dev_addr, mac, ETH_ALEN);
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index 9a03c142b742..99beb181f577 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -123,7 +123,7 @@
 #define BGMAC_TX_LEN_1024_TO_1522		0x334
 #define BGMAC_TX_LEN_1523_TO_2047		0x338
 #define BGMAC_TX_LEN_2048_TO_4095		0x33c
-#define BGMAC_TX_LEN_4095_TO_8191		0x340
+#define BGMAC_TX_LEN_4096_TO_8191		0x340
 #define BGMAC_TX_LEN_8192_TO_MAX		0x344
 #define BGMAC_TX_JABBER_PKTS			0x348		/* Error */
 #define BGMAC_TX_OVERSIZE_PKTS			0x34c		/* Error */
@@ -166,7 +166,7 @@
 #define BGMAC_RX_LEN_1024_TO_1522		0x3e4
 #define BGMAC_RX_LEN_1523_TO_2047		0x3e8
 #define BGMAC_RX_LEN_2048_TO_4095		0x3ec
-#define BGMAC_RX_LEN_4095_TO_8191		0x3f0
+#define BGMAC_RX_LEN_4096_TO_8191		0x3f0
 #define BGMAC_RX_LEN_8192_TO_MAX		0x3f4
 #define BGMAC_RX_JABBER_PKTS			0x3f8		/* Error */
 #define BGMAC_RX_OVERSIZE_PKTS			0x3fc		/* Error */
@@ -441,7 +441,6 @@ struct bgmac {
 	struct net_device *net_dev;
 	struct napi_struct napi;
 	struct mii_bus *mii_bus;
-	struct phy_device *phy_dev;
 
 	/* DMA */
 	struct bgmac_dma_ring tx_ring[BGMAC_MAX_TX_RINGS];
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c5fe915870ad..97e892511666 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -59,9 +59,6 @@
 #include <linux/semaphore.h>
 #include <linux/stringify.h>
 #include <linux/vmalloc.h>
-#if IS_ENABLED(CONFIG_BNX2X_GENEVE)
-#include <net/geneve.h>
-#endif
 #include "bnx2x.h"
 #include "bnx2x_init.h"
 #include "bnx2x_init_ops.h"
@@ -10076,7 +10073,6 @@ static void bnx2x_parity_recover(struct bnx2x *bp)
 	}
 }
 
-#if defined(CONFIG_BNX2X_VXLAN) || IS_ENABLED(CONFIG_BNX2X_GENEVE)
 static int bnx2x_udp_port_update(struct bnx2x *bp)
 {
 	struct bnx2x_func_switch_update_params *switch_update_params;
@@ -10177,47 +10173,42 @@ static void __bnx2x_del_udp_port(struct bnx2x *bp, u16 port,
 		DP(BNX2X_MSG_SP, "Deleted UDP tunnel [%d] port %d\n",
 		   type, port);
 }
-#endif
-
-#ifdef CONFIG_BNX2X_VXLAN
-static void bnx2x_add_vxlan_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
-{
-	struct bnx2x *bp = netdev_priv(netdev);
-	u16 t_port = ntohs(port);
-
-	__bnx2x_add_udp_port(bp, t_port, BNX2X_UDP_PORT_VXLAN);
-}
-
-static void bnx2x_del_vxlan_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
-{
-	struct bnx2x *bp = netdev_priv(netdev);
-	u16 t_port = ntohs(port);
-
-	__bnx2x_del_udp_port(bp, t_port, BNX2X_UDP_PORT_VXLAN);
-}
-#endif
 
-#if IS_ENABLED(CONFIG_BNX2X_GENEVE)
-static void bnx2x_add_geneve_port(struct net_device *netdev,
-				  sa_family_t sa_family, __be16 port)
+static void bnx2x_udp_tunnel_add(struct net_device *netdev,
+				 struct udp_tunnel_info *ti)
 {
 	struct bnx2x *bp = netdev_priv(netdev);
-	u16 t_port = ntohs(port);
+	u16 t_port = ntohs(ti->port);
 
-	__bnx2x_add_udp_port(bp, t_port, BNX2X_UDP_PORT_GENEVE);
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		__bnx2x_add_udp_port(bp, t_port, BNX2X_UDP_PORT_VXLAN);
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		__bnx2x_add_udp_port(bp, t_port, BNX2X_UDP_PORT_GENEVE);
+		break;
+	default:
+		break;
+	}
 }
 
-static void bnx2x_del_geneve_port(struct net_device *netdev,
-				  sa_family_t sa_family, __be16 port)
+static void bnx2x_udp_tunnel_del(struct net_device *netdev,
+				 struct udp_tunnel_info *ti)
 {
 	struct bnx2x *bp = netdev_priv(netdev);
-	u16 t_port = ntohs(port);
+	u16 t_port = ntohs(ti->port);
 
-	__bnx2x_del_udp_port(bp, t_port, BNX2X_UDP_PORT_GENEVE);
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		__bnx2x_del_udp_port(bp, t_port, BNX2X_UDP_PORT_VXLAN);
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		__bnx2x_del_udp_port(bp, t_port, BNX2X_UDP_PORT_GENEVE);
+		break;
+	default:
+		break;
+	}
 }
-#endif
 
 static int bnx2x_close(struct net_device *dev);
 
@@ -10325,7 +10316,6 @@ sp_rtnl_not_reset:
 			       &bp->sp_rtnl_state))
 		bnx2x_update_mng_version(bp);
 
-#if defined(CONFIG_BNX2X_VXLAN) || IS_ENABLED(CONFIG_BNX2X_GENEVE)
 	if (test_and_clear_bit(BNX2X_SP_RTNL_CHANGE_UDP_PORT,
 			       &bp->sp_rtnl_state)) {
 		if (bnx2x_udp_port_update(bp)) {
@@ -10335,20 +10325,14 @@ sp_rtnl_not_reset:
 			       BNX2X_UDP_PORT_MAX);
 		} else {
 			/* Since we don't store additional port information,
-			 * if no port is configured for any feature ask for
+			 * if no ports are configured for any feature ask for
 			 * information about currently configured ports.
 			 */
-#ifdef CONFIG_BNX2X_VXLAN
-			if (!bp->udp_tunnel_ports[BNX2X_UDP_PORT_VXLAN].count)
-				vxlan_get_rx_port(bp->dev);
-#endif
-#if IS_ENABLED(CONFIG_BNX2X_GENEVE)
-			if (!bp->udp_tunnel_ports[BNX2X_UDP_PORT_GENEVE].count)
-				geneve_get_rx_port(bp->dev);
-#endif
+			if (!bp->udp_tunnel_ports[BNX2X_UDP_PORT_VXLAN].count &&
+			    !bp->udp_tunnel_ports[BNX2X_UDP_PORT_GENEVE].count)
+				udp_tunnel_get_rx_info(bp->dev);
 		}
 	}
-#endif
 
 	/* work which needs rtnl lock not-taken (as it takes the lock itself and
 	 * can be called from other contexts as well)
@@ -12551,14 +12535,8 @@ static int bnx2x_open(struct net_device *dev)
 	if (rc)
 		return rc;
 
-#ifdef CONFIG_BNX2X_VXLAN
-	if (IS_PF(bp))
-		vxlan_get_rx_port(dev);
-#endif
-#if IS_ENABLED(CONFIG_BNX2X_GENEVE)
 	if (IS_PF(bp))
-		geneve_get_rx_port(dev);
-#endif
+		udp_tunnel_get_rx_info(dev);
 
 	return 0;
 }
@@ -12895,52 +12873,71 @@ static int __bnx2x_vlan_configure_vid(struct bnx2x *bp, u16 vid, bool add)
 	return rc;
 }
 
-int bnx2x_vlan_reconfigure_vid(struct bnx2x *bp)
+static int bnx2x_vlan_configure_vid_list(struct bnx2x *bp)
 {
 	struct bnx2x_vlan_entry *vlan;
 	int rc = 0;
 
-	if (!bp->vlan_cnt) {
-		DP(NETIF_MSG_IFUP, "No need to re-configure vlan filters\n");
-		return 0;
-	}
-
+	/* Configure all non-configured entries */
 	list_for_each_entry(vlan, &bp->vlan_reg, link) {
-		/* Prepare for cleanup in case of errors */
-		if (rc) {
-			vlan->hw = false;
-			continue;
-		}
-
-		if (!vlan->hw)
+		if (vlan->hw)
 			continue;
 
-		DP(NETIF_MSG_IFUP, "Re-configuring vlan 0x%04x\n", vlan->vid);
+		if (bp->vlan_cnt >= bp->vlan_credit)
+			return -ENOBUFS;
 
 		rc = __bnx2x_vlan_configure_vid(bp, vlan->vid, true);
 		if (rc) {
-			BNX2X_ERR("Unable to configure VLAN %d\n", vlan->vid);
-			vlan->hw = false;
-			rc = -EINVAL;
-			continue;
+			BNX2X_ERR("Unable to config VLAN %d\n", vlan->vid);
+			return rc;
 		}
+
+		DP(NETIF_MSG_IFUP, "HW configured for VLAN %d\n", vlan->vid);
+		vlan->hw = true;
+		bp->vlan_cnt++;
 	}
 
-	return rc;
+	return 0;
+}
+
+static void bnx2x_vlan_configure(struct bnx2x *bp, bool set_rx_mode)
+{
+	bool need_accept_any_vlan;
+
+	need_accept_any_vlan = !!bnx2x_vlan_configure_vid_list(bp);
+
+	if (bp->accept_any_vlan != need_accept_any_vlan) {
+		bp->accept_any_vlan = need_accept_any_vlan;
+		DP(NETIF_MSG_IFUP, "Accept all VLAN %s\n",
+		   bp->accept_any_vlan ? "raised" : "cleared");
+		if (set_rx_mode) {
+			if (IS_PF(bp))
+				bnx2x_set_rx_mode_inner(bp);
+			else
+				bnx2x_vfpf_storm_rx_mode(bp);
+		}
+	}
+}
+
+int bnx2x_vlan_reconfigure_vid(struct bnx2x *bp)
+{
+	struct bnx2x_vlan_entry *vlan;
+
+	/* The hw forgot all entries after reload */
+	list_for_each_entry(vlan, &bp->vlan_reg, link)
+		vlan->hw = false;
+	bp->vlan_cnt = 0;
+
+	/* Don't set rx mode here. Our caller will do it. */
+	bnx2x_vlan_configure(bp, false);
+
+	return 0;
 }
 
 static int bnx2x_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	struct bnx2x_vlan_entry *vlan;
-	bool hw = false;
-	int rc = 0;
-
-	if (!netif_running(bp->dev)) {
-		DP(NETIF_MSG_IFUP,
-		   "Ignoring VLAN configuration the interface is down\n");
-		return -EFAULT;
-	}
 
 	DP(NETIF_MSG_IFUP, "Adding VLAN %d\n", vid);
 
@@ -12948,93 +12945,47 @@ static int bnx2x_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
 	if (!vlan)
 		return -ENOMEM;
 
-	bp->vlan_cnt++;
-	if (bp->vlan_cnt > bp->vlan_credit && !bp->accept_any_vlan) {
-		DP(NETIF_MSG_IFUP, "Accept all VLAN raised\n");
-		bp->accept_any_vlan = true;
-		if (IS_PF(bp))
-			bnx2x_set_rx_mode_inner(bp);
-		else
-			bnx2x_vfpf_storm_rx_mode(bp);
-	} else if (bp->vlan_cnt <= bp->vlan_credit) {
-		rc = __bnx2x_vlan_configure_vid(bp, vid, true);
-		hw = true;
-	}
-
 	vlan->vid = vid;
-	vlan->hw = hw;
-
-	if (!rc) {
-		list_add(&vlan->link, &bp->vlan_reg);
-	} else {
-		bp->vlan_cnt--;
-		kfree(vlan);
-	}
+	vlan->hw = false;
+	list_add_tail(&vlan->link, &bp->vlan_reg);
 
-	DP(NETIF_MSG_IFUP, "Adding VLAN result %d\n", rc);
+	if (netif_running(dev))
+		bnx2x_vlan_configure(bp, true);
 
-	return rc;
+	return 0;
 }
 
 static int bnx2x_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	struct bnx2x_vlan_entry *vlan;
+	bool found = false;
 	int rc = 0;
 
-	if (!netif_running(bp->dev)) {
-		DP(NETIF_MSG_IFUP,
-		   "Ignoring VLAN configuration the interface is down\n");
-		return -EFAULT;
-	}
-
 	DP(NETIF_MSG_IFUP, "Removing VLAN %d\n", vid);
 
-	if (!bp->vlan_cnt) {
-		BNX2X_ERR("Unable to kill VLAN %d\n", vid);
-		return -EINVAL;
-	}
-
 	list_for_each_entry(vlan, &bp->vlan_reg, link)
-		if (vlan->vid == vid)
+		if (vlan->vid == vid) {
+			found = true;
 			break;
+		}
 
-	if (vlan->vid != vid) {
+	if (!found) {
 		BNX2X_ERR("Unable to kill VLAN %d - not found\n", vid);
 		return -EINVAL;
 	}
 
-	if (vlan->hw)
+	if (netif_running(dev) && vlan->hw) {
 		rc = __bnx2x_vlan_configure_vid(bp, vid, false);
+		DP(NETIF_MSG_IFUP, "HW deconfigured for VLAN %d\n", vid);
+		bp->vlan_cnt--;
+	}
 
 	list_del(&vlan->link);
 	kfree(vlan);
 
-	bp->vlan_cnt--;
-
-	if (bp->vlan_cnt <= bp->vlan_credit && bp->accept_any_vlan) {
-		/* Configure all non-configured entries */
-		list_for_each_entry(vlan, &bp->vlan_reg, link) {
-			if (vlan->hw)
-				continue;
-
-			rc = __bnx2x_vlan_configure_vid(bp, vlan->vid, true);
-			if (rc) {
-				BNX2X_ERR("Unable to config VLAN %d\n",
-					  vlan->vid);
-				continue;
-			}
-			DP(NETIF_MSG_IFUP, "HW configured for VLAN %d\n",
-			   vlan->vid);
-			vlan->hw = true;
-		}
-		DP(NETIF_MSG_IFUP, "Accept all VLAN Removed\n");
-		bp->accept_any_vlan = false;
-		if (IS_PF(bp))
-			bnx2x_set_rx_mode_inner(bp);
-		else
-			bnx2x_vfpf_storm_rx_mode(bp);
-	}
+	if (netif_running(dev))
+		bnx2x_vlan_configure(bp, true);
 
 	DP(NETIF_MSG_IFUP, "Removing VLAN result %d\n", rc);
 
@@ -13072,14 +13023,8 @@ static const struct net_device_ops bnx2x_netdev_ops = {
 	.ndo_get_phys_port_id	= bnx2x_get_phys_port_id,
 	.ndo_set_vf_link_state	= bnx2x_set_vf_link_state,
 	.ndo_features_check	= bnx2x_features_check,
-#ifdef CONFIG_BNX2X_VXLAN
-	.ndo_add_vxlan_port	= bnx2x_add_vxlan_port,
-	.ndo_del_vxlan_port	= bnx2x_del_vxlan_port,
-#endif
-#if IS_ENABLED(CONFIG_BNX2X_GENEVE)
-	.ndo_add_geneve_port	= bnx2x_add_geneve_port,
-	.ndo_del_geneve_port	= bnx2x_del_geneve_port,
-#endif
+	.ndo_udp_tunnel_add	= bnx2x_udp_tunnel_add,
+	.ndo_udp_tunnel_del	= bnx2x_udp_tunnel_del,
 };
 
 static int bnx2x_set_coherency_mask(struct bnx2x *bp)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 72a2efff8e49..70b148a10ec8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -37,9 +37,7 @@
 #include <net/udp.h>
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
-#if defined(CONFIG_VXLAN) || defined(CONFIG_VXLAN_MODULE)
-#include <net/vxlan.h>
-#endif
+#include <net/udp_tunnel.h>
 #ifdef CONFIG_NET_RX_BUSY_POLL
 #include <net/busy_poll.h>
 #endif
@@ -75,12 +73,22 @@ enum board_idx {
 	BCM57301,
 	BCM57302,
 	BCM57304,
+	BCM57311,
+	BCM57312,
 	BCM57402,
 	BCM57404,
 	BCM57406,
+	BCM57404_NPAR,
+	BCM57412,
+	BCM57414,
+	BCM57416,
+	BCM57417,
+	BCM57414_NPAR,
 	BCM57314,
 	BCM57304_VF,
 	BCM57404_VF,
+	BCM57414_VF,
+	BCM57314_VF,
 };
 
 /* indexed by enum above */
@@ -90,25 +98,45 @@ static const struct {
 	{ "Broadcom BCM57301 NetXtreme-C Single-port 10Gb Ethernet" },
 	{ "Broadcom BCM57302 NetXtreme-C Dual-port 10Gb/25Gb Ethernet" },
 	{ "Broadcom BCM57304 NetXtreme-C Dual-port 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	{ "Broadcom BCM57311 NetXtreme-C Single-port 10Gb Ethernet" },
+	{ "Broadcom BCM57312 NetXtreme-C Dual-port 10Gb/25Gb Ethernet" },
 	{ "Broadcom BCM57402 NetXtreme-E Dual-port 10Gb Ethernet" },
 	{ "Broadcom BCM57404 NetXtreme-E Dual-port 10Gb/25Gb Ethernet" },
 	{ "Broadcom BCM57406 NetXtreme-E Dual-port 10GBase-T Ethernet" },
+	{ "Broadcom BCM57404 NetXtreme-E Ethernet Partition" },
+	{ "Broadcom BCM57412 NetXtreme-E Dual-port 10Gb Ethernet" },
+	{ "Broadcom BCM57414 NetXtreme-E Dual-port 10Gb/25Gb Ethernet" },
+	{ "Broadcom BCM57416 NetXtreme-E Dual-port 10GBase-T Ethernet" },
+	{ "Broadcom BCM57417 NetXtreme-E Dual-port 10GBase-T Ethernet" },
+	{ "Broadcom BCM57414 NetXtreme-E Ethernet Partition" },
 	{ "Broadcom BCM57314 NetXtreme-C Dual-port 10Gb/25Gb/40Gb/50Gb Ethernet" },
 	{ "Broadcom BCM57304 NetXtreme-C Ethernet Virtual Function" },
 	{ "Broadcom BCM57404 NetXtreme-E Ethernet Virtual Function" },
+	{ "Broadcom BCM57414 NetXtreme-E Ethernet Virtual Function" },
+	{ "Broadcom BCM57314 NetXtreme-E Ethernet Virtual Function" },
 };
 
 static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16c8), .driver_data = BCM57301 },
 	{ PCI_VDEVICE(BROADCOM, 0x16c9), .driver_data = BCM57302 },
 	{ PCI_VDEVICE(BROADCOM, 0x16ca), .driver_data = BCM57304 },
+	{ PCI_VDEVICE(BROADCOM, 0x16ce), .driver_data = BCM57311 },
+	{ PCI_VDEVICE(BROADCOM, 0x16cf), .driver_data = BCM57312 },
 	{ PCI_VDEVICE(BROADCOM, 0x16d0), .driver_data = BCM57402 },
 	{ PCI_VDEVICE(BROADCOM, 0x16d1), .driver_data = BCM57404 },
 	{ PCI_VDEVICE(BROADCOM, 0x16d2), .driver_data = BCM57406 },
+	{ PCI_VDEVICE(BROADCOM, 0x16d4), .driver_data = BCM57404_NPAR },
+	{ PCI_VDEVICE(BROADCOM, 0x16d6), .driver_data = BCM57412 },
+	{ PCI_VDEVICE(BROADCOM, 0x16d7), .driver_data = BCM57414 },
+	{ PCI_VDEVICE(BROADCOM, 0x16d8), .driver_data = BCM57416 },
+	{ PCI_VDEVICE(BROADCOM, 0x16d9), .driver_data = BCM57417 },
+	{ PCI_VDEVICE(BROADCOM, 0x16de), .driver_data = BCM57414_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x16df), .driver_data = BCM57314 },
 #ifdef CONFIG_BNXT_SRIOV
 	{ PCI_VDEVICE(BROADCOM, 0x16cb), .driver_data = BCM57304_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16d3), .driver_data = BCM57404_VF },
+	{ PCI_VDEVICE(BROADCOM, 0x16dc), .driver_data = BCM57414_VF },
+	{ PCI_VDEVICE(BROADCOM, 0x16e1), .driver_data = BCM57314_VF },
 #endif
 	{ 0 }
 };
@@ -125,12 +153,14 @@ static const u16 bnxt_async_events_arr[] = {
 	HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE,
 	HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_UNLOAD,
 	HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED,
+	HWRM_ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE,
 	HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE,
 };
 
 static bool bnxt_vf_pciid(enum board_idx idx)
 {
-	return (idx == BCM57304_VF || idx == BCM57404_VF);
+	return (idx == BCM57304_VF || idx == BCM57404_VF ||
+		idx == BCM57314_VF || idx == BCM57414_VF);
 }
 
 #define DB_CP_REARM_FLAGS	(DB_KEY_CP | DB_IDX_VALID)
@@ -286,7 +316,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			cpu_to_le32(DB_KEY_TX_PUSH | DB_LONG_TX_PUSH | prod);
 		txr->tx_prod = prod;
 
+		tx_buf->is_push = 1;
 		netdev_tx_sent_queue(txq, skb->len);
+		wmb();	/* Sync is_push and byte queue before pushing data */
 
 		push_len = (length + sizeof(*tx_push) + 7) / 8;
 		if (push_len > 16) {
@@ -298,7 +330,6 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 					 push_len);
 		}
 
-		tx_buf->is_push = 1;
 		goto tx_done;
 	}
 
@@ -919,6 +950,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	}
 	tpa_info->flags2 = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_flags2);
 	tpa_info->metadata = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_metadata);
+	tpa_info->hdr_info = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_hdr_info);
 
 	rxr->rx_prod = NEXT_RX(prod);
 	cons = NEXT_RX(cons);
@@ -937,32 +969,102 @@ static void bnxt_abort_tpa(struct bnxt *bp, struct bnxt_napi *bnapi,
 		bnxt_reuse_rx_agg_bufs(bnapi, cp_cons, agg_bufs);
 }
 
+static struct sk_buff *bnxt_gro_func_5731x(struct bnxt_tpa_info *tpa_info,
+					   int payload_off, int tcp_ts,
+					   struct sk_buff *skb)
+{
+#ifdef CONFIG_INET
+	struct tcphdr *th;
+	int len, nw_off;
+	u16 outer_ip_off, inner_ip_off, inner_mac_off;
+	u32 hdr_info = tpa_info->hdr_info;
+	bool loopback = false;
+
+	inner_ip_off = BNXT_TPA_INNER_L3_OFF(hdr_info);
+	inner_mac_off = BNXT_TPA_INNER_L2_OFF(hdr_info);
+	outer_ip_off = BNXT_TPA_OUTER_L3_OFF(hdr_info);
+
+	/* If the packet is an internal loopback packet, the offsets will
+	 * have an extra 4 bytes.
+	 */
+	if (inner_mac_off == 4) {
+		loopback = true;
+	} else if (inner_mac_off > 4) {
+		__be16 proto = *((__be16 *)(skb->data + inner_ip_off -
+					    ETH_HLEN - 2));
+
+		/* We only support inner iPv4/ipv6.  If we don't see the
+		 * correct protocol ID, it must be a loopback packet where
+		 * the offsets are off by 4.
+		 */
+		if (proto != htons(ETH_P_IP) && proto && htons(ETH_P_IPV6))
+			loopback = true;
+	}
+	if (loopback) {
+		/* internal loopback packet, subtract all offsets by 4 */
+		inner_ip_off -= 4;
+		inner_mac_off -= 4;
+		outer_ip_off -= 4;
+	}
+
+	nw_off = inner_ip_off - ETH_HLEN;
+	skb_set_network_header(skb, nw_off);
+	if (tpa_info->flags2 & RX_TPA_START_CMP_FLAGS2_IP_TYPE) {
+		struct ipv6hdr *iph = ipv6_hdr(skb);
+
+		skb_set_transport_header(skb, nw_off + sizeof(struct ipv6hdr));
+		len = skb->len - skb_transport_offset(skb);
+		th = tcp_hdr(skb);
+		th->check = ~tcp_v6_check(len, &iph->saddr, &iph->daddr, 0);
+	} else {
+		struct iphdr *iph = ip_hdr(skb);
+
+		skb_set_transport_header(skb, nw_off + sizeof(struct iphdr));
+		len = skb->len - skb_transport_offset(skb);
+		th = tcp_hdr(skb);
+		th->check = ~tcp_v4_check(len, iph->saddr, iph->daddr, 0);
+	}
+
+	if (inner_mac_off) { /* tunnel */
+		struct udphdr *uh = NULL;
+		__be16 proto = *((__be16 *)(skb->data + outer_ip_off -
+					    ETH_HLEN - 2));
+
+		if (proto == htons(ETH_P_IP)) {
+			struct iphdr *iph = (struct iphdr *)skb->data;
+
+			if (iph->protocol == IPPROTO_UDP)
+				uh = (struct udphdr *)(iph + 1);
+		} else {
+			struct ipv6hdr *iph = (struct ipv6hdr *)skb->data;
+
+			if (iph->nexthdr == IPPROTO_UDP)
+				uh = (struct udphdr *)(iph + 1);
+		}
+		if (uh) {
+			if (uh->check)
+				skb_shinfo(skb)->gso_type |=
+					SKB_GSO_UDP_TUNNEL_CSUM;
+			else
+				skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
+		}
+	}
+#endif
+	return skb;
+}
+
 #define BNXT_IPV4_HDR_SIZE	(sizeof(struct iphdr) + sizeof(struct tcphdr))
 #define BNXT_IPV6_HDR_SIZE	(sizeof(struct ipv6hdr) + sizeof(struct tcphdr))
 
-static inline struct sk_buff *bnxt_gro_skb(struct bnxt_tpa_info *tpa_info,
-					   struct rx_tpa_end_cmp *tpa_end,
-					   struct rx_tpa_end_cmp_ext *tpa_end1,
+static struct sk_buff *bnxt_gro_func_5730x(struct bnxt_tpa_info *tpa_info,
+					   int payload_off, int tcp_ts,
 					   struct sk_buff *skb)
 {
 #ifdef CONFIG_INET
 	struct tcphdr *th;
-	int payload_off, tcp_opt_len = 0;
-	int len, nw_off;
-	u16 segs;
+	int len, nw_off, tcp_opt_len;
 
-	segs = TPA_END_TPA_SEGS(tpa_end);
-	if (segs == 1)
-		return skb;
-
-	NAPI_GRO_CB(skb)->count = segs;
-	skb_shinfo(skb)->gso_size =
-		le32_to_cpu(tpa_end1->rx_tpa_end_cmp_seg_len);
-	skb_shinfo(skb)->gso_type = tpa_info->gso_type;
-	payload_off = (le32_to_cpu(tpa_end->rx_tpa_end_cmp_misc_v1) &
-		       RX_TPA_END_CMP_PAYLOAD_OFFSET) >>
-		      RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT;
-	if (TPA_END_GRO_TS(tpa_end))
+	if (tcp_ts)
 		tcp_opt_len = 12;
 
 	if (tpa_info->gso_type == SKB_GSO_TCPV4) {
@@ -1019,6 +1121,32 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt_tpa_info *tpa_info,
 	return skb;
 }
 
+static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,
+					   struct bnxt_tpa_info *tpa_info,
+					   struct rx_tpa_end_cmp *tpa_end,
+					   struct rx_tpa_end_cmp_ext *tpa_end1,
+					   struct sk_buff *skb)
+{
+#ifdef CONFIG_INET
+	int payload_off;
+	u16 segs;
+
+	segs = TPA_END_TPA_SEGS(tpa_end);
+	if (segs == 1)
+		return skb;
+
+	NAPI_GRO_CB(skb)->count = segs;
+	skb_shinfo(skb)->gso_size =
+		le32_to_cpu(tpa_end1->rx_tpa_end_cmp_seg_len);
+	skb_shinfo(skb)->gso_type = tpa_info->gso_type;
+	payload_off = (le32_to_cpu(tpa_end->rx_tpa_end_cmp_misc_v1) &
+		       RX_TPA_END_CMP_PAYLOAD_OFFSET) >>
+		      RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT;
+	skb = bp->gro_func(tpa_info, payload_off, TPA_END_GRO_TS(tpa_end), skb);
+#endif
+	return skb;
+}
+
 static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 					   struct bnxt_napi *bnapi,
 					   u32 *raw_cons,
@@ -1112,19 +1240,13 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 	if (tpa_info->hash_type != PKT_HASH_TYPE_NONE)
 		skb_set_hash(skb, tpa_info->rss_hash, tpa_info->hash_type);
 
-	if (tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) {
-		netdev_features_t features = skb->dev->features;
+	if ((tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) &&
+	    (skb->dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
 		u16 vlan_proto = tpa_info->metadata >>
 			RX_CMP_FLAGS2_METADATA_TPID_SFT;
+		u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_VID_MASK;
 
-		if (((features & NETIF_F_HW_VLAN_CTAG_RX) &&
-		     vlan_proto == ETH_P_8021Q) ||
-		    ((features & NETIF_F_HW_VLAN_STAG_RX) &&
-		     vlan_proto == ETH_P_8021AD)) {
-			__vlan_hwaccel_put_tag(skb, htons(vlan_proto),
-					       tpa_info->metadata &
-					       RX_CMP_FLAGS2_METADATA_VID_MASK);
-		}
+		__vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
 	}
 
 	skb_checksum_none_assert(skb);
@@ -1135,7 +1257,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 	}
 
 	if (TPA_END_GRO(tpa_end))
-		skb = bnxt_gro_skb(tpa_info, tpa_end, tpa_end1, skb);
+		skb = bnxt_gro_skb(bp, tpa_info, tpa_end, tpa_end1, skb);
 
 	return skb;
 }
@@ -1277,19 +1399,14 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 
 	skb->protocol = eth_type_trans(skb, dev);
 
-	if (rxcmp1->rx_cmp_flags2 &
-	    cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) {
-		netdev_features_t features = skb->dev->features;
+	if ((rxcmp1->rx_cmp_flags2 &
+	     cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) &&
+	    (skb->dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
 		u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
+		u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_VID_MASK;
 		u16 vlan_proto = meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT;
 
-		if (((features & NETIF_F_HW_VLAN_CTAG_RX) &&
-		     vlan_proto == ETH_P_8021Q) ||
-		    ((features & NETIF_F_HW_VLAN_STAG_RX) &&
-		     vlan_proto == ETH_P_8021AD))
-			__vlan_hwaccel_put_tag(skb, htons(vlan_proto),
-					       meta_data &
-					       RX_CMP_FLAGS2_METADATA_VID_MASK);
+		__vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
 	}
 
 	skb_checksum_none_assert(skb);
@@ -1368,6 +1485,11 @@ static int bnxt_async_event_process(struct bnxt *bp,
 		set_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event);
 		break;
 	}
+	case HWRM_ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE:
+		if (BNXT_PF(bp))
+			goto async_event_process_exit;
+		set_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event);
+		break;
 	default:
 		netdev_err(bp->dev, "unhandled ASYNC event (id 0x%x)\n",
 			   event_id);
@@ -2272,7 +2394,7 @@ static void bnxt_set_tpa_flags(struct bnxt *bp)
 	bp->flags &= ~BNXT_FLAG_TPA;
 	if (bp->dev->features & NETIF_F_LRO)
 		bp->flags |= BNXT_FLAG_LRO;
-	if ((bp->dev->features & NETIF_F_GRO) && (bp->pdev->revision > 0))
+	if (bp->dev->features & NETIF_F_GRO)
 		bp->flags |= BNXT_FLAG_GRO;
 }
 
@@ -3287,11 +3409,13 @@ static int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 	unsigned int ring = 0, grp_idx;
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_cfg_input req = {0};
+	u16 def_vlan = 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_CFG, -1, -1);
 	/* Only RSS support for now TBD: COS & LB */
 	req.enables = cpu_to_le32(VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP |
-				  VNIC_CFG_REQ_ENABLES_RSS_RULE);
+				  VNIC_CFG_REQ_ENABLES_RSS_RULE |
+				  VNIC_CFG_REQ_ENABLES_MRU);
 	req.rss_rule = cpu_to_le16(vnic->fw_rss_cos_lb_ctx);
 	req.cos_rule = cpu_to_le16(0xffff);
 	if (vnic->flags & BNXT_VNIC_RSS_FLAG)
@@ -3307,7 +3431,11 @@ static int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 	req.mru = cpu_to_le16(bp->dev->mtu + ETH_HLEN + ETH_FCS_LEN +
 			      VLAN_HLEN);
 
-	if (bp->flags & BNXT_FLAG_STRIP_VLAN)
+#ifdef CONFIG_BNXT_SRIOV
+	if (BNXT_VF(bp))
+		def_vlan = bp->vf.vlan;
+#endif
+	if ((bp->flags & BNXT_FLAG_STRIP_VLAN) || def_vlan)
 		req.flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE);
 
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
@@ -3824,7 +3952,7 @@ static int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp)
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_STAT_CTX_ALLOC, -1, -1);
 
-	req.update_period_ms = cpu_to_le32(1000);
+	req.update_period_ms = cpu_to_le32(bp->stats_coal_ticks / 1000);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	for (i = 0; i < bp->cp_nr_rings; i++) {
@@ -3846,6 +3974,39 @@ static int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp)
 	return 0;
 }
 
+static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
+{
+	struct hwrm_func_qcfg_input req = {0};
+	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1);
+	req.fid = cpu_to_le16(0xffff);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		goto func_qcfg_exit;
+
+#ifdef CONFIG_BNXT_SRIOV
+	if (BNXT_VF(bp)) {
+		struct bnxt_vf_info *vf = &bp->vf;
+
+		vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK;
+	}
+#endif
+	switch (resp->port_partition_type) {
+	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0:
+	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5:
+	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0:
+		bp->port_partition_type = resp->port_partition_type;
+		break;
+	}
+
+func_qcfg_exit:
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
 int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 {
 	int rc = 0;
@@ -3865,6 +4026,7 @@ int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 
 		pf->fw_fid = le16_to_cpu(resp->fid);
 		pf->port_id = le16_to_cpu(resp->port_id);
+		bp->dev->dev_port = pf->port_id;
 		memcpy(pf->mac_addr, resp->mac_address, ETH_ALEN);
 		memcpy(bp->dev->dev_addr, pf->mac_addr, ETH_ALEN);
 		pf->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx);
@@ -4000,6 +4162,8 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	if (resp->hwrm_intf_maj >= 1)
 		bp->hwrm_max_req_len = le16_to_cpu(resp->max_req_win_len);
 
+	bp->chip_num = le16_to_cpu(resp->chip_num);
+
 hwrm_ver_get_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -4153,6 +4317,16 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 #endif
 }
 
+/* Allow PF and VF with default VLAN to be in promiscuous mode */
+static bool bnxt_promisc_ok(struct bnxt *bp)
+{
+#ifdef CONFIG_BNXT_SRIOV
+	if (BNXT_VF(bp) && !bp->vf.vlan)
+		return false;
+#endif
+	return true;
+}
+
 static int bnxt_cfg_rx_mode(struct bnxt *);
 static bool bnxt_mc_list_updated(struct bnxt *, u32 *);
 
@@ -4218,7 +4392,7 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 
 	vnic->rx_mask = CFA_L2_SET_RX_MASK_REQ_MASK_BCAST;
 
-	if ((bp->dev->flags & IFF_PROMISC) && BNXT_PF(bp))
+	if ((bp->dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp))
 		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
 
 	if (bp->dev->flags & IFF_ALLMULTI) {
@@ -4240,6 +4414,11 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 		netdev_warn(bp->dev, "HWRM set coalescing failure rc: %x\n",
 			    rc);
 
+	if (BNXT_VF(bp)) {
+		bnxt_hwrm_func_qcfg(bp);
+		netdev_update_features(bp->dev);
+	}
+
 	return 0;
 
 err_out:
@@ -4654,6 +4833,7 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 	int rc = 0;
 	struct hwrm_port_phy_qcaps_input req = {0};
 	struct hwrm_port_phy_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
+	struct bnxt_link_info *link_info = &bp->link_info;
 
 	if (bp->hwrm_spec_code < 0x10201)
 		return 0;
@@ -4676,6 +4856,8 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 		bp->lpi_tmr_hi = le32_to_cpu(resp->valid_tx_lpi_timer_high) &
 				 PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK;
 	}
+	link_info->support_auto_speeds =
+		le16_to_cpu(resp->supported_speeds_auto_mode);
 
 hwrm_phy_qcaps_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
@@ -4933,7 +5115,7 @@ static int bnxt_hwrm_shutdown_link(struct bnxt *bp)
 {
 	struct hwrm_port_phy_cfg_input req = {0};
 
-	if (BNXT_VF(bp))
+	if (!BNXT_SINGLE_PF(bp))
 		return 0;
 
 	if (pci_num_vf(bp->pdev))
@@ -5083,15 +5265,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 			netdev_warn(bp->dev, "failed to update phy settings\n");
 	}
 
-	if (irq_re_init) {
-#if defined(CONFIG_VXLAN) || defined(CONFIG_VXLAN_MODULE)
-		vxlan_get_rx_port(bp->dev);
-#endif
-		if (!bnxt_hwrm_tunnel_dst_port_alloc(
-				bp, htons(0x17c1),
-				TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE))
-			bp->nge_port_cnt = 1;
-	}
+	if (irq_re_init)
+		udp_tunnel_get_rx_info(bp->dev);
 
 	set_bit(BNXT_STATE_OPEN, &bp->state);
 	bnxt_enable_int(bp);
@@ -5132,12 +5307,19 @@ static int bnxt_open(struct net_device *dev)
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
-	rc = bnxt_hwrm_func_reset(bp);
-	if (rc) {
-		netdev_err(bp->dev, "hwrm chip reset failure rc: %x\n",
-			   rc);
-		rc = -1;
-		return rc;
+	if (!test_bit(BNXT_STATE_FN_RST_DONE, &bp->state)) {
+		rc = bnxt_hwrm_func_reset(bp);
+		if (rc) {
+			netdev_err(bp->dev, "hwrm chip reset failure rc: %x\n",
+				   rc);
+			rc = -EBUSY;
+			return rc;
+		}
+		/* Do func_reset during the 1st PF open only to prevent killing
+		 * the VFs when the PF is brought down and up.
+		 */
+		if (BNXT_PF(bp))
+			set_bit(BNXT_STATE_FN_RST_DONE, &bp->state);
 	}
 	return __bnxt_open_nic(bp, true, true);
 }
@@ -5357,8 +5539,7 @@ static void bnxt_set_rx_mode(struct net_device *dev)
 		  CFA_L2_SET_RX_MASK_REQ_MASK_MCAST |
 		  CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST);
 
-	/* Only allow PF to be in promiscuous mode */
-	if ((dev->flags & IFF_PROMISC) && BNXT_PF(bp))
+	if ((dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp))
 		mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
 
 	uc_update = bnxt_uc_list_updated(bp);
@@ -5466,6 +5647,27 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 
 	if (!bnxt_rfs_capable(bp))
 		features &= ~NETIF_F_NTUPLE;
+
+	/* Both CTAG and STAG VLAN accelaration on the RX side have to be
+	 * turned on or off together.
+	 */
+	if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) !=
+	    (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) {
+		if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
+			features &= ~(NETIF_F_HW_VLAN_CTAG_RX |
+				      NETIF_F_HW_VLAN_STAG_RX);
+		else
+			features |= NETIF_F_HW_VLAN_CTAG_RX |
+				    NETIF_F_HW_VLAN_STAG_RX;
+	}
+#ifdef CONFIG_BNXT_SRIOV
+	if (BNXT_VF(bp)) {
+		if (bp->vf.vlan) {
+			features &= ~(NETIF_F_HW_VLAN_CTAG_RX |
+				      NETIF_F_HW_VLAN_STAG_RX);
+		}
+	}
+#endif
 	return features;
 }
 
@@ -5581,9 +5783,10 @@ static void bnxt_dbg_dump_states(struct bnxt *bp)
 	}
 }
 
-static void bnxt_reset_task(struct bnxt *bp)
+static void bnxt_reset_task(struct bnxt *bp, bool silent)
 {
-	bnxt_dbg_dump_states(bp);
+	if (!silent)
+		bnxt_dbg_dump_states(bp);
 	if (netif_running(bp->dev)) {
 		bnxt_close_nic(bp, false, false);
 		bnxt_open_nic(bp, false, false);
@@ -5634,6 +5837,23 @@ bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
 
+/* Only called from bnxt_sp_task() */
+static void bnxt_reset(struct bnxt *bp, bool silent)
+{
+	/* bnxt_reset_task() calls bnxt_close_nic() which waits
+	 * for BNXT_STATE_IN_SP_TASK to clear.
+	 * If there is a parallel dev_close(), bnxt_close() may be holding
+	 * rtnl() and waiting for BNXT_STATE_IN_SP_TASK to clear.  So we
+	 * must clear BNXT_STATE_IN_SP_TASK before holding rtnl().
+	 */
+	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+	rtnl_lock();
+	if (test_bit(BNXT_STATE_OPEN, &bp->state))
+		bnxt_reset_task(bp, silent);
+	set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+	rtnl_unlock();
+}
+
 static void bnxt_cfg_ntp_filters(struct bnxt *);
 
 static void bnxt_sp_task(struct work_struct *work)
@@ -5670,16 +5890,20 @@ static void bnxt_sp_task(struct work_struct *work)
 		bnxt_hwrm_tunnel_dst_port_free(
 			bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN);
 	}
-	if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event)) {
-		/* bnxt_reset_task() calls bnxt_close_nic() which waits
-		 * for BNXT_STATE_IN_SP_TASK to clear.
-		 */
-		clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-		rtnl_lock();
-		bnxt_reset_task(bp);
-		set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-		rtnl_unlock();
+	if (test_and_clear_bit(BNXT_GENEVE_ADD_PORT_SP_EVENT, &bp->sp_event)) {
+		bnxt_hwrm_tunnel_dst_port_alloc(
+			bp, bp->nge_port,
+			TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE);
 	}
+	if (test_and_clear_bit(BNXT_GENEVE_DEL_PORT_SP_EVENT, &bp->sp_event)) {
+		bnxt_hwrm_tunnel_dst_port_free(
+			bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE);
+	}
+	if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event))
+		bnxt_reset(bp, false);
+
+	if (test_and_clear_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event))
+		bnxt_reset(bp, true);
 
 	if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event))
 		bnxt_get_port_module_status(bp);
@@ -5770,6 +5994,8 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
 	bp->tx_coal_ticks_irq = 2;
 	bp->tx_coal_bufs_irq = 2;
 
+	bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS;
+
 	init_timer(&bp->timer);
 	bp->timer.data = (unsigned long)bp;
 	bp->timer.function = bnxt_timer;
@@ -5835,7 +6061,7 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (new_mtu < 60 || new_mtu > 9000)
+	if (new_mtu < 60 || new_mtu > 9500)
 		return -EINVAL;
 
 	if (netif_running(dev))
@@ -6044,47 +6270,83 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp)
 
 #endif /* CONFIG_RFS_ACCEL */
 
-static void bnxt_add_vxlan_port(struct net_device *dev, sa_family_t sa_family,
-				__be16 port)
+static void bnxt_udp_tunnel_add(struct net_device *dev,
+				struct udp_tunnel_info *ti)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (!netif_running(dev))
+	if (ti->sa_family != AF_INET6 && ti->sa_family != AF_INET)
 		return;
 
-	if (sa_family != AF_INET6 && sa_family != AF_INET)
+	if (!netif_running(dev))
 		return;
 
-	if (bp->vxlan_port_cnt && bp->vxlan_port != port)
-		return;
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		if (bp->vxlan_port_cnt && bp->vxlan_port != ti->port)
+			return;
 
-	bp->vxlan_port_cnt++;
-	if (bp->vxlan_port_cnt == 1) {
-		bp->vxlan_port = port;
-		set_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bp->vxlan_port_cnt++;
+		if (bp->vxlan_port_cnt == 1) {
+			bp->vxlan_port = ti->port;
+			set_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event);
+			schedule_work(&bp->sp_task);
+		}
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (bp->nge_port_cnt && bp->nge_port != ti->port)
+			return;
+
+		bp->nge_port_cnt++;
+		if (bp->nge_port_cnt == 1) {
+			bp->nge_port = ti->port;
+			set_bit(BNXT_GENEVE_ADD_PORT_SP_EVENT, &bp->sp_event);
+		}
+		break;
+	default:
+		return;
 	}
+
+	schedule_work(&bp->sp_task);
 }
 
-static void bnxt_del_vxlan_port(struct net_device *dev, sa_family_t sa_family,
-				__be16 port)
+static void bnxt_udp_tunnel_del(struct net_device *dev,
+				struct udp_tunnel_info *ti)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (!netif_running(dev))
+	if (ti->sa_family != AF_INET6 && ti->sa_family != AF_INET)
 		return;
 
-	if (sa_family != AF_INET6 && sa_family != AF_INET)
+	if (!netif_running(dev))
 		return;
 
-	if (bp->vxlan_port_cnt && bp->vxlan_port == port) {
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		if (!bp->vxlan_port_cnt || bp->vxlan_port != ti->port)
+			return;
 		bp->vxlan_port_cnt--;
 
-		if (bp->vxlan_port_cnt == 0) {
-			set_bit(BNXT_VXLAN_DEL_PORT_SP_EVENT, &bp->sp_event);
-			schedule_work(&bp->sp_task);
-		}
+		if (bp->vxlan_port_cnt != 0)
+			return;
+
+		set_bit(BNXT_VXLAN_DEL_PORT_SP_EVENT, &bp->sp_event);
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (!bp->nge_port_cnt || bp->nge_port != ti->port)
+			return;
+		bp->nge_port_cnt--;
+
+		if (bp->nge_port_cnt != 0)
+			return;
+
+		set_bit(BNXT_GENEVE_DEL_PORT_SP_EVENT, &bp->sp_event);
+		break;
+	default:
+		return;
 	}
+
+	schedule_work(&bp->sp_task);
 }
 
 static const struct net_device_ops bnxt_netdev_ops = {
@@ -6115,8 +6377,8 @@ static const struct net_device_ops bnxt_netdev_ops = {
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	= bnxt_rx_flow_steer,
 #endif
-	.ndo_add_vxlan_port	= bnxt_add_vxlan_port,
-	.ndo_del_vxlan_port	= bnxt_del_vxlan_port,
+	.ndo_udp_tunnel_add	= bnxt_udp_tunnel_add,
+	.ndo_udp_tunnel_del	= bnxt_udp_tunnel_del,
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= bnxt_busy_poll,
 #endif
@@ -6165,6 +6427,12 @@ static int bnxt_probe_phy(struct bnxt *bp)
 		return rc;
 	}
 
+	/* Older firmware does not have supported_auto_speeds, so assume
+	 * that all supported speeds can be autonegotiated.
+	 */
+	if (link_info->auto_link_speeds && !link_info->support_auto_speeds)
+		link_info->support_auto_speeds = link_info->support_speeds;
+
 	/*initialize the ethool setting copy with NVM settings */
 	if (BNXT_AUTO_MODE(link_info->auto_mode)) {
 		link_info->autoneg = BNXT_AUTONEG_SPEED;
@@ -6338,7 +6606,13 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto init_err;
 
 	mutex_init(&bp->hwrm_cmd_lock);
-	bnxt_hwrm_ver_get(bp);
+	rc = bnxt_hwrm_ver_get(bp);
+	if (rc)
+		goto init_err;
+
+	bp->gro_func = bnxt_gro_func_5730x;
+	if (BNXT_CHIP_NUM_57X1X(bp->chip_num))
+		bp->gro_func = bnxt_gro_func_5731x;
 
 	rc = bnxt_hwrm_func_drv_rgtr(bp);
 	if (rc)
@@ -6361,6 +6635,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto init_err;
 	}
 
+	bnxt_hwrm_func_qcfg(bp);
+
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
 	if (BNXT_PF(bp))
@@ -6420,6 +6696,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 					       pci_channel_state_t state)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct bnxt *bp = netdev_priv(netdev);
 
 	netdev_info(netdev, "PCI I/O error detected\n");
 
@@ -6434,6 +6711,8 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	if (netif_running(netdev))
 		bnxt_close(netdev);
 
+	/* So that func_reset will be done during slot_reset */
+	clear_bit(BNXT_STATE_FN_RST_DONE, &bp->state);
 	pci_disable_device(pdev);
 	rtnl_unlock();
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 2824d65b2e35..2313e37e6eb5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -11,10 +11,10 @@
 #define BNXT_H
 
 #define DRV_MODULE_NAME		"bnxt_en"
-#define DRV_MODULE_VERSION	"1.2.0"
+#define DRV_MODULE_VERSION	"1.3.0"
 
 #define DRV_VER_MAJ	1
-#define DRV_VER_MIN	0
+#define DRV_VER_MIN	3
 #define DRV_VER_UPD	0
 
 struct tx_bd {
@@ -298,13 +298,14 @@ struct rx_tpa_start_cmp_ext {
 	#define RX_TPA_START_CMP_FLAGS2_L4_CS_CALC		(0x1 << 1)
 	#define RX_TPA_START_CMP_FLAGS2_T_IP_CS_CALC		(0x1 << 2)
 	#define RX_TPA_START_CMP_FLAGS2_T_L4_CS_CALC		(0x1 << 3)
+	#define RX_TPA_START_CMP_FLAGS2_IP_TYPE			(0x1 << 8)
 
 	__le32 rx_tpa_start_cmp_metadata;
 	__le32 rx_tpa_start_cmp_cfa_code_v2;
 	#define RX_TPA_START_CMP_V2				(0x1 << 0)
 	#define RX_TPA_START_CMP_CFA_CODE			(0xffff << 16)
 	 #define RX_TPA_START_CMPL_CFA_CODE_SHIFT		 16
-	__le32 rx_tpa_start_cmp_unused5;
+	__le32 rx_tpa_start_cmp_hdr_info;
 };
 
 struct rx_tpa_end_cmp {
@@ -358,7 +359,8 @@ struct rx_tpa_end_cmp {
 	 RX_TPA_END_CMP_FLAGS_PLACEMENT_ANY_GRO)
 
 #define TPA_END_GRO_TS(rx_tpa_end)					\
-	((rx_tpa_end)->rx_tpa_end_cmp_tsdelta & cpu_to_le32(RX_TPA_END_GRO_TS))
+	(!!((rx_tpa_end)->rx_tpa_end_cmp_tsdelta &			\
+	    cpu_to_le32(RX_TPA_END_GRO_TS)))
 
 struct rx_tpa_end_cmp_ext {
 	__le32 rx_tpa_end_cmp_dup_acks;
@@ -584,6 +586,19 @@ struct bnxt_tpa_info {
 	u32			metadata;
 	enum pkt_hash_types	hash_type;
 	u32			rss_hash;
+	u32			hdr_info;
+
+#define BNXT_TPA_L4_SIZE(hdr_info)	\
+	(((hdr_info) & 0xf8000000) ? ((hdr_info) >> 27) : 32)
+
+#define BNXT_TPA_INNER_L3_OFF(hdr_info)	\
+	(((hdr_info) >> 18) & 0x1ff)
+
+#define BNXT_TPA_INNER_L2_OFF(hdr_info)	\
+	(((hdr_info) >> 9) & 0x1ff)
+
+#define BNXT_TPA_OUTER_L3_OFF(hdr_info)	\
+	((hdr_info) & 0x1ff)
 };
 
 struct bnxt_rx_ring_info {
@@ -739,8 +754,8 @@ struct bnxt_vf_info {
 struct bnxt_pf_info {
 #define BNXT_FIRST_PF_FID	1
 #define BNXT_FIRST_VF_FID	128
-	u32	fw_fid;
-	u8	port_id;
+	u16	fw_fid;
+	u16	port_id;
 	u8	mac_addr[ETH_ALEN];
 	u16	max_rsscos_ctxs;
 	u16	max_cp_rings;
@@ -835,6 +850,7 @@ struct bnxt_link_info {
 #define BNXT_LINK_SPEED_MSK_25GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_25GB
 #define BNXT_LINK_SPEED_MSK_40GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_40GB
 #define BNXT_LINK_SPEED_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_50GB
+	u16			support_auto_speeds;
 	u16			lp_auto_link_speeds;
 	u16			force_link_speed;
 	u32			preemphasis;
@@ -873,6 +889,44 @@ struct bnxt {
 	void __iomem		*bar2;
 
 	u32			reg_base;
+	u16			chip_num;
+#define CHIP_NUM_57301		0x16c8
+#define CHIP_NUM_57302		0x16c9
+#define CHIP_NUM_57304		0x16ca
+#define CHIP_NUM_57402		0x16d0
+#define CHIP_NUM_57404		0x16d1
+#define CHIP_NUM_57406		0x16d2
+
+#define CHIP_NUM_57311		0x16ce
+#define CHIP_NUM_57312		0x16cf
+#define CHIP_NUM_57314		0x16df
+#define CHIP_NUM_57412		0x16d6
+#define CHIP_NUM_57414		0x16d7
+#define CHIP_NUM_57416		0x16d8
+#define CHIP_NUM_57417		0x16d9
+
+#define BNXT_CHIP_NUM_5730X(chip_num)		\
+	((chip_num) >= CHIP_NUM_57301 &&	\
+	 (chip_num) <= CHIP_NUM_57304)
+
+#define BNXT_CHIP_NUM_5740X(chip_num)		\
+	((chip_num) >= CHIP_NUM_57402 &&	\
+	 (chip_num) <= CHIP_NUM_57406)
+
+#define BNXT_CHIP_NUM_5731X(chip_num)		\
+	((chip_num) == CHIP_NUM_57311 ||	\
+	 (chip_num) == CHIP_NUM_57312 ||	\
+	 (chip_num) == CHIP_NUM_57314)
+
+#define BNXT_CHIP_NUM_5741X(chip_num)		\
+	((chip_num) >= CHIP_NUM_57412 &&	\
+	 (chip_num) <= CHIP_NUM_57417)
+
+#define BNXT_CHIP_NUM_57X0X(chip_num)		\
+	(BNXT_CHIP_NUM_5730X(chip_num) || BNXT_CHIP_NUM_5740X(chip_num))
+
+#define BNXT_CHIP_NUM_57X1X(chip_num)		\
+	(BNXT_CHIP_NUM_5731X(chip_num) || BNXT_CHIP_NUM_5741X(chip_num))
 
 	struct net_device	*dev;
 	struct pci_dev		*pdev;
@@ -907,12 +961,17 @@ struct bnxt {
 
 #define BNXT_PF(bp)		(!((bp)->flags & BNXT_FLAG_VF))
 #define BNXT_VF(bp)		((bp)->flags & BNXT_FLAG_VF)
+#define BNXT_NPAR(bp)		((bp)->port_partition_type)
+#define BNXT_SINGLE_PF(bp)	(BNXT_PF(bp) && !BNXT_NPAR(bp))
 
 	struct bnxt_napi	**bnapi;
 
 	struct bnxt_rx_ring_info	*rx_ring;
 	struct bnxt_tx_ring_info	*tx_ring;
 
+	struct sk_buff *	(*gro_func)(struct bnxt_tpa_info *, int, int,
+					    struct sk_buff *);
+
 	u32			rx_buf_size;
 	u32			rx_buf_use_size;	/* useable size */
 	u32			rx_ring_size;
@@ -959,6 +1018,7 @@ struct bnxt {
 	unsigned long		state;
 #define BNXT_STATE_OPEN		0
 #define BNXT_STATE_IN_SP_TASK	1
+#define BNXT_STATE_FN_RST_DONE	2
 
 	struct bnxt_irq	*irq_tbl;
 	u8			mac_addr[ETH_ALEN];
@@ -991,8 +1051,10 @@ struct bnxt {
 	__be16			vxlan_port;
 	u8			vxlan_port_cnt;
 	__le16			vxlan_fw_dst_port_id;
+	__be16			nge_port;
 	u8			nge_port_cnt;
 	__le16			nge_fw_dst_port_id;
+	u8			port_partition_type;
 
 	u16			rx_coal_ticks;
 	u16			rx_coal_ticks_irq;
@@ -1005,6 +1067,11 @@ struct bnxt {
 
 #define BNXT_USEC_TO_COAL_TIMER(x)	((x) * 25 / 2)
 
+	u32			stats_coal_ticks;
+#define BNXT_DEF_STATS_COAL_TICKS	 1000000
+#define BNXT_MIN_STATS_COAL_TICKS	  250000
+#define BNXT_MAX_STATS_COAL_TICKS	 1000000
+
 	struct work_struct	sp_task;
 	unsigned long		sp_event;
 #define BNXT_RX_MASK_SP_EVENT		0
@@ -1018,6 +1085,9 @@ struct bnxt {
 #define BNXT_HWRM_PF_UNLOAD_SP_EVENT	8
 #define BNXT_PERIODIC_STATS_SP_EVENT	9
 #define BNXT_HWRM_PORT_MODULE_SP_EVENT	10
+#define BNXT_RESET_TASK_SILENT_SP_EVENT	11
+#define BNXT_GENEVE_ADD_PORT_SP_EVENT	12
+#define BNXT_GENEVE_DEL_PORT_SP_EVENT	13
 
 	struct bnxt_pf_info	pf;
 #ifdef CONFIG_BNXT_SRIOV
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index a38cb047b540..0f7dd861ab4d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -56,6 +56,8 @@ static int bnxt_get_coalesce(struct net_device *dev,
 	coal->tx_coalesce_usecs_irq = bp->tx_coal_ticks_irq;
 	coal->tx_max_coalesced_frames_irq = bp->tx_coal_bufs_irq;
 
+	coal->stats_block_coalesce_usecs = bp->stats_coal_ticks;
+
 	return 0;
 }
 
@@ -63,6 +65,7 @@ static int bnxt_set_coalesce(struct net_device *dev,
 			     struct ethtool_coalesce *coal)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	bool update_stats = false;
 	int rc = 0;
 
 	bp->rx_coal_ticks = coal->rx_coalesce_usecs;
@@ -76,8 +79,26 @@ static int bnxt_set_coalesce(struct net_device *dev,
 	bp->tx_coal_ticks_irq = coal->tx_coalesce_usecs_irq;
 	bp->tx_coal_bufs_irq = coal->tx_max_coalesced_frames_irq;
 
-	if (netif_running(dev))
-		rc = bnxt_hwrm_set_coal(bp);
+	if (bp->stats_coal_ticks != coal->stats_block_coalesce_usecs) {
+		u32 stats_ticks = coal->stats_block_coalesce_usecs;
+
+		stats_ticks = clamp_t(u32, stats_ticks,
+				      BNXT_MIN_STATS_COAL_TICKS,
+				      BNXT_MAX_STATS_COAL_TICKS);
+		stats_ticks = rounddown(stats_ticks, BNXT_MIN_STATS_COAL_TICKS);
+		bp->stats_coal_ticks = stats_ticks;
+		update_stats = true;
+	}
+
+	if (netif_running(dev)) {
+		if (update_stats) {
+			rc = bnxt_close_nic(bp, true, false);
+			if (!rc)
+				rc = bnxt_open_nic(bp, true, false);
+		} else {
+			rc = bnxt_hwrm_set_coal(bp);
+		}
+	}
 
 	return rc;
 }
@@ -628,7 +649,66 @@ u32 _bnxt_fw_to_ethtool_adv_spds(u16 fw_speeds, u8 fw_pause)
 	return speed_mask;
 }
 
-static u32 bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info)
+#define BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, fw_pause, lk_ksettings, name)\
+{									\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_100MB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     100baseT_Full);	\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_1GB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     1000baseT_Full);	\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_10GB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     10000baseT_Full);	\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_25GB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     25000baseCR_Full);	\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_40GB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     40000baseCR4_Full);\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_50GB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     50000baseCR2_Full);\
+	if ((fw_pause) & BNXT_LINK_PAUSE_RX) {				\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     Pause);		\
+		if (!((fw_pause) & BNXT_LINK_PAUSE_TX))			\
+			ethtool_link_ksettings_add_link_mode(		\
+					lk_ksettings, name, Asym_Pause);\
+	} else if ((fw_pause) & BNXT_LINK_PAUSE_TX) {			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     Asym_Pause);	\
+	}								\
+}
+
+#define BNXT_ETHTOOL_TO_FW_SPDS(fw_speeds, lk_ksettings, name)		\
+{									\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  100baseT_Full) ||	\
+	    ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  100baseT_Half))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_100MB;		\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  1000baseT_Full) ||	\
+	    ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  1000baseT_Half))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_1GB;			\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  10000baseT_Full))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_10GB;		\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  25000baseCR_Full))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_25GB;		\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  40000baseCR4_Full))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_40GB;		\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  50000baseCR2_Full))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_50GB;		\
+}
+
+static void bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info,
+				struct ethtool_link_ksettings *lk_ksettings)
 {
 	u16 fw_speeds = link_info->auto_link_speeds;
 	u8 fw_pause = 0;
@@ -636,10 +716,11 @@ static u32 bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info)
 	if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL)
 		fw_pause = link_info->auto_pause_setting;
 
-	return _bnxt_fw_to_ethtool_adv_spds(fw_speeds, fw_pause);
+	BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, fw_pause, lk_ksettings, advertising);
 }
 
-static u32 bnxt_fw_to_ethtool_lp_adv(struct bnxt_link_info *link_info)
+static void bnxt_fw_to_ethtool_lp_adv(struct bnxt_link_info *link_info,
+				struct ethtool_link_ksettings *lk_ksettings)
 {
 	u16 fw_speeds = link_info->lp_auto_link_speeds;
 	u8 fw_pause = 0;
@@ -647,16 +728,24 @@ static u32 bnxt_fw_to_ethtool_lp_adv(struct bnxt_link_info *link_info)
 	if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL)
 		fw_pause = link_info->lp_pause;
 
-	return _bnxt_fw_to_ethtool_adv_spds(fw_speeds, fw_pause);
+	BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, fw_pause, lk_ksettings,
+				lp_advertising);
 }
 
-static u32 bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info)
+static void bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info,
+				struct ethtool_link_ksettings *lk_ksettings)
 {
 	u16 fw_speeds = link_info->support_speeds;
-	u32 supported;
 
-	supported = _bnxt_fw_to_ethtool_adv_spds(fw_speeds, 0);
-	return supported | SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+	BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, 0, lk_ksettings, supported);
+
+	ethtool_link_ksettings_add_link_mode(lk_ksettings, supported, Pause);
+	ethtool_link_ksettings_add_link_mode(lk_ksettings, supported,
+					     Asym_Pause);
+
+	if (link_info->support_auto_speeds)
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, supported,
+						     Autoneg);
 }
 
 u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed)
@@ -683,65 +772,62 @@ u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed)
 	}
 }
 
-static int bnxt_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int bnxt_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *lk_ksettings)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info = &bp->link_info;
-	u16 ethtool_speed;
-
-	cmd->supported = bnxt_fw_to_ethtool_support_spds(link_info);
+	struct ethtool_link_settings *base = &lk_ksettings->base;
+	u32 ethtool_speed;
 
-	if (link_info->auto_link_speeds)
-		cmd->supported |= SUPPORTED_Autoneg;
+	ethtool_link_ksettings_zero_link_mode(lk_ksettings, supported);
+	bnxt_fw_to_ethtool_support_spds(link_info, lk_ksettings);
 
+	ethtool_link_ksettings_zero_link_mode(lk_ksettings, advertising);
 	if (link_info->autoneg) {
-		cmd->advertising =
-			bnxt_fw_to_ethtool_advertised_spds(link_info);
-		cmd->advertising |= ADVERTISED_Autoneg;
-		cmd->autoneg = AUTONEG_ENABLE;
+		bnxt_fw_to_ethtool_advertised_spds(link_info, lk_ksettings);
+		ethtool_link_ksettings_add_link_mode(lk_ksettings,
+						     advertising, Autoneg);
+		base->autoneg = AUTONEG_ENABLE;
 		if (link_info->phy_link_status == BNXT_LINK_LINK)
-			cmd->lp_advertising =
-				bnxt_fw_to_ethtool_lp_adv(link_info);
+			bnxt_fw_to_ethtool_lp_adv(link_info, lk_ksettings);
 		ethtool_speed = bnxt_fw_to_ethtool_speed(link_info->link_speed);
 		if (!netif_carrier_ok(dev))
-			cmd->duplex = DUPLEX_UNKNOWN;
+			base->duplex = DUPLEX_UNKNOWN;
 		else if (link_info->duplex & BNXT_LINK_DUPLEX_FULL)
-			cmd->duplex = DUPLEX_FULL;
+			base->duplex = DUPLEX_FULL;
 		else
-			cmd->duplex = DUPLEX_HALF;
+			base->duplex = DUPLEX_HALF;
 	} else {
-		cmd->autoneg = AUTONEG_DISABLE;
-		cmd->advertising = 0;
+		base->autoneg = AUTONEG_DISABLE;
 		ethtool_speed =
 			bnxt_fw_to_ethtool_speed(link_info->req_link_speed);
-		cmd->duplex = DUPLEX_HALF;
+		base->duplex = DUPLEX_HALF;
 		if (link_info->req_duplex == BNXT_LINK_DUPLEX_FULL)
-			cmd->duplex = DUPLEX_FULL;
+			base->duplex = DUPLEX_FULL;
 	}
-	ethtool_cmd_speed_set(cmd, ethtool_speed);
+	base->speed = ethtool_speed;
 
-	cmd->port = PORT_NONE;
+	base->port = PORT_NONE;
 	if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP) {
-		cmd->port = PORT_TP;
-		cmd->supported |= SUPPORTED_TP;
-		cmd->advertising |= ADVERTISED_TP;
+		base->port = PORT_TP;
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, supported,
+						     TP);
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, advertising,
+						     TP);
 	} else {
-		cmd->supported |= SUPPORTED_FIBRE;
-		cmd->advertising |= ADVERTISED_FIBRE;
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, supported,
+						     FIBRE);
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, advertising,
+						     FIBRE);
 
 		if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC)
-			cmd->port = PORT_DA;
+			base->port = PORT_DA;
 		else if (link_info->media_type ==
 			 PORT_PHY_QCFG_RESP_MEDIA_TYPE_FIBRE)
-			cmd->port = PORT_FIBRE;
+			base->port = PORT_FIBRE;
 	}
-
-	if (link_info->transceiver ==
-	    PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_INTERNAL)
-		cmd->transceiver = XCVR_INTERNAL;
-	else
-		cmd->transceiver = XCVR_EXTERNAL;
-	cmd->phy_address = link_info->phy_addr;
+	base->phy_address = link_info->phy_addr;
 
 	return 0;
 }
@@ -815,37 +901,25 @@ u16 bnxt_get_fw_auto_link_speeds(u32 advertising)
 	return fw_speed_mask;
 }
 
-static int bnxt_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int bnxt_set_link_ksettings(struct net_device *dev,
+			   const struct ethtool_link_ksettings *lk_ksettings)
 {
-	int rc = 0;
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info = &bp->link_info;
+	const struct ethtool_link_settings *base = &lk_ksettings->base;
 	u32 speed, fw_advertising = 0;
 	bool set_pause = false;
+	int rc = 0;
 
-	if (BNXT_VF(bp))
-		return rc;
-
-	if (cmd->autoneg == AUTONEG_ENABLE) {
-		u32 supported_spds = bnxt_fw_to_ethtool_support_spds(link_info);
+	if (!BNXT_SINGLE_PF(bp))
+		return -EOPNOTSUPP;
 
-		if (cmd->advertising & ~(supported_spds | ADVERTISED_Autoneg |
-					 ADVERTISED_TP | ADVERTISED_FIBRE)) {
-			netdev_err(dev, "Unsupported advertising mask (adv: 0x%x)\n",
-				   cmd->advertising);
-			rc = -EINVAL;
-			goto set_setting_exit;
-		}
-		fw_advertising = bnxt_get_fw_auto_link_speeds(cmd->advertising);
-		if (fw_advertising & ~link_info->support_speeds) {
-			netdev_err(dev, "Advertising parameters are not supported! (adv: 0x%x)\n",
-				   cmd->advertising);
-			rc = -EINVAL;
-			goto set_setting_exit;
-		}
+	if (base->autoneg == AUTONEG_ENABLE) {
+		BNXT_ETHTOOL_TO_FW_SPDS(fw_advertising, lk_ksettings,
+					advertising);
 		link_info->autoneg |= BNXT_AUTONEG_SPEED;
 		if (!fw_advertising)
-			link_info->advertising = link_info->support_speeds;
+			link_info->advertising = link_info->support_auto_speeds;
 		else
 			link_info->advertising = fw_advertising;
 		/* any change to autoneg will cause link change, therefore the
@@ -863,16 +937,12 @@ static int bnxt_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 			rc = -EINVAL;
 			goto set_setting_exit;
 		}
-		/* TODO: currently don't support half duplex */
-		if (cmd->duplex == DUPLEX_HALF) {
+		if (base->duplex == DUPLEX_HALF) {
 			netdev_err(dev, "HALF DUPLEX is not supported!\n");
 			rc = -EINVAL;
 			goto set_setting_exit;
 		}
-		/* If received a request for an unknown duplex, assume full*/
-		if (cmd->duplex == DUPLEX_UNKNOWN)
-			cmd->duplex = DUPLEX_FULL;
-		speed = ethtool_cmd_speed(cmd);
+		speed = base->speed;
 		fw_speed = bnxt_get_fw_speed(dev, speed);
 		if (!fw_speed) {
 			rc = -EINVAL;
@@ -911,8 +981,8 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info = &bp->link_info;
 
-	if (BNXT_VF(bp))
-		return rc;
+	if (!BNXT_SINGLE_PF(bp))
+		return -EOPNOTSUPP;
 
 	if (epause->autoneg) {
 		if (!(link_info->autoneg & BNXT_AUTONEG_SPEED))
@@ -1010,6 +1080,8 @@ static int bnxt_firmware_reset(struct net_device *dev,
 	case BNX_DIR_TYPE_APE_FW:
 	case BNX_DIR_TYPE_APE_PATCH:
 		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT;
+		/* Self-reset APE upon next PCIe reset: */
+		req.selfrst_status = FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST;
 		break;
 	case BNX_DIR_TYPE_KONG_FW:
 	case BNX_DIR_TYPE_KONG_PATCH:
@@ -1043,9 +1115,27 @@ static int bnxt_flash_firmware(struct net_device *dev,
 	case BNX_DIR_TYPE_BOOTCODE_2:
 		code_type = CODE_BOOT;
 		break;
+	case BNX_DIR_TYPE_CHIMP_PATCH:
+		code_type = CODE_CHIMP_PATCH;
+		break;
 	case BNX_DIR_TYPE_APE_FW:
 		code_type = CODE_MCTP_PASSTHRU;
 		break;
+	case BNX_DIR_TYPE_APE_PATCH:
+		code_type = CODE_APE_PATCH;
+		break;
+	case BNX_DIR_TYPE_KONG_FW:
+		code_type = CODE_KONG_FW;
+		break;
+	case BNX_DIR_TYPE_KONG_PATCH:
+		code_type = CODE_KONG_PATCH;
+		break;
+	case BNX_DIR_TYPE_BONO_FW:
+		code_type = CODE_BONO_FW;
+		break;
+	case BNX_DIR_TYPE_BONO_PATCH:
+		code_type = CODE_BONO_PATCH;
+		break;
 	default:
 		netdev_err(dev, "Unsupported directory entry type: %u\n",
 			   dir_type);
@@ -1100,6 +1190,8 @@ static bool bnxt_dir_type_is_ape_bin_format(u16 dir_type)
 	case BNX_DIR_TYPE_APE_PATCH:
 	case BNX_DIR_TYPE_KONG_FW:
 	case BNX_DIR_TYPE_KONG_PATCH:
+	case BNX_DIR_TYPE_BONO_FW:
+	case BNX_DIR_TYPE_BONO_PATCH:
 		return true;
 	}
 
@@ -1137,7 +1229,8 @@ static int bnxt_flash_firmware_from_file(struct net_device *dev,
 	const struct firmware  *fw;
 	int			rc;
 
-	if (bnxt_dir_type_is_executable(dir_type) == false)
+	if (dir_type != BNX_DIR_TYPE_UPDATE &&
+	    bnxt_dir_type_is_executable(dir_type) == false)
 		return -EINVAL;
 
 	rc = request_firmware(&fw, filename, &dev->dev);
@@ -1433,8 +1526,8 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 		 _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
 	int rc = 0;
 
-	if (BNXT_VF(bp))
-		return 0;
+	if (!BNXT_SINGLE_PF(bp))
+		return -EOPNOTSUPP;
 
 	if (!(bp->flags & BNXT_FLAG_EEE_CAP))
 		return -EOPNOTSUPP;
@@ -1618,8 +1711,8 @@ static int bnxt_get_module_eeprom(struct net_device *dev,
 }
 
 const struct ethtool_ops bnxt_ethtool_ops = {
-	.get_settings		= bnxt_get_settings,
-	.set_settings		= bnxt_set_settings,
+	.get_link_ksettings	= bnxt_get_link_ksettings,
+	.set_link_ksettings	= bnxt_set_link_ksettings,
 	.get_pauseparam		= bnxt_get_pauseparam,
 	.set_pauseparam		= bnxt_set_pauseparam,
 	.get_drvinfo		= bnxt_get_drvinfo,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_fw_hdr.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_fw_hdr.h
index 461675caaacd..82bf44ab811b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_fw_hdr.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_fw_hdr.h
@@ -70,6 +70,7 @@ enum SUPPORTED_CODE {
 	CODE_KONG_PATCH,	/* 18 - KONG Patch firmware */
 	CODE_BONO_FW,		/* 19 - BONO firmware */
 	CODE_BONO_PATCH,	/* 20 - BONO Patch firmware */
+	CODE_CHIMP_PATCH,	/* 21 - ChiMP Patch firmware */
 
 	MAX_CODE_TYPE,
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 05e3c49a7677..517567f6d651 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -105,6 +105,7 @@ struct hwrm_async_event_cmpl {
 	#define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED (0x4UL << 0)
 	#define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_NOT_ALLOWED (0x5UL << 0)
 	#define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE (0x6UL << 0)
+	#define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE (0x7UL << 0)
 	#define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_UNLOAD   (0x10UL << 0)
 	#define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_LOAD     (0x11UL << 0)
 	#define HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_UNLOAD     (0x20UL << 0)
@@ -484,12 +485,12 @@ struct hwrm_async_event_cmpl_hwrm_error {
 	#define HWRM_ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA1_TIMESTAMP 0x1UL
 };
 
-/* HW Resource Manager Specification 1.2.2 */
+/* HW Resource Manager Specification 1.3.0 */
 #define HWRM_VERSION_MAJOR	1
-#define HWRM_VERSION_MINOR	2
-#define HWRM_VERSION_UPDATE	2
+#define HWRM_VERSION_MINOR	3
+#define HWRM_VERSION_UPDATE	0
 
-#define HWRM_VERSION_STR	"1.2.2"
+#define HWRM_VERSION_STR	"1.3.0"
 /*
  * Following is the signature for HWRM message field that indicates not
  * applicable (All F's). Need to cast it the size of the field if needed.
@@ -611,6 +612,9 @@ struct cmd_nums {
 	#define HWRM_FWD_RESP					   (0xd2UL)
 	#define HWRM_FWD_ASYNC_EVENT_CMPL			   (0xd3UL)
 	#define HWRM_TEMP_MONITOR_QUERY			   (0xe0UL)
+	#define HWRM_WOL_FILTER_ALLOC				   (0xf0UL)
+	#define HWRM_WOL_FILTER_FREE				   (0xf1UL)
+	#define HWRM_WOL_FILTER_QCFG				   (0xf2UL)
 	#define HWRM_DBG_READ_DIRECT				   (0xff10UL)
 	#define HWRM_DBG_READ_INDIRECT				   (0xff11UL)
 	#define HWRM_DBG_WRITE_DIRECT				   (0xff12UL)
@@ -1020,6 +1024,10 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED	    0x1UL
 	#define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING      0x2UL
 	#define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED		    0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED	    0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED	    0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED       0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED	    0x40UL
 	u8 mac_address[6];
 	__le16 max_rsscos_ctx;
 	__le16 max_cmpl_rings;
@@ -1066,8 +1074,9 @@ struct hwrm_func_qcfg_output {
 	__le16 fid;
 	__le16 port_id;
 	__le16 vlan;
-	u8 unused_0;
-	u8 unused_1;
+	__le16 flags;
+	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_MAGICPKT_ENABLED      0x1UL
+	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_BMP_ENABLED	    0x2UL
 	u8 mac_address[6];
 	__le16 pci_id;
 	__le16 alloc_rsscos_ctx;
@@ -1086,23 +1095,23 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5	   (0x3UL << 0)
 	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0	   (0x4UL << 0)
 	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN	   (0xffUL << 0)
-	u8 unused_2;
+	u8 unused_0;
 	__le16 dflt_vnic_id;
-	u8 unused_3;
-	u8 unused_4;
+	u8 unused_1;
+	u8 unused_2;
 	__le32 min_bw;
 	__le32 max_bw;
 	u8 evb_mode;
 	#define FUNC_QCFG_RESP_EVB_MODE_NO_EVB			   (0x0UL << 0)
 	#define FUNC_QCFG_RESP_EVB_MODE_VEB			   (0x1UL << 0)
 	#define FUNC_QCFG_RESP_EVB_MODE_VEPA			   (0x2UL << 0)
-	u8 unused_5;
-	__le16 unused_6;
+	u8 unused_3;
+	__le16 unused_4;
 	__le32 alloc_mcast_filters;
 	__le32 alloc_hw_ring_grps;
+	u8 unused_5;
+	u8 unused_6;
 	u8 unused_7;
-	u8 unused_8;
-	u8 unused_9;
 	u8 valid;
 };
 
@@ -1410,8 +1419,8 @@ struct hwrm_func_buf_rgtr_input {
 	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_4K		   (0xcUL << 0)
 	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_8K		   (0xdUL << 0)
 	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_64K	   (0x10UL << 0)
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_2M		   (0x16UL << 0)
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_4M		   (0x17UL << 0)
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_2M		   (0x15UL << 0)
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_4M		   (0x16UL << 0)
 	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_1G		   (0x1eUL << 0)
 	__le16 req_buf_len;
 	__le16 resp_buf_len;
@@ -1499,6 +1508,12 @@ struct hwrm_port_phy_cfg_input {
 	#define PORT_PHY_CFG_REQ_FLAGS_EEE_DISABLE		    0x20UL
 	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_ENABLE	    0x40UL
 	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_DISABLE	    0x80UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_ENABLE	    0x100UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_DISABLE	    0x200UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_ENABLE	    0x400UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE	    0x800UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE	    0x1000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_DISABLE	    0x2000UL
 	__le32 enables;
 	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE		    0x1UL
 	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_DUPLEX		    0x2UL
@@ -1815,13 +1830,22 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP      (0xcUL << 24)
 	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFPPLUS  (0xdUL << 24)
 	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP28    (0x11UL << 24)
-	__le32 unused_1;
+	__le16 fec_cfg;
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED      0x1UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED   0x2UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_ENABLED     0x4UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_SUPPORTED  0x8UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED    0x10UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED  0x20UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED    0x40UL
+	u8 unused_1;
+	u8 unused_2;
 	char phy_vendor_name[16];
 	char phy_vendor_partnumber[16];
-	__le32 unused_2;
-	u8 unused_3;
+	__le32 unused_3;
 	u8 unused_4;
 	u8 unused_5;
+	u8 unused_6;
 	u8 valid;
 };
 
@@ -1842,6 +1866,8 @@ struct hwrm_port_mac_cfg_input {
 	#define PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE   0x20UL
 	#define PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_ENABLE    0x40UL
 	#define PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_DISABLE   0x80UL
+	#define PORT_MAC_CFG_REQ_FLAGS_OOB_WOL_ENABLE		    0x100UL
+	#define PORT_MAC_CFG_REQ_FLAGS_OOB_WOL_DISABLE		    0x200UL
 	__le32 enables;
 	#define PORT_MAC_CFG_REQ_ENABLES_IPG			    0x1UL
 	#define PORT_MAC_CFG_REQ_ENABLES_LPBK			    0x2UL
@@ -2127,6 +2153,7 @@ struct hwrm_port_phy_i2c_read_output {
 	u8 valid;
 };
 
+/* hwrm_queue_qportcfg */
 /* Input (24 bytes) */
 struct hwrm_queue_qportcfg_input {
 	__le16 req_type;
@@ -2382,7 +2409,7 @@ struct hwrm_queue_cos2bw_cfg_input {
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_SP      (0x0UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_ETS     (0x1UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_FIRST (0x2UL << 0)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST (0xffffUL << 0)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST (0xffUL << 0)
 	u8 queue_id0_pri_lvl;
 	u8 queue_id0_bw_weight;
 	u8 queue_id1;
@@ -2392,7 +2419,7 @@ struct hwrm_queue_cos2bw_cfg_input {
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_TSA_ASSIGN_SP      (0x0UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_TSA_ASSIGN_ETS     (0x1UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_TSA_ASSIGN_RESERVED_FIRST (0x2UL << 0)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_TSA_ASSIGN_RESERVED_LAST (0xffffUL << 0)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID1_TSA_ASSIGN_RESERVED_LAST (0xffUL << 0)
 	u8 queue_id1_pri_lvl;
 	u8 queue_id1_bw_weight;
 	u8 queue_id2;
@@ -2402,7 +2429,7 @@ struct hwrm_queue_cos2bw_cfg_input {
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_TSA_ASSIGN_SP      (0x0UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_TSA_ASSIGN_ETS     (0x1UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_TSA_ASSIGN_RESERVED_FIRST (0x2UL << 0)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_TSA_ASSIGN_RESERVED_LAST (0xffffUL << 0)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID2_TSA_ASSIGN_RESERVED_LAST (0xffUL << 0)
 	u8 queue_id2_pri_lvl;
 	u8 queue_id2_bw_weight;
 	u8 queue_id3;
@@ -2412,7 +2439,7 @@ struct hwrm_queue_cos2bw_cfg_input {
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_TSA_ASSIGN_SP      (0x0UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_TSA_ASSIGN_ETS     (0x1UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_TSA_ASSIGN_RESERVED_FIRST (0x2UL << 0)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_TSA_ASSIGN_RESERVED_LAST (0xffffUL << 0)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID3_TSA_ASSIGN_RESERVED_LAST (0xffUL << 0)
 	u8 queue_id3_pri_lvl;
 	u8 queue_id3_bw_weight;
 	u8 queue_id4;
@@ -2422,7 +2449,7 @@ struct hwrm_queue_cos2bw_cfg_input {
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_TSA_ASSIGN_SP      (0x0UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_TSA_ASSIGN_ETS     (0x1UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_TSA_ASSIGN_RESERVED_FIRST (0x2UL << 0)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_TSA_ASSIGN_RESERVED_LAST (0xffffUL << 0)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID4_TSA_ASSIGN_RESERVED_LAST (0xffUL << 0)
 	u8 queue_id4_pri_lvl;
 	u8 queue_id4_bw_weight;
 	u8 queue_id5;
@@ -2432,7 +2459,7 @@ struct hwrm_queue_cos2bw_cfg_input {
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_TSA_ASSIGN_SP      (0x0UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_TSA_ASSIGN_ETS     (0x1UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_TSA_ASSIGN_RESERVED_FIRST (0x2UL << 0)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_TSA_ASSIGN_RESERVED_LAST (0xffffUL << 0)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID5_TSA_ASSIGN_RESERVED_LAST (0xffUL << 0)
 	u8 queue_id5_pri_lvl;
 	u8 queue_id5_bw_weight;
 	u8 queue_id6;
@@ -2442,7 +2469,7 @@ struct hwrm_queue_cos2bw_cfg_input {
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_TSA_ASSIGN_SP      (0x0UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_TSA_ASSIGN_ETS     (0x1UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_TSA_ASSIGN_RESERVED_FIRST (0x2UL << 0)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_TSA_ASSIGN_RESERVED_LAST (0xffffUL << 0)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID6_TSA_ASSIGN_RESERVED_LAST (0xffUL << 0)
 	u8 queue_id6_pri_lvl;
 	u8 queue_id6_bw_weight;
 	u8 queue_id7;
@@ -2452,7 +2479,7 @@ struct hwrm_queue_cos2bw_cfg_input {
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_TSA_ASSIGN_SP      (0x0UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_TSA_ASSIGN_ETS     (0x1UL << 0)
 	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_TSA_ASSIGN_RESERVED_FIRST (0x2UL << 0)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_TSA_ASSIGN_RESERVED_LAST (0xffffUL << 0)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID7_TSA_ASSIGN_RESERVED_LAST (0xffUL << 0)
 	u8 queue_id7_pri_lvl;
 	u8 queue_id7_bw_weight;
 	u8 unused_1[5];
@@ -3150,7 +3177,7 @@ struct hwrm_cfa_l2_filter_cfg_output {
 };
 
 /* hwrm_cfa_l2_set_rx_mask */
-/* Input (40 bytes) */
+/* Input (56 bytes) */
 struct hwrm_cfa_l2_set_rx_mask_input {
 	__le16 req_type;
 	__le16 cmpl_ring;
@@ -3165,9 +3192,15 @@ struct hwrm_cfa_l2_set_rx_mask_input {
 	#define CFA_L2_SET_RX_MASK_REQ_MASK_BCAST		    0x8UL
 	#define CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS	    0x10UL
 	#define CFA_L2_SET_RX_MASK_REQ_MASK_OUTERMOST		    0x20UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_VLANONLY		    0x40UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_VLAN_NONVLAN	    0x80UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_ANYVLAN_NONVLAN	    0x100UL
 	__le64 mc_tbl_addr;
 	__le32 num_mc_entries;
 	__le32 unused_0;
+	__le64 vlan_tag_tbl_addr;
+	__le32 num_vlan_tags;
+	__le32 unused_1;
 };
 
 /* Output (16 bytes) */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
index 40a7b0e09612..73f2249555b5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
@@ -13,6 +13,7 @@
 enum bnxt_nvm_directory_type {
 	BNX_DIR_TYPE_UNUSED = 0,
 	BNX_DIR_TYPE_PKG_LOG = 1,
+	BNX_DIR_TYPE_UPDATE = 2,
 	BNX_DIR_TYPE_CHIMP_PATCH = 3,
 	BNX_DIR_TYPE_BOOTCODE = 4,
 	BNX_DIR_TYPE_VPD = 5,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 363884dd9e8a..50d2007a2640 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -143,6 +143,9 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos)
 	u16 vlan_tag;
 	int rc;
 
+	if (bp->hwrm_spec_code < 0x10201)
+		return -ENOTSUPP;
+
 	rc = bnxt_vf_ndo_prep(bp, vf_id);
 	if (rc)
 		return rc;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 541456398dfb..76ed6df0fe53 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -450,34 +450,6 @@ static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv,
 			genet_dma_ring_regs[r]);
 }
 
-static int bcmgenet_get_settings(struct net_device *dev,
-				 struct ethtool_cmd *cmd)
-{
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	if (!priv->phydev)
-		return -ENODEV;
-
-	return phy_ethtool_gset(priv->phydev, cmd);
-}
-
-static int bcmgenet_set_settings(struct net_device *dev,
-				 struct ethtool_cmd *cmd)
-{
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	if (!priv->phydev)
-		return -ENODEV;
-
-	return phy_ethtool_sset(priv->phydev, cmd);
-}
-
 static int bcmgenet_set_rx_csum(struct net_device *dev,
 				netdev_features_t wanted)
 {
@@ -941,7 +913,7 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e)
 	e->eee_active = p->eee_active;
 	e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER);
 
-	return phy_ethtool_get_eee(priv->phydev, e);
+	return phy_ethtool_get_eee(dev->phydev, e);
 }
 
 static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
@@ -958,7 +930,7 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
 	if (!p->eee_enabled) {
 		bcmgenet_eee_enable_set(dev, false);
 	} else {
-		ret = phy_init_eee(priv->phydev, 0);
+		ret = phy_init_eee(dev->phydev, 0);
 		if (ret) {
 			netif_err(priv, hw, dev, "EEE initialization failed\n");
 			return ret;
@@ -968,14 +940,12 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
 		bcmgenet_eee_enable_set(dev, true);
 	}
 
-	return phy_ethtool_set_eee(priv->phydev, e);
+	return phy_ethtool_set_eee(dev->phydev, e);
 }
 
 static int bcmgenet_nway_reset(struct net_device *dev)
 {
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-
-	return genphy_restart_aneg(priv->phydev);
+	return genphy_restart_aneg(dev->phydev);
 }
 
 /* standard ethtool support functions. */
@@ -983,8 +953,6 @@ static struct ethtool_ops bcmgenet_ethtool_ops = {
 	.get_strings		= bcmgenet_get_strings,
 	.get_sset_count		= bcmgenet_get_sset_count,
 	.get_ethtool_stats	= bcmgenet_get_ethtool_stats,
-	.get_settings		= bcmgenet_get_settings,
-	.set_settings		= bcmgenet_set_settings,
 	.get_drvinfo		= bcmgenet_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_msglevel		= bcmgenet_get_msglevel,
@@ -996,18 +964,21 @@ static struct ethtool_ops bcmgenet_ethtool_ops = {
 	.nway_reset		= bcmgenet_nway_reset,
 	.get_coalesce		= bcmgenet_get_coalesce,
 	.set_coalesce		= bcmgenet_set_coalesce,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 /* Power down the unimac, based on mode. */
 static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode)
 {
+	struct net_device *ndev = priv->dev;
 	int ret = 0;
 	u32 reg;
 
 	switch (mode) {
 	case GENET_POWER_CABLE_SENSE:
-		phy_detach(priv->phydev);
+		phy_detach(ndev->phydev);
 		break;
 
 	case GENET_POWER_WOL_MAGIC:
@@ -1068,7 +1039,6 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 /* ioctl handle special commands that are not present in ethtool. */
 static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct bcmgenet_priv *priv = netdev_priv(dev);
 	int val = 0;
 
 	if (!netif_running(dev))
@@ -1078,10 +1048,10 @@ static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
-		if (!priv->phydev)
+		if (!dev->phydev)
 			val = -ENODEV;
 		else
-			val = phy_mii_ioctl(priv->phydev, rq, cmd);
+			val = phy_mii_ioctl(dev->phydev, rq, cmd);
 		break;
 
 	default:
@@ -2464,6 +2434,7 @@ static void bcmgenet_irq_task(struct work_struct *work)
 {
 	struct bcmgenet_priv *priv = container_of(
 			work, struct bcmgenet_priv, bcmgenet_irq_work);
+	struct net_device *ndev = priv->dev;
 
 	netif_dbg(priv, intr, priv->dev, "%s\n", __func__);
 
@@ -2476,7 +2447,7 @@ static void bcmgenet_irq_task(struct work_struct *work)
 
 	/* Link UP/DOWN event */
 	if (priv->irq0_stat & UMAC_IRQ_LINK_EVENT) {
-		phy_mac_interrupt(priv->phydev,
+		phy_mac_interrupt(ndev->phydev,
 				  !!(priv->irq0_stat & UMAC_IRQ_LINK_UP));
 		priv->irq0_stat &= ~UMAC_IRQ_LINK_EVENT;
 	}
@@ -2838,7 +2809,7 @@ static void bcmgenet_netif_start(struct net_device *dev)
 	/* Monitor link interrupts now */
 	bcmgenet_link_intr_enable(priv);
 
-	phy_start(priv->phydev);
+	phy_start(dev->phydev);
 }
 
 static int bcmgenet_open(struct net_device *dev)
@@ -2937,7 +2908,7 @@ static void bcmgenet_netif_stop(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
 	netif_tx_stop_all_queues(dev);
-	phy_stop(priv->phydev);
+	phy_stop(dev->phydev);
 	bcmgenet_intr_disable(priv);
 	bcmgenet_disable_rx_napi(priv);
 	bcmgenet_disable_tx_napi(priv);
@@ -2963,7 +2934,7 @@ static int bcmgenet_close(struct net_device *dev)
 	bcmgenet_netif_stop(dev);
 
 	/* Really kill the PHY state machine and disconnect from it */
-	phy_disconnect(priv->phydev);
+	phy_disconnect(dev->phydev);
 
 	/* Disable MAC receive */
 	umac_enable_set(priv, CMD_RX_EN, false);
@@ -3522,7 +3493,7 @@ static int bcmgenet_suspend(struct device *d)
 
 	bcmgenet_netif_stop(dev);
 
-	phy_suspend(priv->phydev);
+	phy_suspend(dev->phydev);
 
 	netif_device_detach(dev);
 
@@ -3586,7 +3557,7 @@ static int bcmgenet_resume(struct device *d)
 	if (priv->wolopts)
 		clk_disable_unprepare(priv->clk_wol);
 
-	phy_init_hw(priv->phydev);
+	phy_init_hw(dev->phydev);
 	/* Speed settings must be restored */
 	bcmgenet_mii_config(priv->dev);
 
@@ -3619,7 +3590,7 @@ static int bcmgenet_resume(struct device *d)
 
 	netif_device_attach(dev);
 
-	phy_resume(priv->phydev);
+	phy_resume(dev->phydev);
 
 	if (priv->eee.eee_enabled)
 		bcmgenet_eee_enable_set(dev, true);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 1e2dc34d331a..0f0868c56f05 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -597,7 +597,6 @@ struct bcmgenet_priv {
 
 	/* MDIO bus variables */
 	wait_queue_head_t wq;
-	struct phy_device *phydev;
 	bool internal_phy;
 	struct device_node *phy_dn;
 	struct device_node *mdio_dn;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 457c3bc8cfff..e907acd81da9 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -86,7 +86,7 @@ static int bcmgenet_mii_write(struct mii_bus *bus, int phy_id,
 void bcmgenet_mii_setup(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	u32 reg, cmd_bits = 0;
 	bool status_changed = false;
 
@@ -183,9 +183,9 @@ void bcmgenet_mii_reset(struct net_device *dev)
 	if (GENET_IS_V4(priv))
 		return;
 
-	if (priv->phydev) {
-		phy_init_hw(priv->phydev);
-		phy_start_aneg(priv->phydev);
+	if (dev->phydev) {
+		phy_init_hw(dev->phydev);
+		phy_start_aneg(dev->phydev);
 	}
 }
 
@@ -236,6 +236,7 @@ static void bcmgenet_internal_phy_setup(struct net_device *dev)
 
 static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 {
+	struct net_device *ndev = priv->dev;
 	u32 reg;
 
 	/* Speed settings are set in bcmgenet_mii_setup() */
@@ -244,14 +245,14 @@ static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 	bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL);
 
 	if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
-		fixed_phy_set_link_update(priv->phydev,
+		fixed_phy_set_link_update(ndev->phydev,
 					  bcmgenet_fixed_phy_link_update);
 }
 
 int bcmgenet_mii_config(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	struct device *kdev = &priv->pdev->dev;
 	const char *phy_name = NULL;
 	u32 id_mode_dis = 0;
@@ -302,7 +303,7 @@ int bcmgenet_mii_config(struct net_device *dev)
 		 * capabilities, use that knowledge to also configure the
 		 * Reverse MII interface correctly.
 		 */
-		if ((priv->phydev->supported & PHY_BASIC_FEATURES) ==
+		if ((phydev->supported & PHY_BASIC_FEATURES) ==
 				PHY_BASIC_FEATURES)
 			port_ctrl = PORT_MODE_EXT_RVMII_25;
 		else
@@ -371,7 +372,7 @@ int bcmgenet_mii_probe(struct net_device *dev)
 			return -ENODEV;
 		}
 	} else {
-		phydev = priv->phydev;
+		phydev = dev->phydev;
 		phydev->dev_flags = phy_flags;
 
 		ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup,
@@ -382,8 +383,6 @@ int bcmgenet_mii_probe(struct net_device *dev)
 		}
 	}
 
-	priv->phydev = phydev;
-
 	/* Configure port multiplexer based on what the probed PHY device since
 	 * reading the 'max-speed' property determines the maximum supported
 	 * PHY speed which is needed for bcmgenet_mii_config() to configure
@@ -391,7 +390,7 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	 */
 	ret = bcmgenet_mii_config(dev);
 	if (ret) {
-		phy_disconnect(priv->phydev);
+		phy_disconnect(phydev);
 		return ret;
 	}
 
@@ -401,7 +400,7 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	 * Ethernet MAC ISRs
 	 */
 	if (priv->internal_phy)
-		priv->phydev->irq = PHY_IGNORE_INTERRUPT;
+		phydev->irq = PHY_IGNORE_INTERRUPT;
 
 	return 0;
 }
@@ -606,7 +605,6 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 
 	}
 
-	priv->phydev = phydev;
 	priv->phy_interface = pd->phy_interface;
 
 	return 0;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index cb07d95e3dd9..89c0cfa9719f 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -304,7 +304,7 @@ static void macb_set_tx_clk(struct clk *clk, int speed, struct net_device *dev)
 static void macb_handle_link_change(struct net_device *dev)
 {
 	struct macb *bp = netdev_priv(dev);
-	struct phy_device *phydev = bp->phy_dev;
+	struct phy_device *phydev = dev->phydev;
 	unsigned long flags;
 	int status_change = 0;
 
@@ -414,7 +414,6 @@ static int macb_mii_probe(struct net_device *dev)
 	bp->link = 0;
 	bp->speed = 0;
 	bp->duplex = -1;
-	bp->phy_dev = phydev;
 
 	return 0;
 }
@@ -1886,7 +1885,7 @@ static int macb_open(struct net_device *dev)
 	netif_carrier_off(dev);
 
 	/* if the phy is not yet register, retry later*/
-	if (!bp->phy_dev)
+	if (!dev->phydev)
 		return -EAGAIN;
 
 	/* RX buffers initialization */
@@ -1905,7 +1904,7 @@ static int macb_open(struct net_device *dev)
 	macb_init_hw(bp);
 
 	/* schedule a link state check */
-	phy_start(bp->phy_dev);
+	phy_start(dev->phydev);
 
 	netif_tx_start_all_queues(dev);
 
@@ -1920,8 +1919,8 @@ static int macb_close(struct net_device *dev)
 	netif_tx_stop_all_queues(dev);
 	napi_disable(&bp->napi);
 
-	if (bp->phy_dev)
-		phy_stop(bp->phy_dev);
+	if (dev->phydev)
+		phy_stop(dev->phydev);
 
 	spin_lock_irqsave(&bp->lock, flags);
 	macb_reset_hw(bp);
@@ -2092,28 +2091,6 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
 	return nstat;
 }
 
-static int macb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct macb *bp = netdev_priv(dev);
-	struct phy_device *phydev = bp->phy_dev;
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_ethtool_gset(phydev, cmd);
-}
-
-static int macb_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct macb *bp = netdev_priv(dev);
-	struct phy_device *phydev = bp->phy_dev;
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_ethtool_sset(phydev, cmd);
-}
-
 static int macb_get_regs_len(struct net_device *netdev)
 {
 	return MACB_GREGS_NBR * sizeof(u32);
@@ -2186,19 +2163,17 @@ static int macb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 }
 
 static const struct ethtool_ops macb_ethtool_ops = {
-	.get_settings		= macb_get_settings,
-	.set_settings		= macb_set_settings,
 	.get_regs_len		= macb_get_regs_len,
 	.get_regs		= macb_get_regs,
 	.get_link		= ethtool_op_get_link,
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.get_wol		= macb_get_wol,
 	.set_wol		= macb_set_wol,
+	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
 static const struct ethtool_ops gem_ethtool_ops = {
-	.get_settings		= macb_get_settings,
-	.set_settings		= macb_set_settings,
 	.get_regs_len		= macb_get_regs_len,
 	.get_regs		= macb_get_regs,
 	.get_link		= ethtool_op_get_link,
@@ -2206,12 +2181,13 @@ static const struct ethtool_ops gem_ethtool_ops = {
 	.get_ethtool_stats	= gem_get_ethtool_stats,
 	.get_strings		= gem_get_ethtool_strings,
 	.get_sset_count		= gem_get_sset_count,
+	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
 static int macb_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct macb *bp = netdev_priv(dev);
-	struct phy_device *phydev = bp->phy_dev;
+	struct phy_device *phydev = dev->phydev;
 
 	if (!netif_running(dev))
 		return -EINVAL;
@@ -2570,7 +2546,7 @@ static int at91ether_open(struct net_device *dev)
 			     MACB_BIT(HRESP));
 
 	/* schedule a link state check */
-	phy_start(lp->phy_dev);
+	phy_start(dev->phydev);
 
 	netif_start_queue(dev);
 
@@ -3010,7 +2986,7 @@ static int macb_probe(struct platform_device *pdev)
 	if (err)
 		goto err_out_free_netdev;
 
-	phydev = bp->phy_dev;
+	phydev = dev->phydev;
 
 	netif_carrier_off(dev);
 
@@ -3029,7 +3005,7 @@ static int macb_probe(struct platform_device *pdev)
 	return 0;
 
 err_out_unregister_mdio:
-	phy_disconnect(bp->phy_dev);
+	phy_disconnect(dev->phydev);
 	mdiobus_unregister(bp->mii_bus);
 	mdiobus_free(bp->mii_bus);
 
@@ -3057,8 +3033,8 @@ static int macb_remove(struct platform_device *pdev)
 
 	if (dev) {
 		bp = netdev_priv(dev);
-		if (bp->phy_dev)
-			phy_disconnect(bp->phy_dev);
+		if (dev->phydev)
+			phy_disconnect(dev->phydev);
 		mdiobus_unregister(bp->mii_bus);
 		mdiobus_free(bp->mii_bus);
 
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 8a13824ef802..36893d8958d4 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -823,7 +823,6 @@ struct macb {
 	struct macb_or_gem_ops	macbgem_ops;
 
 	struct mii_bus		*mii_bus;
-	struct phy_device	*phy_dev;
 	int 			link;
 	int 			speed;
 	int 			duplex;
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
index 8ad7425f89bf..c03d37016a48 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
@@ -19,26 +19,16 @@
 * This file may also be available under a different license from Cavium.
 * Contact Cavium, Inc. for more information
 **********************************************************************/
-#include <linux/version.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
 #include <linux/pci.h>
-#include <linux/kthread.h>
 #include <linux/netdevice.h>
-#include "octeon_config.h"
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
 #include "response_manager.h"
 #include "octeon_device.h"
-#include "octeon_nic.h"
 #include "octeon_main.h"
-#include "octeon_network.h"
 #include "cn66xx_regs.h"
 #include "cn66xx_device.h"
-#include "liquidio_image.h"
-#include "octeon_mem_ops.h"
 
 int lio_cn6xxx_soft_reset(struct octeon_device *oct)
 {
@@ -74,9 +64,9 @@ void lio_cn6xxx_enable_error_reporting(struct octeon_device *oct)
 	u32 val;
 
 	pci_read_config_dword(oct->pci_dev, CN6XXX_PCIE_DEVCTL, &val);
-	if (val & 0x000f0000) {
+	if (val & 0x000c0000) {
 		dev_err(&oct->pci_dev->dev, "PCI-E Link error detected: 0x%08x\n",
-			val & 0x000f0000);
+			val & 0x000c0000);
 	}
 
 	val |= 0xf;          /* Enable Link error reporting */
@@ -229,7 +219,7 @@ void lio_cn6xxx_setup_global_output_regs(struct octeon_device *oct)
 	/* / Select Packet count instead of bytes for SLI_PKTi_CNTS[CNT] */
 	octeon_write_csr(oct, CN6XXX_SLI_PKT_OUT_BMODE, 0);
 
-	/* / Select ES,RO,NS setting from register for Output Queue Packet
+	/* Select ES, RO, NS setting from register for Output Queue Packet
 	 * Address
 	 */
 	octeon_write_csr(oct, CN6XXX_SLI_PKT_DPADDR, 0xFFFFFFFF);
@@ -367,7 +357,8 @@ void lio_cn6xxx_enable_io_queues(struct octeon_device *oct)
 
 void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 {
-	u32 mask, i, loop = HZ;
+	int i;
+	u32 mask, loop = HZ;
 	u32 d32;
 
 	/* Reset the Enable bits for Input Queues. */
@@ -376,7 +367,7 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 	octeon_write_csr(oct, CN6XXX_SLI_PKT_INSTR_ENB, mask);
 
 	/* Wait until hardware indicates that the queues are out of reset. */
-	mask = oct->io_qmask.iq;
+	mask = (u32)oct->io_qmask.iq;
 	d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_IQ);
 	while (((d32 & mask) != mask) && loop--) {
 		d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_IQ);
@@ -384,8 +375,8 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 	}
 
 	/* Reset the doorbell register for each Input queue. */
-	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
-		if (!(oct->io_qmask.iq & (1UL << i)))
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+		if (!(oct->io_qmask.iq & (1ULL << i)))
 			continue;
 		octeon_write_csr(oct, CN6XXX_SLI_IQ_DOORBELL(i), 0xFFFFFFFF);
 		d32 = octeon_read_csr(oct, CN6XXX_SLI_IQ_DOORBELL(i));
@@ -398,7 +389,7 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 
 	/* Wait until hardware indicates that the queues are out of reset. */
 	loop = HZ;
-	mask = oct->io_qmask.oq;
+	mask = (u32)oct->io_qmask.oq;
 	d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_OQ);
 	while (((d32 & mask) != mask) && loop--) {
 		d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_OQ);
@@ -408,8 +399,8 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 
 	/* Reset the doorbell register for each Output queue. */
 	/* for (i = 0; i < oct->num_oqs; i++) { */
-	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-		if (!(oct->io_qmask.oq & (1UL << i)))
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
+		if (!(oct->io_qmask.oq & (1ULL << i)))
 			continue;
 		octeon_write_csr(oct, CN6XXX_SLI_OQ_PKTS_CREDIT(i), 0xFFFFFFFF);
 		d32 = octeon_read_csr(oct, CN6XXX_SLI_OQ_PKTS_CREDIT(i));
@@ -429,16 +420,16 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 
 void lio_cn6xxx_reinit_regs(struct octeon_device *oct)
 {
-	u32 i;
+	int i;
 
-	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
-		if (!(oct->io_qmask.iq & (1UL << i)))
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+		if (!(oct->io_qmask.iq & (1ULL << i)))
 			continue;
 		oct->fn_list.setup_iq_regs(oct, i);
 	}
 
-	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-		if (!(oct->io_qmask.oq & (1UL << i)))
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
+		if (!(oct->io_qmask.oq & (1ULL << i)))
 			continue;
 		oct->fn_list.setup_oq_regs(oct, i);
 	}
@@ -450,8 +441,8 @@ void lio_cn6xxx_reinit_regs(struct octeon_device *oct)
 	oct->fn_list.enable_io_queues(oct);
 
 	/* for (i = 0; i < oct->num_oqs; i++) { */
-	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-		if (!(oct->io_qmask.oq & (1UL << i)))
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
+		if (!(oct->io_qmask.oq & (1ULL << i)))
 			continue;
 		writel(oct->droq[i]->max_count, oct->droq[i]->pkts_credit_reg);
 	}
@@ -495,8 +486,7 @@ u32 lio_cn6xxx_bar1_idx_read(struct octeon_device *oct, u32 idx)
 }
 
 u32
-lio_cn6xxx_update_read_index(struct octeon_device *oct __attribute__((unused)),
-			     struct octeon_instr_queue *iq)
+lio_cn6xxx_update_read_index(struct octeon_instr_queue *iq)
 {
 	u32 new_idx = readl(iq->inst_cnt_reg);
 
@@ -547,17 +537,18 @@ static void lio_cn6xxx_get_pcie_qlmport(struct octeon_device *oct)
 	dev_dbg(&oct->pci_dev->dev, "Using PCIE Port %d\n", oct->pcie_port);
 }
 
-void
+static void
 lio_cn6xxx_process_pcie_error_intr(struct octeon_device *oct, u64 intr64)
 {
 	dev_err(&oct->pci_dev->dev, "Error Intr: 0x%016llx\n",
 		CVM_CAST64(intr64));
 }
 
-int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct)
+static int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct)
 {
 	struct octeon_droq *droq;
-	u32 oq_no, pkt_count, droq_time_mask, droq_mask, droq_int_enb;
+	int oq_no;
+	u32 pkt_count, droq_time_mask, droq_mask, droq_int_enb;
 	u32 droq_cnt_enb, droq_cnt_mask;
 
 	droq_cnt_enb = octeon_read_csr(oct, CN6XXX_SLI_PKT_CNT_INT_ENB);
@@ -573,12 +564,12 @@ int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct)
 	oct->droq_intr = 0;
 
 	/* for (oq_no = 0; oq_no < oct->num_oqs; oq_no++) { */
-	for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES; oq_no++) {
-		if (!(droq_mask & (1 << oq_no)))
+	for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES(oct); oq_no++) {
+		if (!(droq_mask & (1ULL << oq_no)))
 			continue;
 
 		droq = oct->droq[oq_no];
-		pkt_count = octeon_droq_check_hw_for_pkts(oct, droq);
+		pkt_count = octeon_droq_check_hw_for_pkts(droq);
 		if (pkt_count) {
 			oct->droq_intr |= (1ULL << oq_no);
 			if (droq->ops.poll_mode) {
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h
index f77918779355..28c47224221a 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h
@@ -82,8 +82,6 @@ void lio_cn6xxx_setup_iq_regs(struct octeon_device *oct, u32 iq_no);
 void lio_cn6xxx_setup_oq_regs(struct octeon_device *oct, u32 oq_no);
 void lio_cn6xxx_enable_io_queues(struct octeon_device *oct);
 void lio_cn6xxx_disable_io_queues(struct octeon_device *oct);
-void lio_cn6xxx_process_pcie_error_intr(struct octeon_device *oct, u64 intr64);
-int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct);
 irqreturn_t lio_cn6xxx_process_interrupt_regs(void *dev);
 void lio_cn6xxx_reinit_regs(struct octeon_device *oct);
 void lio_cn6xxx_bar1_idx_setup(struct octeon_device *oct, u64 core_addr,
@@ -91,8 +89,7 @@ void lio_cn6xxx_bar1_idx_setup(struct octeon_device *oct, u64 core_addr,
 void lio_cn6xxx_bar1_idx_write(struct octeon_device *oct, u32 idx, u32 mask);
 u32 lio_cn6xxx_bar1_idx_read(struct octeon_device *oct, u32 idx);
 u32
-lio_cn6xxx_update_read_index(struct octeon_device *oct __attribute__((unused)),
-			     struct octeon_instr_queue *iq);
+lio_cn6xxx_update_read_index(struct octeon_instr_queue *iq);
 void lio_cn6xxx_enable_interrupt(void *chip);
 void lio_cn6xxx_disable_interrupt(void *chip);
 void cn6xxx_get_pcie_qlmport(struct octeon_device *oct);
diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c
index 8e830d0c0754..29755bc68f12 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c
@@ -19,28 +19,17 @@
 * This file may also be available under a different license from Cavium.
 * Contact Cavium, Inc. for more information
 **********************************************************************/
-#include <linux/version.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
 #include <linux/pci.h>
-#include <linux/kthread.h>
 #include <linux/netdevice.h>
-#include "octeon_config.h"
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
 #include "response_manager.h"
 #include "octeon_device.h"
-#include "octeon_nic.h"
 #include "octeon_main.h"
-#include "octeon_network.h"
 #include "cn66xx_regs.h"
 #include "cn66xx_device.h"
 #include "cn68xx_regs.h"
-#include "cn68xx_device.h"
-#include "liquidio_image.h"
-#include "octeon_mem_ops.h"
 
 static void lio_cn68xx_set_dpi_regs(struct octeon_device *oct)
 {
@@ -129,7 +118,7 @@ static inline void lio_cn68xx_vendor_message_fix(struct octeon_device *oct)
 	pci_write_config_dword(oct->pci_dev, CN6XXX_PCIE_FLTMSK, val);
 }
 
-int lio_is_210nv(struct octeon_device *oct)
+static int lio_is_210nv(struct octeon_device *oct)
 {
 	u64 mio_qlm4_cfg = lio_pci_readq(oct, CN6XXX_MIO_QLM4_CFG);
 
diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.h b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.h
index d4e1c9fb0bf2..ea7bdcce6044 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.h
@@ -28,6 +28,5 @@
 #define  __CN68XX_DEVICE_H__
 
 int lio_setup_cn68xx_octeon_device(struct octeon_device *oct);
-int lio_is_210nv(struct octeon_device *oct);
 
 #endif
diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_regs.h b/drivers/net/ethernet/cavium/liquidio/cn68xx_regs.h
index 38cddbd107b6..d45a0f4aaf1f 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn68xx_regs.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_regs.h
@@ -29,7 +29,6 @@
 
 #ifndef __CN68XX_REGS_H__
 #define __CN68XX_REGS_H__
-#include "cn66xx_regs.h"
 
 /*###################### REQUEST QUEUE #########################*/
 
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 245c063ed4db..289eb8907922 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -19,13 +19,9 @@
 * This file may also be available under a different license from Cavium.
 * Contact Cavium, Inc. for more information
 **********************************************************************/
-#include <linux/version.h>
 #include <linux/netdevice.h>
 #include <linux/net_tstamp.h>
-#include <linux/ethtool.h>
-#include <linux/dma-mapping.h>
 #include <linux/pci.h>
-#include "octeon_config.h"
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
@@ -36,9 +32,8 @@
 #include "octeon_network.h"
 #include "cn66xx_regs.h"
 #include "cn66xx_device.h"
-#include "cn68xx_regs.h"
-#include "cn68xx_device.h"
-#include "liquidio_image.h"
+
+static int octnet_get_link_stats(struct net_device *netdev);
 
 struct oct_mdio_cmd_context {
 	int octeon_id;
@@ -71,34 +66,126 @@ enum {
 	INTERFACE_MODE_RXAUI,
 	INTERFACE_MODE_QSGMII,
 	INTERFACE_MODE_AGL,
+	INTERFACE_MODE_XLAUI,
+	INTERFACE_MODE_XFI,
+	INTERFACE_MODE_10G_KR,
+	INTERFACE_MODE_40G_KR4,
+	INTERFACE_MODE_MIXED,
 };
 
 #define ARRAY_LENGTH(a) (sizeof(a) / sizeof((a)[0]))
 #define OCT_ETHTOOL_REGDUMP_LEN  4096
 #define OCT_ETHTOOL_REGSVER  1
 
+/* statistics of PF */
+static const char oct_stats_strings[][ETH_GSTRING_LEN] = {
+	"rx_packets",
+	"tx_packets",
+	"rx_bytes",
+	"tx_bytes",
+	"rx_errors",	/*jabber_err+l2_err+frame_err */
+	"tx_errors",	/*fw_err_pko+fw_err_link+fw_err_drop */
+	"rx_dropped",   /*st->fromwire.total_rcvd - st->fromwire.fw_total_rcvd
+			*+st->fromwire.dmac_drop + st->fromwire.fw_err_drop
+			*/
+	"tx_dropped",
+
+	"tx_total_sent",
+	"tx_total_fwd",
+	"tx_err_pko",
+	"tx_err_link",
+	"tx_err_drop",
+
+	"tx_tso",
+	"tx_tso_packets",
+	"tx_tso_err",
+	"tx_vxlan",
+
+	"mac_tx_total_pkts",
+	"mac_tx_total_bytes",
+	"mac_tx_mcast_pkts",
+	"mac_tx_bcast_pkts",
+	"mac_tx_ctl_packets",	/*oct->link_stats.fromhost.ctl_sent */
+	"mac_tx_total_collisions",
+	"mac_tx_one_collision",
+	"mac_tx_multi_collison",
+	"mac_tx_max_collision_fail",
+	"mac_tx_max_deferal_fail",
+	"mac_tx_fifo_err",
+	"mac_tx_runts",
+
+	"rx_total_rcvd",
+	"rx_total_fwd",
+	"rx_jabber_err",
+	"rx_l2_err",
+	"rx_frame_err",
+	"rx_err_pko",
+	"rx_err_link",
+	"rx_err_drop",
+
+	"rx_vxlan",
+	"rx_vxlan_err",
+
+	"rx_lro_pkts",
+	"rx_lro_bytes",
+	"rx_total_lro",
+
+	"rx_lro_aborts",
+	"rx_lro_aborts_port",
+	"rx_lro_aborts_seq",
+	"rx_lro_aborts_tsval",
+	"rx_lro_aborts_timer",
+	"rx_fwd_rate",
+
+	"mac_rx_total_rcvd",
+	"mac_rx_bytes",
+	"mac_rx_total_bcst",
+	"mac_rx_total_mcst",
+	"mac_rx_runts",
+	"mac_rx_ctl_packets",
+	"mac_rx_fifo_err",
+	"mac_rx_dma_drop",
+	"mac_rx_fcs_err",
+
+	"link_state_changes",
+};
+
+/* statistics of host tx queue */
 static const char oct_iq_stats_strings[][ETH_GSTRING_LEN] = {
-	"Instr posted",
-	"Instr processed",
-	"Instr dropped",
-	"Bytes Sent",
-	"Sgentry_sent",
-	"Inst cntreg",
-	"Tx done",
-	"Tx Iq busy",
-	"Tx dropped",
-	"Tx bytes",
+	"packets",		/*oct->instr_queue[iq_no]->stats.tx_done*/
+	"bytes",		/*oct->instr_queue[iq_no]->stats.tx_tot_bytes*/
+	"dropped",
+	"iq_busy",
+	"sgentry_sent",
+
+	"fw_instr_posted",
+	"fw_instr_processed",
+	"fw_instr_dropped",
+	"fw_bytes_sent",
+
+	"tso",
+	"vxlan",
+	"txq_restart",
 };
 
+/* statistics of host rx queue */
 static const char oct_droq_stats_strings[][ETH_GSTRING_LEN] = {
-	"OQ Pkts Received",
-	"OQ Bytes Received",
-	"Dropped no dispatch",
-	"Dropped nomem",
-	"Dropped toomany",
-	"Stack RX cnt",
-	"Stack RX Bytes",
-	"RX dropped",
+	"packets",		/*oct->droq[oq_no]->stats.rx_pkts_received */
+	"bytes",		/*oct->droq[oq_no]->stats.rx_bytes_received */
+	"dropped",		/*oct->droq[oq_no]->stats.rx_dropped+
+				 *oct->droq[oq_no]->stats.dropped_nodispatch+
+				 *oct->droq[oq_no]->stats.dropped_toomany+
+				 *oct->droq[oq_no]->stats.dropped_nomem
+				 */
+	"dropped_nomem",
+	"dropped_toomany",
+	"fw_dropped",
+	"fw_pkts_received",
+	"fw_bytes_received",
+	"fw_dropped_nodispatch",
+
+	"vxlan",
+	"buffer_alloc_failure",
 };
 
 #define OCTNIC_NCMD_AUTONEG_ON  0x1
@@ -112,8 +199,9 @@ static int lio_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 
 	linfo = &lio->linfo;
 
-	if (linfo->link.s.interface == INTERFACE_MODE_XAUI ||
-	    linfo->link.s.interface == INTERFACE_MODE_RXAUI) {
+	if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI ||
+	    linfo->link.s.if_mode == INTERFACE_MODE_RXAUI ||
+	    linfo->link.s.if_mode == INTERFACE_MODE_XFI) {
 		ecmd->port = PORT_FIBRE;
 		ecmd->supported =
 			(SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE |
@@ -124,10 +212,11 @@ static int lio_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 		ecmd->autoneg = AUTONEG_DISABLE;
 
 	} else {
-		dev_err(&oct->pci_dev->dev, "Unknown link interface reported\n");
+		dev_err(&oct->pci_dev->dev, "Unknown link interface reported %d\n",
+			linfo->link.s.if_mode);
 	}
 
-	if (linfo->link.s.status) {
+	if (linfo->link.s.link_up) {
 		ethtool_cmd_speed_set(ecmd, linfo->link.s.speed);
 		ecmd->duplex = linfo->link.s.duplex;
 	} else {
@@ -222,23 +311,20 @@ static int octnet_gpio_access(struct net_device *netdev, int addr, int val)
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 	int ret = 0;
 
 	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
 
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = OCTNET_CMD_GPIO_ACCESS;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = addr;
-	nctrl.ncmd.s.param3 = val;
+	nctrl.ncmd.s.param1 = addr;
+	nctrl.ncmd.s.param2 = val;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.wait_time = 100;
 	nctrl.netpndev = (u64)netdev;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 
-	nparams.resp_order = OCTEON_RESP_ORDERED;
-
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "Failed to configure gpio value\n");
 		return -EINVAL;
@@ -253,20 +339,18 @@ static void octnet_mdio_resp_callback(struct octeon_device *oct,
 				      u32 status,
 				      void *buf)
 {
-	struct oct_mdio_cmd_resp *mdio_cmd_rsp;
 	struct oct_mdio_cmd_context *mdio_cmd_ctx;
 	struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
 
-	mdio_cmd_rsp = (struct oct_mdio_cmd_resp *)sc->virtrptr;
 	mdio_cmd_ctx = (struct oct_mdio_cmd_context *)sc->ctxptr;
 
 	oct = lio_get_device(mdio_cmd_ctx->octeon_id);
 	if (status) {
 		dev_err(&oct->pci_dev->dev, "MIDO instruction failed. Status: %llx\n",
 			CVM_CAST64(status));
-		ACCESS_ONCE(mdio_cmd_ctx->cond) = -1;
+		WRITE_ONCE(mdio_cmd_ctx->cond, -1);
 	} else {
-		ACCESS_ONCE(mdio_cmd_ctx->cond) = 1;
+		WRITE_ONCE(mdio_cmd_ctx->cond, 1);
 	}
 	wake_up_interruptible(&mdio_cmd_ctx->wc);
 }
@@ -297,15 +381,16 @@ octnet_mdio45_access(struct lio *lio, int op, int loc, int *value)
 	mdio_cmd_rsp = (struct oct_mdio_cmd_resp *)sc->virtrptr;
 	mdio_cmd = (struct oct_mdio_cmd *)sc->virtdptr;
 
-	ACCESS_ONCE(mdio_cmd_ctx->cond) = 0;
+	WRITE_ONCE(mdio_cmd_ctx->cond, 0);
 	mdio_cmd_ctx->octeon_id = lio_get_device_id(oct_dev);
 	mdio_cmd->op = op;
 	mdio_cmd->mdio_addr = loc;
 	if (op)
 		mdio_cmd->value1 = *value;
-	mdio_cmd->value2 = lio->linfo.ifidx;
 	octeon_swap_8B_data((u64 *)mdio_cmd, sizeof(struct oct_mdio_cmd) / 8);
 
+	sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
 	octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, OPCODE_NIC_MDIO45,
 				    0, 0, 0);
 
@@ -317,7 +402,7 @@ octnet_mdio45_access(struct lio *lio, int op, int loc, int *value)
 
 	retval = octeon_send_soft_command(oct_dev, sc);
 
-	if (retval) {
+	if (retval == IQ_SEND_FAILED) {
 		dev_err(&oct_dev->pci_dev->dev,
 			"octnet_mdio45_access instruction failed status: %x\n",
 			retval);
@@ -335,7 +420,7 @@ octnet_mdio45_access(struct lio *lio, int op, int loc, int *value)
 			octeon_swap_8B_data((u64 *)(&mdio_cmd_rsp->resp),
 					    sizeof(struct oct_mdio_cmd) / 8);
 
-			if (ACCESS_ONCE(mdio_cmd_ctx->cond) == 1) {
+			if (READ_ONCE(mdio_cmd_ctx->cond) == 1) {
 				if (!op)
 					*value = mdio_cmd_rsp->resp.value1;
 			} else {
@@ -379,18 +464,16 @@ static int lio_set_phys_id(struct net_device *netdev,
 
 			/* Configure Beacon values */
 			value = LIO68XX_LED_BEACON_CFGON;
-			ret =
-				octnet_mdio45_access(lio, 1,
-						     LIO68XX_LED_BEACON_ADDR,
-						     &value);
+			ret = octnet_mdio45_access(lio, 1,
+						   LIO68XX_LED_BEACON_ADDR,
+						   &value);
 			if (ret)
 				return ret;
 
 			value = LIO68XX_LED_CTRL_CFGON;
-			ret =
-				octnet_mdio45_access(lio, 1,
-						     LIO68XX_LED_CTRL_ADDR,
-						     &value);
+			ret = octnet_mdio45_access(lio, 1,
+						   LIO68XX_LED_CTRL_ADDR,
+						   &value);
 			if (ret)
 				return ret;
 		} else {
@@ -469,7 +552,7 @@ lio_ethtool_get_ringparam(struct net_device *netdev,
 		tx_pending = CFG_GET_NUM_TX_DESCS_NIC_IF(conf6x, lio->ifidx);
 	}
 
-	if (lio->mtu > OCTNET_DEFAULT_FRM_SIZE) {
+	if (lio->mtu > OCTNET_DEFAULT_FRM_SIZE - OCTNET_FRM_HEADER_SIZE) {
 		ering->rx_pending = 0;
 		ering->rx_max_pending = 0;
 		ering->rx_mini_pending = 0;
@@ -503,10 +586,10 @@ static void lio_set_msglevel(struct net_device *netdev, u32 msglvl)
 	if ((msglvl ^ lio->msg_enable) & NETIF_MSG_HW) {
 		if (msglvl & NETIF_MSG_HW)
 			liquidio_set_feature(netdev,
-					     OCTNET_CMD_VERBOSE_ENABLE);
+					     OCTNET_CMD_VERBOSE_ENABLE, 0);
 		else
 			liquidio_set_feature(netdev,
-					     OCTNET_CMD_VERBOSE_DISABLE);
+					     OCTNET_CMD_VERBOSE_DISABLE, 0);
 	}
 
 	lio->msg_enable = msglvl;
@@ -518,61 +601,279 @@ lio_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 	/* Notes: Not supporting any auto negotiation in these
 	 * drivers. Just report pause frame support.
 	 */
-	pause->tx_pause = 1;
-	pause->rx_pause = 1;    /* TODO: Need to support RX pause frame!!. */
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+
+	pause->autoneg = 0;
+
+	pause->tx_pause = oct->tx_pause;
+	pause->rx_pause = oct->rx_pause;
 }
 
 static void
 lio_get_ethtool_stats(struct net_device *netdev,
-		      struct ethtool_stats *stats, u64 *data)
+		      struct ethtool_stats *stats  __attribute__((unused)),
+		      u64 *data)
 {
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct_dev = lio->oct_dev;
+	struct net_device_stats *netstats = &netdev->stats;
 	int i = 0, j;
 
-	for (j = 0; j < MAX_OCTEON_INSTR_QUEUES; j++) {
-		if (!(oct_dev->io_qmask.iq & (1UL << j)))
+	netdev->netdev_ops->ndo_get_stats(netdev);
+	octnet_get_link_stats(netdev);
+
+	/*sum of oct->droq[oq_no]->stats->rx_pkts_received */
+	data[i++] = CVM_CAST64(netstats->rx_packets);
+	/*sum of oct->instr_queue[iq_no]->stats.tx_done */
+	data[i++] = CVM_CAST64(netstats->tx_packets);
+	/*sum of oct->droq[oq_no]->stats->rx_bytes_received */
+	data[i++] = CVM_CAST64(netstats->rx_bytes);
+	/*sum of oct->instr_queue[iq_no]->stats.tx_tot_bytes */
+	data[i++] = CVM_CAST64(netstats->tx_bytes);
+	data[i++] = CVM_CAST64(netstats->rx_errors);
+	data[i++] = CVM_CAST64(netstats->tx_errors);
+	/*sum of oct->droq[oq_no]->stats->rx_dropped +
+	 *oct->droq[oq_no]->stats->dropped_nodispatch +
+	 *oct->droq[oq_no]->stats->dropped_toomany +
+	 *oct->droq[oq_no]->stats->dropped_nomem
+	 */
+	data[i++] = CVM_CAST64(netstats->rx_dropped);
+	/*sum of oct->instr_queue[iq_no]->stats.tx_dropped */
+	data[i++] = CVM_CAST64(netstats->tx_dropped);
+
+	/*data[i++] = CVM_CAST64(stats->multicast); */
+	/*data[i++] = CVM_CAST64(stats->collisions); */
+
+	/* firmware tx stats */
+	/*per_core_stats[cvmx_get_core_num()].link_stats[mdata->from_ifidx].
+	 *fromhost.fw_total_sent
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_total_sent);
+	/*per_core_stats[i].link_stats[port].fromwire.fw_total_fwd */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_total_fwd);
+	/*per_core_stats[j].link_stats[i].fromhost.fw_err_pko */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_err_pko);
+	/*per_core_stats[j].link_stats[i].fromhost.fw_err_link */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_err_link);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[idx].fromhost.
+	 *fw_err_drop
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_err_drop);
+
+	/*per_core_stats[cvmx_get_core_num()].link_stats[idx].fromhost.fw_tso */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_tso);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[idx].fromhost.
+	 *fw_tso_fwd
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_tso_fwd);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[idx].fromhost.
+	 *fw_err_tso
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_err_tso);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[idx].fromhost.
+	 *fw_tx_vxlan
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_tx_vxlan);
+
+	/* mac tx statistics */
+	/*CVMX_BGXX_CMRX_TX_STAT5 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.total_pkts_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT4 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.total_bytes_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT15 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.mcast_pkts_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT14 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.bcast_pkts_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT17 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.ctl_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT0 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.total_collisions);
+	/*CVMX_BGXX_CMRX_TX_STAT3 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.one_collision_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT2 */
+	data[i++] =
+		CVM_CAST64(oct_dev->link_stats.fromhost.multi_collision_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT0 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.max_collision_fail);
+	/*CVMX_BGXX_CMRX_TX_STAT1 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.max_deferral_fail);
+	/*CVMX_BGXX_CMRX_TX_STAT16 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fifo_err);
+	/*CVMX_BGXX_CMRX_TX_STAT6 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.runts);
+
+	/* RX firmware stats */
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_total_rcvd
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_total_rcvd);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_total_fwd
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_total_fwd);
+	/*per_core_stats[core_id].link_stats[ifidx].fromwire.jabber_err */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.jabber_err);
+	/*per_core_stats[core_id].link_stats[ifidx].fromwire.l2_err */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.l2_err);
+	/*per_core_stats[core_id].link_stats[ifidx].fromwire.frame_err */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.frame_err);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_err_pko
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_err_pko);
+	/*per_core_stats[j].link_stats[i].fromwire.fw_err_link */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_err_link);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[lro_ctx->ifidx].
+	 *fromwire.fw_err_drop
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_err_drop);
+
+	/*per_core_stats[cvmx_get_core_num()].link_stats[lro_ctx->ifidx].
+	 *fromwire.fw_rx_vxlan
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_rx_vxlan);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[lro_ctx->ifidx].
+	 *fromwire.fw_rx_vxlan_err
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_rx_vxlan_err);
+
+	/* LRO */
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_pkts
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_pkts);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_octs
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_octs);
+	/*per_core_stats[j].link_stats[i].fromwire.fw_total_lro */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_total_lro);
+	/*per_core_stats[j].link_stats[i].fromwire.fw_lro_aborts */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_aborts);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_aborts_port
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_aborts_port);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_aborts_seq
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_aborts_seq);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_aborts_tsval
+	 */
+	data[i++] =
+		CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_aborts_tsval);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_aborts_timer
+	 */
+	/* intrmod: packet forward rate */
+	data[i++] =
+		CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_aborts_timer);
+	/*per_core_stats[j].link_stats[i].fromwire.fw_lro_aborts */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fwd_rate);
+
+	/* mac: link-level stats */
+	/*CVMX_BGXX_CMRX_RX_STAT0 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.total_rcvd);
+	/*CVMX_BGXX_CMRX_RX_STAT1 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.bytes_rcvd);
+	/*CVMX_PKI_STATX_STAT5 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.total_bcst);
+	/*CVMX_PKI_STATX_STAT5 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.total_mcst);
+	/*wqe->word2.err_code or wqe->word2.err_level */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.runts);
+	/*CVMX_BGXX_CMRX_RX_STAT2 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.ctl_rcvd);
+	/*CVMX_BGXX_CMRX_RX_STAT6 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fifo_err);
+	/*CVMX_BGXX_CMRX_RX_STAT4 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.dmac_drop);
+	/*wqe->word2.err_code or wqe->word2.err_level */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fcs_err);
+	/*lio->link_changes*/
+	data[i++] = CVM_CAST64(lio->link_changes);
+
+	/* TX  -- lio_update_stats(lio); */
+	for (j = 0; j < MAX_OCTEON_INSTR_QUEUES(oct_dev); j++) {
+		if (!(oct_dev->io_qmask.iq & (1ULL << j)))
 			continue;
+		/*packets to network port*/
+		/*# of packets tx to network */
+		data[i++] = CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_done);
+		/*# of bytes tx to network */
 		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.instr_posted);
-		data[i++] =
-			CVM_CAST64(
-				oct_dev->instr_queue[j]->stats.instr_processed);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_tot_bytes);
+		/*# of packets dropped */
 		data[i++] =
-			CVM_CAST64(
-				oct_dev->instr_queue[j]->stats.instr_dropped);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_dropped);
+		/*# of tx fails due to queue full */
 		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.bytes_sent);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_iq_busy);
+		/*XXX gather entries sent */
 		data[i++] =
 			CVM_CAST64(oct_dev->instr_queue[j]->stats.sgentry_sent);
+
+		/*instruction to firmware: data and control */
+		/*# of instructions to the queue */
 		data[i++] =
-			readl(oct_dev->instr_queue[j]->inst_cnt_reg);
-		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_done);
-		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_iq_busy);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.instr_posted);
+		/*# of instructions processed */
+		data[i++] = CVM_CAST64(oct_dev->instr_queue[j]->
+				       stats.instr_processed);
+		/*# of instructions could not be processed */
+		data[i++] = CVM_CAST64(oct_dev->instr_queue[j]->
+				       stats.instr_dropped);
+		/*bytes sent through the queue */
 		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_dropped);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.bytes_sent);
+
+		/*tso request*/
+		data[i++] = CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_gso);
+		/*vxlan request*/
+		data[i++] = CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_vxlan);
+		/*txq restart*/
 		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_tot_bytes);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_restart);
 	}
 
-	/* for (j = 0; j < oct_dev->num_oqs; j++){ */
-	for (j = 0; j < MAX_OCTEON_OUTPUT_QUEUES; j++) {
-		if (!(oct_dev->io_qmask.oq & (1UL << j)))
+	/* RX */
+	/* for (j = 0; j < oct_dev->num_oqs; j++) { */
+	for (j = 0; j < MAX_OCTEON_OUTPUT_QUEUES(oct_dev); j++) {
+		if (!(oct_dev->io_qmask.oq & (1ULL << j)))
 			continue;
-		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.pkts_received);
-		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.bytes_received);
-		data[i++] =
-			CVM_CAST64(oct_dev->droq[j]->stats.dropped_nodispatch);
-		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.dropped_nomem);
-		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.dropped_toomany);
+
+		/*packets send to TCP/IP network stack */
+		/*# of packets to network stack */
 		data[i++] =
 			CVM_CAST64(oct_dev->droq[j]->stats.rx_pkts_received);
+		/*# of bytes to network stack */
 		data[i++] =
 			CVM_CAST64(oct_dev->droq[j]->stats.rx_bytes_received);
+		/*# of packets dropped */
+		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.dropped_nomem +
+				       oct_dev->droq[j]->stats.dropped_toomany +
+				       oct_dev->droq[j]->stats.rx_dropped);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.dropped_nomem);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.dropped_toomany);
 		data[i++] =
 			CVM_CAST64(oct_dev->droq[j]->stats.rx_dropped);
+
+		/*control and data path*/
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.pkts_received);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.bytes_received);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.dropped_nodispatch);
+
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.rx_vxlan);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.rx_alloc_failure);
 	}
 }
 
@@ -581,26 +882,43 @@ static void lio_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct_dev = lio->oct_dev;
 	int num_iq_stats, num_oq_stats, i, j;
+	int num_stats;
 
-	num_iq_stats = ARRAY_SIZE(oct_iq_stats_strings);
-	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
-		if (!(oct_dev->io_qmask.iq & (1UL << i)))
-			continue;
-		for (j = 0; j < num_iq_stats; j++) {
-			sprintf(data, "IQ%d %s", i, oct_iq_stats_strings[j]);
+	switch (stringset) {
+	case ETH_SS_STATS:
+		num_stats = ARRAY_SIZE(oct_stats_strings);
+		for (j = 0; j < num_stats; j++) {
+			sprintf(data, "%s", oct_stats_strings[j]);
 			data += ETH_GSTRING_LEN;
 		}
-	}
 
-	num_oq_stats = ARRAY_SIZE(oct_droq_stats_strings);
-	/* for (i = 0; i < oct_dev->num_oqs; i++) { */
-	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-		if (!(oct_dev->io_qmask.oq & (1UL << i)))
-			continue;
-		for (j = 0; j < num_oq_stats; j++) {
-			sprintf(data, "OQ%d %s", i, oct_droq_stats_strings[j]);
-			data += ETH_GSTRING_LEN;
+		num_iq_stats = ARRAY_SIZE(oct_iq_stats_strings);
+		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct_dev); i++) {
+			if (!(oct_dev->io_qmask.iq & (1ULL << i)))
+				continue;
+			for (j = 0; j < num_iq_stats; j++) {
+				sprintf(data, "tx-%d-%s", i,
+					oct_iq_stats_strings[j]);
+				data += ETH_GSTRING_LEN;
+			}
 		}
+
+		num_oq_stats = ARRAY_SIZE(oct_droq_stats_strings);
+		/* for (i = 0; i < oct_dev->num_oqs; i++) { */
+		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct_dev); i++) {
+			if (!(oct_dev->io_qmask.oq & (1ULL << i)))
+				continue;
+			for (j = 0; j < num_oq_stats; j++) {
+				sprintf(data, "rx-%d-%s", i,
+					oct_droq_stats_strings[j]);
+				data += ETH_GSTRING_LEN;
+			}
+		}
+		break;
+
+	default:
+		netif_info(lio, drv, lio->netdev, "Unknown Stringset !!\n");
+		break;
 	}
 }
 
@@ -609,8 +927,14 @@ static int lio_get_sset_count(struct net_device *netdev, int sset)
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct_dev = lio->oct_dev;
 
-	return (ARRAY_SIZE(oct_iq_stats_strings) * oct_dev->num_iqs) +
-	       (ARRAY_SIZE(oct_droq_stats_strings) * oct_dev->num_oqs);
+	switch (sset) {
+	case ETH_SS_STATS:
+		return (ARRAY_SIZE(oct_stats_strings) +
+			ARRAY_SIZE(oct_iq_stats_strings) * oct_dev->num_iqs +
+			ARRAY_SIZE(oct_droq_stats_strings) * oct_dev->num_oqs);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int lio_get_intr_coalesce(struct net_device *netdev,
@@ -618,50 +942,49 @@ static int lio_get_intr_coalesce(struct net_device *netdev,
 {
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
-	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
 	struct octeon_instr_queue *iq;
 	struct oct_intrmod_cfg *intrmod_cfg;
 
 	intrmod_cfg = &oct->intrmod;
 
 	switch (oct->chip_id) {
-	/* case OCTEON_CN73XX: Todo */
-	/*      break; */
 	case OCTEON_CN68XX:
-	case OCTEON_CN66XX:
-		if (!intrmod_cfg->intrmod_enable) {
+	case OCTEON_CN66XX: {
+		struct octeon_cn6xxx *cn6xxx =
+			(struct octeon_cn6xxx *)oct->chip;
+
+		if (!intrmod_cfg->rx_enable) {
 			intr_coal->rx_coalesce_usecs =
 				CFG_GET_OQ_INTR_TIME(cn6xxx->conf);
 			intr_coal->rx_max_coalesced_frames =
 				CFG_GET_OQ_INTR_PKT(cn6xxx->conf);
-		} else {
-			intr_coal->use_adaptive_rx_coalesce =
-				intrmod_cfg->intrmod_enable;
-			intr_coal->rate_sample_interval =
-				intrmod_cfg->intrmod_check_intrvl;
-			intr_coal->pkt_rate_high =
-				intrmod_cfg->intrmod_maxpkt_ratethr;
-			intr_coal->pkt_rate_low =
-				intrmod_cfg->intrmod_minpkt_ratethr;
-			intr_coal->rx_max_coalesced_frames_high =
-				intrmod_cfg->intrmod_maxcnt_trigger;
-			intr_coal->rx_coalesce_usecs_high =
-				intrmod_cfg->intrmod_maxtmr_trigger;
-			intr_coal->rx_coalesce_usecs_low =
-				intrmod_cfg->intrmod_mintmr_trigger;
-			intr_coal->rx_max_coalesced_frames_low =
-				intrmod_cfg->intrmod_mincnt_trigger;
 		}
-
-		iq = oct->instr_queue[lio->linfo.txpciq[0]];
+		iq = oct->instr_queue[lio->linfo.txpciq[0].s.q_no];
 		intr_coal->tx_max_coalesced_frames = iq->fill_threshold;
 		break;
-
+	}
 	default:
 		netif_info(lio, drv, lio->netdev, "Unknown Chip !!\n");
 		return -EINVAL;
 	}
-
+	if (intrmod_cfg->rx_enable) {
+		intr_coal->use_adaptive_rx_coalesce =
+			intrmod_cfg->rx_enable;
+		intr_coal->rate_sample_interval =
+			intrmod_cfg->check_intrvl;
+		intr_coal->pkt_rate_high =
+			intrmod_cfg->maxpkt_ratethr;
+		intr_coal->pkt_rate_low =
+			intrmod_cfg->minpkt_ratethr;
+		intr_coal->rx_max_coalesced_frames_high =
+			intrmod_cfg->rx_maxcnt_trigger;
+		intr_coal->rx_coalesce_usecs_high =
+			intrmod_cfg->rx_maxtmr_trigger;
+		intr_coal->rx_coalesce_usecs_low =
+			intrmod_cfg->rx_mintmr_trigger;
+		intr_coal->rx_max_coalesced_frames_low =
+			intrmod_cfg->rx_mincnt_trigger;
+	}
 	return 0;
 }
 
@@ -681,19 +1004,20 @@ static void octnet_intrmod_callback(struct octeon_device *oct_dev,
 	else
 		dev_info(&oct_dev->pci_dev->dev,
 			 "Rx-Adaptive Interrupt moderation enabled:%llx\n",
-			 oct_dev->intrmod.intrmod_enable);
+			 oct_dev->intrmod.rx_enable);
 
 	octeon_free_soft_command(oct_dev, sc);
 }
 
 /*  Configure interrupt moderation parameters */
-static int octnet_set_intrmod_cfg(void *oct, struct oct_intrmod_cfg *intr_cfg)
+static int octnet_set_intrmod_cfg(struct lio *lio,
+				  struct oct_intrmod_cfg *intr_cfg)
 {
 	struct octeon_soft_command *sc;
 	struct oct_intrmod_cmd *cmd;
 	struct oct_intrmod_cfg *cfg;
 	int retval;
-	struct octeon_device *oct_dev = (struct octeon_device *)oct;
+	struct octeon_device *oct_dev = lio->oct_dev;
 
 	/* Alloc soft command */
 	sc = (struct octeon_soft_command *)
@@ -714,6 +1038,8 @@ static int octnet_set_intrmod_cfg(void *oct, struct oct_intrmod_cfg *intr_cfg)
 	cmd->cfg = cfg;
 	cmd->oct_dev = oct_dev;
 
+	sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
 	octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
 				    OPCODE_NIC_INTRMOD_CFG, 0, 0, 0);
 
@@ -722,17 +1048,171 @@ static int octnet_set_intrmod_cfg(void *oct, struct oct_intrmod_cfg *intr_cfg)
 	sc->wait_time = 1000;
 
 	retval = octeon_send_soft_command(oct_dev, sc);
-	if (retval) {
+	if (retval == IQ_SEND_FAILED) {
+		octeon_free_soft_command(oct_dev, sc);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void
+octnet_nic_stats_callback(struct octeon_device *oct_dev,
+			  u32 status, void *ptr)
+{
+	struct octeon_soft_command  *sc = (struct octeon_soft_command  *)ptr;
+	struct oct_nic_stats_resp *resp = (struct oct_nic_stats_resp *)
+		sc->virtrptr;
+	struct oct_nic_stats_ctrl *ctrl = (struct oct_nic_stats_ctrl *)
+		sc->ctxptr;
+	struct nic_rx_stats *rsp_rstats = &resp->stats.fromwire;
+	struct nic_tx_stats *rsp_tstats = &resp->stats.fromhost;
+
+	struct nic_rx_stats *rstats = &oct_dev->link_stats.fromwire;
+	struct nic_tx_stats *tstats = &oct_dev->link_stats.fromhost;
+
+	if ((status != OCTEON_REQUEST_TIMEOUT) && !resp->status) {
+		octeon_swap_8B_data((u64 *)&resp->stats,
+				    (sizeof(struct oct_link_stats)) >> 3);
+
+		/* RX link-level stats */
+		rstats->total_rcvd = rsp_rstats->total_rcvd;
+		rstats->bytes_rcvd = rsp_rstats->bytes_rcvd;
+		rstats->total_bcst = rsp_rstats->total_bcst;
+		rstats->total_mcst = rsp_rstats->total_mcst;
+		rstats->runts      = rsp_rstats->runts;
+		rstats->ctl_rcvd   = rsp_rstats->ctl_rcvd;
+		/* Accounts for over/under-run of buffers */
+		rstats->fifo_err  = rsp_rstats->fifo_err;
+		rstats->dmac_drop = rsp_rstats->dmac_drop;
+		rstats->fcs_err   = rsp_rstats->fcs_err;
+		rstats->jabber_err = rsp_rstats->jabber_err;
+		rstats->l2_err    = rsp_rstats->l2_err;
+		rstats->frame_err = rsp_rstats->frame_err;
+
+		/* RX firmware stats */
+		rstats->fw_total_rcvd = rsp_rstats->fw_total_rcvd;
+		rstats->fw_total_fwd = rsp_rstats->fw_total_fwd;
+		rstats->fw_err_pko = rsp_rstats->fw_err_pko;
+		rstats->fw_err_link = rsp_rstats->fw_err_link;
+		rstats->fw_err_drop = rsp_rstats->fw_err_drop;
+		rstats->fw_rx_vxlan = rsp_rstats->fw_rx_vxlan;
+		rstats->fw_rx_vxlan_err = rsp_rstats->fw_rx_vxlan_err;
+
+		/* Number of packets that are LROed      */
+		rstats->fw_lro_pkts = rsp_rstats->fw_lro_pkts;
+		/* Number of octets that are LROed       */
+		rstats->fw_lro_octs = rsp_rstats->fw_lro_octs;
+		/* Number of LRO packets formed          */
+		rstats->fw_total_lro = rsp_rstats->fw_total_lro;
+		/* Number of times lRO of packet aborted */
+		rstats->fw_lro_aborts = rsp_rstats->fw_lro_aborts;
+		rstats->fw_lro_aborts_port = rsp_rstats->fw_lro_aborts_port;
+		rstats->fw_lro_aborts_seq = rsp_rstats->fw_lro_aborts_seq;
+		rstats->fw_lro_aborts_tsval = rsp_rstats->fw_lro_aborts_tsval;
+		rstats->fw_lro_aborts_timer = rsp_rstats->fw_lro_aborts_timer;
+		/* intrmod: packet forward rate */
+		rstats->fwd_rate = rsp_rstats->fwd_rate;
+
+		/* TX link-level stats */
+		tstats->total_pkts_sent = rsp_tstats->total_pkts_sent;
+		tstats->total_bytes_sent = rsp_tstats->total_bytes_sent;
+		tstats->mcast_pkts_sent = rsp_tstats->mcast_pkts_sent;
+		tstats->bcast_pkts_sent = rsp_tstats->bcast_pkts_sent;
+		tstats->ctl_sent = rsp_tstats->ctl_sent;
+		/* Packets sent after one collision*/
+		tstats->one_collision_sent = rsp_tstats->one_collision_sent;
+		/* Packets sent after multiple collision*/
+		tstats->multi_collision_sent = rsp_tstats->multi_collision_sent;
+		/* Packets not sent due to max collisions */
+		tstats->max_collision_fail = rsp_tstats->max_collision_fail;
+		/* Packets not sent due to max deferrals */
+		tstats->max_deferral_fail = rsp_tstats->max_deferral_fail;
+		/* Accounts for over/under-run of buffers */
+		tstats->fifo_err = rsp_tstats->fifo_err;
+		tstats->runts = rsp_tstats->runts;
+		/* Total number of collisions detected */
+		tstats->total_collisions = rsp_tstats->total_collisions;
+
+		/* firmware stats */
+		tstats->fw_total_sent = rsp_tstats->fw_total_sent;
+		tstats->fw_total_fwd = rsp_tstats->fw_total_fwd;
+		tstats->fw_err_pko = rsp_tstats->fw_err_pko;
+		tstats->fw_err_link = rsp_tstats->fw_err_link;
+		tstats->fw_err_drop = rsp_tstats->fw_err_drop;
+		tstats->fw_tso = rsp_tstats->fw_tso;
+		tstats->fw_tso_fwd = rsp_tstats->fw_tso_fwd;
+		tstats->fw_err_tso = rsp_tstats->fw_err_tso;
+		tstats->fw_tx_vxlan = rsp_tstats->fw_tx_vxlan;
+
+		resp->status = 1;
+	} else {
+		resp->status = -1;
+	}
+	complete(&ctrl->complete);
+}
+
+/*  Configure interrupt moderation parameters */
+static int octnet_get_link_stats(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct_dev = lio->oct_dev;
+
+	struct octeon_soft_command *sc;
+	struct oct_nic_stats_ctrl *ctrl;
+	struct oct_nic_stats_resp *resp;
+
+	int retval;
+
+	/* Alloc soft command */
+	sc = (struct octeon_soft_command *)
+		octeon_alloc_soft_command(oct_dev,
+					  0,
+					  sizeof(struct oct_nic_stats_resp),
+					  sizeof(struct octnic_ctrl_pkt));
+
+	if (!sc)
+		return -ENOMEM;
+
+	resp = (struct oct_nic_stats_resp *)sc->virtrptr;
+	memset(resp, 0, sizeof(struct oct_nic_stats_resp));
+
+	ctrl = (struct oct_nic_stats_ctrl *)sc->ctxptr;
+	memset(ctrl, 0, sizeof(struct oct_nic_stats_ctrl));
+	ctrl->netdev = netdev;
+	init_completion(&ctrl->complete);
+
+	sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
+	octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
+				    OPCODE_NIC_PORT_STATS, 0, 0, 0);
+
+	sc->callback = octnet_nic_stats_callback;
+	sc->callback_arg = sc;
+	sc->wait_time = 500;	/*in milli seconds*/
+
+	retval = octeon_send_soft_command(oct_dev, sc);
+	if (retval == IQ_SEND_FAILED) {
+		octeon_free_soft_command(oct_dev, sc);
+		return -EINVAL;
+	}
+
+	wait_for_completion_timeout(&ctrl->complete, msecs_to_jiffies(1000));
+
+	if (resp->status != 1) {
 		octeon_free_soft_command(oct_dev, sc);
+
 		return -EINVAL;
 	}
 
+	octeon_free_soft_command(oct_dev, sc);
+
 	return 0;
 }
 
 /* Enable/Disable auto interrupt Moderation */
 static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
-				 *intr_coal, int adaptive)
+				 *intr_coal)
 {
 	int ret = 0;
 	struct octeon_device *oct = lio->oct_dev;
@@ -740,59 +1220,73 @@ static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
 
 	intrmod_cfg = &oct->intrmod;
 
-	if (adaptive) {
+	if (oct->intrmod.rx_enable || oct->intrmod.tx_enable) {
 		if (intr_coal->rate_sample_interval)
-			intrmod_cfg->intrmod_check_intrvl =
+			intrmod_cfg->check_intrvl =
 				intr_coal->rate_sample_interval;
 		else
-			intrmod_cfg->intrmod_check_intrvl =
+			intrmod_cfg->check_intrvl =
 				LIO_INTRMOD_CHECK_INTERVAL;
 
 		if (intr_coal->pkt_rate_high)
-			intrmod_cfg->intrmod_maxpkt_ratethr =
+			intrmod_cfg->maxpkt_ratethr =
 				intr_coal->pkt_rate_high;
 		else
-			intrmod_cfg->intrmod_maxpkt_ratethr =
+			intrmod_cfg->maxpkt_ratethr =
 				LIO_INTRMOD_MAXPKT_RATETHR;
 
 		if (intr_coal->pkt_rate_low)
-			intrmod_cfg->intrmod_minpkt_ratethr =
+			intrmod_cfg->minpkt_ratethr =
 				intr_coal->pkt_rate_low;
 		else
-			intrmod_cfg->intrmod_minpkt_ratethr =
+			intrmod_cfg->minpkt_ratethr =
 				LIO_INTRMOD_MINPKT_RATETHR;
-
+	}
+	if (oct->intrmod.rx_enable) {
 		if (intr_coal->rx_max_coalesced_frames_high)
-			intrmod_cfg->intrmod_maxcnt_trigger =
+			intrmod_cfg->rx_maxcnt_trigger =
 				intr_coal->rx_max_coalesced_frames_high;
 		else
-			intrmod_cfg->intrmod_maxcnt_trigger =
-				LIO_INTRMOD_MAXCNT_TRIGGER;
+			intrmod_cfg->rx_maxcnt_trigger =
+				LIO_INTRMOD_RXMAXCNT_TRIGGER;
 
 		if (intr_coal->rx_coalesce_usecs_high)
-			intrmod_cfg->intrmod_maxtmr_trigger =
+			intrmod_cfg->rx_maxtmr_trigger =
 				intr_coal->rx_coalesce_usecs_high;
 		else
-			intrmod_cfg->intrmod_maxtmr_trigger =
-				LIO_INTRMOD_MAXTMR_TRIGGER;
+			intrmod_cfg->rx_maxtmr_trigger =
+				LIO_INTRMOD_RXMAXTMR_TRIGGER;
 
 		if (intr_coal->rx_coalesce_usecs_low)
-			intrmod_cfg->intrmod_mintmr_trigger =
+			intrmod_cfg->rx_mintmr_trigger =
 				intr_coal->rx_coalesce_usecs_low;
 		else
-			intrmod_cfg->intrmod_mintmr_trigger =
-				LIO_INTRMOD_MINTMR_TRIGGER;
+			intrmod_cfg->rx_mintmr_trigger =
+				LIO_INTRMOD_RXMINTMR_TRIGGER;
 
 		if (intr_coal->rx_max_coalesced_frames_low)
-			intrmod_cfg->intrmod_mincnt_trigger =
+			intrmod_cfg->rx_mincnt_trigger =
 				intr_coal->rx_max_coalesced_frames_low;
 		else
-			intrmod_cfg->intrmod_mincnt_trigger =
-				LIO_INTRMOD_MINCNT_TRIGGER;
+			intrmod_cfg->rx_mincnt_trigger =
+				LIO_INTRMOD_RXMINCNT_TRIGGER;
+	}
+	if (oct->intrmod.tx_enable) {
+		if (intr_coal->tx_max_coalesced_frames_high)
+			intrmod_cfg->tx_maxcnt_trigger =
+				intr_coal->tx_max_coalesced_frames_high;
+		else
+			intrmod_cfg->tx_maxcnt_trigger =
+				LIO_INTRMOD_TXMAXCNT_TRIGGER;
+		if (intr_coal->tx_max_coalesced_frames_low)
+			intrmod_cfg->tx_mincnt_trigger =
+				intr_coal->tx_max_coalesced_frames_low;
+		else
+			intrmod_cfg->tx_mincnt_trigger =
+				LIO_INTRMOD_TXMINCNT_TRIGGER;
 	}
 
-	intrmod_cfg->intrmod_enable = adaptive;
-	ret = octnet_set_intrmod_cfg(oct, intrmod_cfg);
+	ret = octnet_set_intrmod_cfg(lio, intrmod_cfg);
 
 	return ret;
 }
@@ -800,54 +1294,82 @@ static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
 static int
 oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
 {
-	int ret;
 	struct octeon_device *oct = lio->oct_dev;
-	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
 	u32 rx_max_coalesced_frames;
 
-	if (!intr_coal->rx_max_coalesced_frames)
-		rx_max_coalesced_frames = CN6XXX_OQ_INTR_PKT;
-	else
-		rx_max_coalesced_frames = intr_coal->rx_max_coalesced_frames;
-
-	/* Disable adaptive interrupt modulation */
-	ret = oct_cfg_adaptive_intr(lio, intr_coal, 0);
-	if (ret)
-		return ret;
-
 	/* Config Cnt based interrupt values */
-	octeon_write_csr(oct, CN6XXX_SLI_OQ_INT_LEVEL_PKTS,
-			 rx_max_coalesced_frames);
-	CFG_SET_OQ_INTR_PKT(cn6xxx->conf, rx_max_coalesced_frames);
+	switch (oct->chip_id) {
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX: {
+		struct octeon_cn6xxx *cn6xxx =
+			(struct octeon_cn6xxx *)oct->chip;
+
+		if (!intr_coal->rx_max_coalesced_frames)
+			rx_max_coalesced_frames = CN6XXX_OQ_INTR_PKT;
+		else
+			rx_max_coalesced_frames =
+				intr_coal->rx_max_coalesced_frames;
+		octeon_write_csr(oct, CN6XXX_SLI_OQ_INT_LEVEL_PKTS,
+				 rx_max_coalesced_frames);
+		CFG_SET_OQ_INTR_PKT(cn6xxx->conf, rx_max_coalesced_frames);
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
 	return 0;
 }
 
 static int oct_cfg_rx_intrtime(struct lio *lio, struct ethtool_coalesce
 			       *intr_coal)
 {
-	int ret;
 	struct octeon_device *oct = lio->oct_dev;
-	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
 	u32 time_threshold, rx_coalesce_usecs;
 
-	if (!intr_coal->rx_coalesce_usecs)
-		rx_coalesce_usecs = CN6XXX_OQ_INTR_TIME;
-	else
-		rx_coalesce_usecs = intr_coal->rx_coalesce_usecs;
+	/* Config Time based interrupt values */
+	switch (oct->chip_id) {
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX: {
+		struct octeon_cn6xxx *cn6xxx =
+			(struct octeon_cn6xxx *)oct->chip;
+		if (!intr_coal->rx_coalesce_usecs)
+			rx_coalesce_usecs = CN6XXX_OQ_INTR_TIME;
+		else
+			rx_coalesce_usecs = intr_coal->rx_coalesce_usecs;
 
-	/* Disable adaptive interrupt modulation */
-	ret = oct_cfg_adaptive_intr(lio, intr_coal, 0);
-	if (ret)
-		return ret;
+		time_threshold = lio_cn6xxx_get_oq_ticks(oct,
+							 rx_coalesce_usecs);
+		octeon_write_csr(oct,
+				 CN6XXX_SLI_OQ_INT_LEVEL_TIME,
+				 time_threshold);
 
-	/* Config Time based interrupt values */
-	time_threshold = lio_cn6xxx_get_oq_ticks(oct, rx_coalesce_usecs);
-	octeon_write_csr(oct, CN6XXX_SLI_OQ_INT_LEVEL_TIME, time_threshold);
-	CFG_SET_OQ_INTR_TIME(cn6xxx->conf, rx_coalesce_usecs);
+		CFG_SET_OQ_INTR_TIME(cn6xxx->conf, rx_coalesce_usecs);
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
 
 	return 0;
 }
 
+static int
+oct_cfg_tx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal
+		   __attribute__((unused)))
+{
+	struct octeon_device *oct = lio->oct_dev;
+
+	/* Config Cnt based interrupt values */
+	switch (oct->chip_id) {
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX:
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int lio_set_intr_coalesce(struct net_device *netdev,
 				 struct ethtool_coalesce *intr_coal)
 {
@@ -855,59 +1377,48 @@ static int lio_set_intr_coalesce(struct net_device *netdev,
 	int ret;
 	struct octeon_device *oct = lio->oct_dev;
 	u32 j, q_no;
+	int db_max, db_min;
 
-	if ((intr_coal->tx_max_coalesced_frames >= CN6XXX_DB_MIN) &&
-	    (intr_coal->tx_max_coalesced_frames <= CN6XXX_DB_MAX)) {
-		for (j = 0; j < lio->linfo.num_txpciq; j++) {
-			q_no = lio->linfo.txpciq[j];
-			oct->instr_queue[q_no]->fill_threshold =
-				intr_coal->tx_max_coalesced_frames;
+	switch (oct->chip_id) {
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX:
+		db_min = CN6XXX_DB_MIN;
+		db_max = CN6XXX_DB_MAX;
+		if ((intr_coal->tx_max_coalesced_frames >= db_min) &&
+		    (intr_coal->tx_max_coalesced_frames <= db_max)) {
+			for (j = 0; j < lio->linfo.num_txpciq; j++) {
+				q_no = lio->linfo.txpciq[j].s.q_no;
+				oct->instr_queue[q_no]->fill_threshold =
+					intr_coal->tx_max_coalesced_frames;
+			}
+		} else {
+			dev_err(&oct->pci_dev->dev,
+				"LIQUIDIO: Invalid tx-frames:%d. Range is min:%d max:%d\n",
+				intr_coal->tx_max_coalesced_frames, db_min,
+				db_max);
+			return -EINVAL;
 		}
-	} else {
-		dev_err(&oct->pci_dev->dev,
-			"LIQUIDIO: Invalid tx-frames:%d. Range is min:%d max:%d\n",
-			intr_coal->tx_max_coalesced_frames, CN6XXX_DB_MIN,
-			CN6XXX_DB_MAX);
+		break;
+	default:
 		return -EINVAL;
 	}
 
-	/* User requested adaptive-rx on */
-	if (intr_coal->use_adaptive_rx_coalesce) {
-		ret = oct_cfg_adaptive_intr(lio, intr_coal, 1);
-		if (ret)
-			goto ret_intrmod;
-	}
+	oct->intrmod.rx_enable = intr_coal->use_adaptive_rx_coalesce ? 1 : 0;
+	oct->intrmod.tx_enable = intr_coal->use_adaptive_tx_coalesce ? 1 : 0;
 
-	/* User requested adaptive-rx off and rx coalesce */
-	if ((intr_coal->rx_coalesce_usecs) &&
-	    (!intr_coal->use_adaptive_rx_coalesce)) {
+	ret = oct_cfg_adaptive_intr(lio, intr_coal);
+
+	if (!intr_coal->use_adaptive_rx_coalesce) {
 		ret = oct_cfg_rx_intrtime(lio, intr_coal);
 		if (ret)
 			goto ret_intrmod;
-	}
 
-	/* User requested adaptive-rx off and rx coalesce */
-	if ((intr_coal->rx_max_coalesced_frames) &&
-	    (!intr_coal->use_adaptive_rx_coalesce)) {
 		ret = oct_cfg_rx_intrcnt(lio, intr_coal);
 		if (ret)
 			goto ret_intrmod;
 	}
-
-	/* User requested adaptive-rx off, so use default coalesce params */
-	if ((!intr_coal->rx_max_coalesced_frames) &&
-	    (!intr_coal->use_adaptive_rx_coalesce) &&
-	    (!intr_coal->rx_coalesce_usecs)) {
-		dev_info(&oct->pci_dev->dev,
-			 "Turning off adaptive-rx interrupt moderation\n");
-		dev_info(&oct->pci_dev->dev,
-			 "Using RX Coalesce Default values rx_coalesce_usecs:%d rx_max_coalesced_frames:%d\n",
-			 CN6XXX_OQ_INTR_TIME, CN6XXX_OQ_INTR_PKT);
-		ret = oct_cfg_rx_intrtime(lio, intr_coal);
-		if (ret)
-			goto ret_intrmod;
-
-		ret = oct_cfg_rx_intrcnt(lio, intr_coal);
+	if (!intr_coal->use_adaptive_tx_coalesce) {
+		ret = oct_cfg_tx_intrcnt(lio, intr_coal);
 		if (ret)
 			goto ret_intrmod;
 	}
@@ -923,23 +1434,28 @@ static int lio_get_ts_info(struct net_device *netdev,
 	struct lio *lio = GET_LIO(netdev);
 
 	info->so_timestamping =
+#ifdef PTP_HARDWARE_TIMESTAMPING
 		SOF_TIMESTAMPING_TX_HARDWARE |
-		SOF_TIMESTAMPING_TX_SOFTWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
+		SOF_TIMESTAMPING_RAW_HARDWARE |
+		SOF_TIMESTAMPING_TX_SOFTWARE |
+#endif
 		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_RAW_HARDWARE;
+		SOF_TIMESTAMPING_SOFTWARE;
 
 	if (lio->ptp_clock)
 		info->phc_index = ptp_clock_index(lio->ptp_clock);
 	else
 		info->phc_index = -1;
 
+#ifdef PTP_HARDWARE_TIMESTAMPING
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON);
 
 	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
 			   (1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
 			   (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
 			   (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT);
+#endif
 
 	return 0;
 }
@@ -950,7 +1466,6 @@ static int lio_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	struct octeon_device *oct = lio->oct_dev;
 	struct oct_link_info *linfo;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 	int ret = 0;
 
 	/* get the link info */
@@ -965,12 +1480,14 @@ static int lio_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 						  ecmd->duplex != DUPLEX_FULL)))
 		return -EINVAL;
 
-	/* Ethtool Support is not provided for XAUI and RXAUI Interfaces
+	/* Ethtool Support is not provided for XAUI, RXAUI, and XFI Interfaces
 	 * as they operate at fixed Speed and Duplex settings
 	 */
-	if (linfo->link.s.interface == INTERFACE_MODE_XAUI ||
-	    linfo->link.s.interface == INTERFACE_MODE_RXAUI) {
-		dev_info(&oct->pci_dev->dev, "XAUI IFs settings cannot be modified.\n");
+	if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI ||
+	    linfo->link.s.if_mode == INTERFACE_MODE_RXAUI ||
+	    linfo->link.s.if_mode == INTERFACE_MODE_XFI) {
+		dev_info(&oct->pci_dev->dev,
+			 "Autonegotiation, duplex and speed settings cannot be modified.\n");
 		return -EINVAL;
 	}
 
@@ -978,9 +1495,9 @@ static int lio_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = OCTNET_CMD_SET_SETTINGS;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.wait_time = 1000;
 	nctrl.netpndev = (u64)netdev;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 
 	/* Passing the parameters sent by ethtool like Speed, Autoneg & Duplex
@@ -990,19 +1507,17 @@ static int lio_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 		/* Autoneg ON */
 		nctrl.ncmd.s.more = OCTNIC_NCMD_PHY_ON |
 				     OCTNIC_NCMD_AUTONEG_ON;
-		nctrl.ncmd.s.param2 = ecmd->advertising;
+		nctrl.ncmd.s.param1 = ecmd->advertising;
 	} else {
 		/* Autoneg OFF */
 		nctrl.ncmd.s.more = OCTNIC_NCMD_PHY_ON;
 
-		nctrl.ncmd.s.param3 = ecmd->duplex;
+		nctrl.ncmd.s.param2 = ecmd->duplex;
 
-		nctrl.ncmd.s.param2 = ecmd->speed;
+		nctrl.ncmd.s.param1 = ecmd->speed;
 	}
 
-	nparams.resp_order = OCTEON_RESP_ORDERED;
-
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "Failed to set settings\n");
 		return -1;
@@ -1026,7 +1541,7 @@ static int lio_nway_reset(struct net_device *netdev)
 }
 
 /* Return register dump len. */
-static int lio_get_regs_len(struct net_device *dev)
+static int lio_get_regs_len(struct net_device *dev __attribute__((unused)))
 {
 	return OCT_ETHTOOL_REGDUMP_LEN;
 }
@@ -1170,13 +1685,12 @@ static void lio_get_regs(struct net_device *dev,
 	int len = 0;
 	struct octeon_device *oct = lio->oct_dev;
 
-	memset(regbuf, 0, OCT_ETHTOOL_REGDUMP_LEN);
 	regs->version = OCT_ETHTOOL_REGSVER;
 
 	switch (oct->chip_id) {
-	/* case OCTEON_CN73XX: Todo */
 	case OCTEON_CN68XX:
 	case OCTEON_CN66XX:
+		memset(regbuf, 0, OCT_ETHTOOL_REGDUMP_LEN);
 		len += cn6xxx_read_csr_reg(regbuf + len, oct);
 		len += cn6xxx_read_config_reg(regbuf + len, oct);
 		break;
@@ -1186,6 +1700,23 @@ static void lio_get_regs(struct net_device *dev,
 	}
 }
 
+static u32 lio_get_priv_flags(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	return lio->oct_dev->priv_flags;
+}
+
+static int lio_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct lio *lio = GET_LIO(netdev);
+	bool intr_by_tx_bytes = !!(flags & (0x1 << OCT_PRIV_FLAG_TX_BYTES));
+
+	lio_set_priv_flag(lio->oct_dev, OCT_PRIV_FLAG_TX_BYTES,
+			  intr_by_tx_bytes);
+	return 0;
+}
+
 static const struct ethtool_ops lio_ethtool_ops = {
 	.get_settings		= lio_get_settings,
 	.get_link		= ethtool_op_get_link,
@@ -1207,6 +1738,8 @@ static const struct ethtool_ops lio_ethtool_ops = {
 	.set_settings		= lio_set_settings,
 	.get_coalesce		= lio_get_intr_coalesce,
 	.set_coalesce		= lio_set_intr_coalesce,
+	.get_priv_flags		= lio_get_priv_flags,
+	.set_priv_flags		= lio_set_priv_flags,
 	.get_ts_info		= lio_get_ts_info,
 };
 
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 8de79ae63231..20d6942edf40 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -20,24 +20,12 @@
 * Contact Cavium, Inc. for more information
 **********************************************************************/
 #include <linux/version.h>
-#include <linux/module.h>
-#include <linux/crc32.h>
-#include <linux/dma-mapping.h>
 #include <linux/pci.h>
-#include <linux/pci_ids.h>
-#include <linux/ip.h>
-#include <net/ip.h>
-#include <linux/ipv6.h>
 #include <linux/net_tstamp.h>
 #include <linux/if_vlan.h>
 #include <linux/firmware.h>
-#include <linux/ethtool.h>
 #include <linux/ptp_clock_kernel.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/workqueue.h>
-#include <linux/interrupt.h>
-#include "octeon_config.h"
+#include <net/vxlan.h>
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
@@ -48,7 +36,6 @@
 #include "octeon_network.h"
 #include "cn66xx_regs.h"
 #include "cn66xx_device.h"
-#include "cn68xx_regs.h"
 #include "cn68xx_device.h"
 #include "liquidio_image.h"
 
@@ -72,6 +59,9 @@ MODULE_PARM_DESC(console_bitmask,
 
 #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
 
+#define INCR_INSTRQUEUE_PKT_COUNT(octeon_dev_ptr, iq_no, field, count)  \
+	(octeon_dev_ptr->instr_queue[iq_no]->stats.field += count)
+
 static int debug = -1;
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "NETIF_MSG debug bits");
@@ -84,6 +74,8 @@ static int conf_type;
 module_param(conf_type, int, 0);
 MODULE_PARM_DESC(conf_type, "select octeon configuration 0 default 1 ovs");
 
+static int ptp_enable = 1;
+
 /* Bit mask values for lio->ifstate */
 #define   LIO_IFSTATE_DROQ_OPS             0x01
 #define   LIO_IFSTATE_REGISTERED           0x02
@@ -166,6 +158,8 @@ struct octnic_gather {
 	 *  received from the IP layer.
 	 */
 	struct octeon_sg_entry *sg;
+
+	u64 sg_dma_ptr;
 };
 
 /** This structure is used by NIC driver to store information required
@@ -220,8 +214,8 @@ static void octeon_droq_bh(unsigned long pdev)
 		(struct octeon_device_priv *)oct->priv;
 
 	/* for (q_no = 0; q_no < oct->num_oqs; q_no++) { */
-	for (q_no = 0; q_no < MAX_OCTEON_OUTPUT_QUEUES; q_no++) {
-		if (!(oct->io_qmask.oq & (1UL << q_no)))
+	for (q_no = 0; q_no < MAX_OCTEON_OUTPUT_QUEUES(oct); q_no++) {
+		if (!(oct->io_qmask.oq & (1ULL << q_no)))
 			continue;
 		reschedule |= octeon_droq_process_packets(oct, oct->droq[q_no],
 							  MAX_PACKET_BUDGET);
@@ -241,11 +235,10 @@ static int lio_wait_for_oq_pkts(struct octeon_device *oct)
 	do {
 		pending_pkts = 0;
 
-		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-			if (!(oct->io_qmask.oq & (1UL << i)))
+		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
+			if (!(oct->io_qmask.oq & (1ULL << i)))
 				continue;
-			pkt_cnt += octeon_droq_check_hw_for_pkts(oct,
-								 oct->droq[i]);
+			pkt_cnt += octeon_droq_check_hw_for_pkts(oct->droq[i]);
 		}
 		if (pkt_cnt > 0) {
 			pending_pkts += pkt_cnt;
@@ -361,7 +354,7 @@ static int wait_for_pending_requests(struct octeon_device *oct)
 				[OCTEON_ORDERED_SC_LIST].pending_req_count);
 		if (pcount)
 			schedule_timeout_uninterruptible(HZ / 10);
-		 else
+		else
 			break;
 	}
 
@@ -392,10 +385,10 @@ static inline void pcierror_quiesce_device(struct octeon_device *oct)
 		dev_err(&oct->pci_dev->dev, "There were pending requests\n");
 
 	/* Force all requests waiting to be fetched by OCTEON to complete. */
-	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
 		struct octeon_instr_queue *iq;
 
-		if (!(oct->io_qmask.iq & (1UL << i)))
+		if (!(oct->io_qmask.iq & (1ULL << i)))
 			continue;
 		iq = oct->instr_queue[i];
 
@@ -405,7 +398,7 @@ static inline void pcierror_quiesce_device(struct octeon_device *oct)
 			iq->octeon_read_index = iq->host_write_index;
 			iq->stats.instr_processed +=
 				atomic_read(&iq->instr_pending);
-			lio_process_iq_request_list(oct, iq);
+			lio_process_iq_request_list(oct, iq, 0);
 			spin_unlock_bh(&iq->lock);
 		}
 	}
@@ -500,7 +493,8 @@ static pci_ers_result_t liquidio_pcie_error_detected(struct pci_dev *pdev,
  * \brief mmio handler
  * @param pdev Pointer to PCI device
  */
-static pci_ers_result_t liquidio_pcie_mmio_enabled(struct pci_dev *pdev)
+static pci_ers_result_t liquidio_pcie_mmio_enabled(
+				struct pci_dev *pdev __attribute__((unused)))
 {
 	/* We should never hit this since we never ask for a reset for a Fatal
 	 * Error. We always return DISCONNECT in io_error above.
@@ -516,7 +510,8 @@ static pci_ers_result_t liquidio_pcie_mmio_enabled(struct pci_dev *pdev)
  * Restart the card from scratch, as if from a cold-boot. Implementation
  * resembles the first-half of the octeon_resume routine.
  */
-static pci_ers_result_t liquidio_pcie_slot_reset(struct pci_dev *pdev)
+static pci_ers_result_t liquidio_pcie_slot_reset(
+				struct pci_dev *pdev __attribute__((unused)))
 {
 	/* We should never hit this since we never ask for a reset for a Fatal
 	 * Error. We always return DISCONNECT in io_error above.
@@ -533,7 +528,7 @@ static pci_ers_result_t liquidio_pcie_slot_reset(struct pci_dev *pdev)
  * its OK to resume normal operation. Implementation resembles the
  * second-half of the octeon_resume routine.
  */
-static void liquidio_pcie_resume(struct pci_dev *pdev)
+static void liquidio_pcie_resume(struct pci_dev *pdev __attribute__((unused)))
 {
 	/* Nothing to be done here. */
 }
@@ -544,7 +539,8 @@ static void liquidio_pcie_resume(struct pci_dev *pdev)
  * @param pdev Pointer to PCI device
  * @param state state to suspend to
  */
-static int liquidio_suspend(struct pci_dev *pdev, pm_message_t state)
+static int liquidio_suspend(struct pci_dev *pdev __attribute__((unused)),
+			    pm_message_t state __attribute__((unused)))
 {
 	return 0;
 }
@@ -553,7 +549,7 @@ static int liquidio_suspend(struct pci_dev *pdev, pm_message_t state)
  * \brief called when resuming
  * @param pdev Pointer to PCI device
  */
-static int liquidio_resume(struct pci_dev *pdev)
+static int liquidio_resume(struct pci_dev *pdev __attribute__((unused)))
 {
 	return 0;
 }
@@ -678,12 +674,24 @@ static inline void txqs_start(struct net_device *netdev)
  */
 static inline void txqs_wake(struct net_device *netdev)
 {
+	struct lio *lio = GET_LIO(netdev);
+
 	if (netif_is_multiqueue(netdev)) {
 		int i;
 
-		for (i = 0; i < netdev->num_tx_queues; i++)
-			netif_wake_subqueue(netdev, i);
+		for (i = 0; i < netdev->num_tx_queues; i++) {
+			int qno = lio->linfo.txpciq[i %
+				(lio->linfo.num_txpciq)].s.q_no;
+
+			if (__netif_subqueue_stopped(netdev, i)) {
+				INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, qno,
+							  tx_restart, 1);
+				netif_wake_subqueue(netdev, i);
+			}
+		}
 	} else {
+		INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, lio->txq,
+					  tx_restart, 1);
 		netif_wake_queue(netdev);
 	}
 }
@@ -705,7 +713,7 @@ static void start_txq(struct net_device *netdev)
 {
 	struct lio *lio = GET_LIO(netdev);
 
-	if (lio->linfo.link.s.status) {
+	if (lio->linfo.link.s.link_up) {
 		txqs_start(netdev);
 		return;
 	}
@@ -752,16 +760,23 @@ static inline int check_txq_status(struct lio *lio)
 
 		/* check each sub-queue state */
 		for (q = 0; q < numqs; q++) {
-			iq = lio->linfo.txpciq[q & (lio->linfo.num_txpciq - 1)];
+			iq = lio->linfo.txpciq[q %
+				(lio->linfo.num_txpciq)].s.q_no;
 			if (octnet_iq_is_full(lio->oct_dev, iq))
 				continue;
-			wake_q(lio->netdev, q);
-			ret_val++;
+			if (__netif_subqueue_stopped(lio->netdev, q)) {
+				wake_q(lio->netdev, q);
+				INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq,
+							  tx_restart, 1);
+				ret_val++;
+			}
 		}
 	} else {
 		if (octnet_iq_is_full(lio->oct_dev, lio->txq))
 			return 0;
 		wake_q(lio->netdev, lio->txq);
+		INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, lio->txq,
+					  tx_restart, 1);
 		ret_val = 1;
 	}
 	return ret_val;
@@ -787,64 +802,116 @@ static inline struct list_head *list_delete_head(struct list_head *root)
 }
 
 /**
- * \brief Delete gather list
+ * \brief Delete gather lists
  * @param lio per-network private data
  */
-static void delete_glist(struct lio *lio)
+static void delete_glists(struct lio *lio)
 {
 	struct octnic_gather *g;
+	int i;
 
-	do {
-		g = (struct octnic_gather *)
-		    list_delete_head(&lio->glist);
-		if (g) {
-			if (g->sg)
-				kfree((void *)((unsigned long)g->sg -
-						g->adjust));
-			kfree(g);
-		}
-	} while (g);
+	if (!lio->glist)
+		return;
+
+	for (i = 0; i < lio->linfo.num_txpciq; i++) {
+		do {
+			g = (struct octnic_gather *)
+				list_delete_head(&lio->glist[i]);
+			if (g) {
+				if (g->sg) {
+					dma_unmap_single(&lio->oct_dev->
+							 pci_dev->dev,
+							 g->sg_dma_ptr,
+							 g->sg_size,
+							 DMA_TO_DEVICE);
+					kfree((void *)((unsigned long)g->sg -
+						       g->adjust));
+				}
+				kfree(g);
+			}
+		} while (g);
+	}
+
+	kfree((void *)lio->glist);
 }
 
 /**
- * \brief Setup gather list
+ * \brief Setup gather lists
  * @param lio per-network private data
  */
-static int setup_glist(struct lio *lio)
+static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs)
 {
-	int i;
+	int i, j;
 	struct octnic_gather *g;
 
-	INIT_LIST_HEAD(&lio->glist);
+	lio->glist_lock = kcalloc(num_iqs, sizeof(*lio->glist_lock),
+				  GFP_KERNEL);
+	if (!lio->glist_lock)
+		return 1;
 
-	for (i = 0; i < lio->tx_qsize; i++) {
-		g = kzalloc(sizeof(*g), GFP_KERNEL);
-		if (!g)
-			break;
+	lio->glist = kcalloc(num_iqs, sizeof(*lio->glist),
+			     GFP_KERNEL);
+	if (!lio->glist) {
+		kfree((void *)lio->glist_lock);
+		return 1;
+	}
 
-		g->sg_size =
-			((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
+	for (i = 0; i < num_iqs; i++) {
+		int numa_node = cpu_to_node(i % num_online_cpus());
 
-		g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL);
-		if (!g->sg) {
-			kfree(g);
-			break;
+		spin_lock_init(&lio->glist_lock[i]);
+
+		INIT_LIST_HEAD(&lio->glist[i]);
+
+		for (j = 0; j < lio->tx_qsize; j++) {
+			g = kzalloc_node(sizeof(*g), GFP_KERNEL,
+					 numa_node);
+			if (!g)
+				g = kzalloc(sizeof(*g), GFP_KERNEL);
+			if (!g)
+				break;
+
+			g->sg_size = ((ROUNDUP4(OCTNIC_MAX_SG) >> 2) *
+				      OCT_SG_ENTRY_SIZE);
+
+			g->sg = kmalloc_node(g->sg_size + 8,
+					     GFP_KERNEL, numa_node);
+			if (!g->sg)
+				g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL);
+			if (!g->sg) {
+				kfree(g);
+				break;
+			}
+
+			/* The gather component should be aligned on 64-bit
+			 * boundary
+			 */
+			if (((unsigned long)g->sg) & 7) {
+				g->adjust = 8 - (((unsigned long)g->sg) & 7);
+				g->sg = (struct octeon_sg_entry *)
+					((unsigned long)g->sg + g->adjust);
+			}
+			g->sg_dma_ptr = dma_map_single(&oct->pci_dev->dev,
+						       g->sg, g->sg_size,
+						       DMA_TO_DEVICE);
+			if (dma_mapping_error(&oct->pci_dev->dev,
+					      g->sg_dma_ptr)) {
+				kfree((void *)((unsigned long)g->sg -
+					       g->adjust));
+				kfree(g);
+				break;
+			}
+
+			list_add_tail(&g->list, &lio->glist[i]);
 		}
 
-		/* The gather component should be aligned on 64-bit boundary */
-		if (((unsigned long)g->sg) & 7) {
-			g->adjust = 8 - (((unsigned long)g->sg) & 7);
-			g->sg = (struct octeon_sg_entry *)
-				((unsigned long)g->sg + g->adjust);
+		if (j != lio->tx_qsize) {
+			delete_glists(lio);
+			return 1;
 		}
-		list_add_tail(&g->list, &lio->glist);
 	}
 
-	if (i == lio->tx_qsize)
-		return 0;
-
-	delete_glist(lio);
-	return 1;
+	return 0;
 }
 
 /**
@@ -858,7 +925,7 @@ static void print_link_info(struct net_device *netdev)
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED) {
 		struct oct_link_info *linfo = &lio->linfo;
 
-		if (linfo->link.s.status) {
+		if (linfo->link.s.link_up) {
 			netif_info(lio, link, lio->netdev, "%d Mbps %s Duplex UP\n",
 				   linfo->link.s.speed,
 				   (linfo->link.s.duplex) ? "Full" : "Half");
@@ -880,13 +947,15 @@ static inline void update_link_status(struct net_device *netdev,
 				      union oct_link_status *ls)
 {
 	struct lio *lio = GET_LIO(netdev);
+	int changed = (lio->linfo.link.u64 != ls->u64);
 
-	if ((lio->intf_open) && (lio->linfo.link.u64 != ls->u64)) {
-		lio->linfo.link.u64 = ls->u64;
+	lio->linfo.link.u64 = ls->u64;
 
+	if ((lio->intf_open) && (changed)) {
 		print_link_info(netdev);
+		lio->link_changes++;
 
-		if (lio->linfo.link.s.status) {
+		if (lio->linfo.link.s.link_up) {
 			netif_carrier_on(netdev);
 			/* start_txq(netdev); */
 			txqs_wake(netdev);
@@ -897,6 +966,42 @@ static inline void update_link_status(struct net_device *netdev,
 	}
 }
 
+/* Runs in interrupt context. */
+static void update_txq_status(struct octeon_device *oct, int iq_num)
+{
+	struct net_device *netdev;
+	struct lio *lio;
+	struct octeon_instr_queue *iq = oct->instr_queue[iq_num];
+
+	/*octeon_update_iq_read_idx(oct, iq);*/
+
+	netdev = oct->props[iq->ifidx].netdev;
+
+	/* This is needed because the first IQ does not have
+	 * a netdev associated with it.
+	 */
+	if (!netdev)
+		return;
+
+	lio = GET_LIO(netdev);
+	if (netif_is_multiqueue(netdev)) {
+		if (__netif_subqueue_stopped(netdev, iq->q_index) &&
+		    lio->linfo.link.s.link_up &&
+		    (!octnet_iq_is_full(oct, iq_num))) {
+			INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num,
+						  tx_restart, 1);
+			netif_wake_subqueue(netdev, iq->q_index);
+		} else {
+			if (!octnet_iq_is_full(oct, lio->txq)) {
+				INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev,
+							  lio->txq,
+							  tx_restart, 1);
+				wake_q(netdev, lio->txq);
+			}
+		}
+	}
+}
+
 /**
  * \brief Droq packet processor sceduler
  * @param oct octeon device
@@ -910,8 +1015,9 @@ void liquidio_schedule_droq_pkt_handlers(struct octeon_device *oct)
 	struct octeon_droq *droq;
 
 	if (oct->int_status & OCT_DEV_INTR_PKT_DATA) {
-		for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES; oq_no++) {
-			if (!(oct->droq_intr & (1 << oq_no)))
+		for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES(oct);
+		     oq_no++) {
+			if (!(oct->droq_intr & (1ULL << oq_no)))
 				continue;
 
 			droq = oct->droq[oq_no];
@@ -987,7 +1093,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
  * @param pdev PCI device structure
  * @param ent unused
  */
-static int liquidio_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+static int
+liquidio_probe(struct pci_dev *pdev,
+	       const struct pci_device_id *ent __attribute__((unused)))
 {
 	struct octeon_device *oct_dev = NULL;
 	struct handshake *hs;
@@ -1022,6 +1130,9 @@ static int liquidio_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENOMEM;
 	}
 
+	oct_dev->rx_pause = 1;
+	oct_dev->tx_pause = 1;
+
 	dev_dbg(&oct_dev->pci_dev->dev, "Device is ready\n");
 
 	return 0;
@@ -1087,19 +1198,13 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 		if (oct->flags & LIO_FLAG_MSI_ENABLED)
 			pci_disable_msi(oct->pci_dev);
 
-		/* Soft reset the octeon device before exiting */
-		oct->fn_list.soft_reset(oct);
-
-		/* Disable the device, releasing the PCI INT */
-		pci_disable_device(oct->pci_dev);
-
 		/* fallthrough */
 	case OCT_DEV_IN_RESET:
 	case OCT_DEV_DROQ_INIT_DONE:
 		/*atomic_set(&oct->status, OCT_DEV_DROQ_INIT_DONE);*/
 		mdelay(100);
-		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-			if (!(oct->io_qmask.oq & (1UL << i)))
+		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
+			if (!(oct->io_qmask.oq & (1ULL << i)))
 				continue;
 			octeon_delete_droq(oct, i);
 		}
@@ -1126,8 +1231,8 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 
 		/* fallthrough */
 	case OCT_DEV_INSTR_QUEUE_INIT_DONE:
-		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
-			if (!(oct->io_qmask.iq & (1UL << i)))
+		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+			if (!(oct->io_qmask.iq & (1ULL << i)))
 				continue;
 			octeon_delete_instr_queue(oct, i);
 		}
@@ -1139,14 +1244,21 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 
 		/* fallthrough */
 	case OCT_DEV_PCI_MAP_DONE:
+
+		/* Soft reset the octeon device before exiting */
+		oct->fn_list.soft_reset(oct);
+
 		octeon_unmap_pci_barx(oct, 0);
 		octeon_unmap_pci_barx(oct, 1);
 
 		/* fallthrough */
 	case OCT_DEV_BEGIN_STATE:
+		/* Disable the device, releasing the PCI INT */
+		pci_disable_device(oct->pci_dev);
+
 		/* Nothing to be done here either */
 		break;
-	}                       /* end switch(oct->status) */
+	}                       /* end switch (oct->status) */
 
 	tasklet_kill(&oct_priv->droq_tasklet);
 }
@@ -1159,18 +1271,15 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
 {
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 
 	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
 
 	nctrl.ncmd.s.cmd = OCTNET_CMD_RX_CTL;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = start_stop;
+	nctrl.ncmd.s.param1 = start_stop;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.netpndev = (u64)lio->netdev;
 
-	nparams.resp_order = OCTEON_RESP_NORESPONSE;
-
-	if (octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams) < 0)
+	if (octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl) < 0)
 		netif_info(lio, rx_err, lio->netdev, "Failed to send RX Control message\n");
 }
 
@@ -1186,6 +1295,7 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 {
 	struct net_device *netdev = oct->props[ifidx].netdev;
 	struct lio *lio;
+	struct napi_struct *napi, *n;
 
 	if (!netdev) {
 		dev_err(&oct->pci_dev->dev, "%s No netdevice ptr for index %d\n",
@@ -1202,13 +1312,22 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_RUNNING)
 		txqs_stop(netdev);
 
+	if (oct->props[lio->ifidx].napi_enabled == 1) {
+		list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
+			napi_disable(napi);
+
+		oct->props[lio->ifidx].napi_enabled = 0;
+	}
+
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED)
 		unregister_netdev(netdev);
 
-	delete_glist(lio);
+	delete_glists(lio);
 
 	free_netdev(netdev);
 
+	oct->props[ifidx].gmxport = -1;
+
 	oct->props[ifidx].netdev = NULL;
 }
 
@@ -1227,10 +1346,15 @@ static int liquidio_stop_nic_module(struct octeon_device *oct)
 		return 1;
 	}
 
+	spin_lock_bh(&oct->cmd_resp_wqlock);
+	oct->cmd_resp_state = OCT_DRV_OFFLINE;
+	spin_unlock_bh(&oct->cmd_resp_wqlock);
+
 	for (i = 0; i < oct->ifcount; i++) {
 		lio = GET_LIO(oct->props[i].netdev);
 		for (j = 0; j < lio->linfo.num_rxpciq; j++)
-			octeon_unregister_droq_ops(oct, lio->linfo.rxpciq[j]);
+			octeon_unregister_droq_ops(oct,
+						   lio->linfo.rxpciq[j].s.q_no);
 	}
 
 	for (i = 0; i < oct->ifcount; i++)
@@ -1274,6 +1398,7 @@ static int octeon_chip_specific_setup(struct octeon_device *oct)
 {
 	u32 dev_id, rev_id;
 	int ret = 1;
+	char *s;
 
 	pci_read_config_dword(oct->pci_dev, 0, &dev_id);
 	pci_read_config_dword(oct->pci_dev, 8, &rev_id);
@@ -1283,22 +1408,27 @@ static int octeon_chip_specific_setup(struct octeon_device *oct)
 	case OCTEON_CN68XX_PCIID:
 		oct->chip_id = OCTEON_CN68XX;
 		ret = lio_setup_cn68xx_octeon_device(oct);
+		s = "CN68XX";
 		break;
 
 	case OCTEON_CN66XX_PCIID:
 		oct->chip_id = OCTEON_CN66XX;
 		ret = lio_setup_cn66xx_octeon_device(oct);
+		s = "CN66XX";
 		break;
+
 	default:
+		s = "?";
 		dev_err(&oct->pci_dev->dev, "Unknown device found (dev_id: %x)\n",
 			dev_id);
 	}
 
 	if (!ret)
-		dev_info(&oct->pci_dev->dev, "CN68XX PASS%d.%d %s\n",
+		dev_info(&oct->pci_dev->dev, "%s PASS%d.%d %s Version: %s\n", s,
 			 OCTEON_MAJOR_REV(oct),
 			 OCTEON_MINOR_REV(oct),
-			 octeon_get_conf(oct)->card_name);
+			 octeon_get_conf(oct)->card_name,
+			 LIQUIDIO_VERSION);
 
 	return ret;
 }
@@ -1326,6 +1456,16 @@ static int octeon_pci_os_setup(struct octeon_device *oct)
 	return 0;
 }
 
+static inline int skb_iq(struct lio *lio, struct sk_buff *skb)
+{
+	int q = 0;
+
+	if (netif_is_multiqueue(lio->netdev))
+		q = skb->queue_mapping % lio->linfo.num_txpciq;
+
+	return q;
+}
+
 /**
  * \brief Check Tx queue state for a given network buffer
  * @param lio per-network private data
@@ -1337,14 +1477,19 @@ static inline int check_txq_state(struct lio *lio, struct sk_buff *skb)
 
 	if (netif_is_multiqueue(lio->netdev)) {
 		q = skb->queue_mapping;
-		iq = lio->linfo.txpciq[(q & (lio->linfo.num_txpciq - 1))];
+		iq = lio->linfo.txpciq[(q % (lio->linfo.num_txpciq))].s.q_no;
 	} else {
 		iq = lio->txq;
+		q = iq;
 	}
 
 	if (octnet_iq_is_full(lio->oct_dev, iq))
 		return 0;
-	wake_q(lio->netdev, q);
+
+	if (__netif_subqueue_stopped(lio->netdev, q)) {
+		INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq, tx_restart, 1);
+		wake_q(lio->netdev, q);
+	}
 	return 1;
 }
 
@@ -1367,7 +1512,7 @@ static void free_netbuf(void *buf)
 
 	check_txq_state(lio, skb);
 
-	recv_buffer_free((struct sk_buff *)skb);
+	tx_buffer_free(skb);
 }
 
 /**
@@ -1380,7 +1525,7 @@ static void free_netsgbuf(void *buf)
 	struct sk_buff *skb;
 	struct lio *lio;
 	struct octnic_gather *g;
-	int i, frags;
+	int i, frags, iq;
 
 	finfo = (struct octnet_buf_free_info *)buf;
 	skb = finfo->skb;
@@ -1402,17 +1547,17 @@ static void free_netsgbuf(void *buf)
 		i++;
 	}
 
-	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
-			 finfo->dptr, g->sg_size,
-			 DMA_TO_DEVICE);
+	dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev,
+				g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE);
 
-	spin_lock(&lio->lock);
-	list_add_tail(&g->list, &lio->glist);
-	spin_unlock(&lio->lock);
+	iq = skb_iq(lio, skb);
+	spin_lock(&lio->glist_lock[iq]);
+	list_add_tail(&g->list, &lio->glist[iq]);
+	spin_unlock(&lio->glist_lock[iq]);
 
 	check_txq_state(lio, skb);     /* mq support: sub-queue state check */
 
-	recv_buffer_free((struct sk_buff *)skb);
+	tx_buffer_free(skb);
 }
 
 /**
@@ -1426,7 +1571,7 @@ static void free_netsgbuf_with_resp(void *buf)
 	struct sk_buff *skb;
 	struct lio *lio;
 	struct octnic_gather *g;
-	int i, frags;
+	int i, frags, iq;
 
 	sc = (struct octeon_soft_command *)buf;
 	skb = (struct sk_buff *)sc->callback_arg;
@@ -1450,13 +1595,14 @@ static void free_netsgbuf_with_resp(void *buf)
 		i++;
 	}
 
-	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
-			 finfo->dptr, g->sg_size,
-			 DMA_TO_DEVICE);
+	dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev,
+				g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE);
+
+	iq = skb_iq(lio, skb);
 
-	spin_lock(&lio->lock);
-	list_add_tail(&g->list, &lio->glist);
-	spin_unlock(&lio->lock);
+	spin_lock(&lio->glist_lock[iq]);
+	list_add_tail(&g->list, &lio->glist[iq]);
+	spin_unlock(&lio->glist_lock[iq]);
 
 	/* Don't free the skb yet */
 
@@ -1569,8 +1715,10 @@ static int liquidio_ptp_settime(struct ptp_clock_info *ptp,
  * @param rq request
  * @param on is it on
  */
-static int liquidio_ptp_enable(struct ptp_clock_info *ptp,
-			       struct ptp_clock_request *rq, int on)
+static int
+liquidio_ptp_enable(struct ptp_clock_info *ptp __attribute__((unused)),
+		    struct ptp_clock_request *rq __attribute__((unused)),
+		    int on __attribute__((unused)))
 {
 	return -EOPNOTSUPP;
 }
@@ -1657,6 +1805,7 @@ static int load_firmware(struct octeon_device *oct)
 	if (ret) {
 		dev_err(&oct->pci_dev->dev, "Request firmware failed. Could not find file %s.\n.",
 			fw_name);
+		release_firmware(fw);
 		return ret;
 	}
 
@@ -1710,7 +1859,7 @@ static int octeon_setup_droq(struct octeon_device *oct, int q_no, int num_descs,
  * @param buf pointer to resp structure
  */
 static void if_cfg_callback(struct octeon_device *oct,
-			    u32 status,
+			    u32 status __attribute__((unused)),
 			    void *buf)
 {
 	struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
@@ -1724,7 +1873,10 @@ static void if_cfg_callback(struct octeon_device *oct,
 	if (resp->status)
 		dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n",
 			CVM_CAST64(resp->status));
-	ACCESS_ONCE(ctx->cond) = 1;
+	WRITE_ONCE(ctx->cond, 1);
+
+	snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s",
+		 resp->cfg_info.liquidio_firmware_version);
 
 	/* This barrier is required to be sure that the response has been
 	 * written fully before waking up the handler
@@ -1741,16 +1893,16 @@ static void if_cfg_callback(struct octeon_device *oct,
  * @returns selected queue number
  */
 static u16 select_q(struct net_device *dev, struct sk_buff *skb,
-		    void *accel_priv, select_queue_fallback_t fallback)
+		    void *accel_priv __attribute__((unused)),
+		    select_queue_fallback_t fallback __attribute__((unused)))
 {
-	int qindex;
+	u32 qindex = 0;
 	struct lio *lio;
 
 	lio = GET_LIO(dev);
-	/* select queue on chosen queue_mapping or core */
-	qindex = skb_rx_queue_recorded(skb) ?
-		 skb_get_rx_queue(skb) : smp_processor_id();
-	return (u16)(qindex & (lio->linfo.num_txpciq - 1));
+	qindex = skb_tx_hash(dev, skb);
+
+	return (u16)(qindex % (lio->linfo.num_txpciq));
 }
 
 /** Routine to push packets arriving on Octeon interface upto network layer.
@@ -1759,26 +1911,28 @@ static u16 select_q(struct net_device *dev, struct sk_buff *skb,
  * @param len      - size of total data received.
  * @param rh       - Control header associated with the packet
  * @param param    - additional control data with the packet
+ * @param arg	   - farg registered in droq_ops
  */
 static void
-liquidio_push_packet(u32 octeon_id,
+liquidio_push_packet(u32 octeon_id __attribute__((unused)),
 		     void *skbuff,
 		     u32 len,
 		     union octeon_rh *rh,
-		     void *param)
+		     void *param,
+		     void *arg)
 {
 	struct napi_struct *napi = param;
-	struct octeon_device *oct = lio_get_device(octeon_id);
 	struct sk_buff *skb = (struct sk_buff *)skbuff;
 	struct skb_shared_hwtstamps *shhwtstamps;
 	u64 ns;
-	struct net_device *netdev =
-		(struct net_device *)oct->props[rh->r_dh.link].netdev;
+	u16 vtag = 0;
+	struct net_device *netdev = (struct net_device *)arg;
 	struct octeon_droq *droq = container_of(param, struct octeon_droq,
 						napi);
 	if (netdev) {
 		int packet_was_received;
 		struct lio *lio = GET_LIO(netdev);
+		struct octeon_device *oct = lio->oct_dev;
 
 		/* Do not proceed if the interface is not in RUNNING state. */
 		if (!ifstate_check(lio, LIO_IFSTATE_RUNNING)) {
@@ -1789,32 +1943,86 @@ liquidio_push_packet(u32 octeon_id,
 
 		skb->dev = netdev;
 
-		if (rh->r_dh.has_hwtstamp) {
-			/* timestamp is included from the hardware at the
-			 * beginning of the packet.
-			 */
-			if (ifstate_check(lio,
-					  LIO_IFSTATE_RX_TIMESTAMP_ENABLED)) {
-				/* Nanoseconds are in the first 64-bits
-				 * of the packet.
+		skb_record_rx_queue(skb, droq->q_no);
+		if (likely(len > MIN_SKB_SIZE)) {
+			struct octeon_skb_page_info *pg_info;
+			unsigned char *va;
+
+			pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+			if (pg_info->page) {
+				/* For Paged allocation use the frags */
+				va = page_address(pg_info->page) +
+					pg_info->page_offset;
+				memcpy(skb->data, va, MIN_SKB_SIZE);
+				skb_put(skb, MIN_SKB_SIZE);
+				skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+						pg_info->page,
+						pg_info->page_offset +
+						MIN_SKB_SIZE,
+						len - MIN_SKB_SIZE,
+						LIO_RXBUFFER_SZ);
+			}
+		} else {
+			struct octeon_skb_page_info *pg_info =
+				((struct octeon_skb_page_info *)(skb->cb));
+			skb_copy_to_linear_data(skb, page_address(pg_info->page)
+						+ pg_info->page_offset, len);
+			skb_put(skb, len);
+			put_page(pg_info->page);
+		}
+
+		if (((oct->chip_id == OCTEON_CN66XX) ||
+		     (oct->chip_id == OCTEON_CN68XX)) &&
+		    ptp_enable) {
+			if (rh->r_dh.has_hwtstamp) {
+				/* timestamp is included from the hardware at
+				 * the beginning of the packet.
 				 */
-				memcpy(&ns, (skb->data), sizeof(ns));
-				shhwtstamps = skb_hwtstamps(skb);
-				shhwtstamps->hwtstamp =
-					ns_to_ktime(ns + lio->ptp_adjust);
+				if (ifstate_check
+				    (lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED)) {
+					/* Nanoseconds are in the first 64-bits
+					 * of the packet.
+					 */
+					memcpy(&ns, (skb->data), sizeof(ns));
+					shhwtstamps = skb_hwtstamps(skb);
+					shhwtstamps->hwtstamp =
+						ns_to_ktime(ns +
+							    lio->ptp_adjust);
+				}
+				skb_pull(skb, sizeof(ns));
 			}
-			skb_pull(skb, sizeof(ns));
 		}
 
 		skb->protocol = eth_type_trans(skb, skb->dev);
-
 		if ((netdev->features & NETIF_F_RXCSUM) &&
-		    (rh->r_dh.csum_verified == CNNIC_CSUM_VERIFIED))
+		    (((rh->r_dh.encap_on) &&
+		      (rh->r_dh.csum_verified & CNNIC_TUN_CSUM_VERIFIED)) ||
+		     (!(rh->r_dh.encap_on) &&
+		      (rh->r_dh.csum_verified & CNNIC_CSUM_VERIFIED))))
 			/* checksum has already been verified */
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 		else
 			skb->ip_summed = CHECKSUM_NONE;
 
+		/* Setting Encapsulation field on basis of status received
+		 * from the firmware
+		 */
+		if (rh->r_dh.encap_on) {
+			skb->encapsulation = 1;
+			skb->csum_level = 1;
+			droq->stats.rx_vxlan++;
+		}
+
+		/* inbound VLAN tag */
+		if ((netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+		    (rh->r_dh.vlan != 0)) {
+			u16 vid = rh->r_dh.vlan;
+			u16 priority = rh->r_dh.priority;
+
+			vtag = priority << 13 | vid;
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vtag);
+		}
+
 		packet_was_received = napi_gro_receive(napi, skb) != GRO_DROP;
 
 		if (packet_was_received) {
@@ -1869,39 +2077,6 @@ static void liquidio_napi_drv_callback(void *arg)
 }
 
 /**
- * \brief Main NAPI poll function
- * @param droq octeon output queue
- * @param budget maximum number of items to process
- */
-static int liquidio_napi_do_rx(struct octeon_droq *droq, int budget)
-{
-	int work_done;
-	struct lio *lio = GET_LIO(droq->napi.dev);
-	struct octeon_device *oct = lio->oct_dev;
-
-	work_done = octeon_process_droq_poll_cmd(oct, droq->q_no,
-						 POLL_EVENT_PROCESS_PKTS,
-						 budget);
-	if (work_done < 0) {
-		netif_info(lio, rx_err, lio->netdev,
-			   "Receive work_done < 0, rxq:%d\n", droq->q_no);
-		goto octnet_napi_finish;
-	}
-
-	if (work_done > budget)
-		dev_err(&oct->pci_dev->dev, ">>>> %s work_done: %d budget: %d\n",
-			__func__, work_done, budget);
-
-	return work_done;
-
-octnet_napi_finish:
-	napi_complete(&droq->napi);
-	octeon_process_droq_poll_cmd(oct, droq->q_no, POLL_EVENT_ENABLE_INTR,
-				     0);
-	return 0;
-}
-
-/**
  * \brief Entry point for NAPI polling
  * @param napi NAPI structure
  * @param budget maximum number of items to process
@@ -1910,35 +2085,57 @@ static int liquidio_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct octeon_droq *droq;
 	int work_done;
+	int tx_done = 0, iq_no;
+	struct octeon_instr_queue *iq;
+	struct octeon_device *oct;
 
 	droq = container_of(napi, struct octeon_droq, napi);
+	oct = droq->oct_dev;
+	iq_no = droq->q_no;
+	/* Handle Droq descriptors */
+	work_done = octeon_process_droq_poll_cmd(oct, droq->q_no,
+						 POLL_EVENT_PROCESS_PKTS,
+						 budget);
 
-	work_done = liquidio_napi_do_rx(droq, budget);
+	/* Flush the instruction queue */
+	iq = oct->instr_queue[iq_no];
+	if (iq) {
+		/* Process iq buffers with in the budget limits */
+		tx_done = octeon_flush_iq(oct, iq, 1, budget);
+		/* Update iq read-index rather than waiting for next interrupt.
+		 * Return back if tx_done is false.
+		 */
+		update_txq_status(oct, iq_no);
+		/*tx_done = (iq->flush_index == iq->octeon_read_index);*/
+	} else {
+		dev_err(&oct->pci_dev->dev, "%s:  iq (%d) num invalid\n",
+			__func__, iq_no);
+	}
 
-	if (work_done < budget) {
+	if ((work_done < budget) && (tx_done)) {
 		napi_complete(napi);
 		octeon_process_droq_poll_cmd(droq->oct_dev, droq->q_no,
 					     POLL_EVENT_ENABLE_INTR, 0);
 		return 0;
 	}
 
-	return work_done;
+	return (!tx_done) ? (budget) : (work_done);
 }
 
 /**
  * \brief Setup input and output queues
  * @param octeon_dev octeon device
- * @param net_device Net device
+ * @param ifidx  Interface Index
  *
  * Note: Queues are with respect to the octeon device. Thus
  * an input queue is for egress packets, and output queues
  * are for ingress packets.
  */
 static inline int setup_io_queues(struct octeon_device *octeon_dev,
-				  struct net_device *net_device)
+				  int ifidx)
 {
-	static int first_time = 1;
-	static struct octeon_droq_ops droq_ops;
+	struct octeon_droq_ops droq_ops;
+	struct net_device *netdev;
 	static int cpu_id;
 	static int cpu_id_modulus;
 	struct octeon_droq *droq;
@@ -1947,23 +2144,26 @@ static inline int setup_io_queues(struct octeon_device *octeon_dev,
 	struct lio *lio;
 	int num_tx_descs;
 
-	lio = GET_LIO(net_device);
-	if (first_time) {
-		first_time = 0;
-		memset(&droq_ops, 0, sizeof(struct octeon_droq_ops));
+	netdev = octeon_dev->props[ifidx].netdev;
 
-		droq_ops.fptr = liquidio_push_packet;
+	lio = GET_LIO(netdev);
 
-		droq_ops.poll_mode = 1;
-		droq_ops.napi_fn = liquidio_napi_drv_callback;
-		cpu_id = 0;
-		cpu_id_modulus = num_present_cpus();
-	}
+	memset(&droq_ops, 0, sizeof(struct octeon_droq_ops));
+
+	droq_ops.fptr = liquidio_push_packet;
+	droq_ops.farg = (void *)netdev;
+
+	droq_ops.poll_mode = 1;
+	droq_ops.napi_fn = liquidio_napi_drv_callback;
+	cpu_id = 0;
+	cpu_id_modulus = num_present_cpus();
 
 	/* set up DROQs. */
 	for (q = 0; q < lio->linfo.num_rxpciq; q++) {
-		q_no = lio->linfo.rxpciq[q];
-
+		q_no = lio->linfo.rxpciq[q].s.q_no;
+		dev_dbg(&octeon_dev->pci_dev->dev,
+			"setup_io_queues index:%d linfo.rxpciq.s.q_no:%d\n",
+			q, q_no);
 		retval = octeon_setup_droq(octeon_dev, q_no,
 					   CFG_GET_NUM_RX_DESCS_NIC_IF
 						   (octeon_get_conf(octeon_dev),
@@ -1980,7 +2180,11 @@ static inline int setup_io_queues(struct octeon_device *octeon_dev,
 
 		droq = octeon_dev->droq[q_no];
 		napi = &droq->napi;
-		netif_napi_add(net_device, napi, liquidio_napi_poll, 64);
+		dev_dbg(&octeon_dev->pci_dev->dev,
+			"netif_napi_add netdev:%llx oct:%llx\n",
+			(u64)netdev,
+			(u64)octeon_dev);
+		netif_napi_add(netdev, napi, liquidio_napi_poll, 64);
 
 		/* designate a CPU for this droq */
 		droq->cpu_id = cpu_id;
@@ -1996,9 +2200,9 @@ static inline int setup_io_queues(struct octeon_device *octeon_dev,
 		num_tx_descs = CFG_GET_NUM_TX_DESCS_NIC_IF(octeon_get_conf
 							   (octeon_dev),
 							   lio->ifidx);
-		retval = octeon_setup_iq(octeon_dev, lio->linfo.txpciq[q],
-					 num_tx_descs,
-					 netdev_get_tx_queue(net_device, q));
+		retval = octeon_setup_iq(octeon_dev, ifidx, q,
+					 lio->linfo.txpciq[q], num_tx_descs,
+					 netdev_get_tx_queue(netdev, q));
 		if (retval) {
 			dev_err(&octeon_dev->pci_dev->dev,
 				" %s : Runtime IQ(TxQ) creation failed.\n",
@@ -2036,7 +2240,8 @@ static inline void setup_tx_poll_fn(struct net_device *netdev)
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 
-	lio->txq_status_wq.wq = create_workqueue("txq-status");
+	lio->txq_status_wq.wq = alloc_workqueue("txq-status",
+						WQ_MEM_RECLAIM, 0);
 	if (!lio->txq_status_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "unable to create cavium txq status wq\n");
 		return;
@@ -2048,6 +2253,14 @@ static inline void setup_tx_poll_fn(struct net_device *netdev)
 			   &lio->txq_status_wq.wk.work, msecs_to_jiffies(1));
 }
 
+static inline void cleanup_tx_poll_fn(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	cancel_delayed_work_sync(&lio->txq_status_wq.wk.work);
+	destroy_workqueue(lio->txq_status_wq.wq);
+}
+
 /**
  * \brief Net device open for LiquidIO
  * @param netdev network device
@@ -2058,17 +2271,22 @@ static int liquidio_open(struct net_device *netdev)
 	struct octeon_device *oct = lio->oct_dev;
 	struct napi_struct *napi, *n;
 
-	list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
-		napi_enable(napi);
+	if (oct->props[lio->ifidx].napi_enabled == 0) {
+		list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
+			napi_enable(napi);
+
+		oct->props[lio->ifidx].napi_enabled = 1;
+	}
 
 	oct_ptp_open(netdev);
 
 	ifstate_set(lio, LIO_IFSTATE_RUNNING);
+
 	setup_tx_poll_fn(netdev);
+
 	start_txq(netdev);
 
 	netif_info(lio, ifup, lio->netdev, "Interface Open, ready for traffic\n");
-	try_module_get(THIS_MODULE);
 
 	/* tell Octeon to start forwarding packets to host */
 	send_rx_ctrl_cmd(lio, 1);
@@ -2088,41 +2306,36 @@ static int liquidio_open(struct net_device *netdev)
  */
 static int liquidio_stop(struct net_device *netdev)
 {
-	struct napi_struct *napi, *n;
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 
-	netif_info(lio, ifdown, lio->netdev, "Stopping interface!\n");
+	ifstate_reset(lio, LIO_IFSTATE_RUNNING);
+
+	netif_tx_disable(netdev);
+
 	/* Inform that netif carrier is down */
+	netif_carrier_off(netdev);
 	lio->intf_open = 0;
-	lio->linfo.link.s.status = 0;
+	lio->linfo.link.s.link_up = 0;
+	lio->link_changes++;
 
-	netif_carrier_off(netdev);
+	/* Pause for a moment and wait for Octeon to flush out (to the wire) any
+	 * egress packets that are in-flight.
+	 */
+	set_current_state(TASK_INTERRUPTIBLE);
+	schedule_timeout(msecs_to_jiffies(100));
 
-	/* tell Octeon to stop forwarding packets to host */
+	/* Now it should be safe to tell Octeon that nic interface is down. */
 	send_rx_ctrl_cmd(lio, 0);
 
-	cancel_delayed_work_sync(&lio->txq_status_wq.wk.work);
-	flush_workqueue(lio->txq_status_wq.wq);
-	destroy_workqueue(lio->txq_status_wq.wq);
+	cleanup_tx_poll_fn(netdev);
 
 	if (lio->ptp_clock) {
 		ptp_clock_unregister(lio->ptp_clock);
 		lio->ptp_clock = NULL;
 	}
 
-	ifstate_reset(lio, LIO_IFSTATE_RUNNING);
-
-	/* This is a hack that allows DHCP to continue working. */
-	set_bit(__LINK_STATE_START, &lio->netdev->state);
-
-	list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
-		napi_disable(napi);
-
-	txqs_stop(netdev);
-
 	dev_info(&oct->pci_dev->dev, "%s interface is stopped\n", netdev->name);
-	module_put(THIS_MODULE);
 
 	return 0;
 }
@@ -2133,6 +2346,7 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
 	struct net_device *netdev = (struct net_device *)nctrl->netpndev;
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
+	u8 *mac;
 
 	switch (nctrl->ncmd.s.cmd) {
 	case OCTNET_CMD_CHANGE_DEVFLAGS:
@@ -2140,22 +2354,24 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
 		break;
 
 	case OCTNET_CMD_CHANGE_MACADDR:
-		/* If command is successful, change the MACADDR. */
-		netif_info(lio, probe, lio->netdev, " MACAddr changed to 0x%llx\n",
-			   CVM_CAST64(nctrl->udd[0]));
-		dev_info(&oct->pci_dev->dev, "%s MACAddr changed to 0x%llx\n",
-			 netdev->name, CVM_CAST64(nctrl->udd[0]));
-		memcpy(netdev->dev_addr, ((u8 *)&nctrl->udd[0]) + 2, ETH_ALEN);
+		mac = ((u8 *)&nctrl->udd[0]) + 2;
+		netif_info(lio, probe, lio->netdev,
+			   "%s %2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x\n",
+			   "MACAddr changed to", mac[0], mac[1],
+			   mac[2], mac[3], mac[4], mac[5]);
 		break;
 
 	case OCTNET_CMD_CHANGE_MTU:
 		/* If command is successful, change the MTU. */
 		netif_info(lio, probe, lio->netdev, " MTU Changed from %d to %d\n",
-			   netdev->mtu, nctrl->ncmd.s.param2);
+			   netdev->mtu, nctrl->ncmd.s.param1);
 		dev_info(&oct->pci_dev->dev, "%s MTU Changed from %d to %d\n",
 			 netdev->name, netdev->mtu,
-			 nctrl->ncmd.s.param2);
-		netdev->mtu = nctrl->ncmd.s.param2;
+			 nctrl->ncmd.s.param1);
+		rtnl_lock();
+		netdev->mtu = nctrl->ncmd.s.param1;
+		call_netdevice_notifiers(NETDEV_CHANGEMTU, netdev);
+		rtnl_unlock();
 		break;
 
 	case OCTNET_CMD_GPIO_ACCESS:
@@ -2181,11 +2397,79 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
 			 netdev->name);
 		break;
 
+	case OCTNET_CMD_ENABLE_VLAN_FILTER:
+		dev_info(&oct->pci_dev->dev, "%s VLAN filter enabled\n",
+			 netdev->name);
+		break;
+
+	case OCTNET_CMD_ADD_VLAN_FILTER:
+		dev_info(&oct->pci_dev->dev, "%s VLAN filter %d added\n",
+			 netdev->name, nctrl->ncmd.s.param1);
+		break;
+
+	case OCTNET_CMD_DEL_VLAN_FILTER:
+		dev_info(&oct->pci_dev->dev, "%s VLAN filter %d removed\n",
+			 netdev->name, nctrl->ncmd.s.param1);
+		break;
+
 	case OCTNET_CMD_SET_SETTINGS:
 		dev_info(&oct->pci_dev->dev, "%s settings changed\n",
 			 netdev->name);
 
 		break;
+		/* Case to handle "OCTNET_CMD_TNL_RX_CSUM_CTL"
+		 * Command passed by NIC driver
+		 */
+	case OCTNET_CMD_TNL_RX_CSUM_CTL:
+		if (nctrl->ncmd.s.param1 == OCTNET_CMD_RXCSUM_ENABLE) {
+			netif_info(lio, probe, lio->netdev,
+				   "%s RX Checksum Offload Enabled\n",
+				   netdev->name);
+		} else if (nctrl->ncmd.s.param1 ==
+			   OCTNET_CMD_RXCSUM_DISABLE) {
+			netif_info(lio, probe, lio->netdev,
+				   "%s RX Checksum Offload Disabled\n",
+				   netdev->name);
+		}
+		break;
+
+		/* Case to handle "OCTNET_CMD_TNL_TX_CSUM_CTL"
+		 * Command passed by NIC driver
+		 */
+	case OCTNET_CMD_TNL_TX_CSUM_CTL:
+		if (nctrl->ncmd.s.param1 == OCTNET_CMD_TXCSUM_ENABLE) {
+			netif_info(lio, probe, lio->netdev,
+				   "%s TX Checksum Offload Enabled\n",
+				   netdev->name);
+		} else if (nctrl->ncmd.s.param1 ==
+			   OCTNET_CMD_TXCSUM_DISABLE) {
+			netif_info(lio, probe, lio->netdev,
+				   "%s TX Checksum Offload Disabled\n",
+				   netdev->name);
+		}
+		break;
+
+		/* Case to handle "OCTNET_CMD_VXLAN_PORT_CONFIG"
+		 * Command passed by NIC driver
+		 */
+	case OCTNET_CMD_VXLAN_PORT_CONFIG:
+		if (nctrl->ncmd.s.more == OCTNET_CMD_VXLAN_PORT_ADD) {
+			netif_info(lio, probe, lio->netdev,
+				   "%s VxLAN Destination UDP PORT:%d ADDED\n",
+				   netdev->name,
+				   nctrl->ncmd.s.param1);
+		} else if (nctrl->ncmd.s.more ==
+			   OCTNET_CMD_VXLAN_PORT_DEL) {
+			netif_info(lio, probe, lio->netdev,
+				   "%s VxLAN Destination UDP PORT:%d DELETED\n",
+				   netdev->name,
+				   nctrl->ncmd.s.param1);
+		}
+		break;
+
+	case OCTNET_CMD_SET_FLOW_CTL:
+		netif_info(lio, probe, lio->netdev, "Set RX/TX flow control parameters\n");
+		break;
 
 	default:
 		dev_err(&oct->pci_dev->dev, "%s Unknown cmd %d\n", __func__,
@@ -2235,10 +2519,9 @@ static void liquidio_set_mcast_list(struct net_device *netdev)
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 	struct netdev_hw_addr *ha;
 	u64 *mc;
-	int ret, i;
+	int ret;
 	int mc_count = min(netdev_mc_count(netdev), MAX_OCTEON_MULTICAST_ADDR);
 
 	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
@@ -2246,15 +2529,14 @@ static void liquidio_set_mcast_list(struct net_device *netdev)
 	/* Create a ctrl pkt command to be sent to core app. */
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = OCTNET_CMD_SET_MULTI_LIST;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = get_new_flags(netdev);
-	nctrl.ncmd.s.param3 = mc_count;
+	nctrl.ncmd.s.param1 = get_new_flags(netdev);
+	nctrl.ncmd.s.param2 = mc_count;
 	nctrl.ncmd.s.more = mc_count;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.netpndev = (u64)netdev;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 
 	/* copy all the addresses into the udd */
-	i = 0;
 	mc = &nctrl.udd[0];
 	netdev_for_each_mc_addr(ha, netdev) {
 		*mc = 0;
@@ -2270,9 +2552,7 @@ static void liquidio_set_mcast_list(struct net_device *netdev)
 	 */
 	nctrl.wait_time = 0;
 
-	nparams.resp_order = OCTEON_RESP_NORESPONSE;
-
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "DEVFLAGS change failed in core (ret: 0x%x)\n",
 			ret);
@@ -2290,19 +2570,17 @@ static int liquidio_set_mac(struct net_device *netdev, void *p)
 	struct octeon_device *oct = lio->oct_dev;
 	struct sockaddr *addr = (struct sockaddr *)p;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 
-	if ((!is_valid_ether_addr(addr->sa_data)) ||
-	    (ifstate_check(lio, LIO_IFSTATE_RUNNING)))
+	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
 	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
 
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = OCTNET_CMD_CHANGE_MACADDR;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = 0;
+	nctrl.ncmd.s.param1 = 0;
 	nctrl.ncmd.s.more = 1;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.netpndev = (u64)netdev;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 	nctrl.wait_time = 100;
@@ -2311,9 +2589,7 @@ static int liquidio_set_mac(struct net_device *netdev, void *p)
 	/* The MAC Address is presented in network byte order. */
 	memcpy((u8 *)&nctrl.udd[0] + 2, addr->sa_data, ETH_ALEN);
 
-	nparams.resp_order = OCTEON_RESP_ORDERED;
-
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "MAC Address change failed\n");
 		return -ENOMEM;
@@ -2341,7 +2617,7 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev)
 	oct = lio->oct_dev;
 
 	for (i = 0; i < lio->linfo.num_txpciq; i++) {
-		iq_no = lio->linfo.txpciq[i];
+		iq_no = lio->linfo.txpciq[i].s.q_no;
 		iq_stats = &oct->instr_queue[iq_no]->stats;
 		pkts += iq_stats->tx_done;
 		drop += iq_stats->tx_dropped;
@@ -2357,7 +2633,7 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev)
 	bytes = 0;
 
 	for (i = 0; i < lio->linfo.num_rxpciq; i++) {
-		oq_no = lio->linfo.rxpciq[i];
+		oq_no = lio->linfo.rxpciq[i].s.q_no;
 		oq_stats = &oct->droq[oq_no]->stats;
 		pkts += oq_stats->rx_pkts_received;
 		drop += (oq_stats->rx_dropped +
@@ -2383,19 +2659,16 @@ static int liquidio_change_mtu(struct net_device *netdev, int new_mtu)
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
-	int max_frm_size = new_mtu + OCTNET_FRM_HEADER_SIZE;
 	int ret = 0;
 
-	/* Limit the MTU to make sure the ethernet packets are between 64 bytes
-	 * and 65535 bytes
+	/* Limit the MTU to make sure the ethernet packets are between 68 bytes
+	 * and 16000 bytes
 	 */
-	if ((max_frm_size < OCTNET_MIN_FRM_SIZE) ||
-	    (max_frm_size > OCTNET_MAX_FRM_SIZE)) {
+	if ((new_mtu < LIO_MIN_MTU_SIZE) ||
+	    (new_mtu > LIO_MAX_MTU_SIZE)) {
 		dev_err(&oct->pci_dev->dev, "Invalid MTU: %d\n", new_mtu);
 		dev_err(&oct->pci_dev->dev, "Valid range %d and %d\n",
-			(OCTNET_MIN_FRM_SIZE - OCTNET_FRM_HEADER_SIZE),
-			(OCTNET_MAX_FRM_SIZE - OCTNET_FRM_HEADER_SIZE));
+			LIO_MIN_MTU_SIZE, LIO_MAX_MTU_SIZE);
 		return -EINVAL;
 	}
 
@@ -2403,15 +2676,13 @@ static int liquidio_change_mtu(struct net_device *netdev, int new_mtu)
 
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = OCTNET_CMD_CHANGE_MTU;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = new_mtu;
+	nctrl.ncmd.s.param1 = new_mtu;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.wait_time = 100;
 	nctrl.netpndev = (u64)netdev;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 
-	nparams.resp_order = OCTEON_RESP_ORDERED;
-
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "Failed to set MTU\n");
 		return -1;
@@ -2428,7 +2699,7 @@ static int liquidio_change_mtu(struct net_device *netdev, int new_mtu)
  * @param ifr interface request
  * @param cmd command
  */
-static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
 {
 	struct hwtstamp_config conf;
 	struct lio *lio = GET_LIO(netdev);
@@ -2489,7 +2760,7 @@ static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 {
 	switch (cmd) {
 	case SIOCSHWTSTAMP:
-		return hwtstamp_ioctl(netdev, ifr, cmd);
+		return hwtstamp_ioctl(netdev, ifr);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -2536,7 +2807,7 @@ static void handle_timestamp(struct octeon_device *oct,
 	}
 
 	octeon_free_soft_command(oct, sc);
-	recv_buffer_free(skb);
+	tx_buffer_free(skb);
 }
 
 /* \brief Send a data packet that will be timestamped
@@ -2551,10 +2822,9 @@ static inline int send_nic_timestamp_pkt(struct octeon_device *oct,
 {
 	int retval;
 	struct octeon_soft_command *sc;
-	struct octeon_instr_ih *ih;
-	struct octeon_instr_rdp *rdp;
 	struct lio *lio;
 	int ring_doorbell;
+	u32 len;
 
 	lio = finfo->lio;
 
@@ -2576,14 +2846,13 @@ static inline int send_nic_timestamp_pkt(struct octeon_device *oct,
 	sc->callback_arg = finfo->skb;
 	sc->iq_no = ndata->q_no;
 
-	ih = (struct octeon_instr_ih *)&sc->cmd.ih;
-	rdp = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+	len = (u32)((struct octeon_instr_ih2 *)(&sc->cmd.cmd2.ih2))->dlengsz;
 
 	ring_doorbell = !xmit_more;
 	retval = octeon_send_command(oct, sc->iq_no, ring_doorbell, &sc->cmd,
-				     sc, ih->dlengsz, ndata->reqtype);
+				     sc, len, ndata->reqtype);
 
-	if (retval) {
+	if (retval == IQ_SEND_FAILED) {
 		dev_err(&oct->pci_dev->dev, "timestamp data packet failed status: %x\n",
 			retval);
 		octeon_free_soft_command(oct, sc);
@@ -2594,68 +2863,6 @@ static inline int send_nic_timestamp_pkt(struct octeon_device *oct,
 	return retval;
 }
 
-static inline int is_ipv4(struct sk_buff *skb)
-{
-	return (skb->protocol == htons(ETH_P_IP)) &&
-	       (ip_hdr(skb)->version == 4);
-}
-
-static inline int is_vlan(struct sk_buff *skb)
-{
-	return skb->protocol == htons(ETH_P_8021Q);
-}
-
-static inline int is_ip_fragmented(struct sk_buff *skb)
-{
-	/* The Don't fragment and Reserved flag fields are ignored.
-	 * IP is fragmented if
-	 * -  the More fragments bit is set (indicating this IP is a fragment
-	 * with more to follow; the current offset could be 0 ).
-	 * -  ths offset field is non-zero.
-	 */
-	return (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) ? 1 : 0;
-}
-
-static inline int is_ipv6(struct sk_buff *skb)
-{
-	return (skb->protocol == htons(ETH_P_IPV6)) &&
-	       (ipv6_hdr(skb)->version == 6);
-}
-
-static inline int is_with_extn_hdr(struct sk_buff *skb)
-{
-	return (ipv6_hdr(skb)->nexthdr != IPPROTO_TCP) &&
-	       (ipv6_hdr(skb)->nexthdr != IPPROTO_UDP);
-}
-
-static inline int is_tcpudp(struct sk_buff *skb)
-{
-	return (ip_hdr(skb)->protocol == IPPROTO_TCP) ||
-	       (ip_hdr(skb)->protocol == IPPROTO_UDP);
-}
-
-static inline u32 get_ipv4_5tuple_tag(struct sk_buff *skb)
-{
-	u32 tag;
-	struct iphdr *iphdr = ip_hdr(skb);
-
-	tag = crc32(0, &iphdr->protocol, 1);
-	tag = crc32(tag, (u8 *)&iphdr->saddr, 8);
-	tag = crc32(tag, skb_transport_header(skb), 4);
-	return tag;
-}
-
-static inline u32 get_ipv6_5tuple_tag(struct sk_buff *skb)
-{
-	u32 tag;
-	struct ipv6hdr *ipv6hdr = ipv6_hdr(skb);
-
-	tag = crc32(0, &ipv6hdr->nexthdr, 1);
-	tag = crc32(tag, (u8 *)&ipv6hdr->saddr, 32);
-	tag = crc32(tag, skb_transport_header(skb), 4);
-	return tag;
-}
-
 /** \brief Transmit networks packets to the Octeon interface
  * @param skbuff   skbuff struct to be passed to network layer.
  * @param netdev    pointer to network device
@@ -2670,18 +2877,22 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 	struct octnic_data_pkt ndata;
 	struct octeon_device *oct;
 	struct oct_iq_stats *stats;
-	int cpu = 0, status = 0;
+	struct octeon_instr_irh *irh;
+	union tx_info *tx_info;
+	int status = 0;
 	int q_idx = 0, iq_no = 0;
-	int xmit_more;
+	int xmit_more, j;
+	u64 dptr = 0;
 	u32 tag = 0;
 
 	lio = GET_LIO(netdev);
 	oct = lio->oct_dev;
 
 	if (netif_is_multiqueue(netdev)) {
-		cpu = skb->queue_mapping;
-		q_idx = (cpu & (lio->linfo.num_txpciq - 1));
-		iq_no = lio->linfo.txpciq[q_idx];
+		q_idx = skb->queue_mapping;
+		q_idx = (q_idx % (lio->linfo.num_txpciq));
+		tag = q_idx;
+		iq_no = lio->linfo.txpciq[q_idx].s.q_no;
 	} else {
 		iq_no = lio->txq;
 	}
@@ -2692,11 +2903,11 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 	 * transmitted.
 	 */
 	if (!(atomic_read(&lio->ifstate) & LIO_IFSTATE_RUNNING) ||
-	    (!lio->linfo.link.s.status) ||
+	    (!lio->linfo.link.s.link_up) ||
 	    (skb->len <= 0)) {
 		netif_info(lio, tx_err, lio->netdev,
 			   "Transmit failed link_status : %d\n",
-			   lio->linfo.link.s.status);
+			   lio->linfo.link.s.link_up);
 		goto lio_xmit_failed;
 	}
 
@@ -2728,62 +2939,25 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 			/* defer sending if queue is full */
 			stats->tx_iq_busy++;
 			netif_info(lio, tx_err, lio->netdev, "Transmit failed iq:%d full\n",
-				   ndata.q_no);
+				   lio->txq);
 			return NETDEV_TX_BUSY;
 		}
 	}
 	/* pr_info(" XMIT - valid Qs: %d, 1st Q no: %d, cpu:  %d, q_no:%d\n",
-	 *	lio->linfo.num_txpciq, lio->txq, cpu, ndata.q_no );
+	 *	lio->linfo.num_txpciq, lio->txq, cpu, ndata.q_no);
 	 */
 
 	ndata.datasize = skb->len;
 
 	cmdsetup.u64 = 0;
-	cmdsetup.s.ifidx = lio->linfo.ifidx;
+	cmdsetup.s.iq_no = iq_no;
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		if (is_ipv4(skb) && !is_ip_fragmented(skb) && is_tcpudp(skb)) {
-			tag = get_ipv4_5tuple_tag(skb);
-
-			cmdsetup.s.cksum_offset = sizeof(struct ethhdr) + 1;
-
-			if (ip_hdr(skb)->ihl > 5)
-				cmdsetup.s.ipv4opts_ipv6exthdr =
-						OCT_PKT_PARAM_IPV4OPTS;
-
-		} else if (is_ipv6(skb)) {
-			tag = get_ipv6_5tuple_tag(skb);
-
-			cmdsetup.s.cksum_offset = sizeof(struct ethhdr) + 1;
-
-			if (is_with_extn_hdr(skb))
-				cmdsetup.s.ipv4opts_ipv6exthdr =
-						OCT_PKT_PARAM_IPV6EXTHDR;
-
-		} else if (is_vlan(skb)) {
-			if (vlan_eth_hdr(skb)->h_vlan_encapsulated_proto
-				== htons(ETH_P_IP) &&
-				!is_ip_fragmented(skb) && is_tcpudp(skb)) {
-				tag = get_ipv4_5tuple_tag(skb);
-
-				cmdsetup.s.cksum_offset =
-					sizeof(struct vlan_ethhdr) + 1;
-
-				if (ip_hdr(skb)->ihl > 5)
-					cmdsetup.s.ipv4opts_ipv6exthdr =
-						OCT_PKT_PARAM_IPV4OPTS;
-
-			} else if (vlan_eth_hdr(skb)->h_vlan_encapsulated_proto
-				== htons(ETH_P_IPV6)) {
-				tag = get_ipv6_5tuple_tag(skb);
-
-				cmdsetup.s.cksum_offset =
-					sizeof(struct vlan_ethhdr) + 1;
-
-				if (is_with_extn_hdr(skb))
-					cmdsetup.s.ipv4opts_ipv6exthdr =
-						OCT_PKT_PARAM_IPV6EXTHDR;
-			}
+		if (skb->encapsulation) {
+			cmdsetup.s.tnl_csum = 1;
+			stats->tx_vxlan++;
+		} else {
+			cmdsetup.s.transport_csum = 1;
 		}
 	}
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
@@ -2793,20 +2967,21 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	if (skb_shinfo(skb)->nr_frags == 0) {
 		cmdsetup.s.u.datasize = skb->len;
-		octnet_prepare_pci_cmd(&ndata.cmd, &cmdsetup, tag);
+		octnet_prepare_pci_cmd(oct, &ndata.cmd, &cmdsetup, tag);
+
 		/* Offload checksum calculation for TCP/UDP packets */
-		ndata.cmd.dptr = dma_map_single(&oct->pci_dev->dev,
-						skb->data,
-						skb->len,
-						DMA_TO_DEVICE);
-		if (dma_mapping_error(&oct->pci_dev->dev, ndata.cmd.dptr)) {
+		dptr = dma_map_single(&oct->pci_dev->dev,
+				      skb->data,
+				      skb->len,
+				      DMA_TO_DEVICE);
+		if (dma_mapping_error(&oct->pci_dev->dev, dptr)) {
 			dev_err(&oct->pci_dev->dev, "%s DMA mapping error 1\n",
 				__func__);
 			return NETDEV_TX_BUSY;
 		}
 
-		finfo->dptr = ndata.cmd.dptr;
-
+		ndata.cmd.cmd2.dptr = dptr;
+		finfo->dptr = dptr;
 		ndata.reqtype = REQTYPE_NORESP_NET;
 
 	} else {
@@ -2814,9 +2989,10 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 		struct skb_frag_struct *frag;
 		struct octnic_gather *g;
 
-		spin_lock(&lio->lock);
-		g = (struct octnic_gather *)list_delete_head(&lio->glist);
-		spin_unlock(&lio->lock);
+		spin_lock(&lio->glist_lock[q_idx]);
+		g = (struct octnic_gather *)
+			list_delete_head(&lio->glist[q_idx]);
+		spin_unlock(&lio->glist_lock[q_idx]);
 
 		if (!g) {
 			netif_info(lio, tx_err, lio->netdev,
@@ -2826,7 +3002,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 		cmdsetup.s.gather = 1;
 		cmdsetup.s.u.gatherptrs = (skb_shinfo(skb)->nr_frags + 1);
-		octnet_prepare_pci_cmd(&ndata.cmd, &cmdsetup, tag);
+		octnet_prepare_pci_cmd(oct, &ndata.cmd, &cmdsetup, tag);
 
 		memset(g->sg, 0, g->sg_size);
 
@@ -2853,36 +3029,52 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 					     frag->size,
 					     DMA_TO_DEVICE);
 
+			if (dma_mapping_error(&oct->pci_dev->dev,
+					      g->sg[i >> 2].ptr[i & 3])) {
+				dma_unmap_single(&oct->pci_dev->dev,
+						 g->sg[0].ptr[0],
+						 skb->len - skb->data_len,
+						 DMA_TO_DEVICE);
+				for (j = 1; j < i; j++) {
+					frag = &skb_shinfo(skb)->frags[j - 1];
+					dma_unmap_page(&oct->pci_dev->dev,
+						       g->sg[j >> 2].ptr[j & 3],
+						       frag->size,
+						       DMA_TO_DEVICE);
+				}
+				dev_err(&oct->pci_dev->dev, "%s DMA mapping error 3\n",
+					__func__);
+				return NETDEV_TX_BUSY;
+			}
+
 			add_sg_size(&g->sg[(i >> 2)], frag->size, (i & 3));
 			i++;
 		}
 
-		ndata.cmd.dptr = dma_map_single(&oct->pci_dev->dev,
-						g->sg, g->sg_size,
-						DMA_TO_DEVICE);
-		if (dma_mapping_error(&oct->pci_dev->dev, ndata.cmd.dptr)) {
-			dev_err(&oct->pci_dev->dev, "%s DMA mapping error 3\n",
-				__func__);
-			dma_unmap_single(&oct->pci_dev->dev, g->sg[0].ptr[0],
-					 skb->len - skb->data_len,
-					 DMA_TO_DEVICE);
-			return NETDEV_TX_BUSY;
-		}
+		dma_sync_single_for_device(&oct->pci_dev->dev, g->sg_dma_ptr,
+					   g->sg_size, DMA_TO_DEVICE);
+		dptr = g->sg_dma_ptr;
 
-		finfo->dptr = ndata.cmd.dptr;
+		ndata.cmd.cmd2.dptr = dptr;
+		finfo->dptr = dptr;
 		finfo->g = g;
 
 		ndata.reqtype = REQTYPE_NORESP_NET_SG;
 	}
 
-	if (skb_shinfo(skb)->gso_size) {
-		struct octeon_instr_irh *irh =
-			(struct octeon_instr_irh *)&ndata.cmd.irh;
-		union tx_info *tx_info = (union tx_info *)&ndata.cmd.ossp[0];
+	irh = (struct octeon_instr_irh *)&ndata.cmd.cmd2.irh;
+	tx_info = (union tx_info *)&ndata.cmd.cmd2.ossp[0];
 
-		irh->len = 1;   /* to indicate that ossp[0] contains tx_info */
+	if (skb_shinfo(skb)->gso_size) {
 		tx_info->s.gso_size = skb_shinfo(skb)->gso_size;
 		tx_info->s.gso_segs = skb_shinfo(skb)->gso_segs;
+		stats->tx_gso++;
+	}
+
+	/* HW insert VLAN tag */
+	if (skb_vlan_tag_present(skb)) {
+		irh->priority = skb_vlan_tag_get(skb) >> 13;
+		irh->vlan = skb_vlan_tag_get(skb) & 0xfff;
 	}
 
 	xmit_more = skb->xmit_more;
@@ -2901,7 +3093,10 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	netif_trans_update(netdev);
 
-	stats->tx_done++;
+	if (skb_shinfo(skb)->gso_size)
+		stats->tx_done += skb_shinfo(skb)->gso_segs;
+	else
+		stats->tx_done++;
 	stats->tx_tot_bytes += skb->len;
 
 	return NETDEV_TX_OK;
@@ -2910,9 +3105,10 @@ lio_xmit_failed:
 	stats->tx_dropped++;
 	netif_info(lio, tx_err, lio->netdev, "IQ%d Transmit dropped:%llu\n",
 		   iq_no, stats->tx_dropped);
-	dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr,
-			 ndata.datasize, DMA_TO_DEVICE);
-	recv_buffer_free(skb);
+	if (dptr)
+		dma_unmap_single(&oct->pci_dev->dev, dptr,
+				 ndata.datasize, DMA_TO_DEVICE);
+	tx_buffer_free(skb);
 	return NETDEV_TX_OK;
 }
 
@@ -2932,27 +3128,145 @@ static void liquidio_tx_timeout(struct net_device *netdev)
 	txqs_wake(netdev);
 }
 
-int liquidio_set_feature(struct net_device *netdev, int cmd)
+static int liquidio_vlan_rx_add_vid(struct net_device *netdev,
+				    __be16 proto __attribute__((unused)),
+				    u16 vid)
 {
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 	int ret = 0;
 
 	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
 
 	nctrl.ncmd.u64 = 0;
-	nctrl.ncmd.s.cmd = cmd;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = OCTNIC_LROIPV4 | OCTNIC_LROIPV6;
+	nctrl.ncmd.s.cmd = OCTNET_CMD_ADD_VLAN_FILTER;
+	nctrl.ncmd.s.param1 = vid;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+	nctrl.wait_time = 100;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
+			ret);
+	}
+
+	return ret;
+}
+
+static int liquidio_vlan_rx_kill_vid(struct net_device *netdev,
+				     __be16 proto __attribute__((unused)),
+				     u16 vid)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct octnic_ctrl_pkt nctrl;
+	int ret = 0;
+
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = OCTNET_CMD_DEL_VLAN_FILTER;
+	nctrl.ncmd.s.param1 = vid;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+	nctrl.wait_time = 100;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
+			ret);
+	}
+	return ret;
+}
+
+/** Sending command to enable/disable RX checksum offload
+ * @param netdev                pointer to network device
+ * @param command               OCTNET_CMD_TNL_RX_CSUM_CTL
+ * @param rx_cmd_bit            OCTNET_CMD_RXCSUM_ENABLE/
+ *                              OCTNET_CMD_RXCSUM_DISABLE
+ * @returns                     SUCCESS or FAILURE
+ */
+int liquidio_set_rxcsum_command(struct net_device *netdev, int command,
+				u8 rx_cmd)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct octnic_ctrl_pkt nctrl;
+	int ret = 0;
+
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = command;
+	nctrl.ncmd.s.param1 = rx_cmd;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.wait_time = 100;
 	nctrl.netpndev = (u64)netdev;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 
-	nparams.resp_order = OCTEON_RESP_NORESPONSE;
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev,
+			"DEVFLAGS RXCSUM change failed in core(ret:0x%x)\n",
+			ret);
+	}
+	return ret;
+}
+
+/** Sending command to add/delete VxLAN UDP port to firmware
+ * @param netdev                pointer to network device
+ * @param command               OCTNET_CMD_VXLAN_PORT_CONFIG
+ * @param vxlan_port            VxLAN port to be added or deleted
+ * @param vxlan_cmd_bit         OCTNET_CMD_VXLAN_PORT_ADD,
+ *                              OCTNET_CMD_VXLAN_PORT_DEL
+ * @returns                     SUCCESS or FAILURE
+ */
+static int liquidio_vxlan_port_command(struct net_device *netdev, int command,
+				       u16 vxlan_port, u8 vxlan_cmd_bit)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct octnic_ctrl_pkt nctrl;
+	int ret = 0;
+
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = command;
+	nctrl.ncmd.s.more = vxlan_cmd_bit;
+	nctrl.ncmd.s.param1 = vxlan_port;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+	nctrl.wait_time = 100;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev,
+			"VxLAN port add/delete failed in core (ret:0x%x)\n",
+			ret);
+	}
+	return ret;
+}
+
+int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct octnic_ctrl_pkt nctrl;
+	int ret = 0;
+
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = cmd;
+	nctrl.ncmd.s.param1 = param1;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+	nctrl.wait_time = 100;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "Feature change failed in core (ret: 0x%x)\n",
 			ret);
@@ -3008,14 +3322,55 @@ static int liquidio_set_features(struct net_device *netdev,
 		return 0;
 
 	if ((features & NETIF_F_LRO) && (lio->dev_capability & NETIF_F_LRO))
-		liquidio_set_feature(netdev, OCTNET_CMD_LRO_ENABLE);
+		liquidio_set_feature(netdev, OCTNET_CMD_LRO_ENABLE,
+				     OCTNIC_LROIPV4 | OCTNIC_LROIPV6);
 	else if (!(features & NETIF_F_LRO) &&
 		 (lio->dev_capability & NETIF_F_LRO))
-		liquidio_set_feature(netdev, OCTNET_CMD_LRO_DISABLE);
+		liquidio_set_feature(netdev, OCTNET_CMD_LRO_DISABLE,
+				     OCTNIC_LROIPV4 | OCTNIC_LROIPV6);
+
+	/* Sending command to firmware to enable/disable RX checksum
+	 * offload settings using ethtool
+	 */
+	if (!(netdev->features & NETIF_F_RXCSUM) &&
+	    (lio->enc_dev_capability & NETIF_F_RXCSUM) &&
+	    (features & NETIF_F_RXCSUM))
+		liquidio_set_rxcsum_command(netdev,
+					    OCTNET_CMD_TNL_RX_CSUM_CTL,
+					    OCTNET_CMD_RXCSUM_ENABLE);
+	else if ((netdev->features & NETIF_F_RXCSUM) &&
+		 (lio->enc_dev_capability & NETIF_F_RXCSUM) &&
+		 !(features & NETIF_F_RXCSUM))
+		liquidio_set_rxcsum_command(netdev, OCTNET_CMD_TNL_RX_CSUM_CTL,
+					    OCTNET_CMD_RXCSUM_DISABLE);
 
 	return 0;
 }
 
+static void liquidio_add_vxlan_port(struct net_device *netdev,
+				    struct udp_tunnel_info *ti)
+{
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
+	liquidio_vxlan_port_command(netdev,
+				    OCTNET_CMD_VXLAN_PORT_CONFIG,
+				    htons(ti->port),
+				    OCTNET_CMD_VXLAN_PORT_ADD);
+}
+
+static void liquidio_del_vxlan_port(struct net_device *netdev,
+				    struct udp_tunnel_info *ti)
+{
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
+	liquidio_vxlan_port_command(netdev,
+				    OCTNET_CMD_VXLAN_PORT_CONFIG,
+				    htons(ti->port),
+				    OCTNET_CMD_VXLAN_PORT_DEL);
+}
+
 static struct net_device_ops lionetdevops = {
 	.ndo_open		= liquidio_open,
 	.ndo_stop		= liquidio_stop,
@@ -3024,10 +3379,15 @@ static struct net_device_ops lionetdevops = {
 	.ndo_set_mac_address	= liquidio_set_mac,
 	.ndo_set_rx_mode	= liquidio_set_mcast_list,
 	.ndo_tx_timeout		= liquidio_tx_timeout,
+
+	.ndo_vlan_rx_add_vid    = liquidio_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid   = liquidio_vlan_rx_kill_vid,
 	.ndo_change_mtu		= liquidio_change_mtu,
 	.ndo_do_ioctl		= liquidio_ioctl,
 	.ndo_fix_features	= liquidio_fix_features,
 	.ndo_set_features	= liquidio_set_features,
+	.ndo_udp_tunnel_add	= liquidio_add_vxlan_port,
+	.ndo_udp_tunnel_del	= liquidio_del_vxlan_port,
 };
 
 /** \brief Entry point for the liquidio module
@@ -3082,24 +3442,27 @@ static int lio_nic_info(struct octeon_recv_info *recv_info, void *buf)
 {
 	struct octeon_device *oct = (struct octeon_device *)buf;
 	struct octeon_recv_pkt *recv_pkt = recv_info->recv_pkt;
-	int ifidx = 0;
+	int gmxport = 0;
 	union oct_link_status *ls;
 	int i;
 
-	if ((recv_pkt->buffer_size[0] != sizeof(*ls)) ||
-	    (recv_pkt->rh.r_nic_info.ifidx > oct->ifcount)) {
+	if (recv_pkt->buffer_size[0] != sizeof(*ls)) {
 		dev_err(&oct->pci_dev->dev, "Malformed NIC_INFO, len=%d, ifidx=%d\n",
 			recv_pkt->buffer_size[0],
-			recv_pkt->rh.r_nic_info.ifidx);
+			recv_pkt->rh.r_nic_info.gmxport);
 		goto nic_info_err;
 	}
 
-	ifidx = recv_pkt->rh.r_nic_info.ifidx;
+	gmxport = recv_pkt->rh.r_nic_info.gmxport;
 	ls = (union oct_link_status *)get_rbd(recv_pkt->buffer_ptr[0]);
 
 	octeon_swap_8B_data((u64 *)ls, (sizeof(union oct_link_status)) >> 3);
-
-	update_link_status(oct->props[ifidx].netdev, ls);
+	for (i = 0; i < oct->ifcount; i++) {
+		if (oct->props[i].gmxport == gmxport) {
+			update_link_status(oct->props[i].netdev, ls);
+			break;
+		}
+	}
 
 nic_info_err:
 	for (i = 0; i < recv_pkt->buffer_count; i++)
@@ -3125,13 +3488,12 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 	struct liquidio_if_cfg_context *ctx;
 	struct liquidio_if_cfg_resp *resp;
 	struct octdev_props *props;
-	int retval, num_iqueues, num_oqueues, q_no;
-	u64 q_mask;
-	int num_cpus = num_online_cpus();
+	int retval, num_iqueues, num_oqueues;
 	union oct_nic_if_cfg if_cfg;
 	unsigned int base_queue;
 	unsigned int gmx_port_id;
 	u32 resp_size, ctx_size;
+	u32 ifidx_or_pfnum;
 
 	/* This is to handle link status changes */
 	octeon_register_dispatch_fn(octeon_dev, OPCODE_NIC,
@@ -3167,14 +3529,12 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 			CFG_GET_BASE_QUE_NIC_IF(octeon_get_conf(octeon_dev), i);
 		gmx_port_id =
 			CFG_GET_GMXID_NIC_IF(octeon_get_conf(octeon_dev), i);
-		if (num_iqueues > num_cpus)
-			num_iqueues = num_cpus;
-		if (num_oqueues > num_cpus)
-			num_oqueues = num_cpus;
+		ifidx_or_pfnum = i;
+
 		dev_dbg(&octeon_dev->pci_dev->dev,
 			"requesting config for interface %d, iqs %d, oqs %d\n",
-			i, num_iqueues, num_oqueues);
-		ACCESS_ONCE(ctx->cond) = 0;
+			ifidx_or_pfnum, num_iqueues, num_oqueues);
+		WRITE_ONCE(ctx->cond, 0);
 		ctx->octeon_id = lio_get_device_id(octeon_dev);
 		init_waitqueue_head(&ctx->wc);
 
@@ -3183,16 +3543,19 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		if_cfg.s.num_oqueues = num_oqueues;
 		if_cfg.s.base_queue = base_queue;
 		if_cfg.s.gmx_port_id = gmx_port_id;
+
+		sc->iq_no = 0;
+
 		octeon_prepare_soft_command(octeon_dev, sc, OPCODE_NIC,
-					    OPCODE_NIC_IF_CFG, i,
+					    OPCODE_NIC_IF_CFG, 0,
 					    if_cfg.u64, 0);
 
 		sc->callback = if_cfg_callback;
 		sc->callback_arg = sc;
-		sc->wait_time = 1000;
+		sc->wait_time = 3000;
 
 		retval = octeon_send_soft_command(octeon_dev, sc);
-		if (retval) {
+		if (retval == IQ_SEND_FAILED) {
 			dev_err(&octeon_dev->pci_dev->dev,
 				"iq/oq config failed status: %x\n",
 				retval);
@@ -3234,8 +3597,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 			goto setup_nic_dev_fail;
 		}
 
-		props = &octeon_dev->props[i];
-		props->netdev = netdev;
+		SET_NETDEV_DEV(netdev, &octeon_dev->pci_dev->dev);
 
 		if (num_iqueues > 1)
 			lionetdevops.ndo_select_queue = select_q;
@@ -3249,23 +3611,21 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 
 		memset(lio, 0, sizeof(struct lio));
 
-		lio->linfo.ifidx = resp->cfg_info.ifidx;
-		lio->ifidx = resp->cfg_info.ifidx;
+		lio->ifidx = ifidx_or_pfnum;
+
+		props = &octeon_dev->props[i];
+		props->gmxport = resp->cfg_info.linfo.gmxport;
+		props->netdev = netdev;
 
 		lio->linfo.num_rxpciq = num_oqueues;
 		lio->linfo.num_txpciq = num_iqueues;
-		q_mask = resp->cfg_info.oqmask;
-		/* q_mask is 0-based and already verified mask is nonzero */
 		for (j = 0; j < num_oqueues; j++) {
-			q_no = __ffs64(q_mask);
-			q_mask &= (~(1UL << q_no));
-			lio->linfo.rxpciq[j] = q_no;
+			lio->linfo.rxpciq[j].u64 =
+				resp->cfg_info.linfo.rxpciq[j].u64;
 		}
-		q_mask = resp->cfg_info.iqmask;
 		for (j = 0; j < num_iqueues; j++) {
-			q_no = __ffs64(q_mask);
-			q_mask &= (~(1UL << q_no));
-			lio->linfo.txpciq[j] = q_no;
+			lio->linfo.txpciq[j].u64 =
+				resp->cfg_info.linfo.txpciq[j].u64;
 		}
 		lio->linfo.hw_addr = resp->cfg_info.linfo.hw_addr;
 		lio->linfo.gmxport = resp->cfg_info.linfo.gmxport;
@@ -3274,16 +3634,41 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		lio->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
 		lio->dev_capability = NETIF_F_HIGHDMA
-				      | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
-				      | NETIF_F_SG | NETIF_F_RXCSUM
-				      | NETIF_F_TSO | NETIF_F_TSO6
-				      | NETIF_F_LRO;
+				| NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
+				| NETIF_F_SG | NETIF_F_RXCSUM
+				| NETIF_F_GRO
+				| NETIF_F_TSO | NETIF_F_TSO6
+				| NETIF_F_LRO;
 		netif_set_gso_max_size(netdev, OCTNIC_GSO_MAX_SIZE);
 
-		netdev->features = lio->dev_capability;
+		/*  Copy of transmit encapsulation capabilities:
+		 *  TSO, TSO6, Checksums for this device
+		 */
+		lio->enc_dev_capability = NETIF_F_IP_CSUM
+					  | NETIF_F_IPV6_CSUM
+					  | NETIF_F_GSO_UDP_TUNNEL
+					  | NETIF_F_HW_CSUM | NETIF_F_SG
+					  | NETIF_F_RXCSUM
+					  | NETIF_F_TSO | NETIF_F_TSO6
+					  | NETIF_F_LRO;
+
+		netdev->hw_enc_features = (lio->enc_dev_capability &
+					   ~NETIF_F_LRO);
+
+		lio->dev_capability |= NETIF_F_GSO_UDP_TUNNEL;
+
 		netdev->vlan_features = lio->dev_capability;
+		/* Add any unchangeable hw features */
+		lio->dev_capability |=  NETIF_F_HW_VLAN_CTAG_FILTER |
+					NETIF_F_HW_VLAN_CTAG_RX |
+					NETIF_F_HW_VLAN_CTAG_TX;
+
+		netdev->features = (lio->dev_capability & ~NETIF_F_LRO);
 
 		netdev->hw_features = lio->dev_capability;
+		/*HW_VLAN_RX and HW_VLAN_FILTER is always on*/
+		netdev->hw_features = netdev->hw_features &
+			~NETIF_F_HW_VLAN_CTAG_RX;
 
 		/* Point to the  properties for octeon device to which this
 		 * interface belongs.
@@ -3291,7 +3676,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		lio->oct_dev = octeon_dev;
 		lio->octprops = props;
 		lio->netdev = netdev;
-		spin_lock_init(&lio->lock);
 
 		dev_dbg(&octeon_dev->pci_dev->dev,
 			"if%d gmx: %d hw_addr: 0x%llx\n", i,
@@ -3306,23 +3690,22 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 
 		ether_addr_copy(netdev->dev_addr, mac);
 
-		if (setup_io_queues(octeon_dev, netdev)) {
+		/* By default all interfaces on a single Octeon uses the same
+		 * tx and rx queues
+		 */
+		lio->txq = lio->linfo.txpciq[0].s.q_no;
+		lio->rxq = lio->linfo.rxpciq[0].s.q_no;
+		if (setup_io_queues(octeon_dev, i)) {
 			dev_err(&octeon_dev->pci_dev->dev, "I/O queues creation failed\n");
 			goto setup_nic_dev_fail;
 		}
 
 		ifstate_set(lio, LIO_IFSTATE_DROQ_OPS);
 
-		/* By default all interfaces on a single Octeon uses the same
-		 * tx and rx queues
-		 */
-		lio->txq = lio->linfo.txpciq[0];
-		lio->rxq = lio->linfo.rxpciq[0];
-
 		lio->tx_qsize = octeon_get_tx_qsize(octeon_dev, lio->txq);
 		lio->rx_qsize = octeon_get_rx_qsize(octeon_dev, lio->rxq);
 
-		if (setup_glist(lio)) {
+		if (setup_glists(octeon_dev, lio, num_iqueues)) {
 			dev_err(&octeon_dev->pci_dev->dev,
 				"Gather list allocation failed\n");
 			goto setup_nic_dev_fail;
@@ -3330,11 +3713,17 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 
 		/* Register ethtool support */
 		liquidio_set_ethtool_ops(netdev);
+		octeon_dev->priv_flags = 0x0;
 
-		liquidio_set_feature(netdev, OCTNET_CMD_LRO_ENABLE);
+		if (netdev->features & NETIF_F_LRO)
+			liquidio_set_feature(netdev, OCTNET_CMD_LRO_ENABLE,
+					     OCTNIC_LROIPV4 | OCTNIC_LROIPV6);
+
+		liquidio_set_feature(netdev, OCTNET_CMD_ENABLE_VLAN_FILTER, 0);
 
 		if ((debug != -1) && (debug & NETIF_MSG_HW))
-			liquidio_set_feature(netdev, OCTNET_CMD_VERBOSE_ENABLE);
+			liquidio_set_feature(netdev,
+					     OCTNET_CMD_VERBOSE_ENABLE, 0);
 
 		/* Register the network device with the OS */
 		if (register_netdev(netdev)) {
@@ -3346,16 +3735,19 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 			"Setup NIC ifidx:%d mac:%02x%02x%02x%02x%02x%02x\n",
 			i, mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
 		netif_carrier_off(netdev);
-
-		if (lio->linfo.link.s.status) {
-			netif_carrier_on(netdev);
-			start_txq(netdev);
-		} else {
-			netif_carrier_off(netdev);
-		}
+		lio->link_changes++;
 
 		ifstate_set(lio, LIO_IFSTATE_REGISTERED);
 
+		/* Sending command to firmware to enable Rx checksum offload
+		 * by default at the time of setup of Liquidio driver for
+		 * this device
+		 */
+		liquidio_set_rxcsum_command(netdev, OCTNET_CMD_TNL_RX_CSUM_CTL,
+					    OCTNET_CMD_RXCSUM_ENABLE);
+		liquidio_set_feature(netdev, OCTNET_CMD_TNL_TX_CSUM_CTL,
+				     OCTNET_CMD_TXCSUM_ENABLE);
+
 		dev_dbg(&octeon_dev->pci_dev->dev,
 			"NIC ifidx:%d Setup successful\n", i);
 
@@ -3386,7 +3778,7 @@ setup_nic_dev_fail:
 static int liquidio_init_nic_module(struct octeon_device *oct)
 {
 	struct oct_intrmod_cfg *intrmod_cfg;
-	int retval = 0;
+	int i, retval = 0;
 	int num_nic_ports = CFG_GET_NUM_NIC_PORTS(octeon_get_conf(oct));
 
 	dev_dbg(&oct->pci_dev->dev, "Initializing network interfaces\n");
@@ -3400,6 +3792,9 @@ static int liquidio_init_nic_module(struct octeon_device *oct)
 	memset(oct->props, 0,
 	       sizeof(struct octdev_props) * num_nic_ports);
 
+	for (i = 0; i < MAX_OCTEON_LINKS; i++)
+		oct->props[i].gmxport = -1;
+
 	retval = setup_nic_devices(oct);
 	if (retval) {
 		dev_err(&oct->pci_dev->dev, "Setup NIC devices failed\n");
@@ -3410,15 +3805,19 @@ static int liquidio_init_nic_module(struct octeon_device *oct)
 
 	/* Initialize interrupt moderation params */
 	intrmod_cfg = &((struct octeon_device *)oct)->intrmod;
-	intrmod_cfg->intrmod_enable = 1;
-	intrmod_cfg->intrmod_check_intrvl = LIO_INTRMOD_CHECK_INTERVAL;
-	intrmod_cfg->intrmod_maxpkt_ratethr = LIO_INTRMOD_MAXPKT_RATETHR;
-	intrmod_cfg->intrmod_minpkt_ratethr = LIO_INTRMOD_MINPKT_RATETHR;
-	intrmod_cfg->intrmod_maxcnt_trigger = LIO_INTRMOD_MAXCNT_TRIGGER;
-	intrmod_cfg->intrmod_maxtmr_trigger = LIO_INTRMOD_MAXTMR_TRIGGER;
-	intrmod_cfg->intrmod_mintmr_trigger = LIO_INTRMOD_MINTMR_TRIGGER;
-	intrmod_cfg->intrmod_mincnt_trigger = LIO_INTRMOD_MINCNT_TRIGGER;
-
+	intrmod_cfg->rx_enable = 1;
+	intrmod_cfg->check_intrvl =   LIO_INTRMOD_CHECK_INTERVAL;
+	intrmod_cfg->maxpkt_ratethr = LIO_INTRMOD_MAXPKT_RATETHR;
+	intrmod_cfg->minpkt_ratethr = LIO_INTRMOD_MINPKT_RATETHR;
+	intrmod_cfg->rx_maxcnt_trigger = LIO_INTRMOD_RXMAXCNT_TRIGGER;
+	intrmod_cfg->rx_maxtmr_trigger = LIO_INTRMOD_RXMAXTMR_TRIGGER;
+	intrmod_cfg->rx_mintmr_trigger = LIO_INTRMOD_RXMINTMR_TRIGGER;
+	intrmod_cfg->rx_mincnt_trigger = LIO_INTRMOD_RXMINCNT_TRIGGER;
+	intrmod_cfg->tx_enable = 1;
+	intrmod_cfg->tx_maxcnt_trigger = LIO_INTRMOD_TXMAXCNT_TRIGGER;
+	intrmod_cfg->tx_mincnt_trigger = LIO_INTRMOD_TXMINCNT_TRIGGER;
+	intrmod_cfg->rx_frames = CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
+	intrmod_cfg->rx_usecs = CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
 	dev_dbg(&oct->pci_dev->dev, "Network interfaces ready\n");
 
 	return retval;
@@ -3481,6 +3880,7 @@ static void nic_starter(struct work_struct *work)
 static int octeon_device_init(struct octeon_device *octeon_dev)
 {
 	int j, ret;
+	char bootcmd[] = "\n";
 	struct octeon_device_priv *oct_priv =
 		(struct octeon_device_priv *)octeon_dev->priv;
 	atomic_set(&octeon_dev->status, OCT_DEV_BEGIN_STATE);
@@ -3558,6 +3958,7 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 		/* Release any previously allocated queues */
 		for (j = 0; j < octeon_dev->num_oqs; j++)
 			octeon_delete_droq(octeon_dev, j);
+		return 1;
 	}
 
 	atomic_set(&octeon_dev->status, OCT_DEV_DROQ_INIT_DONE);
@@ -3580,7 +3981,8 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 
 	/* Setup the interrupt handler and record the INT SUM register address
 	 */
-	octeon_setup_interrupt(octeon_dev);
+	if (octeon_setup_interrupt(octeon_dev))
+		return 1;
 
 	/* Enable Octeon device interrupts */
 	octeon_dev->fn_list.enable_interrupt(octeon_dev->chip);
@@ -3592,14 +3994,19 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 
 	dev_dbg(&octeon_dev->pci_dev->dev, "Waiting for DDR initialization...\n");
 
-	if (ddr_timeout == 0) {
-		dev_info(&octeon_dev->pci_dev->dev,
-			 "WAITING. Set ddr_timeout to non-zero value to proceed with initialization.\n");
-	}
+	if (ddr_timeout == 0)
+		dev_info(&octeon_dev->pci_dev->dev, "WAITING. Set ddr_timeout to non-zero value to proceed with initialization.\n");
 
 	schedule_timeout_uninterruptible(HZ * LIO_RESET_SECS);
 
 	/* Wait for the octeon to initialize DDR after the soft-reset. */
+	while (ddr_timeout == 0) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (schedule_timeout(HZ / 10)) {
+			/* user probably pressed Control-C */
+			return 1;
+		}
+	}
 	ret = octeon_wait_for_ddr_init(octeon_dev, &ddr_timeout);
 	if (ret) {
 		dev_err(&octeon_dev->pci_dev->dev,
@@ -3613,6 +4020,9 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 		return 1;
 	}
 
+	/* Divert uboot to take commands from host instead. */
+	ret = octeon_console_send_cmd(octeon_dev, bootcmd, 50);
+
 	dev_dbg(&octeon_dev->pci_dev->dev, "Initializing consoles\n");
 	ret = octeon_init_consoles(octeon_dev);
 	if (ret) {
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
index 0ac347ccc8ba..199a8b9c7dc5 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
@@ -30,10 +30,10 @@
 
 #include "octeon_config.h"
 
-#define LIQUIDIO_VERSION        "1.1.9"
-#define LIQUIDIO_MAJOR_VERSION  1
-#define LIQUIDIO_MINOR_VERSION  1
-#define LIQUIDIO_MICRO_VERSION  9
+#define LIQUIDIO_BASE_VERSION   "1.4"
+#define LIQUIDIO_MICRO_VERSION  ".1"
+#define LIQUIDIO_PACKAGE ""
+#define LIQUIDIO_VERSION  "1.4.1"
 
 #define CONTROL_IQ 0
 /** Tag types used by Octeon cores in its work. */
@@ -174,9 +174,11 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry,
 /*------------------------- End Scatter/Gather ---------------------------*/
 
 #define   OCTNET_FRM_PTP_HEADER_SIZE  8
-#define   OCTNET_FRM_HEADER_SIZE     30 /* PTP timestamp + VLAN + Ethernet */
 
-#define   OCTNET_MIN_FRM_SIZE        (64  + OCTNET_FRM_PTP_HEADER_SIZE)
+#define   OCTNET_FRM_HEADER_SIZE     22 /* VLAN + Ethernet */
+
+#define   OCTNET_MIN_FRM_SIZE        64
+
 #define   OCTNET_MAX_FRM_SIZE        (16000 + OCTNET_FRM_HEADER_SIZE)
 
 #define   OCTNET_DEFAULT_FRM_SIZE    (1500 + OCTNET_FRM_HEADER_SIZE)
@@ -212,6 +214,17 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry,
 #define   OCTNET_CMD_VERBOSE_ENABLE   0x14
 #define   OCTNET_CMD_VERBOSE_DISABLE  0x15
 
+#define   OCTNET_CMD_ENABLE_VLAN_FILTER 0x16
+#define   OCTNET_CMD_ADD_VLAN_FILTER  0x17
+#define   OCTNET_CMD_DEL_VLAN_FILTER  0x18
+#define   OCTNET_CMD_VXLAN_PORT_CONFIG 0x19
+#define   OCTNET_CMD_VXLAN_PORT_ADD    0x0
+#define   OCTNET_CMD_VXLAN_PORT_DEL    0x1
+#define   OCTNET_CMD_RXCSUM_ENABLE     0x0
+#define   OCTNET_CMD_RXCSUM_DISABLE    0x1
+#define   OCTNET_CMD_TXCSUM_ENABLE     0x0
+#define   OCTNET_CMD_TXCSUM_DISABLE    0x1
+
 /* RX(packets coming from wire) Checksum verification flags */
 /* TCP/UDP csum */
 #define   CNNIC_L4SUM_VERIFIED             0x1
@@ -258,19 +271,19 @@ union octnet_cmd {
 
 		u64 more:6; /* How many udd words follow the command */
 
-		u64 param1:29;
+		u64 reserved:29;
 
-		u64 param2:16;
+		u64 param1:16;
 
-		u64 param3:8;
+		u64 param2:8;
 
 #else
 
-		u64 param3:8;
+		u64 param2:8;
 
-		u64 param2:16;
+		u64 param1:16;
 
-		u64 param1:29;
+		u64 reserved:29;
 
 		u64 more:6;
 
@@ -283,8 +296,140 @@ union octnet_cmd {
 
 #define   OCTNET_CMD_SIZE     (sizeof(union octnet_cmd))
 
+/* Instruction Header(DPI) - for OCTEON-III models */
+struct  octeon_instr_ih3 {
+#ifdef __BIG_ENDIAN_BITFIELD
+
+	/** Reserved3 */
+	u64     reserved3:1;
+
+	/** Gather indicator 1=gather*/
+	u64     gather:1;
+
+	/** Data length OR no. of entries in gather list */
+	u64     dlengsz:14;
+
+	/** Front Data size */
+	u64     fsz:6;
+
+	/** Reserved2 */
+	u64     reserved2:4;
+
+	/** PKI port kind - PKIND */
+	u64     pkind:6;
+
+	/** Reserved1 */
+	u64     reserved1:32;
+
+#else
+	/** Reserved1 */
+	u64     reserved1:32;
+
+	/** PKI port kind - PKIND */
+	u64     pkind:6;
+
+	/** Reserved2 */
+	u64     reserved2:4;
+
+	/** Front Data size */
+	u64     fsz:6;
+
+	/** Data length OR no. of entries in gather list */
+	u64     dlengsz:14;
+
+	/** Gather indicator 1=gather*/
+	u64     gather:1;
+
+	/** Reserved3 */
+	u64     reserved3:1;
+
+#endif
+};
+
+/* Optional PKI Instruction Header(PKI IH) - for OCTEON-III models */
+/** BIG ENDIAN format.   */
+struct  octeon_instr_pki_ih3 {
+#ifdef __BIG_ENDIAN_BITFIELD
+
+	/** Wider bit */
+	u64     w:1;
+
+	/** Raw mode indicator 1 = RAW */
+	u64     raw:1;
+
+	/** Use Tag */
+	u64     utag:1;
+
+	/** Use QPG */
+	u64     uqpg:1;
+
+	/** Reserved2 */
+	u64     reserved2:1;
+
+	/** Parse Mode */
+	u64     pm:3;
+
+	/** Skip Length */
+	u64     sl:8;
+
+	/** Use Tag Type */
+	u64     utt:1;
+
+	/** Tag type */
+	u64     tagtype:2;
+
+	/** Reserved1 */
+	u64     reserved1:2;
+
+	/** QPG Value */
+	u64     qpg:11;
+
+	/** Tag Value */
+	u64     tag:32;
+
+#else
+
+	/** Tag Value */
+	u64     tag:32;
+
+	/** QPG Value */
+	u64     qpg:11;
+
+	/** Reserved1 */
+	u64     reserved1:2;
+
+	/** Tag type */
+	u64     tagtype:2;
+
+	/** Use Tag Type */
+	u64     utt:1;
+
+	/** Skip Length */
+	u64     sl:8;
+
+	/** Parse Mode */
+	u64     pm:3;
+
+	/** Reserved2 */
+	u64     reserved2:1;
+
+	/** Use QPG */
+	u64     uqpg:1;
+
+	/** Use Tag */
+	u64     utag:1;
+
+	/** Raw mode indicator 1 = RAW */
+	u64     raw:1;
+
+	/** Wider bit */
+	u64     w:1;
+#endif
+
+};
+
 /** Instruction Header */
-struct octeon_instr_ih {
+struct octeon_instr_ih2 {
 #ifdef __BIG_ENDIAN_BITFIELD
 	/** Raw mode indicator 1 = RAW */
 	u64 raw:1;
@@ -348,15 +493,15 @@ struct octeon_instr_irh {
 	u64 opcode:4;
 	u64 rflag:1;
 	u64 subcode:7;
-	u64 len:3;
-	u64 rid:13;
-	u64 reserved:4;
+	u64 vlan:12;
+	u64 priority:3;
+	u64 reserved:5;
 	u64 ossp:32;             /* opcode/subcode specific parameters */
 #else
 	u64 ossp:32;             /* opcode/subcode specific parameters */
-	u64 reserved:4;
-	u64 rid:13;
-	u64 len:3;
+	u64 reserved:5;
+	u64 priority:3;
+	u64 vlan:12;
 	u64 subcode:7;
 	u64 rflag:1;
 	u64 opcode:4;
@@ -383,75 +528,77 @@ union octeon_rh {
 	struct {
 		u64 opcode:4;
 		u64 subcode:8;
-		u64 len:3;       /** additional 64-bit words */
-		u64 rid:13;      /** request id in response to pkt sent by host */
-		u64 reserved:4;
-		u64 ossp:32;     /** opcode/subcode specific parameters */
+		u64 len:3;     /** additional 64-bit words */
+		u64 reserved:17;
+		u64 ossp:32;   /** opcode/subcode specific parameters */
 	} r;
 	struct {
 		u64 opcode:4;
 		u64 subcode:8;
-		u64 len:3;       /** additional 64-bit words */
-		u64 rid:13;      /** request id in response to pkt sent by host */
-		u64 extra:24;
-		u64 link:8;
+		u64 len:3;     /** additional 64-bit words */
+		u64 extra:28;
+		u64 vlan:12;
+		u64 priority:3;
 		u64 csum_verified:3;     /** checksum verified. */
 		u64 has_hwtstamp:1;      /** Has hardware timestamp. 1 = yes. */
+		u64 encap_on:1;
+		u64 has_hash:1;          /** Has hash (rth or rss). 1 = yes. */
 	} r_dh;
 	struct {
 		u64 opcode:4;
 		u64 subcode:8;
-		u64 len:3;       /** additional 64-bit words */
-		u64 rid:13;      /** request id in response to pkt sent by host */
+		u64 len:3;     /** additional 64-bit words */
+		u64 reserved:11;
 		u64 num_gmx_ports:8;
-		u64 max_nic_ports:8;
+		u64 max_nic_ports:10;
 		u64 app_cap_flags:4;
-		u64 app_mode:16;
+		u64 app_mode:8;
+		u64 pkind:8;
 	} r_core_drv_init;
 	struct {
 		u64 opcode:4;
 		u64 subcode:8;
 		u64 len:3;       /** additional 64-bit words */
-		u64 rid:13;
-		u64 reserved:4;
+		u64 reserved:8;
 		u64 extra:25;
-		u64 ifidx:7;
+		u64 gmxport:16;
 	} r_nic_info;
 #else
 	u64 u64;
 	struct {
 		u64 ossp:32;  /** opcode/subcode specific parameters */
-		u64 reserved:4;
-		u64 rid:13;   /** req id in response to pkt sent by host */
+		u64 reserved:17;
 		u64 len:3;    /** additional 64-bit words */
 		u64 subcode:8;
 		u64 opcode:4;
 	} r;
 	struct {
+		u64 has_hash:1;          /** Has hash (rth or rss). 1 = yes. */
+		u64 encap_on:1;
 		u64 has_hwtstamp:1;      /** 1 = has hwtstamp */
 		u64 csum_verified:3;     /** checksum verified. */
-		u64 link:8;
-		u64 extra:24;
-		u64 rid:13;   /** req id in response to pkt sent by host */
+		u64 priority:3;
+		u64 vlan:12;
+		u64 extra:28;
 		u64 len:3;    /** additional 64-bit words */
 		u64 subcode:8;
 		u64 opcode:4;
 	} r_dh;
 	struct {
-		u64 app_mode:16;
+		u64 pkind:8;
+		u64 app_mode:8;
 		u64 app_cap_flags:4;
-		u64 max_nic_ports:8;
+		u64 max_nic_ports:10;
 		u64 num_gmx_ports:8;
-		u64 rid:13;
+		u64 reserved:11;
 		u64 len:3;       /** additional 64-bit words */
 		u64 subcode:8;
 		u64 opcode:4;
 	} r_core_drv_init;
 	struct {
-		u64 ifidx:7;
+		u64 gmxport:16;
 		u64 extra:25;
-		u64 reserved:4;
-		u64 rid:13;
+		u64 reserved:8;
 		u64 len:3;       /** additional 64-bit words */
 		u64 subcode:8;
 		u64 opcode:4;
@@ -461,30 +608,25 @@ union octeon_rh {
 
 #define  OCT_RH_SIZE   (sizeof(union  octeon_rh))
 
-#define OCT_PKT_PARAM_IPV4OPTS   1
-#define OCT_PKT_PARAM_IPV6EXTHDR 2
-
 union octnic_packet_params {
 	u32 u32;
 	struct {
 #ifdef __BIG_ENDIAN_BITFIELD
-		u32 reserved:6;
+		u32 reserved:24;
+		u32 ip_csum:1;		/* Perform IP header checksum(s) */
+		/* Perform Outer transport header checksum */
+		u32 transport_csum:1;
+		/* Find tunnel, and perform transport csum. */
 		u32 tnl_csum:1;
-		u32 ip_csum:1;
-		u32 ipv4opts_ipv6exthdr:2;
-		u32 ipsec_ops:4;
-		u32 tsflag:1;
-		u32 csoffset:9;
-		u32 ifidx:8;
+		u32 tsflag:1;		/* Timestamp this packet */
+		u32 ipsec_ops:4;	/* IPsec operation */
 #else
-		u32 ifidx:8;
-		u32 csoffset:9;
-		u32 tsflag:1;
 		u32 ipsec_ops:4;
-		u32 ipv4opts_ipv6exthdr:2;
-		u32 ip_csum:1;
+		u32 tsflag:1;
 		u32 tnl_csum:1;
-		u32 reserved:6;
+		u32 transport_csum:1;
+		u32 ip_csum:1;
+		u32 reserved:24;
 #endif
 	} s;
 };
@@ -496,56 +638,96 @@ union oct_link_status {
 	struct {
 #ifdef __BIG_ENDIAN_BITFIELD
 		u64 duplex:8;
-		u64 status:8;
 		u64 mtu:16;
 		u64 speed:16;
+		u64 link_up:1;
 		u64 autoneg:1;
-		u64 interface:4;
+		u64 if_mode:5;
 		u64 pause:1;
-		u64 reserved:10;
+		u64 flashing:1;
+		u64 reserved:15;
 #else
-		u64 reserved:10;
+		u64 reserved:15;
+		u64 flashing:1;
 		u64 pause:1;
-		u64 interface:4;
+		u64 if_mode:5;
 		u64 autoneg:1;
+		u64 link_up:1;
 		u64 speed:16;
 		u64 mtu:16;
-		u64 status:8;
 		u64 duplex:8;
 #endif
 	} s;
 };
 
+/** The txpciq info passed to host from the firmware */
+
+union oct_txpciq {
+	u64 u64;
+
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		u64 q_no:8;
+		u64 port:8;
+		u64 pkind:6;
+		u64 use_qpg:1;
+		u64 qpg:11;
+		u64 reserved:30;
+#else
+		u64 reserved:30;
+		u64 qpg:11;
+		u64 use_qpg:1;
+		u64 pkind:6;
+		u64 port:8;
+		u64 q_no:8;
+#endif
+	} s;
+};
+
+/** The rxpciq info passed to host from the firmware */
+
+union oct_rxpciq {
+	u64 u64;
+
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		u64 q_no:8;
+		u64 reserved:56;
+#else
+		u64 reserved:56;
+		u64 q_no:8;
+#endif
+	} s;
+};
+
 /** Information for a OCTEON ethernet interface shared between core & host. */
 struct oct_link_info {
 	union oct_link_status link;
 	u64 hw_addr;
 
 #ifdef __BIG_ENDIAN_BITFIELD
-	u16 gmxport;
-	u8 rsvd[3];
-	u8 num_txpciq;
-	u8 num_rxpciq;
-	u8 ifidx;
+	u64 gmxport:16;
+	u64 rsvd:32;
+	u64 num_txpciq:8;
+	u64 num_rxpciq:8;
 #else
-	u8 ifidx;
-	u8 num_rxpciq;
-	u8 num_txpciq;
-	u8 rsvd[3];
-	u16 gmxport;
+	u64 num_rxpciq:8;
+	u64 num_txpciq:8;
+	u64 rsvd:32;
+	u64 gmxport:16;
 #endif
 
-	u8 txpciq[MAX_IOQS_PER_NICIF];
-	u8 rxpciq[MAX_IOQS_PER_NICIF];
+	union oct_txpciq txpciq[MAX_IOQS_PER_NICIF];
+	union oct_rxpciq rxpciq[MAX_IOQS_PER_NICIF];
 };
 
 #define OCT_LINK_INFO_SIZE   (sizeof(struct oct_link_info))
 
 struct liquidio_if_cfg_info {
-	u64 ifidx;
 	u64 iqmask; /** mask for IQs enabled for  the port */
 	u64 oqmask; /** mask for OQs enabled for the port */
 	struct oct_link_info linfo; /** initial link information */
+	char   liquidio_firmware_version[32];
 };
 
 /** Stats for each NIC port in RX direction. */
@@ -570,10 +752,18 @@ struct nic_rx_stats {
 	u64 fw_err_pko;
 	u64 fw_err_link;
 	u64 fw_err_drop;
+	u64 fw_rx_vxlan;
+	u64 fw_rx_vxlan_err;
+
+	/* LRO */
 	u64 fw_lro_pkts;   /* Number of packets that are LROed      */
 	u64 fw_lro_octs;   /* Number of octets that are LROed       */
 	u64 fw_total_lro;  /* Number of LRO packets formed          */
 	u64 fw_lro_aborts; /* Number of times lRO of packet aborted */
+	u64 fw_lro_aborts_port;
+	u64 fw_lro_aborts_seq;
+	u64 fw_lro_aborts_tsval;
+	u64 fw_lro_aborts_timer;
 	/* intrmod: packet forward rate */
 	u64 fwd_rate;
 };
@@ -597,9 +787,14 @@ struct nic_tx_stats {
 	/* firmware stats */
 	u64 fw_total_sent;
 	u64 fw_total_fwd;
+	u64 fw_total_fwd_bytes;
 	u64 fw_err_pko;
 	u64 fw_err_link;
 	u64 fw_err_drop;
+	u64 fw_err_tso;
+	u64 fw_tso;		/* number of tso requests */
+	u64 fw_tso_fwd;		/* number of packets segmented in tso */
+	u64 fw_tx_vxlan;
 };
 
 struct oct_link_stats {
@@ -630,23 +825,44 @@ struct oct_mdio_cmd {
 
 #define OCT_LINK_STATS_SIZE   (sizeof(struct oct_link_stats))
 
+/* intrmod: max. packet rate threshold */
+#define LIO_INTRMOD_MAXPKT_RATETHR	196608
+/* intrmod: min. packet rate threshold */
+#define LIO_INTRMOD_MINPKT_RATETHR	9216
+/* intrmod: max. packets to trigger interrupt */
+#define LIO_INTRMOD_RXMAXCNT_TRIGGER	384
+/* intrmod: min. packets to trigger interrupt */
+#define LIO_INTRMOD_RXMINCNT_TRIGGER	1
+/* intrmod: max. time to trigger interrupt */
+#define LIO_INTRMOD_RXMAXTMR_TRIGGER	128
+/* 66xx:intrmod: min. time to trigger interrupt
+ * (value of 1 is optimum for TCP_RR)
+ */
+#define LIO_INTRMOD_RXMINTMR_TRIGGER	1
+
+/* intrmod: max. packets to trigger interrupt */
+#define LIO_INTRMOD_TXMAXCNT_TRIGGER	64
+/* intrmod: min. packets to trigger interrupt */
+#define LIO_INTRMOD_TXMINCNT_TRIGGER	0
+
+/* intrmod: poll interval in seconds */
 #define LIO_INTRMOD_CHECK_INTERVAL  1
-#define LIO_INTRMOD_MAXPKT_RATETHR  196608 /* max pkt rate threshold */
-#define LIO_INTRMOD_MINPKT_RATETHR  9216   /* min pkt rate threshold */
-#define LIO_INTRMOD_MAXCNT_TRIGGER  384    /* max pkts to trigger interrupt */
-#define LIO_INTRMOD_MINCNT_TRIGGER  1      /* min pkts to trigger interrupt */
-#define LIO_INTRMOD_MAXTMR_TRIGGER  128    /* max time to trigger interrupt */
-#define LIO_INTRMOD_MINTMR_TRIGGER  32     /* min time to trigger interrupt */
 
 struct oct_intrmod_cfg {
-	u64 intrmod_enable;
-	u64 intrmod_check_intrvl;
-	u64 intrmod_maxpkt_ratethr;
-	u64 intrmod_minpkt_ratethr;
-	u64 intrmod_maxcnt_trigger;
-	u64 intrmod_maxtmr_trigger;
-	u64 intrmod_mincnt_trigger;
-	u64 intrmod_mintmr_trigger;
+	u64 rx_enable;
+	u64 tx_enable;
+	u64 check_intrvl;
+	u64 maxpkt_ratethr;
+	u64 minpkt_ratethr;
+	u64 rx_maxcnt_trigger;
+	u64 rx_mincnt_trigger;
+	u64 rx_maxtmr_trigger;
+	u64 rx_mintmr_trigger;
+	u64 tx_mincnt_trigger;
+	u64 tx_maxcnt_trigger;
+	u64 rx_frames;
+	u64 tx_frames;
+	u64 rx_usecs;
 };
 
 #define BASE_QUEUE_NOT_REQUESTED 65535
@@ -659,9 +875,9 @@ union oct_nic_if_cfg {
 		u64 num_iqueues:16;
 		u64 num_oqueues:16;
 		u64 gmx_port_id:8;
-		u64 reserved:8;
+		u64 vf_id:8;
 #else
-		u64 reserved:8;
+		u64 vf_id:8;
 		u64 gmx_port_id:8;
 		u64 num_oqueues:16;
 		u64 num_iqueues:16;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_config.h b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
index 62a8dd5cd3dc..b3396e3a8bab 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_config.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
@@ -37,7 +37,7 @@
 /* Maximum octeon devices defined as MAX_OCTEON_NICIF to support
  * multiple(<= MAX_OCTEON_NICIF) Miniports
  */
-#define   MAX_OCTEON_NICIF             32
+#define   MAX_OCTEON_NICIF             128
 #define   MAX_OCTEON_DEVICES           MAX_OCTEON_NICIF
 #define   MAX_OCTEON_LINKS	       MAX_OCTEON_NICIF
 #define   MAX_OCTEON_MULTICAST_ADDR    32
@@ -135,7 +135,7 @@
 #define CFG_GET_IS_SLI_BP_ON(cfg)                ((cfg)->misc.enable_sli_oq_bp)
 
 /* Max IOQs per OCTEON Link */
-#define MAX_IOQS_PER_NICIF              32
+#define MAX_IOQS_PER_NICIF              64
 
 enum lio_card_type {
 	LIO_210SV = 0, /* Two port, 66xx */
@@ -226,7 +226,7 @@ struct octeon_oq_config {
 	 */
 	u64 refill_threshold:16;
 
-	/** If set, the Output queue uses info-pointer mode. (Default: 1 ) */
+	/** If set, the Output queue uses info-pointer mode. (Default: 1) */
 	u64 info_ptr:32;
 
 	/* Max number of OQs available */
@@ -236,7 +236,7 @@ struct octeon_oq_config {
 	/* Max number of OQs available */
 	u64 max_oqs:8;
 
-	/** If set, the Output queue uses info-pointer mode. (Default: 1 ) */
+	/** If set, the Output queue uses info-pointer mode. (Default: 1) */
 	u64 info_ptr:32;
 
 	/** The number of buffers that were consumed during packet processing by
@@ -416,9 +416,11 @@ struct octeon_config {
 #define DISPATCH_LIST_SIZE                      BIT(OPCODE_MASK_BITS)
 
 /* Maximum number of Octeon Instruction (command) queues */
-#define MAX_OCTEON_INSTR_QUEUES         CN6XXX_MAX_INPUT_QUEUES
+#define MAX_OCTEON_INSTR_QUEUES(oct)         CN6XXX_MAX_INPUT_QUEUES
+/* Maximum number of Octeon Output queues */
+#define MAX_OCTEON_OUTPUT_QUEUES(oct)         CN6XXX_MAX_OUTPUT_QUEUES
 
-/* Maximum number of Octeon Instruction (command) queues */
-#define MAX_OCTEON_OUTPUT_QUEUES        CN6XXX_MAX_OUTPUT_QUEUES
+#define MAX_POSSIBLE_OCTEON_INSTR_QUEUES       CN6XXX_MAX_INPUT_QUEUES
+#define MAX_POSSIBLE_OCTEON_OUTPUT_QUEUES      CN6XXX_MAX_OUTPUT_QUEUES
 
 #endif /* __OCTEON_CONFIG_H__  */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
index 466147e409c9..bbb50ea66f16 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
@@ -23,27 +23,14 @@
 /**
  * @file octeon_console.c
  */
-#include <linux/version.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
 #include <linux/pci.h>
-#include <linux/kthread.h>
 #include <linux/netdevice.h>
-#include "octeon_config.h"
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
 #include "response_manager.h"
 #include "octeon_device.h"
-#include "octeon_nic.h"
 #include "octeon_main.h"
-#include "octeon_network.h"
-#include "cn66xx_regs.h"
-#include "cn66xx_device.h"
-#include "cn68xx_regs.h"
-#include "cn68xx_device.h"
-#include "liquidio_image.h"
 #include "octeon_mem_ops.h"
 
 static void octeon_remote_lock(void);
@@ -51,6 +38,8 @@ static void octeon_remote_unlock(void);
 static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct,
 					     const char *name,
 					     u32 flags);
+static int octeon_console_read(struct octeon_device *oct, u32 console_num,
+			       char *buffer, u32 buf_size);
 
 #define MIN(a, b) min((a), (b))
 #define CAST_ULL(v) ((u64)(v))
@@ -170,8 +159,8 @@ struct octeon_pci_console_desc {
 				offsetof(struct cvmx_bootmem_desc, field),   \
 				SIZEOF_FIELD(struct cvmx_bootmem_desc, field))
 
-#define __cvmx_bootmem_lock(flags)
-#define __cvmx_bootmem_unlock(flags)
+#define __cvmx_bootmem_lock(flags)	(flags = flags)
+#define __cvmx_bootmem_unlock(flags)	(flags = flags)
 
 /**
  * This macro returns a member of the
@@ -234,7 +223,7 @@ static void CVMX_BOOTMEM_NAMED_GET_NAME(struct octeon_device *oct,
 					u32 len)
 {
 	addr += offsetof(struct cvmx_bootmem_named_block_desc, name);
-	octeon_pci_read_core_mem(oct, addr, str, len);
+	octeon_pci_read_core_mem(oct, addr, (u8 *)str, len);
 	str[len] = 0;
 }
 
@@ -323,6 +312,9 @@ static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct,
 			if (name && named_size) {
 				char *name_tmp =
 					kmalloc(name_length + 1, GFP_KERNEL);
+				if (!name_tmp)
+					break;
+
 				CVMX_BOOTMEM_NAMED_GET_NAME(oct, named_addr,
 							    name_tmp,
 							    name_length);
@@ -383,7 +375,7 @@ static void octeon_remote_unlock(void)
 int octeon_console_send_cmd(struct octeon_device *oct, char *cmd_str,
 			    u32 wait_hundredths)
 {
-	u32 len = strlen(cmd_str);
+	u32 len = (u32)strlen(cmd_str);
 
 	dev_dbg(&oct->pci_dev->dev, "sending \"%s\" to bootloader\n", cmd_str);
 
@@ -440,8 +432,7 @@ int octeon_wait_for_bootloader(struct octeon_device *oct,
 }
 
 static void octeon_console_handle_result(struct octeon_device *oct,
-					 size_t console_num,
-					 char *buffer, s32 bytes_read)
+					 size_t console_num)
 {
 	struct octeon_console *console;
 
@@ -492,7 +483,7 @@ static void check_console(struct work_struct *work)
 	struct octeon_console *console;
 	struct cavium_wk *wk = (struct cavium_wk *)work;
 	struct octeon_device *oct = (struct octeon_device *)wk->ctxptr;
-	size_t console_num = wk->ctxul;
+	u32 console_num = (u32)wk->ctxul;
 	u32 delay;
 
 	console = &oct->console[console_num];
@@ -505,20 +496,17 @@ static void check_console(struct work_struct *work)
 		 */
 		bytes_read =
 			octeon_console_read(oct, console_num, console_buffer,
-					    sizeof(console_buffer) - 1, 0);
+					    sizeof(console_buffer) - 1);
 		if (bytes_read > 0) {
 			total_read += bytes_read;
-			if (console->waiting) {
-				octeon_console_handle_result(oct, console_num,
-							     console_buffer,
-							     bytes_read);
-			}
+			if (console->waiting)
+				octeon_console_handle_result(oct, console_num);
 			if (octeon_console_debug_enabled(console_num)) {
 				output_console_line(oct, console, console_num,
 						    console_buffer, bytes_read);
 			}
 		} else if (bytes_read < 0) {
-			dev_err(&oct->pci_dev->dev, "Error reading console %lu, ret=%d\n",
+			dev_err(&oct->pci_dev->dev, "Error reading console %u, ret=%d\n",
 				console_num, bytes_read);
 		}
 
@@ -530,7 +518,7 @@ static void check_console(struct work_struct *work)
 	 */
 	if (octeon_console_debug_enabled(console_num) &&
 	    (total_read == 0) && (console->leftover[0])) {
-		dev_info(&oct->pci_dev->dev, "%lu: %s\n",
+		dev_info(&oct->pci_dev->dev, "%u: %s\n",
 			 console_num, console->leftover);
 		console->leftover[0] = '\0';
 	}
@@ -675,8 +663,8 @@ static inline int octeon_console_avail_bytes(u32 buffer_size,
 	       octeon_console_free_bytes(buffer_size, wr_idx, rd_idx);
 }
 
-int octeon_console_read(struct octeon_device *oct, u32 console_num,
-			char *buffer, u32 buf_size, u32 flags)
+static int octeon_console_read(struct octeon_device *oct, u32 console_num,
+			       char *buffer, u32 buf_size)
 {
 	int bytes_to_read;
 	u32 rd_idx, wr_idx;
@@ -712,7 +700,7 @@ int octeon_console_read(struct octeon_device *oct, u32 console_num,
 		bytes_to_read = console->buffer_size - rd_idx;
 
 	octeon_pci_read_core_mem(oct, console->output_base_addr + rd_idx,
-				 buffer, bytes_to_read);
+				 (u8 *)buffer, bytes_to_read);
 	octeon_write_device_mem32(oct, console->addr +
 				  offsetof(struct octeon_pci_console,
 					   output_read_index),
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 8e23e3fad662..0eb504a4379a 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -19,28 +19,19 @@
 * This file may also be available under a different license from Cavium.
 * Contact Cavium, Inc. for more information
 **********************************************************************/
-#include <linux/version.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <linux/crc32.h>
-#include <linux/kthread.h>
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
-#include "octeon_config.h"
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
 #include "response_manager.h"
 #include "octeon_device.h"
-#include "octeon_nic.h"
 #include "octeon_main.h"
 #include "octeon_network.h"
 #include "cn66xx_regs.h"
 #include "cn66xx_device.h"
-#include "cn68xx_regs.h"
-#include "cn68xx_device.h"
 #include "liquidio_image.h"
 #include "octeon_mem_ops.h"
 
@@ -449,10 +440,10 @@ static struct octeon_config_ptr {
 };
 
 static char oct_dev_state_str[OCT_DEV_STATES + 1][32] = {
-	"BEGIN",	"PCI-MAP-DONE",	      "DISPATCH-INIT-DONE",
+	"BEGIN", "PCI-MAP-DONE", "DISPATCH-INIT-DONE",
 	"IQ-INIT-DONE", "SCBUFF-POOL-INIT-DONE", "RESPLIST-INIT-DONE",
 	"DROQ-INIT-DONE", "IO-QUEUES-INIT-DONE", "CONSOLE-INIT-DONE",
-	"HOST-READY",	"CORE-READY",	      "RUNNING",	   "IN-RESET",
+	"HOST-READY", "CORE-READY", "RUNNING", "IN-RESET",
 	"INVALID"
 };
 
@@ -550,17 +541,19 @@ static char *get_oct_app_string(u32 app_mode)
 	return oct_dev_app_str[CVM_DRV_INVALID_APP - CVM_DRV_APP_START];
 }
 
+u8 fbuf[4 * 1024 * 1024];
+
 int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
 			     size_t size)
 {
 	int ret = 0;
-	u8 *p;
-	u8 *buffer;
+	u8 *p = fbuf;
 	u32 crc32_result;
 	u64 load_addr;
 	u32 image_len;
 	struct octeon_firmware_file_header *h;
-	u32 i;
+	u32 i, rem, base_len = strlen(LIQUIDIO_BASE_VERSION);
+	char *base;
 
 	if (size < sizeof(struct octeon_firmware_file_header)) {
 		dev_err(&oct->pci_dev->dev, "Firmware file too small (%d < %d).\n",
@@ -576,19 +569,26 @@ int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
 		return -EINVAL;
 	}
 
-	crc32_result =
-		crc32(~0, data,
-		      sizeof(struct octeon_firmware_file_header) -
-		      sizeof(u32)) ^ ~0U;
+	crc32_result = crc32((unsigned int)~0, data,
+			     sizeof(struct octeon_firmware_file_header) -
+			     sizeof(u32)) ^ ~0U;
 	if (crc32_result != be32_to_cpu(h->crc32)) {
 		dev_err(&oct->pci_dev->dev, "Firmware CRC mismatch (0x%08x != 0x%08x).\n",
 			crc32_result, be32_to_cpu(h->crc32));
 		return -EINVAL;
 	}
 
-	if (memcmp(LIQUIDIO_VERSION, h->version, strlen(LIQUIDIO_VERSION))) {
-		dev_err(&oct->pci_dev->dev, "Unmatched firmware version. Expected %s, got %s.\n",
-			LIQUIDIO_VERSION, h->version);
+	if (strncmp(LIQUIDIO_PACKAGE, h->version, strlen(LIQUIDIO_PACKAGE))) {
+		dev_err(&oct->pci_dev->dev, "Unmatched firmware package type. Expected %s, got %s.\n",
+			LIQUIDIO_PACKAGE, h->version);
+		return -EINVAL;
+	}
+
+	base = h->version + strlen(LIQUIDIO_PACKAGE);
+	ret = memcmp(LIQUIDIO_BASE_VERSION, base, base_len);
+	if (ret) {
+		dev_err(&oct->pci_dev->dev, "Unmatched firmware version. Expected %s.x, got %s.\n",
+			LIQUIDIO_BASE_VERSION, base);
 		return -EINVAL;
 	}
 
@@ -602,58 +602,58 @@ int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
 	snprintf(oct->fw_info.liquidio_firmware_version, 32, "LIQUIDIO: %s",
 		 h->version);
 
-	buffer = kmemdup(data, size, GFP_KERNEL);
-	if (!buffer)
-		return -ENOMEM;
-
-	p = buffer + sizeof(struct octeon_firmware_file_header);
+	data += sizeof(struct octeon_firmware_file_header);
 
+	dev_info(&oct->pci_dev->dev, "%s: Loading %d images\n", __func__,
+		 be32_to_cpu(h->num_images));
 	/* load all images */
 	for (i = 0; i < be32_to_cpu(h->num_images); i++) {
 		load_addr = be64_to_cpu(h->desc[i].addr);
 		image_len = be32_to_cpu(h->desc[i].len);
 
-		/* validate the image */
-		crc32_result = crc32(~0, p, image_len) ^ ~0U;
-		if (crc32_result != be32_to_cpu(h->desc[i].crc32)) {
-			dev_err(&oct->pci_dev->dev,
-				"Firmware CRC mismatch in image %d (0x%08x != 0x%08x).\n",
-				i, crc32_result,
-				be32_to_cpu(h->desc[i].crc32));
-			ret = -EINVAL;
-			goto done_downloading;
-		}
+		dev_info(&oct->pci_dev->dev, "Loading firmware %d at %llx\n",
+			 image_len, load_addr);
 
-		/* download the image */
-		octeon_pci_write_core_mem(oct, load_addr, p, image_len);
+		/* Write in 4MB chunks*/
+		rem = image_len;
 
-		p += image_len;
-		dev_dbg(&oct->pci_dev->dev,
-			"Downloaded image %d (%d bytes) to address 0x%016llx\n",
-			i, image_len, load_addr);
+		while (rem) {
+			if (rem < (4 * 1024 * 1024))
+				size = rem;
+			else
+				size = 4 * 1024 * 1024;
+
+			memcpy(p, data, size);
+
+			/* download the image */
+			octeon_pci_write_core_mem(oct, load_addr, p, (u32)size);
+
+			data += size;
+			rem -= (u32)size;
+			load_addr += size;
+		}
 	}
+	dev_info(&oct->pci_dev->dev, "Writing boot command: %s\n",
+		 h->bootcmd);
 
 	/* Invoke the bootcmd */
 	ret = octeon_console_send_cmd(oct, h->bootcmd, 50);
 
-done_downloading:
-	kfree(buffer);
-
-	return ret;
+	return 0;
 }
 
 void octeon_free_device_mem(struct octeon_device *oct)
 {
-	u32 i;
+	int i;
 
-	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-		/* could check  mask as well */
-		vfree(oct->droq[i]);
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
+		if (oct->io_qmask.oq & (1ULL << i))
+			vfree(oct->droq[i]);
 	}
 
-	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
-		/* could check mask as well */
-		vfree(oct->instr_queue[i]);
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+		if (oct->io_qmask.iq & (1ULL << i))
+			vfree(oct->instr_queue[i]);
 	}
 
 	i = oct->octeon_id;
@@ -735,55 +735,61 @@ struct octeon_device *octeon_allocate_device(u32 pci_id,
 	octeon_device[oct_idx] = oct;
 
 	oct->octeon_id = oct_idx;
-	snprintf((oct->device_name), sizeof(oct->device_name),
+	snprintf(oct->device_name, sizeof(oct->device_name),
 		 "LiquidIO%d", (oct->octeon_id));
 
 	return oct;
 }
 
+/* this function is only for setting up the first queue */
 int octeon_setup_instr_queues(struct octeon_device *oct)
 {
-	u32 i, num_iqs = 0;
 	u32 num_descs = 0;
+	u32 iq_no = 0;
+	union oct_txpciq txpciq;
+	int numa_node = cpu_to_node(iq_no % num_online_cpus());
 
 	/* this causes queue 0 to be default queue */
-	if (OCTEON_CN6XXX(oct)) {
-		num_iqs = 1;
+	if (OCTEON_CN6XXX(oct))
 		num_descs =
 			CFG_GET_NUM_DEF_TX_DESCS(CHIP_FIELD(oct, cn6xxx, conf));
-	}
 
 	oct->num_iqs = 0;
 
-	for (i = 0; i < num_iqs; i++) {
-		oct->instr_queue[i] =
+	oct->instr_queue[0] = vmalloc_node(sizeof(*oct->instr_queue[0]),
+				numa_node);
+	if (!oct->instr_queue[0])
+		oct->instr_queue[0] =
 			vmalloc(sizeof(struct octeon_instr_queue));
-		if (!oct->instr_queue[i])
-			return 1;
-
-		memset(oct->instr_queue[i], 0,
-		       sizeof(struct octeon_instr_queue));
-
-		oct->instr_queue[i]->app_ctx = (void *)(size_t)i;
-		if (octeon_init_instr_queue(oct, i, num_descs))
-			return 1;
-
-		oct->num_iqs++;
+	if (!oct->instr_queue[0])
+		return 1;
+	memset(oct->instr_queue[0], 0, sizeof(struct octeon_instr_queue));
+	oct->instr_queue[0]->q_index = 0;
+	oct->instr_queue[0]->app_ctx = (void *)(size_t)0;
+	oct->instr_queue[0]->ifidx = 0;
+	txpciq.u64 = 0;
+	txpciq.s.q_no = iq_no;
+	txpciq.s.use_qpg = 0;
+	txpciq.s.qpg = 0;
+	if (octeon_init_instr_queue(oct, txpciq, num_descs)) {
+		/* prevent memory leak */
+		vfree(oct->instr_queue[0]);
+		return 1;
 	}
 
+	oct->num_iqs++;
 	return 0;
 }
 
 int octeon_setup_output_queues(struct octeon_device *oct)
 {
-	u32 i, num_oqs = 0;
 	u32 num_descs = 0;
 	u32 desc_size = 0;
+	u32 oq_no = 0;
+	int numa_node = cpu_to_node(oq_no % num_online_cpus());
 
 	/* this causes queue 0 to be default queue */
 	if (OCTEON_CN6XXX(oct)) {
-		/* CFG_GET_OQ_MAX_BASE_Q(CHIP_FIELD(oct, cn6xxx, conf)); */
-		num_oqs = 1;
 		num_descs =
 			CFG_GET_NUM_DEF_RX_DESCS(CHIP_FIELD(oct, cn6xxx, conf));
 		desc_size =
@@ -791,19 +797,15 @@ int octeon_setup_output_queues(struct octeon_device *oct)
 	}
 
 	oct->num_oqs = 0;
+	oct->droq[0] = vmalloc_node(sizeof(*oct->droq[0]), numa_node);
+	if (!oct->droq[0])
+		oct->droq[0] = vmalloc(sizeof(*oct->droq[0]));
+	if (!oct->droq[0])
+		return 1;
 
-	for (i = 0; i < num_oqs; i++) {
-		oct->droq[i] = vmalloc(sizeof(*oct->droq[i]));
-		if (!oct->droq[i])
-			return 1;
-
-		memset(oct->droq[i], 0, sizeof(struct octeon_droq));
-
-		if (octeon_init_droq(oct, i, num_descs, desc_size, NULL))
-			return 1;
-
-		oct->num_oqs++;
-	}
+	if (octeon_init_droq(oct, oq_no, num_descs, desc_size, NULL))
+		return 1;
+	oct->num_oqs++;
 
 	return 0;
 }
@@ -1005,79 +1007,6 @@ octeon_register_dispatch_fn(struct octeon_device *oct,
 	return 0;
 }
 
-/* octeon_unregister_dispatch_fn
- * Parameters:
- *   oct       - octeon device
- *   opcode    - driver should unregister the function for this opcode
- *   subcode   - driver should unregister the function for this subcode
- * Description:
- *   Unregister the function set for this opcode+subcode.
- * Returns:
- *   Success: 0
- *   Failure: 1
- * Locks:
- *   No locks are held.
- */
-int
-octeon_unregister_dispatch_fn(struct octeon_device *oct, u16 opcode,
-			      u16 subcode)
-{
-	int retval = 0;
-	u32 idx;
-	struct list_head *dispatch, *dfree = NULL, *tmp2;
-	u16 combined_opcode = OPCODE_SUBCODE(opcode, subcode);
-
-	idx = combined_opcode & OCTEON_OPCODE_MASK;
-
-	spin_lock_bh(&oct->dispatch.lock);
-
-	if (oct->dispatch.count == 0) {
-		spin_unlock_bh(&oct->dispatch.lock);
-		dev_err(&oct->pci_dev->dev,
-			"No dispatch functions registered for this device\n");
-		return 1;
-	}
-
-	if (oct->dispatch.dlist[idx].opcode == combined_opcode) {
-		dispatch = &oct->dispatch.dlist[idx].list;
-		if (dispatch->next != dispatch) {
-			dispatch = dispatch->next;
-			oct->dispatch.dlist[idx].opcode =
-				((struct octeon_dispatch *)dispatch)->opcode;
-			oct->dispatch.dlist[idx].dispatch_fn =
-				((struct octeon_dispatch *)
-				 dispatch)->dispatch_fn;
-			oct->dispatch.dlist[idx].arg =
-				((struct octeon_dispatch *)dispatch)->arg;
-			list_del(dispatch);
-			dfree = dispatch;
-		} else {
-			oct->dispatch.dlist[idx].opcode = 0;
-			oct->dispatch.dlist[idx].dispatch_fn = NULL;
-			oct->dispatch.dlist[idx].arg = NULL;
-		}
-	} else {
-		retval = 1;
-		list_for_each_safe(dispatch, tmp2,
-				   &(oct->dispatch.dlist[idx].
-				     list)) {
-			if (((struct octeon_dispatch *)dispatch)->opcode ==
-			    combined_opcode) {
-				list_del(dispatch);
-				dfree = dispatch;
-				retval = 0;
-			}
-		}
-	}
-
-	if (!retval)
-		oct->dispatch.count--;
-
-	spin_unlock_bh(&oct->dispatch.lock);
-	vfree(dfree);
-	return retval;
-}
-
 int octeon_core_drv_init(struct octeon_recv_info *recv_info, void *buf)
 {
 	u32 i;
@@ -1152,8 +1081,8 @@ core_drv_init_err:
 int octeon_get_tx_qsize(struct octeon_device *oct, u32 q_no)
 
 {
-	if (oct && (q_no < MAX_OCTEON_INSTR_QUEUES) &&
-	    (oct->io_qmask.iq & (1UL << q_no)))
+	if (oct && (q_no < MAX_OCTEON_INSTR_QUEUES(oct)) &&
+	    (oct->io_qmask.iq & (1ULL << q_no)))
 		return oct->instr_queue[q_no]->max_count;
 
 	return -1;
@@ -1161,8 +1090,8 @@ int octeon_get_tx_qsize(struct octeon_device *oct, u32 q_no)
 
 int octeon_get_rx_qsize(struct octeon_device *oct, u32 q_no)
 {
-	if (oct && (q_no < MAX_OCTEON_OUTPUT_QUEUES) &&
-	    (oct->io_qmask.oq & (1UL << q_no)))
+	if (oct && (q_no < MAX_OCTEON_OUTPUT_QUEUES(oct)) &&
+	    (oct->io_qmask.oq & (1ULL << q_no)))
 		return oct->droq[q_no]->max_count;
 	return -1;
 }
@@ -1253,10 +1182,10 @@ void lio_pci_writeq(struct octeon_device *oct,
 int octeon_mem_access_ok(struct octeon_device *oct)
 {
 	u64 access_okay = 0;
+	u64 lmc0_reset_ctl;
 
 	/* Check to make sure a DDR interface is enabled */
-	u64 lmc0_reset_ctl = lio_pci_readq(oct, CN6XXX_LMC0_RESET_CTL);
-
+	lmc0_reset_ctl = lio_pci_readq(oct, CN6XXX_LMC0_RESET_CTL);
 	access_okay = (lmc0_reset_ctl & CN6XXX_LMC0_RESET_CTL_DDR3RST_MASK);
 
 	return access_okay ? 0 : 1;
@@ -1270,9 +1199,6 @@ int octeon_wait_for_ddr_init(struct octeon_device *oct, u32 *timeout)
 	if (!timeout)
 		return ret;
 
-	while (*timeout == 0)
-		schedule_timeout_uninterruptible(HZ / 10);
-
 	for (ms = 0; (ret != 0) && ((*timeout == 0) || (ms <= *timeout));
 	     ms += HZ / 10) {
 		ret = octeon_mem_access_ok(oct);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index 36e1f85df8c4..01edfb404346 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -152,9 +152,9 @@ struct octeon_mmio {
 #define   MAX_OCTEON_MAPS    32
 
 struct octeon_io_enable {
-	u32 iq;
-	u32 oq;
-	u32 iq64B;
+	u64 iq;
+	u64 oq;
+	u64 iq64B;
 };
 
 struct octeon_reg_list {
@@ -204,8 +204,7 @@ struct octeon_fn_list {
 	void (*bar1_idx_setup)(struct octeon_device *, u64, u32, int);
 	void (*bar1_idx_write)(struct octeon_device *, u32, u32);
 	u32 (*bar1_idx_read)(struct octeon_device *, u32);
-	u32 (*update_iq_read_idx)(struct octeon_device *,
-				  struct octeon_instr_queue *);
+	u32 (*update_iq_read_idx)(struct octeon_instr_queue *);
 
 	void (*enable_oq_pkt_time_intr)(struct octeon_device *, u32);
 	void (*disable_oq_pkt_time_intr)(struct octeon_device *, u32);
@@ -222,7 +221,7 @@ struct octeon_fn_list {
 
 /* Structure for named memory blocks
  * Number of descriptors
- * available can be changed without affecting compatiblity,
+ * available can be changed without affecting compatibility,
  * but name length changes require a bump in the bootmem
  * descriptor version
  * Note: This structure must be naturally 64 bit aligned, as a single
@@ -255,7 +254,7 @@ struct oct_fw_info {
 struct cavium_wk {
 	struct delayed_work work;
 	void *ctxptr;
-	size_t ctxul;
+	u64 ctxul;
 };
 
 struct cavium_wq {
@@ -267,6 +266,8 @@ struct octdev_props {
 	/* Each interface in the Octeon device has a network
 	 * device pointer (used for OS specific calls).
 	 */
+	int    napi_enabled;
+	int    gmxport;
 	struct net_device *netdev;
 };
 
@@ -324,7 +325,8 @@ struct octeon_device {
 	struct octeon_sc_buffer_pool	sc_buf_pool;
 
 	/** The input instruction queues */
-	struct octeon_instr_queue *instr_queue[MAX_OCTEON_INSTR_QUEUES];
+	struct octeon_instr_queue *instr_queue
+		[MAX_POSSIBLE_OCTEON_INSTR_QUEUES];
 
 	/** The doubly-linked list of instruction response */
 	struct octeon_response_list response_list[MAX_RESPONSE_LISTS];
@@ -332,7 +334,7 @@ struct octeon_device {
 	u32 num_oqs;
 
 	/** The DROQ output queues  */
-	struct octeon_droq *droq[MAX_OCTEON_OUTPUT_QUEUES];
+	struct octeon_droq *droq[MAX_POSSIBLE_OCTEON_OUTPUT_QUEUES];
 
 	struct octeon_io_enable io_qmask;
 
@@ -381,15 +383,29 @@ struct octeon_device {
 
 	struct cavium_wq dma_comp_wq;
 
-	struct cavium_wq check_db_wq[MAX_OCTEON_INSTR_QUEUES];
+	/** Lock for dma response list */
+	spinlock_t cmd_resp_wqlock;
+	u32 cmd_resp_state;
+
+	struct cavium_wq check_db_wq[MAX_POSSIBLE_OCTEON_INSTR_QUEUES];
 
 	struct cavium_wk nic_poll_work;
 
 	struct cavium_wk console_poll_work[MAX_OCTEON_MAPS];
 
 	void *priv;
+
+	int rx_pause;
+	int tx_pause;
+
+	struct oct_link_stats link_stats; /*stastics from firmware*/
+
+	/* private flags to control driver-specific features through ethtool */
+	u32 priv_flags;
 };
 
+#define  OCT_DRV_ONLINE 1
+#define  OCT_DRV_OFFLINE 2
 #define  OCTEON_CN6XXX(oct)           ((oct->chip_id == OCTEON_CN66XX) || \
 				       (oct->chip_id == OCTEON_CN68XX))
 #define CHIP_FIELD(oct, TYPE, field)             \
@@ -569,8 +585,7 @@ int octeon_add_console(struct octeon_device *oct, u32 console_num);
 int octeon_console_write(struct octeon_device *oct, u32 console_num,
 			 char *buffer, u32 write_request_size, u32 flags);
 int octeon_console_write_avail(struct octeon_device *oct, u32 console_num);
-int octeon_console_read(struct octeon_device *oct, u32 console_num,
-			char *buffer, u32 buf_size, u32 flags);
+
 int octeon_console_read_avail(struct octeon_device *oct, u32 console_num);
 
 /** Removes all attached consoles. */
@@ -646,4 +661,17 @@ void *oct_get_config_info(struct octeon_device *oct, u16 card_type);
  */
 struct octeon_config *octeon_get_conf(struct octeon_device *oct);
 
+/* LiquidIO driver pivate flags */
+enum {
+	OCT_PRIV_FLAG_TX_BYTES = 0, /* Tx interrupts by pending byte count */
+};
+
+static inline void lio_set_priv_flag(struct octeon_device *octdev, u32 flag,
+				     u32 val)
+{
+	if (val)
+		octdev->priv_flags |= (0x1 << flag);
+	else
+		octdev->priv_flags &= ~(0x1 << flag);
+}
 #endif
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index 174072b3740b..e0afe4c1fd01 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -19,30 +19,18 @@
 * This file may also be available under a different license from Cavium.
 * Contact Cavium, Inc. for more information
 **********************************************************************/
-#include <linux/version.h>
-#include <linux/types.h>
-#include <linux/list.h>
 #include <linux/pci.h>
-#include <linux/kthread.h>
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
-#include "octeon_config.h"
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
 #include "response_manager.h"
 #include "octeon_device.h"
-#include "octeon_nic.h"
 #include "octeon_main.h"
 #include "octeon_network.h"
 #include "cn66xx_regs.h"
 #include "cn66xx_device.h"
-#include "cn68xx_regs.h"
-#include "cn68xx_device.h"
-#include "liquidio_image.h"
-#include "octeon_mem_ops.h"
-
-/* #define CAVIUM_ONLY_PERF_MODE */
 
 #define     CVM_MIN(d1, d2)           (((d1) < (d2)) ? (d1) : (d2))
 #define     CVM_MAX(d1, d2)           (((d1) > (d2)) ? (d1) : (d2))
@@ -104,8 +92,12 @@ static inline void *octeon_get_dispatch_arg(struct octeon_device *octeon_dev,
 	return fn_arg;
 }
 
-u32 octeon_droq_check_hw_for_pkts(struct octeon_device *oct,
-				  struct octeon_droq *droq)
+/** Check for packets on Droq. This function should be called with
+ * lock held.
+ *  @param  droq - Droq on which count is checked.
+ *  @return Returns packet count.
+ */
+u32 octeon_droq_check_hw_for_pkts(struct octeon_droq *droq)
 {
 	u32 pkt_count = 0;
 
@@ -151,22 +143,26 @@ octeon_droq_destroy_ring_buffers(struct octeon_device *oct,
 				 struct octeon_droq *droq)
 {
 	u32 i;
+	struct octeon_skb_page_info *pg_info;
 
 	for (i = 0; i < droq->max_count; i++) {
-		if (droq->recv_buf_list[i].buffer) {
-			if (droq->desc_ring) {
-				lio_unmap_ring_info(oct->pci_dev,
-						    (u64)droq->
-						    desc_ring[i].info_ptr,
-						    OCT_DROQ_INFO_SIZE);
-				lio_unmap_ring(oct->pci_dev,
-					       (u64)droq->desc_ring[i].
-					       buffer_ptr,
-					       droq->buffer_size);
-			}
-			recv_buffer_free(droq->recv_buf_list[i].buffer);
-			droq->recv_buf_list[i].buffer = NULL;
-		}
+		pg_info = &droq->recv_buf_list[i].pg_info;
+
+		if (pg_info->dma)
+			lio_unmap_ring(oct->pci_dev,
+				       (u64)pg_info->dma);
+		pg_info->dma = 0;
+
+		if (pg_info->page)
+			recv_buffer_destroy(droq->recv_buf_list[i].buffer,
+					    pg_info);
+
+		if (droq->desc_ring && droq->desc_ring[i].info_ptr)
+			lio_unmap_ring_info(oct->pci_dev,
+					    (u64)droq->
+					    desc_ring[i].info_ptr,
+					    OCT_DROQ_INFO_SIZE);
+		droq->recv_buf_list[i].buffer = NULL;
 	}
 
 	octeon_droq_reset_indices(droq);
@@ -181,25 +177,23 @@ octeon_droq_setup_ring_buffers(struct octeon_device *oct,
 	struct octeon_droq_desc *desc_ring = droq->desc_ring;
 
 	for (i = 0; i < droq->max_count; i++) {
-		buf = recv_buffer_alloc(oct, droq->q_no, droq->buffer_size);
+		buf = recv_buffer_alloc(oct, &droq->recv_buf_list[i].pg_info);
 
 		if (!buf) {
 			dev_err(&oct->pci_dev->dev, "%s buffer alloc failed\n",
 				__func__);
+			droq->stats.rx_alloc_failure++;
 			return -ENOMEM;
 		}
 
 		droq->recv_buf_list[i].buffer = buf;
 		droq->recv_buf_list[i].data = get_rbd(buf);
-
 		droq->info_list[i].length = 0;
 
 		/* map ring buffers into memory */
 		desc_ring[i].info_ptr = lio_map_ring_info(droq, i);
 		desc_ring[i].buffer_ptr =
-			lio_map_ring(oct->pci_dev,
-				     droq->recv_buf_list[i].buffer,
-				     droq->buffer_size);
+			lio_map_ring(droq->recv_buf_list[i].buffer);
 	}
 
 	octeon_droq_reset_indices(droq);
@@ -242,6 +236,8 @@ int octeon_init_droq(struct octeon_device *oct,
 	struct octeon_droq *droq;
 	u32 desc_ring_size = 0, c_num_descs = 0, c_buf_size = 0;
 	u32 c_pkts_per_intr = 0, c_refill_threshold = 0;
+	int orig_node = dev_to_node(&oct->pci_dev->dev);
+	int numa_node = cpu_to_node(q_no % num_online_cpus());
 
 	dev_dbg(&oct->pci_dev->dev, "%s[%d]\n", __func__, q_no);
 
@@ -261,15 +257,23 @@ int octeon_init_droq(struct octeon_device *oct,
 		struct octeon_config *conf6x = CHIP_FIELD(oct, cn6xxx, conf);
 
 		c_pkts_per_intr = (u32)CFG_GET_OQ_PKTS_PER_INTR(conf6x);
-		c_refill_threshold = (u32)CFG_GET_OQ_REFILL_THRESHOLD(conf6x);
+		c_refill_threshold =
+			(u32)CFG_GET_OQ_REFILL_THRESHOLD(conf6x);
+	} else {
+		return 1;
 	}
 
 	droq->max_count = c_num_descs;
 	droq->buffer_size = c_buf_size;
 
 	desc_ring_size = droq->max_count * OCT_DROQ_DESC_SIZE;
+	set_dev_node(&oct->pci_dev->dev, numa_node);
 	droq->desc_ring = lio_dma_alloc(oct, desc_ring_size,
 					(dma_addr_t *)&droq->desc_ring_dma);
+	set_dev_node(&oct->pci_dev->dev, orig_node);
+	if (!droq->desc_ring)
+		droq->desc_ring = lio_dma_alloc(oct, desc_ring_size,
+					(dma_addr_t *)&droq->desc_ring_dma);
 
 	if (!droq->desc_ring) {
 		dev_err(&oct->pci_dev->dev,
@@ -283,12 +287,11 @@ int octeon_init_droq(struct octeon_device *oct,
 		droq->max_count);
 
 	droq->info_list =
-		cnnic_alloc_aligned_dma(oct->pci_dev,
-					(droq->max_count * OCT_DROQ_INFO_SIZE),
-					&droq->info_alloc_size,
-					&droq->info_base_addr,
-					&droq->info_list_dma);
-
+		cnnic_numa_alloc_aligned_dma((droq->max_count *
+					      OCT_DROQ_INFO_SIZE),
+					     &droq->info_alloc_size,
+					     &droq->info_base_addr,
+					     numa_node);
 	if (!droq->info_list) {
 		dev_err(&oct->pci_dev->dev, "Cannot allocate memory for info list.\n");
 		lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE),
@@ -297,7 +300,12 @@ int octeon_init_droq(struct octeon_device *oct,
 	}
 
 	droq->recv_buf_list = (struct octeon_recv_buffer *)
-			      vmalloc(droq->max_count *
+			      vmalloc_node(droq->max_count *
+						OCT_DROQ_RECVBUF_SIZE,
+						numa_node);
+	if (!droq->recv_buf_list)
+		droq->recv_buf_list = (struct octeon_recv_buffer *)
+				      vmalloc(droq->max_count *
 						OCT_DROQ_RECVBUF_SIZE);
 	if (!droq->recv_buf_list) {
 		dev_err(&oct->pci_dev->dev, "Output queue recv buf list alloc failed\n");
@@ -320,7 +328,7 @@ int octeon_init_droq(struct octeon_device *oct,
 	/* For 56xx Pass1, this function won't be called, so no checks. */
 	oct->fn_list.setup_oq_regs(oct, q_no);
 
-	oct->io_qmask.oq |= (1 << q_no);
+	oct->io_qmask.oq |= (1ULL << q_no);
 
 	return 0;
 
@@ -358,6 +366,7 @@ static inline struct octeon_recv_info *octeon_create_recv_info(
 	struct octeon_recv_pkt *recv_pkt;
 	struct octeon_recv_info *recv_info;
 	u32 i, bytes_left;
+	struct octeon_skb_page_info *pg_info;
 
 	info = &droq->info_list[idx];
 
@@ -375,9 +384,14 @@ static inline struct octeon_recv_info *octeon_create_recv_info(
 	bytes_left = (u32)info->length;
 
 	while (buf_cnt) {
-		lio_unmap_ring(octeon_dev->pci_dev,
-			       (u64)droq->desc_ring[idx].buffer_ptr,
-			       droq->buffer_size);
+		{
+			pg_info = &droq->recv_buf_list[idx].pg_info;
+
+			lio_unmap_ring(octeon_dev->pci_dev,
+				       (u64)pg_info->dma);
+			pg_info->page = NULL;
+			pg_info->dma = 0;
+		}
 
 		recv_pkt->buffer_size[i] =
 			(bytes_left >=
@@ -449,6 +463,7 @@ octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq)
 	void *buf = NULL;
 	u8 *data;
 	u32 desc_refilled = 0;
+	struct octeon_skb_page_info *pg_info;
 
 	desc_ring = droq->desc_ring;
 
@@ -458,13 +473,22 @@ octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq)
 		 * the buffer, else allocate.
 		 */
 		if (!droq->recv_buf_list[droq->refill_idx].buffer) {
-			buf = recv_buffer_alloc(octeon_dev, droq->q_no,
-						droq->buffer_size);
+			pg_info =
+				&droq->recv_buf_list[droq->refill_idx].pg_info;
+			/* Either recycle the existing pages or go for
+			 * new page alloc
+			 */
+			if (pg_info->page)
+				buf = recv_buffer_reuse(octeon_dev, pg_info);
+			else
+				buf = recv_buffer_alloc(octeon_dev, pg_info);
 			/* If a buffer could not be allocated, no point in
 			 * continuing
 			 */
-			if (!buf)
+			if (!buf) {
+				droq->stats.rx_alloc_failure++;
 				break;
+			}
 			droq->recv_buf_list[droq->refill_idx].buffer =
 				buf;
 			data = get_rbd(buf);
@@ -476,11 +500,8 @@ octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq)
 		droq->recv_buf_list[droq->refill_idx].data = data;
 
 		desc_ring[droq->refill_idx].buffer_ptr =
-			lio_map_ring(octeon_dev->pci_dev,
-				     droq->recv_buf_list[droq->
-				     refill_idx].buffer,
-				     droq->buffer_size);
-
+			lio_map_ring(droq->recv_buf_list[droq->
+				     refill_idx].buffer);
 		/* Reset any previous values in the length field. */
 		droq->info_list[droq->refill_idx].length = 0;
 
@@ -539,7 +560,9 @@ octeon_droq_dispatch_pkt(struct octeon_device *oct,
 			droq->stats.dropped_nomem++;
 		}
 	} else {
-		dev_err(&oct->pci_dev->dev, "DROQ: No dispatch function\n");
+		dev_err(&oct->pci_dev->dev, "DROQ: No dispatch function (opcode %u/%u)\n",
+			(unsigned int)rh->r.opcode,
+			(unsigned int)rh->r.subcode);
 		droq->stats.dropped_nodispatch++;
 	}                       /* else (dispatch_fn ... */
 
@@ -586,6 +609,8 @@ octeon_droq_fast_process_packets(struct octeon_device *oct,
 	for (pkt = 0; pkt < pkt_count; pkt++) {
 		u32 pkt_len = 0;
 		struct sk_buff *nicbuf = NULL;
+		struct octeon_skb_page_info *pg_info;
+		void *buf;
 
 		info = &droq->info_list[droq->read_idx];
 		octeon_swap_8B_data((u64 *)info, 2);
@@ -605,7 +630,6 @@ octeon_droq_fast_process_packets(struct octeon_device *oct,
 		rh = &info->rh;
 
 		total_len += (u32)info->length;
-
 		if (OPCODE_SLOW_PATH(rh)) {
 			u32 buf_cnt;
 
@@ -614,50 +638,45 @@ octeon_droq_fast_process_packets(struct octeon_device *oct,
 			droq->refill_count += buf_cnt;
 		} else {
 			if (info->length <= droq->buffer_size) {
-				lio_unmap_ring(oct->pci_dev,
-					       (u64)droq->desc_ring[
-					       droq->read_idx].buffer_ptr,
-					       droq->buffer_size);
 				pkt_len = (u32)info->length;
 				nicbuf = droq->recv_buf_list[
 					droq->read_idx].buffer;
+				pg_info = &droq->recv_buf_list[
+					droq->read_idx].pg_info;
+				if (recv_buffer_recycle(oct, pg_info))
+					pg_info->page = NULL;
 				droq->recv_buf_list[droq->read_idx].buffer =
 					NULL;
+
 				INCR_INDEX_BY1(droq->read_idx, droq->max_count);
-				skb_put(nicbuf, pkt_len);
 				droq->refill_count++;
 			} else {
-				nicbuf = octeon_fast_packet_alloc(oct, droq,
-								  droq->q_no,
-								  (u32)
+				nicbuf = octeon_fast_packet_alloc((u32)
 								  info->length);
 				pkt_len = 0;
 				/* nicbuf allocation can fail. We'll handle it
 				 * inside the loop.
 				 */
 				while (pkt_len < info->length) {
-					int cpy_len;
+					int cpy_len, idx = droq->read_idx;
 
-					cpy_len = ((pkt_len +
-						droq->buffer_size) >
-						info->length) ?
+					cpy_len = ((pkt_len + droq->buffer_size)
+						   > info->length) ?
 						((u32)info->length - pkt_len) :
 						droq->buffer_size;
 
 					if (nicbuf) {
-						lio_unmap_ring(oct->pci_dev,
-							       (u64)
-							       droq->desc_ring
-							       [droq->read_idx].
-							       buffer_ptr,
-							       droq->
-							       buffer_size);
 						octeon_fast_packet_next(droq,
 									nicbuf,
 									cpy_len,
-									droq->
-									read_idx
-									);
+									idx);
+						buf = droq->recv_buf_list[idx].
+							buffer;
+						recv_buffer_fast_free(buf);
+						droq->recv_buf_list[idx].buffer
+							= NULL;
+					} else {
+						droq->stats.rx_alloc_failure++;
 					}
 
 					pkt_len += cpy_len;
@@ -668,12 +687,14 @@ octeon_droq_fast_process_packets(struct octeon_device *oct,
 			}
 
 			if (nicbuf) {
-				if (droq->ops.fptr)
+				if (droq->ops.fptr) {
 					droq->ops.fptr(oct->octeon_id,
-					nicbuf, pkt_len,
-					rh, &droq->napi);
-				else
+						       nicbuf, pkt_len,
+						       rh, &droq->napi,
+						       droq->ops.farg);
+				} else {
 					recv_buffer_free(nicbuf);
+				}
 			}
 		}
 
@@ -681,16 +702,16 @@ octeon_droq_fast_process_packets(struct octeon_device *oct,
 			int desc_refilled = octeon_droq_refill(oct, droq);
 
 			/* Flush the droq descriptor data to memory to be sure
-			* that when we update the credits the data in memory
-			* is accurate.
-			*/
+			 * that when we update the credits the data in memory
+			 * is accurate.
+			 */
 			wmb();
 			writel((desc_refilled), droq->pkts_credit_reg);
 			/* make sure mmio write completes */
 			mmiowb();
 		}
 
-	}                       /* for ( each packet )... */
+	}                       /* for (each packet)... */
 
 	/* Increment refill_count by the number of buffers processed. */
 	droq->stats.pkts_received += pkt;
@@ -721,7 +742,7 @@ octeon_droq_process_packets(struct octeon_device *oct,
 	if (pkt_count > budget)
 		pkt_count = budget;
 
-	/* Grab the lock */
+	/* Grab the droq lock */
 	spin_lock(&droq->lock);
 
 	pkts_processed = octeon_droq_fast_process_packets(oct, droq, pkt_count);
@@ -783,7 +804,7 @@ octeon_droq_process_poll_pkts(struct octeon_device *oct,
 
 		total_pkts_processed += pkts_processed;
 
-		octeon_droq_check_hw_for_pkts(oct, droq);
+		octeon_droq_check_hw_for_pkts(droq);
 	}
 
 	spin_unlock(&droq->lock);
@@ -807,18 +828,6 @@ octeon_process_droq_poll_cmd(struct octeon_device *oct, u32 q_no, int cmd,
 			     u32 arg)
 {
 	struct octeon_droq *droq;
-	struct octeon_config *oct_cfg = NULL;
-
-	oct_cfg = octeon_get_conf(oct);
-
-	if (!oct_cfg)
-		return -EINVAL;
-
-	if (q_no >= CFG_GET_OQ_MAX_Q(oct_cfg)) {
-		dev_err(&oct->pci_dev->dev, "%s: droq id (%d) exceeds MAX (%d)\n",
-			__func__, q_no, (oct->num_oqs - 1));
-		return -EINVAL;
-	}
 
 	droq = oct->droq[q_no];
 
@@ -937,6 +946,7 @@ int octeon_unregister_droq_ops(struct octeon_device *oct, u32 q_no)
 	spin_lock_irqsave(&droq->lock, flags);
 
 	droq->ops.fptr = NULL;
+	droq->ops.farg = NULL;
 	droq->ops.drop_on_max = 0;
 
 	spin_unlock_irqrestore(&droq->lock, flags);
@@ -949,6 +959,7 @@ int octeon_create_droq(struct octeon_device *oct,
 		       u32 desc_size, void *app_ctx)
 {
 	struct octeon_droq *droq;
+	int numa_node = cpu_to_node(q_no % num_online_cpus());
 
 	if (oct->droq[q_no]) {
 		dev_dbg(&oct->pci_dev->dev, "Droq already in use. Cannot create droq %d again\n",
@@ -957,7 +968,9 @@ int octeon_create_droq(struct octeon_device *oct,
 	}
 
 	/* Allocate the DS for the new droq. */
-	droq = vmalloc(sizeof(*droq));
+	droq = vmalloc_node(sizeof(*droq), numa_node);
+	if (!droq)
+		droq = vmalloc(sizeof(*droq));
 	if (!droq)
 		goto create_droq_fail;
 	memset(droq, 0, sizeof(struct octeon_droq));
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
index 7940ccee12d9..5a6fb9113bbd 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
@@ -65,6 +65,17 @@ struct octeon_droq_info {
 
 #define OCT_DROQ_INFO_SIZE   (sizeof(struct octeon_droq_info))
 
+struct octeon_skb_page_info {
+	/* DMA address for the page */
+	dma_addr_t dma;
+
+	/* Page for the rx dma  **/
+	struct page *page;
+
+	/** which offset into page */
+	unsigned int page_offset;
+};
+
 /** Pointer to data buffer.
  *  Driver keeps a pointer to the data buffer that it made available to
  *  the Octeon device. Since the descriptor ring keeps physical (bus)
@@ -77,6 +88,9 @@ struct octeon_recv_buffer {
 
 	/** Data in the packet buffer.  */
 	u8 *data;
+
+	/** pg_info **/
+	struct octeon_skb_page_info pg_info;
 };
 
 #define OCT_DROQ_RECVBUF_SIZE    (sizeof(struct octeon_recv_buffer))
@@ -106,6 +120,13 @@ struct oct_droq_stats {
 
 	/** Num of Packets dropped due to receive path failures. */
 	u64 rx_dropped;
+
+	/** Num of vxlan packets received; */
+	u64 rx_vxlan;
+
+	/** Num of failures of recv_buffer_alloc() */
+	u64 rx_alloc_failure;
+
 };
 
 #define POLL_EVENT_INTR_ARRIVED  1
@@ -213,7 +234,8 @@ struct octeon_droq_ops {
 	 *  data in the buffer. The receive header gives the port
 	 *  number to the caller.  Function pointer is set by caller.
 	 */
-	void (*fptr)(u32, void *, u32, union octeon_rh *, void *);
+	void (*fptr)(u32, void *, u32, union octeon_rh *, void *, void *);
+	void *farg;
 
 	/* This function will be called by the driver for all NAPI related
 	 * events. The first param is the octeon id. The second param is the
@@ -394,24 +416,9 @@ int octeon_register_dispatch_fn(struct octeon_device *oct,
 				u16 subcode,
 				octeon_dispatch_fn_t fn, void *fn_arg);
 
-/**  Remove registration for an opcode/subcode. This will delete the mapping for
- *   an opcode/subcode. The dispatch function will be unregistered and will no
- *   longer be called if a packet with the opcode/subcode arrives in the driver
- *   output queues.
- *   @param  oct        -  the octeon device to unregister from.
- *   @param  opcode     -  the opcode to be unregistered.
- *   @param  subcode    -  the subcode to be unregistered.
- *
- *   @return Success: 0; Failure: 1
- */
-int octeon_unregister_dispatch_fn(struct octeon_device *oct,
-				  u16 opcode,
-				  u16 subcode);
-
 void octeon_droq_print_stats(void);
 
-u32 octeon_droq_check_hw_for_pkts(struct octeon_device *oct,
-				  struct octeon_droq *droq);
+u32 octeon_droq_check_hw_for_pkts(struct octeon_droq *droq);
 
 int octeon_create_droq(struct octeon_device *oct, u32 q_no,
 		       u32 num_descs, u32 desc_size, void *app_ctx);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index 592fe49b589d..ff4b1d6f007b 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -65,6 +65,11 @@ struct oct_iq_stats {
 	u64 tx_iq_busy;/**< Numof times this iq was found to be full. */
 	u64 tx_dropped;/**< Numof pkts dropped dueto xmitpath errors. */
 	u64 tx_tot_bytes;/**< Total count of bytes sento to network. */
+	u64 tx_gso;  /* count of tso */
+	u64 tx_vxlan; /* tunnel */
+	u64 tx_dmamap_fail;
+	u64 tx_restart;
+	/*u64 tx_timeout_count;*/
 };
 
 #define OCT_IQ_STATS_SIZE   (sizeof(struct oct_iq_stats))
@@ -75,18 +80,26 @@ struct oct_iq_stats {
  *  a Octeon device has one such structure to represent it.
 */
 struct octeon_instr_queue {
+	struct octeon_device *oct_dev;
+
 	/** A spinlock to protect access to the input ring.  */
 	spinlock_t lock;
 
+	/** A spinlock to protect while posting on the ring.  */
+	spinlock_t post_lock;
+
+	/** A spinlock to protect access to the input ring.*/
+	spinlock_t iq_flush_running_lock;
+
 	/** Flag that indicates if the queue uses 64 byte commands. */
 	u32 iqcmd_64B:1;
 
-	/** Queue Number. */
-	u32 iq_no:5;
+	/** Queue info. */
+	union oct_txpciq txpciq;
 
 	u32 rsvd:17;
 
-	/* Controls the periodic flushing of iq */
+	/* Controls whether extra flushing of IQ is done on Tx */
 	u32 do_auto_flush:1;
 
 	u32 status:8;
@@ -147,6 +160,13 @@ struct octeon_instr_queue {
 
 	/** Application context */
 	void *app_ctx;
+
+	/* network stack queue index */
+	int q_index;
+
+	/*os ifidx associated with this queue */
+	int ifidx;
+
 };
 
 /*----------------------  INSTRUCTION FORMAT ----------------------------*/
@@ -176,12 +196,12 @@ struct octeon_instr_32B {
 /** 64-byte instruction format.
  *  Format of instruction for a 64-byte mode input queue.
  */
-struct octeon_instr_64B {
+struct octeon_instr2_64B {
 	/** Pointer where the input data is available. */
 	u64 dptr;
 
 	/** Instruction Header. */
-	u64 ih;
+	u64 ih2;
 
 	/** Input Request Header. */
 	u64 irh;
@@ -198,14 +218,44 @@ struct octeon_instr_64B {
 	u64 rptr;
 
 	u64 reserved;
+};
+
+struct octeon_instr3_64B {
+	/** Pointer where the input data is available. */
+	u64 dptr;
+
+	/** Instruction Header. */
+	u64 ih3;
+
+	/** Instruction Header. */
+	u64 pki_ih3;
+
+	/** Input Request Header. */
+	u64 irh;
 
+	/** opcode/subcode specific parameters */
+	u64 ossp[2];
+
+	/** Return Data Parameters */
+	u64 rdp;
+
+	/** Pointer where the response for a RAW mode packet will be written
+	 * by Octeon.
+	 */
+	u64 rptr;
+
+};
+
+union octeon_instr_64B {
+	struct octeon_instr2_64B cmd2;
+	struct octeon_instr3_64B cmd3;
 };
 
-#define OCT_64B_INSTR_SIZE     (sizeof(struct octeon_instr_64B))
+#define OCT_64B_INSTR_SIZE     (sizeof(union octeon_instr_64B))
 
 /** The size of each buffer in soft command buffer pool
  */
-#define  SOFT_COMMAND_BUFFER_SIZE	1024
+#define  SOFT_COMMAND_BUFFER_SIZE	1536
 
 struct octeon_soft_command {
 	/** Soft command buffer info. */
@@ -214,7 +264,8 @@ struct octeon_soft_command {
 	u32 size;
 
 	/** Command and return status */
-	struct octeon_instr_64B cmd;
+	union octeon_instr_64B cmd;
+
 #define COMPLETION_WORD_INIT    0xffffffffffffffffULL
 	u64 *status_word;
 
@@ -242,7 +293,7 @@ struct octeon_soft_command {
 
 /** Maximum number of buffers to allocate into soft command buffer pool
  */
-#define  MAX_SOFT_COMMAND_BUFFERS	16
+#define  MAX_SOFT_COMMAND_BUFFERS	256
 
 /** Head of a soft command buffer pool.
  */
@@ -268,14 +319,15 @@ void octeon_free_soft_command(struct octeon_device *oct,
 /**
  *  octeon_init_instr_queue()
  *  @param octeon_dev      - pointer to the octeon device structure.
- *  @param iq_no           - queue to be initialized (0 <= q_no <= 3).
+ *  @param txpciq          - queue to be initialized (0 <= q_no <= 3).
  *
  *  Called at driver init time for each input queue. iq_conf has the
  *  configuration parameters for the queue.
  *
  *  @return  Success: 0   Failure: 1
  */
-int octeon_init_instr_queue(struct octeon_device *octeon_dev, u32 iq_no,
+int octeon_init_instr_queue(struct octeon_device *octeon_dev,
+			    union oct_txpciq txpciq,
 			    u32 num_descs);
 
 /**
@@ -298,7 +350,7 @@ octeon_register_reqtype_free_fn(struct octeon_device *oct, int reqtype,
 
 int
 lio_process_iq_request_list(struct octeon_device *oct,
-			    struct octeon_instr_queue *iq);
+			    struct octeon_instr_queue *iq, u32 napi_budget);
 
 int octeon_send_command(struct octeon_device *oct, u32 iq_no,
 			u32 force_db, void *cmd, void *buf,
@@ -313,7 +365,10 @@ void octeon_prepare_soft_command(struct octeon_device *oct,
 int octeon_send_soft_command(struct octeon_device *oct,
 			     struct octeon_soft_command *sc);
 
-int octeon_setup_iq(struct octeon_device *oct, u32 iq_no,
-		    u32 num_descs, void *app_ctx);
-
+int octeon_setup_iq(struct octeon_device *oct, int ifidx,
+		    int q_index, union oct_txpciq iq_no, u32 num_descs,
+		    void *app_ctx);
+int
+octeon_flush_iq(struct octeon_device *oct, struct octeon_instr_queue *iq,
+		u32 pending_thresh, u32 napi_budget);
 #endif				/* __OCTEON_IQ_H__ */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
index cbd081981180..bc14e4c27332 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
@@ -126,22 +126,27 @@ static inline int octeon_map_pci_barx(struct octeon_device *oct,
 }
 
 static inline void *
-cnnic_alloc_aligned_dma(struct pci_dev *pci_dev,
-			u32 size,
-			u32 *alloc_size,
-			size_t *orig_ptr,
-			size_t *dma_addr __attribute__((unused)))
+cnnic_numa_alloc_aligned_dma(u32 size,
+			     u32 *alloc_size,
+			     size_t *orig_ptr,
+			     int numa_node)
 {
 	int retries = 0;
 	void *ptr = NULL;
 
 #define OCTEON_MAX_ALLOC_RETRIES     1
 	do {
-		ptr =
-		    (void *)__get_free_pages(GFP_KERNEL,
-					     get_order(size));
+		struct page *page = NULL;
+
+		page = alloc_pages_node(numa_node,
+					GFP_KERNEL,
+					get_order(size));
+		if (!page)
+			page = alloc_pages(GFP_KERNEL,
+					   get_order(size));
+		ptr = (void *)page_address(page);
 		if ((unsigned long)ptr & 0x07) {
-			free_pages((unsigned long)ptr, get_order(size));
+			__free_pages(page, get_order(size));
 			ptr = NULL;
 			/* Increment the size required if the first
 			 * attempt failed.
@@ -169,7 +174,7 @@ sleep_cond(wait_queue_head_t *wait_queue, int *condition)
 
 	init_waitqueue_entry(&we, current);
 	add_wait_queue(wait_queue, &we);
-	while (!(ACCESS_ONCE(*condition))) {
+	while (!(READ_ONCE(*condition))) {
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (signal_pending(current))
 			goto out;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c
index 5aecef870377..95a4bbedf557 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c
@@ -19,43 +19,29 @@
  * This file may also be available under a different license from Cavium.
  * Contact Cavium, Inc. for more information
  **********************************************************************/
-#include <linux/version.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
 #include <linux/pci.h>
-#include <linux/kthread.h>
 #include <linux/netdevice.h>
-#include "octeon_config.h"
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
 #include "response_manager.h"
 #include "octeon_device.h"
-#include "octeon_nic.h"
-#include "octeon_main.h"
-#include "octeon_network.h"
-#include "cn66xx_regs.h"
-#include "cn66xx_device.h"
-#include "cn68xx_regs.h"
-#include "cn68xx_device.h"
-#include "liquidio_image.h"
-#include "octeon_mem_ops.h"
 
 #define MEMOPS_IDX   MAX_BAR1_MAP_INDEX
 
+#ifdef __BIG_ENDIAN_BITFIELD
 static inline void
-octeon_toggle_bar1_swapmode(struct octeon_device *oct __attribute__((unused)),
-			    u32 idx __attribute__((unused)))
+octeon_toggle_bar1_swapmode(struct octeon_device *oct, u32 idx)
 {
-#ifdef __BIG_ENDIAN_BITFIELD
 	u32 mask;
 
 	mask = oct->fn_list.bar1_idx_read(oct, idx);
 	mask = (mask & 0x2) ? (mask & ~2) : (mask | 2);
 	oct->fn_list.bar1_idx_write(oct, idx, mask);
-#endif
 }
+#else
+#define octeon_toggle_bar1_swapmode(oct, idx) (oct = oct)
+#endif
 
 static void
 octeon_pci_fastwrite(struct octeon_device *oct, u8 __iomem *mapped_addr,
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
index b3abe5818fd3..fb820dc7fcb7 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
@@ -30,6 +30,20 @@
 #include <linux/dma-mapping.h>
 #include <linux/ptp_clock_kernel.h>
 
+#define LIO_MAX_MTU_SIZE (OCTNET_MAX_FRM_SIZE - OCTNET_FRM_HEADER_SIZE)
+#define LIO_MIN_MTU_SIZE 68
+
+struct oct_nic_stats_resp {
+	u64     rh;
+	struct oct_link_stats stats;
+	u64     status;
+};
+
+struct oct_nic_stats_ctrl {
+	struct completion complete;
+	struct net_device *netdev;
+};
+
 /** LiquidIO per-interface network private data */
 struct lio {
 	/** State of the interface. Rx/Tx happens only in the RUNNING state.  */
@@ -48,11 +62,11 @@ struct lio {
 	 */
 	int rxq;
 
-	/** Guards the glist */
-	spinlock_t lock;
+	/** Guards each glist */
+	spinlock_t *glist_lock;
 
-	/** Linked list of gather components */
-	struct list_head glist;
+	/** Array of gather component linked lists */
+	struct list_head *glist;
 
 	/** Pointer to the NIC properties for the Octeon device this network
 	 *  interface is associated with.
@@ -67,6 +81,9 @@ struct lio {
 	/** Link information sent by the core application for this interface. */
 	struct oct_link_info linfo;
 
+	/** counter of link changes */
+	u64 link_changes;
+
 	/** Size of Tx queue for this octeon device. */
 	u32 tx_qsize;
 
@@ -82,6 +99,12 @@ struct lio {
 	/** Copy of Interface capabilities: TSO, TSO6, LRO, Chescksums . */
 	u64 dev_capability;
 
+	/* Copy of transmit encapsulation capabilities:
+	 * TSO, TSO6, Checksums for this device for Kernel
+	 * 3.10.0 onwards
+	 */
+	u64 enc_dev_capability;
+
 	/** Copy of beacaon reg in phy */
 	u32 phy_beacon_val;
 
@@ -101,7 +124,6 @@ struct lio {
 
 	/* work queue for  txq status */
 	struct cavium_wq	txq_status_wq;
-
 };
 
 #define LIO_SIZE         (sizeof(struct lio))
@@ -111,8 +133,9 @@ struct lio {
  * \brief Enable or disable feature
  * @param netdev    pointer to network device
  * @param cmd       Command that just requires acknowledgment
+ * @param param1    Parameter to command
  */
-int liquidio_set_feature(struct net_device *netdev, int cmd);
+int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1);
 
 /**
  * \brief Link control command completion callback
@@ -131,14 +154,30 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr);
  */
 void liquidio_set_ethtool_ops(struct net_device *netdev);
 
-static inline void
-*recv_buffer_alloc(struct octeon_device *oct __attribute__((unused)),
-		   u32 q_no __attribute__((unused)), u32 size)
-{
 #define SKB_ADJ_MASK  0x3F
 #define SKB_ADJ       (SKB_ADJ_MASK + 1)
 
-	struct sk_buff *skb = dev_alloc_skb(size + SKB_ADJ);
+#define MIN_SKB_SIZE       256 /* 8 bytes and more - 8 bytes for PTP */
+#define LIO_RXBUFFER_SZ    2048
+
+static inline void
+*recv_buffer_alloc(struct octeon_device *oct,
+		   struct octeon_skb_page_info *pg_info)
+{
+	struct page *page;
+	struct sk_buff *skb;
+	struct octeon_skb_page_info *skb_pg_info;
+
+	page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+	if (unlikely(!page))
+		return NULL;
+
+	skb = dev_alloc_skb(MIN_SKB_SIZE + SKB_ADJ);
+	if (unlikely(!skb)) {
+		__free_page(page);
+		pg_info->page = NULL;
+		return NULL;
+	}
 
 	if ((unsigned long)skb->data & SKB_ADJ_MASK) {
 		u32 r = SKB_ADJ - ((unsigned long)skb->data & SKB_ADJ_MASK);
@@ -146,11 +185,151 @@ static inline void
 		skb_reserve(skb, r);
 	}
 
+	skb_pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+	/* Get DMA info */
+	pg_info->dma = dma_map_page(&oct->pci_dev->dev, page, 0,
+				    PAGE_SIZE, DMA_FROM_DEVICE);
+
+	/* Mapping failed!! */
+	if (dma_mapping_error(&oct->pci_dev->dev, pg_info->dma)) {
+		__free_page(page);
+		dev_kfree_skb_any((struct sk_buff *)skb);
+		pg_info->page = NULL;
+		return NULL;
+	}
+
+	pg_info->page = page;
+	pg_info->page_offset = 0;
+	skb_pg_info->page = page;
+	skb_pg_info->page_offset = 0;
+	skb_pg_info->dma = pg_info->dma;
+
 	return (void *)skb;
 }
 
+static inline void
+*recv_buffer_fast_alloc(u32 size)
+{
+	struct sk_buff *skb;
+	struct octeon_skb_page_info *skb_pg_info;
+
+	skb = dev_alloc_skb(size + SKB_ADJ);
+	if (unlikely(!skb))
+		return NULL;
+
+	if ((unsigned long)skb->data & SKB_ADJ_MASK) {
+		u32 r = SKB_ADJ - ((unsigned long)skb->data & SKB_ADJ_MASK);
+
+		skb_reserve(skb, r);
+	}
+
+	skb_pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+	skb_pg_info->page = NULL;
+	skb_pg_info->page_offset = 0;
+	skb_pg_info->dma = 0;
+
+	return skb;
+}
+
+static inline int
+recv_buffer_recycle(struct octeon_device *oct, void *buf)
+{
+	struct octeon_skb_page_info *pg_info = buf;
+
+	if (!pg_info->page) {
+		dev_err(&oct->pci_dev->dev, "%s: pg_info->page NULL\n",
+			__func__);
+		return -ENOMEM;
+	}
+
+	if (unlikely(page_count(pg_info->page) != 1) ||
+	    unlikely(page_to_nid(pg_info->page)	!= numa_node_id())) {
+		dma_unmap_page(&oct->pci_dev->dev,
+			       pg_info->dma, (PAGE_SIZE << 0),
+			       DMA_FROM_DEVICE);
+		pg_info->dma = 0;
+		pg_info->page = NULL;
+		pg_info->page_offset = 0;
+		return -ENOMEM;
+	}
+
+	/* Flip to other half of the buffer */
+	if (pg_info->page_offset == 0)
+		pg_info->page_offset = LIO_RXBUFFER_SZ;
+	else
+		pg_info->page_offset = 0;
+	page_ref_inc(pg_info->page);
+
+	return 0;
+}
+
+static inline void
+*recv_buffer_reuse(struct octeon_device *oct, void *buf)
+{
+	struct octeon_skb_page_info *pg_info = buf, *skb_pg_info;
+	struct sk_buff *skb;
+
+	skb = dev_alloc_skb(MIN_SKB_SIZE + SKB_ADJ);
+	if (unlikely(!skb)) {
+		dma_unmap_page(&oct->pci_dev->dev,
+			       pg_info->dma, (PAGE_SIZE << 0),
+			       DMA_FROM_DEVICE);
+		return NULL;
+	}
+
+	if ((unsigned long)skb->data & SKB_ADJ_MASK) {
+		u32 r = SKB_ADJ - ((unsigned long)skb->data & SKB_ADJ_MASK);
+
+		skb_reserve(skb, r);
+	}
+
+	skb_pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+	skb_pg_info->page = pg_info->page;
+	skb_pg_info->page_offset = pg_info->page_offset;
+	skb_pg_info->dma = pg_info->dma;
+
+	return skb;
+}
+
+static inline void
+recv_buffer_destroy(void *buffer, struct octeon_skb_page_info *pg_info)
+{
+	struct sk_buff *skb = (struct sk_buff *)buffer;
+
+	put_page(pg_info->page);
+	pg_info->dma = 0;
+	pg_info->page = NULL;
+	pg_info->page_offset = 0;
+
+	if (skb)
+		dev_kfree_skb_any(skb);
+}
+
 static inline void recv_buffer_free(void *buffer)
 {
+	struct sk_buff *skb = (struct sk_buff *)buffer;
+	struct octeon_skb_page_info *pg_info;
+
+	pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+
+	if (pg_info->page) {
+		put_page(pg_info->page);
+		pg_info->dma = 0;
+		pg_info->page = NULL;
+		pg_info->page_offset = 0;
+	}
+
+	dev_kfree_skb_any((struct sk_buff *)buffer);
+}
+
+static inline void
+recv_buffer_fast_free(void *buffer)
+{
+	dev_kfree_skb_any((struct sk_buff *)buffer);
+}
+
+static inline void tx_buffer_free(void *buffer)
+{
 	dev_kfree_skb_any((struct sk_buff *)buffer);
 }
 
@@ -159,7 +338,17 @@ static inline void recv_buffer_free(void *buffer)
 #define lio_dma_free(oct, size, virt_addr, dma_addr) \
 	dma_free_coherent(&oct->pci_dev->dev, size, virt_addr, dma_addr)
 
-#define   get_rbd(ptr)      (((struct sk_buff *)(ptr))->data)
+static inline
+void *get_rbd(struct sk_buff *skb)
+{
+	struct octeon_skb_page_info *pg_info;
+	unsigned char *va;
+
+	pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+	va = page_address(pg_info->page) + pg_info->page_offset;
+
+	return va;
+}
 
 static inline u64
 lio_map_ring_info(struct octeon_droq *droq, u32 i)
@@ -170,7 +359,7 @@ lio_map_ring_info(struct octeon_droq *droq, u32 i)
 	dma_addr = dma_map_single(&oct->pci_dev->dev, &droq->info_list[i],
 				  OCT_DROQ_INFO_SIZE, DMA_FROM_DEVICE);
 
-	BUG_ON(dma_mapping_error(&oct->pci_dev->dev, dma_addr));
+	WARN_ON(dma_mapping_error(&oct->pci_dev->dev, dma_addr));
 
 	return (u64)dma_addr;
 }
@@ -183,33 +372,44 @@ lio_unmap_ring_info(struct pci_dev *pci_dev,
 }
 
 static inline u64
-lio_map_ring(struct pci_dev *pci_dev,
-	     void *buf, u32 size)
+lio_map_ring(void *buf)
 {
 	dma_addr_t dma_addr;
 
-	dma_addr = dma_map_single(&pci_dev->dev, get_rbd(buf), size,
-				  DMA_FROM_DEVICE);
+	struct sk_buff *skb = (struct sk_buff *)buf;
+	struct octeon_skb_page_info *pg_info;
 
-	BUG_ON(dma_mapping_error(&pci_dev->dev, dma_addr));
+	pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+	if (!pg_info->page) {
+		pr_err("%s: pg_info->page NULL\n", __func__);
+		WARN_ON(1);
+	}
+
+	/* Get DMA info */
+	dma_addr = pg_info->dma;
+	if (!pg_info->dma) {
+		pr_err("%s: ERROR it should be already available\n",
+		       __func__);
+		WARN_ON(1);
+	}
+	dma_addr += pg_info->page_offset;
 
 	return (u64)dma_addr;
 }
 
 static inline void
 lio_unmap_ring(struct pci_dev *pci_dev,
-	       u64 buf_ptr, u32 size)
+	       u64 buf_ptr)
+
 {
-	dma_unmap_single(&pci_dev->dev,
-			 buf_ptr, size,
-			 DMA_FROM_DEVICE);
+	dma_unmap_page(&pci_dev->dev,
+		       buf_ptr, (PAGE_SIZE << 0),
+		       DMA_FROM_DEVICE);
 }
 
-static inline void *octeon_fast_packet_alloc(struct octeon_device *oct,
-					     struct octeon_droq *droq,
-					     u32 q_no, u32 size)
+static inline void *octeon_fast_packet_alloc(u32 size)
 {
-	return recv_buffer_alloc(oct, q_no, size);
+	return recv_buffer_fast_alloc(size);
 }
 
 static inline void octeon_fast_packet_next(struct octeon_droq *droq,
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
index 1a0191549cb3..166727be928f 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
@@ -19,14 +19,9 @@
  * This file may also be available under a different license from Cavium.
  * Contact Cavium, Inc. for more information
  **********************************************************************/
-#include <linux/version.h>
-#include <linux/types.h>
-#include <linux/list.h>
 #include <linux/interrupt.h>
 #include <linux/pci.h>
-#include <linux/kthread.h>
 #include <linux/netdevice.h>
-#include "octeon_config.h"
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
@@ -34,21 +29,14 @@
 #include "octeon_device.h"
 #include "octeon_nic.h"
 #include "octeon_main.h"
-#include "octeon_network.h"
-#include "cn66xx_regs.h"
-#include "cn66xx_device.h"
-#include "cn68xx_regs.h"
-#include "cn68xx_device.h"
-#include "liquidio_image.h"
-#include "octeon_mem_ops.h"
 
 void *
 octeon_alloc_soft_command_resp(struct octeon_device    *oct,
-			       struct octeon_instr_64B *cmd,
-			       size_t		       rdatasize)
+			       union octeon_instr_64B *cmd,
+			       u32		       rdatasize)
 {
 	struct octeon_soft_command *sc;
-	struct octeon_instr_ih  *ih;
+	struct octeon_instr_ih2  *ih2;
 	struct octeon_instr_irh *irh;
 	struct octeon_instr_rdp *rdp;
 
@@ -59,24 +47,25 @@ octeon_alloc_soft_command_resp(struct octeon_device    *oct,
 		return NULL;
 
 	/* Copy existing command structure into the soft command */
-	memcpy(&sc->cmd, cmd, sizeof(struct octeon_instr_64B));
+	memcpy(&sc->cmd, cmd, sizeof(union octeon_instr_64B));
 
 	/* Add in the response related fields. Opcode and Param are already
 	 * there.
 	 */
-	ih      = (struct octeon_instr_ih *)&sc->cmd.ih;
-	ih->fsz = 40; /* irh + ossp[0] + ossp[1] + rdp + rptr = 40 bytes */
+	ih2      = (struct octeon_instr_ih2 *)&sc->cmd.cmd2.ih2;
+	rdp     = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp;
+	irh     = (struct octeon_instr_irh *)&sc->cmd.cmd2.irh;
+	ih2->fsz = 40; /* irh + ossp[0] + ossp[1] + rdp + rptr = 40 bytes */
 
-	irh        = (struct octeon_instr_irh *)&sc->cmd.irh;
 	irh->rflag = 1; /* a response is required */
-	irh->len   = 4; /* means four 64-bit words immediately follow irh */
 
-	rdp            = (struct octeon_instr_rdp *)&sc->cmd.rdp;
 	rdp->pcie_port = oct->pcie_port;
 	rdp->rlen      = rdatasize;
 
 	*sc->status_word = COMPLETION_WORD_INIT;
 
+	sc->cmd.cmd2.rptr =  sc->dmarptr;
+
 	sc->wait_time = 1000;
 	sc->timeout = jiffies + sc->wait_time;
 
@@ -119,12 +108,11 @@ static void octnet_link_ctrl_callback(struct octeon_device *oct,
 
 static inline struct octeon_soft_command
 *octnic_alloc_ctrl_pkt_sc(struct octeon_device *oct,
-			  struct octnic_ctrl_pkt *nctrl,
-			  struct octnic_ctrl_params nparams)
+			  struct octnic_ctrl_pkt *nctrl)
 {
 	struct octeon_soft_command *sc = NULL;
 	u8 *data;
-	size_t rdatasize;
+	u32 rdatasize;
 	u32 uddsize = 0, datasize = 0;
 
 	uddsize = (u32)(nctrl->ncmd.s.more * 8);
@@ -143,7 +131,7 @@ static inline struct octeon_soft_command
 
 	data = (u8 *)sc->virtdptr;
 
-	memcpy(data, &nctrl->ncmd,  OCTNET_CMD_SIZE);
+	memcpy(data, &nctrl->ncmd, OCTNET_CMD_SIZE);
 
 	octeon_swap_8B_data((u64 *)data, (OCTNET_CMD_SIZE >> 3));
 
@@ -152,6 +140,8 @@ static inline struct octeon_soft_command
 		memcpy(data + OCTNET_CMD_SIZE, nctrl->udd, uddsize);
 	}
 
+	sc->iq_no = (u32)nctrl->iq_no;
+
 	octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_CMD,
 				    0, 0, 0);
 
@@ -164,26 +154,41 @@ static inline struct octeon_soft_command
 
 int
 octnet_send_nic_ctrl_pkt(struct octeon_device *oct,
-			 struct octnic_ctrl_pkt *nctrl,
-			 struct octnic_ctrl_params nparams)
+			 struct octnic_ctrl_pkt *nctrl)
 {
 	int retval;
 	struct octeon_soft_command *sc = NULL;
 
-	sc = octnic_alloc_ctrl_pkt_sc(oct, nctrl, nparams);
+	spin_lock_bh(&oct->cmd_resp_wqlock);
+	/* Allow only rx ctrl command to stop traffic on the chip
+	 * during offline operations
+	 */
+	if ((oct->cmd_resp_state == OCT_DRV_OFFLINE) &&
+	    (nctrl->ncmd.s.cmd != OCTNET_CMD_RX_CTL)) {
+		spin_unlock_bh(&oct->cmd_resp_wqlock);
+		dev_err(&oct->pci_dev->dev,
+			"%s cmd:%d not processed since driver offline\n",
+			__func__, nctrl->ncmd.s.cmd);
+		return -1;
+	}
+
+	sc = octnic_alloc_ctrl_pkt_sc(oct, nctrl);
 	if (!sc) {
 		dev_err(&oct->pci_dev->dev, "%s soft command alloc failed\n",
 			__func__);
+		spin_unlock_bh(&oct->cmd_resp_wqlock);
 		return -1;
 	}
 
 	retval = octeon_send_soft_command(oct, sc);
-	if (retval) {
+	if (retval == IQ_SEND_FAILED) {
 		octeon_free_soft_command(oct, sc);
-		dev_err(&oct->pci_dev->dev, "%s soft command send failed status: %x\n",
-			__func__, retval);
+		dev_err(&oct->pci_dev->dev, "%s soft command:%d send failed status: %x\n",
+			__func__, nctrl->ncmd.s.cmd, retval);
+		spin_unlock_bh(&oct->cmd_resp_wqlock);
 		return -1;
 	}
 
+	spin_unlock_bh(&oct->cmd_resp_wqlock);
 	return retval;
 }
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
index 0238857c8105..b71a2bbe4bee 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
@@ -52,6 +52,9 @@ struct octnic_ctrl_pkt {
 	/** Additional data that may be needed by some commands. */
 	u64 udd[MAX_NCTRL_UDD];
 
+	/** Input queue to use to send this command. */
+	u64 iq_no;
+
 	/** Time to wait for Octeon software to respond to this control command.
 	 *  If wait_time is 0, OSI assumes no response is expected.
 	 */
@@ -82,7 +85,7 @@ struct octnic_data_pkt {
 	u32 datasize;
 
 	/** Command to be passed to the Octeon device software. */
-	struct octeon_instr_64B cmd;
+	union octeon_instr_64B cmd;
 
 	/** Input queue to use to send this command. */
 	u32 q_no;
@@ -94,15 +97,14 @@ struct octnic_data_pkt {
  */
 union octnic_cmd_setup {
 	struct {
-		u32 ifidx:8;
-		u32 cksum_offset:7;
+		u32 iq_no:8;
 		u32 gather:1;
 		u32 timestamp:1;
-		u32 ipv4opts_ipv6exthdr:2;
 		u32 ip_csum:1;
+		u32 transport_csum:1;
 		u32 tnl_csum:1;
+		u32 rsvd:19;
 
-		u32 rsvd:11;
 		union {
 			u32 datasize;
 			u32 gatherptrs;
@@ -113,79 +115,146 @@ union octnic_cmd_setup {
 
 };
 
-struct octnic_ctrl_params {
-	u32 resp_order;
-};
-
 static inline int octnet_iq_is_full(struct octeon_device *oct, u32 q_no)
 {
 	return ((u32)atomic_read(&oct->instr_queue[q_no]->instr_pending)
 		>= (oct->instr_queue[q_no]->max_count - 2));
 }
 
-/** Utility function to prepare a 64B NIC instruction based on a setup command
- * @param cmd - pointer to instruction to be filled in.
- * @param setup - pointer to the setup structure
- * @param q_no - which queue for back pressure
- *
- * Assumes the cmd instruction is pre-allocated, but no fields are filled in.
- */
 static inline void
-octnet_prepare_pci_cmd(struct octeon_instr_64B *cmd,
-		       union octnic_cmd_setup *setup, u32 tag)
+octnet_prepare_pci_cmd_o2(struct octeon_device *oct,
+			  union octeon_instr_64B *cmd,
+			  union octnic_cmd_setup *setup, u32 tag)
 {
-	struct octeon_instr_ih *ih;
+	struct octeon_instr_ih2 *ih2;
 	struct octeon_instr_irh *irh;
 	union octnic_packet_params packet_params;
+	int port;
 
-	memset(cmd, 0, sizeof(struct octeon_instr_64B));
+	memset(cmd, 0, sizeof(union octeon_instr_64B));
 
-	ih = (struct octeon_instr_ih *)&cmd->ih;
+	ih2 = (struct octeon_instr_ih2 *)&cmd->cmd2.ih2;
 
 	/* assume that rflag is cleared so therefore front data will only have
-	 * irh and ossp[1] and ossp[2] for a total of 24 bytes
+	 * irh and ossp[0], ossp[1] for a total of 32 bytes
 	 */
-	ih->fsz = 24;
+	ih2->fsz = 24;
+
+	ih2->tagtype = ORDERED_TAG;
+	ih2->grp = DEFAULT_POW_GRP;
 
-	ih->tagtype = ORDERED_TAG;
-	ih->grp = DEFAULT_POW_GRP;
+	port = (int)oct->instr_queue[setup->s.iq_no]->txpciq.s.port;
 
 	if (tag)
-		ih->tag = tag;
+		ih2->tag = tag;
 	else
-		ih->tag = LIO_DATA(setup->s.ifidx);
+		ih2->tag = LIO_DATA(port);
 
-	ih->raw = 1;
-	ih->qos = (setup->s.ifidx & 3) + 4;	/* map qos based on interface */
+	ih2->raw = 1;
+	ih2->qos = (port & 3) + 4;	/* map qos based on interface */
 
 	if (!setup->s.gather) {
-		ih->dlengsz = setup->s.u.datasize;
+		ih2->dlengsz = setup->s.u.datasize;
 	} else {
-		ih->gather = 1;
-		ih->dlengsz = setup->s.u.gatherptrs;
+		ih2->gather = 1;
+		ih2->dlengsz = setup->s.u.gatherptrs;
 	}
 
-	irh = (struct octeon_instr_irh *)&cmd->irh;
+	irh = (struct octeon_instr_irh *)&cmd->cmd2.irh;
 
 	irh->opcode = OPCODE_NIC;
 	irh->subcode = OPCODE_NIC_NW_DATA;
 
 	packet_params.u32 = 0;
 
-	if (setup->s.cksum_offset) {
-		packet_params.s.csoffset = setup->s.cksum_offset;
-		packet_params.s.ipv4opts_ipv6exthdr =
-						setup->s.ipv4opts_ipv6exthdr;
+	packet_params.s.ip_csum = setup->s.ip_csum;
+	packet_params.s.transport_csum = setup->s.transport_csum;
+	packet_params.s.tnl_csum = setup->s.tnl_csum;
+	packet_params.s.tsflag = setup->s.timestamp;
+
+	irh->ossp = packet_params.u32;
+}
+
+static inline void
+octnet_prepare_pci_cmd_o3(struct octeon_device *oct,
+			  union octeon_instr_64B *cmd,
+			  union octnic_cmd_setup *setup, u32 tag)
+{
+	struct octeon_instr_irh *irh;
+	struct octeon_instr_ih3     *ih3;
+	struct octeon_instr_pki_ih3 *pki_ih3;
+	union octnic_packet_params packet_params;
+	int port;
+
+	memset(cmd, 0, sizeof(union octeon_instr_64B));
+
+	ih3 = (struct octeon_instr_ih3 *)&cmd->cmd3.ih3;
+	pki_ih3 = (struct octeon_instr_pki_ih3 *)&cmd->cmd3.pki_ih3;
+
+	/* assume that rflag is cleared so therefore front data will only have
+	 * irh and ossp[1] and ossp[2] for a total of 24 bytes
+	 */
+	ih3->pkind       = oct->instr_queue[setup->s.iq_no]->txpciq.s.pkind;
+	/*PKI IH*/
+	ih3->fsz = 24 + 8;
+
+	if (!setup->s.gather) {
+		ih3->dlengsz = setup->s.u.datasize;
+	} else {
+		ih3->gather = 1;
+		ih3->dlengsz = setup->s.u.gatherptrs;
 	}
 
+	pki_ih3->w       = 1;
+	pki_ih3->raw     = 1;
+	pki_ih3->utag    = 1;
+	pki_ih3->utt     = 1;
+	pki_ih3->uqpg    = oct->instr_queue[setup->s.iq_no]->txpciq.s.use_qpg;
+
+	port = (int)oct->instr_queue[setup->s.iq_no]->txpciq.s.port;
+
+	if (tag)
+		pki_ih3->tag = tag;
+	else
+		pki_ih3->tag     = LIO_DATA(port);
+
+	pki_ih3->tagtype = ORDERED_TAG;
+	pki_ih3->qpg     = oct->instr_queue[setup->s.iq_no]->txpciq.s.qpg;
+	pki_ih3->pm      = 0x7; /*0x7 - meant for Parse nothing, uninterpreted*/
+	pki_ih3->sl      = 8;   /* sl will be sizeof(pki_ih3)*/
+
+	irh = (struct octeon_instr_irh *)&cmd->cmd3.irh;
+
+	irh->opcode = OPCODE_NIC;
+	irh->subcode = OPCODE_NIC_NW_DATA;
+
+	packet_params.u32 = 0;
+
 	packet_params.s.ip_csum = setup->s.ip_csum;
+	packet_params.s.transport_csum = setup->s.transport_csum;
 	packet_params.s.tnl_csum = setup->s.tnl_csum;
-	packet_params.s.ifidx = setup->s.ifidx;
 	packet_params.s.tsflag = setup->s.timestamp;
 
 	irh->ossp = packet_params.u32;
 }
 
+/** Utility function to prepare a 64B NIC instruction based on a setup command
+ * @param cmd - pointer to instruction to be filled in.
+ * @param setup - pointer to the setup structure
+ * @param q_no - which queue for back pressure
+ *
+ * Assumes the cmd instruction is pre-allocated, but no fields are filled in.
+ */
+static inline void
+octnet_prepare_pci_cmd(struct octeon_device *oct, union octeon_instr_64B *cmd,
+		       union octnic_cmd_setup *setup, u32 tag)
+{
+	if (OCTEON_CN6XXX(oct))
+		octnet_prepare_pci_cmd_o2(oct, cmd, setup, tag);
+	else
+		octnet_prepare_pci_cmd_o3(oct, cmd, setup, tag);
+}
+
 /** Allocate and a soft command with space for a response immediately following
  * the commnad.
  * @param oct - octeon device pointer
@@ -198,8 +267,8 @@ octnet_prepare_pci_cmd(struct octeon_instr_64B *cmd,
  */
 void *
 octeon_alloc_soft_command_resp(struct octeon_device    *oct,
-			       struct octeon_instr_64B *cmd,
-			       size_t		       rdatasize);
+			       union octeon_instr_64B *cmd,
+			       u32		       rdatasize);
 
 /** Send a NIC data packet to the device
  * @param oct - octeon device pointer
@@ -214,14 +283,11 @@ int octnet_send_nic_data_pkt(struct octeon_device *oct,
 /** Send a NIC control packet to the device
  * @param oct - octeon device pointer
  * @param nctrl - control structure with command, timout, and callback info
- * @param nparams - response control structure
- *
  * @returns IQ_FAILED if it failed to add to the input queue. IQ_STOP if it the
  * queue should be stopped, and IQ_SEND_OK if it sent okay.
  */
 int
 octnet_send_nic_ctrl_pkt(struct octeon_device *oct,
-			 struct octnic_ctrl_pkt *nctrl,
-			 struct octnic_ctrl_params nparams);
+			 struct octnic_ctrl_pkt *nctrl);
 
 #endif
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index a2a24652c8f3..d32492f185ff 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -19,28 +19,17 @@
  * This file may also be available under a different license from Cavium.
  * Contact Cavium, Inc. for more information
  **********************************************************************/
-#include <linux/version.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
 #include <linux/pci.h>
-#include <linux/kthread.h>
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
-#include "octeon_config.h"
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
 #include "response_manager.h"
 #include "octeon_device.h"
-#include "octeon_nic.h"
 #include "octeon_main.h"
 #include "octeon_network.h"
-#include "cn66xx_regs.h"
 #include "cn66xx_device.h"
-#include "cn68xx_regs.h"
-#include "cn68xx_device.h"
-#include "liquidio_image.h"
 
 #define INCR_INSTRQUEUE_PKT_COUNT(octeon_dev_ptr, iq_no, field, count)  \
 	(octeon_dev_ptr->instr_queue[iq_no]->stats.field += count)
@@ -51,7 +40,7 @@ struct iq_post_status {
 };
 
 static void check_db_timeout(struct work_struct *work);
-static void  __check_db_timeout(struct octeon_device *oct, unsigned long iq_no);
+static void  __check_db_timeout(struct octeon_device *oct, u64 iq_no);
 
 static void (*reqtype_free_fn[MAX_OCTEON_DEVICES][REQTYPE_LAST + 1]) (void *);
 
@@ -69,12 +58,16 @@ static inline int IQ_INSTR_MODE_64B(struct octeon_device *oct, int iq_no)
 
 /* Return 0 on success, 1 on failure */
 int octeon_init_instr_queue(struct octeon_device *oct,
-			    u32 iq_no, u32 num_descs)
+			    union oct_txpciq txpciq,
+			    u32 num_descs)
 {
 	struct octeon_instr_queue *iq;
 	struct octeon_iq_config *conf = NULL;
+	u32 iq_no = (u32)txpciq.s.q_no;
 	u32 q_size;
 	struct cavium_wq *db_wq;
+	int orig_node = dev_to_node(&oct->pci_dev->dev);
+	int numa_node = cpu_to_node(iq_no % num_online_cpus());
 
 	if (OCTEON_CN6XXX(oct))
 		conf = &(CFG_GET_IQ_CFG(CHIP_FIELD(oct, cn6xxx, conf)));
@@ -95,9 +88,15 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 	q_size = (u32)conf->instr_type * num_descs;
 
 	iq = oct->instr_queue[iq_no];
+	iq->oct_dev = oct;
 
+	set_dev_node(&oct->pci_dev->dev, numa_node);
 	iq->base_addr = lio_dma_alloc(oct, q_size,
 				      (dma_addr_t *)&iq->base_addr_dma);
+	set_dev_node(&oct->pci_dev->dev, orig_node);
+	if (!iq->base_addr)
+		iq->base_addr = lio_dma_alloc(oct, q_size,
+					      (dma_addr_t *)&iq->base_addr_dma);
 	if (!iq->base_addr) {
 		dev_err(&oct->pci_dev->dev, "Cannot allocate memory for instr queue %d\n",
 			iq_no);
@@ -109,7 +108,11 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 	/* Initialize a list to holds requests that have been posted to Octeon
 	 * but has yet to be fetched by octeon
 	 */
-	iq->request_list = vmalloc(sizeof(*iq->request_list) * num_descs);
+	iq->request_list = vmalloc_node((sizeof(*iq->request_list) * num_descs),
+					       numa_node);
+	if (!iq->request_list)
+		iq->request_list = vmalloc(sizeof(*iq->request_list) *
+						  num_descs);
 	if (!iq->request_list) {
 		lio_dma_free(oct, q_size, iq->base_addr, iq->base_addr_dma);
 		dev_err(&oct->pci_dev->dev, "Alloc failed for IQ[%d] nr free list\n",
@@ -122,7 +125,7 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 	dev_dbg(&oct->pci_dev->dev, "IQ[%d]: base: %p basedma: %llx count: %d\n",
 		iq_no, iq->base_addr, iq->base_addr_dma, iq->max_count);
 
-	iq->iq_no = iq_no;
+	iq->txpciq.u64 = txpciq.u64;
 	iq->fill_threshold = (u32)conf->db_min;
 	iq->fill_cnt = 0;
 	iq->host_write_index = 0;
@@ -135,8 +138,11 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 
 	/* Initialize the spinlock for this instruction queue */
 	spin_lock_init(&iq->lock);
+	spin_lock_init(&iq->post_lock);
 
-	oct->io_qmask.iq |= (1 << iq_no);
+	spin_lock_init(&iq->iq_flush_running_lock);
+
+	oct->io_qmask.iq |= (1ULL << iq_no);
 
 	/* Set the 32B/64B mode for each input queue */
 	oct->io_qmask.iq64B |= ((conf->instr_type == 64) << iq_no);
@@ -144,7 +150,9 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 
 	oct->fn_list.setup_iq_regs(oct, iq_no);
 
-	oct->check_db_wq[iq_no].wq = create_workqueue("check_iq_db");
+	oct->check_db_wq[iq_no].wq = alloc_workqueue("check_iq_db",
+						     WQ_MEM_RECLAIM,
+						     0);
 	if (!oct->check_db_wq[iq_no].wq) {
 		lio_dma_free(oct, q_size, iq->base_addr, iq->base_addr_dma);
 		dev_err(&oct->pci_dev->dev, "check db wq create failed for iq %d\n",
@@ -168,7 +176,6 @@ int octeon_delete_instr_queue(struct octeon_device *oct, u32 iq_no)
 	struct octeon_instr_queue *iq = oct->instr_queue[iq_no];
 
 	cancel_delayed_work_sync(&oct->check_db_wq[iq_no].wk.work);
-	flush_workqueue(oct->check_db_wq[iq_no].wq);
 	destroy_workqueue(oct->check_db_wq[iq_no].wq);
 
 	if (OCTEON_CN6XXX(oct))
@@ -188,26 +195,38 @@ int octeon_delete_instr_queue(struct octeon_device *oct, u32 iq_no)
 
 /* Return 0 on success, 1 on failure */
 int octeon_setup_iq(struct octeon_device *oct,
-		    u32 iq_no,
+		    int ifidx,
+		    int q_index,
+		    union oct_txpciq txpciq,
 		    u32 num_descs,
 		    void *app_ctx)
 {
+	u32 iq_no = (u32)txpciq.s.q_no;
+	int numa_node = cpu_to_node(iq_no % num_online_cpus());
+
 	if (oct->instr_queue[iq_no]) {
 		dev_dbg(&oct->pci_dev->dev, "IQ is in use. Cannot create the IQ: %d again\n",
 			iq_no);
+		oct->instr_queue[iq_no]->txpciq.u64 = txpciq.u64;
 		oct->instr_queue[iq_no]->app_ctx = app_ctx;
 		return 0;
 	}
 	oct->instr_queue[iq_no] =
-	    vmalloc(sizeof(struct octeon_instr_queue));
+	    vmalloc_node(sizeof(struct octeon_instr_queue), numa_node);
+	if (!oct->instr_queue[iq_no])
+		oct->instr_queue[iq_no] =
+		    vmalloc(sizeof(struct octeon_instr_queue));
 	if (!oct->instr_queue[iq_no])
 		return 1;
 
 	memset(oct->instr_queue[iq_no], 0,
 	       sizeof(struct octeon_instr_queue));
 
+	oct->instr_queue[iq_no]->q_index = q_index;
 	oct->instr_queue[iq_no]->app_ctx = app_ctx;
-	if (octeon_init_instr_queue(oct, iq_no, num_descs)) {
+	oct->instr_queue[iq_no]->ifidx = ifidx;
+
+	if (octeon_init_instr_queue(oct, txpciq, num_descs)) {
 		vfree(oct->instr_queue[iq_no]);
 		oct->instr_queue[iq_no] = NULL;
 		return 1;
@@ -226,8 +245,8 @@ int lio_wait_for_instr_fetch(struct octeon_device *oct)
 		instr_cnt = 0;
 
 		/*for (i = 0; i < oct->num_iqs; i++) {*/
-		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
-			if (!(oct->io_qmask.iq & (1UL << i)))
+		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+			if (!(oct->io_qmask.iq & (1ULL << i)))
 				continue;
 			pending =
 			    atomic_read(&oct->
@@ -271,40 +290,8 @@ static inline void __copy_cmd_into_iq(struct octeon_instr_queue *iq,
 	memcpy(iqptr, cmd, cmdsize);
 }
 
-static inline int
-__post_command(struct octeon_device *octeon_dev __attribute__((unused)),
-	       struct octeon_instr_queue *iq,
-	       u32 force_db __attribute__((unused)), u8 *cmd)
-{
-	u32 index = -1;
-
-	/* This ensures that the read index does not wrap around to the same
-	 * position if queue gets full before Octeon could fetch any instr.
-	 */
-	if (atomic_read(&iq->instr_pending) >= (s32)(iq->max_count - 1))
-		return -1;
-
-	__copy_cmd_into_iq(iq, cmd);
-
-	/* "index" is returned, host_write_index is modified. */
-	index = iq->host_write_index;
-	INCR_INDEX_BY1(iq->host_write_index, iq->max_count);
-	iq->fill_cnt++;
-
-	/* Flush the command into memory. We need to be sure the data is in
-	 * memory before indicating that the instruction is pending.
-	 */
-	wmb();
-
-	atomic_inc(&iq->instr_pending);
-
-	return index;
-}
-
 static inline struct iq_post_status
-__post_command2(struct octeon_device *octeon_dev __attribute__((unused)),
-		struct octeon_instr_queue *iq,
-		u32 force_db __attribute__((unused)), u8 *cmd)
+__post_command2(struct octeon_instr_queue *iq, u8 *cmd)
 {
 	struct iq_post_status st;
 
@@ -362,17 +349,19 @@ __add_to_request_list(struct octeon_instr_queue *iq,
 	iq->request_list[idx].reqtype = reqtype;
 }
 
+/* Can only run in process context */
 int
 lio_process_iq_request_list(struct octeon_device *oct,
-			    struct octeon_instr_queue *iq)
+			    struct octeon_instr_queue *iq, u32 napi_budget)
 {
 	int reqtype;
 	void *buf;
 	u32 old = iq->flush_index;
 	u32 inst_count = 0;
-	unsigned pkts_compl = 0, bytes_compl = 0;
+	unsigned int pkts_compl = 0, bytes_compl = 0;
 	struct octeon_soft_command *sc;
 	struct octeon_instr_irh *irh;
+	unsigned long flags;
 
 	while (old != iq->octeon_read_index) {
 		reqtype = iq->request_list[old].reqtype;
@@ -394,7 +383,7 @@ lio_process_iq_request_list(struct octeon_device *oct,
 		case REQTYPE_SOFT_COMMAND:
 			sc = buf;
 
-			irh = (struct octeon_instr_irh *)&sc->cmd.irh;
+			irh = (struct octeon_instr_irh *)&sc->cmd.cmd2.irh;
 			if (irh->rflag) {
 				/* We're expecting a response from Octeon.
 				 * It's up to lio_process_ordered_list() to
@@ -402,17 +391,22 @@ lio_process_iq_request_list(struct octeon_device *oct,
 				 * command response list because we expect
 				 * a response from Octeon.
 				 */
-				spin_lock_bh(&oct->response_list
-					[OCTEON_ORDERED_SC_LIST].lock);
+				spin_lock_irqsave
+					(&oct->response_list
+					 [OCTEON_ORDERED_SC_LIST].lock,
+					 flags);
 				atomic_inc(&oct->response_list
 					[OCTEON_ORDERED_SC_LIST].
 					pending_req_count);
 				list_add_tail(&sc->node, &oct->response_list
 					[OCTEON_ORDERED_SC_LIST].head);
-				spin_unlock_bh(&oct->response_list
-					[OCTEON_ORDERED_SC_LIST].lock);
+				spin_unlock_irqrestore
+					(&oct->response_list
+					 [OCTEON_ORDERED_SC_LIST].lock,
+					 flags);
 			} else {
 				if (sc->callback) {
+					/* This callback must not sleep */
 					sc->callback(oct, OCTEON_REQUEST_DONE,
 						     sc->callback_arg);
 				}
@@ -430,6 +424,9 @@ lio_process_iq_request_list(struct octeon_device *oct,
  skip_this:
 		inst_count++;
 		INCR_INDEX_BY1(old, iq->max_count);
+
+		if ((napi_budget) && (inst_count >= napi_budget))
+			break;
 	}
 	if (bytes_compl)
 		octeon_report_tx_completion_to_bql(iq->app_ctx, pkts_compl,
@@ -439,38 +436,63 @@ lio_process_iq_request_list(struct octeon_device *oct,
 	return inst_count;
 }
 
-static inline void
-update_iq_indices(struct octeon_device *oct, struct octeon_instr_queue *iq)
+/* Can only be called from process context */
+int
+octeon_flush_iq(struct octeon_device *oct, struct octeon_instr_queue *iq,
+		u32 pending_thresh, u32 napi_budget)
 {
 	u32 inst_processed = 0;
+	u32 tot_inst_processed = 0;
+	int tx_done = 1;
 
-	/* Calculate how many commands Octeon has read and move the read index
-	 * accordingly.
-	 */
-	iq->octeon_read_index = oct->fn_list.update_iq_read_idx(oct, iq);
+	if (!spin_trylock(&iq->iq_flush_running_lock))
+		return tx_done;
 
-	/* Move the NORESPONSE requests to the per-device completion list. */
-	if (iq->flush_index != iq->octeon_read_index)
-		inst_processed = lio_process_iq_request_list(oct, iq);
+	spin_lock_bh(&iq->lock);
 
-	if (inst_processed) {
-		atomic_sub(inst_processed, &iq->instr_pending);
-		iq->stats.instr_processed += inst_processed;
-	}
-}
+	iq->octeon_read_index = oct->fn_list.update_iq_read_idx(iq);
 
-static void
-octeon_flush_iq(struct octeon_device *oct, struct octeon_instr_queue *iq,
-		u32 pending_thresh)
-{
 	if (atomic_read(&iq->instr_pending) >= (s32)pending_thresh) {
-		spin_lock_bh(&iq->lock);
-		update_iq_indices(oct, iq);
-		spin_unlock_bh(&iq->lock);
+		do {
+			/* Process any outstanding IQ packets. */
+			if (iq->flush_index == iq->octeon_read_index)
+				break;
+
+			if (napi_budget)
+				inst_processed = lio_process_iq_request_list
+					(oct, iq,
+					 napi_budget - tot_inst_processed);
+			else
+				inst_processed =
+					lio_process_iq_request_list(oct, iq, 0);
+
+			if (inst_processed) {
+				atomic_sub(inst_processed, &iq->instr_pending);
+				iq->stats.instr_processed += inst_processed;
+			}
+
+			tot_inst_processed += inst_processed;
+			inst_processed = 0;
+
+		} while (tot_inst_processed < napi_budget);
+
+		if (napi_budget && (tot_inst_processed >= napi_budget))
+			tx_done = 0;
 	}
+
+	iq->last_db_time = jiffies;
+
+	spin_unlock_bh(&iq->lock);
+
+	spin_unlock(&iq->iq_flush_running_lock);
+
+	return tx_done;
 }
 
-static void __check_db_timeout(struct octeon_device *oct, unsigned long iq_no)
+/* Process instruction queue after timeout.
+ * This routine gets called from a workqueue or when removing the module.
+ */
+static void __check_db_timeout(struct octeon_device *oct, u64 iq_no)
 {
 	struct octeon_instr_queue *iq;
 	u64 next_time;
@@ -481,24 +503,17 @@ static void __check_db_timeout(struct octeon_device *oct, unsigned long iq_no)
 	if (!iq)
 		return;
 
+	/* return immediately, if no work pending */
+	if (!atomic_read(&iq->instr_pending))
+		return;
 	/* If jiffies - last_db_time < db_timeout do nothing  */
 	next_time = iq->last_db_time + iq->db_timeout;
 	if (!time_after(jiffies, (unsigned long)next_time))
 		return;
 	iq->last_db_time = jiffies;
 
-	/* Get the lock and prevent tasklets. This routine gets called from
-	 * the poll thread. Instructions can now be posted in tasklet context
-	 */
-	spin_lock_bh(&iq->lock);
-	if (iq->fill_cnt != 0)
-		ring_doorbell(oct, iq);
-
-	spin_unlock_bh(&iq->lock);
-
 	/* Flush the instruction queue */
-	if (iq->do_auto_flush)
-		octeon_flush_iq(oct, iq, 1);
+	octeon_flush_iq(oct, iq, 1, 0);
 }
 
 /* Called by the Poll thread at regular intervals to check the instruction
@@ -508,11 +523,12 @@ static void check_db_timeout(struct work_struct *work)
 {
 	struct cavium_wk *wk = (struct cavium_wk *)work;
 	struct octeon_device *oct = (struct octeon_device *)wk->ctxptr;
-	unsigned long iq_no = wk->ctxul;
+	u64 iq_no = wk->ctxul;
 	struct cavium_wq *db_wq = &oct->check_db_wq[iq_no];
+	u32 delay = 10;
 
 	__check_db_timeout(oct, iq_no);
-	queue_delayed_work(db_wq->wq, &db_wq->wk.work, msecs_to_jiffies(1));
+	queue_delayed_work(db_wq->wq, &db_wq->wk.work, msecs_to_jiffies(delay));
 }
 
 int
@@ -523,9 +539,12 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no,
 	struct iq_post_status st;
 	struct octeon_instr_queue *iq = oct->instr_queue[iq_no];
 
-	spin_lock_bh(&iq->lock);
+	/* Get the lock and prevent other tasks and tx interrupt handler from
+	 * running.
+	 */
+	spin_lock_bh(&iq->post_lock);
 
-	st = __post_command2(oct, iq, force_db, cmd);
+	st = __post_command2(iq, cmd);
 
 	if (st.status != IQ_SEND_FAILED) {
 		octeon_report_sent_bytes_to_bql(buf, reqtype);
@@ -533,16 +552,19 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no,
 		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, bytes_sent, datasize);
 		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, instr_posted, 1);
 
-		if (iq->fill_cnt >= iq->fill_threshold || force_db)
+		if (force_db)
 			ring_doorbell(oct, iq);
 	} else {
 		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, instr_dropped, 1);
 	}
 
-	spin_unlock_bh(&iq->lock);
+	spin_unlock_bh(&iq->post_lock);
 
-	if (iq->do_auto_flush)
-		octeon_flush_iq(oct, iq, 2);
+	/* This is only done here to expedite packets being flushed
+	 * for cases where there are no IQ completion interrupts.
+	 */
+	/*if (iq->do_auto_flush)*/
+	/*	octeon_flush_iq(oct, iq, 2, 0);*/
 
 	return st.status;
 }
@@ -557,82 +579,75 @@ octeon_prepare_soft_command(struct octeon_device *oct,
 			    u64 ossp1)
 {
 	struct octeon_config *oct_cfg;
-	struct octeon_instr_ih *ih;
+	struct octeon_instr_ih2 *ih2;
 	struct octeon_instr_irh *irh;
 	struct octeon_instr_rdp *rdp;
 
-	BUG_ON(opcode > 15);
-	BUG_ON(subcode > 127);
+	WARN_ON(opcode > 15);
+	WARN_ON(subcode > 127);
 
 	oct_cfg = octeon_get_conf(oct);
 
-	ih          = (struct octeon_instr_ih *)&sc->cmd.ih;
-	ih->tagtype = ATOMIC_TAG;
-	ih->tag     = LIO_CONTROL;
-	ih->raw     = 1;
-	ih->grp     = CFG_GET_CTRL_Q_GRP(oct_cfg);
+	ih2          = (struct octeon_instr_ih2 *)&sc->cmd.cmd2.ih2;
+	ih2->tagtype = ATOMIC_TAG;
+	ih2->tag     = LIO_CONTROL;
+	ih2->raw     = 1;
+	ih2->grp     = CFG_GET_CTRL_Q_GRP(oct_cfg);
 
 	if (sc->datasize) {
-		ih->dlengsz = sc->datasize;
-		ih->rs = 1;
+		ih2->dlengsz = sc->datasize;
+		ih2->rs = 1;
 	}
 
-	irh            = (struct octeon_instr_irh *)&sc->cmd.irh;
+	irh            = (struct octeon_instr_irh *)&sc->cmd.cmd2.irh;
 	irh->opcode    = opcode;
 	irh->subcode   = subcode;
 
 	/* opcode/subcode specific parameters (ossp) */
 	irh->ossp       = irh_ossp;
-	sc->cmd.ossp[0] = ossp0;
-	sc->cmd.ossp[1] = ossp1;
+	sc->cmd.cmd2.ossp[0] = ossp0;
+	sc->cmd.cmd2.ossp[1] = ossp1;
 
 	if (sc->rdatasize) {
-		rdp            = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+		rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp;
 		rdp->pcie_port = oct->pcie_port;
 		rdp->rlen      = sc->rdatasize;
 
 		irh->rflag =  1;
-		irh->len   =  4;
-		ih->fsz    = 40; /* irh+ossp[0]+ossp[1]+rdp+rptr = 40 bytes */
+		ih2->fsz   = 40; /* irh+ossp[0]+ossp[1]+rdp+rptr = 40 bytes */
 	} else {
 		irh->rflag =  0;
-		irh->len   =  2;
-		ih->fsz    = 24; /* irh + ossp[0] + ossp[1] = 24 bytes */
+		ih2->fsz   = 24; /* irh + ossp[0] + ossp[1] = 24 bytes */
 	}
-
-	while (!(oct->io_qmask.iq & (1 << sc->iq_no)))
-		sc->iq_no++;
 }
 
 int octeon_send_soft_command(struct octeon_device *oct,
 			     struct octeon_soft_command *sc)
 {
-	struct octeon_instr_ih *ih;
+	struct octeon_instr_ih2 *ih2;
 	struct octeon_instr_irh *irh;
-	struct octeon_instr_rdp *rdp;
+	u32 len;
 
-	ih = (struct octeon_instr_ih *)&sc->cmd.ih;
-	if (ih->dlengsz) {
-		BUG_ON(!sc->dmadptr);
-		sc->cmd.dptr = sc->dmadptr;
+	ih2 = (struct octeon_instr_ih2 *)&sc->cmd.cmd2.ih2;
+	if (ih2->dlengsz) {
+		WARN_ON(!sc->dmadptr);
+		sc->cmd.cmd2.dptr = sc->dmadptr;
 	}
-
-	irh = (struct octeon_instr_irh *)&sc->cmd.irh;
+	irh = (struct octeon_instr_irh *)&sc->cmd.cmd2.irh;
 	if (irh->rflag) {
-		BUG_ON(!sc->dmarptr);
-		BUG_ON(!sc->status_word);
+		WARN_ON(!sc->dmarptr);
+		WARN_ON(!sc->status_word);
 		*sc->status_word = COMPLETION_WORD_INIT;
 
-		rdp = (struct octeon_instr_rdp *)&sc->cmd.rdp;
-
-		sc->cmd.rptr = sc->dmarptr;
+		sc->cmd.cmd2.rptr = sc->dmarptr;
 	}
+	len = (u32)ih2->dlengsz;
 
 	if (sc->wait_time)
 		sc->timeout = jiffies + sc->wait_time;
 
-	return octeon_send_command(oct, sc->iq_no, 1, &sc->cmd, sc,
-				   (u32)ih->dlengsz, REQTYPE_SOFT_COMMAND);
+	return (octeon_send_command(oct, sc->iq_no, 1, &sc->cmd, sc,
+				    len, REQTYPE_SOFT_COMMAND));
 }
 
 int octeon_setup_sc_buffer_pool(struct octeon_device *oct)
@@ -667,7 +682,7 @@ int octeon_free_sc_buffer_pool(struct octeon_device *oct)
 	struct list_head *tmp, *tmp2;
 	struct octeon_soft_command *sc;
 
-	spin_lock(&oct->sc_buf_pool.lock);
+	spin_lock_bh(&oct->sc_buf_pool.lock);
 
 	list_for_each_safe(tmp, tmp2, &oct->sc_buf_pool.head) {
 		list_del(tmp);
@@ -679,7 +694,7 @@ int octeon_free_sc_buffer_pool(struct octeon_device *oct)
 
 	INIT_LIST_HEAD(&oct->sc_buf_pool.head);
 
-	spin_unlock(&oct->sc_buf_pool.lock);
+	spin_unlock_bh(&oct->sc_buf_pool.lock);
 
 	return 0;
 }
@@ -695,13 +710,13 @@ struct octeon_soft_command *octeon_alloc_soft_command(struct octeon_device *oct,
 	struct octeon_soft_command *sc = NULL;
 	struct list_head *tmp;
 
-	BUG_ON((offset + datasize + rdatasize + ctxsize) >
+	WARN_ON((offset + datasize + rdatasize + ctxsize) >
 	       SOFT_COMMAND_BUFFER_SIZE);
 
-	spin_lock(&oct->sc_buf_pool.lock);
+	spin_lock_bh(&oct->sc_buf_pool.lock);
 
 	if (list_empty(&oct->sc_buf_pool.head)) {
-		spin_unlock(&oct->sc_buf_pool.lock);
+		spin_unlock_bh(&oct->sc_buf_pool.lock);
 		return NULL;
 	}
 
@@ -712,7 +727,7 @@ struct octeon_soft_command *octeon_alloc_soft_command(struct octeon_device *oct,
 
 	atomic_inc(&oct->sc_buf_pool.alloc_buf_count);
 
-	spin_unlock(&oct->sc_buf_pool.lock);
+	spin_unlock_bh(&oct->sc_buf_pool.lock);
 
 	sc = (struct octeon_soft_command *)tmp;
 
@@ -742,7 +757,7 @@ struct octeon_soft_command *octeon_alloc_soft_command(struct octeon_device *oct,
 	offset = (offset + datasize + 127) & 0xffffff80;
 
 	if (rdatasize) {
-		BUG_ON(rdatasize < 16);
+		WARN_ON(rdatasize < 16);
 		sc->virtrptr = (u8 *)sc + offset;
 		sc->dmarptr = dma_addr + offset;
 		sc->rdatasize = rdatasize;
@@ -755,11 +770,11 @@ struct octeon_soft_command *octeon_alloc_soft_command(struct octeon_device *oct,
 void octeon_free_soft_command(struct octeon_device *oct,
 			      struct octeon_soft_command *sc)
 {
-	spin_lock(&oct->sc_buf_pool.lock);
+	spin_lock_bh(&oct->sc_buf_pool.lock);
 
 	list_add_tail(&sc->node, &oct->sc_buf_pool.head);
 
 	atomic_dec(&oct->sc_buf_pool.alloc_buf_count);
 
-	spin_unlock(&oct->sc_buf_pool.lock);
+	spin_unlock_bh(&oct->sc_buf_pool.lock);
 }
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c
index 091f537a946e..709049e36627 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c
@@ -19,28 +19,14 @@
  * This file may also be available under a different license from Cavium.
  * Contact Cavium, Inc. for more information
  **********************************************************************/
-#include <linux/version.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
 #include <linux/pci.h>
-#include <linux/kthread.h>
 #include <linux/netdevice.h>
-#include "octeon_config.h"
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
 #include "response_manager.h"
 #include "octeon_device.h"
-#include "octeon_nic.h"
 #include "octeon_main.h"
-#include "octeon_network.h"
-#include "cn66xx_regs.h"
-#include "cn66xx_device.h"
-#include "cn68xx_regs.h"
-#include "cn68xx_device.h"
-#include "liquidio_image.h"
 
 static void oct_poll_req_completion(struct work_struct *work);
 
@@ -54,8 +40,9 @@ int octeon_setup_response_list(struct octeon_device *oct)
 		spin_lock_init(&oct->response_list[i].lock);
 		atomic_set(&oct->response_list[i].pending_req_count, 0);
 	}
+	spin_lock_init(&oct->cmd_resp_wqlock);
 
-	oct->dma_comp_wq.wq = create_workqueue("dma-comp");
+	oct->dma_comp_wq.wq = alloc_workqueue("dma-comp", WQ_MEM_RECLAIM, 0);
 	if (!oct->dma_comp_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "failed to create wq thread\n");
 		return -ENOMEM;
@@ -64,7 +51,8 @@ int octeon_setup_response_list(struct octeon_device *oct)
 	cwq = &oct->dma_comp_wq;
 	INIT_DELAYED_WORK(&cwq->wk.work, oct_poll_req_completion);
 	cwq->wk.ctxptr = oct;
-	queue_delayed_work(cwq->wq, &cwq->wk.work, msecs_to_jiffies(100));
+	oct->cmd_resp_state = OCT_DRV_ONLINE;
+	queue_delayed_work(cwq->wq, &cwq->wk.work, msecs_to_jiffies(50));
 
 	return ret;
 }
@@ -72,7 +60,6 @@ int octeon_setup_response_list(struct octeon_device *oct)
 void octeon_delete_response_list(struct octeon_device *oct)
 {
 	cancel_delayed_work_sync(&oct->dma_comp_wq.wk.work);
-	flush_workqueue(oct->dma_comp_wq.wq);
 	destroy_workqueue(oct->dma_comp_wq.wq);
 }
 
@@ -86,6 +73,7 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev,
 	u32 status;
 	u64 status64;
 	struct octeon_instr_rdp *rdp;
+	u64 rptr;
 
 	ordered_sc_list = &octeon_dev->response_list[OCTEON_ORDERED_SC_LIST];
 
@@ -103,7 +91,8 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev,
 
 		sc = (struct octeon_soft_command *)ordered_sc_list->
 		    head.next;
-		rdp = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+		rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp;
+		rptr = sc->cmd.cmd2.rptr;
 
 		status = OCTEON_REQUEST_PENDING;
 
@@ -111,7 +100,7 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev,
 		 * to where rptr is pointing to
 		 */
 		dma_sync_single_for_cpu(&octeon_dev->pci_dev->dev,
-					sc->cmd.rptr, rdp->rlen,
+					rptr, rdp->rlen,
 					DMA_FROM_DEVICE);
 		status64 = *sc->status_word;
 
@@ -173,6 +162,5 @@ static void oct_poll_req_completion(struct work_struct *work)
 	struct cavium_wq *cwq = &oct->dma_comp_wq;
 
 	lio_process_ordered_list(oct, 0);
-
-	queue_delayed_work(cwq->wq, &cwq->wk.work, msecs_to_jiffies(100));
+	queue_delayed_work(cwq->wq, &cwq->wk.work, msecs_to_jiffies(50));
 }
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 388cd799d9ed..e8bc15bcde70 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -146,7 +146,6 @@ struct octeon_mgmt {
 	struct device *dev;
 	struct napi_struct napi;
 	struct tasklet_struct tx_clean_tasklet;
-	struct phy_device *phydev;
 	struct device_node *phy_np;
 	resource_size_t mix_phys;
 	resource_size_t mix_size;
@@ -787,14 +786,12 @@ static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev,
 static int octeon_mgmt_ioctl(struct net_device *netdev,
 			     struct ifreq *rq, int cmd)
 {
-	struct octeon_mgmt *p = netdev_priv(netdev);
-
 	switch (cmd) {
 	case SIOCSHWTSTAMP:
 		return octeon_mgmt_ioctl_hwtstamp(netdev, rq, cmd);
 	default:
-		if (p->phydev)
-			return phy_mii_ioctl(p->phydev, rq, cmd);
+		if (netdev->phydev)
+			return phy_mii_ioctl(netdev->phydev, rq, cmd);
 		return -EINVAL;
 	}
 }
@@ -836,16 +833,18 @@ static void octeon_mgmt_enable_link(struct octeon_mgmt *p)
 
 static void octeon_mgmt_update_link(struct octeon_mgmt *p)
 {
+	struct net_device *ndev = p->netdev;
+	struct phy_device *phydev = ndev->phydev;
 	union cvmx_agl_gmx_prtx_cfg prtx_cfg;
 
 	prtx_cfg.u64 = cvmx_read_csr(p->agl + AGL_GMX_PRT_CFG);
 
-	if (!p->phydev->link)
+	if (!phydev->link)
 		prtx_cfg.s.duplex = 1;
 	else
-		prtx_cfg.s.duplex = p->phydev->duplex;
+		prtx_cfg.s.duplex = phydev->duplex;
 
-	switch (p->phydev->speed) {
+	switch (phydev->speed) {
 	case 10:
 		prtx_cfg.s.speed = 0;
 		prtx_cfg.s.slottime = 0;
@@ -871,7 +870,7 @@ static void octeon_mgmt_update_link(struct octeon_mgmt *p)
 			prtx_cfg.s.speed_msb = 0;
 			/* Only matters for half-duplex */
 			prtx_cfg.s.slottime = 1;
-			prtx_cfg.s.burst = p->phydev->duplex;
+			prtx_cfg.s.burst = phydev->duplex;
 		}
 		break;
 	case 0:  /* No link */
@@ -894,9 +893,9 @@ static void octeon_mgmt_update_link(struct octeon_mgmt *p)
 		/* MII (both speeds) and RGMII 1000 speed. */
 		agl_clk.s.clk_cnt = 1;
 		if (prtx_ctl.s.mode == 0) { /* RGMII mode */
-			if (p->phydev->speed == 10)
+			if (phydev->speed == 10)
 				agl_clk.s.clk_cnt = 50;
-			else if (p->phydev->speed == 100)
+			else if (phydev->speed == 100)
 				agl_clk.s.clk_cnt = 5;
 		}
 		cvmx_write_csr(p->agl + AGL_GMX_TX_CLK, agl_clk.u64);
@@ -906,39 +905,40 @@ static void octeon_mgmt_update_link(struct octeon_mgmt *p)
 static void octeon_mgmt_adjust_link(struct net_device *netdev)
 {
 	struct octeon_mgmt *p = netdev_priv(netdev);
+	struct phy_device *phydev = netdev->phydev;
 	unsigned long flags;
 	int link_changed = 0;
 
-	if (!p->phydev)
+	if (!phydev)
 		return;
 
 	spin_lock_irqsave(&p->lock, flags);
 
 
-	if (!p->phydev->link && p->last_link)
+	if (!phydev->link && p->last_link)
 		link_changed = -1;
 
-	if (p->phydev->link
-	    && (p->last_duplex != p->phydev->duplex
-		|| p->last_link != p->phydev->link
-		|| p->last_speed != p->phydev->speed)) {
+	if (phydev->link &&
+	    (p->last_duplex != phydev->duplex ||
+	     p->last_link != phydev->link ||
+	     p->last_speed != phydev->speed)) {
 		octeon_mgmt_disable_link(p);
 		link_changed = 1;
 		octeon_mgmt_update_link(p);
 		octeon_mgmt_enable_link(p);
 	}
 
-	p->last_link = p->phydev->link;
-	p->last_speed = p->phydev->speed;
-	p->last_duplex = p->phydev->duplex;
+	p->last_link = phydev->link;
+	p->last_speed = phydev->speed;
+	p->last_duplex = phydev->duplex;
 
 	spin_unlock_irqrestore(&p->lock, flags);
 
 	if (link_changed != 0) {
 		if (link_changed > 0) {
 			pr_info("%s: Link is up - %d/%s\n", netdev->name,
-				p->phydev->speed,
-				DUPLEX_FULL == p->phydev->duplex ?
+				phydev->speed,
+				phydev->duplex == DUPLEX_FULL ?
 				"Full" : "Half");
 		} else {
 			pr_info("%s: Link is down\n", netdev->name);
@@ -949,6 +949,7 @@ static void octeon_mgmt_adjust_link(struct net_device *netdev)
 static int octeon_mgmt_init_phy(struct net_device *netdev)
 {
 	struct octeon_mgmt *p = netdev_priv(netdev);
+	struct phy_device *phydev = NULL;
 
 	if (octeon_is_simulation() || p->phy_np == NULL) {
 		/* No PHYs in the simulator. */
@@ -956,11 +957,11 @@ static int octeon_mgmt_init_phy(struct net_device *netdev)
 		return 0;
 	}
 
-	p->phydev = of_phy_connect(netdev, p->phy_np,
-				   octeon_mgmt_adjust_link, 0,
-				   PHY_INTERFACE_MODE_MII);
+	phydev = of_phy_connect(netdev, p->phy_np,
+				octeon_mgmt_adjust_link, 0,
+				PHY_INTERFACE_MODE_MII);
 
-	if (!p->phydev)
+	if (!phydev)
 		return -ENODEV;
 
 	return 0;
@@ -1080,9 +1081,9 @@ static int octeon_mgmt_open(struct net_device *netdev)
 	}
 
 	/* Set the mode of the interface, RGMII/MII. */
-	if (OCTEON_IS_MODEL(OCTEON_CN6XXX) && p->phydev) {
+	if (OCTEON_IS_MODEL(OCTEON_CN6XXX) && netdev->phydev) {
 		union cvmx_agl_prtx_ctl agl_prtx_ctl;
-		int rgmii_mode = (p->phydev->supported &
+		int rgmii_mode = (netdev->phydev->supported &
 				  (SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full)) != 0;
 
 		agl_prtx_ctl.u64 = cvmx_read_csr(p->agl_prt_ctl);
@@ -1205,7 +1206,7 @@ static int octeon_mgmt_open(struct net_device *netdev)
 
 	/* Configure the port duplex, speed and enables */
 	octeon_mgmt_disable_link(p);
-	if (p->phydev)
+	if (netdev->phydev)
 		octeon_mgmt_update_link(p);
 	octeon_mgmt_enable_link(p);
 
@@ -1214,9 +1215,9 @@ static int octeon_mgmt_open(struct net_device *netdev)
 	/* PHY is not present in simulator. The carrier is enabled
 	 * while initializing the phy for simulator, leave it enabled.
 	 */
-	if (p->phydev) {
+	if (netdev->phydev) {
 		netif_carrier_off(netdev);
-		phy_start_aneg(p->phydev);
+		phy_start_aneg(netdev->phydev);
 	}
 
 	netif_wake_queue(netdev);
@@ -1244,9 +1245,8 @@ static int octeon_mgmt_stop(struct net_device *netdev)
 	napi_disable(&p->napi);
 	netif_stop_queue(netdev);
 
-	if (p->phydev)
-		phy_disconnect(p->phydev);
-	p->phydev = NULL;
+	if (netdev->phydev)
+		phy_disconnect(netdev->phydev);
 
 	netif_carrier_off(netdev);
 
@@ -1346,50 +1346,23 @@ static void octeon_mgmt_get_drvinfo(struct net_device *netdev,
 	strlcpy(info->bus_info, "N/A", sizeof(info->bus_info));
 }
 
-static int octeon_mgmt_get_settings(struct net_device *netdev,
-				    struct ethtool_cmd *cmd)
-{
-	struct octeon_mgmt *p = netdev_priv(netdev);
-
-	if (p->phydev)
-		return phy_ethtool_gset(p->phydev, cmd);
-
-	return -EOPNOTSUPP;
-}
-
-static int octeon_mgmt_set_settings(struct net_device *netdev,
-				    struct ethtool_cmd *cmd)
-{
-	struct octeon_mgmt *p = netdev_priv(netdev);
-
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	if (p->phydev)
-		return phy_ethtool_sset(p->phydev, cmd);
-
-	return -EOPNOTSUPP;
-}
-
 static int octeon_mgmt_nway_reset(struct net_device *dev)
 {
-	struct octeon_mgmt *p = netdev_priv(dev);
-
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (p->phydev)
-		return phy_start_aneg(p->phydev);
+	if (dev->phydev)
+		return phy_start_aneg(dev->phydev);
 
 	return -EOPNOTSUPP;
 }
 
 static const struct ethtool_ops octeon_mgmt_ethtool_ops = {
 	.get_drvinfo = octeon_mgmt_get_drvinfo,
-	.get_settings = octeon_mgmt_get_settings,
-	.set_settings = octeon_mgmt_set_settings,
 	.nway_reset = octeon_mgmt_nway_reset,
 	.get_link = ethtool_op_get_link,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 static const struct net_device_ops octeon_mgmt_ops = {
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 95f17f8cadac..16ed20357c5c 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -499,6 +499,7 @@ static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic,
 	u32 rr_quantum;
 	u8 sq_idx = sq->sq_num;
 	u8 pqs_vnic;
+	int svf;
 
 	if (sq->sqs_mode)
 		pqs_vnic = nic->pqs_vf[vnic];
@@ -511,10 +512,19 @@ static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic,
 	/* 24 bytes for FCS, IPG and preamble */
 	rr_quantum = ((NIC_HW_MAX_FRS + 24) / 4);
 
-	tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX);
+	if (!sq->sqs_mode) {
+		tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX);
+	} else {
+		for (svf = 0; svf < MAX_SQS_PER_VF; svf++) {
+			if (nic->vf_sqs[pqs_vnic][svf] == vnic)
+				break;
+		}
+		tl4 = (MAX_LMAC_PER_BGX * NIC_TL4_PER_LMAC);
+		tl4 += (lmac * NIC_TL4_PER_LMAC * MAX_SQS_PER_VF);
+		tl4 += (svf * NIC_TL4_PER_LMAC);
+		tl4 += (bgx * NIC_TL4_PER_BGX);
+	}
 	tl4 += sq_idx;
-	if (sq->sqs_mode)
-		tl4 += vnic * 8;
 
 	tl3 = tl4 / (NIC_MAX_TL4 / NIC_MAX_TL3);
 	nic_reg_write(nic, NIC_PF_QSET_0_127_SQ_0_7_CFG2 |
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 3ed21988626b..63a39ac97d53 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -551,7 +551,9 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 	}
 
 	/* Clear rcvflt bit (latching high) and read it back */
-	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
+	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT)
+		bgx_reg_modify(bgx, lmacid,
+			       BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
 	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
 		dev_err(&bgx->pdev->dev, "Receive fault, retry training\n");
 		if (bgx->use_training) {
@@ -570,13 +572,6 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 		return -1;
 	}
 
-	/* Wait for MAC RX to be ready */
-	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_RX_CTL,
-			 SMU_RX_CTL_STATUS, true)) {
-		dev_err(&bgx->pdev->dev, "SMU RX link not okay\n");
-		return -1;
-	}
-
 	/* Wait for BGX RX to be idle */
 	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_CTL, SMU_CTL_RX_IDLE, false)) {
 		dev_err(&bgx->pdev->dev, "SMU RX not idle\n");
@@ -589,29 +584,30 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 		return -1;
 	}
 
-	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
-		dev_err(&bgx->pdev->dev, "Receive fault\n");
-		return -1;
-	}
-
-	/* Receive link is latching low. Force it high and verify it */
-	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK);
-	if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_STATUS1,
-			 SPU_STATUS1_RCV_LNK, false)) {
-		dev_err(&bgx->pdev->dev, "SPU receive link down\n");
-		return -1;
-	}
-
+	/* Clear receive packet disable */
 	cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_MISC_CONTROL);
 	cfg &= ~SPU_MISC_CTL_RX_DIS;
 	bgx_reg_write(bgx, lmacid, BGX_SPUX_MISC_CONTROL, cfg);
-	return 0;
+
+	/* Check for MAC RX faults */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_RX_CTL);
+	/* 0 - Link is okay, 1 - Local fault, 2 - Remote fault */
+	cfg &= SMU_RX_CTL_STATUS;
+	if (!cfg)
+		return 0;
+
+	/* Rx local/remote fault seen.
+	 * Do lmac reinit to see if condition recovers
+	 */
+	bgx_lmac_xaui_init(bgx, lmacid, bgx->lmac_type);
+
+	return -1;
 }
 
 static void bgx_poll_for_link(struct work_struct *work)
 {
 	struct lmac *lmac;
-	u64 link;
+	u64 spu_link, smu_link;
 
 	lmac = container_of(work, struct lmac, dwork.work);
 
@@ -621,8 +617,11 @@ static void bgx_poll_for_link(struct work_struct *work)
 	bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1,
 		     SPU_STATUS1_RCV_LNK, false);
 
-	link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
-	if (link & SPU_STATUS1_RCV_LNK) {
+	spu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
+	smu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SMUX_RX_CTL);
+
+	if ((spu_link & SPU_STATUS1_RCV_LNK) &&
+	    !(smu_link & SMU_RX_CTL_STATUS)) {
 		lmac->link_up = 1;
 		if (lmac->bgx->lmac_type == BGX_MODE_XLAUI)
 			lmac->last_speed = 40000;
@@ -636,9 +635,15 @@ static void bgx_poll_for_link(struct work_struct *work)
 	}
 
 	if (lmac->last_link != lmac->link_up) {
+		if (lmac->link_up) {
+			if (bgx_xaui_check_link(lmac)) {
+				/* Errors, clear link_up state */
+				lmac->link_up = 0;
+				lmac->last_speed = SPEED_UNKNOWN;
+				lmac->last_duplex = DUPLEX_UNKNOWN;
+			}
+		}
 		lmac->last_link = lmac->link_up;
-		if (lmac->link_up)
-			bgx_xaui_check_link(lmac);
 	}
 
 	queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 2);
@@ -710,7 +715,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 {
 	struct lmac *lmac;
-	u64 cmrx_cfg;
+	u64 cfg;
 
 	lmac = &bgx->lmac[lmacid];
 	if (lmac->check_link) {
@@ -719,9 +724,33 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 		destroy_workqueue(lmac->check_link);
 	}
 
-	cmrx_cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
-	cmrx_cfg &= ~(1 << 15);
-	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
+	/* Disable packet reception */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_PKT_RX_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+	/* Give chance for Rx/Tx FIFO to get drained */
+	bgx_poll_reg(bgx, lmacid, BGX_CMRX_RX_FIFO_LEN, (u64)0x1FFF, true);
+	bgx_poll_reg(bgx, lmacid, BGX_CMRX_TX_FIFO_LEN, (u64)0x3FFF, true);
+
+	/* Disable packet transmission */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_PKT_TX_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+	/* Disable serdes lanes */
+        if (!lmac->is_sgmii)
+                bgx_reg_modify(bgx, lmacid,
+                               BGX_SPUX_CONTROL1, SPU_CTL_LOW_POWER);
+        else
+                bgx_reg_modify(bgx, lmacid,
+                               BGX_GMP_PCS_MRX_CTL, PCS_MRX_CTL_PWR_DN);
+
+	/* Disable LMAC */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
 	bgx_flush_dmac_addrs(bgx, lmacid);
 
 	if ((bgx->lmac_type != BGX_MODE_XFI) &&
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 149e179363a1..42010d2e5ddf 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -41,6 +41,7 @@
 #define BGX_CMRX_RX_STAT10		0xC0
 #define BGX_CMRX_RX_BP_DROP		0xC8
 #define BGX_CMRX_RX_DMAC_CTL		0x0E8
+#define BGX_CMRX_RX_FIFO_LEN		0x108
 #define BGX_CMR_RX_DMACX_CAM		0x200
 #define  RX_DMACX_CAM_EN			BIT_ULL(48)
 #define  RX_DMACX_CAM_LMACID(x)			(x << 49)
@@ -50,6 +51,7 @@
 #define BGX_CMR_CHAN_MSK_AND		0x450
 #define BGX_CMR_BIST_STATUS		0x460
 #define BGX_CMR_RX_LMACS		0x468
+#define BGX_CMRX_TX_FIFO_LEN		0x518
 #define BGX_CMRX_TX_STAT0		0x600
 #define BGX_CMRX_TX_STAT1		0x608
 #define BGX_CMRX_TX_STAT2		0x610
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 477db477b133..c45de49dc963 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -64,6 +64,7 @@
 #include <net/bonding.h>
 #include <net/addrconf.h>
 #include <asm/uaccess.h>
+#include <linux/crash_dump.h>
 
 #include "cxgb4.h"
 #include "t4_regs.h"
@@ -206,7 +207,7 @@ static int rx_dma_offset = 2;
 static unsigned int num_vf[NUM_OF_PF_WITH_SRIOV];
 
 module_param_array(num_vf, uint, NULL, 0644);
-MODULE_PARM_DESC(num_vf, "number of VFs for each of PFs 0-3");
+MODULE_PARM_DESC(num_vf, "number of VFs for each of PFs 0-3, deprecated parameter - please use the pci sysfs interface.");
 #endif
 
 /* TX Queue select used to determine what algorithm to use for selecting TX
@@ -460,11 +461,8 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok)
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
 
-	if (!(dev->flags & IFF_PROMISC)) {
-		__dev_uc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
-		if (!(dev->flags & IFF_ALLMULTI))
-			__dev_mc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
-	}
+	__dev_uc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
+	__dev_mc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
 
 	return t4_set_rxmode(adapter, adapter->mbox, pi->viid, mtu,
 			     (dev->flags & IFF_PROMISC) ? 1 : 0,
@@ -3735,7 +3733,8 @@ static int adap_init0(struct adapter *adap)
 		return ret;
 
 	/* Contact FW, advertising Master capability */
-	ret = t4_fw_hello(adap, adap->mbox, adap->mbox, MASTER_MAY, &state);
+	ret = t4_fw_hello(adap, adap->mbox, adap->mbox,
+			  is_kdump_kernel() ? MASTER_MUST : MASTER_MAY, &state);
 	if (ret < 0) {
 		dev_err(adap->pdev_dev, "could not connect to FW, error %d\n",
 			ret);
@@ -4366,6 +4365,11 @@ static void cfg_queues(struct adapter *adap)
 	if (q10g > netif_get_num_default_rss_queues())
 		q10g = netif_get_num_default_rss_queues();
 
+	/* Reduce memory usage in kdump environment, disable all offload.
+	 */
+	if (is_kdump_kernel())
+		adap->params.offload = 0;
+
 	for_each_port(adap, i) {
 		struct port_info *pi = adap2pinfo(adap, i);
 
@@ -4829,6 +4833,60 @@ static int get_chip_type(struct pci_dev *pdev, u32 pl_rev)
 	return -EINVAL;
 }
 
+#ifdef CONFIG_PCI_IOV
+static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	int err = 0;
+	int current_vfs = pci_num_vf(pdev);
+	u32 pcie_fw;
+	void __iomem *regs;
+
+	regs = pci_ioremap_bar(pdev, 0);
+	if (!regs) {
+		dev_err(&pdev->dev, "cannot map device registers\n");
+		return -ENOMEM;
+	}
+
+	pcie_fw = readl(regs + PCIE_FW_A);
+	iounmap(regs);
+	/* Check if cxgb4 is the MASTER and fw is initialized */
+	if (!(pcie_fw & PCIE_FW_INIT_F) ||
+	    !(pcie_fw & PCIE_FW_MASTER_VLD_F) ||
+	    PCIE_FW_MASTER_G(pcie_fw) != 4) {
+		dev_warn(&pdev->dev,
+			 "cxgb4 driver needs to be MASTER to support SRIOV\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* If any of the VF's is already assigned to Guest OS, then
+	 * SRIOV for the same cannot be modified
+	 */
+	if (current_vfs && pci_vfs_assigned(pdev)) {
+		dev_err(&pdev->dev,
+			"Cannot modify SR-IOV while VFs are assigned\n");
+		num_vfs = current_vfs;
+		return num_vfs;
+	}
+
+	/* Disable SRIOV when zero is passed.
+	 * One needs to disable SRIOV before modifying it, else
+	 * stack throws the below warning:
+	 * " 'n' VFs already enabled. Disable before enabling 'm' VFs."
+	 */
+	if (!num_vfs) {
+		pci_disable_sriov(pdev);
+		return num_vfs;
+	}
+
+	if (num_vfs != current_vfs) {
+		err = pci_enable_sriov(pdev, num_vfs);
+		if (err)
+			return err;
+	}
+	return num_vfs;
+}
+#endif
+
 static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int func, i, err, s_qpp, qpp, num_seg;
@@ -5162,11 +5220,16 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 sriov:
 #ifdef CONFIG_PCI_IOV
-	if (func < ARRAY_SIZE(num_vf) && num_vf[func] > 0)
+	if (func < ARRAY_SIZE(num_vf) && num_vf[func] > 0) {
+		dev_warn(&pdev->dev,
+			 "Enabling SR-IOV VFs using the num_vf module "
+			 "parameter is deprecated - please use the pci sysfs "
+			 "interface instead.\n");
 		if (pci_enable_sriov(pdev, num_vf[func]) == 0)
 			dev_info(&pdev->dev,
 				 "instantiated %u virtual functions\n",
 				 num_vf[func]);
+	}
 #endif
 	return 0;
 
@@ -5259,6 +5322,9 @@ static struct pci_driver cxgb4_driver = {
 	.probe    = init_one,
 	.remove   = remove_one,
 	.shutdown = remove_one,
+#ifdef CONFIG_PCI_IOV
+	.sriov_configure = cxgb4_iov_configure,
+#endif
 	.err_handler = &cxgb4_eeh,
 };
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index a2cdfc1261dc..50812a1d67bd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -144,6 +144,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x5015),	/* T502-bt */
 	CH_PCI_ID_TABLE_FENTRY(0x5016),	/* T580-OCP-SO */
 	CH_PCI_ID_TABLE_FENTRY(0x5017),	/* T520-OCP-SO */
+	CH_PCI_ID_TABLE_FENTRY(0x5018),	/* T540-BT */
 	CH_PCI_ID_TABLE_FENTRY(0x5080),	/* Custom T540-cr */
 	CH_PCI_ID_TABLE_FENTRY(0x5081),	/* Custom T540-LL-cr */
 	CH_PCI_ID_TABLE_FENTRY(0x5082),	/* Custom T504-cr */
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h
index 734dd776c22f..109bc630408b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h
@@ -353,6 +353,10 @@ struct hash_mac_addr {
 	u8 addr[ETH_ALEN];
 };
 
+struct mbox_list {
+	struct list_head list;
+};
+
 /*
  * Per-"adapter" (Virtual Function) information.
  */
@@ -387,6 +391,10 @@ struct adapter {
 	/* various locks */
 	spinlock_t stats_lock;
 
+	/* lock for mailbox cmd list */
+	spinlock_t mbox_lock;
+	struct mbox_list mlist;
+
 	/* support for mailbox command/reply logging */
 #define T4VF_OS_LOG_MBOX_CMDS 256
 	struct mbox_cmd_log *mbox_log;
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 04fc6f6d1e25..9f5526478d2f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -937,12 +937,8 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok)
 {
 	struct port_info *pi = netdev_priv(dev);
 
-	if (!(dev->flags & IFF_PROMISC)) {
-		__dev_uc_sync(dev, cxgb4vf_mac_sync, cxgb4vf_mac_unsync);
-		if (!(dev->flags & IFF_ALLMULTI))
-			__dev_mc_sync(dev, cxgb4vf_mac_sync,
-				      cxgb4vf_mac_unsync);
-	}
+	__dev_uc_sync(dev, cxgb4vf_mac_sync, cxgb4vf_mac_unsync);
+	__dev_mc_sync(dev, cxgb4vf_mac_sync, cxgb4vf_mac_unsync);
 	return t4vf_set_rxmode(pi->adapter, pi->viid, -1,
 			       (dev->flags & IFF_PROMISC) != 0,
 			       (dev->flags & IFF_ALLMULTI) != 0,
@@ -2778,6 +2774,8 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	 * Initialize SMP data synchronization resources.
 	 */
 	spin_lock_init(&adapter->stats_lock);
+	spin_lock_init(&adapter->mbox_lock);
+	INIT_LIST_HEAD(&adapter->mlist.list);
 
 	/*
 	 * Map our I/O registers in BAR0.
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index 955ff7c61f1b..61bfe86da86d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -139,6 +139,7 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
 	u32 mbox_ctl = T4VF_CIM_BASE_ADDR + CIM_VF_EXT_MAILBOX_CTRL;
 	u32 cmd_op = FW_CMD_OP_G(be32_to_cpu(((struct fw_cmd_hdr *)cmd)->hi));
 	__be64 cmd_rpl[MBOX_LEN / 8];
+	struct mbox_list entry;
 
 	/* In T6, mailbox size is changed to 128 bytes to avoid
 	 * invalidating the entire prefetch buffer.
@@ -156,6 +157,51 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
 	    size > NUM_CIM_VF_MAILBOX_DATA_INSTANCES * 4)
 		return -EINVAL;
 
+	/* Queue ourselves onto the mailbox access list.  When our entry is at
+	 * the front of the list, we have rights to access the mailbox.  So we
+	 * wait [for a while] till we're at the front [or bail out with an
+	 * EBUSY] ...
+	 */
+	spin_lock(&adapter->mbox_lock);
+	list_add_tail(&entry.list, &adapter->mlist.list);
+	spin_unlock(&adapter->mbox_lock);
+
+	delay_idx = 0;
+	ms = delay[0];
+
+	for (i = 0; ; i += ms) {
+		/* If we've waited too long, return a busy indication.  This
+		 * really ought to be based on our initial position in the
+		 * mailbox access list but this is a start.  We very rearely
+		 * contend on access to the mailbox ...
+		 */
+		if (i > FW_CMD_MAX_TIMEOUT) {
+			spin_lock(&adapter->mbox_lock);
+			list_del(&entry.list);
+			spin_unlock(&adapter->mbox_lock);
+			ret = -EBUSY;
+			t4vf_record_mbox(adapter, cmd, size, access, ret);
+			return ret;
+		}
+
+		/* If we're at the head, break out and start the mailbox
+		 * protocol.
+		 */
+		if (list_first_entry(&adapter->mlist.list, struct mbox_list,
+				     list) == &entry)
+			break;
+
+		/* Delay for a bit before checking again ... */
+		if (sleep_ok) {
+			ms = delay[delay_idx];  /* last element may repeat */
+			if (delay_idx < ARRAY_SIZE(delay) - 1)
+				delay_idx++;
+			msleep(ms);
+		} else {
+			mdelay(ms);
+		}
+	}
+
 	/*
 	 * Loop trying to get ownership of the mailbox.  Return an error
 	 * if we can't gain ownership.
@@ -164,6 +210,9 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
 	for (i = 0; v == MBOX_OWNER_NONE && i < 3; i++)
 		v = MBOWNER_G(t4_read_reg(adapter, mbox_ctl));
 	if (v != MBOX_OWNER_DRV) {
+		spin_lock(&adapter->mbox_lock);
+		list_del(&entry.list);
+		spin_unlock(&adapter->mbox_lock);
 		ret = (v == MBOX_OWNER_FW) ? -EBUSY : -ETIMEDOUT;
 		t4vf_record_mbox(adapter, cmd, size, access, ret);
 		return ret;
@@ -248,6 +297,9 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
 			if (cmd_op != FW_VI_STATS_CMD)
 				t4vf_record_mbox(adapter, cmd_rpl, size, access,
 						 execute);
+			spin_lock(&adapter->mbox_lock);
+			list_del(&entry.list);
+			spin_unlock(&adapter->mbox_lock);
 			return -FW_CMD_RETVAL_G(v);
 		}
 	}
@@ -255,6 +307,9 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
 	/* We timed out.  Return the error ... */
 	ret = -ETIMEDOUT;
 	t4vf_record_mbox(adapter, cmd, size, access, ret);
+	spin_lock(&adapter->mbox_lock);
+	list_del(&entry.list);
+	spin_unlock(&adapter->mbox_lock);
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c
index 60383040d6c6..c363b58552e9 100644
--- a/drivers/net/ethernet/cirrus/cs89x0.c
+++ b/drivers/net/ethernet/cirrus/cs89x0.c
@@ -53,6 +53,8 @@
 #include <linux/errno.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -1895,9 +1897,17 @@ static int cs89x0_platform_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct __maybe_unused of_device_id cs89x0_match[] = {
+	{ .compatible = "cirrus,cs8900", },
+	{ .compatible = "cirrus,cs8920", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, cs89x0_match);
+
 static struct platform_driver cs89x0_driver = {
 	.driver	= {
-		.name	= DRV_NAME,
+		.name		= DRV_NAME,
+		.of_match_table	= of_match_ptr(cs89x0_match),
 	},
 	.remove	= cs89x0_platform_remove,
 };
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index f44a39c40642..fd3980cc1e34 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -103,25 +103,29 @@ static void enic_intr_coal_set_rx(struct enic *enic, u32 timer)
 	}
 }
 
-static int enic_get_settings(struct net_device *netdev,
-	struct ethtool_cmd *ecmd)
+static int enic_get_ksettings(struct net_device *netdev,
+			      struct ethtool_link_ksettings *ecmd)
 {
 	struct enic *enic = netdev_priv(netdev);
+	struct ethtool_link_settings *base = &ecmd->base;
 
-	ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE);
-	ecmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE);
-	ecmd->port = PORT_FIBRE;
-	ecmd->transceiver = XCVR_EXTERNAL;
+	ethtool_link_ksettings_add_link_mode(ecmd, supported,
+					     10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, FIBRE);
+	ethtool_link_ksettings_add_link_mode(ecmd, advertising,
+					     10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, advertising, FIBRE);
+	base->port = PORT_FIBRE;
 
 	if (netif_carrier_ok(netdev)) {
-		ethtool_cmd_speed_set(ecmd, vnic_dev_port_speed(enic->vdev));
-		ecmd->duplex = DUPLEX_FULL;
+		base->speed = vnic_dev_port_speed(enic->vdev);
+		base->duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		base->speed = SPEED_UNKNOWN;
+		base->duplex = DUPLEX_UNKNOWN;
 	}
 
-	ecmd->autoneg = AUTONEG_DISABLE;
+	base->autoneg = AUTONEG_DISABLE;
 
 	return 0;
 }
@@ -500,7 +504,6 @@ static int enic_set_rxfh(struct net_device *netdev, const u32 *indir,
 }
 
 static const struct ethtool_ops enic_ethtool_ops = {
-	.get_settings = enic_get_settings,
 	.get_drvinfo = enic_get_drvinfo,
 	.get_msglevel = enic_get_msglevel,
 	.set_msglevel = enic_set_msglevel,
@@ -516,6 +519,7 @@ static const struct ethtool_ops enic_ethtool_ops = {
 	.get_rxfh_key_size = enic_get_rxfh_key_size,
 	.get_rxfh = enic_get_rxfh,
 	.set_rxfh = enic_set_rxfh,
+	.get_link_ksettings = enic_get_ksettings,
 };
 
 void enic_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c
index b69a9eacc531..c3b64cdd0dec 100644
--- a/drivers/net/ethernet/dnet.c
+++ b/drivers/net/ethernet/dnet.c
@@ -173,7 +173,7 @@ static int dnet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 static void dnet_handle_link_change(struct net_device *dev)
 {
 	struct dnet *bp = netdev_priv(dev);
-	struct phy_device *phydev = bp->phy_dev;
+	struct phy_device *phydev = dev->phydev;
 	unsigned long flags;
 	u32 mode_reg, ctl_reg;
 
@@ -295,7 +295,6 @@ static int dnet_mii_probe(struct net_device *dev)
 	bp->link = 0;
 	bp->speed = 0;
 	bp->duplex = -1;
-	bp->phy_dev = phydev;
 
 	return 0;
 }
@@ -629,16 +628,16 @@ static int dnet_open(struct net_device *dev)
 	struct dnet *bp = netdev_priv(dev);
 
 	/* if the phy is not yet register, retry later */
-	if (!bp->phy_dev)
+	if (!dev->phydev)
 		return -EAGAIN;
 
 	napi_enable(&bp->napi);
 	dnet_init_hw(bp);
 
-	phy_start_aneg(bp->phy_dev);
+	phy_start_aneg(dev->phydev);
 
 	/* schedule a link state check */
-	phy_start(bp->phy_dev);
+	phy_start(dev->phydev);
 
 	netif_start_queue(dev);
 
@@ -652,8 +651,8 @@ static int dnet_close(struct net_device *dev)
 	netif_stop_queue(dev);
 	napi_disable(&bp->napi);
 
-	if (bp->phy_dev)
-		phy_stop(bp->phy_dev);
+	if (dev->phydev)
+		phy_stop(dev->phydev);
 
 	dnet_reset_hw(bp);
 	netif_carrier_off(dev);
@@ -731,32 +730,9 @@ static struct net_device_stats *dnet_get_stats(struct net_device *dev)
 	return nstat;
 }
 
-static int dnet_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct dnet *bp = netdev_priv(dev);
-	struct phy_device *phydev = bp->phy_dev;
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_ethtool_gset(phydev, cmd);
-}
-
-static int dnet_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct dnet *bp = netdev_priv(dev);
-	struct phy_device *phydev = bp->phy_dev;
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_ethtool_sset(phydev, cmd);
-}
-
 static int dnet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct dnet *bp = netdev_priv(dev);
-	struct phy_device *phydev = bp->phy_dev;
+	struct phy_device *phydev = dev->phydev;
 
 	if (!netif_running(dev))
 		return -EINVAL;
@@ -776,11 +752,11 @@ static void dnet_get_drvinfo(struct net_device *dev,
 }
 
 static const struct ethtool_ops dnet_ethtool_ops = {
-	.get_settings		= dnet_get_settings,
-	.set_settings		= dnet_set_settings,
 	.get_drvinfo		= dnet_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
 static const struct net_device_ops dnet_netdev_ops = {
@@ -875,7 +851,7 @@ static int dnet_probe(struct platform_device *pdev)
 	       (bp->capabilities & DNET_HAS_IRQ) ? "" : "no ",
 	       (bp->capabilities & DNET_HAS_GIGABIT) ? "" : "no ",
 	       (bp->capabilities & DNET_HAS_DMA) ? "" : "no ");
-	phydev = bp->phy_dev;
+	phydev = dev->phydev;
 	phy_attached_info(phydev);
 
 	return 0;
@@ -899,8 +875,8 @@ static int dnet_remove(struct platform_device *pdev)
 
 	if (dev) {
 		bp = netdev_priv(dev);
-		if (bp->phy_dev)
-			phy_disconnect(bp->phy_dev);
+		if (dev->phydev)
+			phy_disconnect(dev->phydev);
 		mdiobus_unregister(bp->mii_bus);
 		mdiobus_free(bp->mii_bus);
 		unregister_netdev(dev);
diff --git a/drivers/net/ethernet/dnet.h b/drivers/net/ethernet/dnet.h
index 37f5b30fa78b..d985080bbd5d 100644
--- a/drivers/net/ethernet/dnet.h
+++ b/drivers/net/ethernet/dnet.h
@@ -216,7 +216,6 @@ struct dnet {
 
 	/* PHY stuff */
 	struct mii_bus			*mii_bus;
-	struct phy_device		*phy_dev;
 	unsigned int			link;
 	unsigned int			speed;
 	unsigned int			duplex;
diff --git a/drivers/net/ethernet/emulex/benet/Kconfig b/drivers/net/ethernet/emulex/benet/Kconfig
index 7108563260ae..b4853ec9de8d 100644
--- a/drivers/net/ethernet/emulex/benet/Kconfig
+++ b/drivers/net/ethernet/emulex/benet/Kconfig
@@ -13,11 +13,3 @@ config BE2NET_HWMON
 	---help---
 	  Say Y here if you want to expose thermal sensor data on
 	  be2net network adapter.
-
-config BE2NET_VXLAN
-        bool "VXLAN offload support on be2net driver"
-        default y
-        depends on BE2NET && VXLAN && !(BE2NET=y && VXLAN=m)
-        ---help---
-	  Say Y here if you want to enable VXLAN offload support on
-	  be2net driver.
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index fe3763df3f13..4555e041ef69 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2015 Emulex
+ * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -97,7 +97,8 @@
 					 * SURF/DPDK
 					 */
 
-#define MAX_RSS_IFACES		15
+#define MAX_PORT_RSS_TABLES	15
+#define MAX_NIC_FUNCS		16
 #define MAX_RX_QS		32
 #define MAX_EVT_QS		32
 #define MAX_TX_QS		32
@@ -442,8 +443,20 @@ struct be_resources {
 	u16 max_iface_count;
 	u16 max_mcc_count;
 	u16 max_evt_qs;
+	u16 max_nic_evt_qs;	/* NIC's share of evt qs */
 	u32 if_cap_flags;
 	u32 vf_if_cap_flags;	/* VF if capability flags */
+	u32 flags;
+	/* Calculated PF Pool's share of RSS Tables. This is not enforced by
+	 * the FW, but is a self-imposed driver limitation.
+	 */
+	u16 max_rss_tables;
+};
+
+/* These are port-wide values */
+struct be_port_resources {
+	u16 max_vfs;
+	u16 nic_pfs;
 };
 
 #define be_is_os2bmc_enabled(adapter) (adapter->flags & BE_FLAGS_OS2BMC)
@@ -513,7 +526,8 @@ struct be_adapter {
 	spinlock_t mcc_lock;	/* For serializing mcc cmds to BE card */
 	spinlock_t mcc_cq_lock;
 
-	u16 cfg_num_qs;		/* configured via set-channels */
+	u16 cfg_num_rx_irqs;		/* configured via set-channels */
+	u16 cfg_num_tx_irqs;		/* configured via set-channels */
 	u16 num_evt_qs;
 	u16 num_msix_vec;
 	struct be_eq_obj eq_obj[MAX_EVT_QS];
@@ -632,16 +646,42 @@ struct be_adapter {
 #define be_max_txqs(adapter)		(adapter->res.max_tx_qs)
 #define be_max_prio_txqs(adapter)	(adapter->res.max_prio_tx_qs)
 #define be_max_rxqs(adapter)		(adapter->res.max_rx_qs)
-#define be_max_eqs(adapter)		(adapter->res.max_evt_qs)
+/* Max number of EQs available for the function (NIC + RoCE (if enabled)) */
+#define be_max_func_eqs(adapter)	(adapter->res.max_evt_qs)
+/* Max number of EQs available avaialble only for NIC */
+#define be_max_nic_eqs(adapter)		(adapter->res.max_nic_evt_qs)
 #define be_if_cap_flags(adapter)	(adapter->res.if_cap_flags)
-
-static inline u16 be_max_qs(struct be_adapter *adapter)
+#define be_max_pf_pool_rss_tables(adapter)	\
+				(adapter->pool_res.max_rss_tables)
+/* Max irqs avaialble for NIC */
+#define be_max_irqs(adapter)		\
+			(min_t(u16, be_max_nic_eqs(adapter), num_online_cpus()))
+
+/* Max irqs *needed* for RX queues */
+static inline u16 be_max_rx_irqs(struct be_adapter *adapter)
 {
-	/* If no RSS, need atleast the one def RXQ */
+	/* If no RSS, need atleast one irq for def-RXQ */
 	u16 num = max_t(u16, be_max_rss(adapter), 1);
 
-	num = min(num, be_max_eqs(adapter));
-	return min_t(u16, num, num_online_cpus());
+	return min_t(u16, num, be_max_irqs(adapter));
+}
+
+/* Max irqs *needed* for TX queues */
+static inline u16 be_max_tx_irqs(struct be_adapter *adapter)
+{
+	return min_t(u16, be_max_txqs(adapter), be_max_irqs(adapter));
+}
+
+/* Max irqs *needed* for combined queues */
+static inline u16 be_max_qp_irqs(struct be_adapter *adapter)
+{
+	return min(be_max_tx_irqs(adapter), be_max_rx_irqs(adapter));
+}
+
+/* Max irqs *needed* for RX and TX queues together */
+static inline u16 be_max_any_irqs(struct be_adapter *adapter)
+{
+	return max(be_max_tx_irqs(adapter), be_max_rx_irqs(adapter));
 }
 
 /* Is BE in pvid_tagging mode */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 22402db275f2..2cc11756859f 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2015 Emulex
+ * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -87,6 +87,11 @@ static struct be_cmd_priv_map cmd_priv_map[] = {
 		CMD_SUBSYSTEM_LOWLEVEL,
 		BE_PRIV_DEVCFG | BE_PRIV_DEVSEC
 	},
+	{
+		OPCODE_COMMON_SET_HSW_CONFIG,
+		CMD_SUBSYSTEM_COMMON,
+		BE_PRIV_DEVCFG | BE_PRIV_VHADM
+	},
 };
 
 static bool be_cmd_allowed(struct be_adapter *adapter, u8 opcode, u8 subsystem)
@@ -3850,6 +3855,10 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 	void *ctxt;
 	int status;
 
+	if (!be_cmd_allowed(adapter, OPCODE_COMMON_SET_HSW_CONFIG,
+			    CMD_SUBSYSTEM_COMMON))
+		return -EPERM;
+
 	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
@@ -3871,7 +3880,7 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 		AMAP_SET_BITS(struct amap_set_hsw_context, pvid_valid, ctxt, 1);
 		AMAP_SET_BITS(struct amap_set_hsw_context, pvid, ctxt, pvid);
 	}
-	if (!BEx_chip(adapter) && hsw_mode) {
+	if (hsw_mode) {
 		AMAP_SET_BITS(struct amap_set_hsw_context, interface_id,
 			      ctxt, adapter->hba_port_num);
 		AMAP_SET_BITS(struct amap_set_hsw_context, pport, ctxt, 1);
@@ -4023,7 +4032,10 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 		resp = (struct be_cmd_resp_acpi_wol_magic_config_v1 *)cmd.va;
 
 		adapter->wol_cap = resp->wol_settings;
-		if (adapter->wol_cap & BE_WOL_CAP)
+
+		/* Non-zero macaddr indicates WOL is enabled */
+		if (adapter->wol_cap & BE_WOL_CAP &&
+		    !is_zero_ether_addr(resp->magic_mac))
 			adapter->wol_en = true;
 	}
 err:
@@ -4360,9 +4372,35 @@ err:
 	return status;
 }
 
+/* This routine returns a list of all the NIC PF_nums in the adapter */
+u16 be_get_nic_pf_num_list(u8 *buf, u32 desc_count, u16 *nic_pf_nums)
+{
+	struct be_res_desc_hdr *hdr = (struct be_res_desc_hdr *)buf;
+	struct be_pcie_res_desc *pcie = NULL;
+	int i;
+	u16 nic_pf_count = 0;
+
+	for (i = 0; i < desc_count; i++) {
+		if (hdr->desc_type == PCIE_RESOURCE_DESC_TYPE_V0 ||
+		    hdr->desc_type == PCIE_RESOURCE_DESC_TYPE_V1) {
+			pcie = (struct be_pcie_res_desc *)hdr;
+			if (pcie->pf_state && (pcie->pf_type == MISSION_NIC ||
+					       pcie->pf_type == MISSION_RDMA)) {
+				nic_pf_nums[nic_pf_count++] = pcie->pf_num;
+			}
+		}
+
+		hdr->desc_len = hdr->desc_len ? : RESOURCE_DESC_SIZE_V0;
+		hdr = (void *)hdr + hdr->desc_len;
+	}
+	return nic_pf_count;
+}
+
 /* Will use MBOX only if MCCQ has not been created */
 int be_cmd_get_profile_config(struct be_adapter *adapter,
-			      struct be_resources *res, u8 query, u8 domain)
+			      struct be_resources *res,
+			      struct be_port_resources *port_res,
+			      u8 profile_type, u8 query, u8 domain)
 {
 	struct be_cmd_resp_get_profile_config *resp;
 	struct be_cmd_req_get_profile_config *req;
@@ -4389,7 +4427,7 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 
 	if (!lancer_chip(adapter))
 		req->hdr.version = 1;
-	req->type = ACTIVE_PROFILE_TYPE;
+	req->type = profile_type;
 	req->hdr.domain = domain;
 
 	/* When QUERY_MODIFIABLE_FIELDS_TYPE bit is set, cmd returns the
@@ -4406,6 +4444,28 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 	resp = cmd.va;
 	desc_count = le16_to_cpu(resp->desc_count);
 
+	if (port_res) {
+		u16 nic_pf_cnt = 0, i;
+		u16 nic_pf_num_list[MAX_NIC_FUNCS];
+
+		nic_pf_cnt = be_get_nic_pf_num_list(resp->func_param,
+						    desc_count,
+						    nic_pf_num_list);
+
+		for (i = 0; i < nic_pf_cnt; i++) {
+			nic = be_get_func_nic_desc(resp->func_param, desc_count,
+						   nic_pf_num_list[i]);
+			if (nic->link_param == adapter->port_num) {
+				port_res->nic_pfs++;
+				pcie = be_get_pcie_desc(resp->func_param,
+							desc_count,
+							nic_pf_num_list[i]);
+				port_res->max_vfs += le16_to_cpu(pcie->num_vfs);
+			}
+		}
+		return status;
+	}
+
 	pcie = be_get_pcie_desc(resp->func_param, desc_count,
 				adapter->pf_num);
 	if (pcie)
@@ -4465,7 +4525,7 @@ static int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
 }
 
 /* Mark all fields invalid */
-static void be_reset_nic_desc(struct be_nic_res_desc *nic)
+void be_reset_nic_desc(struct be_nic_res_desc *nic)
 {
 	memset(nic, 0, sizeof(*nic));
 	nic->unicast_mac_count = 0xFFFF;
@@ -4534,73 +4594,9 @@ int be_cmd_config_qos(struct be_adapter *adapter, u32 max_rate, u16 link_speed,
 					 1, version, domain);
 }
 
-static void be_fill_vf_res_template(struct be_adapter *adapter,
-				    struct be_resources pool_res,
-				    u16 num_vfs, u16 num_vf_qs,
-				    struct be_nic_res_desc *nic_vft)
-{
-	u32 vf_if_cap_flags = pool_res.vf_if_cap_flags;
-	struct be_resources res_mod = {0};
-
-	/* Resource with fields set to all '1's by GET_PROFILE_CONFIG cmd,
-	 * which are modifiable using SET_PROFILE_CONFIG cmd.
-	 */
-	be_cmd_get_profile_config(adapter, &res_mod, RESOURCE_MODIFIABLE, 0);
-
-	/* If RSS IFACE capability flags are modifiable for a VF, set the
-	 * capability flag as valid and set RSS and DEFQ_RSS IFACE flags if
-	 * more than 1 RSSQ is available for a VF.
-	 * Otherwise, provision only 1 queue pair for VF.
-	 */
-	if (res_mod.vf_if_cap_flags & BE_IF_FLAGS_RSS) {
-		nic_vft->flags |= BIT(IF_CAPS_FLAGS_VALID_SHIFT);
-		if (num_vf_qs > 1) {
-			vf_if_cap_flags |= BE_IF_FLAGS_RSS;
-			if (pool_res.if_cap_flags & BE_IF_FLAGS_DEFQ_RSS)
-				vf_if_cap_flags |= BE_IF_FLAGS_DEFQ_RSS;
-		} else {
-			vf_if_cap_flags &= ~(BE_IF_FLAGS_RSS |
-					     BE_IF_FLAGS_DEFQ_RSS);
-		}
-	} else {
-		num_vf_qs = 1;
-	}
-
-	if (res_mod.vf_if_cap_flags & BE_IF_FLAGS_VLAN_PROMISCUOUS) {
-		nic_vft->flags |= BIT(IF_CAPS_FLAGS_VALID_SHIFT);
-		vf_if_cap_flags &= ~BE_IF_FLAGS_VLAN_PROMISCUOUS;
-	}
-
-	nic_vft->cap_flags = cpu_to_le32(vf_if_cap_flags);
-	nic_vft->rq_count = cpu_to_le16(num_vf_qs);
-	nic_vft->txq_count = cpu_to_le16(num_vf_qs);
-	nic_vft->rssq_count = cpu_to_le16(num_vf_qs);
-	nic_vft->cq_count = cpu_to_le16(pool_res.max_cq_count /
-					(num_vfs + 1));
-
-	/* Distribute unicast MACs, VLANs, IFACE count and MCCQ count equally
-	 * among the PF and it's VFs, if the fields are changeable
-	 */
-	if (res_mod.max_uc_mac == FIELD_MODIFIABLE)
-		nic_vft->unicast_mac_count = cpu_to_le16(pool_res.max_uc_mac /
-							 (num_vfs + 1));
-
-	if (res_mod.max_vlans == FIELD_MODIFIABLE)
-		nic_vft->vlan_count = cpu_to_le16(pool_res.max_vlans /
-						  (num_vfs + 1));
-
-	if (res_mod.max_iface_count == FIELD_MODIFIABLE)
-		nic_vft->iface_count = cpu_to_le16(pool_res.max_iface_count /
-						   (num_vfs + 1));
-
-	if (res_mod.max_mcc_count == FIELD_MODIFIABLE)
-		nic_vft->mcc_count = cpu_to_le16(pool_res.max_mcc_count /
-						 (num_vfs + 1));
-}
-
 int be_cmd_set_sriov_config(struct be_adapter *adapter,
 			    struct be_resources pool_res, u16 num_vfs,
-			    u16 num_vf_qs)
+			    struct be_resources *vft_res)
 {
 	struct {
 		struct be_pcie_res_desc pcie;
@@ -4620,12 +4616,26 @@ int be_cmd_set_sriov_config(struct be_adapter *adapter,
 	be_reset_nic_desc(&desc.nic_vft);
 	desc.nic_vft.hdr.desc_type = NIC_RESOURCE_DESC_TYPE_V1;
 	desc.nic_vft.hdr.desc_len = RESOURCE_DESC_SIZE_V1;
-	desc.nic_vft.flags = BIT(VFT_SHIFT) | BIT(IMM_SHIFT) | BIT(NOSV_SHIFT);
+	desc.nic_vft.flags = vft_res->flags | BIT(VFT_SHIFT) |
+			     BIT(IMM_SHIFT) | BIT(NOSV_SHIFT);
 	desc.nic_vft.pf_num = adapter->pdev->devfn;
 	desc.nic_vft.vf_num = 0;
-
-	be_fill_vf_res_template(adapter, pool_res, num_vfs, num_vf_qs,
-				&desc.nic_vft);
+	desc.nic_vft.cap_flags = cpu_to_le32(vft_res->vf_if_cap_flags);
+	desc.nic_vft.rq_count = cpu_to_le16(vft_res->max_rx_qs);
+	desc.nic_vft.txq_count = cpu_to_le16(vft_res->max_tx_qs);
+	desc.nic_vft.rssq_count = cpu_to_le16(vft_res->max_rss_qs);
+	desc.nic_vft.cq_count = cpu_to_le16(vft_res->max_cq_count);
+
+	if (vft_res->max_uc_mac)
+		desc.nic_vft.unicast_mac_count =
+					cpu_to_le16(vft_res->max_uc_mac);
+	if (vft_res->max_vlans)
+		desc.nic_vft.vlan_count = cpu_to_le16(vft_res->max_vlans);
+	if (vft_res->max_iface_count)
+		desc.nic_vft.iface_count =
+				cpu_to_le16(vft_res->max_iface_count);
+	if (vft_res->max_mcc_count)
+		desc.nic_vft.mcc_count = cpu_to_le16(vft_res->max_mcc_count);
 
 	return be_cmd_set_profile_config(adapter, &desc,
 					 2 * RESOURCE_DESC_SIZE_V1, 2, 1, 0);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index d8540ae95e5a..0d6be224a787 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2015 Emulex
+ * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -1556,7 +1556,9 @@ struct be_cmd_resp_acpi_wol_magic_config_v1 {
 	u8 rsvd0[2];
 	u8 wol_settings;
 	u8 rsvd1[5];
-	u32 rsvd2[295];
+	u32 rsvd2[288];
+	u8 magic_mac[6];
+	u8 rsvd3[22];
 } __packed;
 
 #define BE_GET_WOL_CAP			2
@@ -2128,6 +2130,9 @@ struct be_cmd_req_set_ext_fat_caps {
 #define IMM_SHIFT				6	/* Immediate */
 #define NOSV_SHIFT				7	/* No save */
 
+#define MISSION_NIC				1
+#define MISSION_RDMA				8
+
 struct be_res_desc_hdr {
 	u8 desc_type;
 	u8 desc_len;
@@ -2244,6 +2249,7 @@ struct be_cmd_req_get_profile_config {
 	struct be_cmd_req_hdr hdr;
 	u8 rsvd;
 #define ACTIVE_PROFILE_TYPE			0x2
+#define SAVED_PROFILE_TYPE			0x0
 #define QUERY_MODIFIABLE_FIELDS_TYPE		BIT(3)
 	u8 type;
 	u16 rsvd1;
@@ -2449,7 +2455,9 @@ int be_cmd_query_port_name(struct be_adapter *adapter);
 int be_cmd_get_func_config(struct be_adapter *adapter,
 			   struct be_resources *res);
 int be_cmd_get_profile_config(struct be_adapter *adapter,
-			      struct be_resources *res, u8 query, u8 domain);
+			      struct be_resources *res,
+			      struct be_port_resources *port_res,
+			      u8 profile_type, u8 query, u8 domain);
 int be_cmd_get_active_profile(struct be_adapter *adapter, u16 *profile);
 int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 		     int vf_num);
@@ -2461,4 +2469,4 @@ int be_cmd_set_vxlan_port(struct be_adapter *adapter, __be16 port);
 int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op);
 int be_cmd_set_sriov_config(struct be_adapter *adapter,
 			    struct be_resources res, u16 num_vfs,
-			    u16 num_vf_qs);
+			    struct be_resources *vft_res);
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 2ff691636dac..50e7be5da50c 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2015 Emulex
+ * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -793,6 +793,11 @@ static void be_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 static int be_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
+	struct device *dev = &adapter->pdev->dev;
+	struct be_dma_mem cmd;
+	u8 mac[ETH_ALEN];
+	bool enable;
+	int status;
 
 	if (wol->wolopts & ~WAKE_MAGIC)
 		return -EOPNOTSUPP;
@@ -802,12 +807,32 @@ static int be_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 		return -EOPNOTSUPP;
 	}
 
-	if (wol->wolopts & WAKE_MAGIC)
-		adapter->wol_en = true;
-	else
-		adapter->wol_en = false;
+	cmd.size = sizeof(struct be_cmd_req_acpi_wol_magic_config);
+	cmd.va = dma_zalloc_coherent(dev, cmd.size, &cmd.dma, GFP_KERNEL);
+	if (!cmd.va)
+		return -ENOMEM;
 
-	return 0;
+	eth_zero_addr(mac);
+
+	enable = wol->wolopts & WAKE_MAGIC;
+	if (enable)
+		ether_addr_copy(mac, adapter->netdev->dev_addr);
+
+	status = be_cmd_enable_magic_wol(adapter, mac, &cmd);
+	if (status) {
+		dev_err(dev, "Could not set Wake-on-lan mac address\n");
+		status = be_cmd_status(status);
+		goto err;
+	}
+
+	pci_enable_wake(adapter->pdev, PCI_D3hot, enable);
+	pci_enable_wake(adapter->pdev, PCI_D3cold, enable);
+
+	adapter->wol_en = enable ? true : false;
+
+err:
+	dma_free_coherent(dev, cmd.size, cmd.va, cmd.dma);
+	return status;
 }
 
 static int be_test_ddr_dma(struct be_adapter *adapter)
@@ -1171,9 +1196,17 @@ static void be_get_channels(struct net_device *netdev,
 			    struct ethtool_channels *ch)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
+	u16 num_rx_irqs = max_t(u16, adapter->num_rss_qs, 1);
 
-	ch->combined_count = adapter->num_evt_qs;
-	ch->max_combined = be_max_qs(adapter);
+	/* num_tx_qs is always same as the number of irqs used for TX */
+	ch->combined_count = min(adapter->num_tx_qs, num_rx_irqs);
+	ch->rx_count = num_rx_irqs - ch->combined_count;
+	ch->tx_count = adapter->num_tx_qs - ch->combined_count;
+
+	ch->max_combined = be_max_qp_irqs(adapter);
+	/* The user must create atleast one combined channel */
+	ch->max_rx = be_max_rx_irqs(adapter) - 1;
+	ch->max_tx = be_max_tx_irqs(adapter) - 1;
 }
 
 static int be_set_channels(struct net_device  *netdev,
@@ -1182,11 +1215,22 @@ static int be_set_channels(struct net_device  *netdev,
 	struct be_adapter *adapter = netdev_priv(netdev);
 	int status;
 
-	if (ch->rx_count || ch->tx_count || ch->other_count ||
-	    !ch->combined_count || ch->combined_count > be_max_qs(adapter))
+	/* we support either only combined channels or a combination of
+	 * combined and either RX-only or TX-only channels.
+	 */
+	if (ch->other_count || !ch->combined_count ||
+	    (ch->rx_count && ch->tx_count))
+		return -EINVAL;
+
+	if (ch->combined_count > be_max_qp_irqs(adapter) ||
+	    (ch->rx_count &&
+	     (ch->rx_count + ch->combined_count) > be_max_rx_irqs(adapter)) ||
+	    (ch->tx_count &&
+	     (ch->tx_count + ch->combined_count) > be_max_tx_irqs(adapter)))
 		return -EINVAL;
 
-	adapter->cfg_num_qs = ch->combined_count;
+	adapter->cfg_num_rx_irqs = ch->combined_count + ch->rx_count;
+	adapter->cfg_num_tx_irqs = ch->combined_count + ch->tx_count;
 
 	status = be_update_queues(adapter);
 	return be_cmd_status(status);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index ed98ef1ecac3..1f16e73f6d0c 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2015 Emulex
+ * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -2620,8 +2620,10 @@ static int be_evt_queues_create(struct be_adapter *adapter)
 	struct be_aic_obj *aic;
 	int i, rc;
 
+	/* need enough EQs to service both RX and TX queues */
 	adapter->num_evt_qs = min_t(u16, num_irqs(adapter),
-				    adapter->cfg_num_qs);
+				    max(adapter->cfg_num_rx_irqs,
+					adapter->cfg_num_tx_irqs));
 
 	for_all_evt_queues(adapter, eqo, i) {
 		int numa_node = dev_to_node(&adapter->pdev->dev);
@@ -2726,7 +2728,7 @@ static int be_tx_qs_create(struct be_adapter *adapter)
 	struct be_eq_obj *eqo;
 	int status, i;
 
-	adapter->num_tx_qs = min(adapter->num_evt_qs, be_max_txqs(adapter));
+	adapter->num_tx_qs = min(adapter->num_evt_qs, adapter->cfg_num_tx_irqs);
 
 	for_all_tx_queues(adapter, txo, i) {
 		cq = &txo->cq;
@@ -2784,11 +2786,11 @@ static int be_rx_cqs_create(struct be_adapter *adapter)
 	struct be_rx_obj *rxo;
 	int rc, i;
 
-	/* We can create as many RSS rings as there are EQs. */
-	adapter->num_rss_qs = adapter->num_evt_qs;
+	adapter->num_rss_qs =
+			min(adapter->num_evt_qs, adapter->cfg_num_rx_irqs);
 
 	/* We'll use RSS only if atleast 2 RSS rings are supported. */
-	if (adapter->num_rss_qs <= 1)
+	if (adapter->num_rss_qs < 2)
 		adapter->num_rss_qs = 0;
 
 	adapter->num_rx_qs = adapter->num_rss_qs + adapter->need_def_rxq;
@@ -3249,18 +3251,23 @@ static void be_msix_disable(struct be_adapter *adapter)
 
 static int be_msix_enable(struct be_adapter *adapter)
 {
-	int i, num_vec;
+	unsigned int i, max_roce_eqs;
 	struct device *dev = &adapter->pdev->dev;
+	int num_vec;
 
-	/* If RoCE is supported, program the max number of NIC vectors that
-	 * may be configured via set-channels, along with vectors needed for
-	 * RoCe. Else, just program the number we'll use initially.
+	/* If RoCE is supported, program the max number of vectors that
+	 * could be used for NIC and RoCE, else, just program the number
+	 * we'll use initially.
 	 */
-	if (be_roce_supported(adapter))
-		num_vec = min_t(int, 2 * be_max_eqs(adapter),
-				2 * num_online_cpus());
-	else
-		num_vec = adapter->cfg_num_qs;
+	if (be_roce_supported(adapter)) {
+		max_roce_eqs =
+			be_max_func_eqs(adapter) - be_max_nic_eqs(adapter);
+		max_roce_eqs = min(max_roce_eqs, num_online_cpus());
+		num_vec = be_max_any_irqs(adapter) + max_roce_eqs;
+	} else {
+		num_vec = max(adapter->cfg_num_rx_irqs,
+			      adapter->cfg_num_tx_irqs);
+	}
 
 	for (i = 0; i < num_vec; i++)
 		adapter->msix_entries[i].entry = i;
@@ -3625,10 +3632,8 @@ static int be_open(struct net_device *netdev)
 		be_link_status_update(adapter, link_status);
 
 	netif_tx_start_all_queues(netdev);
-#ifdef CONFIG_BE2NET_VXLAN
 	if (skyhawk_chip(adapter))
-		vxlan_get_rx_port(netdev);
-#endif
+		udp_tunnel_get_rx_info(netdev);
 
 	return 0;
 err:
@@ -3636,40 +3641,6 @@ err:
 	return -EIO;
 }
 
-static int be_setup_wol(struct be_adapter *adapter, bool enable)
-{
-	struct device *dev = &adapter->pdev->dev;
-	struct be_dma_mem cmd;
-	u8 mac[ETH_ALEN];
-	int status;
-
-	eth_zero_addr(mac);
-
-	cmd.size = sizeof(struct be_cmd_req_acpi_wol_magic_config);
-	cmd.va = dma_zalloc_coherent(dev, cmd.size, &cmd.dma, GFP_KERNEL);
-	if (!cmd.va)
-		return -ENOMEM;
-
-	if (enable) {
-		status = pci_write_config_dword(adapter->pdev,
-						PCICFG_PM_CONTROL_OFFSET,
-						PCICFG_PM_CONTROL_MASK);
-		if (status) {
-			dev_err(dev, "Could not enable Wake-on-lan\n");
-			goto err;
-		}
-	} else {
-		ether_addr_copy(mac, adapter->netdev->dev_addr);
-	}
-
-	status = be_cmd_enable_magic_wol(adapter, mac, &cmd);
-	pci_enable_wake(adapter->pdev, PCI_D3hot, enable);
-	pci_enable_wake(adapter->pdev, PCI_D3cold, enable);
-err:
-	dma_free_coherent(dev, cmd.size, cmd.va, cmd.dma);
-	return status;
-}
-
 static void be_vf_eth_addr_generate(struct be_adapter *adapter, u8 *mac)
 {
 	u32 addr;
@@ -3759,6 +3730,11 @@ static void be_vf_clear(struct be_adapter *adapter)
 
 		be_cmd_if_destroy(adapter, vf_cfg->if_handle, vf + 1);
 	}
+
+	if (BE3_chip(adapter))
+		be_cmd_set_hsw_config(adapter, 0, 0,
+				      adapter->if_handle,
+				      PORT_FWD_TYPE_PASSTHRU, 0);
 done:
 	kfree(adapter->vf_cfg);
 	adapter->num_vfs = 0;
@@ -3789,7 +3765,6 @@ static void be_cancel_err_detection(struct be_adapter *adapter)
 	}
 }
 
-#ifdef CONFIG_BE2NET_VXLAN
 static void be_disable_vxlan_offloads(struct be_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
@@ -3808,37 +3783,87 @@ static void be_disable_vxlan_offloads(struct be_adapter *adapter)
 	netdev->hw_features &= ~(NETIF_F_GSO_UDP_TUNNEL);
 	netdev->features &= ~(NETIF_F_GSO_UDP_TUNNEL);
 }
-#endif
 
-static u16 be_calculate_vf_qs(struct be_adapter *adapter, u16 num_vfs)
+static void be_calculate_vf_res(struct be_adapter *adapter, u16 num_vfs,
+				struct be_resources *vft_res)
 {
 	struct be_resources res = adapter->pool_res;
+	u32 vf_if_cap_flags = res.vf_if_cap_flags;
+	struct be_resources res_mod = {0};
 	u16 num_vf_qs = 1;
 
-	/* Distribute the queue resources among the PF and it's VFs
-	 * Do not distribute queue resources in multi-channel configuration.
-	 */
-	if (num_vfs && !be_is_mc(adapter)) {
-		 /* Divide the qpairs evenly among the VFs and the PF, capped
-		  * at VF-EQ-count. Any remainder qpairs belong to the PF.
-		  */
+	/* Distribute the queue resources among the PF and it's VFs */
+	if (num_vfs) {
+		/* Divide the rx queues evenly among the VFs and the PF, capped
+		 * at VF-EQ-count. Any remainder queues belong to the PF.
+		 */
 		num_vf_qs = min(SH_VF_MAX_NIC_EQS,
 				res.max_rss_qs / (num_vfs + 1));
 
-		/* Skyhawk-R chip supports only MAX_RSS_IFACES RSS capable
-		 * interfaces per port. Provide RSS on VFs, only if number
-		 * of VFs requested is less than MAX_RSS_IFACES limit.
+		/* Skyhawk-R chip supports only MAX_PORT_RSS_TABLES
+		 * RSS Tables per port. Provide RSS on VFs, only if number of
+		 * VFs requested is less than it's PF Pool's RSS Tables limit.
 		 */
-		if (num_vfs >= MAX_RSS_IFACES)
+		if (num_vfs >= be_max_pf_pool_rss_tables(adapter))
 			num_vf_qs = 1;
 	}
-	return num_vf_qs;
+
+	/* Resource with fields set to all '1's by GET_PROFILE_CONFIG cmd,
+	 * which are modifiable using SET_PROFILE_CONFIG cmd.
+	 */
+	be_cmd_get_profile_config(adapter, &res_mod, NULL, ACTIVE_PROFILE_TYPE,
+				  RESOURCE_MODIFIABLE, 0);
+
+	/* If RSS IFACE capability flags are modifiable for a VF, set the
+	 * capability flag as valid and set RSS and DEFQ_RSS IFACE flags if
+	 * more than 1 RSSQ is available for a VF.
+	 * Otherwise, provision only 1 queue pair for VF.
+	 */
+	if (res_mod.vf_if_cap_flags & BE_IF_FLAGS_RSS) {
+		vft_res->flags |= BIT(IF_CAPS_FLAGS_VALID_SHIFT);
+		if (num_vf_qs > 1) {
+			vf_if_cap_flags |= BE_IF_FLAGS_RSS;
+			if (res.if_cap_flags & BE_IF_FLAGS_DEFQ_RSS)
+				vf_if_cap_flags |= BE_IF_FLAGS_DEFQ_RSS;
+		} else {
+			vf_if_cap_flags &= ~(BE_IF_FLAGS_RSS |
+					     BE_IF_FLAGS_DEFQ_RSS);
+		}
+	} else {
+		num_vf_qs = 1;
+	}
+
+	if (res_mod.vf_if_cap_flags & BE_IF_FLAGS_VLAN_PROMISCUOUS) {
+		vft_res->flags |= BIT(IF_CAPS_FLAGS_VALID_SHIFT);
+		vf_if_cap_flags &= ~BE_IF_FLAGS_VLAN_PROMISCUOUS;
+	}
+
+	vft_res->vf_if_cap_flags = vf_if_cap_flags;
+	vft_res->max_rx_qs = num_vf_qs;
+	vft_res->max_rss_qs = num_vf_qs;
+	vft_res->max_tx_qs = res.max_tx_qs / (num_vfs + 1);
+	vft_res->max_cq_count = res.max_cq_count / (num_vfs + 1);
+
+	/* Distribute unicast MACs, VLANs, IFACE count and MCCQ count equally
+	 * among the PF and it's VFs, if the fields are changeable
+	 */
+	if (res_mod.max_uc_mac == FIELD_MODIFIABLE)
+		vft_res->max_uc_mac = res.max_uc_mac / (num_vfs + 1);
+
+	if (res_mod.max_vlans == FIELD_MODIFIABLE)
+		vft_res->max_vlans = res.max_vlans / (num_vfs + 1);
+
+	if (res_mod.max_iface_count == FIELD_MODIFIABLE)
+		vft_res->max_iface_count = res.max_iface_count / (num_vfs + 1);
+
+	if (res_mod.max_mcc_count == FIELD_MODIFIABLE)
+		vft_res->max_mcc_count = res.max_mcc_count / (num_vfs + 1);
 }
 
 static int be_clear(struct be_adapter *adapter)
 {
 	struct pci_dev *pdev = adapter->pdev;
-	u16 num_vf_qs;
+	struct  be_resources vft_res = {0};
 
 	be_cancel_worker(adapter);
 
@@ -3850,16 +3875,15 @@ static int be_clear(struct be_adapter *adapter)
 	 */
 	if (skyhawk_chip(adapter) && be_physfn(adapter) &&
 	    !pci_vfs_assigned(pdev)) {
-		num_vf_qs = be_calculate_vf_qs(adapter,
-					       pci_sriov_get_totalvfs(pdev));
+		be_calculate_vf_res(adapter,
+				    pci_sriov_get_totalvfs(pdev),
+				    &vft_res);
 		be_cmd_set_sriov_config(adapter, adapter->pool_res,
 					pci_sriov_get_totalvfs(pdev),
-					num_vf_qs);
+					&vft_res);
 	}
 
-#ifdef CONFIG_BE2NET_VXLAN
 	be_disable_vxlan_offloads(adapter);
-#endif
 	kfree(adapter->pmac_id);
 	adapter->pmac_id = NULL;
 
@@ -3884,7 +3908,8 @@ static int be_vfs_if_create(struct be_adapter *adapter)
 
 	for_all_vfs(adapter, vf_cfg, vf) {
 		if (!BE3_chip(adapter)) {
-			status = be_cmd_get_profile_config(adapter, &res,
+			status = be_cmd_get_profile_config(adapter, &res, NULL,
+							   ACTIVE_PROFILE_TYPE,
 							   RESOURCE_LIMITS,
 							   vf + 1);
 			if (!status) {
@@ -4000,6 +4025,15 @@ static int be_vf_setup(struct be_adapter *adapter)
 		}
 	}
 
+	if (BE3_chip(adapter)) {
+		/* On BE3, enable VEB only when SRIOV is enabled */
+		status = be_cmd_set_hsw_config(adapter, 0, 0,
+					       adapter->if_handle,
+					       PORT_FWD_TYPE_VEB, 0);
+		if (status)
+			goto err;
+	}
+
 	adapter->flags |= BE_FLAGS_SRIOV_ENABLED;
 	return 0;
 err:
@@ -4069,8 +4103,9 @@ static void BEx_get_resources(struct be_adapter *adapter,
 		/* On a SuperNIC profile, the driver needs to use the
 		 * GET_PROFILE_CONFIG cmd to query the per-function TXQ limits
 		 */
-		be_cmd_get_profile_config(adapter, &super_nic_res,
-					  RESOURCE_LIMITS, 0);
+		be_cmd_get_profile_config(adapter, &super_nic_res, NULL,
+					  ACTIVE_PROFILE_TYPE, RESOURCE_LIMITS,
+					  0);
 		/* Some old versions of BE3 FW don't report max_tx_qs value */
 		res->max_tx_qs = super_nic_res.max_tx_qs ? : BE3_MAX_TX_QS;
 	} else {
@@ -4109,12 +4144,38 @@ static void be_setup_init(struct be_adapter *adapter)
 		adapter->cmd_privileges = MIN_PRIVILEGES;
 }
 
+/* HW supports only MAX_PORT_RSS_TABLES RSS Policy Tables per port.
+ * However, this HW limitation is not exposed to the host via any SLI cmd.
+ * As a result, in the case of SRIOV and in particular multi-partition configs
+ * the driver needs to calcuate a proportional share of RSS Tables per PF-pool
+ * for distribution between the VFs. This self-imposed limit will determine the
+ * no: of VFs for which RSS can be enabled.
+ */
+void be_calculate_pf_pool_rss_tables(struct be_adapter *adapter)
+{
+	struct be_port_resources port_res = {0};
+	u8 rss_tables_on_port;
+	u16 max_vfs = be_max_vfs(adapter);
+
+	be_cmd_get_profile_config(adapter, NULL, &port_res, SAVED_PROFILE_TYPE,
+				  RESOURCE_LIMITS, 0);
+
+	rss_tables_on_port = MAX_PORT_RSS_TABLES - port_res.nic_pfs;
+
+	/* Each PF Pool's RSS Tables limit =
+	 * PF's Max VFs / Total_Max_VFs on Port * RSS Tables on Port
+	 */
+	adapter->pool_res.max_rss_tables =
+		max_vfs * rss_tables_on_port / port_res.max_vfs;
+}
+
 static int be_get_sriov_config(struct be_adapter *adapter)
 {
 	struct be_resources res = {0};
 	int max_vfs, old_vfs;
 
-	be_cmd_get_profile_config(adapter, &res, RESOURCE_LIMITS, 0);
+	be_cmd_get_profile_config(adapter, &res, NULL, ACTIVE_PROFILE_TYPE,
+				  RESOURCE_LIMITS, 0);
 
 	/* Some old versions of BE3 FW don't report max_vfs value */
 	if (BE3_chip(adapter) && !res.max_vfs) {
@@ -4138,13 +4199,19 @@ static int be_get_sriov_config(struct be_adapter *adapter)
 		adapter->num_vfs = old_vfs;
 	}
 
+	if (skyhawk_chip(adapter) && be_max_vfs(adapter) && !old_vfs) {
+		be_calculate_pf_pool_rss_tables(adapter);
+		dev_info(&adapter->pdev->dev,
+			 "RSS can be enabled for all VFs if num_vfs <= %d\n",
+			 be_max_pf_pool_rss_tables(adapter));
+	}
 	return 0;
 }
 
 static void be_alloc_sriov_res(struct be_adapter *adapter)
 {
 	int old_vfs = pci_num_vf(adapter->pdev);
-	u16 num_vf_qs;
+	struct  be_resources vft_res = {0};
 	int status;
 
 	be_get_sriov_config(adapter);
@@ -4158,9 +4225,9 @@ static void be_alloc_sriov_res(struct be_adapter *adapter)
 	 * Also, this is done by FW in Lancer chip.
 	 */
 	if (skyhawk_chip(adapter) && be_max_vfs(adapter) && !old_vfs) {
-		num_vf_qs = be_calculate_vf_qs(adapter, 0);
+		be_calculate_vf_res(adapter, 0, &vft_res);
 		status = be_cmd_set_sriov_config(adapter, adapter->pool_res, 0,
-						 num_vf_qs);
+						 &vft_res);
 		if (status)
 			dev_err(&adapter->pdev->dev,
 				"Failed to optimize SRIOV resources\n");
@@ -4173,16 +4240,13 @@ static int be_get_resources(struct be_adapter *adapter)
 	struct be_resources res = {0};
 	int status;
 
-	if (BEx_chip(adapter)) {
-		BEx_get_resources(adapter, &res);
-		adapter->res = res;
-	}
-
 	/* For Lancer, SH etc read per-function resource limits from FW.
 	 * GET_FUNC_CONFIG returns per function guaranteed limits.
 	 * GET_PROFILE_CONFIG returns PCI-E related limits PF-pool limits
 	 */
-	if (!BEx_chip(adapter)) {
+	if (BEx_chip(adapter)) {
+		BEx_get_resources(adapter, &res);
+	} else {
 		status = be_cmd_get_func_config(adapter, &res);
 		if (status)
 			return status;
@@ -4191,13 +4255,13 @@ static int be_get_resources(struct be_adapter *adapter)
 		if (res.max_rss_qs && res.max_rss_qs == res.max_rx_qs &&
 		    !(res.if_cap_flags & BE_IF_FLAGS_DEFQ_RSS))
 			res.max_rss_qs -= 1;
-
-		/* If RoCE may be enabled stash away half the EQs for RoCE */
-		if (be_roce_supported(adapter))
-			res.max_evt_qs /= 2;
-		adapter->res = res;
 	}
 
+	/* If RoCE is supported stash away half the EQs for RoCE */
+	res.max_nic_evt_qs = be_roce_supported(adapter) ?
+				res.max_evt_qs / 2 : res.max_evt_qs;
+	adapter->res = res;
+
 	/* If FW supports RSS default queue, then skip creating non-RSS
 	 * queue for non-IP traffic.
 	 */
@@ -4206,15 +4270,17 @@ static int be_get_resources(struct be_adapter *adapter)
 
 	dev_info(dev, "Max: txqs %d, rxqs %d, rss %d, eqs %d, vfs %d\n",
 		 be_max_txqs(adapter), be_max_rxqs(adapter),
-		 be_max_rss(adapter), be_max_eqs(adapter),
+		 be_max_rss(adapter), be_max_nic_eqs(adapter),
 		 be_max_vfs(adapter));
 	dev_info(dev, "Max: uc-macs %d, mc-macs %d, vlans %d\n",
 		 be_max_uc(adapter), be_max_mc(adapter),
 		 be_max_vlans(adapter));
 
-	/* Sanitize cfg_num_qs based on HW and platform limits */
-	adapter->cfg_num_qs = min_t(u16, netif_get_num_default_rss_queues(),
-				    be_max_qs(adapter));
+	/* Ensure RX and TX queues are created in pairs at init time */
+	adapter->cfg_num_rx_irqs =
+				min_t(u16, netif_get_num_default_rss_queues(),
+				      be_max_qp_irqs(adapter));
+	adapter->cfg_num_tx_irqs = adapter->cfg_num_rx_irqs;
 	return 0;
 }
 
@@ -4241,6 +4307,8 @@ static int be_get_config(struct be_adapter *adapter)
 	}
 
 	be_cmd_get_acpi_wol_cap(adapter);
+	pci_enable_wake(adapter->pdev, PCI_D3hot, adapter->wol_en);
+	pci_enable_wake(adapter->pdev, PCI_D3cold, adapter->wol_en);
 
 	be_cmd_query_port_name(adapter);
 
@@ -4251,15 +4319,6 @@ static int be_get_config(struct be_adapter *adapter)
 				 "Using profile 0x%x\n", profile_id);
 	}
 
-	status = be_get_resources(adapter);
-	if (status)
-		return status;
-
-	adapter->pmac_id = kcalloc(be_max_uc(adapter),
-				   sizeof(*adapter->pmac_id), GFP_KERNEL);
-	if (!adapter->pmac_id)
-		return -ENOMEM;
-
 	return 0;
 }
 
@@ -4334,7 +4393,7 @@ static int be_if_create(struct be_adapter *adapter)
 	u32 cap_flags = be_if_cap_flags(adapter);
 	int status;
 
-	if (adapter->cfg_num_qs == 1)
+	if (adapter->cfg_num_rx_irqs == 1)
 		cap_flags &= ~(BE_IF_FLAGS_DEFQ_RSS | BE_IF_FLAGS_RSS);
 
 	en_flags &= cap_flags;
@@ -4460,13 +4519,22 @@ static int be_setup(struct be_adapter *adapter)
 			return status;
 	}
 
+	status = be_get_config(adapter);
+	if (status)
+		goto err;
+
 	if (!BE2_chip(adapter) && be_physfn(adapter))
 		be_alloc_sriov_res(adapter);
 
-	status = be_get_config(adapter);
+	status = be_get_resources(adapter);
 	if (status)
 		goto err;
 
+	adapter->pmac_id = kcalloc(be_max_uc(adapter),
+				   sizeof(*adapter->pmac_id), GFP_KERNEL);
+	if (!adapter->pmac_id)
+		return -ENOMEM;
+
 	status = be_msix_enable(adapter);
 	if (status)
 		goto err;
@@ -4511,6 +4579,15 @@ static int be_setup(struct be_adapter *adapter)
 		be_cmd_set_logical_link_config(adapter,
 					       IFLA_VF_LINK_STATE_AUTO, 0);
 
+	/* BE3 EVB echoes broadcast/multicast packets back to PF's vport
+	 * confusing a linux bridge or OVS that it might be connected to.
+	 * Set the EVB to PASSTHRU mode which effectively disables the EVB
+	 * when SRIOV is not enabled.
+	 */
+	if (BE3_chip(adapter))
+		be_cmd_set_hsw_config(adapter, 0, 0, adapter->if_handle,
+				      PORT_FWD_TYPE_PASSTHRU, 0);
+
 	if (adapter->num_vfs)
 		be_vf_setup(adapter);
 
@@ -4651,7 +4728,6 @@ static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 				       0, 0, nlflags, filter_mask, NULL);
 }
 
-#ifdef CONFIG_BE2NET_VXLAN
 /* VxLAN offload Notes:
  *
  * The stack defines tunnel offload flags (hw_enc_features) for IP and doesn't
@@ -4666,13 +4742,17 @@ static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
  * adds more than one port, disable offloads and don't re-enable them again
  * until after all the tunnels are removed.
  */
-static void be_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
-			      __be16 port)
+static void be_add_vxlan_port(struct net_device *netdev,
+			      struct udp_tunnel_info *ti)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct device *dev = &adapter->pdev->dev;
+	__be16 port = ti->port;
 	int status;
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
 	if (lancer_chip(adapter) || BEx_chip(adapter) || be_is_mc(adapter))
 		return;
 
@@ -4720,10 +4800,14 @@ err:
 	be_disable_vxlan_offloads(adapter);
 }
 
-static void be_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
-			      __be16 port)
+static void be_del_vxlan_port(struct net_device *netdev,
+			      struct udp_tunnel_info *ti)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
+	__be16 port = ti->port;
+
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
 
 	if (lancer_chip(adapter) || BEx_chip(adapter) || be_is_mc(adapter))
 		return;
@@ -4785,7 +4869,6 @@ static netdev_features_t be_features_check(struct sk_buff *skb,
 
 	return features;
 }
-#endif
 
 static int be_get_phys_port_id(struct net_device *dev,
 			       struct netdev_phys_item_id *ppid)
@@ -4833,11 +4916,9 @@ static const struct net_device_ops be_netdev_ops = {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= be_busy_poll,
 #endif
-#ifdef CONFIG_BE2NET_VXLAN
-	.ndo_add_vxlan_port	= be_add_vxlan_port,
-	.ndo_del_vxlan_port	= be_del_vxlan_port,
+	.ndo_udp_tunnel_add	= be_add_vxlan_port,
+	.ndo_udp_tunnel_del	= be_del_vxlan_port,
 	.ndo_features_check	= be_features_check,
-#endif
 	.ndo_get_phys_port_id   = be_get_phys_port_id,
 };
 
@@ -5410,9 +5491,6 @@ static int be_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	struct be_adapter *adapter = pci_get_drvdata(pdev);
 
-	if (adapter->wol_en)
-		be_setup_wol(adapter, true);
-
 	be_intr_set(adapter, false);
 	be_cancel_err_detection(adapter);
 
@@ -5441,9 +5519,6 @@ static int be_pci_resume(struct pci_dev *pdev)
 
 	be_schedule_err_detection(adapter, ERR_DETECTION_DELAY);
 
-	if (adapter->wol_en)
-		be_setup_wol(adapter, false);
-
 	return 0;
 }
 
@@ -5552,7 +5627,7 @@ err:
 static int be_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 {
 	struct be_adapter *adapter = pci_get_drvdata(pdev);
-	u16 num_vf_qs;
+	struct be_resources vft_res = {0};
 	int status;
 
 	if (!num_vfs)
@@ -5575,9 +5650,10 @@ static int be_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	 * Also, this is done by FW in Lancer chip.
 	 */
 	if (skyhawk_chip(adapter) && !pci_num_vf(pdev)) {
-		num_vf_qs = be_calculate_vf_qs(adapter, adapter->num_vfs);
+		be_calculate_vf_res(adapter, adapter->num_vfs,
+				    &vft_res);
 		status = be_cmd_set_sriov_config(adapter, adapter->pool_res,
-						 adapter->num_vfs, num_vf_qs);
+						 adapter->num_vfs, &vft_res);
 		if (status)
 			dev_err(&pdev->dev,
 				"Failed to optimize SR-IOV resources\n");
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.c b/drivers/net/ethernet/emulex/benet/be_roce.c
index 4089156a7f5e..2b62841c4c63 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.c
+++ b/drivers/net/ethernet/emulex/benet/be_roce.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2015 Emulex
+ * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.h b/drivers/net/ethernet/emulex/benet/be_roce.h
index fde609789483..e51719a7307f 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.h
+++ b/drivers/net/ethernet/emulex/benet/be_roce.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2015 Emulex
+ * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 41b010645100..4edb98c3c6c7 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1195,7 +1195,7 @@ static int ethoc_probe(struct platform_device *pdev)
 	priv->mdio = mdiobus_alloc();
 	if (!priv->mdio) {
 		ret = -ENOMEM;
-		goto free;
+		goto free2;
 	}
 
 	priv->mdio->name = "ethoc-mdio";
@@ -1208,7 +1208,7 @@ static int ethoc_probe(struct platform_device *pdev)
 	ret = mdiobus_register(priv->mdio);
 	if (ret) {
 		dev_err(&netdev->dev, "failed to register MDIO bus\n");
-		goto free;
+		goto free2;
 	}
 
 	ret = ethoc_mdio_probe(netdev);
@@ -1241,9 +1241,10 @@ error2:
 error:
 	mdiobus_unregister(priv->mdio);
 	mdiobus_free(priv->mdio);
-free:
+free2:
 	if (priv->clk)
 		clk_disable_unprepare(priv->clk);
+free:
 	free_netdev(netdev);
 out:
 	return ret;
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index f58f9ea51639..92fd5c0bf4df 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -442,6 +442,8 @@ struct bufdesc_ex {
 #define FEC_QUIRK_SINGLE_MDIO		(1 << 11)
 /* Controller supports RACC register */
 #define FEC_QUIRK_HAS_RACC		(1 << 12)
+/* Controller supports interrupt coalesc */
+#define FEC_QUIRK_HAS_COALESCE		(1 << 13)
 
 struct bufdesc_prop {
 	int qid;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 3c0255e98535..4040003a74f9 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -111,7 +111,13 @@ static struct platform_device_id fec_devtype[] = {
 				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
 				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
 				FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
-				FEC_QUIRK_HAS_RACC,
+				FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE,
+	}, {
+		.name = "imx6ul-fec",
+		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
+				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
+				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_BUG_CAPTURE |
+				FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE,
 	}, {
 		/* sentinel */
 	}
@@ -125,6 +131,7 @@ enum imx_fec_type {
 	IMX6Q_FEC,
 	MVF600_FEC,
 	IMX6SX_FEC,
+	IMX6UL_FEC,
 };
 
 static const struct of_device_id fec_dt_ids[] = {
@@ -134,6 +141,7 @@ static const struct of_device_id fec_dt_ids[] = {
 	{ .compatible = "fsl,imx6q-fec", .data = &fec_devtype[IMX6Q_FEC], },
 	{ .compatible = "fsl,mvf600-fec", .data = &fec_devtype[MVF600_FEC], },
 	{ .compatible = "fsl,imx6sx-fec", .data = &fec_devtype[IMX6SX_FEC], },
+	{ .compatible = "fsl,imx6ul-fec", .data = &fec_devtype[IMX6UL_FEC], },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fec_dt_ids);
@@ -2358,9 +2366,6 @@ static void fec_enet_itr_coal_set(struct net_device *ndev)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int rx_itr, tx_itr;
 
-	if (!(fep->quirks & FEC_QUIRK_HAS_AVB))
-		return;
-
 	/* Must be greater than zero to avoid unpredictable behavior */
 	if (!fep->rx_time_itr || !fep->rx_pkts_itr ||
 	    !fep->tx_time_itr || !fep->tx_pkts_itr)
@@ -2383,10 +2388,12 @@ static void fec_enet_itr_coal_set(struct net_device *ndev)
 
 	writel(tx_itr, fep->hwp + FEC_TXIC0);
 	writel(rx_itr, fep->hwp + FEC_RXIC0);
-	writel(tx_itr, fep->hwp + FEC_TXIC1);
-	writel(rx_itr, fep->hwp + FEC_RXIC1);
-	writel(tx_itr, fep->hwp + FEC_TXIC2);
-	writel(rx_itr, fep->hwp + FEC_RXIC2);
+	if (fep->quirks & FEC_QUIRK_HAS_AVB) {
+		writel(tx_itr, fep->hwp + FEC_TXIC1);
+		writel(rx_itr, fep->hwp + FEC_RXIC1);
+		writel(tx_itr, fep->hwp + FEC_TXIC2);
+		writel(rx_itr, fep->hwp + FEC_RXIC2);
+	}
 }
 
 static int
@@ -2394,7 +2401,7 @@ fec_enet_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
-	if (!(fep->quirks & FEC_QUIRK_HAS_AVB))
+	if (!(fep->quirks & FEC_QUIRK_HAS_COALESCE))
 		return -EOPNOTSUPP;
 
 	ec->rx_coalesce_usecs = fep->rx_time_itr;
@@ -2412,28 +2419,28 @@ fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	unsigned int cycle;
 
-	if (!(fep->quirks & FEC_QUIRK_HAS_AVB))
+	if (!(fep->quirks & FEC_QUIRK_HAS_COALESCE))
 		return -EOPNOTSUPP;
 
 	if (ec->rx_max_coalesced_frames > 255) {
-		pr_err("Rx coalesced frames exceed hardware limiation");
+		pr_err("Rx coalesced frames exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
 	if (ec->tx_max_coalesced_frames > 255) {
-		pr_err("Tx coalesced frame exceed hardware limiation");
+		pr_err("Tx coalesced frame exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
 	cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
 	if (cycle > 0xFFFF) {
-		pr_err("Rx coalesed usec exceeed hardware limiation");
+		pr_err("Rx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
 	cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
 	if (cycle > 0xFFFF) {
-		pr_err("Rx coalesed usec exceeed hardware limiation");
+		pr_err("Rx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
@@ -3191,7 +3198,12 @@ static void fec_reset_phy(struct platform_device *pdev)
 		dev_err(&pdev->dev, "failed to get phy-reset-gpios: %d\n", err);
 		return;
 	}
-	msleep(msec);
+
+	if (msec > 20)
+		msleep(msec);
+	else
+		usleep_range(msec * 1000, msec * 1000 + 1000);
+
 	gpio_set_value_cansleep(phy_reset, !active_high);
 }
 #else /* CONFIG_OF */
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 7615e0668acb..d20935dc8399 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2275,7 +2275,7 @@ static inline void gfar_tx_checksum(struct sk_buff *skb, struct txfcb *fcb,
 	fcb->flags = flags;
 }
 
-void inline gfar_tx_vlan(struct sk_buff *skb, struct txfcb *fcb)
+static inline void gfar_tx_vlan(struct sk_buff *skb, struct txfcb *fcb)
 {
 	fcb->flags |= TXFCB_VLN;
 	fcb->vlctl = cpu_to_be16(skb_vlan_tag_get(skb));
@@ -2440,7 +2440,8 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 						 tx_queue->tx_ring_size);
 
 	if (likely(!nr_frags)) {
-		lstatus |= BD_LFLAG(TXBD_LAST | TXBD_INTERRUPT);
+		if (likely(!do_tstamp))
+			lstatus |= BD_LFLAG(TXBD_LAST | TXBD_INTERRUPT);
 	} else {
 		u32 lstatus_start = lstatus;
 
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 4ccc032633c4..2e2566230e27 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -5,7 +5,7 @@
 config NET_VENDOR_HISILICON
 	bool "Hisilicon devices"
 	default y
-	depends on OF && HAS_DMA
+	depends on (OF || ACPI) && HAS_DMA
 	depends on ARM || ARM64 || COMPILE_TEST
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
index b9f2ea59308a..275618bb4646 100644
--- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
@@ -218,7 +218,6 @@ struct hix5hd2_priv {
 	struct device *dev;
 	struct net_device *netdev;
 
-	struct phy_device *phy;
 	struct device_node *phy_node;
 	phy_interface_t	phy_mode;
 
@@ -402,7 +401,7 @@ static int hix5hd2_net_set_mac_address(struct net_device *dev, void *p)
 static void hix5hd2_adjust_link(struct net_device *dev)
 {
 	struct hix5hd2_priv *priv = netdev_priv(dev);
-	struct phy_device *phy = priv->phy;
+	struct phy_device *phy = dev->phydev;
 
 	if ((priv->speed != phy->speed) || (priv->duplex != phy->duplex)) {
 		hix5hd2_config_port(dev, phy->speed, phy->duplex);
@@ -679,6 +678,7 @@ static void hix5hd2_free_dma_desc_rings(struct hix5hd2_priv *priv)
 static int hix5hd2_net_open(struct net_device *dev)
 {
 	struct hix5hd2_priv *priv = netdev_priv(dev);
+	struct phy_device *phy;
 	int ret;
 
 	ret = clk_prepare_enable(priv->clk);
@@ -687,12 +687,12 @@ static int hix5hd2_net_open(struct net_device *dev)
 		return ret;
 	}
 
-	priv->phy = of_phy_connect(dev, priv->phy_node,
-				   &hix5hd2_adjust_link, 0, priv->phy_mode);
-	if (!priv->phy)
+	phy = of_phy_connect(dev, priv->phy_node,
+			     &hix5hd2_adjust_link, 0, priv->phy_mode);
+	if (!phy)
 		return -ENODEV;
 
-	phy_start(priv->phy);
+	phy_start(phy);
 	hix5hd2_hw_init(priv);
 	hix5hd2_rx_refill(priv);
 
@@ -716,9 +716,9 @@ static int hix5hd2_net_close(struct net_device *dev)
 	netif_stop_queue(dev);
 	hix5hd2_free_dma_desc_rings(priv);
 
-	if (priv->phy) {
-		phy_stop(priv->phy);
-		phy_disconnect(priv->phy);
+	if (dev->phydev) {
+		phy_stop(dev->phydev);
+		phy_disconnect(dev->phydev);
 	}
 
 	clk_disable_unprepare(priv->clk);
@@ -750,32 +750,10 @@ static const struct net_device_ops hix5hd2_netdev_ops = {
 	.ndo_set_mac_address	= hix5hd2_net_set_mac_address,
 };
 
-static int hix5hd2_get_settings(struct net_device *net_dev,
-				struct ethtool_cmd *cmd)
-{
-	struct hix5hd2_priv *priv = netdev_priv(net_dev);
-
-	if (!priv->phy)
-		return -ENODEV;
-
-	return phy_ethtool_gset(priv->phy, cmd);
-}
-
-static int hix5hd2_set_settings(struct net_device *net_dev,
-				struct ethtool_cmd *cmd)
-{
-	struct hix5hd2_priv *priv = netdev_priv(net_dev);
-
-	if (!priv->phy)
-		return -ENODEV;
-
-	return phy_ethtool_sset(priv->phy, cmd);
-}
-
 static struct ethtool_ops hix5hd2_ethtools_ops = {
 	.get_link		= ethtool_op_get_link,
-	.get_settings		= hix5hd2_get_settings,
-	.set_settings		= hix5hd2_set_settings,
+	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
 static int hix5hd2_mdio_wait_ready(struct mii_bus *bus)
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index 5d3047cc8380..c54c6fac0d1d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -400,7 +400,6 @@ int hnae_ae_register(struct hnae_ae_dev *hdev, struct module *owner)
 
 	if (!hdev->ops || !hdev->ops->get_handle ||
 	    !hdev->ops->toggle_ring_irq ||
-	    !hdev->ops->toggle_queue_status ||
 	    !hdev->ops->get_status || !hdev->ops->adjust_link)
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index 529cb1341270..e093cbf26c8c 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -363,6 +363,14 @@ enum hnae_port_type {
 	HNAE_PORT_DEBUG
 };
 
+/* mac media type */
+enum hnae_media_type {
+	HNAE_MEDIA_TYPE_UNKNOWN = 0,
+	HNAE_MEDIA_TYPE_FIBER,
+	HNAE_MEDIA_TYPE_COPPER,
+	HNAE_MEDIA_TYPE_BACKPLANE,
+};
+
 /* This struct defines the operation on the handle.
  *
  * get_handle(): (mandatory)
@@ -454,7 +462,6 @@ struct hnae_ae_ops {
 	int (*get_info)(struct hnae_handle *handle,
 			u8 *auto_neg, u16 *speed, u8 *duplex);
 	void (*toggle_ring_irq)(struct hnae_ring *ring, u32 val);
-	void (*toggle_queue_status)(struct hnae_queue *queue, u32 val);
 	void (*adjust_link)(struct hnae_handle *handle, int speed, int duplex);
 	int (*set_loopback)(struct hnae_handle *handle,
 			    enum hnae_loop loop_mode, int en);
@@ -473,6 +480,11 @@ struct hnae_ae_ops {
 	int (*set_coalesce_usecs)(struct hnae_handle *handle, u32 timeout);
 	int (*set_coalesce_frames)(struct hnae_handle *handle,
 				   u32 coalesce_frames);
+	void (*get_coalesce_range)(struct hnae_handle *handle,
+				   u32 *tx_frames_low, u32 *rx_frames_low,
+				   u32 *tx_frames_high, u32 *rx_frames_high,
+				   u32 *tx_usecs_low, u32 *rx_usecs_low,
+				   u32 *tx_usecs_high, u32 *rx_usecs_high);
 	void (*set_promisc_mode)(struct hnae_handle *handle, u32 en);
 	int (*get_mac_addr)(struct hnae_handle *handle, void **p);
 	int (*set_mac_addr)(struct hnae_handle *handle, void *p);
@@ -521,6 +533,7 @@ struct hnae_handle {
 	u32 eport_id;
 	u32 dport_id;	/* v2 tx bd should fill the dport_id */
 	enum hnae_port_type port_type;
+	enum hnae_media_type media_type;
 	struct list_head node;    /* list to hnae_ae_dev->handle_list */
 	struct hnae_buf_ops *bops; /* operation for the buffer */
 	struct hnae_queue **qs;  /* array base of all queues */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index d37b778b4a1b..e28d960997af 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -134,6 +134,7 @@ struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev,
 	ae_handle->phy_dev = vf_cb->mac_cb->phy_dev;
 	ae_handle->if_support = vf_cb->mac_cb->if_support;
 	ae_handle->port_type = vf_cb->mac_cb->mac_type;
+	ae_handle->media_type = vf_cb->mac_cb->media_type;
 	ae_handle->dport_id = port_id;
 
 	return ae_handle;
@@ -247,12 +248,21 @@ static void hns_ae_set_tso_stats(struct hnae_handle *handle, int enable)
 static int hns_ae_start(struct hnae_handle *handle)
 {
 	int ret;
+	int k;
 	struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
 
 	ret = hns_mac_vm_config_bc_en(mac_cb, 0, true);
 	if (ret)
 		return ret;
 
+	for (k = 0; k < handle->q_num; k++) {
+		if (AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver))
+			hns_rcb_int_clr_hw(handle->qs[k],
+					   RCB_INT_FLAG_TX | RCB_INT_FLAG_RX);
+		else
+			hns_rcbv2_int_clr_hw(handle->qs[k],
+					     RCB_INT_FLAG_TX | RCB_INT_FLAG_RX);
+	}
 	hns_ae_ring_enable_all(handle, 1);
 	msleep(100);
 
@@ -313,18 +323,6 @@ static void hns_aev2_toggle_ring_irq(struct hnae_ring *ring, u32 mask)
 	hns_rcbv2_int_ctrl_hw(ring->q, flag, mask);
 }
 
-static void hns_ae_toggle_queue_status(struct hnae_queue *queue, u32 val)
-{
-	struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(queue->dev);
-
-	if (AE_IS_VER1(dsaf_dev->dsaf_ver))
-		hns_rcb_int_clr_hw(queue, RCB_INT_FLAG_TX | RCB_INT_FLAG_RX);
-	else
-		hns_rcbv2_int_clr_hw(queue, RCB_INT_FLAG_TX | RCB_INT_FLAG_RX);
-
-	hns_rcb_start(queue, val);
-}
-
 static int hns_ae_get_link_status(struct hnae_handle *handle)
 {
 	u32 link_status;
@@ -465,6 +463,30 @@ static int  hns_ae_set_coalesce_frames(struct hnae_handle *handle,
 		ring_pair->port_id_in_comm, coalesce_frames);
 }
 
+static void hns_ae_get_coalesce_range(struct hnae_handle *handle,
+				      u32 *tx_frames_low, u32 *rx_frames_low,
+				      u32 *tx_frames_high, u32 *rx_frames_high,
+				      u32 *tx_usecs_low, u32 *rx_usecs_low,
+				      u32 *tx_usecs_high, u32 *rx_usecs_high)
+{
+	struct dsaf_device *dsaf_dev;
+
+	dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
+
+	*tx_frames_low  = HNS_RCB_MIN_COALESCED_FRAMES;
+	*rx_frames_low  = HNS_RCB_MIN_COALESCED_FRAMES;
+	*tx_frames_high =
+		(dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ?
+		HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1;
+	*rx_frames_high =
+		(dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ?
+		 HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1;
+	*tx_usecs_low   = 0;
+	*rx_usecs_low   = 0;
+	*tx_usecs_high  = HNS_RCB_MAX_COALESCED_USECS;
+	*rx_usecs_high  = HNS_RCB_MAX_COALESCED_USECS;
+}
+
 void hns_ae_update_stats(struct hnae_handle *handle,
 			 struct net_device_stats *net_stats)
 {
@@ -587,6 +609,7 @@ void hns_ae_get_strings(struct hnae_handle *handle,
 	int idx;
 	struct hns_mac_cb *mac_cb;
 	struct hns_ppe_cb *ppe_cb;
+	struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
 	u8 *p = data;
 	struct	hnae_vf_cb *vf_cb;
 
@@ -609,13 +632,14 @@ void hns_ae_get_strings(struct hnae_handle *handle,
 	p += ETH_GSTRING_LEN * hns_mac_get_sset_count(mac_cb, stringset);
 
 	if (mac_cb->mac_type == HNAE_PORT_SERVICE)
-		hns_dsaf_get_strings(stringset, p, port);
+		hns_dsaf_get_strings(stringset, p, port, dsaf_dev);
 }
 
 int hns_ae_get_sset_count(struct hnae_handle *handle, int stringset)
 {
 	u32 sset_count = 0;
 	struct hns_mac_cb *mac_cb;
+	struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
 
 	assert(handle);
 
@@ -626,7 +650,7 @@ int hns_ae_get_sset_count(struct hnae_handle *handle, int stringset)
 	sset_count += hns_mac_get_sset_count(mac_cb, stringset);
 
 	if (mac_cb->mac_type == HNAE_PORT_SERVICE)
-		sset_count += hns_dsaf_get_sset_count(stringset);
+		sset_count += hns_dsaf_get_sset_count(dsaf_dev, stringset);
 
 	return sset_count;
 }
@@ -782,7 +806,6 @@ static struct hnae_ae_ops hns_dsaf_ops = {
 	.stop = hns_ae_stop,
 	.reset = hns_ae_reset,
 	.toggle_ring_irq = hns_ae_toggle_ring_irq,
-	.toggle_queue_status = hns_ae_toggle_queue_status,
 	.get_status = hns_ae_get_link_status,
 	.get_info = hns_ae_get_mac_info,
 	.adjust_link = hns_ae_adjust_link,
@@ -796,6 +819,7 @@ static struct hnae_ae_ops hns_dsaf_ops = {
 	.get_rx_max_coalesced_frames = hns_ae_get_rx_max_coalesced_frames,
 	.set_coalesce_usecs = hns_ae_set_coalesce_usecs,
 	.set_coalesce_frames = hns_ae_set_coalesce_frames,
+	.get_coalesce_range = hns_ae_get_coalesce_range,
 	.set_promisc_mode = hns_ae_set_promisc_mode,
 	.set_mac_addr = hns_ae_set_mac_address,
 	.set_mc_addr = hns_ae_set_multicast_one,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index c526558e6367..3fb87e233c49 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -56,20 +56,6 @@ static const enum mac_mode g_mac_mode_1000[] = {
 	[PHY_INTERFACE_MODE_RTBI]   = MAC_MODE_RTBI_1000
 };
 
-static enum mac_mode hns_mac_dev_to_enet_if(const struct hns_mac_cb *mac_cb)
-{
-	switch (mac_cb->max_speed) {
-	case MAC_SPEED_100:
-		return g_mac_mode_100[mac_cb->phy_if];
-	case MAC_SPEED_1000:
-		return g_mac_mode_1000[mac_cb->phy_if];
-	case MAC_SPEED_10000:
-		return MAC_MODE_XGMII_10000;
-	default:
-		return MAC_MODE_MII_100;
-	}
-}
-
 static enum mac_mode hns_get_enet_interface(const struct hns_mac_cb *mac_cb)
 {
 	switch (mac_cb->max_speed) {
@@ -134,7 +120,6 @@ void hns_mac_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex)
 
 	mac_cb->speed = speed;
 	mac_cb->half_duplex = !duplex;
-	mac_ctrl_drv->mac_mode = hns_mac_dev_to_enet_if(mac_cb);
 
 	if (mac_ctrl_drv->adjust_link) {
 		ret = mac_ctrl_drv->adjust_link(mac_ctrl_drv,
@@ -748,6 +733,18 @@ static void hns_mac_register_phy(struct hns_mac_cb *mac_cb)
 			mac_cb->mac_id, addr);
 }
 
+#define MAC_MEDIA_TYPE_MAX_LEN		16
+
+static const struct {
+	enum hnae_media_type value;
+	const char *name;
+} media_type_defs[] = {
+	{HNAE_MEDIA_TYPE_UNKNOWN,	"unknown" },
+	{HNAE_MEDIA_TYPE_FIBER,		"fiber" },
+	{HNAE_MEDIA_TYPE_COPPER,	"copper" },
+	{HNAE_MEDIA_TYPE_BACKPLANE,	"backplane" },
+};
+
 /**
  *hns_mac_get_info  - get mac information from device node
  *@mac_cb: mac device
@@ -759,10 +756,13 @@ static int  hns_mac_get_info(struct hns_mac_cb *mac_cb)
 	struct device_node *np;
 	struct regmap *syscon;
 	struct of_phandle_args cpld_args;
+	const char *media_type;
+	u32 i;
 	u32 ret;
 
 	mac_cb->link = false;
 	mac_cb->half_duplex = false;
+	mac_cb->media_type = HNAE_MEDIA_TYPE_UNKNOWN;
 	mac_cb->speed = mac_phy_to_speed[mac_cb->phy_if];
 	mac_cb->max_speed = mac_cb->speed;
 
@@ -864,6 +864,17 @@ static int  hns_mac_get_info(struct hns_mac_cb *mac_cb)
 			mac_cb->mac_id);
 	}
 
+	if (!fwnode_property_read_string(mac_cb->fw_port, "media-type",
+					 &media_type)) {
+		for (i = 0; i < ARRAY_SIZE(media_type_defs); i++) {
+			if (!strncmp(media_type_defs[i].name, media_type,
+				     MAC_MEDIA_TYPE_MAX_LEN)) {
+				mac_cb->media_type = media_type_defs[i].value;
+				break;
+			}
+		}
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
index 05a6e8f7a419..4cbdf14f5c16 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
@@ -335,6 +335,7 @@ struct hns_mac_cb {
 	u64 txpkt_for_led;
 	u64 rxpkt_for_led;
 	enum hnae_port_type mac_type;
+	enum hnae_media_type media_type;
 	phy_interface_t phy_if;
 	enum hnae_loop loop_mode;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index ac03c4a53e08..2ef4277d00b3 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -114,9 +114,9 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 
 			dsaf_dev->sc_base = devm_ioremap_resource(&pdev->dev,
 								  res);
-			if (!dsaf_dev->sc_base) {
+			if (IS_ERR(dsaf_dev->sc_base)) {
 				dev_err(dsaf_dev->dev, "subctrl can not map!\n");
-				return -ENOMEM;
+				return PTR_ERR(dsaf_dev->sc_base);
 			}
 
 			res = platform_get_resource(pdev, IORESOURCE_MEM,
@@ -128,9 +128,9 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 
 			dsaf_dev->sds_base = devm_ioremap_resource(&pdev->dev,
 								   res);
-			if (!dsaf_dev->sds_base) {
+			if (IS_ERR(dsaf_dev->sds_base)) {
 				dev_err(dsaf_dev->dev, "serdes-ctrl can not map!\n");
-				return -ENOMEM;
+				return PTR_ERR(dsaf_dev->sds_base);
 			}
 		} else {
 			dsaf_dev->sub_ctrl = syscon;
@@ -146,9 +146,9 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 		}
 	}
 	dsaf_dev->ppe_base = devm_ioremap_resource(&pdev->dev, res);
-	if (!dsaf_dev->ppe_base) {
+	if (IS_ERR(dsaf_dev->ppe_base)) {
 		dev_err(dsaf_dev->dev, "ppe-base resource can not map!\n");
-		return -ENOMEM;
+		return PTR_ERR(dsaf_dev->ppe_base);
 	}
 	dsaf_dev->ppe_paddr = res->start;
 
@@ -165,9 +165,9 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 			}
 		}
 		dsaf_dev->io_base = devm_ioremap_resource(&pdev->dev, res);
-		if (!dsaf_dev->io_base) {
+		if (IS_ERR(dsaf_dev->io_base)) {
 			dev_err(dsaf_dev->dev, "dsaf-base resource can not map!\n");
-			return -ENOMEM;
+			return PTR_ERR(dsaf_dev->io_base);
 		}
 	}
 
@@ -176,7 +176,7 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 	    desc_num > HNS_DSAF_MAX_DESC_CNT) {
 		dev_err(dsaf_dev->dev, "get desc-num(%d) fail, ret=%d!\n",
 			desc_num, ret);
-		goto unmap_base_addr;
+		return -EINVAL;
 	}
 	dsaf_dev->desc_num = desc_num;
 
@@ -192,7 +192,7 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 	if (ret < 0) {
 		dev_err(dsaf_dev->dev,
 			"get buf-size fail, ret=%d!\r\n", ret);
-		goto unmap_base_addr;
+		return ret;
 	}
 	dsaf_dev->buf_size = buf_size;
 
@@ -200,7 +200,7 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 	if (dsaf_dev->buf_size_type < 0) {
 		dev_err(dsaf_dev->dev,
 			"buf_size(%d) is wrong!\n", buf_size);
-		goto unmap_base_addr;
+		return -EINVAL;
 	}
 
 	dsaf_dev->misc_op = hns_misc_op_get(dsaf_dev);
@@ -213,32 +213,6 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 		dev_err(dsaf_dev->dev, "set mask to 64bit fail!\n");
 
 	return 0;
-
-unmap_base_addr:
-	if (dsaf_dev->io_base)
-		iounmap(dsaf_dev->io_base);
-	if (dsaf_dev->ppe_base)
-		iounmap(dsaf_dev->ppe_base);
-	if (dsaf_dev->sds_base)
-		iounmap(dsaf_dev->sds_base);
-	if (dsaf_dev->sc_base)
-		iounmap(dsaf_dev->sc_base);
-	return ret;
-}
-
-static void hns_dsaf_free_cfg(struct dsaf_device *dsaf_dev)
-{
-	if (dsaf_dev->io_base)
-		iounmap(dsaf_dev->io_base);
-
-	if (dsaf_dev->ppe_base)
-		iounmap(dsaf_dev->ppe_base);
-
-	if (dsaf_dev->sds_base)
-		iounmap(dsaf_dev->sds_base);
-
-	if (dsaf_dev->sc_base)
-		iounmap(dsaf_dev->sc_base);
 }
 
 /**
@@ -542,10 +516,10 @@ static void hns_dsafv2_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev)
 		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 110);
+			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 48);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 160);
+			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 80);
 		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
 
 		/* for no enable pfc mode */
@@ -553,29 +527,39 @@ static void hns_dsafv2_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev)
 		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 128);
+			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 192);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 192);
+			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 240);
 		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
 	}
 
 	/* PPE */
-	reg = DSAF_SBM_BP_CFG_2_PPE_REG_0_REG + 0x80 * i;
-	o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
-	dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG2_SET_BUF_NUM_M,
-		       DSAFV2_SBM_CFG2_SET_BUF_NUM_S, 10);
-	dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG2_RESET_BUF_NUM_M,
-		       DSAFV2_SBM_CFG2_RESET_BUF_NUM_S, 12);
-	dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
+	for (i = 0; i < DSAFV2_SBM_PPE_CHN; i++) {
+		reg = DSAF_SBM_BP_CFG_2_PPE_REG_0_REG + 0x80 * i;
+		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
+		dsaf_set_field(o_sbm_bp_cfg,
+			       DSAFV2_SBM_CFG2_PPE_SET_BUF_NUM_M,
+			       DSAFV2_SBM_CFG2_PPE_SET_BUF_NUM_S, 2);
+		dsaf_set_field(o_sbm_bp_cfg,
+			       DSAFV2_SBM_CFG2_PPE_RESET_BUF_NUM_M,
+			       DSAFV2_SBM_CFG2_PPE_RESET_BUF_NUM_S, 3);
+		dsaf_set_field(o_sbm_bp_cfg,
+			       DSAFV2_SBM_CFG2_PPE_CFG_USEFUL_NUM_M,
+			       DSAFV2_SBM_CFG2_PPE_CFG_USEFUL_NUM_S, 52);
+		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
+	}
+
 	/* RoCEE */
 	for (i = 0; i < DASFV2_ROCEE_CRD_NUM; i++) {
 		reg = DSAFV2_SBM_BP_CFG_2_ROCEE_REG_0_REG + 0x80 * i;
 		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
-		dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG2_SET_BUF_NUM_M,
-			       DSAFV2_SBM_CFG2_SET_BUF_NUM_S, 2);
-		dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG2_RESET_BUF_NUM_M,
-			       DSAFV2_SBM_CFG2_RESET_BUF_NUM_S, 4);
+		dsaf_set_field(o_sbm_bp_cfg,
+			       DSAFV2_SBM_CFG2_ROCEE_SET_BUF_NUM_M,
+			       DSAFV2_SBM_CFG2_ROCEE_SET_BUF_NUM_S, 2);
+		dsaf_set_field(o_sbm_bp_cfg,
+			       DSAFV2_SBM_CFG2_ROCEE_RESET_BUF_NUM_M,
+			       DSAFV2_SBM_CFG2_ROCEE_RESET_BUF_NUM_S, 4);
 		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
 	}
 }
@@ -886,6 +870,8 @@ static void hns_dsaf_single_line_tbl_cfg(
 	struct dsaf_device *dsaf_dev,
 	u32 address, struct dsaf_tbl_line_cfg *ptbl_line)
 {
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_line_addr_cfg(dsaf_dev, address);
 
@@ -894,6 +880,8 @@ static void hns_dsaf_single_line_tbl_cfg(
 
 	/*Write Plus*/
 	hns_dsaf_tbl_line_pul(dsaf_dev);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -907,6 +895,8 @@ static void hns_dsaf_tcam_uc_cfg(
 	struct dsaf_tbl_tcam_data *ptbl_tcam_data,
 	struct dsaf_tbl_tcam_ucast_cfg *ptbl_tcam_ucast)
 {
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address);
 	/*Write Tcam Data*/
@@ -915,6 +905,8 @@ static void hns_dsaf_tcam_uc_cfg(
 	hns_dsaf_tbl_tcam_ucast_cfg(dsaf_dev, ptbl_tcam_ucast);
 	/*Write Plus*/
 	hns_dsaf_tbl_tcam_data_ucast_pul(dsaf_dev);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -929,6 +921,8 @@ static void hns_dsaf_tcam_mc_cfg(
 	struct dsaf_tbl_tcam_data *ptbl_tcam_data,
 	struct dsaf_tbl_tcam_mcast_cfg *ptbl_tcam_mcast)
 {
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address);
 	/*Write Tcam Data*/
@@ -937,6 +931,8 @@ static void hns_dsaf_tcam_mc_cfg(
 	hns_dsaf_tbl_tcam_mcast_cfg(dsaf_dev, ptbl_tcam_mcast);
 	/*Write Plus*/
 	hns_dsaf_tbl_tcam_data_mcast_pul(dsaf_dev);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -946,6 +942,8 @@ static void hns_dsaf_tcam_mc_cfg(
  */
 static void hns_dsaf_tcam_mc_invld(struct dsaf_device *dsaf_dev, u32 address)
 {
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address);
 
@@ -958,6 +956,8 @@ static void hns_dsaf_tcam_mc_invld(struct dsaf_device *dsaf_dev, u32 address)
 
 	/*Write Plus*/
 	hns_dsaf_tbl_tcam_mcast_pul(dsaf_dev);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -975,6 +975,8 @@ static void hns_dsaf_tcam_uc_get(
 	u32 tcam_read_data0;
 	u32 tcam_read_data4;
 
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address);
 
@@ -983,9 +985,9 @@ static void hns_dsaf_tcam_uc_get(
 
 	/*read tcam data*/
 	ptbl_tcam_data->tbl_tcam_data_high
-		= dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_LOW_0_REG);
-	ptbl_tcam_data->tbl_tcam_data_low
 		= dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_HIGH_0_REG);
+	ptbl_tcam_data->tbl_tcam_data_low
+		= dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_LOW_0_REG);
 
 	/*read tcam mcast*/
 	tcam_read_data0 = dsaf_read_dev(dsaf_dev,
@@ -1007,6 +1009,8 @@ static void hns_dsaf_tcam_uc_get(
 				 DSAF_TBL_UCAST_CFG1_OUT_PORT_S);
 	ptbl_tcam_ucast->tbl_ucast_dvc
 		= dsaf_get_bit(tcam_read_data0, DSAF_TBL_UCAST_CFG1_DVC_S);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -1023,6 +1027,8 @@ static void hns_dsaf_tcam_mc_get(
 {
 	u32 data_tmp;
 
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address);
 
@@ -1031,9 +1037,9 @@ static void hns_dsaf_tcam_mc_get(
 
 	/*read tcam data*/
 	ptbl_tcam_data->tbl_tcam_data_high =
-		dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_LOW_0_REG);
-	ptbl_tcam_data->tbl_tcam_data_low =
 		dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_HIGH_0_REG);
+	ptbl_tcam_data->tbl_tcam_data_low =
+		dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_LOW_0_REG);
 
 	/*read tcam mcast*/
 	ptbl_tcam_mcast->tbl_mcast_port_msk[0] =
@@ -1053,6 +1059,8 @@ static void hns_dsaf_tcam_mc_get(
 	ptbl_tcam_mcast->tbl_mcast_port_msk[4] =
 		dsaf_get_field(data_tmp, DSAF_TBL_MCAST_CFG4_VM128_112_M,
 			       DSAF_TBL_MCAST_CFG4_VM128_112_S);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -1114,10 +1122,10 @@ int hns_dsaf_set_rx_mac_pause_en(struct dsaf_device *dsaf_dev, int mac_id,
 				 u32 en)
 {
 	if (AE_IS_VER1(dsaf_dev->dsaf_ver)) {
-		if (!en)
+		if (!en) {
 			dev_err(dsaf_dev->dev, "dsafv1 can't close rx_pause!\n");
-
-		return -EINVAL;
+			return -EINVAL;
+		}
 	}
 
 	dsaf_set_dev_bit(dsaf_dev, DSAF_PAUSE_CFG_REG + mac_id * 4,
@@ -1377,6 +1385,7 @@ static int hns_dsaf_init(struct dsaf_device *dsaf_dev)
 	if (HNS_DSAF_IS_DEBUG(dsaf_dev))
 		return 0;
 
+	spin_lock_init(&dsaf_dev->tcam_lock);
 	ret = hns_dsaf_init_hw(dsaf_dev);
 	if (ret)
 		return ret;
@@ -2122,11 +2131,24 @@ void hns_dsaf_fix_mac_mode(struct hns_mac_cb *mac_cb)
 	hns_dsaf_port_work_rate_cfg(dsaf_dev, mac_id, mode);
 }
 
+static u32 hns_dsaf_get_inode_prio_reg(int index)
+{
+	int base_index, offset;
+	u32 base_addr = DSAF_INODE_IN_PRIO_PAUSE_BASE_REG;
+
+	base_index = (index + 1) / DSAF_REG_PER_ZONE;
+	offset = (index + 1) % DSAF_REG_PER_ZONE;
+
+	return base_addr + DSAF_INODE_IN_PRIO_PAUSE_BASE_OFFSET * base_index +
+		DSAF_INODE_IN_PRIO_PAUSE_OFFSET * offset;
+}
+
 void hns_dsaf_update_stats(struct dsaf_device *dsaf_dev, u32 node_num)
 {
 	struct dsaf_hw_stats *hw_stats
 		= &dsaf_dev->hw_stats[node_num];
 	bool is_ver1 = AE_IS_VER1(dsaf_dev->dsaf_ver);
+	int i;
 	u32 reg_tmp;
 
 	hw_stats->pad_drop += dsaf_read_dev(dsaf_dev,
@@ -2161,6 +2183,18 @@ void hns_dsaf_update_stats(struct dsaf_device *dsaf_dev, u32 node_num)
 	hw_stats->stp_drop += dsaf_read_dev(dsaf_dev,
 		DSAF_INODE_IN_DATA_STP_DISC_0_REG + 0x80 * (u64)node_num);
 
+	/* pfc pause frame statistics stored in dsaf inode*/
+	if ((node_num < DSAF_SERVICE_NW_NUM) && !is_ver1) {
+		for (i = 0; i < DSAF_PRIO_NR; i++) {
+			reg_tmp = hns_dsaf_get_inode_prio_reg(i);
+			hw_stats->rx_pfc[i] += dsaf_read_dev(dsaf_dev,
+				reg_tmp + 0x4 * (u64)node_num);
+			hw_stats->tx_pfc[i] += dsaf_read_dev(dsaf_dev,
+				DSAF_XOD_XGE_PFC_PRIO_CNT_BASE_REG +
+				DSAF_XOD_XGE_PFC_PRIO_CNT_OFFSET * i +
+				0xF0 * (u64)node_num);
+		}
+	}
 	hw_stats->tx_pkts += dsaf_read_dev(dsaf_dev,
 		DSAF_XOD_RCVPKT_CNT_0_REG + 0x90 * (u64)node_num);
 }
@@ -2498,38 +2532,53 @@ void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data)
 		p[i] = 0xdddddddd;
 }
 
-static char *hns_dsaf_get_node_stats_strings(char *data, int node)
+static char *hns_dsaf_get_node_stats_strings(char *data, int node,
+					     struct dsaf_device *dsaf_dev)
 {
 	char *buff = data;
+	int i;
+	bool is_ver1 = AE_IS_VER1(dsaf_dev->dsaf_ver);
 
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_pad_drop_pkts", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_manage_pkts", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_rx_pkts", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_rx_pkt_id", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_rx_pause_frame", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_release_buf_num", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_sbm_drop_pkts", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_crc_false_pkts", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_bp_drop_pkts", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_lookup_rslt_drop_pkts", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_local_rslt_fail_pkts", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_vlan_drop_pkts", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_stp_drop_pkts", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
+	if (node < DSAF_SERVICE_NW_NUM && !is_ver1) {
+		for (i = 0; i < DSAF_PRIO_NR; i++) {
+			snprintf(buff + 0 * ETH_GSTRING_LEN * DSAF_PRIO_NR,
+				 ETH_GSTRING_LEN, "inod%d_pfc_prio%d_pkts",
+				 node, i);
+			snprintf(buff + 1 * ETH_GSTRING_LEN * DSAF_PRIO_NR,
+				 ETH_GSTRING_LEN, "onod%d_pfc_prio%d_pkts",
+				 node, i);
+			buff += ETH_GSTRING_LEN;
+		}
+		buff += 1 * DSAF_PRIO_NR * ETH_GSTRING_LEN;
+	}
 	snprintf(buff, ETH_GSTRING_LEN, "onnod%d_tx_pkts", node);
-	buff = buff + ETH_GSTRING_LEN;
+	buff += ETH_GSTRING_LEN;
 
 	return buff;
 }
@@ -2538,7 +2587,9 @@ static u64 *hns_dsaf_get_node_stats(struct dsaf_device *ddev, u64 *data,
 				    int node_num)
 {
 	u64 *p = data;
+	int i;
 	struct dsaf_hw_stats *hw_stats = &ddev->hw_stats[node_num];
+	bool is_ver1 = AE_IS_VER1(ddev->dsaf_ver);
 
 	p[0] = hw_stats->pad_drop;
 	p[1] = hw_stats->man_pkts;
@@ -2553,8 +2604,16 @@ static u64 *hns_dsaf_get_node_stats(struct dsaf_device *ddev, u64 *data,
 	p[10] = hw_stats->local_addr_false;
 	p[11] = hw_stats->vlan_drop;
 	p[12] = hw_stats->stp_drop;
-	p[13] = hw_stats->tx_pkts;
+	if (node_num < DSAF_SERVICE_NW_NUM && !is_ver1) {
+		for (i = 0; i < DSAF_PRIO_NR; i++) {
+			p[13 + i + 0 * DSAF_PRIO_NR] = hw_stats->rx_pfc[i];
+			p[13 + i + 1 * DSAF_PRIO_NR] = hw_stats->tx_pfc[i];
+		}
+		p[29] = hw_stats->tx_pkts;
+		return &p[30];
+	}
 
+	p[13] = hw_stats->tx_pkts;
 	return &p[14];
 }
 
@@ -2582,11 +2641,16 @@ void hns_dsaf_get_stats(struct dsaf_device *ddev, u64 *data, int port)
  *@stringset: type of values in data
  *return dsaf string name count
  */
-int hns_dsaf_get_sset_count(int stringset)
+int hns_dsaf_get_sset_count(struct dsaf_device *dsaf_dev, int stringset)
 {
-	if (stringset == ETH_SS_STATS)
-		return DSAF_STATIC_NUM;
+	bool is_ver1 = AE_IS_VER1(dsaf_dev->dsaf_ver);
 
+	if (stringset == ETH_SS_STATS) {
+		if (is_ver1)
+			return DSAF_STATIC_NUM;
+		else
+			return DSAF_V2_STATIC_NUM;
+	}
 	return 0;
 }
 
@@ -2596,7 +2660,8 @@ int hns_dsaf_get_sset_count(int stringset)
  *@data:strings name value
  *@port:port index
  */
-void hns_dsaf_get_strings(int stringset, u8 *data, int port)
+void hns_dsaf_get_strings(int stringset, u8 *data, int port,
+			  struct dsaf_device *dsaf_dev)
 {
 	char *buff = (char *)data;
 	int node = port;
@@ -2605,11 +2670,11 @@ void hns_dsaf_get_strings(int stringset, u8 *data, int port)
 		return;
 
 	/* for ge/xge node info */
-	buff = hns_dsaf_get_node_stats_strings(buff, node);
+	buff = hns_dsaf_get_node_stats_strings(buff, node, dsaf_dev);
 
 	/* for ppe node info */
 	node = port + DSAF_PPE_INODE_BASE;
-	(void)hns_dsaf_get_node_stats_strings(buff, node);
+	(void)hns_dsaf_get_node_stats_strings(buff, node, dsaf_dev);
 }
 
 /**
@@ -2645,7 +2710,7 @@ static int hns_dsaf_probe(struct platform_device *pdev)
 
 	ret = hns_dsaf_init(dsaf_dev);
 	if (ret)
-		goto free_cfg;
+		goto free_dev;
 
 	ret = hns_mac_init(dsaf_dev);
 	if (ret)
@@ -2670,9 +2735,6 @@ uninit_mac:
 uninit_dsaf:
 	hns_dsaf_free(dsaf_dev);
 
-free_cfg:
-	hns_dsaf_free_cfg(dsaf_dev);
-
 free_dev:
 	hns_dsaf_free_dev(dsaf_dev);
 
@@ -2695,8 +2757,6 @@ static int hns_dsaf_remove(struct platform_device *pdev)
 
 	hns_dsaf_free(dsaf_dev);
 
-	hns_dsaf_free_cfg(dsaf_dev);
-
 	hns_dsaf_free_dev(dsaf_dev);
 
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index 2e55b3cc4515..1daf018d9071 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -39,6 +39,9 @@ struct hns_mac_cb;
 
 #define DSAF_DUMP_REGS_NUM 504
 #define DSAF_STATIC_NUM 28
+#define DSAF_V2_STATIC_NUM	44
+#define DSAF_PRIO_NR	8
+#define DSAF_REG_PER_ZONE	3
 
 #define DSAF_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset))))
 #define HNS_DSAF_IS_DEBUG(dev) (dev->dsaf_mode == DSAF_MODE_DISABLE_SP)
@@ -176,6 +179,8 @@ struct dsaf_hw_stats {
 	u64 local_addr_false;
 	u64 vlan_drop;
 	u64 stp_drop;
+	u64 rx_pfc[DSAF_PRIO_NR];
+	u64 tx_pfc[DSAF_PRIO_NR];
 	u64 tx_pkts;
 };
 
@@ -317,6 +322,8 @@ struct dsaf_device {
 
 	struct dsaf_hw_stats hw_stats[DSAF_NODE_NUM];
 	struct dsaf_int_stat int_stat;
+	/* make sure tcam table config spinlock */
+	spinlock_t tcam_lock;
 };
 
 static inline void *hns_dsaf_dev_priv(const struct dsaf_device *dsaf_dev)
@@ -417,9 +424,10 @@ void hns_dsaf_ae_uninit(struct dsaf_device *dsaf_dev);
 
 void hns_dsaf_update_stats(struct dsaf_device *dsaf_dev, u32 inode_num);
 
-int hns_dsaf_get_sset_count(int stringset);
+int hns_dsaf_get_sset_count(struct dsaf_device *dsaf_dev, int stringset);
 void hns_dsaf_get_stats(struct dsaf_device *ddev, u64 *data, int port);
-void hns_dsaf_get_strings(int stringset, u8 *data, int port);
+void hns_dsaf_get_strings(int stringset, u8 *data, int port,
+			  struct dsaf_device *dsaf_dev);
 
 void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data);
 int hns_dsaf_get_regs_count(void);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index 96cb628a7c5f..611b67b6f450 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -86,9 +86,10 @@ static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status,
 			mac_cb->cpld_led_value = value;
 		}
 	} else {
-		dsaf_write_syscon(mac_cb->cpld_ctrl, mac_cb->cpld_ctrl_reg,
-				  CPLD_LED_DEFAULT_VALUE);
-		mac_cb->cpld_led_value = CPLD_LED_DEFAULT_VALUE;
+		value = (mac_cb->cpld_led_value) & (0x1 << DSAF_LED_ANCHOR_B);
+		dsaf_write_syscon(mac_cb->cpld_ctrl,
+				  mac_cb->cpld_ctrl_reg, value);
+		mac_cb->cpld_led_value = value;
 	}
 }
 
@@ -114,7 +115,7 @@ static int cpld_set_led_id(struct hns_mac_cb *mac_cb,
 			     CPLD_LED_ON_VALUE);
 		dsaf_write_syscon(mac_cb->cpld_ctrl, mac_cb->cpld_ctrl_reg,
 				  mac_cb->cpld_led_value);
-		return 2;
+		break;
 	case HNAE_LED_INACTIVE:
 		dsaf_set_bit(mac_cb->cpld_led_value, DSAF_LED_ANCHOR_B,
 			     CPLD_LED_DEFAULT_VALUE);
@@ -122,7 +123,8 @@ static int cpld_set_led_id(struct hns_mac_cb *mac_cb,
 				  mac_cb->cpld_led_value);
 		break;
 	default:
-		break;
+		dev_err(mac_cb->dev, "invalid led state: %d!", status);
+		return -EINVAL;
 	}
 
 	return 0;
@@ -251,10 +253,9 @@ static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port,
 		reg_val_1  = 0x1 << port;
 		port_rst_off = dsaf_dev->mac_cb[port]->port_rst_off;
 		/* there is difference between V1 and V2 in register.*/
-		if (AE_IS_VER1(dsaf_dev->dsaf_ver))
-			reg_val_2  = 0x1041041 << port_rst_off;
-		else
-			reg_val_2  = 0x2082082 << port_rst_off;
+		reg_val_2 = AE_IS_VER1(dsaf_dev->dsaf_ver) ?
+				0x1041041 : 0x2082082;
+		reg_val_2 <<= port_rst_off;
 
 		if (!dereset) {
 			dsaf_write_sub(dsaf_dev, DSAF_SUB_SC_GE_RESET_REQ1_REG,
@@ -270,8 +271,11 @@ static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port,
 				       reg_val_1);
 		}
 	} else {
-		reg_val_1 = 0x15540 << dsaf_dev->reset_offset;
-		reg_val_2 = 0x100 << dsaf_dev->reset_offset;
+		reg_val_1 = 0x15540;
+		reg_val_2 = AE_IS_VER1(dsaf_dev->dsaf_ver) ? 0x100 : 0x40;
+
+		reg_val_1 <<= dsaf_dev->reset_offset;
+		reg_val_2 <<= dsaf_dev->reset_offset;
 
 		if (!dereset) {
 			dsaf_write_sub(dsaf_dev, DSAF_SUB_SC_GE_RESET_REQ1_REG,
@@ -431,11 +435,6 @@ int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
  */
 static int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, bool en)
 {
-	/* port 0-3 hilink4 base is serdes_vaddr + 0x00280000
-	 * port 4-7 hilink3 base is serdes_vaddr + 0x00200000
-	 */
-	u8 *base_addr = (u8 *)mac_cb->serdes_vaddr +
-		       (mac_cb->mac_id <= 3 ? 0x00280000 : 0x00200000);
 	const u8 lane_id[] = {
 		0,	/* mac 0 -> lane 0 */
 		1,	/* mac 1 -> lane 1 */
@@ -461,11 +460,30 @@ static int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, bool en)
 	}
 
 	if (mac_cb->serdes_ctrl) {
-		u32 origin = dsaf_read_syscon(mac_cb->serdes_ctrl, reg_offset);
+		u32 origin;
+
+		if (!AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver)) {
+#define HILINK_ACCESS_SEL_CFG		0x40008
+			/* hilink4 & hilink3 use the same xge training and
+			 * xge u adaptor. There is a hilink access sel cfg
+			 * register to select which one to be configed
+			 */
+			if ((!HNS_DSAF_IS_DEBUG(mac_cb->dsaf_dev)) &&
+			    (mac_cb->mac_id <= 3))
+				dsaf_write_syscon(mac_cb->serdes_ctrl,
+						  HILINK_ACCESS_SEL_CFG, 0);
+			else
+				dsaf_write_syscon(mac_cb->serdes_ctrl,
+						  HILINK_ACCESS_SEL_CFG, 3);
+		}
+
+		origin = dsaf_read_syscon(mac_cb->serdes_ctrl, reg_offset);
 
 		dsaf_set_field(origin, 1ull << 10, 10, en);
 		dsaf_write_syscon(mac_cb->serdes_ctrl, reg_offset, origin);
 	} else {
+		u8 *base_addr = (u8 *)mac_cb->serdes_vaddr +
+				(mac_cb->mac_id <= 3 ? 0x00280000 : 0x00200000);
 		dsaf_set_reg_field(base_addr, reg_offset, 1ull << 10, 10, en);
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index 3ce24097fcf4..ef1107777c08 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -540,7 +540,7 @@ int hns_rcb_set_coalesce_usecs(
 	}
 	if (timeout > HNS_RCB_MAX_COALESCED_USECS) {
 		dev_err(rcb_common->dsaf_dev->dev,
-			"error: not support coalesce %dus!\n", timeout);
+			"error: coalesce_usecs setting supports 0~1023us\n");
 		return -EINVAL;
 	}
 	hns_rcb_set_port_timeout(rcb_common, port_idx, timeout);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
index bd54dac82ee0..99b4e1ba0a94 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
@@ -40,7 +40,7 @@ struct rcb_common_cb;
 #define HNS_RCB_DEF_COALESCED_FRAMES		50
 #define HNS_RCB_CLK_FREQ_MHZ			350
 #define HNS_RCB_MAX_COALESCED_USECS		0x3ff
-#define HNS_RCB_DEF_COALESCED_USECS		3
+#define HNS_RCB_DEF_COALESCED_USECS		50
 
 #define HNS_RCB_COMMON_ENDIAN			1
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index 7c3b5103d151..235f74444b1d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -32,7 +32,7 @@
 #define DSAFV2_SBM_NUM		8
 #define DSAFV2_SBM_XGE_CHN    6
 #define DSAFV2_SBM_PPE_CHN    1
-#define DASFV2_ROCEE_CRD_NUM  8
+#define DASFV2_ROCEE_CRD_NUM  1
 
 #define DSAF_VOQ_NUM		DSAF_NODE_NUM
 #define DSAF_INODE_NUM		DSAF_NODE_NUM
@@ -166,6 +166,9 @@
 #define DSAF_INODE_GE_FC_EN_0_REG		0x1B00
 #define DSAF_INODE_VC0_IN_PKT_NUM_0_REG		0x1B50
 #define DSAF_INODE_VC1_IN_PKT_NUM_0_REG		0x1C00
+#define DSAF_INODE_IN_PRIO_PAUSE_BASE_REG	0x1C00
+#define DSAF_INODE_IN_PRIO_PAUSE_BASE_OFFSET	0x100
+#define DSAF_INODE_IN_PRIO_PAUSE_OFFSET		0x50
 
 #define DSAF_SBM_CFG_REG_0_REG			0x2000
 #define DSAF_SBM_BP_CFG_0_XGE_REG_0_REG		0x2004
@@ -175,7 +178,7 @@
 #define DSAF_SBM_BP_CFG_2_XGE_REG_0_REG		0x200C
 #define DSAF_SBM_BP_CFG_2_PPE_REG_0_REG		0x230C
 #define DSAF_SBM_BP_CFG_2_ROCEE_REG_0_REG	0x260C
-#define DSAFV2_SBM_BP_CFG_2_ROCEE_REG_0_REG		 0x238C
+#define DSAFV2_SBM_BP_CFG_2_ROCEE_REG_0_REG	0x238C
 #define DSAF_SBM_FREE_CNT_0_0_REG		0x2010
 #define DSAF_SBM_FREE_CNT_1_0_REG		0x2014
 #define DSAF_SBM_BP_CNT_0_0_REG			0x2018
@@ -232,6 +235,8 @@
 #define DSAF_XOD_ROCEE_RCVIN0_CNT_0_REG		0x3074
 #define DSAF_XOD_ROCEE_RCVIN1_CNT_0_REG		0x3078
 #define DSAF_XOD_FIFO_STATUS_0_REG		0x307C
+#define DSAF_XOD_XGE_PFC_PRIO_CNT_BASE_REG	0x3A00
+#define DSAF_XOD_XGE_PFC_PRIO_CNT_OFFSET	0x4
 
 #define DSAF_VOQ_ECC_INVERT_EN_0_REG		0x4004
 #define DSAF_VOQ_SRAM_PKT_NUM_0_REG		0x4008
@@ -791,6 +796,18 @@
 #define DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S 9
 #define DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_M (((1ULL << 9) - 1) << 9)
 
+#define DSAFV2_SBM_CFG2_ROCEE_SET_BUF_NUM_S 0
+#define DSAFV2_SBM_CFG2_ROCEE_SET_BUF_NUM_M (((1ULL << 8) - 1) << 0)
+#define DSAFV2_SBM_CFG2_ROCEE_RESET_BUF_NUM_S 8
+#define DSAFV2_SBM_CFG2_ROCEE_RESET_BUF_NUM_M (((1ULL << 8) - 1) << 8)
+
+#define DSAFV2_SBM_CFG2_PPE_SET_BUF_NUM_S (0)
+#define DSAFV2_SBM_CFG2_PPE_SET_BUF_NUM_M (((1ULL << 6) - 1) << 0)
+#define DSAFV2_SBM_CFG2_PPE_RESET_BUF_NUM_S (6)
+#define DSAFV2_SBM_CFG2_PPE_RESET_BUF_NUM_M (((1ULL << 6) - 1) << 6)
+#define DSAFV2_SBM_CFG2_PPE_CFG_USEFUL_NUM_S (12)
+#define DSAFV2_SBM_CFG2_PPE_CFG_USEFUL_NUM_M (((1ULL << 6) - 1) << 12)
+
 #define DSAF_TBL_TCAM_ADDR_S 0
 #define DSAF_TBL_TCAM_ADDR_M ((1ULL << 9) - 1)
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index ad742a6f5879..d7e1f8c7ae92 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -600,6 +600,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
 		ring->stats.sw_err_cnt++;
 		return -ENOMEM;
 	}
+	skb_reset_mac_header(skb);
 
 	prefetchw(skb->data);
 	length = le16_to_cpu(desc->rx.pkt_len);
@@ -761,16 +762,16 @@ static int hns_nic_rx_poll_one(struct hns_nic_ring_data *ring_data,
 	recv_pkts = 0, recv_bds = 0, clean_count = 0;
 recv:
 	while (recv_pkts < budget && recv_bds < num) {
-		/* reuse or realloc buffers*/
+		/* reuse or realloc buffers */
 		if (clean_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) {
 			hns_nic_alloc_rx_buffers(ring_data, clean_count);
 			clean_count = 0;
 		}
 
-		/* poll one pkg*/
+		/* poll one pkt */
 		err = hns_nic_poll_rx_skb(ring_data, &skb, &bnum);
 		if (unlikely(!skb)) /* this fault cannot be repaired */
-			break;
+			goto out;
 
 		recv_bds += bnum;
 		clean_count += bnum;
@@ -796,6 +797,7 @@ recv:
 		}
 	}
 
+out:
 	/* make all data has been write before submit */
 	if (clean_count > 0)
 		hns_nic_alloc_rx_buffers(ring_data, clean_count);
@@ -990,8 +992,26 @@ static void hns_nic_adjust_link(struct net_device *ndev)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	struct hnae_handle *h = priv->ae_handle;
+	int state = 1;
+
+	if (priv->phy) {
+		h->dev->ops->adjust_link(h, ndev->phydev->speed,
+					 ndev->phydev->duplex);
+		state = priv->phy->link;
+	}
+	state = state && h->dev->ops->get_status(h);
 
-	h->dev->ops->adjust_link(h, ndev->phydev->speed, ndev->phydev->duplex);
+	if (state != priv->link) {
+		if (state) {
+			netif_carrier_on(ndev);
+			netif_tx_wake_all_queues(ndev);
+			netdev_info(ndev, "link up\n");
+		} else {
+			netif_carrier_off(ndev);
+			netdev_info(ndev, "link down\n");
+		}
+		priv->link = state;
+	}
 }
 
 /**
@@ -1181,7 +1201,7 @@ static int hns_nic_net_up(struct net_device *ndev)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	struct hnae_handle *h = priv->ae_handle;
-	int i, j, k;
+	int i, j;
 	int ret;
 
 	ret = hns_nic_init_irq(priv);
@@ -1196,9 +1216,6 @@ static int hns_nic_net_up(struct net_device *ndev)
 			goto out_has_some_queues;
 	}
 
-	for (k = 0; k < h->q_num; k++)
-		h->dev->ops->toggle_queue_status(h->qs[k], 1);
-
 	ret = h->dev->ops->set_mac_addr(h, ndev->dev_addr);
 	if (ret)
 		goto out_set_mac_addr_err;
@@ -1218,8 +1235,6 @@ static int hns_nic_net_up(struct net_device *ndev)
 out_start_err:
 	netif_stop_queue(ndev);
 out_set_mac_addr_err:
-	for (k = 0; k < h->q_num; k++)
-		h->dev->ops->toggle_queue_status(h->qs[k], 0);
 out_has_some_queues:
 	for (j = i - 1; j >= 0; j--)
 		hns_nic_ring_close(ndev, j);
@@ -1426,7 +1441,6 @@ static int hns_nic_set_features(struct net_device *netdev,
 				netdev_features_t features)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
-	struct hnae_handle *h = priv->ae_handle;
 
 	switch (priv->enet_ver) {
 	case AE_VERSION_1:
@@ -1439,11 +1453,9 @@ static int hns_nic_set_features(struct net_device *netdev,
 			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso;
 			/* The chip only support 7*4096 */
 			netif_set_gso_max_size(netdev, 7 * 4096);
-			h->dev->ops->set_tso_stats(h, 1);
 		} else {
 			priv->ops.fill_desc = fill_v2_desc;
 			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx;
-			h->dev->ops->set_tso_stats(h, 0);
 		}
 		break;
 	}
@@ -1576,27 +1588,14 @@ static void hns_nic_update_link_status(struct net_device *netdev)
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 
 	struct hnae_handle *h = priv->ae_handle;
-	int state = 1;
 
-	if (priv->phy) {
-		if (!genphy_update_link(priv->phy))
-			state = priv->phy->link;
-		else
-			state = 0;
-	}
-	state = state && h->dev->ops->get_status(h);
+	if (h->phy_dev) {
+		if (h->phy_if != PHY_INTERFACE_MODE_XGMII)
+			return;
 
-	if (state != priv->link) {
-		if (state) {
-			netif_carrier_on(netdev);
-			netif_tx_wake_all_queues(netdev);
-			netdev_info(netdev, "link up\n");
-		} else {
-			netif_carrier_off(netdev);
-			netdev_info(netdev, "link down\n");
-		}
-		priv->link = state;
+		(void)genphy_read_status(h->phy_dev);
 	}
+	hns_nic_adjust_link(netdev);
 }
 
 /* for dumping key regs*/
@@ -1632,7 +1631,7 @@ static void hns_nic_dump(struct hns_nic_priv *priv)
 	}
 }
 
-/* for resetting suntask*/
+/* for resetting subtask */
 static void hns_nic_reset_subtask(struct hns_nic_priv *priv)
 {
 	enum hnae_port_type type = priv->ae_handle->port_type;
@@ -1802,11 +1801,14 @@ static void hns_nic_set_priv_ops(struct net_device *netdev)
 			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso;
 			/* This chip only support 7*4096 */
 			netif_set_gso_max_size(netdev, 7 * 4096);
-			h->dev->ops->set_tso_stats(h, 1);
 		} else {
 			priv->ops.fill_desc = fill_v2_desc;
 			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx;
 		}
+		/* enable tso when init
+		 * control tso on/off through TSE bit in bd
+		 */
+		h->dev->ops->set_tso_stats(h, 1);
 	}
 }
 
@@ -1971,7 +1973,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 	if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)))
 		dev_dbg(dev, "set mask to 64bit\n");
 	else
-		dev_err(dev, "set mask to 32bit fail!\n");
+		dev_err(dev, "set mask to 64bit fail!\n");
 
 	/* carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(ndev);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index a809f52f6c16..ab33487a5321 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -49,7 +49,7 @@ static u32 hns_nic_get_link(struct net_device *net_dev)
 	h = priv->ae_handle;
 
 	if (priv->phy) {
-		if (!genphy_update_link(priv->phy))
+		if (!genphy_read_status(priv->phy))
 			link_stat = priv->phy->link;
 		else
 			link_stat = 0;
@@ -165,13 +165,21 @@ static int hns_nic_get_settings(struct net_device *net_dev,
 		cmd->advertising |= ADVERTISED_10000baseKR_Full;
 	}
 
-	if (h->port_type == HNAE_PORT_SERVICE) {
+	switch (h->media_type) {
+	case HNAE_MEDIA_TYPE_FIBER:
 		cmd->port = PORT_FIBRE;
-		cmd->supported |= SUPPORTED_Pause;
-	} else {
+		break;
+	case HNAE_MEDIA_TYPE_COPPER:
 		cmd->port = PORT_TP;
+		break;
+	case HNAE_MEDIA_TYPE_UNKNOWN:
+	default:
+		break;
 	}
 
+	if (!(AE_IS_VER1(priv->enet_ver) && h->port_type == HNAE_PORT_DEBUG))
+		cmd->supported |= SUPPORTED_Pause;
+
 	cmd->transceiver = XCVR_EXTERNAL;
 	cmd->mdio_support = (ETH_MDIO_SUPPORTS_C45 | ETH_MDIO_SUPPORTS_C22);
 	hns_get_mdix_mode(net_dev, cmd);
@@ -242,6 +250,7 @@ static const char hns_nic_test_strs[][ETH_GSTRING_LEN] = {
 static int hns_nic_config_phy_loopback(struct phy_device *phy_dev, u8 en)
 {
 #define COPPER_CONTROL_REG 0
+#define PHY_POWER_DOWN BIT(11)
 #define PHY_LOOP_BACK BIT(14)
 	u16 val = 0;
 
@@ -252,33 +261,40 @@ static int hns_nic_config_phy_loopback(struct phy_device *phy_dev, u8 en)
 		/* speed : 1000M */
 		phy_write(phy_dev, HNS_PHY_PAGE_REG, 2);
 		phy_write(phy_dev, 21, 0x1046);
+
+		phy_write(phy_dev, HNS_PHY_PAGE_REG, 0);
 		/* Force Master */
 		phy_write(phy_dev, 9, 0x1F00);
+
 		/* Soft-reset */
 		phy_write(phy_dev, 0, 0x9140);
 		/* If autoneg disabled,two soft-reset operations */
 		phy_write(phy_dev, 0, 0x9140);
-		phy_write(phy_dev, 22, 0xFA);
+
+		phy_write(phy_dev, HNS_PHY_PAGE_REG, 0xFA);
 
 		/* Default is 0x0400 */
 		phy_write(phy_dev, 1, 0x418);
 
 		/* Force 1000M Link, Default is 0x0200 */
 		phy_write(phy_dev, 7, 0x20C);
-		phy_write(phy_dev, 22, 0);
+		phy_write(phy_dev, HNS_PHY_PAGE_REG, 0);
 
-		/* Enable MAC loop-back */
+		/* Enable PHY loop-back */
 		val = phy_read(phy_dev, COPPER_CONTROL_REG);
 		val |= PHY_LOOP_BACK;
+		val &= ~PHY_POWER_DOWN;
 		phy_write(phy_dev, COPPER_CONTROL_REG, val);
 	} else {
-		phy_write(phy_dev, 22, 0xFA);
+		phy_write(phy_dev, HNS_PHY_PAGE_REG, 0xFA);
 		phy_write(phy_dev, 1, 0x400);
 		phy_write(phy_dev, 7, 0x200);
-		phy_write(phy_dev, 22, 0);
+		phy_write(phy_dev, HNS_PHY_PAGE_REG, 0);
+		phy_write(phy_dev, 9, 0xF00);
 
 		val = phy_read(phy_dev, COPPER_CONTROL_REG);
 		val &= ~PHY_LOOP_BACK;
+		val |= PHY_POWER_DOWN;
 		phy_write(phy_dev, COPPER_CONTROL_REG, val);
 	}
 	return 0;
@@ -339,28 +355,16 @@ static int __lb_up(struct net_device *ndev,
 
 	hns_nic_net_reset(ndev);
 
-	if (priv->phy) {
-		phy_disconnect(priv->phy);
-		msleep(100);
-
-		ret = hns_nic_init_phy(ndev, h);
-		if (ret)
-			return ret;
-	}
-
 	ret = __lb_setup(ndev, loop_mode);
 	if (ret)
 		return ret;
 
-	msleep(100);
+	msleep(200);
 
 	ret = h->dev->ops->start ? h->dev->ops->start(h) : 0;
 	if (ret)
 		return ret;
 
-	if (priv->phy)
-		phy_start(priv->phy);
-
 	/* link adjust duplex*/
 	if (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII)
 		speed = 1000;
@@ -561,9 +565,6 @@ static int __lb_down(struct net_device *ndev)
 			   __func__,
 			   ret);
 
-	if (priv->phy)
-		phy_stop(priv->phy);
-
 	if (h->dev->ops->stop)
 		h->dev->ops->stop(h);
 
@@ -758,6 +759,16 @@ static int hns_get_coalesce(struct net_device *net_dev,
 		&ec->tx_max_coalesced_frames,
 		&ec->rx_max_coalesced_frames);
 
+	ops->get_coalesce_range(priv->ae_handle,
+				&ec->tx_max_coalesced_frames_low,
+				&ec->rx_max_coalesced_frames_low,
+				&ec->tx_max_coalesced_frames_high,
+				&ec->rx_max_coalesced_frames_high,
+				&ec->tx_coalesce_usecs_low,
+				&ec->rx_coalesce_usecs_low,
+				&ec->tx_coalesce_usecs_high,
+				&ec->rx_coalesce_usecs_high);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 761a32fceceb..33f4c483af0f 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -37,9 +37,19 @@
 
 #define MDIO_TIMEOUT			1000000
 
+struct hns_mdio_sc_reg {
+	u16 mdio_clk_en;
+	u16 mdio_clk_dis;
+	u16 mdio_reset_req;
+	u16 mdio_reset_dreq;
+	u16 mdio_clk_st;
+	u16 mdio_reset_st;
+};
+
 struct hns_mdio_device {
 	void *vbase;		/* mdio reg base address */
 	struct regmap *subctrl_vbase;
+	struct hns_mdio_sc_reg sc_reg;
 };
 
 /* mdio reg */
@@ -93,7 +103,6 @@ enum mdio_c45_op_seq {
 #define MDIO_SC_CLK_DIS		0x33C
 #define MDIO_SC_RESET_REQ	0xA38
 #define MDIO_SC_RESET_DREQ	0xA3C
-#define MDIO_SC_CTRL		0x2010
 #define MDIO_SC_CLK_ST		0x531C
 #define MDIO_SC_RESET_ST	0x5A1C
 
@@ -353,6 +362,7 @@ static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
 static int hns_mdio_reset(struct mii_bus *bus)
 {
 	struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv;
+	const struct hns_mdio_sc_reg *sc_reg;
 	int ret;
 
 	if (dev_of_node(bus->parent)) {
@@ -361,9 +371,10 @@ static int hns_mdio_reset(struct mii_bus *bus)
 			return -ENODEV;
 		}
 
+		sc_reg = &mdio_dev->sc_reg;
 		/* 1. reset req, and read reset st check */
-		ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_RESET_REQ, 0x1,
-					    MDIO_SC_RESET_ST, 0x1,
+		ret = mdio_sc_cfg_reg_write(mdio_dev, sc_reg->mdio_reset_req,
+					    0x1, sc_reg->mdio_reset_st, 0x1,
 					    MDIO_CHECK_SET_ST);
 		if (ret) {
 			dev_err(&bus->dev, "MDIO reset fail\n");
@@ -371,8 +382,8 @@ static int hns_mdio_reset(struct mii_bus *bus)
 		}
 
 		/* 2. dis clk, and read clk st check */
-		ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_CLK_DIS,
-					    0x1, MDIO_SC_CLK_ST, 0x1,
+		ret = mdio_sc_cfg_reg_write(mdio_dev, sc_reg->mdio_clk_dis,
+					    0x1, sc_reg->mdio_clk_st, 0x1,
 					    MDIO_CHECK_CLR_ST);
 		if (ret) {
 			dev_err(&bus->dev, "MDIO dis clk fail\n");
@@ -380,8 +391,8 @@ static int hns_mdio_reset(struct mii_bus *bus)
 		}
 
 		/* 3. reset dreq, and read reset st check */
-		ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_RESET_DREQ, 0x1,
-					    MDIO_SC_RESET_ST, 0x1,
+		ret = mdio_sc_cfg_reg_write(mdio_dev, sc_reg->mdio_reset_dreq,
+					    0x1, sc_reg->mdio_reset_st, 0x1,
 					    MDIO_CHECK_CLR_ST);
 		if (ret) {
 			dev_err(&bus->dev, "MDIO dis clk fail\n");
@@ -389,8 +400,8 @@ static int hns_mdio_reset(struct mii_bus *bus)
 		}
 
 		/* 4. en clk, and read clk st check */
-		ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_CLK_EN,
-					    0x1, MDIO_SC_CLK_ST, 0x1,
+		ret = mdio_sc_cfg_reg_write(mdio_dev, sc_reg->mdio_clk_en,
+					    0x1, sc_reg->mdio_clk_st, 0x1,
 					    MDIO_CHECK_SET_ST);
 		if (ret)
 			dev_err(&bus->dev, "MDIO en clk fail\n");
@@ -458,13 +469,54 @@ static int hns_mdio_probe(struct platform_device *pdev)
 	snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s-%s", "Mii",
 		 dev_name(&pdev->dev));
 	if (dev_of_node(&pdev->dev)) {
-		mdio_dev->subctrl_vbase = syscon_node_to_regmap(
-			of_parse_phandle(pdev->dev.of_node,
-					 "subctrl-vbase", 0));
-		if (IS_ERR(mdio_dev->subctrl_vbase)) {
-			dev_warn(&pdev->dev, "no syscon hisilicon,peri-c-subctrl\n");
+		struct of_phandle_args reg_args;
+
+		ret = of_parse_phandle_with_fixed_args(pdev->dev.of_node,
+						       "subctrl-vbase",
+						       4,
+						       0,
+						       &reg_args);
+		if (!ret) {
+			mdio_dev->subctrl_vbase =
+				syscon_node_to_regmap(reg_args.np);
+			if (IS_ERR(mdio_dev->subctrl_vbase)) {
+				dev_warn(&pdev->dev, "syscon_node_to_regmap error\n");
+				mdio_dev->subctrl_vbase = NULL;
+			} else {
+				if (reg_args.args_count == 4) {
+					mdio_dev->sc_reg.mdio_clk_en =
+						(u16)reg_args.args[0];
+					mdio_dev->sc_reg.mdio_clk_dis =
+						(u16)reg_args.args[0] + 4;
+					mdio_dev->sc_reg.mdio_reset_req =
+						(u16)reg_args.args[1];
+					mdio_dev->sc_reg.mdio_reset_dreq =
+						(u16)reg_args.args[1] + 4;
+					mdio_dev->sc_reg.mdio_clk_st =
+						(u16)reg_args.args[2];
+					mdio_dev->sc_reg.mdio_reset_st =
+						(u16)reg_args.args[3];
+				} else {
+					/* for compatible */
+					mdio_dev->sc_reg.mdio_clk_en =
+						MDIO_SC_CLK_EN;
+					mdio_dev->sc_reg.mdio_clk_dis =
+						MDIO_SC_CLK_DIS;
+					mdio_dev->sc_reg.mdio_reset_req =
+						MDIO_SC_RESET_REQ;
+					mdio_dev->sc_reg.mdio_reset_dreq =
+						MDIO_SC_RESET_DREQ;
+					mdio_dev->sc_reg.mdio_clk_st =
+						MDIO_SC_CLK_ST;
+					mdio_dev->sc_reg.mdio_reset_st =
+						MDIO_SC_RESET_ST;
+				}
+			}
+		} else {
+			dev_warn(&pdev->dev, "find syscon ret = %#x\n", ret);
 			mdio_dev->subctrl_vbase = NULL;
 		}
+
 		ret = of_mdiobus_register(new_bus, pdev->dev.of_node);
 	} else if (is_acpi_node(pdev->dev.fwnode)) {
 		/* Clear all the IRQ properties */
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 864cb21351a4..ecdb6854a898 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2121,7 +2121,7 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,
 				  struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_error_buff *error_buff;
+	struct ibmvnic_error_buff *error_buff, *tmp;
 	unsigned long flags;
 	bool found = false;
 	int i;
@@ -2133,7 +2133,7 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,
 	}
 
 	spin_lock_irqsave(&adapter->error_list_lock, flags);
-	list_for_each_entry(error_buff, &adapter->errors, list)
+	list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list)
 		if (error_buff->error_id == crq->request_error_rsp.error_id) {
 			found = true;
 			list_del(&error_buff->list);
@@ -3141,14 +3141,14 @@ static void handle_request_ras_comp_num_rsp(union ibmvnic_crq *crq,
 
 static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
 {
-	struct ibmvnic_inflight_cmd *inflight_cmd;
+	struct ibmvnic_inflight_cmd *inflight_cmd, *tmp1;
 	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_error_buff *error_buff;
+	struct ibmvnic_error_buff *error_buff, *tmp2;
 	unsigned long flags;
 	unsigned long flags2;
 
 	spin_lock_irqsave(&adapter->inflight_lock, flags);
-	list_for_each_entry(inflight_cmd, &adapter->inflight, list) {
+	list_for_each_entry_safe(inflight_cmd, tmp1, &adapter->inflight, list) {
 		switch (inflight_cmd->crq.generic.cmd) {
 		case LOGIN:
 			dma_unmap_single(dev, adapter->login_buf_token,
@@ -3165,8 +3165,8 @@ static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
 			break;
 		case REQUEST_ERROR_INFO:
 			spin_lock_irqsave(&adapter->error_list_lock, flags2);
-			list_for_each_entry(error_buff, &adapter->errors,
-					    list) {
+			list_for_each_entry_safe(error_buff, tmp2,
+						 &adapter->errors, list) {
 				dma_unmap_single(dev, error_buff->dma,
 						 error_buff->len,
 						 DMA_FROM_DEVICE);
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 714bd1014ddb..c0e17433f623 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -167,17 +167,6 @@ config IXGBE
 	  To compile this driver as a module, choose M here. The module
 	  will be called ixgbe.
 
-config IXGBE_VXLAN
-	bool "Virtual eXtensible Local Area Network Support"
-	default n
-	depends on IXGBE && VXLAN && !(IXGBE=y && VXLAN=m)
-	---help---
-	  This allows one to create VXLAN virtual interfaces that provide
-	  Layer 2 Networks over Layer 3 Networks. VXLAN is often used
-	  to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to use Virtual eXtensible Local Area Network
-	  (VXLAN) in the driver.
-
 config IXGBE_HWMON
 	bool "Intel(R) 10GbE PCI Express adapters HWMON support"
 	default y
@@ -236,27 +225,6 @@ config I40E
 	  To compile this driver as a module, choose M here. The module
 	  will be called i40e.
 
-config I40E_VXLAN
-	bool "Virtual eXtensible Local Area Network Support"
-	default n
-	depends on I40E && VXLAN && !(I40E=y && VXLAN=m)
-	---help---
-	  This allows one to create VXLAN virtual interfaces that provide
-	  Layer 2 Networks over Layer 3 Networks. VXLAN is often used
-	  to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to use Virtual eXtensible Local Area Network
-	  (VXLAN) in the driver.
-
-config I40E_GENEVE
-	bool "Generic Network Virtualization Encapsulation (GENEVE) Support"
-	depends on I40E && GENEVE && !(I40E=y && GENEVE=m)
-	default n
-	---help---
-	  This allows one to create GENEVE virtual interfaces that provide
-	  Layer 2 Networks over Layer 3 Networks. GENEVE is often used
-	  to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to use GENEVE in the driver.
-
 config I40E_DCB
 	bool "Data Center Bridging (DCB) Support"
 	default n
@@ -307,15 +275,4 @@ config FM10K
 	  To compile this driver as a module, choose M here. The module
 	  will be called fm10k.  MSI-X interrupt support is required
 
-config FM10K_VXLAN
-	bool "Virtual eXtensible Local Area Network Support"
-	default n
-	depends on FM10K && VXLAN && !(FM10K=y && VXLAN=m)
-	---help---
-	  This allows one to create VXLAN virtual interfaces that provide
-	  Layer 2 Networks over Layer 3 Networks. VXLAN is often used
-	  to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to use Virtual eXtensible Local Area Network
-	  (VXLAN) in the driver.
-
 endif # NET_VENDOR_INTEL
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 75e60897b7e7..8294c9a10bd2 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -154,6 +154,16 @@ void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val)
 	writel(val, hw->hw_addr + reg);
 }
 
+static bool e1000e_vlan_used(struct e1000_adapter *adapter)
+{
+	u16 vid;
+
+	for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID)
+		return true;
+
+	return false;
+}
+
 /**
  * e1000_regdump - register printout routine
  * @hw: pointer to the HW structure
@@ -2789,7 +2799,7 @@ static void e1000e_vlan_filter_enable(struct e1000_adapter *adapter)
 }
 
 /**
- * e1000e_vlan_strip_enable - helper to disable HW VLAN stripping
+ * e1000e_vlan_strip_disable - helper to disable HW VLAN stripping
  * @adapter: board private structure to initialize
  **/
 static void e1000e_vlan_strip_disable(struct e1000_adapter *adapter)
@@ -3443,7 +3453,8 @@ static void e1000e_set_rx_mode(struct net_device *netdev)
 
 	ew32(RCTL, rctl);
 
-	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
+	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX ||
+	    e1000e_vlan_used(adapter))
 		e1000e_vlan_strip_enable(adapter);
 	else
 		e1000e_vlan_strip_disable(adapter);
@@ -4352,7 +4363,8 @@ static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc)
 
 			time_delta = systim_next - systim;
 			temp = time_delta;
-			rem = do_div(temp, incvalue);
+			/* VMWare users have seen incvalue of zero, don't div / 0 */
+			rem = incvalue ? do_div(temp, incvalue) : (time_delta != 0);
 
 			systim = systim_next;
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index fcf106e545c5..e98b86bf0ca1 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -406,7 +406,7 @@ static inline u16 fm10k_desc_unused(struct fm10k_ring *ring)
 	 (&(((union fm10k_rx_desc *)((R)->desc))[i]))
 
 #define FM10K_MAX_TXD_PWR	14
-#define FM10K_MAX_DATA_PER_TXD	BIT(FM10K_MAX_TXD_PWR)
+#define FM10K_MAX_DATA_PER_TXD	(1u << FM10K_MAX_TXD_PWR)
 
 /* Tx Descriptors needed, worst case */
 #define TXD_USE_COUNT(S)	DIV_ROUND_UP((S), FM10K_MAX_DATA_PER_TXD)
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
index 9c0d87503977..9b5195435c87 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -983,9 +983,10 @@ void fm10k_write_reta(struct fm10k_intfc *interface, const u32 *indir)
 		/* generate a new table if we weren't given one */
 		for (j = 0; j < 4; j++) {
 			if (indir)
-				n = indir[i + j];
+				n = indir[4 * i + j];
 			else
-				n = ethtool_rxfh_indir_default(i + j, rss_i);
+				n = ethtool_rxfh_indir_default(4 * i + j,
+							       rss_i);
 
 			table[j] = n;
 		}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 0e166e9c90c8..a9ccc1eb3ea4 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -56,7 +56,7 @@ static int __init fm10k_init_module(void)
 	pr_info("%s\n", fm10k_copyright);
 
 	/* create driver workqueue */
-	fm10k_workqueue = create_workqueue("fm10k");
+	fm10k_workqueue = alloc_workqueue("fm10k", WQ_MEM_RECLAIM, 0);
 
 	fm10k_dbg_init();
 
@@ -77,7 +77,6 @@ static void __exit fm10k_exit_module(void)
 	fm10k_dbg_exit();
 
 	/* destroy driver workqueue */
-	flush_workqueue(fm10k_workqueue);
 	destroy_workqueue(fm10k_workqueue);
 }
 module_exit(fm10k_exit_module);
@@ -272,7 +271,7 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer,
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = FM10K_RX_BUFSZ;
 #else
-	unsigned int truesize = SKB_DATA_ALIGN(size);
+	unsigned int truesize = ALIGN(size, 512);
 #endif
 	unsigned int pull_len;
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 2a08d3f5b6df..d00cb193da9a 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -20,9 +20,7 @@
 
 #include "fm10k.h"
 #include <linux/vmalloc.h>
-#ifdef CONFIG_FM10K_VXLAN
-#include <net/vxlan.h>
-#endif /* CONFIG_FM10K_VXLAN */
+#include <net/udp_tunnel.h>
 
 /**
  * fm10k_setup_tx_resources - allocate Tx resources (Descriptors)
@@ -436,6 +434,7 @@ static void fm10k_restore_vxlan_port(struct fm10k_intfc *interface)
  * @netdev: network interface device structure
  * @sa_family: Address family of new port
  * @port: port number used for VXLAN
+ * @type: Enumerated value specifying udp encapsulation type
  *
  * This function is called when a new VXLAN interface has added a new port
  * number to the range that is currently in use for VXLAN.  The new port
@@ -444,18 +443,21 @@ static void fm10k_restore_vxlan_port(struct fm10k_intfc *interface)
  * is always used as the VXLAN port number for offloads.
  **/
 static void fm10k_add_vxlan_port(struct net_device *dev,
-				 sa_family_t sa_family, __be16 port) {
+				 struct udp_tunnel_info *ti)
+{
 	struct fm10k_intfc *interface = netdev_priv(dev);
 	struct fm10k_vxlan_port *vxlan_port;
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
 	/* only the PF supports configuring tunnels */
 	if (interface->hw.mac.type != fm10k_mac_pf)
 		return;
 
 	/* existing ports are pulled out so our new entry is always last */
 	fm10k_vxlan_port_for_each(vxlan_port, interface) {
-		if ((vxlan_port->port == port) &&
-		    (vxlan_port->sa_family == sa_family)) {
+		if ((vxlan_port->port == ti->port) &&
+		    (vxlan_port->sa_family == ti->sa_family)) {
 			list_del(&vxlan_port->list);
 			goto insert_tail;
 		}
@@ -465,8 +467,8 @@ static void fm10k_add_vxlan_port(struct net_device *dev,
 	vxlan_port = kmalloc(sizeof(*vxlan_port), GFP_ATOMIC);
 	if (!vxlan_port)
 		return;
-	vxlan_port->port = port;
-	vxlan_port->sa_family = sa_family;
+	vxlan_port->port = ti->port;
+	vxlan_port->sa_family = ti->sa_family;
 
 insert_tail:
 	/* add new port value to list */
@@ -480,6 +482,7 @@ insert_tail:
  * @netdev: network interface device structure
  * @sa_family: Address family of freed port
  * @port: port number used for VXLAN
+ * @type: Enumerated value specifying udp encapsulation type
  *
  * This function is called when a new VXLAN interface has freed a port
  * number from the range that is currently in use for VXLAN.  The freed
@@ -487,17 +490,20 @@ insert_tail:
  * the port number for offloads.
  **/
 static void fm10k_del_vxlan_port(struct net_device *dev,
-				 sa_family_t sa_family, __be16 port) {
+				 struct udp_tunnel_info *ti)
+{
 	struct fm10k_intfc *interface = netdev_priv(dev);
 	struct fm10k_vxlan_port *vxlan_port;
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
 	if (interface->hw.mac.type != fm10k_mac_pf)
 		return;
 
 	/* find the port in the list and free it */
 	fm10k_vxlan_port_for_each(vxlan_port, interface) {
-		if ((vxlan_port->port == port) &&
-		    (vxlan_port->sa_family == sa_family)) {
+		if ((vxlan_port->port == ti->port) &&
+		    (vxlan_port->sa_family == ti->sa_family)) {
 			list_del(&vxlan_port->list);
 			kfree(vxlan_port);
 			break;
@@ -553,10 +559,8 @@ int fm10k_open(struct net_device *netdev)
 	if (err)
 		goto err_set_queues;
 
-#ifdef CONFIG_FM10K_VXLAN
 	/* update VXLAN port configuration */
-	vxlan_get_rx_port(netdev);
-#endif
+	udp_tunnel_get_rx_info(netdev);
 
 	fm10k_up(interface);
 
@@ -1375,8 +1379,8 @@ static const struct net_device_ops fm10k_netdev_ops = {
 	.ndo_set_vf_vlan	= fm10k_ndo_set_vf_vlan,
 	.ndo_set_vf_rate	= fm10k_ndo_set_vf_bw,
 	.ndo_get_vf_config	= fm10k_ndo_get_vf_config,
-	.ndo_add_vxlan_port	= fm10k_add_vxlan_port,
-	.ndo_del_vxlan_port	= fm10k_del_vxlan_port,
+	.ndo_udp_tunnel_add	= fm10k_add_vxlan_port,
+	.ndo_udp_tunnel_del	= fm10k_del_vxlan_port,
 	.ndo_dfwd_add_station	= fm10k_dfwd_add_station,
 	.ndo_dfwd_del_station	= fm10k_dfwd_del_station,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 9c44739da5e2..e83fc8afb30f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -283,6 +283,7 @@ struct i40e_pf {
 #endif /* I40E_FCOE */
 	u16 num_lan_qps;           /* num lan queues this PF has set up */
 	u16 num_lan_msix;          /* num queue vectors for the base PF vsi */
+	u16 num_fdsb_msix;         /* num queue vectors for sideband Fdir */
 	u16 num_iwarp_msix;        /* num of iwarp vectors for this PF */
 	int iwarp_base_vector;
 	int queues_left;           /* queues left unclaimed */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 422b41d61c9a..e447dc435464 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1967,6 +1967,62 @@ aq_add_vsi_exit:
 }
 
 /**
+ * i40e_aq_set_default_vsi
+ * @hw: pointer to the hw struct
+ * @seid: vsi number
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_set_default_vsi(struct i40e_hw *hw,
+				    u16 seid,
+				    struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
+		(struct i40e_aqc_set_vsi_promiscuous_modes *)
+		&desc.params.raw;
+	i40e_status status;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_set_vsi_promiscuous_modes);
+
+	cmd->promiscuous_flags = cpu_to_le16(I40E_AQC_SET_VSI_DEFAULT);
+	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_DEFAULT);
+	cmd->seid = cpu_to_le16(seid);
+
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	return status;
+}
+
+/**
+ * i40e_aq_clear_default_vsi
+ * @hw: pointer to the hw struct
+ * @seid: vsi number
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_clear_default_vsi(struct i40e_hw *hw,
+				      u16 seid,
+				      struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
+		(struct i40e_aqc_set_vsi_promiscuous_modes *)
+		&desc.params.raw;
+	i40e_status status;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_set_vsi_promiscuous_modes);
+
+	cmd->promiscuous_flags = cpu_to_le16(0);
+	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_DEFAULT);
+	cmd->seid = cpu_to_le16(seid);
+
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	return status;
+}
+
+/**
  * i40e_aq_set_vsi_unicast_promiscuous
  * @hw: pointer to the hw struct
  * @seid: vsi number
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 5e8d84ff7d5f..4962e855fbd3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -313,8 +313,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
 		*advertising |= ADVERTISED_Autoneg |
 				ADVERTISED_40000baseCR4_Full;
 	}
-	if ((phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) &&
-	    !(phy_types & I40E_CAP_PHY_TYPE_1000BASE_T)) {
+	if (phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) {
 		*supported |= SUPPORTED_Autoneg |
 			      SUPPORTED_100baseT_Full;
 		*advertising |= ADVERTISED_Autoneg |
@@ -663,6 +662,7 @@ static int i40e_set_settings(struct net_device *netdev,
 	if (hw->phy.media_type != I40E_MEDIA_TYPE_BASET &&
 	    hw->phy.media_type != I40E_MEDIA_TYPE_FIBER &&
 	    hw->phy.media_type != I40E_MEDIA_TYPE_BACKPLANE &&
+	    hw->phy.media_type != I40E_MEDIA_TYPE_DA &&
 	    hw->phy.link_info.link_info & I40E_AQ_LINK_UP)
 		return -EOPNOTSUPP;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5ea22008d721..2b1140563a64 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -31,12 +31,7 @@
 /* Local includes */
 #include "i40e.h"
 #include "i40e_diag.h"
-#if IS_ENABLED(CONFIG_VXLAN)
-#include <net/vxlan.h>
-#endif
-#if IS_ENABLED(CONFIG_GENEVE)
-#include <net/geneve.h>
-#endif
+#include <net/udp_tunnel.h>
 
 const char i40e_driver_name[] = "i40e";
 static const char i40e_driver_string[] =
@@ -45,8 +40,8 @@ static const char i40e_driver_string[] =
 #define DRV_KERN "-k"
 
 #define DRV_VERSION_MAJOR 1
-#define DRV_VERSION_MINOR 5
-#define DRV_VERSION_BUILD 16
+#define DRV_VERSION_MINOR 6
+#define DRV_VERSION_BUILD 4
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -1584,14 +1579,8 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 	vsi->tc_config.numtc = numtc;
 	vsi->tc_config.enabled_tc = enabled_tc ? enabled_tc : 1;
 	/* Number of queues per enabled TC */
-	/* In MFP case we can have a much lower count of MSIx
-	 * vectors available and so we need to lower the used
-	 * q count.
-	 */
-	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
-		qcount = min_t(int, vsi->alloc_queue_pairs, pf->num_lan_msix);
-	else
-		qcount = vsi->alloc_queue_pairs;
+	qcount = vsi->alloc_queue_pairs;
+
 	num_tc_qps = qcount / numtc;
 	num_tc_qps = min_t(int, num_tc_qps, i40e_pf_get_max_q_per_tc(pf));
 
@@ -1845,8 +1834,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 {
 	struct list_head tmp_del_list, tmp_add_list;
 	struct i40e_mac_filter *f, *ftmp, *fclone;
+	struct i40e_hw *hw = &vsi->back->hw;
 	bool promisc_forced_on = false;
 	bool add_happened = false;
+	char vsi_name[16] = "PF";
 	int filter_list_len = 0;
 	u32 changed_flags = 0;
 	i40e_status aq_ret = 0;
@@ -1874,6 +1865,11 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 	INIT_LIST_HEAD(&tmp_del_list);
 	INIT_LIST_HEAD(&tmp_add_list);
 
+	if (vsi->type == I40E_VSI_SRIOV)
+		snprintf(vsi_name, sizeof(vsi_name) - 1, "VF %d", vsi->vf_id);
+	else if (vsi->type != I40E_VSI_MAIN)
+		snprintf(vsi_name, sizeof(vsi_name) - 1, "vsi %d", vsi->seid);
+
 	if (vsi->flags & I40E_VSI_FLAG_FILTER_CHANGED) {
 		vsi->flags &= ~I40E_VSI_FLAG_FILTER_CHANGED;
 
@@ -1925,7 +1921,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 	if (!list_empty(&tmp_del_list)) {
 		int del_list_size;
 
-		filter_list_len = pf->hw.aq.asq_buf_size /
+		filter_list_len = hw->aq.asq_buf_size /
 			    sizeof(struct i40e_aqc_remove_macvlan_element_data);
 		del_list_size = filter_list_len *
 			    sizeof(struct i40e_aqc_remove_macvlan_element_data);
@@ -1957,21 +1953,21 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 
 			/* flush a full buffer */
 			if (num_del == filter_list_len) {
-				aq_ret = i40e_aq_remove_macvlan(&pf->hw,
-								vsi->seid,
-								del_list,
-								num_del,
-								NULL);
-				aq_err = pf->hw.aq.asq_last_status;
+				aq_ret =
+					i40e_aq_remove_macvlan(hw, vsi->seid,
+							       del_list,
+							       num_del, NULL);
+				aq_err = hw->aq.asq_last_status;
 				num_del = 0;
 				memset(del_list, 0, del_list_size);
 
 				if (aq_ret && aq_err != I40E_AQ_RC_ENOENT) {
 					retval = -EIO;
 					dev_err(&pf->pdev->dev,
-						"ignoring delete macvlan error, err %s, aq_err %s while flushing a full buffer\n",
-						i40e_stat_str(&pf->hw, aq_ret),
-						i40e_aq_str(&pf->hw, aq_err));
+						 "ignoring delete macvlan error on %s, err %s, aq_err %s while flushing a full buffer\n",
+						 vsi_name,
+						 i40e_stat_str(hw, aq_ret),
+						 i40e_aq_str(hw, aq_err));
 				}
 			}
 			/* Release memory for MAC filter entries which were
@@ -1982,17 +1978,17 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 		}
 
 		if (num_del) {
-			aq_ret = i40e_aq_remove_macvlan(&pf->hw, vsi->seid,
-							del_list, num_del,
-							NULL);
-			aq_err = pf->hw.aq.asq_last_status;
+			aq_ret = i40e_aq_remove_macvlan(hw, vsi->seid, del_list,
+							num_del, NULL);
+			aq_err = hw->aq.asq_last_status;
 			num_del = 0;
 
 			if (aq_ret && aq_err != I40E_AQ_RC_ENOENT)
 				dev_info(&pf->pdev->dev,
-					 "ignoring delete macvlan error, err %s aq_err %s\n",
-					 i40e_stat_str(&pf->hw, aq_ret),
-					 i40e_aq_str(&pf->hw, aq_err));
+					 "ignoring delete macvlan error on %s, err %s aq_err %s\n",
+					 vsi_name,
+					 i40e_stat_str(hw, aq_ret),
+					 i40e_aq_str(hw, aq_err));
 		}
 
 		kfree(del_list);
@@ -2003,7 +1999,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 		int add_list_size;
 
 		/* do all the adds now */
-		filter_list_len = pf->hw.aq.asq_buf_size /
+		filter_list_len = hw->aq.asq_buf_size /
 			       sizeof(struct i40e_aqc_add_macvlan_element_data),
 		add_list_size = filter_list_len *
 			       sizeof(struct i40e_aqc_add_macvlan_element_data);
@@ -2038,10 +2034,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 
 			/* flush a full buffer */
 			if (num_add == filter_list_len) {
-				aq_ret = i40e_aq_add_macvlan(&pf->hw, vsi->seid,
+				aq_ret = i40e_aq_add_macvlan(hw, vsi->seid,
 							     add_list, num_add,
 							     NULL);
-				aq_err = pf->hw.aq.asq_last_status;
+				aq_err = hw->aq.asq_last_status;
 				num_add = 0;
 
 				if (aq_ret)
@@ -2056,9 +2052,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 		}
 
 		if (num_add) {
-			aq_ret = i40e_aq_add_macvlan(&pf->hw, vsi->seid,
+			aq_ret = i40e_aq_add_macvlan(hw, vsi->seid,
 						     add_list, num_add, NULL);
-			aq_err = pf->hw.aq.asq_last_status;
+			aq_err = hw->aq.asq_last_status;
 			num_add = 0;
 		}
 		kfree(add_list);
@@ -2067,16 +2063,18 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 		if (add_happened && aq_ret && aq_err != I40E_AQ_RC_EINVAL) {
 			retval = i40e_aq_rc_to_posix(aq_ret, aq_err);
 			dev_info(&pf->pdev->dev,
-				 "add filter failed, err %s aq_err %s\n",
-				 i40e_stat_str(&pf->hw, aq_ret),
-				 i40e_aq_str(&pf->hw, aq_err));
-			if ((pf->hw.aq.asq_last_status == I40E_AQ_RC_ENOSPC) &&
+				 "add filter failed on %s, err %s aq_err %s\n",
+				 vsi_name,
+				 i40e_stat_str(hw, aq_ret),
+				 i40e_aq_str(hw, aq_err));
+			if ((hw->aq.asq_last_status == I40E_AQ_RC_ENOSPC) &&
 			    !test_bit(__I40E_FILTER_OVERFLOW_PROMISC,
 				      &vsi->state)) {
 				promisc_forced_on = true;
 				set_bit(__I40E_FILTER_OVERFLOW_PROMISC,
 					&vsi->state);
-				dev_info(&pf->pdev->dev, "promiscuous mode forced on\n");
+				dev_info(&pf->pdev->dev, "promiscuous mode forced on %s\n",
+					 vsi_name);
 			}
 		}
 	}
@@ -2098,12 +2096,12 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 							       NULL);
 		if (aq_ret) {
 			retval = i40e_aq_rc_to_posix(aq_ret,
-						     pf->hw.aq.asq_last_status);
+						     hw->aq.asq_last_status);
 			dev_info(&pf->pdev->dev,
-				 "set multi promisc failed, err %s aq_err %s\n",
-				 i40e_stat_str(&pf->hw, aq_ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+				 "set multi promisc failed on %s, err %s aq_err %s\n",
+				 vsi_name,
+				 i40e_stat_str(hw, aq_ret),
+				 i40e_aq_str(hw, hw->aq.asq_last_status));
 		}
 	}
 	if ((changed_flags & IFF_PROMISC) || promisc_forced_on) {
@@ -2122,33 +2120,58 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 			 */
 			if (pf->cur_promisc != cur_promisc) {
 				pf->cur_promisc = cur_promisc;
-				set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+				if (cur_promisc)
+					aq_ret =
+					      i40e_aq_set_default_vsi(hw,
+								      vsi->seid,
+								      NULL);
+				else
+					aq_ret =
+					    i40e_aq_clear_default_vsi(hw,
+								      vsi->seid,
+								      NULL);
+				if (aq_ret) {
+					retval = i40e_aq_rc_to_posix(aq_ret,
+							hw->aq.asq_last_status);
+					dev_info(&pf->pdev->dev,
+						 "Set default VSI failed on %s, err %s, aq_err %s\n",
+						 vsi_name,
+						 i40e_stat_str(hw, aq_ret),
+						 i40e_aq_str(hw,
+						     hw->aq.asq_last_status));
+				}
 			}
 		} else {
 			aq_ret = i40e_aq_set_vsi_unicast_promiscuous(
-							  &vsi->back->hw,
+							  hw,
 							  vsi->seid,
 							  cur_promisc, NULL,
 							  true);
 			if (aq_ret) {
 				retval =
 				i40e_aq_rc_to_posix(aq_ret,
-						    pf->hw.aq.asq_last_status);
+						    hw->aq.asq_last_status);
 				dev_info(&pf->pdev->dev,
-					 "set unicast promisc failed, err %d, aq_err %d\n",
-					 aq_ret, pf->hw.aq.asq_last_status);
+					 "set unicast promisc failed on %s, err %s, aq_err %s\n",
+					 vsi_name,
+					 i40e_stat_str(hw, aq_ret),
+					 i40e_aq_str(hw,
+						     hw->aq.asq_last_status));
 			}
 			aq_ret = i40e_aq_set_vsi_multicast_promiscuous(
-							  &vsi->back->hw,
+							  hw,
 							  vsi->seid,
 							  cur_promisc, NULL);
 			if (aq_ret) {
 				retval =
 				i40e_aq_rc_to_posix(aq_ret,
-						    pf->hw.aq.asq_last_status);
+						    hw->aq.asq_last_status);
 				dev_info(&pf->pdev->dev,
-					 "set multicast promisc failed, err %d, aq_err %d\n",
-					 aq_ret, pf->hw.aq.asq_last_status);
+					 "set multicast promisc failed on %s, err %s, aq_err %s\n",
+					 vsi_name,
+					 i40e_stat_str(hw, aq_ret),
+					 i40e_aq_str(hw,
+						     hw->aq.asq_last_status));
 			}
 		}
 		aq_ret = i40e_aq_set_vsi_broadcast(&vsi->back->hw,
@@ -2159,9 +2182,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 						     pf->hw.aq.asq_last_status);
 			dev_info(&pf->pdev->dev,
 				 "set brdcast promisc failed, err %s, aq_err %s\n",
-				 i40e_stat_str(&pf->hw, aq_ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
+					 i40e_stat_str(hw, aq_ret),
+					 i40e_aq_str(hw,
+						     hw->aq.asq_last_status));
 		}
 	}
 out:
@@ -3952,6 +3975,7 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi)
 			/* clear the affinity_mask in the IRQ descriptor */
 			irq_set_affinity_hint(pf->msix_entries[vector].vector,
 					      NULL);
+			synchronize_irq(pf->msix_entries[vector].vector);
 			free_irq(pf->msix_entries[vector].vector,
 				 vsi->q_vectors[i]);
 
@@ -4958,7 +4982,6 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf)
 			if (pf->vsi[v]->netdev)
 				i40e_dcbnl_set_all(pf->vsi[v]);
 		}
-		i40e_notify_client_of_l2_param_changes(pf->vsi[v]);
 	}
 }
 
@@ -5183,12 +5206,6 @@ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi)
 		usleep_range(1000, 2000);
 	i40e_down(vsi);
 
-	/* Give a VF some time to respond to the reset.  The
-	 * two second wait is based upon the watchdog cycle in
-	 * the VF driver.
-	 */
-	if (vsi->type == I40E_VSI_SRIOV)
-		msleep(2000);
 	i40e_up(vsi);
 	clear_bit(__I40E_CONFIG_BUSY, &pf->state);
 }
@@ -5231,6 +5248,9 @@ void i40e_down(struct i40e_vsi *vsi)
 		i40e_clean_tx_ring(vsi->tx_rings[i]);
 		i40e_clean_rx_ring(vsi->rx_rings[i]);
 	}
+
+	i40e_notify_client_of_netdev_close(vsi, false);
+
 }
 
 /**
@@ -5342,14 +5362,7 @@ int i40e_open(struct net_device *netdev)
 						       TCP_FLAG_CWR) >> 16);
 	wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16);
 
-#ifdef CONFIG_I40E_VXLAN
-	vxlan_get_rx_port(netdev);
-#endif
-#ifdef CONFIG_I40E_GENEVE
-	if (pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE)
-		geneve_get_rx_port(netdev);
-#endif
-
+	udp_tunnel_get_rx_info(netdev);
 	i40e_notify_client_of_netdev_open(vsi);
 
 	return 0;
@@ -5716,6 +5729,8 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 		i40e_service_event_schedule(pf);
 	} else {
 		i40e_pf_unquiesce_all_vsi(pf);
+		/* Notify the client for the DCB changes */
+		i40e_notify_client_of_l2_param_changes(pf->vsi[pf->lan_vsi]);
 	}
 
 exit:
@@ -5940,7 +5955,6 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 		if (I40E_DEBUG_FD & pf->hw.debug_mask)
 			dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
 	}
-
 }
 
 /**
@@ -7057,7 +7071,6 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
  **/
 static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 {
-#if IS_ENABLED(CONFIG_VXLAN) || IS_ENABLED(CONFIG_GENEVE)
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status ret;
 	__be16 port;
@@ -7092,7 +7105,6 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 			}
 		}
 	}
-#endif
 }
 
 /**
@@ -7174,7 +7186,7 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
 		vsi->alloc_queue_pairs = 1;
 		vsi->num_desc = ALIGN(I40E_FDIR_RING_COUNT,
 				      I40E_REQ_DESCRIPTOR_MULTIPLE);
-		vsi->num_q_vectors = 1;
+		vsi->num_q_vectors = pf->num_fdsb_msix;
 		break;
 
 	case I40E_VSI_VMDQ2:
@@ -7558,9 +7570,11 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	/* reserve one vector for sideband flow director */
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
 		if (vectors_left) {
+			pf->num_fdsb_msix = 1;
 			v_budget++;
 			vectors_left--;
 		} else {
+			pf->num_fdsb_msix = 0;
 			pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
 		}
 	}
@@ -8579,7 +8593,9 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
 		/* Enable filters and mark for reset */
 		if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
 			need_reset = true;
-		pf->flags |= I40E_FLAG_FD_SB_ENABLED;
+		/* enable FD_SB only if there is MSI-X vector */
+		if (pf->num_fdsb_msix > 0)
+			pf->flags |= I40E_FLAG_FD_SB_ENABLED;
 	} else {
 		/* turn off filters, mark for reset and clear SW filter list */
 		if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
@@ -8628,7 +8644,6 @@ static int i40e_set_features(struct net_device *netdev,
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_VXLAN) || IS_ENABLED(CONFIG_GENEVE)
 /**
  * i40e_get_udp_port_idx - Lookup a possibly offloaded for Rx UDP port
  * @pf: board private structure
@@ -8648,21 +8663,18 @@ static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port)
 	return i;
 }
 
-#endif
-
-#if IS_ENABLED(CONFIG_VXLAN)
 /**
- * i40e_add_vxlan_port - Get notifications about VXLAN ports that come up
+ * i40e_udp_tunnel_add - Get notifications about UDP tunnel ports that come up
  * @netdev: This physical port's netdev
- * @sa_family: Socket Family that VXLAN is notifying us about
- * @port: New UDP port number that VXLAN started listening to
+ * @ti: Tunnel endpoint information
  **/
-static void i40e_add_vxlan_port(struct net_device *netdev,
-				sa_family_t sa_family, __be16 port)
+static void i40e_udp_tunnel_add(struct net_device *netdev,
+				struct udp_tunnel_info *ti)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
+	__be16 port = ti->port;
 	u8 next_idx;
 	u8 idx;
 
@@ -8670,7 +8682,7 @@ static void i40e_add_vxlan_port(struct net_device *netdev,
 
 	/* Check if port already exists */
 	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "vxlan port %d already offloaded\n",
+		netdev_info(netdev, "port %d already offloaded\n",
 			    ntohs(port));
 		return;
 	}
@@ -8679,131 +8691,75 @@ static void i40e_add_vxlan_port(struct net_device *netdev,
 	next_idx = i40e_get_udp_port_idx(pf, 0);
 
 	if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "maximum number of vxlan UDP ports reached, not adding port %d\n",
-			    ntohs(port));
-		return;
-	}
-
-	/* New port: add it and mark its index in the bitmap */
-	pf->udp_ports[next_idx].index = port;
-	pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN;
-	pf->pending_udp_bitmap |= BIT_ULL(next_idx);
-	pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
-}
-
-/**
- * i40e_del_vxlan_port - Get notifications about VXLAN ports that go away
- * @netdev: This physical port's netdev
- * @sa_family: Socket Family that VXLAN is notifying us about
- * @port: UDP port number that VXLAN stopped listening to
- **/
-static void i40e_del_vxlan_port(struct net_device *netdev,
-				sa_family_t sa_family, __be16 port)
-{
-	struct i40e_netdev_priv *np = netdev_priv(netdev);
-	struct i40e_vsi *vsi = np->vsi;
-	struct i40e_pf *pf = vsi->back;
-	u8 idx;
-
-	idx = i40e_get_udp_port_idx(pf, port);
-
-	/* Check if port already exists */
-	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		/* if port exists, set it to 0 (mark for deletion)
-		 * and make it pending
-		 */
-		pf->udp_ports[idx].index = 0;
-		pf->pending_udp_bitmap |= BIT_ULL(idx);
-		pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
-	} else {
-		netdev_warn(netdev, "vxlan port %d was not found, not deleting\n",
-			    ntohs(port));
-	}
-}
-#endif
-
-#if IS_ENABLED(CONFIG_GENEVE)
-/**
- * i40e_add_geneve_port - Get notifications about GENEVE ports that come up
- * @netdev: This physical port's netdev
- * @sa_family: Socket Family that GENEVE is notifying us about
- * @port: New UDP port number that GENEVE started listening to
- **/
-static void i40e_add_geneve_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
-{
-	struct i40e_netdev_priv *np = netdev_priv(netdev);
-	struct i40e_vsi *vsi = np->vsi;
-	struct i40e_pf *pf = vsi->back;
-	u8 next_idx;
-	u8 idx;
-
-	if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE))
-		return;
-
-	idx = i40e_get_udp_port_idx(pf, port);
-
-	/* Check if port already exists */
-	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "udp port %d already offloaded\n",
+		netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n",
 			    ntohs(port));
 		return;
 	}
 
-	/* Now check if there is space to add the new port */
-	next_idx = i40e_get_udp_port_idx(pf, 0);
-
-	if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "maximum number of UDP ports reached, not adding port %d\n",
-			    ntohs(port));
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN;
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE))
+			return;
+		pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_NGE;
+		break;
+	default:
 		return;
 	}
 
 	/* New port: add it and mark its index in the bitmap */
 	pf->udp_ports[next_idx].index = port;
-	pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_NGE;
 	pf->pending_udp_bitmap |= BIT_ULL(next_idx);
 	pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
-
-	dev_info(&pf->pdev->dev, "adding geneve port %d\n", ntohs(port));
 }
 
 /**
- * i40e_del_geneve_port - Get notifications about GENEVE ports that go away
+ * i40e_udp_tunnel_del - Get notifications about UDP tunnel ports that go away
  * @netdev: This physical port's netdev
- * @sa_family: Socket Family that GENEVE is notifying us about
- * @port: UDP port number that GENEVE stopped listening to
+ * @ti: Tunnel endpoint information
  **/
-static void i40e_del_geneve_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
+static void i40e_udp_tunnel_del(struct net_device *netdev,
+				struct udp_tunnel_info *ti)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
+	__be16 port = ti->port;
 	u8 idx;
 
-	if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE))
-		return;
-
 	idx = i40e_get_udp_port_idx(pf, port);
 
 	/* Check if port already exists */
-	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		/* if port exists, set it to 0 (mark for deletion)
-		 * and make it pending
-		 */
-		pf->udp_ports[idx].index = 0;
-		pf->pending_udp_bitmap |= BIT_ULL(idx);
-		pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
+	if (idx >= I40E_MAX_PF_UDP_OFFLOAD_PORTS)
+		goto not_found;
 
-		dev_info(&pf->pdev->dev, "deleting geneve port %d\n",
-			 ntohs(port));
-	} else {
-		netdev_warn(netdev, "geneve port %d was not found, not deleting\n",
-			    ntohs(port));
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_VXLAN)
+			goto not_found;
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_NGE)
+			goto not_found;
+		break;
+	default:
+		goto not_found;
 	}
+
+	/* if port exists, set it to 0 (mark for deletion)
+	 * and make it pending
+	 */
+	pf->udp_ports[idx].index = 0;
+	pf->pending_udp_bitmap |= BIT_ULL(idx);
+	pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
+
+	return;
+not_found:
+	netdev_warn(netdev, "UDP port %d was not found, not deleting\n",
+		    ntohs(port));
 }
-#endif
 
 static int i40e_get_phys_port_id(struct net_device *netdev,
 				 struct netdev_phys_item_id *ppid)
@@ -9033,14 +8989,8 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_set_vf_link_state	= i40e_ndo_set_vf_link_state,
 	.ndo_set_vf_spoofchk	= i40e_ndo_set_vf_spoofchk,
 	.ndo_set_vf_trust	= i40e_ndo_set_vf_trust,
-#if IS_ENABLED(CONFIG_VXLAN)
-	.ndo_add_vxlan_port	= i40e_add_vxlan_port,
-	.ndo_del_vxlan_port	= i40e_del_vxlan_port,
-#endif
-#if IS_ENABLED(CONFIG_GENEVE)
-	.ndo_add_geneve_port	= i40e_add_geneve_port,
-	.ndo_del_geneve_port	= i40e_del_geneve_port,
-#endif
+	.ndo_udp_tunnel_add	= i40e_udp_tunnel_add,
+	.ndo_udp_tunnel_del	= i40e_udp_tunnel_del,
 	.ndo_get_phys_port_id	= i40e_get_phys_port_id,
 	.ndo_fdb_add		= i40e_ndo_fdb_add,
 	.ndo_features_check	= i40e_features_check,
@@ -10133,14 +10083,14 @@ void i40e_veb_release(struct i40e_veb *veb)
 static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = veb->pf;
-	bool is_default = veb->pf->cur_promisc;
 	bool enable_stats = !!(pf->flags & I40E_FLAG_VEB_STATS_ENABLED);
 	int ret;
 
-	/* get a VEB from the hardware */
 	ret = i40e_aq_add_veb(&pf->hw, veb->uplink_seid, vsi->seid,
-			      veb->enabled_tc, is_default,
+			      veb->enabled_tc, false,
 			      &veb->seid, enable_stats, NULL);
+
+	/* get a VEB from the hardware */
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "couldn't add VEB, err %s aq_err %s\n",
@@ -10689,12 +10639,8 @@ static void i40e_print_features(struct i40e_pf *pf)
 	}
 	if (pf->flags & I40E_FLAG_DCB_CAPABLE)
 		i += snprintf(&buf[i], REMAIN(i), " DCB");
-#if IS_ENABLED(CONFIG_VXLAN)
 	i += snprintf(&buf[i], REMAIN(i), " VxLAN");
-#endif
-#if IS_ENABLED(CONFIG_GENEVE)
 	i += snprintf(&buf[i], REMAIN(i), " Geneve");
-#endif
 	if (pf->flags & I40E_FLAG_PTP)
 		i += snprintf(&buf[i], REMAIN(i), " PTP");
 #ifdef I40E_FCOE
@@ -11525,6 +11471,7 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
 	struct i40e_hw *hw = &pf->hw;
+	int retval = 0;
 
 	set_bit(__I40E_SUSPENDED, &pf->state);
 	set_bit(__I40E_DOWN, &pf->state);
@@ -11536,10 +11483,16 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state)
 	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
 	wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
 
+	i40e_stop_misc_vector(pf);
+
+	retval = pci_save_state(pdev);
+	if (retval)
+		return retval;
+
 	pci_wake_from_d3(pdev, pf->wol_en);
 	pci_set_power_state(pdev, PCI_D3hot);
 
-	return 0;
+	return retval;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 80403c6ee7f0..4660c5abc855 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -98,6 +98,8 @@ i40e_status i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags,
 				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_set_default_vsi(struct i40e_hw *hw, u16 vsi_id,
 				struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_clear_default_vsi(struct i40e_hw *hw, u16 vsi_id,
+				      struct i40e_asq_cmd_details *cmd_details);
 enum i40e_status_code i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
 			bool qualified_modules, bool report_init,
 			struct i40e_aq_get_phy_abilities_resp *abilities,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 1fcafcfa8f14..6fcbf764f32b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -665,6 +665,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 		goto error_alloc_vsi_res;
 	}
 	if (type == I40E_VSI_SRIOV) {
+		u64 hena = i40e_pf_get_default_rss_hena(pf);
+
 		vf->lan_vsi_idx = vsi->idx;
 		vf->lan_vsi_id = vsi->id;
 		/* If the port VLAN has been configured and then the
@@ -687,6 +689,10 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 					vf->default_lan_addr.addr, vf->vf_id);
 		}
 		spin_unlock_bh(&vsi->mac_filter_list_lock);
+		i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id),
+				  (u32)hena);
+		i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id),
+				  (u32)(hena >> 32));
 	}
 
 	/* program mac filter */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 16c552952860..eac057b88055 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -37,8 +37,8 @@ static const char i40evf_driver_string[] =
 #define DRV_KERN "-k"
 
 #define DRV_VERSION_MAJOR 1
-#define DRV_VERSION_MINOR 5
-#define DRV_VERSION_BUILD 10
+#define DRV_VERSION_MINOR 6
+#define DRV_VERSION_BUILD 4
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD) \
@@ -825,7 +825,7 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter,
 
 		ether_addr_copy(f->macaddr, macaddr);
 
-		list_add(&f->list, &adapter->mac_filter_list);
+		list_add_tail(&f->list, &adapter->mac_filter_list);
 		f->add = true;
 		adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
 	}
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index f13445691507..d76c221d4c8a 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -434,6 +434,8 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter)
 			ether_addr_copy(veal->list[i].addr, f->macaddr);
 			i++;
 			f->add = false;
+			if (i == count)
+				break;
 		}
 	}
 	if (!more)
@@ -497,6 +499,8 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter)
 			i++;
 			list_del(&f->list);
 			kfree(f);
+			if (i == count)
+				break;
 		}
 	}
 	if (!more)
@@ -560,6 +564,8 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter)
 			vvfl->vlan_id[i] = f->vlan;
 			i++;
 			f->add = false;
+			if (i == count)
+				break;
 		}
 	}
 	if (!more)
@@ -623,6 +629,8 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter)
 			i++;
 			list_del(&f->list);
 			kfree(f);
+			if (i == count)
+				break;
 		}
 	}
 	if (!more)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index b9609afa5ca3..5387b3a96489 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -445,6 +445,7 @@ struct igb_adapter {
 	unsigned long ptp_tx_start;
 	unsigned long last_rx_ptp_check;
 	unsigned long last_rx_timestamp;
+	unsigned int ptp_flags;
 	spinlock_t tmreg_lock;
 	struct cyclecounter cc;
 	struct timecounter tc;
@@ -474,12 +475,15 @@ struct igb_adapter {
 	u16 eee_advert;
 };
 
+/* flags controlling PTP/1588 function */
+#define IGB_PTP_ENABLED		BIT(0)
+#define IGB_PTP_OVERFLOW_CHECK	BIT(1)
+
 #define IGB_FLAG_HAS_MSI		BIT(0)
 #define IGB_FLAG_DCA_ENABLED		BIT(1)
 #define IGB_FLAG_QUAD_PORT_A		BIT(2)
 #define IGB_FLAG_QUEUE_PAIRS		BIT(3)
 #define IGB_FLAG_DMAC			BIT(4)
-#define IGB_FLAG_PTP			BIT(5)
 #define IGB_FLAG_RSS_FIELD_IPV4_UDP	BIT(6)
 #define IGB_FLAG_RSS_FIELD_IPV6_UDP	BIT(7)
 #define IGB_FLAG_WOL_SUPPORTED		BIT(8)
@@ -546,6 +550,7 @@ void igb_set_fw_version(struct igb_adapter *);
 void igb_ptp_init(struct igb_adapter *adapter);
 void igb_ptp_stop(struct igb_adapter *adapter);
 void igb_ptp_reset(struct igb_adapter *adapter);
+void igb_ptp_suspend(struct igb_adapter *adapter);
 void igb_ptp_rx_hang(struct igb_adapter *adapter);
 void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
 void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, unsigned char *va,
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index ef3d642f5ff2..9bcba42abb91 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2027,7 +2027,8 @@ void igb_reset(struct igb_adapter *adapter)
 	wr32(E1000_VET, ETHERNET_IEEE_VLAN_TYPE);
 
 	/* Re-enable PTP, where applicable. */
-	igb_ptp_reset(adapter);
+	if (adapter->ptp_flags & IGB_PTP_ENABLED)
+		igb_ptp_reset(adapter);
 
 	igb_get_phy_info(hw);
 }
@@ -6855,12 +6856,12 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
  **/
 static bool igb_add_rx_frag(struct igb_ring *rx_ring,
 			    struct igb_rx_buffer *rx_buffer,
+			    unsigned int size,
 			    union e1000_adv_rx_desc *rx_desc,
 			    struct sk_buff *skb)
 {
 	struct page *page = rx_buffer->page;
 	unsigned char *va = page_address(page) + rx_buffer->page_offset;
-	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = IGB_RX_BUFSZ;
 #else
@@ -6912,6 +6913,7 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
 					   union e1000_adv_rx_desc *rx_desc,
 					   struct sk_buff *skb)
 {
+	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
 	struct igb_rx_buffer *rx_buffer;
 	struct page *page;
 
@@ -6947,11 +6949,11 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
 	dma_sync_single_range_for_cpu(rx_ring->dev,
 				      rx_buffer->dma,
 				      rx_buffer->page_offset,
-				      IGB_RX_BUFSZ,
+				      size,
 				      DMA_FROM_DEVICE);
 
 	/* pull page into skb */
-	if (igb_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) {
+	if (igb_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) {
 		/* hand second half of page back to the ring */
 		igb_reuse_rx_page(rx_ring, rx_buffer);
 	} else {
@@ -7527,6 +7529,8 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 	if (netif_running(netdev))
 		__igb_close(netdev, true);
 
+	igb_ptp_suspend(adapter);
+
 	igb_clear_interrupt_scheme(adapter);
 
 #ifdef CONFIG_PM
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index f097c5a8ab93..e61b647f5f2a 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -684,6 +684,7 @@ void igb_ptp_rx_hang(struct igb_adapter *adapter)
 	u32 tsyncrxctl = rd32(E1000_TSYNCRXCTL);
 	unsigned long rx_event;
 
+	/* Other hardware uses per-packet timestamps */
 	if (hw->mac.type != e1000_82576)
 		return;
 
@@ -1042,6 +1043,13 @@ int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
 		-EFAULT : 0;
 }
 
+/**
+ * igb_ptp_init - Initialize PTP functionality
+ * @adapter: Board private structure
+ *
+ * This function is called at device probe to initialize the PTP
+ * functionality.
+ */
 void igb_ptp_init(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
@@ -1064,8 +1072,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->cc.mask = CYCLECOUNTER_MASK(64);
 		adapter->cc.mult = 1;
 		adapter->cc.shift = IGB_82576_TSYNC_SHIFT;
-		/* Dial the nominal frequency. */
-		wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576);
+		adapter->ptp_flags |= IGB_PTP_OVERFLOW_CHECK;
 		break;
 	case e1000_82580:
 	case e1000_i354:
@@ -1084,8 +1091,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->cc.mask = CYCLECOUNTER_MASK(IGB_NBITS_82580);
 		adapter->cc.mult = 1;
 		adapter->cc.shift = 0;
-		/* Enable the timer functions by clearing bit 31. */
-		wr32(E1000_TSAUXC, 0x0);
+		adapter->ptp_flags |= IGB_PTP_OVERFLOW_CHECK;
 		break;
 	case e1000_i210:
 	case e1000_i211:
@@ -1110,44 +1116,24 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.settime64 = igb_ptp_settime_i210;
 		adapter->ptp_caps.enable = igb_ptp_feature_enable_i210;
 		adapter->ptp_caps.verify = igb_ptp_verify_pin;
-		/* Enable the timer functions by clearing bit 31. */
-		wr32(E1000_TSAUXC, 0x0);
 		break;
 	default:
 		adapter->ptp_clock = NULL;
 		return;
 	}
 
-	wrfl();
-
 	spin_lock_init(&adapter->tmreg_lock);
 	INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work);
 
-	/* Initialize the clock and overflow work for devices that need it. */
-	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) {
-		struct timespec64 ts = ktime_to_timespec64(ktime_get_real());
-
-		igb_ptp_settime_i210(&adapter->ptp_caps, &ts);
-	} else {
-		timecounter_init(&adapter->tc, &adapter->cc,
-				 ktime_to_ns(ktime_get_real()));
-
+	if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK)
 		INIT_DELAYED_WORK(&adapter->ptp_overflow_work,
 				  igb_ptp_overflow_check);
 
-		schedule_delayed_work(&adapter->ptp_overflow_work,
-				      IGB_SYSTIM_OVERFLOW_PERIOD);
-	}
-
-	/* Initialize the time sync interrupts for devices that support it. */
-	if (hw->mac.type >= e1000_82580) {
-		wr32(E1000_TSIM, TSYNC_INTERRUPTS);
-		wr32(E1000_IMS, E1000_IMS_TS);
-	}
-
 	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
 
+	igb_ptp_reset(adapter);
+
 	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps,
 						&adapter->pdev->dev);
 	if (IS_ERR(adapter->ptp_clock)) {
@@ -1156,32 +1142,24 @@ void igb_ptp_init(struct igb_adapter *adapter)
 	} else {
 		dev_info(&adapter->pdev->dev, "added PHC on %s\n",
 			 adapter->netdev->name);
-		adapter->flags |= IGB_FLAG_PTP;
+		adapter->ptp_flags |= IGB_PTP_ENABLED;
 	}
 }
 
 /**
- * igb_ptp_stop - Disable PTP device and stop the overflow check.
- * @adapter: Board private structure.
+ * igb_ptp_suspend - Disable PTP work items and prepare for suspend
+ * @adapter: Board private structure
  *
- * This function stops the PTP support and cancels the delayed work.
- **/
-void igb_ptp_stop(struct igb_adapter *adapter)
+ * This function stops the overflow check work and PTP Tx timestamp work, and
+ * will prepare the device for OS suspend.
+ */
+void igb_ptp_suspend(struct igb_adapter *adapter)
 {
-	switch (adapter->hw.mac.type) {
-	case e1000_82576:
-	case e1000_82580:
-	case e1000_i354:
-	case e1000_i350:
-		cancel_delayed_work_sync(&adapter->ptp_overflow_work);
-		break;
-	case e1000_i210:
-	case e1000_i211:
-		/* No delayed work to cancel. */
-		break;
-	default:
+	if (!(adapter->ptp_flags & IGB_PTP_ENABLED))
 		return;
-	}
+
+	if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK)
+		cancel_delayed_work_sync(&adapter->ptp_overflow_work);
 
 	cancel_work_sync(&adapter->ptp_tx_work);
 	if (adapter->ptp_tx_skb) {
@@ -1189,12 +1167,23 @@ void igb_ptp_stop(struct igb_adapter *adapter)
 		adapter->ptp_tx_skb = NULL;
 		clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state);
 	}
+}
+
+/**
+ * igb_ptp_stop - Disable PTP device and stop the overflow check.
+ * @adapter: Board private structure.
+ *
+ * This function stops the PTP support and cancels the delayed work.
+ **/
+void igb_ptp_stop(struct igb_adapter *adapter)
+{
+	igb_ptp_suspend(adapter);
 
 	if (adapter->ptp_clock) {
 		ptp_clock_unregister(adapter->ptp_clock);
 		dev_info(&adapter->pdev->dev, "removed PHC on %s\n",
 			 adapter->netdev->name);
-		adapter->flags &= ~IGB_FLAG_PTP;
+		adapter->ptp_flags &= ~IGB_PTP_ENABLED;
 	}
 }
 
@@ -1209,9 +1198,6 @@ void igb_ptp_reset(struct igb_adapter *adapter)
 	struct e1000_hw *hw = &adapter->hw;
 	unsigned long flags;
 
-	if (!(adapter->flags & IGB_FLAG_PTP))
-		return;
-
 	/* reset the tstamp_config */
 	igb_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config);
 
@@ -1248,4 +1234,10 @@ void igb_ptp_reset(struct igb_adapter *adapter)
 	}
 out:
 	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+
+	wrfl();
+
+	if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK)
+		schedule_delayed_work(&adapter->ptp_overflow_work,
+				      IGB_SYSTIM_OVERFLOW_PERIOD);
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 59b771b9b354..8a8450788124 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -2991,10 +2991,15 @@ static int ixgbe_get_ts_info(struct net_device *dev,
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 
+	/* we always support timestamping disabled */
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE);
+
 	switch (adapter->hw.mac.type) {
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+		info->rx_filters |= BIT(HWTSTAMP_FILTER_ALL);
+		/* fallthrough */
 	case ixgbe_mac_X540:
 	case ixgbe_mac_82599EB:
 		info->so_timestamping =
@@ -3014,8 +3019,7 @@ static int ixgbe_get_ts_info(struct net_device *dev,
 			BIT(HWTSTAMP_TX_OFF) |
 			BIT(HWTSTAMP_TX_ON);
 
-		info->rx_filters =
-			BIT(HWTSTAMP_FILTER_NONE) |
+		info->rx_filters |=
 			BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) |
 			BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) |
 			BIT(HWTSTAMP_FILTER_PTP_V2_EVENT);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 088c47cf27d9..fd5a761c68f3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -50,7 +50,7 @@
 #include <linux/if_bridge.h>
 #include <linux/prefetch.h>
 #include <scsi/fc/fc_fcoe.h>
-#include <net/vxlan.h>
+#include <net/udp_tunnel.h>
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
@@ -5722,9 +5722,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter)
 #ifdef CONFIG_IXGBE_DCA
 		adapter->flags &= ~IXGBE_FLAG_DCA_CAPABLE;
 #endif
-#ifdef CONFIG_IXGBE_VXLAN
 		adapter->flags |= IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE;
-#endif
 		break;
 	default:
 		break;
@@ -6158,9 +6156,7 @@ int ixgbe_open(struct net_device *netdev)
 	ixgbe_up_complete(adapter);
 
 	ixgbe_clear_vxlan_port(adapter);
-#ifdef CONFIG_IXGBE_VXLAN
-	vxlan_get_rx_port(netdev);
-#endif
+	udp_tunnel_get_rx_info(netdev);
 
 	return 0;
 
@@ -7262,14 +7258,12 @@ static void ixgbe_service_task(struct work_struct *work)
 		ixgbe_service_event_complete(adapter);
 		return;
 	}
-#ifdef CONFIG_IXGBE_VXLAN
-	rtnl_lock();
 	if (adapter->flags2 & IXGBE_FLAG2_VXLAN_REREG_NEEDED) {
+		rtnl_lock();
 		adapter->flags2 &= ~IXGBE_FLAG2_VXLAN_REREG_NEEDED;
-		vxlan_get_rx_port(adapter->netdev);
+		udp_tunnel_get_rx_info(adapter->netdev);
+		rtnl_unlock();
 	}
-	rtnl_unlock();
-#endif /* CONFIG_IXGBE_VXLAN */
 	ixgbe_reset_subtask(adapter);
 	ixgbe_phy_interrupt_subtask(adapter);
 	ixgbe_sfp_detection_subtask(adapter);
@@ -7697,7 +7691,6 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
 	/* snag network header to get L4 type and address */
 	skb = first->skb;
 	hdr.network = skb_network_header(skb);
-#ifdef CONFIG_IXGBE_VXLAN
 	if (skb->encapsulation &&
 	    first->protocol == htons(ETH_P_IP) &&
 	    hdr.ipv4->protocol != IPPROTO_UDP) {
@@ -7708,7 +7701,6 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
 		    udp_hdr(skb)->dest == adapter->vxlan_port)
 			hdr.network = skb_inner_network_header(skb);
 	}
-#endif /* CONFIG_IXGBE_VXLAN */
 
 	/* Currently only IPv4/IPv6 with TCP is supported */
 	switch (hdr.ipv4->version) {
@@ -8308,14 +8300,53 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc)
 static int ixgbe_delete_clsu32(struct ixgbe_adapter *adapter,
 			       struct tc_cls_u32_offload *cls)
 {
+	u32 hdl = cls->knode.handle;
 	u32 uhtid = TC_U32_USERHTID(cls->knode.handle);
-	u32 loc;
-	int err;
+	u32 loc = cls->knode.handle & 0xfffff;
+	int err = 0, i, j;
+	struct ixgbe_jump_table *jump = NULL;
+
+	if (loc > IXGBE_MAX_HW_ENTRIES)
+		return -EINVAL;
 
 	if ((uhtid != 0x800) && (uhtid >= IXGBE_MAX_LINK_HANDLE))
 		return -EINVAL;
 
-	loc = cls->knode.handle & 0xfffff;
+	/* Clear this filter in the link data it is associated with */
+	if (uhtid != 0x800) {
+		jump = adapter->jump_tables[uhtid];
+		if (!jump)
+			return -EINVAL;
+		if (!test_bit(loc - 1, jump->child_loc_map))
+			return -EINVAL;
+		clear_bit(loc - 1, jump->child_loc_map);
+	}
+
+	/* Check if the filter being deleted is a link */
+	for (i = 1; i < IXGBE_MAX_LINK_HANDLE; i++) {
+		jump = adapter->jump_tables[i];
+		if (jump && jump->link_hdl == hdl) {
+			/* Delete filters in the hardware in the child hash
+			 * table associated with this link
+			 */
+			for (j = 0; j < IXGBE_MAX_HW_ENTRIES; j++) {
+				if (!test_bit(j, jump->child_loc_map))
+					continue;
+				spin_lock(&adapter->fdir_perfect_lock);
+				err = ixgbe_update_ethtool_fdir_entry(adapter,
+								      NULL,
+								      j + 1);
+				spin_unlock(&adapter->fdir_perfect_lock);
+				clear_bit(j, jump->child_loc_map);
+			}
+			/* Remove resources for this link */
+			kfree(jump->input);
+			kfree(jump->mask);
+			kfree(jump);
+			adapter->jump_tables[i] = NULL;
+			return err;
+		}
+	}
 
 	spin_lock(&adapter->fdir_perfect_lock);
 	err = ixgbe_update_ethtool_fdir_entry(adapter, NULL, loc);
@@ -8549,6 +8580,18 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter,
 		if (!test_bit(link_uhtid - 1, &adapter->tables))
 			return err;
 
+		/* Multiple filters as links to the same hash table are not
+		 * supported. To add a new filter with the same next header
+		 * but different match/jump conditions, create a new hash table
+		 * and link to it.
+		 */
+		if (adapter->jump_tables[link_uhtid] &&
+		    (adapter->jump_tables[link_uhtid])->link_hdl) {
+			e_err(drv, "Link filter exists for link: %x\n",
+			      link_uhtid);
+			return err;
+		}
+
 		for (i = 0; nexthdr[i].jump; i++) {
 			if (nexthdr[i].o != cls->knode.sel->offoff ||
 			    nexthdr[i].s != cls->knode.sel->offshift ||
@@ -8570,6 +8613,8 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter,
 			}
 			jump->input = input;
 			jump->mask = mask;
+			jump->link_hdl = cls->knode.handle;
+
 			err = ixgbe_clsu32_build_input(input, mask, cls,
 						       field_ptr, &nexthdr[i]);
 			if (!err) {
@@ -8597,6 +8642,20 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter,
 		if ((adapter->jump_tables[uhtid])->mask)
 			memcpy(mask, (adapter->jump_tables[uhtid])->mask,
 			       sizeof(*mask));
+
+		/* Lookup in all child hash tables if this location is already
+		 * filled with a filter
+		 */
+		for (i = 1; i < IXGBE_MAX_LINK_HANDLE; i++) {
+			struct ixgbe_jump_table *link = adapter->jump_tables[i];
+
+			if (link && (test_bit(loc - 1, link->child_loc_map))) {
+				e_err(drv, "Filter exists in location: %x\n",
+				      loc);
+				err = -EINVAL;
+				goto err_out;
+			}
+		}
 	}
 	err = ixgbe_clsu32_build_input(input, mask, cls, field_ptr, NULL);
 	if (err)
@@ -8628,6 +8687,9 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter,
 		ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx);
 	spin_unlock(&adapter->fdir_perfect_lock);
 
+	if ((uhtid != 0x800) && (adapter->jump_tables[uhtid]))
+		set_bit(loc - 1, (adapter->jump_tables[uhtid])->child_loc_map);
+
 	kfree(mask);
 	return err;
 err_out_w_lock:
@@ -8770,14 +8832,12 @@ static int ixgbe_set_features(struct net_device *netdev,
 
 	netdev->features = features;
 
-#ifdef CONFIG_IXGBE_VXLAN
 	if ((adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE)) {
 		if (features & NETIF_F_RXCSUM)
 			adapter->flags2 |= IXGBE_FLAG2_VXLAN_REREG_NEEDED;
 		else
 			ixgbe_clear_vxlan_port(adapter);
 	}
-#endif /* CONFIG_IXGBE_VXLAN */
 
 	if (need_reset)
 		ixgbe_do_reset(netdev);
@@ -8788,23 +8848,27 @@ static int ixgbe_set_features(struct net_device *netdev,
 	return 0;
 }
 
-#ifdef CONFIG_IXGBE_VXLAN
 /**
  * ixgbe_add_vxlan_port - Get notifications about VXLAN ports that come up
  * @dev: The port's netdev
  * @sa_family: Socket Family that VXLAN is notifiying us about
  * @port: New UDP port number that VXLAN started listening to
+ * @type: Enumerated type specifying UDP tunnel type
  **/
-static void ixgbe_add_vxlan_port(struct net_device *dev, sa_family_t sa_family,
-				 __be16 port)
+static void ixgbe_add_vxlan_port(struct net_device *dev,
+				 struct udp_tunnel_info *ti)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
+	__be16 port = ti->port;
 
-	if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE))
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (sa_family == AF_INET6)
+	if (ti->sa_family != AF_INET)
+		return;
+
+	if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE))
 		return;
 
 	if (adapter->vxlan_port == port)
@@ -8826,28 +8890,31 @@ static void ixgbe_add_vxlan_port(struct net_device *dev, sa_family_t sa_family,
  * @dev: The port's netdev
  * @sa_family: Socket Family that VXLAN is notifying us about
  * @port: UDP port number that VXLAN stopped listening to
+ * @type: Enumerated type specifying UDP tunnel type
  **/
-static void ixgbe_del_vxlan_port(struct net_device *dev, sa_family_t sa_family,
-				 __be16 port)
+static void ixgbe_del_vxlan_port(struct net_device *dev,
+				 struct udp_tunnel_info *ti)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 
-	if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE))
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (sa_family == AF_INET6)
+	if (ti->sa_family != AF_INET)
 		return;
 
-	if (adapter->vxlan_port != port) {
+	if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE))
+		return;
+
+	if (adapter->vxlan_port != ti->port) {
 		netdev_info(dev, "Port %d was not found, not deleting\n",
-			    ntohs(port));
+			    ntohs(ti->port));
 		return;
 	}
 
 	ixgbe_clear_vxlan_port(adapter);
 	adapter->flags2 |= IXGBE_FLAG2_VXLAN_REREG_NEEDED;
 }
-#endif /* CONFIG_IXGBE_VXLAN */
 
 static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			     struct net_device *dev,
@@ -9160,10 +9227,8 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_bridge_getlink	= ixgbe_ndo_bridge_getlink,
 	.ndo_dfwd_add_station	= ixgbe_fwd_add,
 	.ndo_dfwd_del_station	= ixgbe_fwd_del,
-#ifdef CONFIG_IXGBE_VXLAN
-	.ndo_add_vxlan_port	= ixgbe_add_vxlan_port,
-	.ndo_del_vxlan_port	= ixgbe_del_vxlan_port,
-#endif /* CONFIG_IXGBE_VXLAN */
+	.ndo_udp_tunnel_add	= ixgbe_add_vxlan_port,
+	.ndo_udp_tunnel_del	= ixgbe_del_vxlan_port,
 	.ndo_features_check	= ixgbe_features_check,
 };
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h
index a8bed3d887f7..538a1c5475b6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h
@@ -42,8 +42,12 @@ struct ixgbe_jump_table {
 	struct ixgbe_mat_field *mat;
 	struct ixgbe_fdir_filter *input;
 	union ixgbe_atr_input *mask;
+	u32 link_hdl;
+	unsigned long child_loc_map[32];
 };
 
+#define IXGBE_MAX_HW_ENTRIES 2045
+
 static inline int ixgbe_mat_prgm_sip(struct ixgbe_fdir_filter *input,
 				     union ixgbe_atr_input *mask,
 				     u32 val, u32 m)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index c5caacdd193d..8618599dfd6f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -954,6 +954,7 @@ static int ixgbe_set_vf_macvlan_msg(struct ixgbe_adapter *adapter,
 			struct ixgbe_hw *hw = &adapter->hw;
 
 			hw->mac.ops.set_mac_anti_spoofing(hw, false, vf);
+			hw->mac.ops.set_vlan_anti_spoofing(hw, false, vf);
 		}
 	}
 
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index dc82b1b19574..91e09d68b7e2 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -102,7 +102,6 @@ struct ltq_etop_priv {
 	struct resource *res;
 
 	struct mii_bus *mii_bus;
-	struct phy_device *phydev;
 
 	struct ltq_etop_chan ch[MAX_DMA_CHAN];
 	int tx_free[MAX_DMA_CHAN >> 1];
@@ -305,34 +304,16 @@ ltq_etop_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 }
 
 static int
-ltq_etop_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct ltq_etop_priv *priv = netdev_priv(dev);
-
-	return phy_ethtool_gset(priv->phydev, cmd);
-}
-
-static int
-ltq_etop_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct ltq_etop_priv *priv = netdev_priv(dev);
-
-	return phy_ethtool_sset(priv->phydev, cmd);
-}
-
-static int
 ltq_etop_nway_reset(struct net_device *dev)
 {
-	struct ltq_etop_priv *priv = netdev_priv(dev);
-
-	return phy_start_aneg(priv->phydev);
+	return phy_start_aneg(dev->phydev);
 }
 
 static const struct ethtool_ops ltq_etop_ethtool_ops = {
 	.get_drvinfo = ltq_etop_get_drvinfo,
-	.get_settings = ltq_etop_get_settings,
-	.set_settings = ltq_etop_set_settings,
 	.nway_reset = ltq_etop_nway_reset,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 static int
@@ -401,7 +382,6 @@ ltq_etop_mdio_probe(struct net_device *dev)
 			      | SUPPORTED_TP);
 
 	phydev->advertising = phydev->supported;
-	priv->phydev = phydev;
 	phy_attached_info(phydev);
 
 	return 0;
@@ -411,7 +391,6 @@ static int
 ltq_etop_mdio_init(struct net_device *dev)
 {
 	struct ltq_etop_priv *priv = netdev_priv(dev);
-	int i;
 	int err;
 
 	priv->mii_bus = mdiobus_alloc();
@@ -451,7 +430,7 @@ ltq_etop_mdio_cleanup(struct net_device *dev)
 {
 	struct ltq_etop_priv *priv = netdev_priv(dev);
 
-	phy_disconnect(priv->phydev);
+	phy_disconnect(dev->phydev);
 	mdiobus_unregister(priv->mii_bus);
 	mdiobus_free(priv->mii_bus);
 }
@@ -470,7 +449,7 @@ ltq_etop_open(struct net_device *dev)
 		ltq_dma_open(&ch->dma);
 		napi_enable(&ch->napi);
 	}
-	phy_start(priv->phydev);
+	phy_start(dev->phydev);
 	netif_tx_start_all_queues(dev);
 	return 0;
 }
@@ -482,7 +461,7 @@ ltq_etop_stop(struct net_device *dev)
 	int i;
 
 	netif_tx_stop_all_queues(dev);
-	phy_stop(priv->phydev);
+	phy_stop(dev->phydev);
 	for (i = 0; i < MAX_DMA_CHAN; i++) {
 		struct ltq_etop_chan *ch = &priv->ch[i];
 
@@ -557,10 +536,8 @@ ltq_etop_change_mtu(struct net_device *dev, int new_mtu)
 static int
 ltq_etop_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct ltq_etop_priv *priv = netdev_priv(dev);
-
 	/* TODO: mii-toll reports "No MII transceiver present!." ?!*/
-	return phy_mii_ioctl(priv->phydev, rq, cmd);
+	return phy_mii_ioctl(dev->phydev, rq, cmd);
 }
 
 static int
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 868a957f24bb..0b047178cda1 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -699,7 +699,6 @@ struct mvpp2_port {
 	u16 rx_ring_size;
 	struct mvpp2_pcpu_stats __percpu *stats;
 
-	struct phy_device *phy_dev;
 	phy_interface_t phy_interface;
 	struct device_node *phy_node;
 	unsigned int link;
@@ -4850,7 +4849,7 @@ static irqreturn_t mvpp2_isr(int irq, void *dev_id)
 static void mvpp2_link_event(struct net_device *dev)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
-	struct phy_device *phydev = port->phy_dev;
+	struct phy_device *phydev = dev->phydev;
 	int status_change = 0;
 	u32 val;
 
@@ -5416,6 +5415,8 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
 /* Set hw internals when starting port */
 static void mvpp2_start_dev(struct mvpp2_port *port)
 {
+	struct net_device *ndev = port->dev;
+
 	mvpp2_gmac_max_rx_size_set(port);
 	mvpp2_txp_max_tx_size_set(port);
 
@@ -5425,13 +5426,15 @@ static void mvpp2_start_dev(struct mvpp2_port *port)
 	mvpp2_interrupts_enable(port);
 
 	mvpp2_port_enable(port);
-	phy_start(port->phy_dev);
+	phy_start(ndev->phydev);
 	netif_tx_start_all_queues(port->dev);
 }
 
 /* Set hw internals when stopping port */
 static void mvpp2_stop_dev(struct mvpp2_port *port)
 {
+	struct net_device *ndev = port->dev;
+
 	/* Stop new packets from arriving to RXQs */
 	mvpp2_ingress_disable(port);
 
@@ -5447,7 +5450,7 @@ static void mvpp2_stop_dev(struct mvpp2_port *port)
 
 	mvpp2_egress_disable(port);
 	mvpp2_port_disable(port);
-	phy_stop(port->phy_dev);
+	phy_stop(ndev->phydev);
 }
 
 /* Return positive if MTU is valid */
@@ -5535,7 +5538,6 @@ static int mvpp2_phy_connect(struct mvpp2_port *port)
 	phy_dev->supported &= PHY_GBIT_FEATURES;
 	phy_dev->advertising = phy_dev->supported;
 
-	port->phy_dev = phy_dev;
 	port->link    = 0;
 	port->duplex  = 0;
 	port->speed   = 0;
@@ -5545,8 +5547,9 @@ static int mvpp2_phy_connect(struct mvpp2_port *port)
 
 static void mvpp2_phy_disconnect(struct mvpp2_port *port)
 {
-	phy_disconnect(port->phy_dev);
-	port->phy_dev = NULL;
+	struct net_device *ndev = port->dev;
+
+	phy_disconnect(ndev->phydev);
 }
 
 static int mvpp2_open(struct net_device *dev)
@@ -5796,13 +5799,12 @@ mvpp2_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 
 static int mvpp2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
-	struct mvpp2_port *port = netdev_priv(dev);
 	int ret;
 
-	if (!port->phy_dev)
+	if (!dev->phydev)
 		return -ENOTSUPP;
 
-	ret = phy_mii_ioctl(port->phy_dev, ifr, cmd);
+	ret = phy_mii_ioctl(dev->phydev, ifr, cmd);
 	if (!ret)
 		mvpp2_link_event(dev);
 
@@ -5811,28 +5813,6 @@ static int mvpp2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 /* Ethtool methods */
 
-/* Get settings (phy address, speed) for ethtools */
-static int mvpp2_ethtool_get_settings(struct net_device *dev,
-				      struct ethtool_cmd *cmd)
-{
-	struct mvpp2_port *port = netdev_priv(dev);
-
-	if (!port->phy_dev)
-		return -ENODEV;
-	return phy_ethtool_gset(port->phy_dev, cmd);
-}
-
-/* Set settings (phy address, speed) for ethtools */
-static int mvpp2_ethtool_set_settings(struct net_device *dev,
-				      struct ethtool_cmd *cmd)
-{
-	struct mvpp2_port *port = netdev_priv(dev);
-
-	if (!port->phy_dev)
-		return -ENODEV;
-	return phy_ethtool_sset(port->phy_dev, cmd);
-}
-
 /* Set interrupt coalescing for ethtools */
 static int mvpp2_ethtool_set_coalesce(struct net_device *dev,
 				      struct ethtool_coalesce *c)
@@ -5967,13 +5947,13 @@ static const struct net_device_ops mvpp2_netdev_ops = {
 
 static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.get_link	= ethtool_op_get_link,
-	.get_settings	= mvpp2_ethtool_get_settings,
-	.set_settings	= mvpp2_ethtool_set_settings,
 	.set_coalesce	= mvpp2_ethtool_set_coalesce,
 	.get_coalesce	= mvpp2_ethtool_get_coalesce,
 	.get_drvinfo	= mvpp2_ethtool_get_drvinfo,
 	.get_ringparam	= mvpp2_ethtool_get_ringparam,
 	.set_ringparam	= mvpp2_ethtool_set_ringparam,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 /* Driver initialization */
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index c984462fad2a..682797ea5e11 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -133,6 +133,8 @@ static int mtk_mdio_read(struct mii_bus *bus, int phy_addr, int phy_reg)
 static void mtk_phy_link_adjust(struct net_device *dev)
 {
 	struct mtk_mac *mac = netdev_priv(dev);
+	u16 lcl_adv = 0, rmt_adv = 0;
+	u8 flowctrl;
 	u32 mcr = MAC_MCR_MAX_RX_1536 | MAC_MCR_IPG_CFG |
 		  MAC_MCR_FORCE_MODE | MAC_MCR_TX_EN |
 		  MAC_MCR_RX_EN | MAC_MCR_BACKOFF_EN |
@@ -150,11 +152,30 @@ static void mtk_phy_link_adjust(struct net_device *dev)
 	if (mac->phy_dev->link)
 		mcr |= MAC_MCR_FORCE_LINK;
 
-	if (mac->phy_dev->duplex)
+	if (mac->phy_dev->duplex) {
 		mcr |= MAC_MCR_FORCE_DPX;
 
-	if (mac->phy_dev->pause)
-		mcr |= MAC_MCR_FORCE_RX_FC | MAC_MCR_FORCE_TX_FC;
+		if (mac->phy_dev->pause)
+			rmt_adv = LPA_PAUSE_CAP;
+		if (mac->phy_dev->asym_pause)
+			rmt_adv |= LPA_PAUSE_ASYM;
+
+		if (mac->phy_dev->advertising & ADVERTISED_Pause)
+			lcl_adv |= ADVERTISE_PAUSE_CAP;
+		if (mac->phy_dev->advertising & ADVERTISED_Asym_Pause)
+			lcl_adv |= ADVERTISE_PAUSE_ASYM;
+
+		flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
+
+		if (flowctrl & FLOW_CTRL_TX)
+			mcr |= MAC_MCR_FORCE_TX_FC;
+		if (flowctrl & FLOW_CTRL_RX)
+			mcr |= MAC_MCR_FORCE_RX_FC;
+
+		netif_dbg(mac->hw, link, dev, "rx pause %s, tx pause %s\n",
+			  flowctrl & FLOW_CTRL_RX ? "enabled" : "disabled",
+			  flowctrl & FLOW_CTRL_TX ? "enabled" : "disabled");
+	}
 
 	mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id));
 
@@ -208,10 +229,16 @@ static int mtk_phy_connect(struct mtk_mac *mac)
 	u32 val, ge_mode;
 
 	np = of_parse_phandle(mac->of_node, "phy-handle", 0);
+	if (!np && of_phy_is_fixed_link(mac->of_node))
+		if (!of_phy_register_fixed_link(mac->of_node))
+			np = of_node_get(mac->of_node);
 	if (!np)
 		return -ENODEV;
 
 	switch (of_get_phy_mode(np)) {
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII:
 		ge_mode = 0;
 		break;
@@ -236,7 +263,8 @@ static int mtk_phy_connect(struct mtk_mac *mac)
 	mac->phy_dev->autoneg = AUTONEG_ENABLE;
 	mac->phy_dev->speed = 0;
 	mac->phy_dev->duplex = 0;
-	mac->phy_dev->supported &= PHY_BASIC_FEATURES;
+	mac->phy_dev->supported &= PHY_GBIT_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause;
 	mac->phy_dev->advertising = mac->phy_dev->supported |
 				    ADVERTISED_Autoneg;
 	phy_start_aneg(mac->phy_dev);
@@ -280,7 +308,7 @@ static int mtk_mdio_init(struct mtk_eth *eth)
 	return 0;
 
 err_free_bus:
-	kfree(eth->mii_bus);
+	mdiobus_free(eth->mii_bus);
 
 err_put_node:
 	of_node_put(mii_np);
@@ -295,27 +323,29 @@ static void mtk_mdio_cleanup(struct mtk_eth *eth)
 
 	mdiobus_unregister(eth->mii_bus);
 	of_node_put(eth->mii_bus->dev.of_node);
-	kfree(eth->mii_bus);
+	mdiobus_free(eth->mii_bus);
 }
 
 static inline void mtk_irq_disable(struct mtk_eth *eth, u32 mask)
 {
+	unsigned long flags;
 	u32 val;
 
+	spin_lock_irqsave(&eth->irq_lock, flags);
 	val = mtk_r32(eth, MTK_QDMA_INT_MASK);
 	mtk_w32(eth, val & ~mask, MTK_QDMA_INT_MASK);
-	/* flush write */
-	mtk_r32(eth, MTK_QDMA_INT_MASK);
+	spin_unlock_irqrestore(&eth->irq_lock, flags);
 }
 
 static inline void mtk_irq_enable(struct mtk_eth *eth, u32 mask)
 {
+	unsigned long flags;
 	u32 val;
 
+	spin_lock_irqsave(&eth->irq_lock, flags);
 	val = mtk_r32(eth, MTK_QDMA_INT_MASK);
 	mtk_w32(eth, val | mask, MTK_QDMA_INT_MASK);
-	/* flush write */
-	mtk_r32(eth, MTK_QDMA_INT_MASK);
+	spin_unlock_irqrestore(&eth->irq_lock, flags);
 }
 
 static int mtk_set_mac_address(struct net_device *dev, void *p)
@@ -453,20 +483,23 @@ static inline void mtk_rx_get_desc(struct mtk_rx_dma *rxd,
 /* the qdma core needs scratch memory to be setup */
 static int mtk_init_fq_dma(struct mtk_eth *eth)
 {
-	dma_addr_t phy_ring_head, phy_ring_tail;
+	dma_addr_t phy_ring_tail;
 	int cnt = MTK_DMA_SIZE;
 	dma_addr_t dma_addr;
 	int i;
 
 	eth->scratch_ring = dma_alloc_coherent(eth->dev,
 					       cnt * sizeof(struct mtk_tx_dma),
-					       &phy_ring_head,
+					       &eth->phy_scratch_ring,
 					       GFP_ATOMIC | __GFP_ZERO);
 	if (unlikely(!eth->scratch_ring))
 		return -ENOMEM;
 
 	eth->scratch_head = kcalloc(cnt, MTK_QDMA_PAGE_SIZE,
 				    GFP_KERNEL);
+	if (unlikely(!eth->scratch_head))
+		return -ENOMEM;
+
 	dma_addr = dma_map_single(eth->dev,
 				  eth->scratch_head, cnt * MTK_QDMA_PAGE_SIZE,
 				  DMA_FROM_DEVICE);
@@ -474,19 +507,19 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 		return -ENOMEM;
 
 	memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt);
-	phy_ring_tail = phy_ring_head +
+	phy_ring_tail = eth->phy_scratch_ring +
 			(sizeof(struct mtk_tx_dma) * (cnt - 1));
 
 	for (i = 0; i < cnt; i++) {
 		eth->scratch_ring[i].txd1 =
 					(dma_addr + (i * MTK_QDMA_PAGE_SIZE));
 		if (i < cnt - 1)
-			eth->scratch_ring[i].txd2 = (phy_ring_head +
+			eth->scratch_ring[i].txd2 = (eth->phy_scratch_ring +
 				((i + 1) * sizeof(struct mtk_tx_dma)));
 		eth->scratch_ring[i].txd3 = TX_DMA_SDL(MTK_QDMA_PAGE_SIZE);
 	}
 
-	mtk_w32(eth, phy_ring_head, MTK_QDMA_FQ_HEAD);
+	mtk_w32(eth, eth->phy_scratch_ring, MTK_QDMA_FQ_HEAD);
 	mtk_w32(eth, phy_ring_tail, MTK_QDMA_FQ_TAIL);
 	mtk_w32(eth, (cnt << 16) | cnt, MTK_QDMA_FQ_CNT);
 	mtk_w32(eth, MTK_QDMA_PAGE_SIZE << 16, MTK_QDMA_FQ_BLEN);
@@ -643,7 +676,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 
 err_dma:
 	do {
-		tx_buf = mtk_desc_to_tx_buf(ring, txd);
+		tx_buf = mtk_desc_to_tx_buf(ring, itxd);
 
 		/* unmap dma */
 		mtk_tx_unmap(&dev->dev, tx_buf);
@@ -673,6 +706,20 @@ static inline int mtk_cal_txd_req(struct sk_buff *skb)
 	return nfrags;
 }
 
+static int mtk_queue_stopped(struct mtk_eth *eth)
+{
+	int i;
+
+	for (i = 0; i < MTK_MAC_COUNT; i++) {
+		if (!eth->netdev[i])
+			continue;
+		if (netif_queue_stopped(eth->netdev[i]))
+			return 1;
+	}
+
+	return 0;
+}
+
 static void mtk_wake_queue(struct mtk_eth *eth)
 {
 	int i;
@@ -738,12 +785,9 @@ static int mtk_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (mtk_tx_map(skb, dev, tx_num, ring, gso) < 0)
 		goto drop;
 
-	if (unlikely(atomic_read(&ring->free_count) <= ring->thresh)) {
+	if (unlikely(atomic_read(&ring->free_count) <= ring->thresh))
 		mtk_stop_queue(eth);
-		if (unlikely(atomic_read(&ring->free_count) >
-			     ring->thresh))
-			mtk_wake_queue(eth);
-	}
+
 	spin_unlock_irqrestore(&eth->page_lock, flags);
 
 	return NETDEV_TX_OK;
@@ -756,7 +800,7 @@ drop:
 }
 
 static int mtk_poll_rx(struct napi_struct *napi, int budget,
-		       struct mtk_eth *eth, u32 rx_intr)
+		       struct mtk_eth *eth)
 {
 	struct mtk_rx_ring *ring = &eth->rx_ring;
 	int idx = ring->calc_idx;
@@ -798,6 +842,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 					  DMA_FROM_DEVICE);
 		if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) {
 			skb_free_frag(new_data);
+			netdev->stats.rx_dropped++;
 			goto release_desc;
 		}
 
@@ -805,6 +850,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		skb = build_skb(data, ring->frag_size);
 		if (unlikely(!skb)) {
 			put_page(virt_to_head_page(new_data));
+			netdev->stats.rx_dropped++;
 			goto release_desc;
 		}
 		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
@@ -842,22 +888,22 @@ release_desc:
 	}
 
 	if (done < budget)
-		mtk_w32(eth, rx_intr, MTK_QMTK_INT_STATUS);
+		mtk_w32(eth, MTK_RX_DONE_INT, MTK_QMTK_INT_STATUS);
 
 	return done;
 }
 
-static int mtk_poll_tx(struct mtk_eth *eth, int budget, bool *tx_again)
+static int mtk_poll_tx(struct mtk_eth *eth, int budget)
 {
 	struct mtk_tx_ring *ring = &eth->tx_ring;
 	struct mtk_tx_dma *desc;
 	struct sk_buff *skb;
 	struct mtk_tx_buf *tx_buf;
-	int total = 0, done[MTK_MAX_DEVS];
+	unsigned int done[MTK_MAX_DEVS];
 	unsigned int bytes[MTK_MAX_DEVS];
 	u32 cpu, dma;
 	static int condition;
-	int i;
+	int total = 0, i;
 
 	memset(done, 0, sizeof(done));
 	memset(bytes, 0, sizeof(bytes));
@@ -893,7 +939,6 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget, bool *tx_again)
 		}
 		mtk_tx_unmap(eth->dev, tx_buf);
 
-		ring->last_free->txd2 = next_cpu;
 		ring->last_free = desc;
 		atomic_inc(&ring->free_count);
 
@@ -909,64 +954,82 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget, bool *tx_again)
 		total += done[i];
 	}
 
-	/* read hw index again make sure no new tx packet */
-	if (cpu != dma || cpu != mtk_r32(eth, MTK_QTX_DRX_PTR))
-		*tx_again = true;
-	else
-		mtk_w32(eth, MTK_TX_DONE_INT, MTK_QMTK_INT_STATUS);
-
-	if (!total)
-		return 0;
-
-	if (atomic_read(&ring->free_count) > ring->thresh)
+	if (mtk_queue_stopped(eth) &&
+	    (atomic_read(&ring->free_count) > ring->thresh))
 		mtk_wake_queue(eth);
 
 	return total;
 }
 
-static int mtk_poll(struct napi_struct *napi, int budget)
+static void mtk_handle_status_irq(struct mtk_eth *eth)
 {
-	struct mtk_eth *eth = container_of(napi, struct mtk_eth, rx_napi);
-	u32 status, status2, mask, tx_intr, rx_intr, status_intr;
-	int tx_done, rx_done;
-	bool tx_again = false;
+	u32 status2 = mtk_r32(eth, MTK_INT_STATUS2);
 
-	status = mtk_r32(eth, MTK_QMTK_INT_STATUS);
-	status2 = mtk_r32(eth, MTK_INT_STATUS2);
-	tx_intr = MTK_TX_DONE_INT;
-	rx_intr = MTK_RX_DONE_INT;
-	status_intr = (MTK_GDM1_AF | MTK_GDM2_AF);
-	tx_done = 0;
-	rx_done = 0;
-	tx_again = 0;
+	if (unlikely(status2 & (MTK_GDM1_AF | MTK_GDM2_AF))) {
+		mtk_stats_update(eth);
+		mtk_w32(eth, (MTK_GDM1_AF | MTK_GDM2_AF),
+			MTK_INT_STATUS2);
+	}
+}
 
-	if (status & tx_intr)
-		tx_done = mtk_poll_tx(eth, budget, &tx_again);
+static int mtk_napi_tx(struct napi_struct *napi, int budget)
+{
+	struct mtk_eth *eth = container_of(napi, struct mtk_eth, tx_napi);
+	u32 status, mask;
+	int tx_done = 0;
 
-	if (status & rx_intr)
-		rx_done = mtk_poll_rx(napi, budget, eth, rx_intr);
+	mtk_handle_status_irq(eth);
+	mtk_w32(eth, MTK_TX_DONE_INT, MTK_QMTK_INT_STATUS);
+	tx_done = mtk_poll_tx(eth, budget);
 
-	if (unlikely(status2 & status_intr)) {
-		mtk_stats_update(eth);
-		mtk_w32(eth, status_intr, MTK_INT_STATUS2);
+	if (unlikely(netif_msg_intr(eth))) {
+		status = mtk_r32(eth, MTK_QMTK_INT_STATUS);
+		mask = mtk_r32(eth, MTK_QDMA_INT_MASK);
+		dev_info(eth->dev,
+			 "done tx %d, intr 0x%08x/0x%x\n",
+			 tx_done, status, mask);
 	}
 
+	if (tx_done == budget)
+		return budget;
+
+	status = mtk_r32(eth, MTK_QMTK_INT_STATUS);
+	if (status & MTK_TX_DONE_INT)
+		return budget;
+
+	napi_complete(napi);
+	mtk_irq_enable(eth, MTK_TX_DONE_INT);
+
+	return tx_done;
+}
+
+static int mtk_napi_rx(struct napi_struct *napi, int budget)
+{
+	struct mtk_eth *eth = container_of(napi, struct mtk_eth, rx_napi);
+	u32 status, mask;
+	int rx_done = 0;
+
+	mtk_handle_status_irq(eth);
+	mtk_w32(eth, MTK_RX_DONE_INT, MTK_QMTK_INT_STATUS);
+	rx_done = mtk_poll_rx(napi, budget, eth);
+
 	if (unlikely(netif_msg_intr(eth))) {
+		status = mtk_r32(eth, MTK_QMTK_INT_STATUS);
 		mask = mtk_r32(eth, MTK_QDMA_INT_MASK);
-		netdev_info(eth->netdev[0],
-			    "done tx %d, rx %d, intr 0x%08x/0x%x\n",
-			    tx_done, rx_done, status, mask);
+		dev_info(eth->dev,
+			 "done rx %d, intr 0x%08x/0x%x\n",
+			 rx_done, status, mask);
 	}
 
-	if (tx_again || rx_done == budget)
+	if (rx_done == budget)
 		return budget;
 
 	status = mtk_r32(eth, MTK_QMTK_INT_STATUS);
-	if (status & (tx_intr | rx_intr))
+	if (status & MTK_RX_DONE_INT)
 		return budget;
 
 	napi_complete(napi);
-	mtk_irq_enable(eth, tx_intr | rx_intr);
+	mtk_irq_enable(eth, MTK_RX_DONE_INT);
 
 	return rx_done;
 }
@@ -999,9 +1062,8 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 
 	atomic_set(&ring->free_count, MTK_DMA_SIZE - 2);
 	ring->next_free = &ring->dma[0];
-	ring->last_free = &ring->dma[MTK_DMA_SIZE - 2];
-	ring->thresh = max((unsigned long)MTK_DMA_SIZE >> 2,
-			      MAX_SKB_FRAGS);
+	ring->last_free = &ring->dma[MTK_DMA_SIZE - 1];
+	ring->thresh = MAX_SKB_FRAGS;
 
 	/* make sure that all changes to the dma ring are flushed before we
 	 * continue
@@ -1179,6 +1241,14 @@ static void mtk_dma_free(struct mtk_eth *eth)
 	for (i = 0; i < MTK_MAC_COUNT; i++)
 		if (eth->netdev[i])
 			netdev_reset_queue(eth->netdev[i]);
+	if (eth->scratch_ring) {
+		dma_free_coherent(eth->dev,
+				  MTK_DMA_SIZE * sizeof(struct mtk_tx_dma),
+				  eth->scratch_ring,
+				  eth->phy_scratch_ring);
+		eth->scratch_ring = NULL;
+		eth->phy_scratch_ring = 0;
+	}
 	mtk_tx_clean(eth);
 	mtk_rx_clean(eth);
 	kfree(eth->scratch_head);
@@ -1195,22 +1265,26 @@ static void mtk_tx_timeout(struct net_device *dev)
 	schedule_work(&eth->pending_work);
 }
 
-static irqreturn_t mtk_handle_irq(int irq, void *_eth)
+static irqreturn_t mtk_handle_irq_rx(int irq, void *_eth)
 {
 	struct mtk_eth *eth = _eth;
-	u32 status;
 
-	status = mtk_r32(eth, MTK_QMTK_INT_STATUS);
-	if (unlikely(!status))
-		return IRQ_NONE;
+	if (likely(napi_schedule_prep(&eth->rx_napi))) {
+		__napi_schedule(&eth->rx_napi);
+		mtk_irq_disable(eth, MTK_RX_DONE_INT);
+	}
 
-	if (likely(status & (MTK_RX_DONE_INT | MTK_TX_DONE_INT))) {
-		if (likely(napi_schedule_prep(&eth->rx_napi)))
-			__napi_schedule(&eth->rx_napi);
-	} else {
-		mtk_w32(eth, status, MTK_QMTK_INT_STATUS);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t mtk_handle_irq_tx(int irq, void *_eth)
+{
+	struct mtk_eth *eth = _eth;
+
+	if (likely(napi_schedule_prep(&eth->tx_napi))) {
+		__napi_schedule(&eth->tx_napi);
+		mtk_irq_disable(eth, MTK_TX_DONE_INT);
 	}
-	mtk_irq_disable(eth, (MTK_RX_DONE_INT | MTK_TX_DONE_INT));
 
 	return IRQ_HANDLED;
 }
@@ -1223,7 +1297,7 @@ static void mtk_poll_controller(struct net_device *dev)
 	u32 int_mask = MTK_TX_DONE_INT | MTK_RX_DONE_INT;
 
 	mtk_irq_disable(eth, int_mask);
-	mtk_handle_irq(dev->irq, dev);
+	mtk_handle_irq_rx(eth->irq[2], dev);
 	mtk_irq_enable(eth, int_mask);
 }
 #endif
@@ -1241,7 +1315,7 @@ static int mtk_start_dma(struct mtk_eth *eth)
 	mtk_w32(eth,
 		MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN |
 		MTK_RX_2B_OFFSET | MTK_DMA_SIZE_16DWORDS |
-		MTK_RX_BT_32DWORDS,
+		MTK_RX_BT_32DWORDS | MTK_NDP_CO_PRO,
 		MTK_QDMA_GLO_CFG);
 
 	return 0;
@@ -1259,6 +1333,7 @@ static int mtk_open(struct net_device *dev)
 		if (err)
 			return err;
 
+		napi_enable(&eth->tx_napi);
 		napi_enable(&eth->rx_napi);
 		mtk_irq_enable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT);
 	}
@@ -1307,6 +1382,7 @@ static int mtk_stop(struct net_device *dev)
 		return 0;
 
 	mtk_irq_disable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT);
+	napi_disable(&eth->tx_napi);
 	napi_disable(&eth->rx_napi);
 
 	mtk_stop_dma(eth, MTK_QDMA_GLO_CFG);
@@ -1344,7 +1420,11 @@ static int __init mtk_hw_init(struct mtk_eth *eth)
 	/* Enable RX VLan Offloading */
 	mtk_w32(eth, 1, MTK_CDMP_EG_CTRL);
 
-	err = devm_request_irq(eth->dev, eth->irq, mtk_handle_irq, 0,
+	err = devm_request_irq(eth->dev, eth->irq[1], mtk_handle_irq_tx, 0,
+			       dev_name(eth->dev), eth);
+	if (err)
+		return err;
+	err = devm_request_irq(eth->dev, eth->irq[2], mtk_handle_irq_rx, 0,
 			       dev_name(eth->dev), eth);
 	if (err)
 		return err;
@@ -1355,12 +1435,16 @@ static int __init mtk_hw_init(struct mtk_eth *eth)
 
 	/* disable delay and normal interrupt */
 	mtk_w32(eth, 0, MTK_QDMA_DELAY_INT);
-	mtk_irq_disable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT);
+	mtk_irq_disable(eth, ~0);
 	mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
 	mtk_w32(eth, 0, MTK_RST_GL);
 
 	/* FE int grouping */
-	mtk_w32(eth, 0, MTK_FE_INT_GRP);
+	mtk_w32(eth, MTK_TX_DONE_INT, MTK_PDMA_INT_GRP1);
+	mtk_w32(eth, MTK_RX_DONE_INT, MTK_PDMA_INT_GRP2);
+	mtk_w32(eth, MTK_TX_DONE_INT, MTK_QDMA_INT_GRP1);
+	mtk_w32(eth, MTK_RX_DONE_INT, MTK_QDMA_INT_GRP2);
+	mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);
 
 	for (i = 0; i < 2; i++) {
 		u32 val = mtk_r32(eth, MTK_GDMA_FWD_CFG(i));
@@ -1408,7 +1492,8 @@ static void mtk_uninit(struct net_device *dev)
 	phy_disconnect(mac->phy_dev);
 	mtk_mdio_cleanup(eth);
 	mtk_irq_disable(eth, ~0);
-	free_irq(dev->irq, dev);
+	free_irq(eth->irq[1], dev);
+	free_irq(eth->irq[2], dev);
 }
 
 static int mtk_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
@@ -1669,7 +1754,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET;
 
 	SET_NETDEV_DEV(eth->netdev[id], eth->dev);
-	eth->netdev[id]->watchdog_timeo = HZ;
+	eth->netdev[id]->watchdog_timeo = 5 * HZ;
 	eth->netdev[id]->netdev_ops = &mtk_netdev_ops;
 	eth->netdev[id]->base_addr = (unsigned long)eth->base;
 	eth->netdev[id]->vlan_features = MTK_HW_FEATURES &
@@ -1682,10 +1767,10 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 		dev_err(eth->dev, "error bringing up device\n");
 		goto free_netdev;
 	}
-	eth->netdev[id]->irq = eth->irq;
+	eth->netdev[id]->irq = eth->irq[0];
 	netif_info(eth, probe, eth->netdev[id],
 		   "mediatek frame engine at 0x%08lx, irq %d\n",
-		   eth->netdev[id]->base_addr, eth->netdev[id]->irq);
+		   eth->netdev[id]->base_addr, eth->irq[0]);
 
 	return 0;
 
@@ -1702,6 +1787,7 @@ static int mtk_probe(struct platform_device *pdev)
 	struct mtk_soc_data *soc;
 	struct mtk_eth *eth;
 	int err;
+	int i;
 
 	match = of_match_device(of_mtk_match, &pdev->dev);
 	soc = (struct mtk_soc_data *)match->data;
@@ -1715,6 +1801,7 @@ static int mtk_probe(struct platform_device *pdev)
 		return PTR_ERR(eth->base);
 
 	spin_lock_init(&eth->page_lock);
+	spin_lock_init(&eth->irq_lock);
 
 	eth->ethsys = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
 						      "mediatek,ethsys");
@@ -1736,10 +1823,12 @@ static int mtk_probe(struct platform_device *pdev)
 		return PTR_ERR(eth->rstc);
 	}
 
-	eth->irq = platform_get_irq(pdev, 0);
-	if (eth->irq < 0) {
-		dev_err(&pdev->dev, "no IRQ resource found\n");
-		return -ENXIO;
+	for (i = 0; i < 3; i++) {
+		eth->irq[i] = platform_get_irq(pdev, i);
+		if (eth->irq[i] < 0) {
+			dev_err(&pdev->dev, "no IRQ%d resource found\n", i);
+			return -ENXIO;
+		}
 	}
 
 	eth->clk_ethif = devm_clk_get(&pdev->dev, "ethif");
@@ -1780,7 +1869,9 @@ static int mtk_probe(struct platform_device *pdev)
 	 * for NAPI to work
 	 */
 	init_dummy_netdev(&eth->dummy_dev);
-	netif_napi_add(&eth->dummy_dev, &eth->rx_napi, mtk_poll,
+	netif_napi_add(&eth->dummy_dev, &eth->tx_napi, mtk_napi_tx,
+		       MTK_NAPI_WEIGHT);
+	netif_napi_add(&eth->dummy_dev, &eth->rx_napi, mtk_napi_rx,
 		       MTK_NAPI_WEIGHT);
 
 	platform_set_drvdata(pdev, eth);
@@ -1801,6 +1892,7 @@ static int mtk_remove(struct platform_device *pdev)
 	clk_disable_unprepare(eth->clk_gp1);
 	clk_disable_unprepare(eth->clk_gp2);
 
+	netif_napi_del(&eth->tx_napi);
 	netif_napi_del(&eth->rx_napi);
 	mtk_cleanup(eth);
 	platform_set_drvdata(pdev, NULL);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index eed626d56ea4..f82e3acb947b 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -68,6 +68,10 @@
 /* Unicast Filter MAC Address Register - High */
 #define MTK_GDMA_MAC_ADRH(x)	(0x50C + (x * 0x1000))
 
+/* PDMA Interrupt grouping registers */
+#define MTK_PDMA_INT_GRP1	0xa50
+#define MTK_PDMA_INT_GRP2	0xa54
+
 /* QDMA TX Queue Configuration Registers */
 #define MTK_QTX_CFG(x)		(0x1800 + (x * 0x10))
 #define QDMA_RES_THRES		4
@@ -91,6 +95,7 @@
 #define MTK_QDMA_GLO_CFG	0x1A04
 #define MTK_RX_2B_OFFSET	BIT(31)
 #define MTK_RX_BT_32DWORDS	(3 << 11)
+#define MTK_NDP_CO_PRO		BIT(10)
 #define MTK_TX_WB_DDONE		BIT(6)
 #define MTK_DMA_SIZE_16DWORDS	(2 << 4)
 #define MTK_RX_DMA_BUSY		BIT(3)
@@ -124,6 +129,11 @@
 #define MTK_TX_DONE_INT		(MTK_TX_DONE_INT0 | MTK_TX_DONE_INT1 | \
 				 MTK_TX_DONE_INT2 | MTK_TX_DONE_INT3)
 
+/* QDMA Interrupt grouping registers */
+#define MTK_QDMA_INT_GRP1	0x1a20
+#define MTK_QDMA_INT_GRP2	0x1a24
+#define MTK_RLS_DONE_INT	BIT(0)
+
 /* QDMA Interrupt Status Register */
 #define MTK_QDMA_INT_MASK	0x1A1C
 
@@ -355,8 +365,10 @@ struct mtk_rx_ring {
  * @dma_refcnt:		track how many netdevs are using the DMA engine
  * @tx_ring:		Pointer to the memore holding info about the TX ring
  * @rx_ring:		Pointer to the memore holding info about the RX ring
- * @rx_napi:		The NAPI struct
+ * @tx_napi:		The TX NAPI struct
+ * @rx_napi:		The RX NAPI struct
  * @scratch_ring:	Newer SoCs need memory for a second HW managed TX ring
+ * @phy_scratch_ring:	physical address of scratch_ring
  * @scratch_head:	The scratch memory that scratch_ring points to.
  * @clk_ethif:		The ethif clock
  * @clk_esw:		The switch clock
@@ -371,10 +383,11 @@ struct mtk_eth {
 	void __iomem			*base;
 	struct reset_control		*rstc;
 	spinlock_t			page_lock;
+	spinlock_t			irq_lock;
 	struct net_device		dummy_dev;
 	struct net_device		*netdev[MTK_MAX_DEVS];
 	struct mtk_mac			*mac[MTK_MAX_DEVS];
-	int				irq;
+	int				irq[3];
 	u32				msg_enable;
 	unsigned long			sysclk;
 	struct regmap			*ethsys;
@@ -382,8 +395,10 @@ struct mtk_eth {
 	atomic_t			dma_refcnt;
 	struct mtk_tx_ring		tx_ring;
 	struct mtk_rx_ring		rx_ring;
+	struct napi_struct		tx_napi;
 	struct napi_struct		rx_napi;
 	struct mtk_tx_dma		*scratch_ring;
+	dma_addr_t			phy_scratch_ring;
 	void				*scratch_head;
 	struct clk			*clk_ethif;
 	struct clk			*clk_esw;
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index 9ca3734ebb6b..5098e7f21987 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -24,13 +24,6 @@ config MLX4_EN_DCB
 
 	  If unsure, set to Y
 
-config MLX4_EN_VXLAN
-	bool "VXLAN offloads Support"
-	default y
-	depends on MLX4_EN && VXLAN && !(MLX4_EN=y && VXLAN=m)
-	---help---
-	  Say Y here if you want to use VXLAN offloads in the driver.
-
 config MLX4_CORE
 	tristate
 	depends on PCI
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index e94ca1c3fc7c..f04a423ff79d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2597,7 +2597,6 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	priv->cmd.free_head = 0;
 
 	sema_init(&priv->cmd.event_sem, priv->cmd.max_cmds);
-	spin_lock_init(&priv->cmd.context_lock);
 
 	for (priv->cmd.token_mask = 1;
 	     priv->cmd.token_mask < priv->cmd.max_cmds;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index f01918c63f28..99c6bbdff501 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -37,6 +37,11 @@
 #include "mlx4_en.h"
 #include "fw_qos.h"
 
+enum {
+	MLX4_CEE_STATE_DOWN   = 0,
+	MLX4_CEE_STATE_UP     = 1,
+};
+
 /* Definitions for QCN
  */
 
@@ -80,13 +85,202 @@ struct mlx4_congestion_control_mb_prio_802_1_qau_statistics {
 	__be32 reserved3[4];
 };
 
+static u8 mlx4_en_dcbnl_getcap(struct net_device *dev, int capid, u8 *cap)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	switch (capid) {
+	case DCB_CAP_ATTR_PFC:
+		*cap = true;
+		break;
+	case DCB_CAP_ATTR_DCBX:
+		*cap = priv->cee_params.dcbx_cap;
+		break;
+	case DCB_CAP_ATTR_PFC_TCS:
+		*cap = 1 <<  mlx4_max_tc(priv->mdev->dev);
+		break;
+	default:
+		*cap = false;
+		break;
+	}
+
+	return 0;
+}
+
+static u8 mlx4_en_dcbnl_getpfcstate(struct net_device *netdev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	return priv->cee_params.dcb_cfg.pfc_state;
+}
+
+static void mlx4_en_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	priv->cee_params.dcb_cfg.pfc_state = state;
+}
+
+static void mlx4_en_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
+				      u8 *setting)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	*setting = priv->cee_params.dcb_cfg.tc_config[priority].dcb_pfc;
+}
+
+static void mlx4_en_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
+				      u8 setting)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	priv->cee_params.dcb_cfg.tc_config[priority].dcb_pfc = setting;
+	priv->cee_params.dcb_cfg.pfc_state = true;
+}
+
+static int mlx4_en_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	if (!(priv->flags & MLX4_EN_FLAG_DCB_ENABLED))
+		return -EINVAL;
+
+	if (tcid == DCB_NUMTCS_ATTR_PFC)
+		*num = mlx4_max_tc(priv->mdev->dev);
+	else
+		*num = 0;
+
+	return 0;
+}
+
+static u8 mlx4_en_dcbnl_set_all(struct net_device *netdev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_cee_config *dcb_cfg = &priv->cee_params.dcb_cfg;
+	int err = 0;
+
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return -EINVAL;
+
+	if (dcb_cfg->pfc_state) {
+		int tc;
+
+		priv->prof->rx_pause = 0;
+		priv->prof->tx_pause = 0;
+		for (tc = 0; tc < CEE_DCBX_MAX_PRIO; tc++) {
+			u8 tc_mask = 1 << tc;
+
+			switch (dcb_cfg->tc_config[tc].dcb_pfc) {
+			case pfc_disabled:
+				priv->prof->tx_ppp &= ~tc_mask;
+				priv->prof->rx_ppp &= ~tc_mask;
+				break;
+			case pfc_enabled_full:
+				priv->prof->tx_ppp |= tc_mask;
+				priv->prof->rx_ppp |= tc_mask;
+				break;
+			case pfc_enabled_tx:
+				priv->prof->tx_ppp |= tc_mask;
+				priv->prof->rx_ppp &= ~tc_mask;
+				break;
+			case pfc_enabled_rx:
+				priv->prof->tx_ppp &= ~tc_mask;
+				priv->prof->rx_ppp |= tc_mask;
+				break;
+			default:
+				break;
+			}
+		}
+		en_dbg(DRV, priv, "Set pfc on\n");
+	} else {
+		priv->prof->rx_pause = 1;
+		priv->prof->tx_pause = 1;
+		en_dbg(DRV, priv, "Set pfc off\n");
+	}
+
+	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
+				    priv->rx_skb_size + ETH_FCS_LEN,
+				    priv->prof->tx_pause,
+				    priv->prof->tx_ppp,
+				    priv->prof->rx_pause,
+				    priv->prof->rx_ppp);
+	if (err)
+		en_err(priv, "Failed setting pause params\n");
+	return err;
+}
+
+static u8 mlx4_en_dcbnl_get_state(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	if (priv->flags & MLX4_EN_FLAG_DCB_ENABLED)
+		return MLX4_CEE_STATE_UP;
+
+	return MLX4_CEE_STATE_DOWN;
+}
+
+static u8 mlx4_en_dcbnl_set_state(struct net_device *dev, u8 state)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	int num_tcs = 0;
+
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return 1;
+
+	if (!!(state) == !!(priv->flags & MLX4_EN_FLAG_DCB_ENABLED))
+		return 0;
+
+	if (state) {
+		priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
+		num_tcs = IEEE_8021QAZ_MAX_TCS;
+	} else {
+		priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
+	}
+
+	return mlx4_en_setup_tc(dev, num_tcs);
+}
+
+/* On success returns a non-zero 802.1p user priority bitmap
+ * otherwise returns 0 as the invalid user priority bitmap to
+ * indicate an error.
+ */
+static int mlx4_en_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct dcb_app app = {
+				.selector = idtype,
+				.protocol = id,
+			     };
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return 0;
+
+	return dcb_getapp(netdev, &app);
+}
+
+static int mlx4_en_dcbnl_setapp(struct net_device *netdev, u8 idtype,
+				u16 id, u8 up)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct dcb_app app;
+
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return -EINVAL;
+
+	memset(&app, 0, sizeof(struct dcb_app));
+	app.selector = idtype;
+	app.protocol = id;
+	app.priority = up;
+
+	return dcb_setapp(netdev, &app);
+}
+
 static int mlx4_en_dcbnl_ieee_getets(struct net_device *dev,
 				   struct ieee_ets *ets)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct ieee_ets *my_ets = &priv->ets;
 
-	/* No IEEE PFC settings available */
 	if (!my_ets)
 		return -EINVAL;
 
@@ -237,18 +431,51 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
 
 static u8 mlx4_en_dcbnl_getdcbx(struct net_device *dev)
 {
-	return DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE;
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	return priv->cee_params.dcbx_cap;
 }
 
 static u8 mlx4_en_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 {
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct ieee_ets ets = {0};
+	struct ieee_pfc pfc = {0};
+
+	if (mode == priv->cee_params.dcbx_cap)
+		return 0;
+
 	if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
-	    (mode & DCB_CAP_DCBX_VER_CEE) ||
-	    !(mode & DCB_CAP_DCBX_VER_IEEE) ||
+	    ((mode & DCB_CAP_DCBX_VER_IEEE) &&
+	     (mode & DCB_CAP_DCBX_VER_CEE)) ||
 	    !(mode & DCB_CAP_DCBX_HOST))
-		return 1;
+		goto err;
+
+	priv->cee_params.dcbx_cap = mode;
+
+	ets.ets_cap = IEEE_8021QAZ_MAX_TCS;
+	pfc.pfc_cap = IEEE_8021QAZ_MAX_TCS;
+
+	if (mode & DCB_CAP_DCBX_VER_IEEE) {
+		if (mlx4_en_dcbnl_ieee_setets(dev, &ets))
+			goto err;
+		if (mlx4_en_dcbnl_ieee_setpfc(dev, &pfc))
+			goto err;
+	} else if (mode & DCB_CAP_DCBX_VER_CEE) {
+		if (mlx4_en_dcbnl_set_all(dev))
+			goto err;
+	} else {
+		if (mlx4_en_dcbnl_ieee_setets(dev, &ets))
+			goto err;
+		if (mlx4_en_dcbnl_ieee_setpfc(dev, &pfc))
+			goto err;
+		if (mlx4_en_setup_tc(dev, 0))
+			goto err;
+	}
 
 	return 0;
+err:
+	return 1;
 }
 
 #define MLX4_RATELIMIT_UNITS_IN_KB 100000 /* rate-limit HW unit in Kbps */
@@ -463,24 +690,46 @@ static int mlx4_en_dcbnl_ieee_getqcnstats(struct net_device *dev,
 }
 
 const struct dcbnl_rtnl_ops mlx4_en_dcbnl_ops = {
-	.ieee_getets	= mlx4_en_dcbnl_ieee_getets,
-	.ieee_setets	= mlx4_en_dcbnl_ieee_setets,
-	.ieee_getmaxrate = mlx4_en_dcbnl_ieee_getmaxrate,
-	.ieee_setmaxrate = mlx4_en_dcbnl_ieee_setmaxrate,
-	.ieee_getpfc	= mlx4_en_dcbnl_ieee_getpfc,
-	.ieee_setpfc	= mlx4_en_dcbnl_ieee_setpfc,
+	.ieee_getets		= mlx4_en_dcbnl_ieee_getets,
+	.ieee_setets		= mlx4_en_dcbnl_ieee_setets,
+	.ieee_getmaxrate	= mlx4_en_dcbnl_ieee_getmaxrate,
+	.ieee_setmaxrate	= mlx4_en_dcbnl_ieee_setmaxrate,
+	.ieee_getqcn		= mlx4_en_dcbnl_ieee_getqcn,
+	.ieee_setqcn		= mlx4_en_dcbnl_ieee_setqcn,
+	.ieee_getqcnstats	= mlx4_en_dcbnl_ieee_getqcnstats,
+	.ieee_getpfc		= mlx4_en_dcbnl_ieee_getpfc,
+	.ieee_setpfc		= mlx4_en_dcbnl_ieee_setpfc,
+
+	.getstate	= mlx4_en_dcbnl_get_state,
+	.setstate	= mlx4_en_dcbnl_set_state,
+	.getpfccfg	= mlx4_en_dcbnl_get_pfc_cfg,
+	.setpfccfg	= mlx4_en_dcbnl_set_pfc_cfg,
+	.setall		= mlx4_en_dcbnl_set_all,
+	.getcap		= mlx4_en_dcbnl_getcap,
+	.getnumtcs	= mlx4_en_dcbnl_getnumtcs,
+	.getpfcstate	= mlx4_en_dcbnl_getpfcstate,
+	.setpfcstate	= mlx4_en_dcbnl_setpfcstate,
+	.getapp		= mlx4_en_dcbnl_getapp,
+	.setapp		= mlx4_en_dcbnl_setapp,
 
 	.getdcbx	= mlx4_en_dcbnl_getdcbx,
 	.setdcbx	= mlx4_en_dcbnl_setdcbx,
-	.ieee_getqcn	= mlx4_en_dcbnl_ieee_getqcn,
-	.ieee_setqcn	= mlx4_en_dcbnl_ieee_setqcn,
-	.ieee_getqcnstats = mlx4_en_dcbnl_ieee_getqcnstats,
 };
 
 const struct dcbnl_rtnl_ops mlx4_en_dcbnl_pfc_ops = {
 	.ieee_getpfc	= mlx4_en_dcbnl_ieee_getpfc,
 	.ieee_setpfc	= mlx4_en_dcbnl_ieee_setpfc,
 
+	.setstate	= mlx4_en_dcbnl_set_state,
+	.getpfccfg	= mlx4_en_dcbnl_get_pfc_cfg,
+	.setpfccfg	= mlx4_en_dcbnl_set_pfc_cfg,
+	.setall		= mlx4_en_dcbnl_set_all,
+	.getnumtcs	= mlx4_en_dcbnl_getnumtcs,
+	.getpfcstate	= mlx4_en_dcbnl_getpfcstate,
+	.setpfcstate	= mlx4_en_dcbnl_setpfcstate,
+	.getapp		= mlx4_en_dcbnl_getapp,
+	.setapp		= mlx4_en_dcbnl_setapp,
+
 	.getdcbx	= mlx4_en_dcbnl_getdcbx,
 	.setdcbx	= mlx4_en_dcbnl_setdcbx,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index fc95affaf76b..51a2e8252b82 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1107,7 +1107,7 @@ static u32 mlx4_en_get_rxfh_indir_size(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
-	return priv->rx_ring_num;
+	return rounddown_pow_of_two(priv->rx_ring_num);
 }
 
 static u32 mlx4_en_get_rxfh_key_size(struct net_device *netdev)
@@ -1141,19 +1141,17 @@ static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
 			    u8 *hfunc)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	struct mlx4_en_rss_map *rss_map = &priv->rss_map;
-	int rss_rings;
-	size_t n = priv->rx_ring_num;
+	u32 n = mlx4_en_get_rxfh_indir_size(dev);
+	u32 i, rss_rings;
 	int err = 0;
 
-	rss_rings = priv->prof->rss_rings ?: priv->rx_ring_num;
-	rss_rings = 1 << ilog2(rss_rings);
+	rss_rings = priv->prof->rss_rings ?: n;
+	rss_rings = rounddown_pow_of_two(rss_rings);
 
-	while (n--) {
+	for (i = 0; i < n; i++) {
 		if (!ring_index)
 			break;
-		ring_index[n] = rss_map->qps[n % rss_rings].qpn -
-			rss_map->base_qpn;
+		ring_index[i] = i % rss_rings;
 	}
 	if (key)
 		memcpy(key, priv->rss_key, MLX4_EN_RSS_KEY_SIZE);
@@ -1166,6 +1164,7 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 			    const u8 *key, const u8 hfunc)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	u32 n = mlx4_en_get_rxfh_indir_size(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
 	int port_up = 0;
 	int err = 0;
@@ -1175,18 +1174,18 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 	/* Calculate RSS table size and make sure flows are spread evenly
 	 * between rings
 	 */
-	for (i = 0; i < priv->rx_ring_num; i++) {
+	for (i = 0; i < n; i++) {
 		if (!ring_index)
-			continue;
+			break;
 		if (i > 0 && !ring_index[i] && !rss_rings)
 			rss_rings = i;
 
-		if (ring_index[i] != (i % (rss_rings ?: priv->rx_ring_num)))
+		if (ring_index[i] != (i % (rss_rings ?: n)))
 			return -EINVAL;
 	}
 
 	if (!rss_rings)
-		rss_rings = priv->rx_ring_num;
+		rss_rings = n;
 
 	/* RSS table size must be an order of 2 */
 	if (!is_power_of_2(rss_rings))
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 19ceced6736c..6083775dae16 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -67,6 +67,17 @@ int mlx4_en_setup_tc(struct net_device *dev, u8 up)
 		offset += priv->num_tx_rings_p_up;
 	}
 
+#ifdef CONFIG_MLX4_EN_DCB
+	if (!mlx4_is_slave(priv->mdev->dev)) {
+		if (up) {
+			priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
+		} else {
+			priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
+			priv->cee_params.dcb_cfg.pfc_state = false;
+		}
+	}
+#endif /* CONFIG_MLX4_EN_DCB */
+
 	return 0;
 }
 
@@ -406,14 +417,18 @@ static int mlx4_en_vlan_rx_add_vid(struct net_device *dev,
 	mutex_lock(&mdev->state_lock);
 	if (mdev->device_up && priv->port_up) {
 		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
-		if (err)
+		if (err) {
 			en_err(priv, "Failed configuring VLAN filter\n");
+			goto out;
+		}
 	}
-	if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx))
-		en_dbg(HW, priv, "failed adding vlan %d\n", vid);
-	mutex_unlock(&mdev->state_lock);
+	err = mlx4_register_vlan(mdev->dev, priv->port, vid, &idx);
+	if (err)
+		en_dbg(HW, priv, "Failed adding vlan %d\n", vid);
 
-	return 0;
+out:
+	mutex_unlock(&mdev->state_lock);
+	return err;
 }
 
 static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
@@ -421,7 +436,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
-	int err;
+	int err = 0;
 
 	en_dbg(HW, priv, "Killing VID:%d\n", vid);
 
@@ -438,7 +453,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
 	}
 	mutex_unlock(&mdev->state_lock);
 
-	return 0;
+	return err;
 }
 
 static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac)
@@ -1197,8 +1212,8 @@ static void mlx4_en_netpoll(struct net_device *dev)
 	struct mlx4_en_cq *cq;
 	int i;
 
-	for (i = 0; i < priv->rx_ring_num; i++) {
-		cq = priv->rx_cq[i];
+	for (i = 0; i < priv->tx_ring_num; i++) {
+		cq = priv->tx_cq[i];
 		napi_schedule(&cq->napi);
 	}
 }
@@ -1692,10 +1707,9 @@ int mlx4_en_start_port(struct net_device *dev)
 	/* Schedule multicast task to populate multicast list */
 	queue_work(mdev->workqueue, &priv->rx_mode_task);
 
-#ifdef CONFIG_MLX4_EN_VXLAN
 	if (priv->mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
-		vxlan_get_rx_port(dev);
-#endif
+		udp_tunnel_get_rx_info(dev);
+
 	priv->port_up = true;
 	netif_tx_start_all_queues(dev);
 	netif_device_attach(dev);
@@ -2032,11 +2046,20 @@ err:
 	return -ENOMEM;
 }
 
+static void mlx4_en_shutdown(struct net_device *dev)
+{
+	rtnl_lock();
+	netif_device_detach(dev);
+	mlx4_en_close(dev);
+	rtnl_unlock();
+}
 
 void mlx4_en_destroy_netdev(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	bool shutdown = mdev->dev->persist->interface_state &
+					    MLX4_INTERFACE_STATE_SHUTDOWN;
 
 	en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port);
 
@@ -2044,7 +2067,10 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
 	if (priv->registered) {
 		devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev,
 							      priv->port));
-		unregister_netdev(dev);
+		if (shutdown)
+			mlx4_en_shutdown(dev);
+		else
+			unregister_netdev(dev);
 	}
 
 	if (priv->allocated)
@@ -2069,7 +2095,8 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
 	kfree(priv->tx_ring);
 	kfree(priv->tx_cq);
 
-	free_netdev(dev);
+	if (!shutdown)
+		free_netdev(dev);
 }
 
 static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
@@ -2342,7 +2369,6 @@ static int mlx4_en_get_phys_port_id(struct net_device *dev,
 	return 0;
 }
 
-#ifdef CONFIG_MLX4_EN_VXLAN
 static void mlx4_en_add_vxlan_offloads(struct work_struct *work)
 {
 	int ret;
@@ -2392,15 +2418,19 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
 }
 
 static void mlx4_en_add_vxlan_port(struct  net_device *dev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	__be16 port = ti->port;
 	__be16 current_port;
 
-	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
+	if (ti->sa_family != AF_INET)
 		return;
 
-	if (sa_family == AF_INET6)
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		return;
 
 	current_port = priv->vxlan_port;
@@ -2415,15 +2445,19 @@ static void mlx4_en_add_vxlan_port(struct  net_device *dev,
 }
 
 static void mlx4_en_del_vxlan_port(struct  net_device *dev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	__be16 port = ti->port;
 	__be16 current_port;
 
-	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
+	if (ti->sa_family != AF_INET)
 		return;
 
-	if (sa_family == AF_INET6)
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		return;
 
 	current_port = priv->vxlan_port;
@@ -2447,13 +2481,17 @@ static netdev_features_t mlx4_en_features_check(struct sk_buff *skb,
 	 * strip that feature if this is an IPv6 encapsulated frame.
 	 */
 	if (skb->encapsulation &&
-	    (skb->ip_summed == CHECKSUM_PARTIAL) &&
-	    (ip_hdr(skb)->version != 4))
-		features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+	    (skb->ip_summed == CHECKSUM_PARTIAL)) {
+		struct mlx4_en_priv *priv = netdev_priv(dev);
+
+		if (!priv->vxlan_port ||
+		    (ip_hdr(skb)->version != 4) ||
+		    (udp_hdr(skb)->dest != priv->vxlan_port))
+			features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+	}
 
 	return features;
 }
-#endif
 
 static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 maxrate)
 {
@@ -2506,11 +2544,9 @@ static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
 #endif
 	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
-#ifdef CONFIG_MLX4_EN_VXLAN
-	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
-	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
+	.ndo_udp_tunnel_add	= mlx4_en_add_vxlan_port,
+	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
-#endif
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
 };
 
@@ -2544,11 +2580,9 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
 #endif
 	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
-#ifdef CONFIG_MLX4_EN_VXLAN
-	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
-	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
+	.ndo_udp_tunnel_add	= mlx4_en_add_vxlan_port,
+	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
-#endif
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
 };
 
@@ -2814,6 +2848,9 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	struct mlx4_en_priv *priv;
 	int i;
 	int err;
+#ifdef CONFIG_MLX4_EN_DCB
+	struct tc_configuration *tc;
+#endif
 
 	dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv),
 				 MAX_TX_RINGS, MAX_RX_RINGS);
@@ -2839,10 +2876,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate);
 	INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats);
 	INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task);
-#ifdef CONFIG_MLX4_EN_VXLAN
 	INIT_WORK(&priv->vxlan_add_task, mlx4_en_add_vxlan_offloads);
 	INIT_WORK(&priv->vxlan_del_task, mlx4_en_del_vxlan_offloads);
-#endif
 #ifdef CONFIG_RFS_ACCEL
 	INIT_LIST_HEAD(&priv->filters);
 	spin_lock_init(&priv->filters_lock);
@@ -2882,6 +2917,17 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->msg_enable = MLX4_EN_MSG_LEVEL;
 #ifdef CONFIG_MLX4_EN_DCB
 	if (!mlx4_is_slave(priv->mdev->dev)) {
+		priv->cee_params.dcbx_cap = DCB_CAP_DCBX_VER_CEE |
+					    DCB_CAP_DCBX_HOST |
+					    DCB_CAP_DCBX_VER_IEEE;
+		priv->flags |= MLX4_EN_DCB_ENABLED;
+		priv->cee_params.dcb_cfg.pfc_state = false;
+
+		for (i = 0; i < MLX4_EN_NUM_UP; i++) {
+			tc = &priv->cee_params.dcb_cfg.tc_config[i];
+			tc->dcb_pfc = pfc_disabled;
+		}
+
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETS_CFG) {
 			dev->dcbnl_ops = &mlx4_en_dcbnl_ops;
 		} else {
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index e97094598b2d..f4497cf4d06d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -1128,6 +1128,7 @@ int mlx4_QUERY_PORT(struct mlx4_dev *dev, int port, struct mlx4_port_cap *port_c
 		port_cap->max_pkeys	   = 1 << (field & 0xf);
 		MLX4_GET(field, outbox, QUERY_PORT_MAX_VL_OFFSET);
 		port_cap->max_vl	   = field & 0xf;
+		port_cap->max_tc_eth	   = field >> 4;
 		MLX4_GET(field, outbox, QUERY_PORT_MAX_MACVLAN_OFFSET);
 		port_cap->log_max_macs  = field & 0xf;
 		port_cap->log_max_vlans = field >> 4;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 7ea258af636a..cdbd76f10ced 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -53,6 +53,7 @@ struct mlx4_port_cap {
 	int ib_mtu;
 	int max_port_width;
 	int max_vl;
+	int max_tc_eth;
 	int max_gids;
 	int max_pkeys;
 	u64 def_mac;
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index dec77d6f0ac9..7ae1cdad9bf0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -147,7 +147,7 @@ int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
 	if (enable) {
 		dev->flags |= MLX4_FLAG_BONDED;
 	} else {
-		 ret = mlx4_virt2phy_port_map(dev, 1, 2);
+		ret = mlx4_virt2phy_port_map(dev, 1, 2);
 		if (ret) {
 			mlx4_err(dev, "Fail to reset port map\n");
 			return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 12c77a70abdb..75dd2e3d3059 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -292,6 +292,7 @@ static int _mlx4_dev_port(struct mlx4_dev *dev, int port,
 	dev->caps.pkey_table_len[port] = port_cap->max_pkeys;
 	dev->caps.port_width_cap[port] = port_cap->max_port_width;
 	dev->caps.eth_mtu_cap[port]    = port_cap->eth_mtu;
+	dev->caps.max_tc_eth	       = port_cap->max_tc_eth;
 	dev->caps.def_mac[port]        = port_cap->def_mac;
 	dev->caps.supported_type[port] = port_cap->supported_port_types;
 	dev->caps.suggested_type[port] = port_cap->suggested_type;
@@ -2599,7 +2600,7 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 	err = mlx4_init_uar_table(dev);
 	if (err) {
 		mlx4_err(dev, "Failed to initialize user access region table, aborting\n");
-		 return err;
+		return err;
 	}
 
 	err = mlx4_uar_alloc(dev, &priv->driver_uar);
@@ -3222,6 +3223,7 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 
 	INIT_LIST_HEAD(&priv->pgdir_list);
 	mutex_init(&priv->pgdir_mutex);
+	spin_lock_init(&priv->cmd.context_lock);
 
 	INIT_LIST_HEAD(&priv->bf_list);
 	mutex_init(&priv->bf_mutex);
@@ -4134,8 +4136,11 @@ static void mlx4_shutdown(struct pci_dev *pdev)
 
 	mlx4_info(persist->dev, "mlx4_shutdown was called\n");
 	mutex_lock(&persist->interface_state_mutex);
-	if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
+	if (persist->interface_state & MLX4_INTERFACE_STATE_UP) {
+		/* Notify mlx4 clients that the kernel is being shut down */
+		persist->interface_state |= MLX4_INTERFACE_STATE_SHUTDOWN;
 		mlx4_unload_one(pdev);
+	}
 	mutex_unlock(&persist->interface_state_mutex);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index f2d0920018a5..94b891c118c1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -618,8 +618,8 @@ static int remove_promisc_qp(struct mlx4_dev *dev, u8 port,
 				err = mlx4_READ_ENTRY(dev,
 						      entry->index,
 						      mailbox);
-					if (err)
-						goto out_mailbox;
+				if (err)
+					goto out_mailbox;
 				members_count =
 					be32_to_cpu(mgm->members_count) &
 					0xffffff;
@@ -657,8 +657,8 @@ static int remove_promisc_qp(struct mlx4_dev *dev, u8 port,
 				err = mlx4_WRITE_ENTRY(dev,
 						       entry->index,
 						       mailbox);
-					if (err)
-						goto out_mailbox;
+				if (err)
+					goto out_mailbox;
 			}
 		}
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 467d47ed2c39..d39bf594abe4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -448,6 +448,27 @@ struct mlx4_en_frag_info {
 
 #define MLX4_EN_TC_ETS 7
 
+enum dcb_pfc_type {
+	pfc_disabled = 0,
+	pfc_enabled_full,
+	pfc_enabled_tx,
+	pfc_enabled_rx
+};
+
+struct tc_configuration {
+	enum dcb_pfc_type  dcb_pfc;
+};
+
+struct mlx4_en_cee_config {
+	bool	pfc_state;
+	struct	tc_configuration tc_config[MLX4_EN_NUM_UP];
+};
+
+struct mlx4_en_cee_params {
+	u8 dcbx_cap;
+	struct mlx4_en_cee_config dcb_cfg;
+};
+
 #endif
 
 struct ethtool_flow_id {
@@ -467,6 +488,9 @@ enum {
 	MLX4_EN_FLAG_RX_FILTER_NEEDED	= (1 << 3),
 	MLX4_EN_FLAG_FORCE_PROMISC	= (1 << 4),
 	MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP	= (1 << 5),
+#ifdef CONFIG_MLX4_EN_DCB
+	MLX4_EN_FLAG_DCB_ENABLED        = (1 << 6),
+#endif
 };
 
 #define PORT_BEACON_MAX_LIMIT (65535)
@@ -545,10 +569,8 @@ struct mlx4_en_priv {
 	struct work_struct linkstate_task;
 	struct delayed_work stats_task;
 	struct delayed_work service_task;
-#ifdef CONFIG_MLX4_EN_VXLAN
 	struct work_struct vxlan_add_task;
 	struct work_struct vxlan_del_task;
-#endif
 	struct mlx4_en_perf_stats pstats;
 	struct mlx4_en_pkt_stats pkstats;
 	struct mlx4_en_counter_stats pf_stats;
@@ -570,9 +592,11 @@ struct mlx4_en_priv {
 	u32 counter_index;
 
 #ifdef CONFIG_MLX4_EN_DCB
+#define MLX4_EN_DCB_ENABLED	0x3
 	struct ieee_ets ets;
 	u16 maxrate[IEEE_8021QAZ_MAX_TCS];
 	enum dcbnl_cndd_states cndd_state[IEEE_8021QAZ_MAX_TCS];
+	struct mlx4_en_cee_params cee_params;
 #endif
 #ifdef CONFIG_RFS_ACCEL
 	spinlock_t filters_lock;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 93195191f45b..395b5463cfd9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -248,7 +248,7 @@ static void mlx4_free_mtt_range(struct mlx4_dev *dev, u32 offset, int order)
 				  offset, order);
 		return;
 	}
-	 __mlx4_free_mtt_range(dev, offset, order);
+	__mlx4_free_mtt_range(dev, offset, order);
 }
 
 void mlx4_mtt_cleanup(struct mlx4_dev *dev, struct mlx4_mtt *mtt)
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 087b23b320cb..3d2095e5c61c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -52,6 +52,7 @@
 
 #define MLX4_FLAG_V_IGNORE_FCS_MASK		0x2
 #define MLX4_IGNORE_FCS_MASK			0x1
+#define MLNX4_TX_MAX_NUMBER			8
 
 void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table)
 {
@@ -2015,3 +2016,14 @@ out:
 	return ret;
 }
 EXPORT_SYMBOL(mlx4_get_module_info);
+
+int mlx4_max_tc(struct mlx4_dev *dev)
+{
+	u8 num_tc = dev->caps.max_tc_eth;
+
+	if (!num_tc)
+		num_tc = MLNX4_TX_MAX_NUMBER;
+
+	return num_tc;
+}
+EXPORT_SYMBOL(mlx4_max_tc);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index cd9b2b28df88..8b81114bdc72 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2372,16 +2372,15 @@ static int mpt_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 		__mlx4_mpt_release(dev, index);
 		break;
 	case RES_OP_MAP_ICM:
-			index = get_param_l(&in_param);
-			id = index & mpt_mask(dev);
-			err = mr_res_start_move_to(dev, slave, id,
-						   RES_MPT_RESERVED, &mpt);
-			if (err)
-				return err;
-
-			__mlx4_mpt_free_icm(dev, mpt->key);
-			res_end_move(dev, slave, RES_MPT, id);
+		index = get_param_l(&in_param);
+		id = index & mpt_mask(dev);
+		err = mr_res_start_move_to(dev, slave, id,
+					   RES_MPT_RESERVED, &mpt);
+		if (err)
 			return err;
+
+		__mlx4_mpt_free_icm(dev, mpt->key);
+		res_end_move(dev, slave, RES_MPT, id);
 		break;
 	default:
 		err = -EINVAL;
@@ -4253,9 +4252,8 @@ int mlx4_UPDATE_QP_wrapper(struct mlx4_dev *dev, int slave,
 	     (1ULL << MLX4_UPD_QP_PATH_MASK_ETH_SRC_CHECK_MC_LB)) &&
 		!(dev->caps.flags2 &
 		  MLX4_DEV_CAP_FLAG2_UPDATE_QP_SRC_CHECK_LB)) {
-			mlx4_warn(dev,
-				  "Src check LB for slave %d isn't supported\n",
-				   slave);
+		mlx4_warn(dev, "Src check LB for slave %d isn't supported\n",
+			  slave);
 		return -ENOTSUPP;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 1cf722eba607..aae46884bf93 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -4,6 +4,7 @@
 
 config MLX5_CORE
 	tristate "Mellanox Technologies ConnectX-4 and Connect-IB core driver"
+	depends on MAY_USE_DEVLINK
 	depends on PCI
 	default n
 	---help---
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 9ea7b583096a..05cc1effc13c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -1,11 +1,13 @@
 obj-$(CONFIG_MLX5_CORE)		+= mlx5_core.o
 
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
-		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o   \
-		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o fs_counters.o
+		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
+		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
+		fs_counters.o rl.o
 
-mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o \
-		en_main.o en_fs.o en_ethtool.o en_tx.o en_rx.o \
-		en_txrx.o en_clock.o vxlan.o en_tc.o en_arfs.o
+mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o eswitch_offloads.o \
+		en_main.o en_common.o en_fs.o en_ethtool.o en_tx.o \
+		en_rx.o en_rx_am.o en_txrx.o en_clock.o vxlan.o \
+		en_tc.o en_arfs.o en_rep.o en_fs_ethtool.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) +=  en_dcbnl.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index dcd2df6518de..0b4986268cc9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -545,6 +545,7 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_FLOW_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_FLOW_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_FLOW_COUNTER);
+	MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE);
 	default: return "unknown command opcode";
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index e8a6c3325b39..1365cdc81838 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -44,6 +44,7 @@
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/transobj.h>
 #include <linux/rhashtable.h>
+#include <net/switchdev.h>
 #include "wq.h"
 #include "mlx5_core.h"
 #include "en_stats.h"
@@ -79,6 +80,7 @@
 
 #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC      0x10
+#define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE 0x3
 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS      0x20
 #define MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC      0x10
 #define MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS      0x20
@@ -88,6 +90,7 @@
 #define MLX5E_LOG_INDIR_RQT_SIZE       0x7
 #define MLX5E_INDIR_RQT_SIZE           BIT(MLX5E_LOG_INDIR_RQT_SIZE)
 #define MLX5E_MAX_NUM_CHANNELS         (MLX5E_INDIR_RQT_SIZE >> 1)
+#define MLX5E_MAX_NUM_SQS              (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
 #define MLX5E_TX_CQ_POLL_BUDGET        128
 #define MLX5E_UPDATE_STATS_INTERVAL    200 /* msecs */
 #define MLX5E_SQ_BF_BUDGET             16
@@ -143,11 +146,32 @@ struct mlx5e_umr_wqe {
 	struct mlx5_wqe_data_seg       data;
 };
 
+static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = {
+	"rx_cqe_moder",
+};
+
+enum mlx5e_priv_flag {
+	MLX5E_PFLAG_RX_CQE_BASED_MODER = (1 << 0),
+};
+
+#define MLX5E_SET_PRIV_FLAG(priv, pflag, enable)    \
+	do {                                        \
+		if (enable)                         \
+			priv->pflags |= pflag;      \
+		else                                \
+			priv->pflags &= ~pflag;     \
+	} while (0)
+
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
 #define MLX5E_MIN_BW_ALLOC 1   /* Min percentage of BW allocation */
 #endif
 
+struct mlx5e_cq_moder {
+	u16 usec;
+	u16 pkts;
+};
+
 struct mlx5e_params {
 	u8  log_sq_size;
 	u8  rq_wq_type;
@@ -156,12 +180,11 @@ struct mlx5e_params {
 	u8  log_rq_size;
 	u16 num_channels;
 	u8  num_tc;
+	u8  rx_cq_period_mode;
 	bool rx_cqe_compress_admin;
 	bool rx_cqe_compress;
-	u16 rx_cq_moderation_usec;
-	u16 rx_cq_moderation_pkts;
-	u16 tx_cq_moderation_usec;
-	u16 tx_cq_moderation_pkts;
+	struct mlx5e_cq_moder rx_cq_moderation;
+	struct mlx5e_cq_moder tx_cq_moderation;
 	u16 min_rx_wqes;
 	bool lro_en;
 	u32 lro_wqe_sz;
@@ -173,6 +196,7 @@ struct mlx5e_params {
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	struct ieee_ets ets;
 #endif
+	bool rx_am_enabled;
 };
 
 struct mlx5e_tstamp {
@@ -191,6 +215,7 @@ struct mlx5e_tstamp {
 enum {
 	MLX5E_RQ_STATE_POST_WQES_ENABLE,
 	MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS,
+	MLX5E_RQ_STATE_AM,
 };
 
 struct mlx5e_cq {
@@ -198,6 +223,7 @@ struct mlx5e_cq {
 	struct mlx5_cqwq           wq;
 
 	/* data path - accessed per napi poll */
+	u16                        event_ctr;
 	struct napi_struct        *napi;
 	struct mlx5_core_cq        mcq;
 	struct mlx5e_channel      *channel;
@@ -225,6 +251,30 @@ struct mlx5e_dma_info {
 	dma_addr_t	addr;
 };
 
+struct mlx5e_rx_am_stats {
+	int ppms; /* packets per msec */
+	int epms; /* events per msec */
+};
+
+struct mlx5e_rx_am_sample {
+	ktime_t		time;
+	unsigned int	pkt_ctr;
+	u16		event_ctr;
+};
+
+struct mlx5e_rx_am { /* Adaptive Moderation */
+	u8					state;
+	struct mlx5e_rx_am_stats		prev_stats;
+	struct mlx5e_rx_am_sample		start_sample;
+	struct work_struct			work;
+	u8					profile_ix;
+	u8					mode;
+	u8					tune_state;
+	u8					steps_right;
+	u8					steps_left;
+	u8					tired;
+};
+
 struct mlx5e_rq {
 	/* data path */
 	struct mlx5_wq_ll      wq;
@@ -245,6 +295,8 @@ struct mlx5e_rq {
 	unsigned long          state;
 	int                    ix;
 
+	struct mlx5e_rx_am     am; /* Adaptive Moderation */
+
 	/* control */
 	struct mlx5_wq_ctrl    wq_ctrl;
 	u8                     wq_type;
@@ -354,6 +406,7 @@ struct mlx5e_sq {
 	struct mlx5e_channel      *channel;
 	int                        tc;
 	struct mlx5e_ico_wqe_info *ico_wqe_info;
+	u32                        rate_limit;
 } ____cacheline_aligned_in_smp;
 
 static inline bool mlx5e_sq_has_room_for(struct mlx5e_sq *sq, u16 n)
@@ -401,7 +454,7 @@ enum mlx5e_traffic_types {
 };
 
 enum {
-	MLX5E_STATE_ASYNC_EVENTS_ENABLE,
+	MLX5E_STATE_ASYNC_EVENTS_ENABLED,
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
 };
@@ -491,8 +544,24 @@ enum {
 	MLX5E_ARFS_FT_LEVEL
 };
 
+struct mlx5e_ethtool_table {
+	struct mlx5_flow_table *ft;
+	int                    num_rules;
+};
+
+#define ETHTOOL_NUM_L3_L4_FTS 7
+#define ETHTOOL_NUM_L2_FTS 4
+
+struct mlx5e_ethtool_steering {
+	struct mlx5e_ethtool_table      l3_l4_ft[ETHTOOL_NUM_L3_L4_FTS];
+	struct mlx5e_ethtool_table      l2_ft[ETHTOOL_NUM_L2_FTS];
+	struct list_head                rules;
+	int                             tot_num_rules;
+};
+
 struct mlx5e_flow_steering {
 	struct mlx5_flow_namespace      *ns;
+	struct mlx5e_ethtool_steering   ethtool;
 	struct mlx5e_tc_table           tc;
 	struct mlx5e_vlan_table         vlan;
 	struct mlx5e_l2_table           l2;
@@ -500,9 +569,15 @@ struct mlx5e_flow_steering {
 	struct mlx5e_arfs_tables        arfs;
 };
 
-struct mlx5e_direct_tir {
-	u32              tirn;
+struct mlx5e_rqt {
 	u32              rqtn;
+	bool		 enabled;
+};
+
+struct mlx5e_tir {
+	u32		  tirn;
+	struct mlx5e_rqt  rqt;
+	struct list_head  list;
 };
 
 enum {
@@ -510,6 +585,22 @@ enum {
 	MLX5E_NIC_PRIO
 };
 
+struct mlx5e_profile {
+	void	(*init)(struct mlx5_core_dev *mdev,
+			struct net_device *netdev,
+			const struct mlx5e_profile *profile, void *ppriv);
+	void	(*cleanup)(struct mlx5e_priv *priv);
+	int	(*init_rx)(struct mlx5e_priv *priv);
+	void	(*cleanup_rx)(struct mlx5e_priv *priv);
+	int	(*init_tx)(struct mlx5e_priv *priv);
+	void	(*cleanup_tx)(struct mlx5e_priv *priv);
+	void	(*enable)(struct mlx5e_priv *priv);
+	void	(*disable)(struct mlx5e_priv *priv);
+	void	(*update_stats)(struct mlx5e_priv *priv);
+	int	(*max_nch)(struct mlx5_core_dev *mdev);
+	int	max_tc;
+};
+
 struct mlx5e_priv {
 	/* priv data path fields - start */
 	struct mlx5e_sq            **txq_to_sq_map;
@@ -518,18 +609,15 @@ struct mlx5e_priv {
 
 	unsigned long              state;
 	struct mutex               state_lock; /* Protects Interface state */
-	struct mlx5_uar            cq_uar;
-	u32                        pdn;
-	u32                        tdn;
-	struct mlx5_core_mkey      mkey;
 	struct mlx5_core_mkey      umr_mkey;
 	struct mlx5e_rq            drop_rq;
 
 	struct mlx5e_channel     **channel;
 	u32                        tisn[MLX5E_MAX_NUM_TC];
-	u32                        indir_rqtn;
-	u32                        indir_tirn[MLX5E_NUM_INDIR_TIRS];
-	struct mlx5e_direct_tir    direct_tir[MLX5E_MAX_NUM_CHANNELS];
+	struct mlx5e_rqt           indir_rqt;
+	struct mlx5e_tir           indir_tir[MLX5E_NUM_INDIR_TIRS];
+	struct mlx5e_tir           direct_tir[MLX5E_MAX_NUM_CHANNELS];
+	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
 
 	struct mlx5e_flow_steering fs;
 	struct mlx5e_vxlan_db      vxlan;
@@ -540,11 +628,14 @@ struct mlx5e_priv {
 	struct work_struct         set_rx_mode_work;
 	struct delayed_work        update_stats_work;
 
+	u32                        pflags;
 	struct mlx5_core_dev      *mdev;
 	struct net_device         *netdev;
 	struct mlx5e_stats         stats;
 	struct mlx5e_tstamp        tstamp;
 	u16 q_counter;
+	const struct mlx5e_profile *profile;
+	void                      *ppriv;
 };
 
 enum mlx5e_link_mode {
@@ -562,6 +653,7 @@ enum mlx5e_link_mode {
 	MLX5E_10GBASE_ER	 = 14,
 	MLX5E_40GBASE_SR4	 = 15,
 	MLX5E_40GBASE_LR4	 = 16,
+	MLX5E_50GBASE_SR2	 = 18,
 	MLX5E_100GBASE_CR4	 = 20,
 	MLX5E_100GBASE_SR4	 = 21,
 	MLX5E_100GBASE_KR4	 = 22,
@@ -579,6 +671,9 @@ enum mlx5e_link_mode {
 
 #define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
 
+
+void mlx5e_build_ptys2ethtool_map(void);
+
 void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw);
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 		       void *accel_priv, select_queue_fallback_t fallback);
@@ -612,12 +707,26 @@ void mlx5e_free_rx_fragmented_mpwqe(struct mlx5e_rq *rq,
 				    struct mlx5e_mpw_info *wi);
 struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq);
 
+void mlx5e_rx_am(struct mlx5e_rq *rq);
+void mlx5e_rx_am_work(struct work_struct *work);
+struct mlx5e_cq_moder mlx5e_am_get_def_profile(u8 rx_cq_period_mode);
+
 void mlx5e_update_stats(struct mlx5e_priv *priv);
 
 int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
 void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
 void mlx5e_init_l2_addr(struct mlx5e_priv *priv);
 void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
+int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
+			   int location);
+int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv,
+				struct ethtool_rxnfc *info, u32 *rule_locs);
+int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
+			       struct ethtool_rx_flow_spec *fs);
+int mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv,
+			      int location);
+void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
+void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
 void mlx5e_set_rx_mode_work(struct work_struct *work);
 
 void mlx5e_fill_hwstamp(struct mlx5e_tstamp *clock, u64 timestamp,
@@ -647,6 +756,9 @@ void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev,
 				   int num_channels);
 int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 
+void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
+				 u8 cq_period_mode);
+
 static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
 				      struct mlx5_wqe_ctrl_seg *ctrl, int bf_sz)
 {
@@ -723,5 +835,39 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 #endif
 
 u16 mlx5e_get_max_inline_cap(struct mlx5_core_dev *mdev);
+int mlx5e_create_tir(struct mlx5_core_dev *mdev,
+		     struct mlx5e_tir *tir, u32 *in, int inlen);
+void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
+		       struct mlx5e_tir *tir);
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
+void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
+int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5_core_dev *mdev);
+
+struct mlx5_eswitch_rep;
+int mlx5e_vport_rep_load(struct mlx5_eswitch *esw,
+			 struct mlx5_eswitch_rep *rep);
+void mlx5e_vport_rep_unload(struct mlx5_eswitch *esw,
+			    struct mlx5_eswitch_rep *rep);
+int mlx5e_nic_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep);
+void mlx5e_nic_rep_unload(struct mlx5_eswitch *esw,
+			  struct mlx5_eswitch_rep *rep);
+int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
+void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
+int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr);
+
+int mlx5e_create_direct_rqts(struct mlx5e_priv *priv);
+void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
+int mlx5e_create_direct_tirs(struct mlx5e_priv *priv);
+void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
+int mlx5e_create_tises(struct mlx5e_priv *priv);
+void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv);
+int mlx5e_close(struct net_device *netdev);
+int mlx5e_open(struct net_device *netdev);
+void mlx5e_update_stats_work(struct work_struct *work);
+void *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
+			  const struct mlx5e_profile *profile, void *ppriv);
+void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv);
+struct rtnl_link_stats64 *
+mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
 
 #endif /* __MLX5_EN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 3515e78ba68f..a8cb38789774 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -93,14 +93,14 @@ static enum mlx5e_traffic_types arfs_get_tt(enum arfs_type type)
 static int arfs_disable(struct mlx5e_priv *priv)
 {
 	struct mlx5_flow_destination dest;
-	u32 *tirn = priv->indir_tirn;
+	struct mlx5e_tir *tir = priv->indir_tir;
 	int err = 0;
 	int tt;
 	int i;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 	for (i = 0; i < ARFS_NUM_TYPES; i++) {
-		dest.tir_num = tirn[i];
+		dest.tir_num = tir[i].tirn;
 		tt = arfs_get_tt(i);
 		/* Modify ttc rules destination to bypass the aRFS tables*/
 		err = mlx5_modify_rule_destination(priv->fs.ttc.rules[tt],
@@ -175,15 +175,12 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
 {
 	struct arfs_table *arfs_t = &priv->fs.arfs.arfs_tables[type];
 	struct mlx5_flow_destination dest;
-	u8 match_criteria_enable = 0;
-	u32 *tirn = priv->indir_tirn;
-	u32 *match_criteria;
-	u32 *match_value;
+	struct mlx5e_tir *tir = priv->indir_tir;
+	struct mlx5_flow_spec *spec;
 	int err = 0;
 
-	match_value	= mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
-	match_criteria	= mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
-	if (!match_value || !match_criteria) {
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec) {
 		netdev_err(priv->netdev, "%s: alloc failed\n", __func__);
 		err = -ENOMEM;
 		goto out;
@@ -192,24 +189,23 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 	switch (type) {
 	case ARFS_IPV4_TCP:
-		dest.tir_num = tirn[MLX5E_TT_IPV4_TCP];
+		dest.tir_num = tir[MLX5E_TT_IPV4_TCP].tirn;
 		break;
 	case ARFS_IPV4_UDP:
-		dest.tir_num = tirn[MLX5E_TT_IPV4_UDP];
+		dest.tir_num = tir[MLX5E_TT_IPV4_UDP].tirn;
 		break;
 	case ARFS_IPV6_TCP:
-		dest.tir_num = tirn[MLX5E_TT_IPV6_TCP];
+		dest.tir_num = tir[MLX5E_TT_IPV6_TCP].tirn;
 		break;
 	case ARFS_IPV6_UDP:
-		dest.tir_num = tirn[MLX5E_TT_IPV6_UDP];
+		dest.tir_num = tir[MLX5E_TT_IPV6_UDP].tirn;
 		break;
 	default:
 		err = -EINVAL;
 		goto out;
 	}
 
-	arfs_t->default_rule = mlx5_add_flow_rule(arfs_t->ft.t, match_criteria_enable,
-						  match_criteria, match_value,
+	arfs_t->default_rule = mlx5_add_flow_rule(arfs_t->ft.t, spec,
 						  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
 						  MLX5_FS_DEFAULT_FLOW_TAG,
 						  &dest);
@@ -220,8 +216,7 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
 			   __func__, type);
 	}
 out:
-	kvfree(match_criteria);
-	kvfree(match_value);
+	kvfree(spec);
 	return err;
 }
 
@@ -475,23 +470,20 @@ static struct mlx5_flow_rule *arfs_add_rule(struct mlx5e_priv *priv,
 	struct mlx5_flow_rule *rule = NULL;
 	struct mlx5_flow_destination dest;
 	struct arfs_table *arfs_table;
-	u8 match_criteria_enable = 0;
+	struct mlx5_flow_spec *spec;
 	struct mlx5_flow_table *ft;
-	u32 *match_criteria;
-	u32 *match_value;
 	int err = 0;
 
-	match_value	= mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
-	match_criteria	= mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
-	if (!match_value || !match_criteria) {
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec) {
 		netdev_err(priv->netdev, "%s: alloc failed\n", __func__);
 		err = -ENOMEM;
 		goto out;
 	}
-	match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 			 outer_headers.ethertype);
-	MLX5_SET(fte_match_param, match_value, outer_headers.ethertype,
+	MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype,
 		 ntohs(tuple->etype));
 	arfs_table = arfs_get_table(arfs, tuple->ip_proto, tuple->etype);
 	if (!arfs_table) {
@@ -501,59 +493,58 @@ static struct mlx5_flow_rule *arfs_add_rule(struct mlx5e_priv *priv,
 
 	ft = arfs_table->ft.t;
 	if (tuple->ip_proto == IPPROTO_TCP) {
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 				 outer_headers.tcp_dport);
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 				 outer_headers.tcp_sport);
-		MLX5_SET(fte_match_param, match_value, outer_headers.tcp_dport,
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.tcp_dport,
 			 ntohs(tuple->dst_port));
-		MLX5_SET(fte_match_param, match_value, outer_headers.tcp_sport,
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.tcp_sport,
 			 ntohs(tuple->src_port));
 	} else {
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 				 outer_headers.udp_dport);
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 				 outer_headers.udp_sport);
-		MLX5_SET(fte_match_param, match_value, outer_headers.udp_dport,
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.udp_dport,
 			 ntohs(tuple->dst_port));
-		MLX5_SET(fte_match_param, match_value, outer_headers.udp_sport,
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.udp_sport,
 			 ntohs(tuple->src_port));
 	}
 	if (tuple->etype == htons(ETH_P_IP)) {
-		memcpy(MLX5_ADDR_OF(fte_match_param, match_value,
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4),
 		       &tuple->src_ipv4,
 		       4);
-		memcpy(MLX5_ADDR_OF(fte_match_param, match_value,
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
 		       &tuple->dst_ipv4,
 		       4);
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 				 outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4);
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 				 outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
 	} else {
-		memcpy(MLX5_ADDR_OF(fte_match_param, match_value,
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6),
 		       &tuple->src_ipv6,
 		       16);
-		memcpy(MLX5_ADDR_OF(fte_match_param, match_value,
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
 		       &tuple->dst_ipv6,
 		       16);
-		memset(MLX5_ADDR_OF(fte_match_param, match_criteria,
+		memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
 				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6),
 		       0xff,
 		       16);
-		memset(MLX5_ADDR_OF(fte_match_param, match_criteria,
+		memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
 				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
 		       0xff,
 		       16);
 	}
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 	dest.tir_num = priv->direct_tir[arfs_rule->rxq].tirn;
-	rule = mlx5_add_flow_rule(ft, match_criteria_enable, match_criteria,
-				  match_value, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+	rule = mlx5_add_flow_rule(ft, spec, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
 				  MLX5_FS_DEFAULT_FLOW_TAG,
 				  &dest);
 	if (IS_ERR(rule)) {
@@ -563,8 +554,7 @@ static struct mlx5_flow_rule *arfs_add_rule(struct mlx5e_priv *priv,
 	}
 
 out:
-	kvfree(match_criteria);
-	kvfree(match_value);
+	kvfree(spec);
 	return err ? ERR_PTR(err) : rule;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
new file mode 100644
index 000000000000..673043ccd76c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -0,0 +1,160 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "en.h"
+
+/* mlx5e global resources should be placed in this file.
+ * Global resources are common to all the netdevices crated on the same nic.
+ */
+
+int mlx5e_create_tir(struct mlx5_core_dev *mdev,
+		     struct mlx5e_tir *tir, u32 *in, int inlen)
+{
+	int err;
+
+	err = mlx5_core_create_tir(mdev, in, inlen, &tir->tirn);
+	if (err)
+		return err;
+
+	list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list);
+
+	return 0;
+}
+
+void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
+		       struct mlx5e_tir *tir)
+{
+	mlx5_core_destroy_tir(mdev, tir->tirn);
+	list_del(&tir->list);
+}
+
+static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
+			     struct mlx5_core_mkey *mkey)
+{
+	struct mlx5_create_mkey_mbox_in *in;
+	int err;
+
+	in = mlx5_vzalloc(sizeof(*in));
+	if (!in)
+		return -ENOMEM;
+
+	in->seg.flags = MLX5_PERM_LOCAL_WRITE |
+			MLX5_PERM_LOCAL_READ  |
+			MLX5_ACCESS_MODE_PA;
+	in->seg.flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64);
+	in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
+
+	err = mlx5_core_create_mkey(mdev, mkey, in, sizeof(*in), NULL, NULL,
+				    NULL);
+
+	kvfree(in);
+
+	return err;
+}
+
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
+{
+	struct mlx5e_resources *res = &mdev->mlx5e_res;
+	int err;
+
+	err = mlx5_alloc_map_uar(mdev, &res->cq_uar, false);
+	if (err) {
+		mlx5_core_err(mdev, "alloc_map uar failed, %d\n", err);
+		return err;
+	}
+
+	err = mlx5_core_alloc_pd(mdev, &res->pdn);
+	if (err) {
+		mlx5_core_err(mdev, "alloc pd failed, %d\n", err);
+		goto err_unmap_free_uar;
+	}
+
+	err = mlx5_core_alloc_transport_domain(mdev, &res->td.tdn);
+	if (err) {
+		mlx5_core_err(mdev, "alloc td failed, %d\n", err);
+		goto err_dealloc_pd;
+	}
+
+	err = mlx5e_create_mkey(mdev, res->pdn, &res->mkey);
+	if (err) {
+		mlx5_core_err(mdev, "create mkey failed, %d\n", err);
+		goto err_dealloc_transport_domain;
+	}
+
+	INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
+
+	return 0;
+
+err_dealloc_transport_domain:
+	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
+err_dealloc_pd:
+	mlx5_core_dealloc_pd(mdev, res->pdn);
+err_unmap_free_uar:
+	mlx5_unmap_free_uar(mdev, &res->cq_uar);
+
+	return err;
+}
+
+void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
+{
+	struct mlx5e_resources *res = &mdev->mlx5e_res;
+
+	mlx5_core_destroy_mkey(mdev, &res->mkey);
+	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
+	mlx5_core_dealloc_pd(mdev, res->pdn);
+	mlx5_unmap_free_uar(mdev, &res->cq_uar);
+}
+
+int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5_core_dev *mdev)
+{
+	struct mlx5e_tir *tir;
+	void *in;
+	int inlen;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
+
+	list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
+		err = mlx5_core_modify_tir(mdev, tir->tirn, in, inlen);
+		if (err)
+			return err;
+	}
+
+	kvfree(in);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index b2db180ae2a5..e6883132b555 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -191,7 +191,6 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	enum mlx5_port_status ps;
 	u8 curr_pfc_en;
 	int ret;
 
@@ -200,14 +199,8 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev,
 	if (pfc->pfc_en == curr_pfc_en)
 		return 0;
 
-	mlx5_query_port_admin_status(mdev, &ps);
-	if (ps == MLX5_PORT_UP)
-		mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN);
-
 	ret = mlx5_set_port_pfc(mdev, pfc->pfc_en, pfc->pfc_en);
-
-	if (ps == MLX5_PORT_UP)
-		mlx5_set_port_admin_status(mdev, MLX5_PORT_UP);
+	mlx5_toggle_port_link(mdev);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index fc7dcc03b1de..4a3757e60441 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -48,123 +48,85 @@ static void mlx5e_get_drvinfo(struct net_device *dev,
 		sizeof(drvinfo->bus_info));
 }
 
-static const struct {
-	u32 supported;
-	u32 advertised;
+struct ptys2ethtool_config {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertised);
 	u32 speed;
-} ptys2ethtool_table[MLX5E_LINK_MODES_NUMBER] = {
-	[MLX5E_1000BASE_CX_SGMII] = {
-		.supported  = SUPPORTED_1000baseKX_Full,
-		.advertised = ADVERTISED_1000baseKX_Full,
-		.speed      = 1000,
-	},
-	[MLX5E_1000BASE_KX] = {
-		.supported  = SUPPORTED_1000baseKX_Full,
-		.advertised = ADVERTISED_1000baseKX_Full,
-		.speed      = 1000,
-	},
-	[MLX5E_10GBASE_CX4] = {
-		.supported  = SUPPORTED_10000baseKX4_Full,
-		.advertised = ADVERTISED_10000baseKX4_Full,
-		.speed      = 10000,
-	},
-	[MLX5E_10GBASE_KX4] = {
-		.supported  = SUPPORTED_10000baseKX4_Full,
-		.advertised = ADVERTISED_10000baseKX4_Full,
-		.speed      = 10000,
-	},
-	[MLX5E_10GBASE_KR] = {
-		.supported  = SUPPORTED_10000baseKR_Full,
-		.advertised = ADVERTISED_10000baseKR_Full,
-		.speed      = 10000,
-	},
-	[MLX5E_20GBASE_KR2] = {
-		.supported  = SUPPORTED_20000baseKR2_Full,
-		.advertised = ADVERTISED_20000baseKR2_Full,
-		.speed      = 20000,
-	},
-	[MLX5E_40GBASE_CR4] = {
-		.supported  = SUPPORTED_40000baseCR4_Full,
-		.advertised = ADVERTISED_40000baseCR4_Full,
-		.speed      = 40000,
-	},
-	[MLX5E_40GBASE_KR4] = {
-		.supported  = SUPPORTED_40000baseKR4_Full,
-		.advertised = ADVERTISED_40000baseKR4_Full,
-		.speed      = 40000,
-	},
-	[MLX5E_56GBASE_R4] = {
-		.supported  = SUPPORTED_56000baseKR4_Full,
-		.advertised = ADVERTISED_56000baseKR4_Full,
-		.speed      = 56000,
-	},
-	[MLX5E_10GBASE_CR] = {
-		.supported  = SUPPORTED_10000baseKR_Full,
-		.advertised = ADVERTISED_10000baseKR_Full,
-		.speed      = 10000,
-	},
-	[MLX5E_10GBASE_SR] = {
-		.supported  = SUPPORTED_10000baseKR_Full,
-		.advertised = ADVERTISED_10000baseKR_Full,
-		.speed      = 10000,
-	},
-	[MLX5E_10GBASE_ER] = {
-		.supported  = SUPPORTED_10000baseKR_Full,
-		.advertised = ADVERTISED_10000baseKR_Full,
-		.speed      = 10000,
-	},
-	[MLX5E_40GBASE_SR4] = {
-		.supported  = SUPPORTED_40000baseSR4_Full,
-		.advertised = ADVERTISED_40000baseSR4_Full,
-		.speed      = 40000,
-	},
-	[MLX5E_40GBASE_LR4] = {
-		.supported  = SUPPORTED_40000baseLR4_Full,
-		.advertised = ADVERTISED_40000baseLR4_Full,
-		.speed      = 40000,
-	},
-	[MLX5E_100GBASE_CR4] = {
-		.speed      = 100000,
-	},
-	[MLX5E_100GBASE_SR4] = {
-		.speed      = 100000,
-	},
-	[MLX5E_100GBASE_KR4] = {
-		.speed      = 100000,
-	},
-	[MLX5E_100GBASE_LR4] = {
-		.speed      = 100000,
-	},
-	[MLX5E_100BASE_TX]   = {
-		.speed      = 100,
-	},
-	[MLX5E_1000BASE_T]    = {
-		.supported  = SUPPORTED_1000baseT_Full,
-		.advertised = ADVERTISED_1000baseT_Full,
-		.speed      = 1000,
-	},
-	[MLX5E_10GBASE_T]    = {
-		.supported  = SUPPORTED_10000baseT_Full,
-		.advertised = ADVERTISED_10000baseT_Full,
-		.speed      = 1000,
-	},
-	[MLX5E_25GBASE_CR]   = {
-		.speed      = 25000,
-	},
-	[MLX5E_25GBASE_KR]   = {
-		.speed      = 25000,
-	},
-	[MLX5E_25GBASE_SR]   = {
-		.speed      = 25000,
-	},
-	[MLX5E_50GBASE_CR2]  = {
-		.speed      = 50000,
-	},
-	[MLX5E_50GBASE_KR2]  = {
-		.speed      = 50000,
-	},
 };
 
+static struct ptys2ethtool_config ptys2ethtool_table[MLX5E_LINK_MODES_NUMBER];
+
+#define MLX5_BUILD_PTYS2ETHTOOL_CONFIG(reg_, speed_, ...)               \
+	({                                                              \
+		struct ptys2ethtool_config *cfg;                        \
+		const unsigned int modes[] = { __VA_ARGS__ };           \
+		unsigned int i;                                         \
+		cfg = &ptys2ethtool_table[reg_];                        \
+		cfg->speed = speed_;                                    \
+		bitmap_zero(cfg->supported,                             \
+			    __ETHTOOL_LINK_MODE_MASK_NBITS);            \
+		bitmap_zero(cfg->advertised,                            \
+			    __ETHTOOL_LINK_MODE_MASK_NBITS);            \
+		for (i = 0 ; i < ARRAY_SIZE(modes) ; ++i) {             \
+			__set_bit(modes[i], cfg->supported);            \
+			__set_bit(modes[i], cfg->advertised);           \
+		}                                                       \
+	})
+
+void mlx5e_build_ptys2ethtool_map(void)
+{
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_CX_SGMII, SPEED_1000,
+				       ETHTOOL_LINK_MODE_1000baseKX_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_KX, SPEED_1000,
+				       ETHTOOL_LINK_MODE_1000baseKX_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CX4, SPEED_10000,
+				       ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KX4, SPEED_10000,
+				       ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KR, SPEED_10000,
+				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_20GBASE_KR2, SPEED_20000,
+				       ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_CR4, SPEED_40000,
+				       ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_KR4, SPEED_40000,
+				       ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_56GBASE_R4, SPEED_56000,
+				       ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CR, SPEED_10000,
+				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_SR, SPEED_10000,
+				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_ER, SPEED_10000,
+				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_SR4, SPEED_40000,
+				       ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_LR4, SPEED_40000,
+				       ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_SR2, SPEED_50000,
+				       ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_CR4, SPEED_100000,
+				       ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_SR4, SPEED_100000,
+				       ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_KR4, SPEED_100000,
+				       ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4, SPEED_100000,
+				       ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T, SPEED_10000,
+				       ETHTOOL_LINK_MODE_10000baseT_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR, SPEED_25000,
+				       ETHTOOL_LINK_MODE_25000baseCR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_KR, SPEED_25000,
+				       ETHTOOL_LINK_MODE_25000baseKR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_SR, SPEED_25000,
+				       ETHTOOL_LINK_MODE_25000baseSR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_CR2, SPEED_50000,
+				       ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_KR2, SPEED_50000,
+				       ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT);
+}
+
 static unsigned long mlx5e_query_pfc_combined(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -177,6 +139,18 @@ static unsigned long mlx5e_query_pfc_combined(struct mlx5e_priv *priv)
 	return err ? 0 : pfc_en_tx | pfc_en_rx;
 }
 
+static bool mlx5e_query_global_pause_combined(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 rx_pause;
+	u32 tx_pause;
+	int err;
+
+	err = mlx5_query_port_pause(mdev, &rx_pause, &tx_pause);
+
+	return err ? false : rx_pause | tx_pause;
+}
+
 #define MLX5E_NUM_Q_CNTRS(priv) (NUM_Q_COUNTERS * (!!priv->q_counter))
 #define MLX5E_NUM_RQ_STATS(priv) \
 	(NUM_RQ_STATS * priv->params.num_channels * \
@@ -184,7 +158,9 @@ static unsigned long mlx5e_query_pfc_combined(struct mlx5e_priv *priv)
 #define MLX5E_NUM_SQ_STATS(priv) \
 	(NUM_SQ_STATS * priv->params.num_channels * priv->params.num_tc * \
 	 test_bit(MLX5E_STATE_OPENED, &priv->state))
-#define MLX5E_NUM_PFC_COUNTERS(priv) hweight8(mlx5e_query_pfc_combined(priv))
+#define MLX5E_NUM_PFC_COUNTERS(priv) \
+	((mlx5e_query_global_pause_combined(priv) + hweight8(mlx5e_query_pfc_combined(priv))) * \
+	  NUM_PPORT_PER_PRIO_PFC_COUNTERS)
 
 static int mlx5e_get_sset_count(struct net_device *dev, int sset)
 {
@@ -198,6 +174,8 @@ static int mlx5e_get_sset_count(struct net_device *dev, int sset)
 		       MLX5E_NUM_RQ_STATS(priv) +
 		       MLX5E_NUM_SQ_STATS(priv) +
 		       MLX5E_NUM_PFC_COUNTERS(priv);
+	case ETH_SS_PRIV_FLAGS:
+		return ARRAY_SIZE(mlx5e_priv_flags);
 	/* fallthrough */
 	default:
 		return -EOPNOTSUPP;
@@ -211,42 +189,51 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
 
 	/* SW counters */
 	for (i = 0; i < NUM_SW_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, sw_stats_desc[i].name);
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, sw_stats_desc[i].format);
 
 	/* Q counters */
 	for (i = 0; i < MLX5E_NUM_Q_CNTRS(priv); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].name);
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].format);
 
 	/* VPORT counters */
 	for (i = 0; i < NUM_VPORT_COUNTERS; i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       vport_stats_desc[i].name);
+		       vport_stats_desc[i].format);
 
 	/* PPORT counters */
 	for (i = 0; i < NUM_PPORT_802_3_COUNTERS; i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_802_3_stats_desc[i].name);
+		       pport_802_3_stats_desc[i].format);
 
 	for (i = 0; i < NUM_PPORT_2863_COUNTERS; i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_2863_stats_desc[i].name);
+		       pport_2863_stats_desc[i].format);
 
 	for (i = 0; i < NUM_PPORT_2819_COUNTERS; i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_2819_stats_desc[i].name);
+		       pport_2819_stats_desc[i].format);
 
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN, "prio%d_%s",
-				prio,
-				pport_per_prio_traffic_stats_desc[i].name);
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				pport_per_prio_traffic_stats_desc[i].format, prio);
 	}
 
 	pfc_combined = mlx5e_query_pfc_combined(priv);
 	for_each_set_bit(prio, &pfc_combined, NUM_PPORT_PRIO) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
-			sprintf(data + (idx++) * ETH_GSTRING_LEN, "prio%d_%s",
-				prio, pport_per_prio_pfc_stats_desc[i].name);
+			char pfc_string[ETH_GSTRING_LEN];
+
+			snprintf(pfc_string, sizeof(pfc_string), "prio%d", prio);
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				pport_per_prio_pfc_stats_desc[i].format, pfc_string);
+		}
+	}
+
+	if (mlx5e_query_global_pause_combined(priv)) {
+		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				pport_per_prio_pfc_stats_desc[i].format, "global");
 		}
 	}
 
@@ -256,25 +243,27 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
 	/* per channel counters */
 	for (i = 0; i < priv->params.num_channels; i++)
 		for (j = 0; j < NUM_RQ_STATS; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN, "rx%d_%s", i,
-				rq_stats_desc[j].name);
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				rq_stats_desc[j].format, i);
 
 	for (tc = 0; tc < priv->params.num_tc; tc++)
 		for (i = 0; i < priv->params.num_channels; i++)
 			for (j = 0; j < NUM_SQ_STATS; j++)
 				sprintf(data + (idx++) * ETH_GSTRING_LEN,
-					"tx%d_%s",
-					priv->channeltc_to_txq_map[i][tc],
-					sq_stats_desc[j].name);
+					sq_stats_desc[j].format,
+					priv->channeltc_to_txq_map[i][tc]);
 }
 
 static void mlx5e_get_strings(struct net_device *dev,
 			      uint32_t stringset, uint8_t *data)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	int i;
 
 	switch (stringset) {
 	case ETH_SS_PRIV_FLAGS:
+		for (i = 0; i < ARRAY_SIZE(mlx5e_priv_flags); i++)
+			strcpy(data + i * ETH_GSTRING_LEN, mlx5e_priv_flags[i]);
 		break;
 
 	case ETH_SS_TEST:
@@ -339,6 +328,13 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 		}
 	}
 
+	if (mlx5e_query_global_pause_combined(priv)) {
+		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
+			data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[0],
+							  pport_per_prio_pfc_stats_desc, 0);
+		}
+	}
+
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		return;
 
@@ -519,10 +515,11 @@ static int mlx5e_get_coalesce(struct net_device *netdev,
 	if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
 		return -ENOTSUPP;
 
-	coal->rx_coalesce_usecs       = priv->params.rx_cq_moderation_usec;
-	coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation_pkts;
-	coal->tx_coalesce_usecs       = priv->params.tx_cq_moderation_usec;
-	coal->tx_max_coalesced_frames = priv->params.tx_cq_moderation_pkts;
+	coal->rx_coalesce_usecs       = priv->params.rx_cq_moderation.usec;
+	coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation.pkts;
+	coal->tx_coalesce_usecs       = priv->params.tx_cq_moderation.usec;
+	coal->tx_max_coalesced_frames = priv->params.tx_cq_moderation.pkts;
+	coal->use_adaptive_rx_coalesce = priv->params.rx_am_enabled;
 
 	return 0;
 }
@@ -533,6 +530,10 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_channel *c;
+	bool restart =
+		!!coal->use_adaptive_rx_coalesce != priv->params.rx_am_enabled;
+	bool was_opened;
+	int err = 0;
 	int tc;
 	int i;
 
@@ -540,12 +541,19 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 		return -ENOTSUPP;
 
 	mutex_lock(&priv->state_lock);
-	priv->params.tx_cq_moderation_usec = coal->tx_coalesce_usecs;
-	priv->params.tx_cq_moderation_pkts = coal->tx_max_coalesced_frames;
-	priv->params.rx_cq_moderation_usec = coal->rx_coalesce_usecs;
-	priv->params.rx_cq_moderation_pkts = coal->rx_max_coalesced_frames;
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
+	if (was_opened && restart) {
+		mlx5e_close_locked(netdev);
+		priv->params.rx_am_enabled = !!coal->use_adaptive_rx_coalesce;
+	}
+
+	priv->params.tx_cq_moderation.usec = coal->tx_coalesce_usecs;
+	priv->params.tx_cq_moderation.pkts = coal->tx_max_coalesced_frames;
+	priv->params.rx_cq_moderation.usec = coal->rx_coalesce_usecs;
+	priv->params.rx_cq_moderation.pkts = coal->rx_max_coalesced_frames;
+
+	if (!was_opened || restart)
 		goto out;
 
 	for (i = 0; i < priv->params.num_channels; ++i) {
@@ -564,35 +572,37 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 	}
 
 out:
+	if (was_opened && restart)
+		err = mlx5e_open_locked(netdev);
+
 	mutex_unlock(&priv->state_lock);
-	return 0;
+	return err;
 }
 
-static u32 ptys2ethtool_supported_link(u32 eth_proto_cap)
+static void ptys2ethtool_supported_link(unsigned long *supported_modes,
+					u32 eth_proto_cap)
 {
-	int i;
-	u32 supported_modes = 0;
+	int proto;
 
-	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
-		if (eth_proto_cap & MLX5E_PROT_MASK(i))
-			supported_modes |= ptys2ethtool_table[i].supported;
-	}
-	return supported_modes;
+	for_each_set_bit(proto, (unsigned long *)&eth_proto_cap, MLX5E_LINK_MODES_NUMBER)
+		bitmap_or(supported_modes, supported_modes,
+			  ptys2ethtool_table[proto].supported,
+			  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static u32 ptys2ethtool_adver_link(u32 eth_proto_cap)
+static void ptys2ethtool_adver_link(unsigned long *advertising_modes,
+				    u32 eth_proto_cap)
 {
-	int i;
-	u32 advertising_modes = 0;
+	int proto;
 
-	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
-		if (eth_proto_cap & MLX5E_PROT_MASK(i))
-			advertising_modes |= ptys2ethtool_table[i].advertised;
-	}
-	return advertising_modes;
+	for_each_set_bit(proto, (unsigned long *)&eth_proto_cap, MLX5E_LINK_MODES_NUMBER)
+		bitmap_or(advertising_modes, advertising_modes,
+			  ptys2ethtool_table[proto].advertised,
+			  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static u32 ptys2ethtool_supported_port(u32 eth_proto_cap)
+static void ptys2ethtool_supported_port(struct ethtool_link_ksettings *link_ksettings,
+					u32 eth_proto_cap)
 {
 	if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR)
 			   | MLX5E_PROT_MASK(MLX5E_10GBASE_SR)
@@ -600,7 +610,7 @@ static u32 ptys2ethtool_supported_port(u32 eth_proto_cap)
 			   | MLX5E_PROT_MASK(MLX5E_40GBASE_SR4)
 			   | MLX5E_PROT_MASK(MLX5E_100GBASE_SR4)
 			   | MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII))) {
-		return SUPPORTED_FIBRE;
+		ethtool_link_ksettings_add_link_mode(link_ksettings, supported, FIBRE);
 	}
 
 	if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_100GBASE_KR4)
@@ -608,9 +618,8 @@ static u32 ptys2ethtool_supported_port(u32 eth_proto_cap)
 			   | MLX5E_PROT_MASK(MLX5E_10GBASE_KR)
 			   | MLX5E_PROT_MASK(MLX5E_10GBASE_KX4)
 			   | MLX5E_PROT_MASK(MLX5E_1000BASE_KX))) {
-		return SUPPORTED_Backplane;
+		ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Backplane);
 	}
-	return 0;
 }
 
 int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
@@ -634,7 +643,7 @@ int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 
 static void get_speed_duplex(struct net_device *netdev,
 			     u32 eth_proto_oper,
-			     struct ethtool_cmd *cmd)
+			     struct ethtool_link_ksettings *link_ksettings)
 {
 	int i;
 	u32 speed = SPEED_UNKNOWN;
@@ -651,23 +660,32 @@ static void get_speed_duplex(struct net_device *netdev,
 		}
 	}
 out:
-	ethtool_cmd_speed_set(cmd, speed);
-	cmd->duplex = duplex;
+	link_ksettings->base.speed = speed;
+	link_ksettings->base.duplex = duplex;
 }
 
-static void get_supported(u32 eth_proto_cap, u32 *supported)
+static void get_supported(u32 eth_proto_cap,
+			  struct ethtool_link_ksettings *link_ksettings)
 {
-	*supported |= ptys2ethtool_supported_port(eth_proto_cap);
-	*supported |= ptys2ethtool_supported_link(eth_proto_cap);
-	*supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+	unsigned long *supported = link_ksettings->link_modes.supported;
+
+	ptys2ethtool_supported_port(link_ksettings, eth_proto_cap);
+	ptys2ethtool_supported_link(supported, eth_proto_cap);
+	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
+	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Asym_Pause);
 }
 
 static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
-			    u8 rx_pause, u32 *advertising)
+			    u8 rx_pause,
+			    struct ethtool_link_ksettings *link_ksettings)
 {
-	*advertising |= ptys2ethtool_adver_link(eth_proto_cap);
-	*advertising |= tx_pause ? ADVERTISED_Pause : 0;
-	*advertising |= (tx_pause ^ rx_pause) ? ADVERTISED_Asym_Pause : 0;
+	unsigned long *advertising = link_ksettings->link_modes.advertising;
+
+	ptys2ethtool_adver_link(advertising, eth_proto_cap);
+	if (tx_pause)
+		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
+	if (tx_pause ^ rx_pause)
+		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Asym_Pause);
 }
 
 static u8 get_connector_port(u32 eth_proto)
@@ -695,13 +713,16 @@ static u8 get_connector_port(u32 eth_proto)
 	return PORT_OTHER;
 }
 
-static void get_lp_advertising(u32 eth_proto_lp, u32 *lp_advertising)
+static void get_lp_advertising(u32 eth_proto_lp,
+			       struct ethtool_link_ksettings *link_ksettings)
 {
-	*lp_advertising = ptys2ethtool_adver_link(eth_proto_lp);
+	unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
+
+	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp);
 }
 
-static int mlx5e_get_settings(struct net_device *netdev,
-			      struct ethtool_cmd *cmd)
+static int mlx5e_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -710,6 +731,8 @@ static int mlx5e_get_settings(struct net_device *netdev,
 	u32 eth_proto_admin;
 	u32 eth_proto_lp;
 	u32 eth_proto_oper;
+	u8 an_disable_admin;
+	u8 an_status;
 	int err;
 
 	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1);
@@ -720,35 +743,49 @@ static int mlx5e_get_settings(struct net_device *netdev,
 		goto err_query_ptys;
 	}
 
-	eth_proto_cap   = MLX5_GET(ptys_reg, out, eth_proto_capability);
-	eth_proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin);
-	eth_proto_oper  = MLX5_GET(ptys_reg, out, eth_proto_oper);
-	eth_proto_lp    = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise);
+	eth_proto_cap    = MLX5_GET(ptys_reg, out, eth_proto_capability);
+	eth_proto_admin  = MLX5_GET(ptys_reg, out, eth_proto_admin);
+	eth_proto_oper   = MLX5_GET(ptys_reg, out, eth_proto_oper);
+	eth_proto_lp     = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise);
+	an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
+	an_status        = MLX5_GET(ptys_reg, out, an_status);
 
-	cmd->supported   = 0;
-	cmd->advertising = 0;
+	ethtool_link_ksettings_zero_link_mode(link_ksettings, supported);
+	ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
 
-	get_supported(eth_proto_cap, &cmd->supported);
-	get_advertising(eth_proto_admin, 0, 0, &cmd->advertising);
-	get_speed_duplex(netdev, eth_proto_oper, cmd);
+	get_supported(eth_proto_cap, link_ksettings);
+	get_advertising(eth_proto_admin, 0, 0, link_ksettings);
+	get_speed_duplex(netdev, eth_proto_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
 
-	cmd->port = get_connector_port(eth_proto_oper);
-	get_lp_advertising(eth_proto_lp, &cmd->lp_advertising);
+	link_ksettings->base.port = get_connector_port(eth_proto_oper);
+	get_lp_advertising(eth_proto_lp, link_ksettings);
 
-	cmd->transceiver = XCVR_INTERNAL;
+	if (an_status == MLX5_AN_COMPLETE)
+		ethtool_link_ksettings_add_link_mode(link_ksettings,
+						     lp_advertising, Autoneg);
+
+	link_ksettings->base.autoneg = an_disable_admin ? AUTONEG_DISABLE :
+							  AUTONEG_ENABLE;
+	ethtool_link_ksettings_add_link_mode(link_ksettings, supported,
+					     Autoneg);
+	if (!an_disable_admin)
+		ethtool_link_ksettings_add_link_mode(link_ksettings,
+						     advertising, Autoneg);
 
 err_query_ptys:
 	return err;
 }
 
-static u32 mlx5e_ethtool2ptys_adver_link(u32 link_modes)
+static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 {
 	u32 i, ptys_modes = 0;
 
 	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
-		if (ptys2ethtool_table[i].advertised & link_modes)
+		if (bitmap_intersects(ptys2ethtool_table[i].advertised,
+				      link_modes,
+				      __ETHTOOL_LINK_MODE_MASK_NBITS))
 			ptys_modes |= MLX5E_PROT_MASK(i);
 	}
 
@@ -767,21 +804,25 @@ static u32 mlx5e_ethtool2ptys_speed_link(u32 speed)
 	return speed_links;
 }
 
-static int mlx5e_set_settings(struct net_device *netdev,
-			      struct ethtool_cmd *cmd)
+static int mlx5e_set_link_ksettings(struct net_device *netdev,
+				    const struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 eth_proto_cap, eth_proto_admin;
+	bool an_changes = false;
+	u8 an_disable_admin;
+	u8 an_disable_cap;
+	bool an_disable;
 	u32 link_modes;
+	u8 an_status;
 	u32 speed;
-	u32 eth_proto_cap, eth_proto_admin;
-	enum mlx5_port_status ps;
 	int err;
 
-	speed = ethtool_cmd_speed(cmd);
+	speed = link_ksettings->base.speed;
 
-	link_modes = cmd->autoneg == AUTONEG_ENABLE ?
-		mlx5e_ethtool2ptys_adver_link(cmd->advertising) :
+	link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ?
+		mlx5e_ethtool2ptys_adver_link(link_ksettings->link_modes.advertising) :
 		mlx5e_ethtool2ptys_speed_link(speed);
 
 	err = mlx5_query_port_proto_cap(mdev, &eth_proto_cap, MLX5_PTYS_EN);
@@ -806,15 +847,18 @@ static int mlx5e_set_settings(struct net_device *netdev,
 		goto out;
 	}
 
-	if (link_modes == eth_proto_admin)
+	mlx5_query_port_autoneg(mdev, MLX5_PTYS_EN, &an_status,
+				&an_disable_cap, &an_disable_admin);
+
+	an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE;
+	an_changes = ((!an_disable && an_disable_admin) ||
+		      (an_disable && !an_disable_admin));
+
+	if (!an_changes && link_modes == eth_proto_admin)
 		goto out;
 
-	mlx5_query_port_admin_status(mdev, &ps);
-	if (ps == MLX5_PORT_UP)
-		mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN);
-	mlx5_set_port_proto(mdev, link_modes, MLX5_PTYS_EN);
-	if (ps == MLX5_PORT_UP)
-		mlx5_set_port_admin_status(mdev, MLX5_PORT_UP);
+	mlx5_set_port_ptys(mdev, an_disable, link_modes, MLX5_PTYS_EN);
+	mlx5_toggle_port_link(mdev);
 
 out:
 	return err;
@@ -861,7 +905,7 @@ static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 	mlx5e_build_tir_ctx_hash(tirc, priv);
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
-		mlx5_core_modify_tir(mdev, priv->indir_tirn[i], in, inlen);
+		mlx5_core_modify_tir(mdev, priv->indir_tir[i].tirn, in, inlen);
 }
 
 static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
@@ -883,7 +927,7 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 	mutex_lock(&priv->state_lock);
 
 	if (indir) {
-		u32 rqtn = priv->indir_rqtn;
+		u32 rqtn = priv->indir_rqt.rqtn;
 
 		memcpy(priv->params.indirection_rqt, indir,
 		       sizeof(priv->params.indirection_rqt));
@@ -916,6 +960,15 @@ static int mlx5e_get_rxnfc(struct net_device *netdev,
 	case ETHTOOL_GRXRINGS:
 		info->data = priv->params.num_channels;
 		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		info->rule_cnt = priv->fs.ethtool.tot_num_rules;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		err = mlx5e_ethtool_get_flow(priv, info, info->fs.location);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
@@ -1272,6 +1325,107 @@ static int mlx5e_get_module_eeprom(struct net_device *netdev,
 	return 0;
 }
 
+typedef int (*mlx5e_pflag_handler)(struct net_device *netdev, bool enable);
+
+static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	bool rx_mode_changed;
+	u8 rx_cq_period_mode;
+	int err = 0;
+	bool reset;
+
+	rx_cq_period_mode = enable ?
+		MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
+		MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+	rx_mode_changed = rx_cq_period_mode != priv->params.rx_cq_period_mode;
+
+	if (rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE &&
+	    !MLX5_CAP_GEN(mdev, cq_period_start_from_cqe))
+		return -ENOTSUPP;
+
+	if (!rx_mode_changed)
+		return 0;
+
+	reset = test_bit(MLX5E_STATE_OPENED, &priv->state);
+	if (reset)
+		mlx5e_close_locked(netdev);
+
+	mlx5e_set_rx_cq_mode_params(&priv->params, rx_cq_period_mode);
+
+	if (reset)
+		err = mlx5e_open_locked(netdev);
+
+	return err;
+}
+
+static int mlx5e_handle_pflag(struct net_device *netdev,
+			      u32 wanted_flags,
+			      enum mlx5e_priv_flag flag,
+			      mlx5e_pflag_handler pflag_handler)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	bool enable = !!(wanted_flags & flag);
+	u32 changes = wanted_flags ^ priv->pflags;
+	int err;
+
+	if (!(changes & flag))
+		return 0;
+
+	err = pflag_handler(netdev, enable);
+	if (err) {
+		netdev_err(netdev, "%s private flag 0x%x failed err %d\n",
+			   enable ? "Enable" : "Disable", flag, err);
+		return err;
+	}
+
+	MLX5E_SET_PRIV_FLAG(priv, flag, enable);
+	return 0;
+}
+
+static int mlx5e_set_priv_flags(struct net_device *netdev, u32 pflags)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	int err;
+
+	mutex_lock(&priv->state_lock);
+
+	err = mlx5e_handle_pflag(netdev, pflags,
+				 MLX5E_PFLAG_RX_CQE_BASED_MODER,
+				 set_pflag_rx_cqe_based_moder);
+
+	mutex_unlock(&priv->state_lock);
+	return err ? -EINVAL : 0;
+}
+
+static u32 mlx5e_get_priv_flags(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return priv->pflags;
+}
+
+static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	int err = 0;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		err = mlx5e_ethtool_flow_replace(priv, &cmd->fs);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
 const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_drvinfo       = mlx5e_get_drvinfo,
 	.get_link          = ethtool_op_get_link,
@@ -1284,13 +1438,14 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.set_channels      = mlx5e_set_channels,
 	.get_coalesce      = mlx5e_get_coalesce,
 	.set_coalesce      = mlx5e_set_coalesce,
-	.get_settings      = mlx5e_get_settings,
-	.set_settings      = mlx5e_set_settings,
+	.get_link_ksettings  = mlx5e_get_link_ksettings,
+	.set_link_ksettings  = mlx5e_set_link_ksettings,
 	.get_rxfh_key_size   = mlx5e_get_rxfh_key_size,
 	.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
 	.get_rxfh          = mlx5e_get_rxfh,
 	.set_rxfh          = mlx5e_set_rxfh,
 	.get_rxnfc         = mlx5e_get_rxnfc,
+	.set_rxnfc         = mlx5e_set_rxnfc,
 	.get_tunable       = mlx5e_get_tunable,
 	.set_tunable       = mlx5e_set_tunable,
 	.get_pauseparam    = mlx5e_get_pauseparam,
@@ -1301,4 +1456,6 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.set_wol	   = mlx5e_set_wol,
 	.get_module_info   = mlx5e_get_module_info,
 	.get_module_eeprom = mlx5e_get_module_eeprom,
+	.get_priv_flags    = mlx5e_get_priv_flags,
+	.set_priv_flags    = mlx5e_set_priv_flags
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index b32740092854..1587a9fd5724 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -156,19 +156,18 @@ enum mlx5e_vlan_rule_type {
 
 static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
 				 enum mlx5e_vlan_rule_type rule_type,
-				 u16 vid, u32 *mc, u32 *mv)
+				 u16 vid, struct mlx5_flow_spec *spec)
 {
 	struct mlx5_flow_table *ft = priv->fs.vlan.ft.t;
 	struct mlx5_flow_destination dest;
-	u8 match_criteria_enable = 0;
 	struct mlx5_flow_rule **rule_p;
 	int err = 0;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest.ft = priv->fs.l2.ft.t;
 
-	match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-	MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.vlan_tag);
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.vlan_tag);
 
 	switch (rule_type) {
 	case MLX5E_VLAN_RULE_TYPE_UNTAGGED:
@@ -176,17 +175,19 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
 		break;
 	case MLX5E_VLAN_RULE_TYPE_ANY_VID:
 		rule_p = &priv->fs.vlan.any_vlan_rule;
-		MLX5_SET(fte_match_param, mv, outer_headers.vlan_tag, 1);
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.vlan_tag, 1);
 		break;
 	default: /* MLX5E_VLAN_RULE_TYPE_MATCH_VID */
 		rule_p = &priv->fs.vlan.active_vlans_rule[vid];
-		MLX5_SET(fte_match_param, mv, outer_headers.vlan_tag, 1);
-		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.first_vid);
-		MLX5_SET(fte_match_param, mv, outer_headers.first_vid, vid);
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.vlan_tag, 1);
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 outer_headers.first_vid);
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid,
+			 vid);
 		break;
 	}
 
-	*rule_p = mlx5_add_flow_rule(ft, match_criteria_enable, mc, mv,
+	*rule_p = mlx5_add_flow_rule(ft, spec,
 				     MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
 				     MLX5_FS_DEFAULT_FLOW_TAG,
 				     &dest);
@@ -203,27 +204,21 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
 static int mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
 			       enum mlx5e_vlan_rule_type rule_type, u16 vid)
 {
-	u32 *match_criteria;
-	u32 *match_value;
+	struct mlx5_flow_spec *spec;
 	int err = 0;
 
-	match_value	= mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
-	match_criteria	= mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
-	if (!match_value || !match_criteria) {
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec) {
 		netdev_err(priv->netdev, "%s: alloc failed\n", __func__);
-		err = -ENOMEM;
-		goto add_vlan_rule_out;
+		return -ENOMEM;
 	}
 
 	if (rule_type == MLX5E_VLAN_RULE_TYPE_MATCH_VID)
 		mlx5e_vport_context_update_vlans(priv);
 
-	err = __mlx5e_add_vlan_rule(priv, rule_type, vid, match_criteria,
-				    match_value);
+	err = __mlx5e_add_vlan_rule(priv, rule_type, vid, spec);
 
-add_vlan_rule_out:
-	kvfree(match_criteria);
-	kvfree(match_value);
+	kvfree(spec);
 
 	return err;
 }
@@ -598,32 +593,27 @@ static struct mlx5_flow_rule *mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
 						      u8 proto)
 {
 	struct mlx5_flow_rule *rule;
-	u8 match_criteria_enable = 0;
-	u32 *match_criteria;
-	u32 *match_value;
+	struct mlx5_flow_spec *spec;
 	int err = 0;
 
-	match_value	= mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
-	match_criteria	= mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
-	if (!match_value || !match_criteria) {
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec) {
 		netdev_err(priv->netdev, "%s: alloc failed\n", __func__);
-		err = -ENOMEM;
-		goto out;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	if (proto) {
-		match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.ip_protocol);
-		MLX5_SET(fte_match_param, match_value, outer_headers.ip_protocol, proto);
+		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol);
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, proto);
 	}
 	if (etype) {
-		match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.ethertype);
-		MLX5_SET(fte_match_param, match_value, outer_headers.ethertype, etype);
+		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ethertype);
+		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype);
 	}
 
-	rule = mlx5_add_flow_rule(ft, match_criteria_enable,
-				  match_criteria, match_value,
+	rule = mlx5_add_flow_rule(ft, spec,
 				  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
 				  MLX5_FS_DEFAULT_FLOW_TAG,
 				  dest);
@@ -631,9 +621,8 @@ static struct mlx5_flow_rule *mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
 		err = PTR_ERR(rule);
 		netdev_err(priv->netdev, "%s: add rule failed\n", __func__);
 	}
-out:
-	kvfree(match_criteria);
-	kvfree(match_value);
+
+	kvfree(spec);
 	return err ? ERR_PTR(err) : rule;
 }
 
@@ -655,7 +644,7 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv)
 		if (tt == MLX5E_TT_ANY)
 			dest.tir_num = priv->direct_tir[0].tirn;
 		else
-			dest.tir_num = priv->indir_tirn[tt];
+			dest.tir_num = priv->indir_tir[tt].tirn;
 		rules[tt] = mlx5e_generate_ttc_rule(priv, ft, &dest,
 						    ttc_rules[tt].etype,
 						    ttc_rules[tt].proto);
@@ -792,24 +781,20 @@ static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv,
 {
 	struct mlx5_flow_table *ft = priv->fs.l2.ft.t;
 	struct mlx5_flow_destination dest;
-	u8 match_criteria_enable = 0;
-	u32 *match_criteria;
-	u32 *match_value;
+	struct mlx5_flow_spec *spec;
 	int err = 0;
 	u8 *mc_dmac;
 	u8 *mv_dmac;
 
-	match_value    = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
-	match_criteria = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
-	if (!match_value || !match_criteria) {
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec) {
 		netdev_err(priv->netdev, "%s: alloc failed\n", __func__);
-		err = -ENOMEM;
-		goto add_l2_rule_out;
+		return -ENOMEM;
 	}
 
-	mc_dmac = MLX5_ADDR_OF(fte_match_param, match_criteria,
+	mc_dmac = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
 			       outer_headers.dmac_47_16);
-	mv_dmac = MLX5_ADDR_OF(fte_match_param, match_value,
+	mv_dmac = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 			       outer_headers.dmac_47_16);
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
@@ -817,13 +802,13 @@ static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv,
 
 	switch (type) {
 	case MLX5E_FULLMATCH:
-		match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
 		eth_broadcast_addr(mc_dmac);
 		ether_addr_copy(mv_dmac, ai->addr);
 		break;
 
 	case MLX5E_ALLMULTI:
-		match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
 		mc_dmac[0] = 0x01;
 		mv_dmac[0] = 0x01;
 		break;
@@ -832,8 +817,7 @@ static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv,
 		break;
 	}
 
-	ai->rule = mlx5_add_flow_rule(ft, match_criteria_enable, match_criteria,
-				      match_value,
+	ai->rule = mlx5_add_flow_rule(ft, spec,
 				      MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
 				      MLX5_FS_DEFAULT_FLOW_TAG, &dest);
 	if (IS_ERR(ai->rule)) {
@@ -843,9 +827,7 @@ static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv,
 		ai->rule = NULL;
 	}
 
-add_l2_rule_out:
-	kvfree(match_criteria);
-	kvfree(match_value);
+	kvfree(spec);
 
 	return err;
 }
@@ -1102,6 +1084,8 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
 		goto err_destroy_l2_table;
 	}
 
+	mlx5e_ethtool_init_steering(priv);
+
 	return 0;
 
 err_destroy_l2_table:
@@ -1121,4 +1105,5 @@ void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv)
 	mlx5e_destroy_l2_table(priv);
 	mlx5e_destroy_ttc_table(priv);
 	mlx5e_arfs_destroy_tables(priv);
+	mlx5e_ethtool_cleanup_steering(priv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
new file mode 100644
index 000000000000..d17c24227900
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -0,0 +1,586 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/mlx5/fs.h>
+#include "en.h"
+
+struct mlx5e_ethtool_rule {
+	struct list_head             list;
+	struct ethtool_rx_flow_spec  flow_spec;
+	struct mlx5_flow_rule        *rule;
+	struct mlx5e_ethtool_table   *eth_ft;
+};
+
+static void put_flow_table(struct mlx5e_ethtool_table *eth_ft)
+{
+	if (!--eth_ft->num_rules) {
+		mlx5_destroy_flow_table(eth_ft->ft);
+		eth_ft->ft = NULL;
+	}
+}
+
+#define MLX5E_ETHTOOL_L3_L4_PRIO 0
+#define MLX5E_ETHTOOL_L2_PRIO (MLX5E_ETHTOOL_L3_L4_PRIO + ETHTOOL_NUM_L3_L4_FTS)
+#define MLX5E_ETHTOOL_NUM_ENTRIES 64000
+#define MLX5E_ETHTOOL_NUM_GROUPS  10
+static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
+						  struct ethtool_rx_flow_spec *fs,
+						  int num_tuples)
+{
+	struct mlx5e_ethtool_table *eth_ft;
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_table *ft;
+	int max_tuples;
+	int table_size;
+	int prio;
+
+	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+		max_tuples = ETHTOOL_NUM_L3_L4_FTS;
+		prio = MLX5E_ETHTOOL_L3_L4_PRIO + (max_tuples - num_tuples);
+		eth_ft = &priv->fs.ethtool.l3_l4_ft[prio];
+		break;
+	case IP_USER_FLOW:
+		max_tuples = ETHTOOL_NUM_L3_L4_FTS;
+		prio = MLX5E_ETHTOOL_L3_L4_PRIO + (max_tuples - num_tuples);
+		eth_ft = &priv->fs.ethtool.l3_l4_ft[prio];
+		break;
+	case ETHER_FLOW:
+		max_tuples = ETHTOOL_NUM_L2_FTS;
+		prio = max_tuples - num_tuples;
+		eth_ft = &priv->fs.ethtool.l2_ft[prio];
+		prio += MLX5E_ETHTOOL_L2_PRIO;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	eth_ft->num_rules++;
+	if (eth_ft->ft)
+		return eth_ft;
+
+	ns = mlx5_get_flow_namespace(priv->mdev,
+				     MLX5_FLOW_NAMESPACE_ETHTOOL);
+	if (!ns)
+		return ERR_PTR(-ENOTSUPP);
+
+	table_size = min_t(u32, BIT(MLX5_CAP_FLOWTABLE(priv->mdev,
+						       flow_table_properties_nic_receive.log_max_ft_size)),
+			   MLX5E_ETHTOOL_NUM_ENTRIES);
+	ft = mlx5_create_auto_grouped_flow_table(ns, prio,
+						 table_size,
+						 MLX5E_ETHTOOL_NUM_GROUPS, 0);
+	if (IS_ERR(ft))
+		return (void *)ft;
+
+	eth_ft->ft = ft;
+	return eth_ft;
+}
+
+static void mask_spec(u8 *mask, u8 *val, size_t size)
+{
+	unsigned int i;
+
+	for (i = 0; i < size; i++, mask++, val++)
+		*((u8 *)val) = *((u8 *)mask) & *((u8 *)val);
+}
+
+static void set_ips(void *outer_headers_v, void *outer_headers_c, __be32 ip4src_m,
+		    __be32 ip4src_v, __be32 ip4dst_m, __be32 ip4dst_v)
+{
+	if (ip4src_m) {
+		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
+				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
+		       &ip4src_v, sizeof(ip4src_v));
+		memset(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
+				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
+		       0xff, sizeof(ip4src_m));
+	}
+	if (ip4dst_m) {
+		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
+				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+		       &ip4dst_v, sizeof(ip4dst_v));
+		memset(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
+				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+		       0xff, sizeof(ip4dst_m));
+	}
+	MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
+		 ethertype, ETH_P_IP);
+	MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
+		 ethertype, 0xffff);
+}
+
+static int set_flow_attrs(u32 *match_c, u32 *match_v,
+			  struct ethtool_rx_flow_spec *fs)
+{
+	void *outer_headers_c = MLX5_ADDR_OF(fte_match_param, match_c,
+					     outer_headers);
+	void *outer_headers_v = MLX5_ADDR_OF(fte_match_param, match_v,
+					     outer_headers);
+	u32 flow_type = fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT);
+	struct ethtool_tcpip4_spec *l4_mask;
+	struct ethtool_tcpip4_spec *l4_val;
+	struct ethtool_usrip4_spec *l3_mask;
+	struct ethtool_usrip4_spec *l3_val;
+	struct ethhdr *eth_val;
+	struct ethhdr *eth_mask;
+
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+		l4_mask = &fs->m_u.tcp_ip4_spec;
+		l4_val = &fs->h_u.tcp_ip4_spec;
+		set_ips(outer_headers_v, outer_headers_c, l4_mask->ip4src,
+			l4_val->ip4src, l4_mask->ip4dst, l4_val->ip4dst);
+
+		if (l4_mask->psrc) {
+			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, tcp_sport,
+				 0xffff);
+			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, tcp_sport,
+				 ntohs(l4_val->psrc));
+		}
+		if (l4_mask->pdst) {
+			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, tcp_dport,
+				 0xffff);
+			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, tcp_dport,
+				 ntohs(l4_val->pdst));
+		}
+		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
+			 0xffff);
+		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ip_protocol,
+			 IPPROTO_TCP);
+		break;
+	case UDP_V4_FLOW:
+		l4_mask = &fs->m_u.tcp_ip4_spec;
+		l4_val = &fs->h_u.tcp_ip4_spec;
+		set_ips(outer_headers_v, outer_headers_c, l4_mask->ip4src,
+			l4_val->ip4src, l4_mask->ip4dst, l4_val->ip4dst);
+
+		if (l4_mask->psrc) {
+			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, udp_sport,
+				 0xffff);
+			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, udp_sport,
+				 ntohs(l4_val->psrc));
+		}
+		if (l4_mask->pdst) {
+			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, udp_dport,
+				 0xffff);
+			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, udp_dport,
+				 ntohs(l4_val->pdst));
+		}
+		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
+			 0xffff);
+		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ip_protocol,
+			 IPPROTO_UDP);
+		break;
+	case IP_USER_FLOW:
+		l3_mask = &fs->m_u.usr_ip4_spec;
+		l3_val = &fs->h_u.usr_ip4_spec;
+		set_ips(outer_headers_v, outer_headers_c, l3_mask->ip4src,
+			l3_val->ip4src, l3_mask->ip4dst, l3_val->ip4dst);
+		break;
+	case ETHER_FLOW:
+		eth_mask = &fs->m_u.ether_spec;
+		eth_val = &fs->h_u.ether_spec;
+
+		mask_spec((u8 *)eth_mask, (u8 *)eth_val, sizeof(*eth_mask));
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
+					     outer_headers_c, smac_47_16),
+				eth_mask->h_source);
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
+					     outer_headers_v, smac_47_16),
+				eth_val->h_source);
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
+					     outer_headers_c, dmac_47_16),
+				eth_mask->h_dest);
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
+					     outer_headers_v, dmac_47_16),
+				eth_val->h_dest);
+		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ethertype,
+			 ntohs(eth_mask->h_proto));
+		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ethertype,
+			 ntohs(eth_val->h_proto));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if ((fs->flow_type & FLOW_EXT) &&
+	    (fs->m_ext.vlan_tci & cpu_to_be16(VLAN_VID_MASK))) {
+		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
+			 vlan_tag, 1);
+		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
+			 vlan_tag, 1);
+		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
+			 first_vid, 0xfff);
+		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
+			 first_vid, ntohs(fs->h_ext.vlan_tci));
+	}
+	if (fs->flow_type & FLOW_MAC_EXT &&
+	    !is_zero_ether_addr(fs->m_ext.h_dest)) {
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
+					     outer_headers_c, dmac_47_16),
+				fs->m_ext.h_dest);
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
+					     outer_headers_v, dmac_47_16),
+				fs->h_ext.h_dest);
+	}
+
+	return 0;
+}
+
+static void add_rule_to_list(struct mlx5e_priv *priv,
+			     struct mlx5e_ethtool_rule *rule)
+{
+	struct mlx5e_ethtool_rule *iter;
+	struct list_head *head = &priv->fs.ethtool.rules;
+
+	list_for_each_entry(iter, &priv->fs.ethtool.rules, list) {
+		if (iter->flow_spec.location > rule->flow_spec.location)
+			break;
+		head = &iter->list;
+	}
+	priv->fs.ethtool.tot_num_rules++;
+	list_add(&rule->list, head);
+}
+
+static bool outer_header_zero(u32 *match_criteria)
+{
+	int size = MLX5_ST_SZ_BYTES(fte_match_param);
+	char *outer_headers_c = MLX5_ADDR_OF(fte_match_param, match_criteria,
+					     outer_headers);
+
+	return outer_headers_c[0] == 0 && !memcmp(outer_headers_c,
+						  outer_headers_c + 1,
+						  size - 1);
+}
+
+static struct mlx5_flow_rule *add_ethtool_flow_rule(struct mlx5e_priv *priv,
+						    struct mlx5_flow_table *ft,
+						    struct ethtool_rx_flow_spec *fs)
+{
+	struct mlx5_flow_destination *dst = NULL;
+	struct mlx5_flow_spec *spec;
+	struct mlx5_flow_rule *rule;
+	int err = 0;
+	u32 action;
+
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec)
+		return ERR_PTR(-ENOMEM);
+	err = set_flow_attrs(spec->match_criteria, spec->match_value,
+			     fs);
+	if (err)
+		goto free;
+
+	if (fs->ring_cookie == RX_CLS_FLOW_DISC) {
+		action = MLX5_FLOW_CONTEXT_ACTION_DROP;
+	} else {
+		dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+		if (!dst) {
+			err = -ENOMEM;
+			goto free;
+		}
+
+		dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR;
+		dst->tir_num = priv->direct_tir[fs->ring_cookie].tirn;
+		action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	}
+
+	spec->match_criteria_enable = (!outer_header_zero(spec->match_criteria));
+	rule = mlx5_add_flow_rule(ft, spec, action,
+				  MLX5_FS_DEFAULT_FLOW_TAG, dst);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		netdev_err(priv->netdev, "%s: failed to add ethtool steering rule: %d\n",
+			   __func__, err);
+		goto free;
+	}
+free:
+	kvfree(spec);
+	kfree(dst);
+	return err ? ERR_PTR(err) : rule;
+}
+
+static void del_ethtool_rule(struct mlx5e_priv *priv,
+			     struct mlx5e_ethtool_rule *eth_rule)
+{
+	if (eth_rule->rule)
+		mlx5_del_flow_rule(eth_rule->rule);
+	list_del(&eth_rule->list);
+	priv->fs.ethtool.tot_num_rules--;
+	put_flow_table(eth_rule->eth_ft);
+	kfree(eth_rule);
+}
+
+static struct mlx5e_ethtool_rule *find_ethtool_rule(struct mlx5e_priv *priv,
+						    int location)
+{
+	struct mlx5e_ethtool_rule *iter;
+
+	list_for_each_entry(iter, &priv->fs.ethtool.rules, list) {
+		if (iter->flow_spec.location == location)
+			return iter;
+	}
+	return NULL;
+}
+
+static struct mlx5e_ethtool_rule *get_ethtool_rule(struct mlx5e_priv *priv,
+						   int location)
+{
+	struct mlx5e_ethtool_rule *eth_rule;
+
+	eth_rule = find_ethtool_rule(priv, location);
+	if (eth_rule)
+		del_ethtool_rule(priv, eth_rule);
+
+	eth_rule = kzalloc(sizeof(*eth_rule), GFP_KERNEL);
+	if (!eth_rule)
+		return ERR_PTR(-ENOMEM);
+
+	add_rule_to_list(priv, eth_rule);
+	return eth_rule;
+}
+
+#define MAX_NUM_OF_ETHTOOL_RULES BIT(10)
+
+#define all_ones(field) (field == (__force typeof(field))-1)
+#define all_zeros_or_all_ones(field)		\
+	((field) == 0 || (field) == (__force typeof(field))-1)
+
+static int validate_flow(struct mlx5e_priv *priv,
+			 struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *l4_mask;
+	struct ethtool_usrip4_spec *l3_mask;
+	struct ethhdr *eth_mask;
+	int num_tuples = 0;
+
+	if (fs->location >= MAX_NUM_OF_ETHTOOL_RULES)
+		return -EINVAL;
+
+	if (fs->ring_cookie >= priv->params.num_channels &&
+	    fs->ring_cookie != RX_CLS_FLOW_DISC)
+		return -EINVAL;
+
+	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+	case ETHER_FLOW:
+		eth_mask = &fs->m_u.ether_spec;
+		if (!is_zero_ether_addr(eth_mask->h_dest))
+			num_tuples++;
+		if (!is_zero_ether_addr(eth_mask->h_source))
+			num_tuples++;
+		if (eth_mask->h_proto)
+			num_tuples++;
+		break;
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+		if (fs->m_u.tcp_ip4_spec.tos)
+			return -EINVAL;
+		l4_mask = &fs->m_u.tcp_ip4_spec;
+		if (l4_mask->ip4src) {
+			if (!all_ones(l4_mask->ip4src))
+				return -EINVAL;
+			num_tuples++;
+		}
+		if (l4_mask->ip4dst) {
+			if (!all_ones(l4_mask->ip4dst))
+				return -EINVAL;
+			num_tuples++;
+		}
+		if (l4_mask->psrc) {
+			if (!all_ones(l4_mask->psrc))
+				return -EINVAL;
+			num_tuples++;
+		}
+		if (l4_mask->pdst) {
+			if (!all_ones(l4_mask->pdst))
+				return -EINVAL;
+			num_tuples++;
+		}
+		/* Flow is TCP/UDP */
+		num_tuples++;
+		break;
+	case IP_USER_FLOW:
+		l3_mask = &fs->m_u.usr_ip4_spec;
+		if (l3_mask->l4_4_bytes || l3_mask->tos || l3_mask->proto ||
+		    fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4)
+			return -EINVAL;
+		if (l3_mask->ip4src) {
+			if (!all_ones(l3_mask->ip4src))
+				return -EINVAL;
+			num_tuples++;
+		}
+		if (l3_mask->ip4dst) {
+			if (!all_ones(l3_mask->ip4dst))
+				return -EINVAL;
+			num_tuples++;
+		}
+		/* Flow is IPv4 */
+		num_tuples++;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if ((fs->flow_type & FLOW_EXT)) {
+		if (fs->m_ext.vlan_etype ||
+		    (fs->m_ext.vlan_tci != cpu_to_be16(VLAN_VID_MASK)))
+			return -EINVAL;
+
+		if (fs->m_ext.vlan_tci) {
+			if (be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID)
+				return -EINVAL;
+		}
+		num_tuples++;
+	}
+
+	if (fs->flow_type & FLOW_MAC_EXT &&
+	    !is_zero_ether_addr(fs->m_ext.h_dest))
+		num_tuples++;
+
+	return num_tuples;
+}
+
+int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
+			       struct ethtool_rx_flow_spec *fs)
+{
+	struct mlx5e_ethtool_table *eth_ft;
+	struct mlx5e_ethtool_rule *eth_rule;
+	struct mlx5_flow_rule *rule;
+	int num_tuples;
+	int err;
+
+	num_tuples = validate_flow(priv, fs);
+	if (num_tuples <= 0) {
+		netdev_warn(priv->netdev, "%s: flow is not valid\n",  __func__);
+		return -EINVAL;
+	}
+
+	eth_ft = get_flow_table(priv, fs, num_tuples);
+	if (IS_ERR(eth_ft))
+		return PTR_ERR(eth_ft);
+
+	eth_rule = get_ethtool_rule(priv, fs->location);
+	if (IS_ERR(eth_rule)) {
+		put_flow_table(eth_ft);
+		return PTR_ERR(eth_rule);
+	}
+
+	eth_rule->flow_spec = *fs;
+	eth_rule->eth_ft = eth_ft;
+	if (!eth_ft->ft) {
+		err = -EINVAL;
+		goto del_ethtool_rule;
+	}
+	rule = add_ethtool_flow_rule(priv, eth_ft->ft, fs);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		goto del_ethtool_rule;
+	}
+
+	eth_rule->rule = rule;
+
+	return 0;
+
+del_ethtool_rule:
+	del_ethtool_rule(priv, eth_rule);
+
+	return err;
+}
+
+int mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv,
+			      int location)
+{
+	struct mlx5e_ethtool_rule *eth_rule;
+	int err = 0;
+
+	if (location >= MAX_NUM_OF_ETHTOOL_RULES)
+		return -ENOSPC;
+
+	eth_rule = find_ethtool_rule(priv, location);
+	if (!eth_rule) {
+		err =  -ENOENT;
+		goto out;
+	}
+
+	del_ethtool_rule(priv, eth_rule);
+out:
+	return err;
+}
+
+int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
+			   int location)
+{
+	struct mlx5e_ethtool_rule *eth_rule;
+
+	if (location < 0 || location >= MAX_NUM_OF_ETHTOOL_RULES)
+		return -EINVAL;
+
+	list_for_each_entry(eth_rule, &priv->fs.ethtool.rules, list) {
+		if (eth_rule->flow_spec.location == location) {
+			info->fs = eth_rule->flow_spec;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
+int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
+				u32 *rule_locs)
+{
+	int location = 0;
+	int idx = 0;
+	int err = 0;
+
+	while ((!err || err == -ENOENT) && idx < info->rule_cnt) {
+		err = mlx5e_ethtool_get_flow(priv, info, location);
+		if (!err)
+			rule_locs[idx++] = location;
+		location++;
+	}
+	return err;
+}
+
+void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv)
+{
+	struct mlx5e_ethtool_rule *iter;
+	struct mlx5e_ethtool_rule *temp;
+
+	list_for_each_entry_safe(iter, temp, &priv->fs.ethtool.rules, list)
+		del_ethtool_rule(priv, iter);
+}
+
+void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)
+{
+	INIT_LIST_HEAD(&priv->fs.ethtool.rules);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index fd4392999eee..96ec53a6a595 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -40,8 +40,9 @@
 #include "vxlan.h"
 
 struct mlx5e_rq_param {
-	u32                        rqc[MLX5_ST_SZ_DW(rqc)];
-	struct mlx5_wq_param       wq;
+	u32			rqc[MLX5_ST_SZ_DW(rqc)];
+	struct mlx5_wq_param	wq;
+	bool			am_enabled;
 };
 
 struct mlx5e_sq_param {
@@ -55,6 +56,7 @@ struct mlx5e_cq_param {
 	u32                        cqc[MLX5_ST_SZ_DW(cqc)];
 	struct mlx5_wq_param       wq;
 	u16                        eq_ix;
+	u8                         cq_period_mode;
 };
 
 struct mlx5e_channel_param {
@@ -105,11 +107,11 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 
 		s->rx_packets	+= rq_stats->packets;
 		s->rx_bytes	+= rq_stats->bytes;
-		s->lro_packets	+= rq_stats->lro_packets;
-		s->lro_bytes	+= rq_stats->lro_bytes;
+		s->rx_lro_packets += rq_stats->lro_packets;
+		s->rx_lro_bytes	+= rq_stats->lro_bytes;
 		s->rx_csum_none	+= rq_stats->csum_none;
-		s->rx_csum_sw	+= rq_stats->csum_sw;
-		s->rx_csum_inner += rq_stats->csum_inner;
+		s->rx_csum_complete += rq_stats->csum_complete;
+		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_wqe_err   += rq_stats->wqe_err;
 		s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
 		s->rx_mpwqe_frag   += rq_stats->mpwqe_frag;
@@ -122,24 +124,23 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 
 			s->tx_packets		+= sq_stats->packets;
 			s->tx_bytes		+= sq_stats->bytes;
-			s->tso_packets		+= sq_stats->tso_packets;
-			s->tso_bytes		+= sq_stats->tso_bytes;
-			s->tso_inner_packets	+= sq_stats->tso_inner_packets;
-			s->tso_inner_bytes	+= sq_stats->tso_inner_bytes;
+			s->tx_tso_packets	+= sq_stats->tso_packets;
+			s->tx_tso_bytes		+= sq_stats->tso_bytes;
+			s->tx_tso_inner_packets	+= sq_stats->tso_inner_packets;
+			s->tx_tso_inner_bytes	+= sq_stats->tso_inner_bytes;
 			s->tx_queue_stopped	+= sq_stats->stopped;
 			s->tx_queue_wake	+= sq_stats->wake;
 			s->tx_queue_dropped	+= sq_stats->dropped;
-			s->tx_csum_inner	+= sq_stats->csum_offload_inner;
-			tx_offload_none		+= sq_stats->csum_offload_none;
+			s->tx_csum_partial_inner += sq_stats->csum_partial_inner;
+			tx_offload_none		+= sq_stats->csum_none;
 		}
 	}
 
 	/* Update calculated offload counters */
-	s->tx_csum_offload = s->tx_packets - tx_offload_none - s->tx_csum_inner;
-	s->rx_csum_good    = s->rx_packets - s->rx_csum_none -
-			     s->rx_csum_sw;
+	s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner;
+	s->rx_csum_unnecessary = s->rx_packets - s->rx_csum_none - s->rx_csum_complete;
 
-	s->link_down_events = MLX5_GET(ppcnt_reg,
+	s->link_down_events_phy = MLX5_GET(ppcnt_reg,
 				priv->stats.pport.phy_counters,
 				counter_set.phys_layer_cntrs.link_down_events);
 }
@@ -225,14 +226,14 @@ void mlx5e_update_stats(struct mlx5e_priv *priv)
 	mlx5e_update_sw_counters(priv);
 }
 
-static void mlx5e_update_stats_work(struct work_struct *work)
+void mlx5e_update_stats_work(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5e_priv *priv = container_of(dwork, struct mlx5e_priv,
 					       update_stats_work);
 	mutex_lock(&priv->state_lock);
 	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		mlx5e_update_stats(priv);
+		priv->profile->update_stats(priv);
 		queue_delayed_work(priv->wq, dwork,
 				   msecs_to_jiffies(MLX5E_UPDATE_STATS_INTERVAL));
 	}
@@ -244,7 +245,7 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
 {
 	struct mlx5e_priv *priv = vpriv;
 
-	if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state))
+	if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state))
 		return;
 
 	switch (event) {
@@ -260,12 +261,12 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
 
 static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
 {
-	set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state);
+	set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
 }
 
 static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
 {
-	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state);
+	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
 	synchronize_irq(mlx5_get_msix_vec(priv->mdev, MLX5_EQ_VEC_ASYNC));
 }
 
@@ -336,6 +337,9 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		wqe->data.byte_count = cpu_to_be32(byte_count);
 	}
 
+	INIT_WORK(&rq->am.work, mlx5e_rx_am_work);
+	rq->am.mode = priv->params.rx_cq_period_mode;
+
 	rq->wq_type = priv->params.rq_wq_type;
 	rq->pdev    = c->pdev;
 	rq->netdev  = c->netdev;
@@ -508,6 +512,9 @@ static int mlx5e_open_rq(struct mlx5e_channel *c,
 	if (err)
 		goto err_disable_rq;
 
+	if (param->am_enabled)
+		set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
+
 	set_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
 
 	sq->ico_wqe_info[pi].opcode     = MLX5_OPCODE_NOP;
@@ -536,6 +543,8 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq)
 	/* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */
 	napi_synchronize(&rq->channel->napi);
 
+	cancel_work_sync(&rq->am.work);
+
 	mlx5e_disable_rq(rq);
 	mlx5e_destroy_rq(rq);
 }
@@ -580,7 +589,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c,
 	void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq);
 	int err;
 
-	err = mlx5_alloc_map_uar(mdev, &sq->uar, true);
+	err = mlx5_alloc_map_uar(mdev, &sq->uar, !!MLX5_CAP_GEN(mdev, bf));
 	if (err)
 		return err;
 
@@ -702,7 +711,8 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
 	return err;
 }
 
-static int mlx5e_modify_sq(struct mlx5e_sq *sq, int curr_state, int next_state)
+static int mlx5e_modify_sq(struct mlx5e_sq *sq, int curr_state,
+			   int next_state, bool update_rl, int rl_index)
 {
 	struct mlx5e_channel *c = sq->channel;
 	struct mlx5e_priv *priv = c->priv;
@@ -722,6 +732,10 @@ static int mlx5e_modify_sq(struct mlx5e_sq *sq, int curr_state, int next_state)
 
 	MLX5_SET(modify_sq_in, in, sq_state, curr_state);
 	MLX5_SET(sqc, sqc, state, next_state);
+	if (update_rl && next_state == MLX5_SQC_STATE_RDY) {
+		MLX5_SET64(modify_sq_in, in, modify_bitmask, 1);
+		MLX5_SET(sqc,  sqc, packet_pacing_rate_limit_index, rl_index);
+	}
 
 	err = mlx5_core_modify_sq(mdev, sq->sqn, in, inlen);
 
@@ -737,6 +751,8 @@ static void mlx5e_disable_sq(struct mlx5e_sq *sq)
 	struct mlx5_core_dev *mdev = priv->mdev;
 
 	mlx5_core_destroy_sq(mdev, sq->sqn);
+	if (sq->rate_limit)
+		mlx5_rl_remove_rate(mdev, sq->rate_limit);
 }
 
 static int mlx5e_open_sq(struct mlx5e_channel *c,
@@ -754,7 +770,8 @@ static int mlx5e_open_sq(struct mlx5e_channel *c,
 	if (err)
 		goto err_destroy_sq;
 
-	err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RST, MLX5_SQC_STATE_RDY);
+	err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RST, MLX5_SQC_STATE_RDY,
+			      false, 0);
 	if (err)
 		goto err_disable_sq;
 
@@ -793,7 +810,8 @@ static void mlx5e_close_sq(struct mlx5e_sq *sq)
 		if (mlx5e_sq_has_room_for(sq, 1))
 			mlx5e_send_nop(sq, true);
 
-		mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR);
+		mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR,
+				false, 0);
 	}
 
 	while (sq->cc != sq->pc) /* wait till sq is empty */
@@ -840,7 +858,7 @@ static int mlx5e_create_cq(struct mlx5e_channel *c,
 	mcq->comp       = mlx5e_completion_event;
 	mcq->event      = mlx5e_cq_error_event;
 	mcq->irqn       = irqn;
-	mcq->uar        = &priv->cq_uar;
+	mcq->uar        = &mdev->mlx5e_res.cq_uar;
 
 	for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) {
 		struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, i);
@@ -887,6 +905,7 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 
 	mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used);
 
+	MLX5_SET(cqc,   cqc, cq_period_mode, param->cq_period_mode);
 	MLX5_SET(cqc,   cqc, c_eqn,         eqn);
 	MLX5_SET(cqc,   cqc, uar_page,      mcq->uar->index);
 	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
@@ -916,8 +935,7 @@ static void mlx5e_disable_cq(struct mlx5e_cq *cq)
 static int mlx5e_open_cq(struct mlx5e_channel *c,
 			 struct mlx5e_cq_param *param,
 			 struct mlx5e_cq *cq,
-			 u16 moderation_usecs,
-			 u16 moderation_frames)
+			 struct mlx5e_cq_moder moderation)
 {
 	int err;
 	struct mlx5e_priv *priv = c->priv;
@@ -933,8 +951,8 @@ static int mlx5e_open_cq(struct mlx5e_channel *c,
 
 	if (MLX5_CAP_GEN(mdev, cq_moderation))
 		mlx5_core_modify_cq_moderation(mdev, &cq->mcq,
-					       moderation_usecs,
-					       moderation_frames);
+					       moderation.usec,
+					       moderation.pkts);
 	return 0;
 
 err_destroy_cq:
@@ -963,8 +981,7 @@ static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
 
 	for (tc = 0; tc < c->num_tc; tc++) {
 		err = mlx5e_open_cq(c, &cparam->tx_cq, &c->sq[tc].cq,
-				    priv->params.tx_cq_moderation_usec,
-				    priv->params.tx_cq_moderation_pkts);
+				    priv->params.tx_cq_moderation);
 		if (err)
 			goto err_close_tx_cqs;
 	}
@@ -1019,19 +1036,96 @@ static void mlx5e_build_channeltc_to_txq_map(struct mlx5e_priv *priv, int ix)
 {
 	int i;
 
-	for (i = 0; i < MLX5E_MAX_NUM_TC; i++)
+	for (i = 0; i < priv->profile->max_tc; i++)
 		priv->channeltc_to_txq_map[ix][i] =
 			ix + i * priv->params.num_channels;
 }
 
+static int mlx5e_set_sq_maxrate(struct net_device *dev,
+				struct mlx5e_sq *sq, u32 rate)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u16 rl_index = 0;
+	int err;
+
+	if (rate == sq->rate_limit)
+		/* nothing to do */
+		return 0;
+
+	if (sq->rate_limit)
+		/* remove current rl index to free space to next ones */
+		mlx5_rl_remove_rate(mdev, sq->rate_limit);
+
+	sq->rate_limit = 0;
+
+	if (rate) {
+		err = mlx5_rl_add_rate(mdev, rate, &rl_index);
+		if (err) {
+			netdev_err(dev, "Failed configuring rate %u: %d\n",
+				   rate, err);
+			return err;
+		}
+	}
+
+	err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
+			      MLX5_SQC_STATE_RDY, true, rl_index);
+	if (err) {
+		netdev_err(dev, "Failed configuring rate %u: %d\n",
+			   rate, err);
+		/* remove the rate from the table */
+		if (rate)
+			mlx5_rl_remove_rate(mdev, rate);
+		return err;
+	}
+
+	sq->rate_limit = rate;
+	return 0;
+}
+
+static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_sq *sq = priv->txq_to_sq_map[index];
+	int err = 0;
+
+	if (!mlx5_rl_is_supported(mdev)) {
+		netdev_err(dev, "Rate limiting is not supported on this device\n");
+		return -EINVAL;
+	}
+
+	/* rate is given in Mb/sec, HW config is in Kb/sec */
+	rate = rate << 10;
+
+	/* Check whether rate in valid range, 0 is always valid */
+	if (rate && !mlx5_rl_is_in_range(mdev, rate)) {
+		netdev_err(dev, "TX rate %u, is not in range\n", rate);
+		return -ERANGE;
+	}
+
+	mutex_lock(&priv->state_lock);
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+		err = mlx5e_set_sq_maxrate(dev, sq, rate);
+	if (!err)
+		priv->tx_rates[index] = rate;
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
 static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 			      struct mlx5e_channel_param *cparam,
 			      struct mlx5e_channel **cp)
 {
+	struct mlx5e_cq_moder icosq_cq_moder = {0, 0};
 	struct net_device *netdev = priv->netdev;
+	struct mlx5e_cq_moder rx_cq_profile;
 	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
+	struct mlx5e_sq *sq;
 	int err;
+	int i;
 
 	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
@@ -1042,14 +1136,19 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->cpu      = cpu;
 	c->pdev     = &priv->mdev->pdev->dev;
 	c->netdev   = priv->netdev;
-	c->mkey_be  = cpu_to_be32(priv->mkey.key);
+	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
 	c->num_tc   = priv->params.num_tc;
 
+	if (priv->params.rx_am_enabled)
+		rx_cq_profile = mlx5e_am_get_def_profile(priv->params.rx_cq_period_mode);
+	else
+		rx_cq_profile = priv->params.rx_cq_moderation;
+
 	mlx5e_build_channeltc_to_txq_map(priv, ix);
 
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
 
-	err = mlx5e_open_cq(c, &cparam->icosq_cq, &c->icosq.cq, 0, 0);
+	err = mlx5e_open_cq(c, &cparam->icosq_cq, &c->icosq.cq, icosq_cq_moder);
 	if (err)
 		goto err_napi_del;
 
@@ -1058,8 +1157,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 		goto err_close_icosq_cq;
 
 	err = mlx5e_open_cq(c, &cparam->rx_cq, &c->rq.cq,
-			    priv->params.rx_cq_moderation_usec,
-			    priv->params.rx_cq_moderation_pkts);
+			    rx_cq_profile);
 	if (err)
 		goto err_close_tx_cqs;
 
@@ -1073,6 +1171,16 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		goto err_close_icosq;
 
+	for (i = 0; i < priv->params.num_tc; i++) {
+		u32 txq_ix = priv->channeltc_to_txq_map[ix][i];
+
+		if (priv->tx_rates[txq_ix]) {
+			sq = priv->txq_to_sq_map[txq_ix];
+			mlx5e_set_sq_maxrate(priv->netdev, sq,
+					     priv->tx_rates[txq_ix]);
+		}
+	}
+
 	err = mlx5e_open_rq(c, &cparam->rq, &c->rq);
 	if (err)
 		goto err_close_sqs;
@@ -1144,11 +1252,13 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 	MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
 	MLX5_SET(wq, wq, log_wq_stride,    ilog2(sizeof(struct mlx5e_rx_wqe)));
 	MLX5_SET(wq, wq, log_wq_sz,        priv->params.log_rq_size);
-	MLX5_SET(wq, wq, pd,               priv->pdn);
+	MLX5_SET(wq, wq, pd,               priv->mdev->mlx5e_res.pdn);
 	MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter);
 
 	param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev);
 	param->wq.linear = 1;
+
+	param->am_enabled = priv->params.rx_am_enabled;
 }
 
 static void mlx5e_build_drop_rq_param(struct mlx5e_rq_param *param)
@@ -1167,7 +1277,7 @@ static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
 
 	MLX5_SET(wq, wq, log_wq_stride, ilog2(MLX5_SEND_WQE_BB));
-	MLX5_SET(wq, wq, pd,            priv->pdn);
+	MLX5_SET(wq, wq, pd,            priv->mdev->mlx5e_res.pdn);
 
 	param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev);
 }
@@ -1189,7 +1299,7 @@ static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
 {
 	void *cqc = param->cqc;
 
-	MLX5_SET(cqc, cqc, uar_page, priv->cq_uar.index);
+	MLX5_SET(cqc, cqc, uar_page, priv->mdev->mlx5e_res.cq_uar.index);
 }
 
 static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
@@ -1214,6 +1324,8 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 	}
 
 	mlx5e_build_common_cq_param(priv, param);
+
+	param->cq_period_mode = priv->params.rx_cq_period_mode;
 }
 
 static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
@@ -1224,6 +1336,8 @@ static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
 	MLX5_SET(cqc, cqc, log_cq_size, priv->params.log_sq_size);
 
 	mlx5e_build_common_cq_param(priv, param);
+
+	param->cq_period_mode = MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 }
 
 static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
@@ -1235,6 +1349,8 @@ static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
 	MLX5_SET(cqc, cqc, log_cq_size, log_wq_size);
 
 	mlx5e_build_common_cq_param(priv, param);
+
+	param->cq_period_mode = MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 }
 
 static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
@@ -1370,7 +1486,8 @@ static void mlx5e_fill_direct_rqt_rqn(struct mlx5e_priv *priv, void *rqtc,
 	MLX5_SET(rqtc, rqtc, rq_num[0], rqn);
 }
 
-static int mlx5e_create_rqt(struct mlx5e_priv *priv, int sz, int ix, u32 *rqtn)
+static int mlx5e_create_rqt(struct mlx5e_priv *priv, int sz,
+			    int ix, struct mlx5e_rqt *rqt)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	void *rqtc;
@@ -1393,34 +1510,36 @@ static int mlx5e_create_rqt(struct mlx5e_priv *priv, int sz, int ix, u32 *rqtn)
 	else
 		mlx5e_fill_direct_rqt_rqn(priv, rqtc, ix);
 
-	err = mlx5_core_create_rqt(mdev, in, inlen, rqtn);
+	err = mlx5_core_create_rqt(mdev, in, inlen, &rqt->rqtn);
+	if (!err)
+		rqt->enabled = true;
 
 	kvfree(in);
 	return err;
 }
 
-static void mlx5e_destroy_rqt(struct mlx5e_priv *priv, u32 rqtn)
+void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt)
 {
-	mlx5_core_destroy_rqt(priv->mdev, rqtn);
+	rqt->enabled = false;
+	mlx5_core_destroy_rqt(priv->mdev, rqt->rqtn);
 }
 
-static int mlx5e_create_rqts(struct mlx5e_priv *priv)
+static int mlx5e_create_indirect_rqts(struct mlx5e_priv *priv)
 {
-	int nch = mlx5e_get_max_num_channels(priv->mdev);
-	u32 *rqtn;
+	struct mlx5e_rqt *rqt = &priv->indir_rqt;
+
+	return mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, 0, rqt);
+}
+
+int mlx5e_create_direct_rqts(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rqt *rqt;
 	int err;
 	int ix;
 
-	/* Indirect RQT */
-	rqtn = &priv->indir_rqtn;
-	err = mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, 0, rqtn);
-	if (err)
-		return err;
-
-	/* Direct RQTs */
-	for (ix = 0; ix < nch; ix++) {
-		rqtn = &priv->direct_tir[ix].rqtn;
-		err = mlx5e_create_rqt(priv, 1 /*size */, ix, rqtn);
+	for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
+		rqt = &priv->direct_tir[ix].rqt;
+		err = mlx5e_create_rqt(priv, 1 /*size */, ix, rqt);
 		if (err)
 			goto err_destroy_rqts;
 	}
@@ -1429,24 +1548,11 @@ static int mlx5e_create_rqts(struct mlx5e_priv *priv)
 
 err_destroy_rqts:
 	for (ix--; ix >= 0; ix--)
-		mlx5e_destroy_rqt(priv, priv->direct_tir[ix].rqtn);
-
-	mlx5e_destroy_rqt(priv, priv->indir_rqtn);
+		mlx5e_destroy_rqt(priv, &priv->direct_tir[ix].rqt);
 
 	return err;
 }
 
-static void mlx5e_destroy_rqts(struct mlx5e_priv *priv)
-{
-	int nch = mlx5e_get_max_num_channels(priv->mdev);
-	int i;
-
-	for (i = 0; i < nch; i++)
-		mlx5e_destroy_rqt(priv, priv->direct_tir[i].rqtn);
-
-	mlx5e_destroy_rqt(priv, priv->indir_rqtn);
-}
-
 int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -1482,10 +1588,15 @@ static void mlx5e_redirect_rqts(struct mlx5e_priv *priv)
 	u32 rqtn;
 	int ix;
 
-	rqtn = priv->indir_rqtn;
-	mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
+	if (priv->indir_rqt.enabled) {
+		rqtn = priv->indir_rqt.rqtn;
+		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
+	}
+
 	for (ix = 0; ix < priv->params.num_channels; ix++) {
-		rqtn = priv->direct_tir[ix].rqtn;
+		if (!priv->direct_tir[ix].rqt.enabled)
+			continue;
+		rqtn = priv->direct_tir[ix].rqt.rqtn;
 		mlx5e_redirect_rqt(priv, rqtn, 1, ix);
 	}
 }
@@ -1545,13 +1656,13 @@ static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
 	mlx5e_build_tir_ctx_lro(tirc, priv);
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		err = mlx5_core_modify_tir(mdev, priv->indir_tirn[tt], in,
+		err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in,
 					   inlen);
 		if (err)
 			goto free_in;
 	}
 
-	for (ix = 0; ix < mlx5e_get_max_num_channels(mdev); ix++) {
+	for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
 		err = mlx5_core_modify_tir(mdev, priv->direct_tir[ix].tirn,
 					   in, inlen);
 		if (err)
@@ -1564,40 +1675,6 @@ free_in:
 	return err;
 }
 
-static int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5e_priv *priv)
-{
-	void *in;
-	int inlen;
-	int err;
-	int i;
-
-	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
-	in = mlx5_vzalloc(inlen);
-	if (!in)
-		return -ENOMEM;
-
-	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
-
-	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) {
-		err = mlx5_core_modify_tir(priv->mdev, priv->indir_tirn[i], in,
-					   inlen);
-		if (err)
-			return err;
-	}
-
-	for (i = 0; i < priv->params.num_channels; i++) {
-		err = mlx5_core_modify_tir(priv->mdev,
-					   priv->direct_tir[i].tirn, in,
-					   inlen);
-		if (err)
-			return err;
-	}
-
-	kvfree(in);
-
-	return 0;
-}
-
 static int mlx5e_set_mtu(struct mlx5e_priv *priv, u16 mtu)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -1666,6 +1743,7 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 int mlx5e_open_locked(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
 	int num_txqs;
 	int err;
 
@@ -1688,7 +1766,7 @@ int mlx5e_open_locked(struct net_device *netdev)
 		goto err_clear_state_opened_flag;
 	}
 
-	err = mlx5e_refresh_tirs_self_loopback_enable(priv);
+	err = mlx5e_refresh_tirs_self_loopback_enable(priv->mdev);
 	if (err) {
 		netdev_err(netdev, "%s: mlx5e_refresh_tirs_self_loopback_enable failed, %d\n",
 			   __func__, err);
@@ -1701,9 +1779,14 @@ int mlx5e_open_locked(struct net_device *netdev)
 #ifdef CONFIG_RFS_ACCEL
 	priv->netdev->rx_cpu_rmap = priv->mdev->rmap;
 #endif
+	if (priv->profile->update_stats)
+		queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
 
-	queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
-
+	if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
+		err = mlx5e_add_sqs_fwd_rules(priv);
+		if (err)
+			goto err_close_channels;
+	}
 	return 0;
 
 err_close_channels:
@@ -1713,7 +1796,7 @@ err_clear_state_opened_flag:
 	return err;
 }
 
-static int mlx5e_open(struct net_device *netdev)
+int mlx5e_open(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	int err;
@@ -1728,6 +1811,7 @@ static int mlx5e_open(struct net_device *netdev)
 int mlx5e_close_locked(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
 
 	/* May already be CLOSED in case a previous configuration operation
 	 * (e.g RX/TX queue size change) that involves close&open failed.
@@ -1737,6 +1821,9 @@ int mlx5e_close_locked(struct net_device *netdev)
 
 	clear_bit(MLX5E_STATE_OPENED, &priv->state);
 
+	if (MLX5_CAP_GEN(mdev, vport_group_manager))
+		mlx5e_remove_sqs_fwd_rules(priv);
+
 	mlx5e_timestamp_cleanup(priv);
 	netif_carrier_off(priv->netdev);
 	mlx5e_redirect_rqts(priv);
@@ -1745,7 +1832,7 @@ int mlx5e_close_locked(struct net_device *netdev)
 	return 0;
 }
 
-static int mlx5e_close(struct net_device *netdev)
+int mlx5e_close(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	int err;
@@ -1804,7 +1891,7 @@ static int mlx5e_create_drop_cq(struct mlx5e_priv *priv,
 	mcq->comp       = mlx5e_completion_event;
 	mcq->event      = mlx5e_cq_error_event;
 	mcq->irqn       = irqn;
-	mcq->uar        = &priv->cq_uar;
+	mcq->uar        = &mdev->mlx5e_res.cq_uar;
 
 	cq->priv = priv;
 
@@ -1870,7 +1957,7 @@ static int mlx5e_create_tis(struct mlx5e_priv *priv, int tc)
 	memset(in, 0, sizeof(in));
 
 	MLX5_SET(tisc, tisc, prio, tc << 1);
-	MLX5_SET(tisc, tisc, transport_domain, priv->tdn);
+	MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.td.tdn);
 
 	return mlx5_core_create_tis(mdev, in, sizeof(in), &priv->tisn[tc]);
 }
@@ -1880,12 +1967,12 @@ static void mlx5e_destroy_tis(struct mlx5e_priv *priv, int tc)
 	mlx5_core_destroy_tis(priv->mdev, priv->tisn[tc]);
 }
 
-static int mlx5e_create_tises(struct mlx5e_priv *priv)
+int mlx5e_create_tises(struct mlx5e_priv *priv)
 {
 	int err;
 	int tc;
 
-	for (tc = 0; tc < MLX5E_MAX_NUM_TC; tc++) {
+	for (tc = 0; tc < priv->profile->max_tc; tc++) {
 		err = mlx5e_create_tis(priv, tc);
 		if (err)
 			goto err_close_tises;
@@ -1900,11 +1987,11 @@ err_close_tises:
 	return err;
 }
 
-static void mlx5e_destroy_tises(struct mlx5e_priv *priv)
+void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 {
 	int tc;
 
-	for (tc = 0; tc < MLX5E_MAX_NUM_TC; tc++)
+	for (tc = 0; tc < priv->profile->max_tc; tc++)
 		mlx5e_destroy_tis(priv, tc);
 }
 
@@ -1913,7 +2000,7 @@ static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
 {
 	void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
 
-	MLX5_SET(tirc, tirc, transport_domain, priv->tdn);
+	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
 
 #define MLX5_HASH_IP            (MLX5_HASH_FIELD_SEL_SRC_IP   |\
 				 MLX5_HASH_FIELD_SEL_DST_IP)
@@ -1930,7 +2017,7 @@ static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
 	mlx5e_build_tir_ctx_lro(tirc, priv);
 
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
-	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqtn);
+	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
 	mlx5e_build_tir_ctx_hash(tirc, priv);
 
 	switch (tt) {
@@ -2020,7 +2107,7 @@ static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
 static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
 				       u32 rqtn)
 {
-	MLX5_SET(tirc, tirc, transport_domain, priv->tdn);
+	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
 
 	mlx5e_build_tir_ctx_lro(tirc, priv);
 
@@ -2029,15 +2116,13 @@ static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
 	MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8);
 }
 
-static int mlx5e_create_tirs(struct mlx5e_priv *priv)
+static int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv)
 {
-	int nch = mlx5e_get_max_num_channels(priv->mdev);
+	struct mlx5e_tir *tir;
 	void *tirc;
 	int inlen;
-	u32 *tirn;
 	int err;
 	u32 *in;
-	int ix;
 	int tt;
 
 	inlen = MLX5_ST_SZ_BYTES(create_tir_in);
@@ -2045,25 +2130,51 @@ static int mlx5e_create_tirs(struct mlx5e_priv *priv)
 	if (!in)
 		return -ENOMEM;
 
-	/* indirect tirs */
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		memset(in, 0, inlen);
-		tirn = &priv->indir_tirn[tt];
+		tir = &priv->indir_tir[tt];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
 		mlx5e_build_indir_tir_ctx(priv, tirc, tt);
-		err = mlx5_core_create_tir(priv->mdev, in, inlen, tirn);
+		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
 		if (err)
 			goto err_destroy_tirs;
 	}
 
-	/* direct tirs */
+	kvfree(in);
+
+	return 0;
+
+err_destroy_tirs:
+	for (tt--; tt >= 0; tt--)
+		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[tt]);
+
+	kvfree(in);
+
+	return err;
+}
+
+int mlx5e_create_direct_tirs(struct mlx5e_priv *priv)
+{
+	int nch = priv->profile->max_nch(priv->mdev);
+	struct mlx5e_tir *tir;
+	void *tirc;
+	int inlen;
+	int err;
+	u32 *in;
+	int ix;
+
+	inlen = MLX5_ST_SZ_BYTES(create_tir_in);
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
 	for (ix = 0; ix < nch; ix++) {
 		memset(in, 0, inlen);
-		tirn = &priv->direct_tir[ix].tirn;
+		tir = &priv->direct_tir[ix];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
 		mlx5e_build_direct_tir_ctx(priv, tirc,
-					   priv->direct_tir[ix].rqtn);
-		err = mlx5_core_create_tir(priv->mdev, in, inlen, tirn);
+					   priv->direct_tir[ix].rqt.rqtn);
+		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
 		if (err)
 			goto err_destroy_ch_tirs;
 	}
@@ -2074,27 +2185,28 @@ static int mlx5e_create_tirs(struct mlx5e_priv *priv)
 
 err_destroy_ch_tirs:
 	for (ix--; ix >= 0; ix--)
-		mlx5_core_destroy_tir(priv->mdev, priv->direct_tir[ix].tirn);
-
-err_destroy_tirs:
-	for (tt--; tt >= 0; tt--)
-		mlx5_core_destroy_tir(priv->mdev, priv->indir_tirn[tt]);
+		mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[ix]);
 
 	kvfree(in);
 
 	return err;
 }
 
-static void mlx5e_destroy_tirs(struct mlx5e_priv *priv)
+static void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv)
 {
-	int nch = mlx5e_get_max_num_channels(priv->mdev);
 	int i;
 
-	for (i = 0; i < nch; i++)
-		mlx5_core_destroy_tir(priv->mdev, priv->direct_tir[i].tirn);
-
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
-		mlx5_core_destroy_tir(priv->mdev, priv->indir_tirn[i]);
+		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[i]);
+}
+
+void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv)
+{
+	int nch = priv->profile->max_nch(priv->mdev);
+	int i;
+
+	for (i = 0; i < nch; i++)
+		mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[i]);
 }
 
 int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd)
@@ -2168,7 +2280,7 @@ mqprio:
 	return mlx5e_setup_tc(dev, tc->tc);
 }
 
-static struct rtnl_link_stats64 *
+struct rtnl_link_stats64 *
 mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
@@ -2520,25 +2632,31 @@ static int mlx5e_get_vf_stats(struct net_device *dev,
 }
 
 static void mlx5e_add_vxlan_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
+				 struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
 	if (!mlx5e_vxlan_allowed(priv->mdev))
 		return;
 
-	mlx5e_vxlan_queue_work(priv, sa_family, be16_to_cpu(port), 1);
+	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 1);
 }
 
 static void mlx5e_del_vxlan_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
+				 struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
 	if (!mlx5e_vxlan_allowed(priv->mdev))
 		return;
 
-	mlx5e_vxlan_queue_work(priv, sa_family, be16_to_cpu(port), 0);
+	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 0);
 }
 
 static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv,
@@ -2605,6 +2723,7 @@ static const struct net_device_ops mlx5e_netdev_ops_basic = {
 	.ndo_set_features        = mlx5e_set_features,
 	.ndo_change_mtu          = mlx5e_change_mtu,
 	.ndo_do_ioctl            = mlx5e_ioctl,
+	.ndo_set_tx_maxrate      = mlx5e_set_tx_maxrate,
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
 #endif
@@ -2624,8 +2743,9 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
 	.ndo_set_features        = mlx5e_set_features,
 	.ndo_change_mtu          = mlx5e_change_mtu,
 	.ndo_do_ioctl            = mlx5e_ioctl,
-	.ndo_add_vxlan_port      = mlx5e_add_vxlan_port,
-	.ndo_del_vxlan_port      = mlx5e_del_vxlan_port,
+	.ndo_udp_tunnel_add	 = mlx5e_add_vxlan_port,
+	.ndo_udp_tunnel_del	 = mlx5e_del_vxlan_port,
+	.ndo_set_tx_maxrate      = mlx5e_set_tx_maxrate,
 	.ndo_features_check      = mlx5e_features_check,
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
@@ -2754,13 +2874,31 @@ static bool cqe_compress_heuristic(u32 link_speed, u32 pci_bw)
 		(pci_bw < 40000) && (pci_bw < link_speed));
 }
 
-static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
-				    struct net_device *netdev,
-				    int num_channels)
+void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+{
+	params->rx_cq_period_mode = cq_period_mode;
+
+	params->rx_cq_moderation.pkts =
+		MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
+	params->rx_cq_moderation.usec =
+			MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC;
+
+	if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
+		params->rx_cq_moderation.usec =
+			MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE;
+}
+
+static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
+					struct net_device *netdev,
+					const struct mlx5e_profile *profile,
+					void *ppriv)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	u32 link_speed = 0;
 	u32 pci_bw = 0;
+	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
+					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
+					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
 	priv->params.log_sq_size           =
 		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
@@ -2806,13 +2944,13 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
 
 	priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
 					    BIT(priv->params.log_rq_size));
-	priv->params.rx_cq_moderation_usec =
-		MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC;
-	priv->params.rx_cq_moderation_pkts =
-		MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
-	priv->params.tx_cq_moderation_usec =
+
+	priv->params.rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	mlx5e_set_rx_cq_mode_params(&priv->params, cq_period_mode);
+
+	priv->params.tx_cq_moderation.usec =
 		MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
-	priv->params.tx_cq_moderation_pkts =
+	priv->params.tx_cq_moderation.pkts =
 		MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
 	priv->params.tx_max_inline         = mlx5e_get_max_inline_cap(mdev);
 	priv->params.num_tc                = 1;
@@ -2822,14 +2960,20 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
 			    sizeof(priv->params.toeplitz_hash_key));
 
 	mlx5e_build_default_indir_rqt(mdev, priv->params.indirection_rqt,
-				      MLX5E_INDIR_RQT_SIZE, num_channels);
+				      MLX5E_INDIR_RQT_SIZE, profile->max_nch(mdev));
 
 	priv->params.lro_wqe_sz            =
 		MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
 
+	/* Initialize pflags */
+	MLX5E_SET_PRIV_FLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER,
+			    priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
+
 	priv->mdev                         = mdev;
 	priv->netdev                       = netdev;
-	priv->params.num_channels          = num_channels;
+	priv->params.num_channels          = profile->max_nch(mdev);
+	priv->profile                      = profile;
+	priv->ppriv                        = ppriv;
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_ets_init(priv);
@@ -2854,7 +2998,11 @@ static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
 	}
 }
 
-static void mlx5e_build_netdev(struct net_device *netdev)
+static const struct switchdev_ops mlx5e_switchdev_ops = {
+	.switchdev_port_attr_get	= mlx5e_attr_get,
+};
+
+static void mlx5e_build_nic_netdev(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -2935,31 +3083,11 @@ static void mlx5e_build_netdev(struct net_device *netdev)
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
 	mlx5e_set_netdev_dev_addr(netdev);
-}
-
-static int mlx5e_create_mkey(struct mlx5e_priv *priv, u32 pdn,
-			     struct mlx5_core_mkey *mkey)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_create_mkey_mbox_in *in;
-	int err;
-
-	in = mlx5_vzalloc(sizeof(*in));
-	if (!in)
-		return -ENOMEM;
 
-	in->seg.flags = MLX5_PERM_LOCAL_WRITE |
-			MLX5_PERM_LOCAL_READ  |
-			MLX5_ACCESS_MODE_PA;
-	in->seg.flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64);
-	in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
-
-	err = mlx5_core_create_mkey(mdev, mkey, in, sizeof(*in), NULL, NULL,
-				    NULL);
-
-	kvfree(in);
-
-	return err;
+#ifdef CONFIG_NET_SWITCHDEV
+	if (MLX5_CAP_GEN(mdev, vport_group_manager))
+		netdev->switchdev_ops = &mlx5e_switchdev_ops;
+#endif
 }
 
 static void mlx5e_create_q_counter(struct mlx5e_priv *priv)
@@ -2989,7 +3117,7 @@ static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv)
 	struct mlx5_mkey_seg *mkc;
 	int inlen = sizeof(*in);
 	u64 npages =
-		mlx5e_get_max_num_channels(mdev) * MLX5_CHANNEL_MAX_NUM_MTTS;
+		priv->profile->max_nch(mdev) * MLX5_CHANNEL_MAX_NUM_MTTS;
 	int err;
 
 	in = mlx5_vzalloc(inlen);
@@ -3004,7 +3132,7 @@ static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv)
 		     MLX5_ACCESS_MODE_MTT;
 
 	mkc->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
-	mkc->flags_pd = cpu_to_be32(priv->pdn);
+	mkc->flags_pd = cpu_to_be32(mdev->mlx5e_res.pdn);
 	mkc->len = cpu_to_be64(npages << PAGE_SHIFT);
 	mkc->xlt_oct_size = cpu_to_be32(mlx5e_get_mtt_octw(npages));
 	mkc->log2_page_size = PAGE_SHIFT;
@@ -3017,160 +3145,233 @@ static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv)
 	return err;
 }
 
-static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev)
+static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
+			   struct net_device *netdev,
+			   const struct mlx5e_profile *profile,
+			   void *ppriv)
 {
-	struct net_device *netdev;
-	struct mlx5e_priv *priv;
-	int nch = mlx5e_get_max_num_channels(mdev);
-	int err;
-
-	if (mlx5e_check_required_hca_cap(mdev))
-		return NULL;
+	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv),
-				    nch * MLX5E_MAX_NUM_TC,
-				    nch);
-	if (!netdev) {
-		mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n");
-		return NULL;
-	}
+	mlx5e_build_nic_netdev_priv(mdev, netdev, profile, ppriv);
+	mlx5e_build_nic_netdev(netdev);
+	mlx5e_vxlan_init(priv);
+}
 
-	mlx5e_build_netdev_priv(mdev, netdev, nch);
-	mlx5e_build_netdev(netdev);
+static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
 
-	netif_carrier_off(netdev);
+	mlx5e_vxlan_cleanup(priv);
 
-	priv = netdev_priv(netdev);
+	if (MLX5_CAP_GEN(mdev, vport_group_manager))
+		mlx5_eswitch_unregister_vport_rep(esw, 0);
+}
 
-	priv->wq = create_singlethread_workqueue("mlx5e");
-	if (!priv->wq)
-		goto err_free_netdev;
+static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int err;
+	int i;
 
-	err = mlx5_alloc_map_uar(mdev, &priv->cq_uar, false);
+	err = mlx5e_create_indirect_rqts(priv);
 	if (err) {
-		mlx5_core_err(mdev, "alloc_map uar failed, %d\n", err);
-		goto err_destroy_wq;
+		mlx5_core_warn(mdev, "create indirect rqts failed, %d\n", err);
+		return err;
 	}
 
-	err = mlx5_core_alloc_pd(mdev, &priv->pdn);
+	err = mlx5e_create_direct_rqts(priv);
 	if (err) {
-		mlx5_core_err(mdev, "alloc pd failed, %d\n", err);
-		goto err_unmap_free_uar;
+		mlx5_core_warn(mdev, "create direct rqts failed, %d\n", err);
+		goto err_destroy_indirect_rqts;
 	}
 
-	err = mlx5_core_alloc_transport_domain(mdev, &priv->tdn);
+	err = mlx5e_create_indirect_tirs(priv);
 	if (err) {
-		mlx5_core_err(mdev, "alloc td failed, %d\n", err);
-		goto err_dealloc_pd;
+		mlx5_core_warn(mdev, "create indirect tirs failed, %d\n", err);
+		goto err_destroy_direct_rqts;
 	}
 
-	err = mlx5e_create_mkey(priv, priv->pdn, &priv->mkey);
+	err = mlx5e_create_direct_tirs(priv);
 	if (err) {
-		mlx5_core_err(mdev, "create mkey failed, %d\n", err);
-		goto err_dealloc_transport_domain;
+		mlx5_core_warn(mdev, "create direct tirs failed, %d\n", err);
+		goto err_destroy_indirect_tirs;
 	}
 
-	err = mlx5e_create_umr_mkey(priv);
+	err = mlx5e_create_flow_steering(priv);
 	if (err) {
-		mlx5_core_err(mdev, "create umr mkey failed, %d\n", err);
-		goto err_destroy_mkey;
+		mlx5_core_warn(mdev, "create flow steering failed, %d\n", err);
+		goto err_destroy_direct_tirs;
 	}
 
+	err = mlx5e_tc_init(priv);
+	if (err)
+		goto err_destroy_flow_steering;
+
+	return 0;
+
+err_destroy_flow_steering:
+	mlx5e_destroy_flow_steering(priv);
+err_destroy_direct_tirs:
+	mlx5e_destroy_direct_tirs(priv);
+err_destroy_indirect_tirs:
+	mlx5e_destroy_indirect_tirs(priv);
+err_destroy_direct_rqts:
+	for (i = 0; i < priv->profile->max_nch(mdev); i++)
+		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+err_destroy_indirect_rqts:
+	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+	return err;
+}
+
+static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
+{
+	int i;
+
+	mlx5e_tc_cleanup(priv);
+	mlx5e_destroy_flow_steering(priv);
+	mlx5e_destroy_direct_tirs(priv);
+	mlx5e_destroy_indirect_tirs(priv);
+	for (i = 0; i < priv->profile->max_nch(priv->mdev); i++)
+		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+}
+
+static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
+{
+	int err;
+
 	err = mlx5e_create_tises(priv);
 	if (err) {
-		mlx5_core_warn(mdev, "create tises failed, %d\n", err);
-		goto err_destroy_umr_mkey;
+		mlx5_core_warn(priv->mdev, "create tises failed, %d\n", err);
+		return err;
 	}
 
-	err = mlx5e_open_drop_rq(priv);
-	if (err) {
-		mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
-		goto err_destroy_tises;
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+	mlx5e_dcbnl_ieee_setets_core(priv, &priv->params.ets);
+#endif
+	return 0;
+}
+
+static void mlx5e_nic_enable(struct mlx5e_priv *priv)
+{
+	struct net_device *netdev = priv->netdev;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	struct mlx5_eswitch_rep rep;
+
+	if (mlx5e_vxlan_allowed(mdev)) {
+		rtnl_lock();
+		udp_tunnel_get_rx_info(netdev);
+		rtnl_unlock();
 	}
 
-	err = mlx5e_create_rqts(priv);
-	if (err) {
-		mlx5_core_warn(mdev, "create rqts failed, %d\n", err);
-		goto err_close_drop_rq;
+	mlx5e_enable_async_events(priv);
+	queue_work(priv->wq, &priv->set_rx_mode_work);
+
+	if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
+		rep.load = mlx5e_nic_rep_load;
+		rep.unload = mlx5e_nic_rep_unload;
+		rep.vport = 0;
+		rep.priv_data = priv;
+		mlx5_eswitch_register_vport_rep(esw, &rep);
 	}
+}
 
-	err = mlx5e_create_tirs(priv);
-	if (err) {
-		mlx5_core_warn(mdev, "create tirs failed, %d\n", err);
-		goto err_destroy_rqts;
+static void mlx5e_nic_disable(struct mlx5e_priv *priv)
+{
+	queue_work(priv->wq, &priv->set_rx_mode_work);
+	mlx5e_disable_async_events(priv);
+}
+
+static const struct mlx5e_profile mlx5e_nic_profile = {
+	.init		   = mlx5e_nic_init,
+	.cleanup	   = mlx5e_nic_cleanup,
+	.init_rx	   = mlx5e_init_nic_rx,
+	.cleanup_rx	   = mlx5e_cleanup_nic_rx,
+	.init_tx	   = mlx5e_init_nic_tx,
+	.cleanup_tx	   = mlx5e_cleanup_nic_tx,
+	.enable		   = mlx5e_nic_enable,
+	.disable	   = mlx5e_nic_disable,
+	.update_stats	   = mlx5e_update_stats,
+	.max_nch	   = mlx5e_get_max_num_channels,
+	.max_tc		   = MLX5E_MAX_NUM_TC,
+};
+
+void *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
+			  const struct mlx5e_profile *profile, void *ppriv)
+{
+	struct net_device *netdev;
+	struct mlx5e_priv *priv;
+	int nch = profile->max_nch(mdev);
+	int err;
+
+	netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv),
+				    nch * profile->max_tc,
+				    nch);
+	if (!netdev) {
+		mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n");
+		return NULL;
 	}
 
-	err = mlx5e_create_flow_steering(priv);
+	profile->init(mdev, netdev, profile, ppriv);
+
+	netif_carrier_off(netdev);
+
+	priv = netdev_priv(netdev);
+
+	priv->wq = create_singlethread_workqueue("mlx5e");
+	if (!priv->wq)
+		goto err_free_netdev;
+
+	err = mlx5e_create_umr_mkey(priv);
 	if (err) {
-		mlx5_core_warn(mdev, "create flow steering failed, %d\n", err);
-		goto err_destroy_tirs;
+		mlx5_core_err(mdev, "create umr mkey failed, %d\n", err);
+		goto err_destroy_wq;
 	}
 
-	mlx5e_create_q_counter(priv);
-
-	mlx5e_init_l2_addr(priv);
+	err = profile->init_tx(priv);
+	if (err)
+		goto err_destroy_umr_mkey;
 
-	mlx5e_vxlan_init(priv);
+	err = mlx5e_open_drop_rq(priv);
+	if (err) {
+		mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
+		goto err_cleanup_tx;
+	}
 
-	err = mlx5e_tc_init(priv);
+	err = profile->init_rx(priv);
 	if (err)
-		goto err_dealloc_q_counters;
+		goto err_close_drop_rq;
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
-	mlx5e_dcbnl_ieee_setets_core(priv, &priv->params.ets);
-#endif
+	mlx5e_create_q_counter(priv);
+
+	mlx5e_init_l2_addr(priv);
 
 	err = register_netdev(netdev);
 	if (err) {
 		mlx5_core_err(mdev, "register_netdev failed, %d\n", err);
-		goto err_tc_cleanup;
-	}
-
-	if (mlx5e_vxlan_allowed(mdev)) {
-		rtnl_lock();
-		vxlan_get_rx_port(netdev);
-		rtnl_unlock();
+		goto err_dealloc_q_counters;
 	}
 
-	mlx5e_enable_async_events(priv);
-	queue_work(priv->wq, &priv->set_rx_mode_work);
+	if (profile->enable)
+		profile->enable(priv);
 
 	return priv;
 
-err_tc_cleanup:
-	mlx5e_tc_cleanup(priv);
-
 err_dealloc_q_counters:
 	mlx5e_destroy_q_counter(priv);
-	mlx5e_destroy_flow_steering(priv);
-
-err_destroy_tirs:
-	mlx5e_destroy_tirs(priv);
-
-err_destroy_rqts:
-	mlx5e_destroy_rqts(priv);
+	profile->cleanup_rx(priv);
 
 err_close_drop_rq:
 	mlx5e_close_drop_rq(priv);
 
-err_destroy_tises:
-	mlx5e_destroy_tises(priv);
+err_cleanup_tx:
+	profile->cleanup_tx(priv);
 
 err_destroy_umr_mkey:
 	mlx5_core_destroy_mkey(mdev, &priv->umr_mkey);
 
-err_destroy_mkey:
-	mlx5_core_destroy_mkey(mdev, &priv->mkey);
-
-err_dealloc_transport_domain:
-	mlx5_core_dealloc_transport_domain(mdev, priv->tdn);
-
-err_dealloc_pd:
-	mlx5_core_dealloc_pd(mdev, priv->pdn);
-
-err_unmap_free_uar:
-	mlx5_unmap_free_uar(mdev, &priv->cq_uar);
-
 err_destroy_wq:
 	destroy_workqueue(priv->wq);
 
@@ -3180,46 +3381,96 @@ err_free_netdev:
 	return NULL;
 }
 
-static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv)
+static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev)
 {
-	struct mlx5e_priv *priv = vpriv;
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
+	int vport;
+
+	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
+		return;
+
+	for (vport = 1; vport < total_vfs; vport++) {
+		struct mlx5_eswitch_rep rep;
+
+		rep.load = mlx5e_vport_rep_load;
+		rep.unload = mlx5e_vport_rep_unload;
+		rep.vport = vport;
+		mlx5_eswitch_register_vport_rep(esw, &rep);
+	}
+}
+
+static void *mlx5e_add(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	void *ppriv = NULL;
+	void *ret;
+
+	if (mlx5e_check_required_hca_cap(mdev))
+		return NULL;
+
+	if (mlx5e_create_mdev_resources(mdev))
+		return NULL;
+
+	mlx5e_register_vport_rep(mdev);
+
+	if (MLX5_CAP_GEN(mdev, vport_group_manager))
+		ppriv = &esw->offloads.vport_reps[0];
+
+	ret = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, ppriv);
+	if (!ret) {
+		mlx5e_destroy_mdev_resources(mdev);
+		return NULL;
+	}
+	return ret;
+}
+
+void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv)
+{
+	const struct mlx5e_profile *profile = priv->profile;
 	struct net_device *netdev = priv->netdev;
 
 	set_bit(MLX5E_STATE_DESTROYING, &priv->state);
+	if (profile->disable)
+		profile->disable(priv);
 
-	queue_work(priv->wq, &priv->set_rx_mode_work);
-	mlx5e_disable_async_events(priv);
 	flush_workqueue(priv->wq);
 	if (test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state)) {
 		netif_device_detach(netdev);
-		mutex_lock(&priv->state_lock);
-		if (test_bit(MLX5E_STATE_OPENED, &priv->state))
-			mlx5e_close_locked(netdev);
-		mutex_unlock(&priv->state_lock);
+		mlx5e_close(netdev);
 	} else {
 		unregister_netdev(netdev);
 	}
 
-	mlx5e_tc_cleanup(priv);
-	mlx5e_vxlan_cleanup(priv);
 	mlx5e_destroy_q_counter(priv);
-	mlx5e_destroy_flow_steering(priv);
-	mlx5e_destroy_tirs(priv);
-	mlx5e_destroy_rqts(priv);
+	profile->cleanup_rx(priv);
 	mlx5e_close_drop_rq(priv);
-	mlx5e_destroy_tises(priv);
+	profile->cleanup_tx(priv);
 	mlx5_core_destroy_mkey(priv->mdev, &priv->umr_mkey);
-	mlx5_core_destroy_mkey(priv->mdev, &priv->mkey);
-	mlx5_core_dealloc_transport_domain(priv->mdev, priv->tdn);
-	mlx5_core_dealloc_pd(priv->mdev, priv->pdn);
-	mlx5_unmap_free_uar(priv->mdev, &priv->cq_uar);
 	cancel_delayed_work_sync(&priv->update_stats_work);
 	destroy_workqueue(priv->wq);
+	if (profile->cleanup)
+		profile->cleanup(priv);
 
 	if (!test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state))
 		free_netdev(netdev);
 }
 
+static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
+	struct mlx5e_priv *priv = vpriv;
+	int vport;
+
+	mlx5e_destroy_netdev(mdev, priv);
+
+	for (vport = 1; vport < total_vfs; vport++)
+		mlx5_eswitch_unregister_vport_rep(esw, vport);
+
+	mlx5e_destroy_mdev_resources(mdev);
+}
+
 static void *mlx5e_get_netdev(void *vpriv)
 {
 	struct mlx5e_priv *priv = vpriv;
@@ -3228,8 +3479,8 @@ static void *mlx5e_get_netdev(void *vpriv)
 }
 
 static struct mlx5_interface mlx5e_interface = {
-	.add       = mlx5e_create_netdev,
-	.remove    = mlx5e_destroy_netdev,
+	.add       = mlx5e_add,
+	.remove    = mlx5e_remove,
 	.event     = mlx5e_async_event,
 	.protocol  = MLX5_INTERFACE_PROTOCOL_ETH,
 	.get_dev   = mlx5e_get_netdev,
@@ -3237,6 +3488,7 @@ static struct mlx5_interface mlx5e_interface = {
 
 void mlx5e_init(void)
 {
+	mlx5e_build_ptys2ethtool_map();
 	mlx5_register_interface(&mlx5e_interface);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
new file mode 100644
index 000000000000..5ef02f02a1d5
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -0,0 +1,394 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <generated/utsrelease.h>
+#include <linux/mlx5/fs.h>
+#include <net/switchdev.h>
+
+#include "eswitch.h"
+#include "en.h"
+
+static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
+
+static void mlx5e_rep_get_drvinfo(struct net_device *dev,
+				  struct ethtool_drvinfo *drvinfo)
+{
+	strlcpy(drvinfo->driver, mlx5e_rep_driver_name,
+		sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, UTS_RELEASE, sizeof(drvinfo->version));
+}
+
+static const struct counter_desc sw_rep_stats_desc[] = {
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) },
+};
+
+#define NUM_VPORT_REP_COUNTERS	ARRAY_SIZE(sw_rep_stats_desc)
+
+static void mlx5e_rep_get_strings(struct net_device *dev,
+				  u32 stringset, uint8_t *data)
+{
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++)
+			strcpy(data + (i * ETH_GSTRING_LEN),
+			       sw_rep_stats_desc[i].format);
+		break;
+	}
+}
+
+static void mlx5e_update_sw_rep_counters(struct mlx5e_priv *priv)
+{
+	struct mlx5e_sw_stats *s = &priv->stats.sw;
+	struct mlx5e_rq_stats *rq_stats;
+	struct mlx5e_sq_stats *sq_stats;
+	int i, j;
+
+	memset(s, 0, sizeof(*s));
+	for (i = 0; i < priv->params.num_channels; i++) {
+		rq_stats = &priv->channel[i]->rq.stats;
+
+		s->rx_packets	+= rq_stats->packets;
+		s->rx_bytes	+= rq_stats->bytes;
+
+		for (j = 0; j < priv->params.num_tc; j++) {
+			sq_stats = &priv->channel[i]->sq[j].stats;
+
+			s->tx_packets		+= sq_stats->packets;
+			s->tx_bytes		+= sq_stats->bytes;
+		}
+	}
+}
+
+static void mlx5e_rep_get_ethtool_stats(struct net_device *dev,
+					struct ethtool_stats *stats, u64 *data)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int i;
+
+	if (!data)
+		return;
+
+	mutex_lock(&priv->state_lock);
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+		mlx5e_update_sw_rep_counters(priv);
+	mutex_unlock(&priv->state_lock);
+
+	for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++)
+		data[i] = MLX5E_READ_CTR64_CPU(&priv->stats.sw,
+					       sw_rep_stats_desc, i);
+}
+
+static int mlx5e_rep_get_sset_count(struct net_device *dev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return NUM_VPORT_REP_COUNTERS;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct ethtool_ops mlx5e_rep_ethtool_ops = {
+	.get_drvinfo	   = mlx5e_rep_get_drvinfo,
+	.get_link	   = ethtool_op_get_link,
+	.get_strings       = mlx5e_rep_get_strings,
+	.get_sset_count    = mlx5e_rep_get_sset_count,
+	.get_ethtool_stats = mlx5e_rep_get_ethtool_stats,
+};
+
+int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	u8 mac[ETH_ALEN];
+
+	if (esw->mode == SRIOV_NONE)
+		return -EOPNOTSUPP;
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
+		mlx5_query_nic_vport_mac_address(priv->mdev, 0, mac);
+		attr->u.ppid.id_len = ETH_ALEN;
+		memcpy(&attr->u.ppid.id, &mac, ETH_ALEN);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv)
+
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5e_channel *c;
+	int n, tc, err, num_sqs = 0;
+	u16 *sqs;
+
+	sqs = kcalloc(priv->params.num_channels * priv->params.num_tc, sizeof(u16), GFP_KERNEL);
+	if (!sqs)
+		return -ENOMEM;
+
+	for (n = 0; n < priv->params.num_channels; n++) {
+		c = priv->channel[n];
+		for (tc = 0; tc < c->num_tc; tc++)
+			sqs[num_sqs++] = c->sq[tc].sqn;
+	}
+
+	err = mlx5_eswitch_sqs2vport_start(esw, rep, sqs, num_sqs);
+
+	kfree(sqs);
+	return err;
+}
+
+int mlx5e_nic_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5e_priv *priv = rep->priv_data;
+
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+		return mlx5e_add_sqs_fwd_rules(priv);
+	return 0;
+}
+
+void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_eswitch_rep *rep = priv->ppriv;
+
+	mlx5_eswitch_sqs2vport_stop(esw, rep);
+}
+
+void mlx5e_nic_rep_unload(struct mlx5_eswitch *esw,
+			  struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5e_priv *priv = rep->priv_data;
+
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+		mlx5e_remove_sqs_fwd_rules(priv);
+}
+
+static int mlx5e_rep_get_phys_port_name(struct net_device *dev,
+					char *buf, size_t len)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	int ret;
+
+	ret = snprintf(buf, len, "%d", rep->vport - 1);
+	if (ret >= len)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static const struct switchdev_ops mlx5e_rep_switchdev_ops = {
+	.switchdev_port_attr_get	= mlx5e_attr_get,
+};
+
+static const struct net_device_ops mlx5e_netdev_ops_rep = {
+	.ndo_open                = mlx5e_open,
+	.ndo_stop                = mlx5e_close,
+	.ndo_start_xmit          = mlx5e_xmit,
+	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
+	.ndo_get_stats64         = mlx5e_get_stats,
+};
+
+static void mlx5e_build_rep_netdev_priv(struct mlx5_core_dev *mdev,
+					struct net_device *netdev,
+					const struct mlx5e_profile *profile,
+					void *ppriv)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
+					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
+					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+
+	priv->params.log_sq_size           =
+		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	priv->params.rq_wq_type = MLX5_WQ_TYPE_LINKED_LIST;
+	priv->params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+
+	priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
+					    BIT(priv->params.log_rq_size));
+
+	priv->params.rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	mlx5e_set_rx_cq_mode_params(&priv->params, cq_period_mode);
+
+	priv->params.tx_max_inline         = mlx5e_get_max_inline_cap(mdev);
+	priv->params.num_tc                = 1;
+
+	priv->params.lro_wqe_sz            =
+		MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
+
+	priv->mdev                         = mdev;
+	priv->netdev                       = netdev;
+	priv->params.num_channels          = profile->max_nch(mdev);
+	priv->profile                      = profile;
+	priv->ppriv                        = ppriv;
+
+	mutex_init(&priv->state_lock);
+
+	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
+}
+
+static void mlx5e_build_rep_netdev(struct net_device *netdev)
+{
+	netdev->netdev_ops = &mlx5e_netdev_ops_rep;
+
+	netdev->watchdog_timeo    = 15 * HZ;
+
+	netdev->ethtool_ops	  = &mlx5e_rep_ethtool_ops;
+
+#ifdef CONFIG_NET_SWITCHDEV
+	netdev->switchdev_ops = &mlx5e_rep_switchdev_ops;
+#endif
+
+	netdev->features	 |= NETIF_F_VLAN_CHALLENGED;
+
+	eth_hw_addr_random(netdev);
+}
+
+static void mlx5e_init_rep(struct mlx5_core_dev *mdev,
+			   struct net_device *netdev,
+			   const struct mlx5e_profile *profile,
+			   void *ppriv)
+{
+	mlx5e_build_rep_netdev_priv(mdev, netdev, profile, ppriv);
+	mlx5e_build_rep_netdev(netdev);
+}
+
+static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_flow_rule *flow_rule;
+	int err;
+	int i;
+
+	err = mlx5e_create_direct_rqts(priv);
+	if (err) {
+		mlx5_core_warn(mdev, "create direct rqts failed, %d\n", err);
+		return err;
+	}
+
+	err = mlx5e_create_direct_tirs(priv);
+	if (err) {
+		mlx5_core_warn(mdev, "create direct tirs failed, %d\n", err);
+		goto err_destroy_direct_rqts;
+	}
+
+	flow_rule = mlx5_eswitch_create_vport_rx_rule(esw,
+						      rep->vport,
+						      priv->direct_tir[0].tirn);
+	if (IS_ERR(flow_rule)) {
+		err = PTR_ERR(flow_rule);
+		goto err_destroy_direct_tirs;
+	}
+	rep->vport_rx_rule = flow_rule;
+
+	return 0;
+
+err_destroy_direct_tirs:
+	mlx5e_destroy_direct_tirs(priv);
+err_destroy_direct_rqts:
+	for (i = 0; i < priv->params.num_channels; i++)
+		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+	return err;
+}
+
+static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
+{
+	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	int i;
+
+	mlx5_del_flow_rule(rep->vport_rx_rule);
+	mlx5e_destroy_direct_tirs(priv);
+	for (i = 0; i < priv->params.num_channels; i++)
+		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+}
+
+static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
+{
+	int err;
+
+	err = mlx5e_create_tises(priv);
+	if (err) {
+		mlx5_core_warn(priv->mdev, "create tises failed, %d\n", err);
+		return err;
+	}
+	return 0;
+}
+
+static int mlx5e_get_rep_max_num_channels(struct mlx5_core_dev *mdev)
+{
+#define	MLX5E_PORT_REPRESENTOR_NCH 1
+	return MLX5E_PORT_REPRESENTOR_NCH;
+}
+
+static struct mlx5e_profile mlx5e_rep_profile = {
+	.init			= mlx5e_init_rep,
+	.init_rx		= mlx5e_init_rep_rx,
+	.cleanup_rx		= mlx5e_cleanup_rep_rx,
+	.init_tx		= mlx5e_init_rep_tx,
+	.cleanup_tx		= mlx5e_cleanup_nic_tx,
+	.update_stats           = mlx5e_update_sw_rep_counters,
+	.max_nch		= mlx5e_get_rep_max_num_channels,
+	.max_tc			= 1,
+};
+
+int mlx5e_vport_rep_load(struct mlx5_eswitch *esw,
+			 struct mlx5_eswitch_rep *rep)
+{
+	rep->priv_data = mlx5e_create_netdev(esw->dev, &mlx5e_rep_profile, rep);
+	if (!rep->priv_data) {
+		pr_warn("Failed to create representor for vport %d\n",
+			rep->vport);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+void mlx5e_vport_rep_unload(struct mlx5_eswitch *esw,
+			    struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5e_priv *priv = rep->priv_data;
+
+	mlx5e_destroy_netdev(esw->dev, priv);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index bd947704b59c..022acc2e8922 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -689,7 +689,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 	if (is_first_ethertype_ip(skb)) {
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
-		rq->stats.csum_sw++;
+		rq->stats.csum_complete++;
 		return;
 	}
 
@@ -699,7 +699,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		if (cqe_is_tunneled(cqe)) {
 			skb->csum_level = 1;
 			skb->encapsulation = 1;
-			rq->stats.csum_inner++;
+			rq->stats.csum_unnecessary_inner++;
 		}
 		return;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
new file mode 100644
index 000000000000..1fffe48a93cc
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
@@ -0,0 +1,335 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "en.h"
+
+/* Adaptive moderation profiles */
+#define MLX5E_AM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256
+#define MLX5E_RX_AM_DEF_PROFILE_CQE 1
+#define MLX5E_RX_AM_DEF_PROFILE_EQE 1
+#define MLX5E_PARAMS_AM_NUM_PROFILES 5
+
+/* All profiles sizes must be MLX5E_PARAMS_AM_NUM_PROFILES */
+#define MLX5_AM_EQE_PROFILES { \
+	{1,   MLX5E_AM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+	{8,   MLX5E_AM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+	{64,  MLX5E_AM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+	{128, MLX5E_AM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+	{256, MLX5E_AM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+}
+
+#define MLX5_AM_CQE_PROFILES { \
+	{2,  256},             \
+	{8,  128},             \
+	{16, 64},              \
+	{32, 64},              \
+	{64, 64}               \
+}
+
+static const struct mlx5e_cq_moder
+profile[MLX5_CQ_PERIOD_NUM_MODES][MLX5E_PARAMS_AM_NUM_PROFILES] = {
+	MLX5_AM_EQE_PROFILES,
+	MLX5_AM_CQE_PROFILES,
+};
+
+static inline struct mlx5e_cq_moder mlx5e_am_get_profile(u8 cq_period_mode, int ix)
+{
+	return profile[cq_period_mode][ix];
+}
+
+struct mlx5e_cq_moder mlx5e_am_get_def_profile(u8 rx_cq_period_mode)
+{
+	int default_profile_ix;
+
+	if (rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
+		default_profile_ix = MLX5E_RX_AM_DEF_PROFILE_CQE;
+	else /* MLX5_CQ_PERIOD_MODE_START_FROM_EQE */
+		default_profile_ix = MLX5E_RX_AM_DEF_PROFILE_EQE;
+
+	return profile[rx_cq_period_mode][default_profile_ix];
+}
+
+/* Adaptive moderation logic */
+enum {
+	MLX5E_AM_START_MEASURE,
+	MLX5E_AM_MEASURE_IN_PROGRESS,
+	MLX5E_AM_APPLY_NEW_PROFILE,
+};
+
+enum {
+	MLX5E_AM_PARKING_ON_TOP,
+	MLX5E_AM_PARKING_TIRED,
+	MLX5E_AM_GOING_RIGHT,
+	MLX5E_AM_GOING_LEFT,
+};
+
+enum {
+	MLX5E_AM_STATS_WORSE,
+	MLX5E_AM_STATS_SAME,
+	MLX5E_AM_STATS_BETTER,
+};
+
+enum {
+	MLX5E_AM_STEPPED,
+	MLX5E_AM_TOO_TIRED,
+	MLX5E_AM_ON_EDGE,
+};
+
+static bool mlx5e_am_on_top(struct mlx5e_rx_am *am)
+{
+	switch (am->tune_state) {
+	case MLX5E_AM_PARKING_ON_TOP:
+	case MLX5E_AM_PARKING_TIRED:
+		WARN_ONCE(true, "mlx5e_am_on_top: PARKING\n");
+		return true;
+	case MLX5E_AM_GOING_RIGHT:
+		return (am->steps_left > 1) && (am->steps_right == 1);
+	default: /* MLX5E_AM_GOING_LEFT */
+		return (am->steps_right > 1) && (am->steps_left == 1);
+	}
+}
+
+static void mlx5e_am_turn(struct mlx5e_rx_am *am)
+{
+	switch (am->tune_state) {
+	case MLX5E_AM_PARKING_ON_TOP:
+	case MLX5E_AM_PARKING_TIRED:
+		WARN_ONCE(true, "mlx5e_am_turn: PARKING\n");
+		break;
+	case MLX5E_AM_GOING_RIGHT:
+		am->tune_state = MLX5E_AM_GOING_LEFT;
+		am->steps_left = 0;
+		break;
+	case MLX5E_AM_GOING_LEFT:
+		am->tune_state = MLX5E_AM_GOING_RIGHT;
+		am->steps_right = 0;
+		break;
+	}
+}
+
+static int mlx5e_am_step(struct mlx5e_rx_am *am)
+{
+	if (am->tired == (MLX5E_PARAMS_AM_NUM_PROFILES * 2))
+		return MLX5E_AM_TOO_TIRED;
+
+	switch (am->tune_state) {
+	case MLX5E_AM_PARKING_ON_TOP:
+	case MLX5E_AM_PARKING_TIRED:
+		WARN_ONCE(true, "mlx5e_am_step: PARKING\n");
+		break;
+	case MLX5E_AM_GOING_RIGHT:
+		if (am->profile_ix == (MLX5E_PARAMS_AM_NUM_PROFILES - 1))
+			return MLX5E_AM_ON_EDGE;
+		am->profile_ix++;
+		am->steps_right++;
+		break;
+	case MLX5E_AM_GOING_LEFT:
+		if (am->profile_ix == 0)
+			return MLX5E_AM_ON_EDGE;
+		am->profile_ix--;
+		am->steps_left++;
+		break;
+	}
+
+	am->tired++;
+	return MLX5E_AM_STEPPED;
+}
+
+static void mlx5e_am_park_on_top(struct mlx5e_rx_am *am)
+{
+	am->steps_right  = 0;
+	am->steps_left   = 0;
+	am->tired        = 0;
+	am->tune_state   = MLX5E_AM_PARKING_ON_TOP;
+}
+
+static void mlx5e_am_park_tired(struct mlx5e_rx_am *am)
+{
+	am->steps_right  = 0;
+	am->steps_left   = 0;
+	am->tune_state   = MLX5E_AM_PARKING_TIRED;
+}
+
+static void mlx5e_am_exit_parking(struct mlx5e_rx_am *am)
+{
+	am->tune_state = am->profile_ix ? MLX5E_AM_GOING_LEFT :
+					  MLX5E_AM_GOING_RIGHT;
+	mlx5e_am_step(am);
+}
+
+static int mlx5e_am_stats_compare(struct mlx5e_rx_am_stats *curr,
+				  struct mlx5e_rx_am_stats *prev)
+{
+	int diff;
+
+	if (!prev->ppms)
+		return curr->ppms ? MLX5E_AM_STATS_BETTER :
+				    MLX5E_AM_STATS_SAME;
+
+	diff = curr->ppms - prev->ppms;
+	if (((100 * abs(diff)) / prev->ppms) > 10) /* more than 10% diff */
+		return (diff > 0) ? MLX5E_AM_STATS_BETTER :
+				    MLX5E_AM_STATS_WORSE;
+
+	if (!prev->epms)
+		return curr->epms ? MLX5E_AM_STATS_WORSE :
+				    MLX5E_AM_STATS_SAME;
+
+	diff = curr->epms - prev->epms;
+	if (((100 * abs(diff)) / prev->epms) > 10) /* more than 10% diff */
+		return (diff < 0) ? MLX5E_AM_STATS_BETTER :
+				    MLX5E_AM_STATS_WORSE;
+
+	return MLX5E_AM_STATS_SAME;
+}
+
+static bool mlx5e_am_decision(struct mlx5e_rx_am_stats *curr_stats,
+			      struct mlx5e_rx_am *am)
+{
+	int prev_state = am->tune_state;
+	int prev_ix = am->profile_ix;
+	int stats_res;
+	int step_res;
+
+	switch (am->tune_state) {
+	case MLX5E_AM_PARKING_ON_TOP:
+		stats_res = mlx5e_am_stats_compare(curr_stats, &am->prev_stats);
+		if (stats_res != MLX5E_AM_STATS_SAME)
+			mlx5e_am_exit_parking(am);
+		break;
+
+	case MLX5E_AM_PARKING_TIRED:
+		am->tired--;
+		if (!am->tired)
+			mlx5e_am_exit_parking(am);
+		break;
+
+	case MLX5E_AM_GOING_RIGHT:
+	case MLX5E_AM_GOING_LEFT:
+		stats_res = mlx5e_am_stats_compare(curr_stats, &am->prev_stats);
+		if (stats_res != MLX5E_AM_STATS_BETTER)
+			mlx5e_am_turn(am);
+
+		if (mlx5e_am_on_top(am)) {
+			mlx5e_am_park_on_top(am);
+			break;
+		}
+
+		step_res = mlx5e_am_step(am);
+		switch (step_res) {
+		case MLX5E_AM_ON_EDGE:
+			mlx5e_am_park_on_top(am);
+			break;
+		case MLX5E_AM_TOO_TIRED:
+			mlx5e_am_park_tired(am);
+			break;
+		}
+
+		break;
+	}
+
+	if ((prev_state     != MLX5E_AM_PARKING_ON_TOP) ||
+	    (am->tune_state != MLX5E_AM_PARKING_ON_TOP))
+		am->prev_stats = *curr_stats;
+
+	return am->profile_ix != prev_ix;
+}
+
+static void mlx5e_am_sample(struct mlx5e_rq *rq,
+			    struct mlx5e_rx_am_sample *s)
+{
+	s->time	     = ktime_get();
+	s->pkt_ctr   = rq->stats.packets;
+	s->event_ctr = rq->cq.event_ctr;
+}
+
+#define MLX5E_AM_NEVENTS 64
+
+static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start,
+				struct mlx5e_rx_am_sample *end,
+				struct mlx5e_rx_am_stats *curr_stats)
+{
+	/* u32 holds up to 71 minutes, should be enough */
+	u32 delta_us = ktime_us_delta(end->time, start->time);
+	unsigned int npkts = end->pkt_ctr - start->pkt_ctr;
+
+	if (!delta_us) {
+		WARN_ONCE(true, "mlx5e_am_calc_stats: delta_us=0\n");
+		return;
+	}
+
+	curr_stats->ppms =            (npkts * USEC_PER_MSEC) / delta_us;
+	curr_stats->epms = (MLX5E_AM_NEVENTS * USEC_PER_MSEC) / delta_us;
+}
+
+void mlx5e_rx_am_work(struct work_struct *work)
+{
+	struct mlx5e_rx_am *am = container_of(work, struct mlx5e_rx_am,
+					      work);
+	struct mlx5e_rq *rq = container_of(am, struct mlx5e_rq, am);
+	struct mlx5e_cq_moder cur_profile = profile[am->mode][am->profile_ix];
+
+	mlx5_core_modify_cq_moderation(rq->priv->mdev, &rq->cq.mcq,
+				       cur_profile.usec, cur_profile.pkts);
+
+	am->state = MLX5E_AM_START_MEASURE;
+}
+
+void mlx5e_rx_am(struct mlx5e_rq *rq)
+{
+	struct mlx5e_rx_am *am = &rq->am;
+	struct mlx5e_rx_am_sample end_sample;
+	struct mlx5e_rx_am_stats curr_stats;
+	u16 nevents;
+
+	switch (am->state) {
+	case MLX5E_AM_MEASURE_IN_PROGRESS:
+		nevents = rq->cq.event_ctr - am->start_sample.event_ctr;
+		if (nevents < MLX5E_AM_NEVENTS)
+			break;
+		mlx5e_am_sample(rq, &end_sample);
+		mlx5e_am_calc_stats(&am->start_sample, &end_sample,
+				    &curr_stats);
+		if (mlx5e_am_decision(&curr_stats, am)) {
+			am->state = MLX5E_AM_APPLY_NEW_PROFILE;
+			schedule_work(&am->work);
+			break;
+		}
+		/* fall through */
+	case MLX5E_AM_START_MEASURE:
+		mlx5e_am_sample(rq, &am->start_sample);
+		am->state = MLX5E_AM_MEASURE_IN_PROGRESS;
+		break;
+	case MLX5E_AM_APPLY_NEW_PROFILE:
+		break;
+	}
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 83bc32b25849..7b9d8a989b52 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -42,9 +42,11 @@
 	be64_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset))
 
 #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld)
+#define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld)
 
 struct counter_desc {
-	char		name[ETH_GSTRING_LEN];
+	char		format[ETH_GSTRING_LEN];
 	int		offset; /* Byte offset */
 };
 
@@ -53,18 +55,18 @@ struct mlx5e_sw_stats {
 	u64 rx_bytes;
 	u64 tx_packets;
 	u64 tx_bytes;
-	u64 tso_packets;
-	u64 tso_bytes;
-	u64 tso_inner_packets;
-	u64 tso_inner_bytes;
-	u64 lro_packets;
-	u64 lro_bytes;
-	u64 rx_csum_good;
+	u64 tx_tso_packets;
+	u64 tx_tso_bytes;
+	u64 tx_tso_inner_packets;
+	u64 tx_tso_inner_bytes;
+	u64 rx_lro_packets;
+	u64 rx_lro_bytes;
+	u64 rx_csum_unnecessary;
 	u64 rx_csum_none;
-	u64 rx_csum_sw;
-	u64 rx_csum_inner;
-	u64 tx_csum_offload;
-	u64 tx_csum_inner;
+	u64 rx_csum_complete;
+	u64 rx_csum_unnecessary_inner;
+	u64 tx_csum_partial;
+	u64 tx_csum_partial_inner;
 	u64 tx_queue_stopped;
 	u64 tx_queue_wake;
 	u64 tx_queue_dropped;
@@ -76,7 +78,7 @@ struct mlx5e_sw_stats {
 	u64 rx_cqe_compress_pkts;
 
 	/* Special handling counters */
-	u64 link_down_events;
+	u64 link_down_events_phy;
 };
 
 static const struct counter_desc sw_stats_desc[] = {
@@ -84,18 +86,18 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_inner_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_inner_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, lro_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, lro_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_good) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_sw) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_inner) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_offload) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_inner) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
@@ -105,7 +107,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events_phy) },
 };
 
 struct mlx5e_qcounter_stats {
@@ -125,12 +127,6 @@ struct mlx5e_vport_stats {
 };
 
 static const struct counter_desc vport_stats_desc[] = {
-	{ "rx_vport_error_packets",
-		VPORT_COUNTER_OFF(received_errors.packets) },
-	{ "rx_vport_error_bytes", VPORT_COUNTER_OFF(received_errors.octets) },
-	{ "tx_vport_error_packets",
-		VPORT_COUNTER_OFF(transmit_errors.packets) },
-	{ "tx_vport_error_bytes", VPORT_COUNTER_OFF(transmit_errors.octets) },
 	{ "rx_vport_unicast_packets",
 		VPORT_COUNTER_OFF(received_eth_unicast.packets) },
 	{ "rx_vport_unicast_bytes",
@@ -155,6 +151,22 @@ static const struct counter_desc vport_stats_desc[] = {
 		VPORT_COUNTER_OFF(transmitted_eth_broadcast.packets) },
 	{ "tx_vport_broadcast_bytes",
 		VPORT_COUNTER_OFF(transmitted_eth_broadcast.octets) },
+	{ "rx_vport_rdma_unicast_packets",
+		VPORT_COUNTER_OFF(received_ib_unicast.packets) },
+	{ "rx_vport_rdma_unicast_bytes",
+		VPORT_COUNTER_OFF(received_ib_unicast.octets) },
+	{ "tx_vport_rdma_unicast_packets",
+		VPORT_COUNTER_OFF(transmitted_ib_unicast.packets) },
+	{ "tx_vport_rdma_unicast_bytes",
+		VPORT_COUNTER_OFF(transmitted_ib_unicast.octets) },
+	{ "rx_vport_rdma_multicast_packets",
+		VPORT_COUNTER_OFF(received_ib_multicast.packets) },
+	{ "rx_vport_rdma_multicast_bytes",
+		VPORT_COUNTER_OFF(received_ib_multicast.octets) },
+	{ "tx_vport_rdma_multicast_packets",
+		VPORT_COUNTER_OFF(transmitted_ib_multicast.packets) },
+	{ "tx_vport_rdma_multicast_bytes",
+		VPORT_COUNTER_OFF(transmitted_ib_multicast.octets) },
 };
 
 #define PPORT_802_3_OFF(c) \
@@ -192,94 +204,69 @@ struct mlx5e_pport_stats {
 };
 
 static const struct counter_desc pport_802_3_stats_desc[] = {
-	{ "frames_tx", PPORT_802_3_OFF(a_frames_transmitted_ok) },
-	{ "frames_rx", PPORT_802_3_OFF(a_frames_received_ok) },
-	{ "check_seq_err", PPORT_802_3_OFF(a_frame_check_sequence_errors) },
-	{ "alignment_err", PPORT_802_3_OFF(a_alignment_errors) },
-	{ "octets_tx", PPORT_802_3_OFF(a_octets_transmitted_ok) },
-	{ "octets_received", PPORT_802_3_OFF(a_octets_received_ok) },
-	{ "multicast_xmitted", PPORT_802_3_OFF(a_multicast_frames_xmitted_ok) },
-	{ "broadcast_xmitted", PPORT_802_3_OFF(a_broadcast_frames_xmitted_ok) },
-	{ "multicast_rx", PPORT_802_3_OFF(a_multicast_frames_received_ok) },
-	{ "broadcast_rx", PPORT_802_3_OFF(a_broadcast_frames_received_ok) },
-	{ "in_range_len_errors", PPORT_802_3_OFF(a_in_range_length_errors) },
-	{ "out_of_range_len", PPORT_802_3_OFF(a_out_of_range_length_field) },
-	{ "too_long_errors", PPORT_802_3_OFF(a_frame_too_long_errors) },
-	{ "symbol_err", PPORT_802_3_OFF(a_symbol_error_during_carrier) },
-	{ "mac_control_tx", PPORT_802_3_OFF(a_mac_control_frames_transmitted) },
-	{ "mac_control_rx", PPORT_802_3_OFF(a_mac_control_frames_received) },
-	{ "unsupported_op_rx",
-		PPORT_802_3_OFF(a_unsupported_opcodes_received) },
-	{ "pause_ctrl_rx", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_received) },
-	{ "pause_ctrl_tx",
-		PPORT_802_3_OFF(a_pause_mac_ctrl_frames_transmitted) },
+	{ "tx_packets_phy", PPORT_802_3_OFF(a_frames_transmitted_ok) },
+	{ "rx_packets_phy", PPORT_802_3_OFF(a_frames_received_ok) },
+	{ "rx_crc_errors_phy", PPORT_802_3_OFF(a_frame_check_sequence_errors) },
+	{ "tx_bytes_phy", PPORT_802_3_OFF(a_octets_transmitted_ok) },
+	{ "rx_bytes_phy", PPORT_802_3_OFF(a_octets_received_ok) },
+	{ "tx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_xmitted_ok) },
+	{ "tx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_xmitted_ok) },
+	{ "rx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_received_ok) },
+	{ "rx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_received_ok) },
+	{ "rx_in_range_len_errors_phy", PPORT_802_3_OFF(a_in_range_length_errors) },
+	{ "rx_out_of_range_len_phy", PPORT_802_3_OFF(a_out_of_range_length_field) },
+	{ "rx_oversize_pkts_phy", PPORT_802_3_OFF(a_frame_too_long_errors) },
+	{ "rx_symbol_err_phy", PPORT_802_3_OFF(a_symbol_error_during_carrier) },
+	{ "tx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_transmitted) },
+	{ "rx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_received) },
+	{ "rx_unsupported_op_phy", PPORT_802_3_OFF(a_unsupported_opcodes_received) },
+	{ "rx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_received) },
+	{ "tx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_transmitted) },
 };
 
 static const struct counter_desc pport_2863_stats_desc[] = {
-	{ "in_octets", PPORT_2863_OFF(if_in_octets) },
-	{ "in_ucast_pkts", PPORT_2863_OFF(if_in_ucast_pkts) },
-	{ "in_discards", PPORT_2863_OFF(if_in_discards) },
-	{ "in_errors", PPORT_2863_OFF(if_in_errors) },
-	{ "in_unknown_protos", PPORT_2863_OFF(if_in_unknown_protos) },
-	{ "out_octets", PPORT_2863_OFF(if_out_octets) },
-	{ "out_ucast_pkts", PPORT_2863_OFF(if_out_ucast_pkts) },
-	{ "out_discards", PPORT_2863_OFF(if_out_discards) },
-	{ "out_errors", PPORT_2863_OFF(if_out_errors) },
-	{ "in_multicast_pkts", PPORT_2863_OFF(if_in_multicast_pkts) },
-	{ "in_broadcast_pkts", PPORT_2863_OFF(if_in_broadcast_pkts) },
-	{ "out_multicast_pkts", PPORT_2863_OFF(if_out_multicast_pkts) },
-	{ "out_broadcast_pkts", PPORT_2863_OFF(if_out_broadcast_pkts) },
+	{ "rx_discards_phy", PPORT_2863_OFF(if_in_discards) },
+	{ "tx_discards_phy", PPORT_2863_OFF(if_out_discards) },
+	{ "tx_errors_phy", PPORT_2863_OFF(if_out_errors) },
 };
 
 static const struct counter_desc pport_2819_stats_desc[] = {
-	{ "drop_events", PPORT_2819_OFF(ether_stats_drop_events) },
-	{ "octets", PPORT_2819_OFF(ether_stats_octets) },
-	{ "pkts", PPORT_2819_OFF(ether_stats_pkts) },
-	{ "broadcast_pkts", PPORT_2819_OFF(ether_stats_broadcast_pkts) },
-	{ "multicast_pkts", PPORT_2819_OFF(ether_stats_multicast_pkts) },
-	{ "crc_align_errors", PPORT_2819_OFF(ether_stats_crc_align_errors) },
-	{ "undersize_pkts", PPORT_2819_OFF(ether_stats_undersize_pkts) },
-	{ "oversize_pkts", PPORT_2819_OFF(ether_stats_oversize_pkts) },
-	{ "fragments", PPORT_2819_OFF(ether_stats_fragments) },
-	{ "jabbers", PPORT_2819_OFF(ether_stats_jabbers) },
-	{ "collisions", PPORT_2819_OFF(ether_stats_collisions) },
-	{ "p64octets", PPORT_2819_OFF(ether_stats_pkts64octets) },
-	{ "p65to127octets", PPORT_2819_OFF(ether_stats_pkts65to127octets) },
-	{ "p128to255octets", PPORT_2819_OFF(ether_stats_pkts128to255octets) },
-	{ "p256to511octets", PPORT_2819_OFF(ether_stats_pkts256to511octets) },
-	{ "p512to1023octets", PPORT_2819_OFF(ether_stats_pkts512to1023octets) },
-	{ "p1024to1518octets",
-		PPORT_2819_OFF(ether_stats_pkts1024to1518octets) },
-	{ "p1519to2047octets",
-		PPORT_2819_OFF(ether_stats_pkts1519to2047octets) },
-	{ "p2048to4095octets",
-		PPORT_2819_OFF(ether_stats_pkts2048to4095octets) },
-	{ "p4096to8191octets",
-		PPORT_2819_OFF(ether_stats_pkts4096to8191octets) },
-	{ "p8192to10239octets",
-		PPORT_2819_OFF(ether_stats_pkts8192to10239octets) },
+	{ "rx_undersize_pkts_phy", PPORT_2819_OFF(ether_stats_undersize_pkts) },
+	{ "rx_fragments_phy", PPORT_2819_OFF(ether_stats_fragments) },
+	{ "rx_jabbers_phy", PPORT_2819_OFF(ether_stats_jabbers) },
+	{ "rx_64_bytes_phy", PPORT_2819_OFF(ether_stats_pkts64octets) },
+	{ "rx_65_to_127_bytes_phy", PPORT_2819_OFF(ether_stats_pkts65to127octets) },
+	{ "rx_128_to_255_bytes_phy", PPORT_2819_OFF(ether_stats_pkts128to255octets) },
+	{ "rx_256_to_511_bytes_phy", PPORT_2819_OFF(ether_stats_pkts256to511octets) },
+	{ "rx_512_to_1023_bytes_phy", PPORT_2819_OFF(ether_stats_pkts512to1023octets) },
+	{ "rx_1024_to_1518_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1024to1518octets) },
+	{ "rx_1519_to_2047_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1519to2047octets) },
+	{ "rx_2048_to_4095_bytes_phy", PPORT_2819_OFF(ether_stats_pkts2048to4095octets) },
+	{ "rx_4096_to_8191_bytes_phy", PPORT_2819_OFF(ether_stats_pkts4096to8191octets) },
+	{ "rx_8192_to_10239_bytes_phy", PPORT_2819_OFF(ether_stats_pkts8192to10239octets) },
 };
 
 static const struct counter_desc pport_per_prio_traffic_stats_desc[] = {
-	{ "rx_octets", PPORT_PER_PRIO_OFF(rx_octets) },
-	{ "rx_frames", PPORT_PER_PRIO_OFF(rx_frames) },
-	{ "tx_octets", PPORT_PER_PRIO_OFF(tx_octets) },
-	{ "tx_frames", PPORT_PER_PRIO_OFF(tx_frames) },
+	{ "rx_prio%d_bytes", PPORT_PER_PRIO_OFF(rx_octets) },
+	{ "rx_prio%d_packets", PPORT_PER_PRIO_OFF(rx_frames) },
+	{ "tx_prio%d_bytes", PPORT_PER_PRIO_OFF(tx_octets) },
+	{ "tx_prio%d_packets", PPORT_PER_PRIO_OFF(tx_frames) },
 };
 
 static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
-	{ "rx_pause", PPORT_PER_PRIO_OFF(rx_pause) },
-	{ "rx_pause_duration", PPORT_PER_PRIO_OFF(rx_pause_duration) },
-	{ "tx_pause", PPORT_PER_PRIO_OFF(tx_pause) },
-	{ "tx_pause_duration", PPORT_PER_PRIO_OFF(tx_pause_duration) },
-	{ "rx_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
+	/* %s is "global" or "prio{i}" */
+	{ "rx_%s_pause", PPORT_PER_PRIO_OFF(rx_pause) },
+	{ "rx_%s_pause_duration", PPORT_PER_PRIO_OFF(rx_pause_duration) },
+	{ "tx_%s_pause", PPORT_PER_PRIO_OFF(tx_pause) },
+	{ "tx_%s_pause_duration", PPORT_PER_PRIO_OFF(tx_pause_duration) },
+	{ "rx_%s_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
 };
 
 struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
-	u64 csum_sw;
-	u64 csum_inner;
+	u64 csum_complete;
+	u64 csum_unnecessary_inner;
 	u64 csum_none;
 	u64 lro_packets;
 	u64 lro_bytes;
@@ -292,19 +279,19 @@ struct mlx5e_rq_stats {
 };
 
 static const struct counter_desc rq_stats_desc[] = {
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_sw) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_inner) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_none) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, lro_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, lro_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, wqe_err) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, mpwqe_frag) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_frag) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
 };
 
 struct mlx5e_sq_stats {
@@ -315,28 +302,28 @@ struct mlx5e_sq_stats {
 	u64 tso_bytes;
 	u64 tso_inner_packets;
 	u64 tso_inner_bytes;
-	u64 csum_offload_inner;
+	u64 csum_partial_inner;
 	u64 nop;
 	/* less likely accessed in data path */
-	u64 csum_offload_none;
+	u64 csum_none;
 	u64 stopped;
 	u64 wake;
 	u64 dropped;
 };
 
 static const struct counter_desc sq_stats_desc[] = {
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_inner_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_inner_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, csum_offload_inner) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, nop) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, csum_offload_none) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, stopped) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, wake) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, dropped) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, packets) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_packets) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_packets) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
 };
 
 #define NUM_SW_COUNTERS			ARRAY_SIZE(sw_stats_desc)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 704c3d30493e..3261e8b1286e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -50,7 +50,7 @@ struct mlx5e_tc_flow {
 #define MLX5E_TC_TABLE_NUM_GROUPS 4
 
 static struct mlx5_flow_rule *mlx5e_tc_add_flow(struct mlx5e_priv *priv,
-						u32 *match_c, u32 *match_v,
+						struct mlx5_flow_spec *spec,
 						u32 action, u32 flow_tag)
 {
 	struct mlx5_core_dev *dev = priv->mdev;
@@ -88,8 +88,8 @@ static struct mlx5_flow_rule *mlx5e_tc_add_flow(struct mlx5e_priv *priv,
 		table_created = true;
 	}
 
-	rule = mlx5_add_flow_rule(priv->fs.tc.t, MLX5_MATCH_OUTER_HEADERS,
-				  match_c, match_v,
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	rule = mlx5_add_flow_rule(priv->fs.tc.t, spec,
 				  action, flow_tag,
 				  &dest);
 
@@ -126,12 +126,13 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 	}
 }
 
-static int parse_cls_flower(struct mlx5e_priv *priv,
-			    u32 *match_c, u32 *match_v,
+static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec,
 			    struct tc_cls_flower_offload *f)
 {
-	void *headers_c = MLX5_ADDR_OF(fte_match_param, match_c, outer_headers);
-	void *headers_v = MLX5_ADDR_OF(fte_match_param, match_v, outer_headers);
+	void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				       outer_headers);
+	void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				       outer_headers);
 	u16 addr_type = 0;
 	u8 ip_proto = 0;
 
@@ -342,12 +343,11 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 			   struct tc_cls_flower_offload *f)
 {
 	struct mlx5e_tc_table *tc = &priv->fs.tc;
-	u32 *match_c;
-	u32 *match_v;
 	int err = 0;
 	u32 flow_tag;
 	u32 action;
 	struct mlx5e_tc_flow *flow;
+	struct mlx5_flow_spec *spec;
 	struct mlx5_flow_rule *old = NULL;
 
 	flow = rhashtable_lookup_fast(&tc->ht, &f->cookie,
@@ -357,16 +357,15 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 	else
 		flow = kzalloc(sizeof(*flow), GFP_KERNEL);
 
-	match_c = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
-	match_v = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
-	if (!match_c || !match_v || !flow) {
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec || !flow) {
 		err = -ENOMEM;
 		goto err_free;
 	}
 
 	flow->cookie = f->cookie;
 
-	err = parse_cls_flower(priv, match_c, match_v, f);
+	err = parse_cls_flower(priv, spec, f);
 	if (err < 0)
 		goto err_free;
 
@@ -379,8 +378,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 	if (err)
 		goto err_free;
 
-	flow->rule = mlx5e_tc_add_flow(priv, match_c, match_v, action,
-				       flow_tag);
+	flow->rule = mlx5e_tc_add_flow(priv, spec, action, flow_tag);
 	if (IS_ERR(flow->rule)) {
 		err = PTR_ERR(flow->rule);
 		goto err_hash_del;
@@ -398,8 +396,7 @@ err_free:
 	if (!old)
 		kfree(flow);
 out:
-	kfree(match_c);
-	kfree(match_v);
+	kvfree(spec);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 229ab16fb8d3..5a750b9cd006 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -192,12 +192,12 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 		if (skb->encapsulation) {
 			eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM |
 					  MLX5_ETH_WQE_L4_INNER_CSUM;
-			sq->stats.csum_offload_inner++;
+			sq->stats.csum_partial_inner++;
 		} else {
 			eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
 		}
 	} else
-		sq->stats.csum_offload_none++;
+		sq->stats.csum_none++;
 
 	if (sq->cc != sq->prev_cc) {
 		sq->prev_cc = sq->cc;
@@ -317,7 +317,8 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	while ((sq->pc & wq->sz_m1) > sq->edge)
 		mlx5e_send_nop(sq, false);
 
-	sq->bf_budget = bf ? sq->bf_budget - 1 : 0;
+	if (bf)
+		sq->bf_budget--;
 
 	sq->stats.packets++;
 	sq->stats.bytes += num_bytes;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index c38781fa567d..64ae2e800daa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -136,6 +136,10 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 
 	for (i = 0; i < c->num_tc; i++)
 		mlx5e_cq_arm(&c->sq[i].cq);
+
+	if (test_bit(MLX5E_RQ_STATE_AM, &c->rq.state))
+		mlx5e_rx_am(&c->rq);
+
 	mlx5e_cq_arm(&c->rq.cq);
 	mlx5e_cq_arm(&c->icosq.cq);
 
@@ -146,6 +150,7 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 
+	cq->event_ctr++;
 	set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags);
 	napi_schedule(cq->napi);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index b84a6918a700..f6d667797ee1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -40,17 +40,6 @@
 
 #define UPLINK_VPORT 0xFFFF
 
-#define MLX5_DEBUG_ESWITCH_MASK BIT(3)
-
-#define esw_info(dev, format, ...)				\
-	pr_info("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
-
-#define esw_warn(dev, format, ...)				\
-	pr_warn("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
-
-#define esw_debug(dev, format, ...)				\
-	mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__)
-
 enum {
 	MLX5_ACTION_NONE = 0,
 	MLX5_ACTION_ADD  = 1,
@@ -92,6 +81,9 @@ enum {
 			    MC_ADDR_CHANGE | \
 			    PROMISC_CHANGE)
 
+int esw_offloads_init(struct mlx5_eswitch *esw, int nvports);
+void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports);
+
 static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 					u32 events_mask)
 {
@@ -337,25 +329,23 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
 			    MLX5_MATCH_OUTER_HEADERS);
 	struct mlx5_flow_rule *flow_rule = NULL;
 	struct mlx5_flow_destination dest;
+	struct mlx5_flow_spec *spec;
 	void *mv_misc = NULL;
 	void *mc_misc = NULL;
 	u8 *dmac_v = NULL;
 	u8 *dmac_c = NULL;
-	u32 *match_v;
-	u32 *match_c;
 
 	if (rx_rule)
 		match_header |= MLX5_MATCH_MISC_PARAMETERS;
-	match_v = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
-	match_c = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
-	if (!match_v || !match_c) {
+
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec) {
 		pr_warn("FDB: Failed to alloc match parameters\n");
-		goto out;
+		return NULL;
 	}
-
-	dmac_v = MLX5_ADDR_OF(fte_match_param, match_v,
+	dmac_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 			      outer_headers.dmac_47_16);
-	dmac_c = MLX5_ADDR_OF(fte_match_param, match_c,
+	dmac_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
 			      outer_headers.dmac_47_16);
 
 	if (match_header & MLX5_MATCH_OUTER_HEADERS) {
@@ -364,8 +354,10 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
 	}
 
 	if (match_header & MLX5_MATCH_MISC_PARAMETERS) {
-		mv_misc  = MLX5_ADDR_OF(fte_match_param, match_v, misc_parameters);
-		mc_misc  = MLX5_ADDR_OF(fte_match_param, match_c, misc_parameters);
+		mv_misc  = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+					misc_parameters);
+		mc_misc  = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+					misc_parameters);
 		MLX5_SET(fte_match_set_misc, mv_misc, source_port, UPLINK_VPORT);
 		MLX5_SET_TO_ONES(fte_match_set_misc, mc_misc, source_port);
 	}
@@ -376,22 +368,19 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
 	esw_debug(esw->dev,
 		  "\tFDB add rule dmac_v(%pM) dmac_c(%pM) -> vport(%d)\n",
 		  dmac_v, dmac_c, vport);
+	spec->match_criteria_enable = match_header;
 	flow_rule =
-		mlx5_add_flow_rule(esw->fdb_table.fdb,
-				   match_header,
-				   match_c,
-				   match_v,
+		mlx5_add_flow_rule(esw->fdb_table.fdb, spec,
 				   MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
 				   0, &dest);
-	if (IS_ERR_OR_NULL(flow_rule)) {
+	if (IS_ERR(flow_rule)) {
 		pr_warn(
 			"FDB: Failed to add flow rule: dmac_v(%pM) dmac_c(%pM) -> vport(%d), err(%ld)\n",
 			 dmac_v, dmac_c, vport, PTR_ERR(flow_rule));
 		flow_rule = NULL;
 	}
-out:
-	kfree(match_v);
-	kfree(match_c);
+
+	kvfree(spec);
 	return flow_rule;
 }
 
@@ -428,7 +417,7 @@ esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
 	return __esw_fdb_set_vport_rule(esw, vport, true, mac_c, mac_v);
 }
 
-static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports)
+static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_core_dev *dev = esw->dev;
@@ -457,7 +446,7 @@ static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports)
 
 	table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
 	fdb = mlx5_create_flow_table(root_ns, 0, table_size, 0);
-	if (IS_ERR_OR_NULL(fdb)) {
+	if (IS_ERR(fdb)) {
 		err = PTR_ERR(fdb);
 		esw_warn(dev, "Failed to create FDB Table err %d\n", err);
 		goto out;
@@ -474,12 +463,12 @@ static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports)
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 3);
 	eth_broadcast_addr(dmac);
 	g = mlx5_create_flow_group(fdb, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create flow group err(%d)\n", err);
 		goto out;
 	}
-	esw->fdb_table.addr_grp = g;
+	esw->fdb_table.legacy.addr_grp = g;
 
 	/* Allmulti group : One rule that forwards any mcast traffic */
 	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
@@ -489,12 +478,12 @@ static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports)
 	eth_zero_addr(dmac);
 	dmac[0] = 0x01;
 	g = mlx5_create_flow_group(fdb, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create allmulti flow group err(%d)\n", err);
 		goto out;
 	}
-	esw->fdb_table.allmulti_grp = g;
+	esw->fdb_table.legacy.allmulti_grp = g;
 
 	/* Promiscuous group :
 	 * One rule that forward all unmatched traffic from previous groups
@@ -506,22 +495,22 @@ static int esw_create_fdb_table(struct mlx5_eswitch *esw, int nvports)
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, table_size - 1);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 1);
 	g = mlx5_create_flow_group(fdb, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create promisc flow group err(%d)\n", err);
 		goto out;
 	}
-	esw->fdb_table.promisc_grp = g;
+	esw->fdb_table.legacy.promisc_grp = g;
 
 out:
 	if (err) {
-		if (!IS_ERR_OR_NULL(esw->fdb_table.allmulti_grp)) {
-			mlx5_destroy_flow_group(esw->fdb_table.allmulti_grp);
-			esw->fdb_table.allmulti_grp = NULL;
+		if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.allmulti_grp)) {
+			mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
+			esw->fdb_table.legacy.allmulti_grp = NULL;
 		}
-		if (!IS_ERR_OR_NULL(esw->fdb_table.addr_grp)) {
-			mlx5_destroy_flow_group(esw->fdb_table.addr_grp);
-			esw->fdb_table.addr_grp = NULL;
+		if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.addr_grp)) {
+			mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
+			esw->fdb_table.legacy.addr_grp = NULL;
 		}
 		if (!IS_ERR_OR_NULL(esw->fdb_table.fdb)) {
 			mlx5_destroy_flow_table(esw->fdb_table.fdb);
@@ -529,24 +518,24 @@ out:
 		}
 	}
 
-	kfree(flow_group_in);
+	kvfree(flow_group_in);
 	return err;
 }
 
-static void esw_destroy_fdb_table(struct mlx5_eswitch *esw)
+static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw)
 {
 	if (!esw->fdb_table.fdb)
 		return;
 
 	esw_debug(esw->dev, "Destroy FDB Table\n");
-	mlx5_destroy_flow_group(esw->fdb_table.promisc_grp);
-	mlx5_destroy_flow_group(esw->fdb_table.allmulti_grp);
-	mlx5_destroy_flow_group(esw->fdb_table.addr_grp);
+	mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp);
+	mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
+	mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
 	mlx5_destroy_flow_table(esw->fdb_table.fdb);
 	esw->fdb_table.fdb = NULL;
-	esw->fdb_table.addr_grp = NULL;
-	esw->fdb_table.allmulti_grp = NULL;
-	esw->fdb_table.promisc_grp = NULL;
+	esw->fdb_table.legacy.addr_grp = NULL;
+	esw->fdb_table.legacy.allmulti_grp = NULL;
+	esw->fdb_table.legacy.promisc_grp = NULL;
 }
 
 /* E-Switch vport UC/MC lists management */
@@ -578,7 +567,8 @@ static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 	if (err)
 		goto abort;
 
-	if (esw->fdb_table.fdb) /* SRIOV is enabled: Forward UC MAC to vport */
+	/* SRIOV is enabled: Forward UC MAC to vport */
+	if (esw->fdb_table.fdb && esw->mode == SRIOV_LEGACY)
 		vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport);
 
 	esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM index:%d fr(%p)\n",
@@ -651,6 +641,7 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
 					esw_fdb_set_vport_rule(esw,
 							       mac,
 							       vport_idx);
+			iter_vaddr->mc_promisc = true;
 			break;
 		case MLX5_ACTION_DEL:
 			if (!iter_vaddr)
@@ -1060,7 +1051,7 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
 		return;
 
 	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
-	if (IS_ERR_OR_NULL(acl)) {
+	if (IS_ERR(acl)) {
 		err = PTR_ERR(acl);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] egress flow Table, err(%d)\n",
 			 vport->vport, err);
@@ -1075,7 +1066,7 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
 
 	vlan_grp = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(vlan_grp)) {
+	if (IS_ERR(vlan_grp)) {
 		err = PTR_ERR(vlan_grp);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] egress allowed vlans flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1086,7 +1077,7 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
 	drop_grp = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(drop_grp)) {
+	if (IS_ERR(drop_grp)) {
 		err = PTR_ERR(drop_grp);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] egress drop flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1097,7 +1088,7 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
 	vport->egress.drop_grp = drop_grp;
 	vport->egress.allowed_vlans_grp = vlan_grp;
 out:
-	kfree(flow_group_in);
+	kvfree(flow_group_in);
 	if (err && !IS_ERR_OR_NULL(vlan_grp))
 		mlx5_destroy_flow_group(vlan_grp);
 	if (err && !IS_ERR_OR_NULL(acl))
@@ -1174,7 +1165,7 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 		return;
 
 	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
-	if (IS_ERR_OR_NULL(acl)) {
+	if (IS_ERR(acl)) {
 		err = PTR_ERR(acl);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress flow Table, err(%d)\n",
 			 vport->vport, err);
@@ -1192,7 +1183,7 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
 
 	g = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged spoofchk flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1207,7 +1198,7 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
 
 	g = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1223,7 +1214,7 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 2);
 
 	g = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress spoofchk flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1236,7 +1227,7 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 3);
 
 	g = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress drop flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1259,7 +1250,7 @@ out:
 			mlx5_destroy_flow_table(vport->ingress.acl);
 	}
 
-	kfree(flow_group_in);
+	kvfree(flow_group_in);
 }
 
 static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
@@ -1299,9 +1290,8 @@ static void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
 static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 				    struct mlx5_vport *vport)
 {
+	struct mlx5_flow_spec *spec;
 	u8 smac[ETH_ALEN];
-	u32 *match_v;
-	u32 *match_c;
 	int err = 0;
 	u8 *smac_v;
 
@@ -1335,9 +1325,8 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 		  "vport[%d] configure ingress rules, vlan(%d) qos(%d)\n",
 		  vport->vport, vport->vlan, vport->qos);
 
-	match_v = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
-	match_c = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
-	if (!match_v || !match_c) {
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec) {
 		err = -ENOMEM;
 		esw_warn(esw->dev, "vport[%d] configure ingress rules failed, err(%d)\n",
 			 vport->vport, err);
@@ -1345,25 +1334,23 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 	}
 
 	if (vport->vlan || vport->qos)
-		MLX5_SET_TO_ONES(fte_match_param, match_c, outer_headers.vlan_tag);
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.vlan_tag);
 
 	if (vport->spoofchk) {
-		MLX5_SET_TO_ONES(fte_match_param, match_c, outer_headers.smac_47_16);
-		MLX5_SET_TO_ONES(fte_match_param, match_c, outer_headers.smac_15_0);
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.smac_47_16);
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.smac_15_0);
 		smac_v = MLX5_ADDR_OF(fte_match_param,
-				      match_v,
+				      spec->match_value,
 				      outer_headers.smac_47_16);
 		ether_addr_copy(smac_v, smac);
 	}
 
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
 	vport->ingress.allow_rule =
-		mlx5_add_flow_rule(vport->ingress.acl,
-				   MLX5_MATCH_OUTER_HEADERS,
-				   match_c,
-				   match_v,
+		mlx5_add_flow_rule(vport->ingress.acl, spec,
 				   MLX5_FLOW_CONTEXT_ACTION_ALLOW,
 				   0, NULL);
-	if (IS_ERR_OR_NULL(vport->ingress.allow_rule)) {
+	if (IS_ERR(vport->ingress.allow_rule)) {
 		err = PTR_ERR(vport->ingress.allow_rule);
 		pr_warn("vport[%d] configure ingress allow rule, err(%d)\n",
 			vport->vport, err);
@@ -1371,16 +1358,12 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 		goto out;
 	}
 
-	memset(match_c, 0, MLX5_ST_SZ_BYTES(fte_match_param));
-	memset(match_v, 0, MLX5_ST_SZ_BYTES(fte_match_param));
+	memset(spec, 0, sizeof(*spec));
 	vport->ingress.drop_rule =
-		mlx5_add_flow_rule(vport->ingress.acl,
-				   0,
-				   match_c,
-				   match_v,
+		mlx5_add_flow_rule(vport->ingress.acl, spec,
 				   MLX5_FLOW_CONTEXT_ACTION_DROP,
 				   0, NULL);
-	if (IS_ERR_OR_NULL(vport->ingress.drop_rule)) {
+	if (IS_ERR(vport->ingress.drop_rule)) {
 		err = PTR_ERR(vport->ingress.drop_rule);
 		pr_warn("vport[%d] configure ingress drop rule, err(%d)\n",
 			vport->vport, err);
@@ -1391,17 +1374,14 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 out:
 	if (err)
 		esw_vport_cleanup_ingress_rules(esw, vport);
-
-	kfree(match_v);
-	kfree(match_c);
+	kvfree(spec);
 	return err;
 }
 
 static int esw_vport_egress_config(struct mlx5_eswitch *esw,
 				   struct mlx5_vport *vport)
 {
-	u32 *match_v;
-	u32 *match_c;
+	struct mlx5_flow_spec *spec;
 	int err = 0;
 
 	esw_vport_cleanup_egress_rules(esw, vport);
@@ -1417,9 +1397,8 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
 		  "vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
 		  vport->vport, vport->vlan, vport->qos);
 
-	match_v = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
-	match_c = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
-	if (!match_v || !match_c) {
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec) {
 		err = -ENOMEM;
 		esw_warn(esw->dev, "vport[%d] configure egress rules failed, err(%d)\n",
 			 vport->vport, err);
@@ -1427,19 +1406,17 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
 	}
 
 	/* Allowed vlan rule */
-	MLX5_SET_TO_ONES(fte_match_param, match_c, outer_headers.vlan_tag);
-	MLX5_SET_TO_ONES(fte_match_param, match_v, outer_headers.vlan_tag);
-	MLX5_SET_TO_ONES(fte_match_param, match_c, outer_headers.first_vid);
-	MLX5_SET(fte_match_param, match_v, outer_headers.first_vid, vport->vlan);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.vlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.vlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid);
+	MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, vport->vlan);
 
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
 	vport->egress.allowed_vlan =
-		mlx5_add_flow_rule(vport->egress.acl,
-				   MLX5_MATCH_OUTER_HEADERS,
-				   match_c,
-				   match_v,
+		mlx5_add_flow_rule(vport->egress.acl, spec,
 				   MLX5_FLOW_CONTEXT_ACTION_ALLOW,
 				   0, NULL);
-	if (IS_ERR_OR_NULL(vport->egress.allowed_vlan)) {
+	if (IS_ERR(vport->egress.allowed_vlan)) {
 		err = PTR_ERR(vport->egress.allowed_vlan);
 		pr_warn("vport[%d] configure egress allowed vlan rule failed, err(%d)\n",
 			vport->vport, err);
@@ -1448,24 +1425,19 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
 	}
 
 	/* Drop others rule (star rule) */
-	memset(match_c, 0, MLX5_ST_SZ_BYTES(fte_match_param));
-	memset(match_v, 0, MLX5_ST_SZ_BYTES(fte_match_param));
+	memset(spec, 0, sizeof(*spec));
 	vport->egress.drop_rule =
-		mlx5_add_flow_rule(vport->egress.acl,
-				   0,
-				   match_c,
-				   match_v,
+		mlx5_add_flow_rule(vport->egress.acl, spec,
 				   MLX5_FLOW_CONTEXT_ACTION_DROP,
 				   0, NULL);
-	if (IS_ERR_OR_NULL(vport->egress.drop_rule)) {
+	if (IS_ERR(vport->egress.drop_rule)) {
 		err = PTR_ERR(vport->egress.drop_rule);
 		pr_warn("vport[%d] configure egress drop rule failed, err(%d)\n",
 			vport->vport, err);
 		vport->egress.drop_rule = NULL;
 	}
 out:
-	kfree(match_v);
-	kfree(match_c);
+	kvfree(spec);
 	return err;
 }
 
@@ -1491,14 +1463,11 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 
 	/* Sync with current vport context */
 	vport->enabled_events = enable_events;
-	esw_vport_change_handle_locked(vport);
-
 	vport->enabled = true;
 
 	/* only PF is trusted by default */
 	vport->trusted = (vport_num) ? false : true;
-
-	arm_vport_context_events_cmd(esw->dev, vport_num, enable_events);
+	esw_vport_change_handle_locked(vport);
 
 	esw->enabled_vports++;
 	esw_debug(esw->dev, "Enabled VPORT(%d)\n", vport_num);
@@ -1542,10 +1511,10 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 }
 
 /* Public E-Switch API */
-int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs)
+int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 {
 	int err;
-	int i;
+	int i, enabled_events;
 
 	if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager) ||
 	    MLX5_CAP_GEN(esw->dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
@@ -1563,16 +1532,20 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs)
 	if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support))
 		esw_warn(esw->dev, "E-Switch engress ACL is not supported by FW\n");
 
-	esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d)\n", nvfs);
-
+	esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode);
+	esw->mode = mode;
 	esw_disable_vport(esw, 0);
 
-	err = esw_create_fdb_table(esw, nvfs + 1);
+	if (mode == SRIOV_LEGACY)
+		err = esw_create_legacy_fdb_table(esw, nvfs + 1);
+	else
+		err = esw_offloads_init(esw, nvfs + 1);
 	if (err)
 		goto abort;
 
+	enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : UC_ADDR_CHANGE;
 	for (i = 0; i <= nvfs; i++)
-		esw_enable_vport(esw, i, SRIOV_VPORT_EVENTS);
+		esw_enable_vport(esw, i, enabled_events);
 
 	esw_info(esw->dev, "SRIOV enabled: active vports(%d)\n",
 		 esw->enabled_vports);
@@ -1586,16 +1559,18 @@ abort:
 void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 {
 	struct esw_mc_addr *mc_promisc;
+	int nvports;
 	int i;
 
 	if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager) ||
 	    MLX5_CAP_GEN(esw->dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
 		return;
 
-	esw_info(esw->dev, "disable SRIOV: active vports(%d)\n",
-		 esw->enabled_vports);
+	esw_info(esw->dev, "disable SRIOV: active vports(%d) mode(%d)\n",
+		 esw->enabled_vports, esw->mode);
 
 	mc_promisc = esw->mc_promisc;
+	nvports = esw->enabled_vports;
 
 	for (i = 0; i < esw->total_vports; i++)
 		esw_disable_vport(esw, i);
@@ -1603,8 +1578,12 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 	if (mc_promisc && mc_promisc->uplink_rule)
 		mlx5_del_flow_rule(mc_promisc->uplink_rule);
 
-	esw_destroy_fdb_table(esw);
+	if (esw->mode == SRIOV_LEGACY)
+		esw_destroy_legacy_fdb_table(esw);
+	else if (esw->mode == SRIOV_OFFLOADS)
+		esw_offloads_cleanup(esw, nvports);
 
+	esw->mode = SRIOV_NONE;
 	/* VPORT 0 (PF) must be enabled back with non-sriov configuration */
 	esw_enable_vport(esw, 0, UC_ADDR_CHANGE);
 }
@@ -1662,6 +1641,14 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		goto abort;
 	}
 
+	esw->offloads.vport_reps =
+		kzalloc(total_vports * sizeof(struct mlx5_eswitch_rep),
+			GFP_KERNEL);
+	if (!esw->offloads.vport_reps) {
+		err = -ENOMEM;
+		goto abort;
+	}
+
 	mutex_init(&esw->state_lock);
 
 	for (vport_num = 0; vport_num < total_vports; vport_num++) {
@@ -1675,6 +1662,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 
 	esw->total_vports = total_vports;
 	esw->enabled_vports = 0;
+	esw->mode = SRIOV_NONE;
 
 	dev->priv.eswitch = esw;
 	esw_enable_vport(esw, 0, UC_ADDR_CHANGE);
@@ -1685,6 +1673,7 @@ abort:
 		destroy_workqueue(esw->work_queue);
 	kfree(esw->l2_table.bitmap);
 	kfree(esw->vports);
+	kfree(esw->offloads.vport_reps);
 	kfree(esw);
 	return err;
 }
@@ -1702,6 +1691,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 	destroy_workqueue(esw->work_queue);
 	kfree(esw->l2_table.bitmap);
 	kfree(esw->mc_promisc);
+	kfree(esw->offloads.vport_reps);
 	kfree(esw->vports);
 	kfree(esw);
 }
@@ -1728,11 +1718,24 @@ void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe)
 	(esw && MLX5_CAP_GEN(esw->dev, vport_group_manager) && mlx5_core_is_pf(esw->dev))
 #define LEGAL_VPORT(esw, vport) (vport >= 0 && vport < esw->total_vports)
 
+static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
+{
+	((u8 *)node_guid)[7] = mac[0];
+	((u8 *)node_guid)[6] = mac[1];
+	((u8 *)node_guid)[5] = mac[2];
+	((u8 *)node_guid)[4] = 0xff;
+	((u8 *)node_guid)[3] = 0xfe;
+	((u8 *)node_guid)[2] = mac[3];
+	((u8 *)node_guid)[1] = mac[4];
+	((u8 *)node_guid)[0] = mac[5];
+}
+
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 			       int vport, u8 mac[ETH_ALEN])
 {
-	int err = 0;
 	struct mlx5_vport *evport;
+	u64 node_guid;
+	int err = 0;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
@@ -1756,11 +1759,17 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 		return err;
 	}
 
+	node_guid_gen_from_mac(&node_guid, mac);
+	err = mlx5_modify_nic_vport_node_guid(esw->dev, vport, node_guid);
+	if (err)
+		mlx5_core_warn(esw->dev,
+			       "Failed to set vport %d node guid, err = %d. RDMA_CM will not function properly for this VF.\n",
+			       vport, err);
+
 	mutex_lock(&esw->state_lock);
 	if (evport->enabled)
 		err = esw_vport_ingress_config(esw, evport);
 	mutex_unlock(&esw->state_lock);
-
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index fd6800256d4a..7b45e6a6efb8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -35,6 +35,7 @@
 
 #include <linux/if_ether.h>
 #include <linux/if_link.h>
+#include <net/devlink.h>
 #include <linux/mlx5/device.h>
 
 #define MLX5_MAX_UC_PER_VPORT(dev) \
@@ -46,6 +47,8 @@
 #define MLX5_L2_ADDR_HASH_SIZE (BIT(BITS_PER_BYTE))
 #define MLX5_L2_ADDR_HASH(addr) (addr[5])
 
+#define FDB_UPLINK_VPORT 0xffff
+
 /* L2 -mac address based- hash helpers */
 struct l2addr_node {
 	struct hlist_node hlist;
@@ -134,9 +137,48 @@ struct mlx5_l2_table {
 
 struct mlx5_eswitch_fdb {
 	void *fdb;
-	struct mlx5_flow_group *addr_grp;
-	struct mlx5_flow_group *allmulti_grp;
-	struct mlx5_flow_group *promisc_grp;
+	union {
+		struct legacy_fdb {
+			struct mlx5_flow_group *addr_grp;
+			struct mlx5_flow_group *allmulti_grp;
+			struct mlx5_flow_group *promisc_grp;
+		} legacy;
+
+		struct offloads_fdb {
+			struct mlx5_flow_group *send_to_vport_grp;
+			struct mlx5_flow_group *miss_grp;
+			struct mlx5_flow_rule  *miss_rule;
+		} offloads;
+	};
+};
+
+enum {
+	SRIOV_NONE,
+	SRIOV_LEGACY,
+	SRIOV_OFFLOADS
+};
+
+struct mlx5_esw_sq {
+	struct mlx5_flow_rule	*send_to_vport_rule;
+	struct list_head	 list;
+};
+
+struct mlx5_eswitch_rep {
+	int		       (*load)(struct mlx5_eswitch *esw,
+				       struct mlx5_eswitch_rep *rep);
+	void		       (*unload)(struct mlx5_eswitch *esw,
+					 struct mlx5_eswitch_rep *rep);
+	u16		       vport;
+	struct mlx5_flow_rule *vport_rx_rule;
+	void		      *priv_data;
+	struct list_head       vport_sqs_list;
+	bool		       valid;
+};
+
+struct mlx5_esw_offload {
+	struct mlx5_flow_table *ft_offloads;
+	struct mlx5_flow_group *vport_rx_group;
+	struct mlx5_eswitch_rep *vport_reps;
 };
 
 struct mlx5_eswitch {
@@ -153,13 +195,15 @@ struct mlx5_eswitch {
 	 */
 	struct mutex            state_lock;
 	struct esw_mc_addr      *mc_promisc;
+	struct mlx5_esw_offload offloads;
+	int                     mode;
 };
 
 /* E-Switch API */
 int mlx5_eswitch_init(struct mlx5_core_dev *dev);
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw);
 void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe);
-int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs);
+int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode);
 void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw);
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 			       int vport, u8 mac[ETH_ALEN]);
@@ -177,4 +221,30 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 				 int vport,
 				 struct ifla_vf_stats *vf_stats);
 
+struct mlx5_flow_rule *
+mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn);
+
+int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
+				 struct mlx5_eswitch_rep *rep,
+				 u16 *sqns_array, int sqns_num);
+void mlx5_eswitch_sqs2vport_stop(struct mlx5_eswitch *esw,
+				 struct mlx5_eswitch_rep *rep);
+
+int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode);
+int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode);
+void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
+				     struct mlx5_eswitch_rep *rep);
+void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw,
+				       int vport);
+
+#define MLX5_DEBUG_ESWITCH_MASK BIT(3)
+
+#define esw_info(dev, format, ...)				\
+	pr_info("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
+
+#define esw_warn(dev, format, ...)				\
+	pr_warn("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
+
+#define esw_debug(dev, format, ...)				\
+	mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__)
 #endif /* __MLX5_ESWITCH_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
new file mode 100644
index 000000000000..1842dfb4636b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -0,0 +1,561 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/vport.h>
+#include <linux/mlx5/fs.h>
+#include "mlx5_core.h"
+#include "eswitch.h"
+
+static struct mlx5_flow_rule *
+mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn)
+{
+	struct mlx5_flow_destination dest;
+	struct mlx5_flow_rule *flow_rule;
+	struct mlx5_flow_spec *spec;
+	void *misc;
+
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec) {
+		esw_warn(esw->dev, "FDB: Failed to alloc match parameters\n");
+		flow_rule = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+	MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn);
+	MLX5_SET(fte_match_set_misc, misc, source_port, 0x0); /* source vport is 0 */
+
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+	dest.vport_num = vport;
+
+	flow_rule = mlx5_add_flow_rule(esw->fdb_table.fdb, spec,
+				       MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+				       0, &dest);
+	if (IS_ERR(flow_rule))
+		esw_warn(esw->dev, "FDB: Failed to add send to vport rule err %ld\n", PTR_ERR(flow_rule));
+out:
+	kvfree(spec);
+	return flow_rule;
+}
+
+void mlx5_eswitch_sqs2vport_stop(struct mlx5_eswitch *esw,
+				 struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5_esw_sq *esw_sq, *tmp;
+
+	if (esw->mode != SRIOV_OFFLOADS)
+		return;
+
+	list_for_each_entry_safe(esw_sq, tmp, &rep->vport_sqs_list, list) {
+		mlx5_del_flow_rule(esw_sq->send_to_vport_rule);
+		list_del(&esw_sq->list);
+		kfree(esw_sq);
+	}
+}
+
+int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
+				 struct mlx5_eswitch_rep *rep,
+				 u16 *sqns_array, int sqns_num)
+{
+	struct mlx5_flow_rule *flow_rule;
+	struct mlx5_esw_sq *esw_sq;
+	int vport;
+	int err;
+	int i;
+
+	if (esw->mode != SRIOV_OFFLOADS)
+		return 0;
+
+	vport = rep->vport == 0 ?
+		FDB_UPLINK_VPORT : rep->vport;
+
+	for (i = 0; i < sqns_num; i++) {
+		esw_sq = kzalloc(sizeof(*esw_sq), GFP_KERNEL);
+		if (!esw_sq) {
+			err = -ENOMEM;
+			goto out_err;
+		}
+
+		/* Add re-inject rule to the PF/representor sqs */
+		flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw,
+								vport,
+								sqns_array[i]);
+		if (IS_ERR(flow_rule)) {
+			err = PTR_ERR(flow_rule);
+			kfree(esw_sq);
+			goto out_err;
+		}
+		esw_sq->send_to_vport_rule = flow_rule;
+		list_add(&esw_sq->list, &rep->vport_sqs_list);
+	}
+	return 0;
+
+out_err:
+	mlx5_eswitch_sqs2vport_stop(esw, rep);
+	return err;
+}
+
+static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
+{
+	struct mlx5_flow_destination dest;
+	struct mlx5_flow_rule *flow_rule = NULL;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec) {
+		esw_warn(esw->dev, "FDB: Failed to alloc match parameters\n");
+		err = -ENOMEM;
+		goto out;
+	}
+
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+	dest.vport_num = 0;
+
+	flow_rule = mlx5_add_flow_rule(esw->fdb_table.fdb, spec,
+				       MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+				       0, &dest);
+	if (IS_ERR(flow_rule)) {
+		err = PTR_ERR(flow_rule);
+		esw_warn(esw->dev,  "FDB: Failed to add miss flow rule err %d\n", err);
+		goto out;
+	}
+
+	esw->fdb_table.offloads.miss_rule = flow_rule;
+out:
+	kvfree(spec);
+	return err;
+}
+
+#define MAX_PF_SQ 256
+
+static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_namespace *root_ns;
+	struct mlx5_flow_table *fdb = NULL;
+	struct mlx5_flow_group *g;
+	u32 *flow_group_in;
+	void *match_criteria;
+	int table_size, ix, err = 0;
+
+	flow_group_in = mlx5_vzalloc(inlen);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	if (!root_ns) {
+		esw_warn(dev, "Failed to get FDB flow namespace\n");
+		goto ns_err;
+	}
+
+	esw_debug(dev, "Create offloads FDB table, log_max_size(%d)\n",
+		  MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
+
+	table_size = nvports + MAX_PF_SQ + 1;
+	fdb = mlx5_create_flow_table(root_ns, 0, table_size, 0);
+	if (IS_ERR(fdb)) {
+		err = PTR_ERR(fdb);
+		esw_warn(dev, "Failed to create FDB Table err %d\n", err);
+		goto fdb_err;
+	}
+	esw->fdb_table.fdb = fdb;
+
+	/* create send-to-vport group */
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS);
+
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
+
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_sqn);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port);
+
+	ix = nvports + MAX_PF_SQ;
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix - 1);
+
+	g = mlx5_create_flow_group(fdb, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create send-to-vport flow group err(%d)\n", err);
+		goto send_vport_err;
+	}
+	esw->fdb_table.offloads.send_to_vport_grp = g;
+
+	/* create miss group */
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, 0);
+
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + 1);
+
+	g = mlx5_create_flow_group(fdb, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create miss flow group err(%d)\n", err);
+		goto miss_err;
+	}
+	esw->fdb_table.offloads.miss_grp = g;
+
+	err = esw_add_fdb_miss_rule(esw);
+	if (err)
+		goto miss_rule_err;
+
+	return 0;
+
+miss_rule_err:
+	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
+miss_err:
+	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
+send_vport_err:
+	mlx5_destroy_flow_table(fdb);
+fdb_err:
+ns_err:
+	kvfree(flow_group_in);
+	return err;
+}
+
+static void esw_destroy_offloads_fdb_table(struct mlx5_eswitch *esw)
+{
+	if (!esw->fdb_table.fdb)
+		return;
+
+	esw_debug(esw->dev, "Destroy offloads FDB Table\n");
+	mlx5_del_flow_rule(esw->fdb_table.offloads.miss_rule);
+	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
+	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
+
+	mlx5_destroy_flow_table(esw->fdb_table.fdb);
+}
+
+static int esw_create_offloads_table(struct mlx5_eswitch *esw)
+{
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_table *ft_offloads;
+	struct mlx5_core_dev *dev = esw->dev;
+	int err = 0;
+
+	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_OFFLOADS);
+	if (!ns) {
+		esw_warn(esw->dev, "Failed to get offloads flow namespace\n");
+		return -ENOMEM;
+	}
+
+	ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0);
+	if (IS_ERR(ft_offloads)) {
+		err = PTR_ERR(ft_offloads);
+		esw_warn(esw->dev, "Failed to create offloads table, err %d\n", err);
+		return err;
+	}
+
+	esw->offloads.ft_offloads = ft_offloads;
+	return 0;
+}
+
+static void esw_destroy_offloads_table(struct mlx5_eswitch *esw)
+{
+	struct mlx5_esw_offload *offloads = &esw->offloads;
+
+	mlx5_destroy_flow_table(offloads->ft_offloads);
+}
+
+static int esw_create_vport_rx_group(struct mlx5_eswitch *esw)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *g;
+	struct mlx5_priv *priv = &esw->dev->priv;
+	u32 *flow_group_in;
+	void *match_criteria, *misc;
+	int err = 0;
+	int nvports = priv->sriov.num_vfs + 2;
+
+	flow_group_in = mlx5_vzalloc(inlen);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	/* create vport rx group */
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS);
+
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
+	misc = MLX5_ADDR_OF(fte_match_param, match_criteria, misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, nvports - 1);
+
+	g = mlx5_create_flow_group(esw->offloads.ft_offloads, flow_group_in);
+
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		mlx5_core_warn(esw->dev, "Failed to create vport rx group err %d\n", err);
+		goto out;
+	}
+
+	esw->offloads.vport_rx_group = g;
+out:
+	kfree(flow_group_in);
+	return err;
+}
+
+static void esw_destroy_vport_rx_group(struct mlx5_eswitch *esw)
+{
+	mlx5_destroy_flow_group(esw->offloads.vport_rx_group);
+}
+
+struct mlx5_flow_rule *
+mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn)
+{
+	struct mlx5_flow_destination dest;
+	struct mlx5_flow_rule *flow_rule;
+	struct mlx5_flow_spec *spec;
+	void *misc;
+
+	spec = mlx5_vzalloc(sizeof(*spec));
+	if (!spec) {
+		esw_warn(esw->dev, "Failed to alloc match parameters\n");
+		flow_rule = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+	MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
+	dest.tir_num = tirn;
+
+	flow_rule = mlx5_add_flow_rule(esw->offloads.ft_offloads, spec,
+				       MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+				       0, &dest);
+	if (IS_ERR(flow_rule)) {
+		esw_warn(esw->dev, "fs offloads: Failed to add vport rx rule err %ld\n", PTR_ERR(flow_rule));
+		goto out;
+	}
+
+out:
+	kvfree(spec);
+	return flow_rule;
+}
+
+static int esw_offloads_start(struct mlx5_eswitch *esw)
+{
+	int err, num_vfs = esw->dev->priv.sriov.num_vfs;
+
+	if (esw->mode != SRIOV_LEGACY) {
+		esw_warn(esw->dev, "Can't set offloads mode, SRIOV legacy not enabled\n");
+		return -EINVAL;
+	}
+
+	mlx5_eswitch_disable_sriov(esw);
+	err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS);
+	if (err)
+		esw_warn(esw->dev, "Failed set eswitch to offloads, err %d\n", err);
+	return err;
+}
+
+int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
+{
+	struct mlx5_eswitch_rep *rep;
+	int vport;
+	int err;
+
+	err = esw_create_offloads_fdb_table(esw, nvports);
+	if (err)
+		return err;
+
+	err = esw_create_offloads_table(esw);
+	if (err)
+		goto create_ft_err;
+
+	err = esw_create_vport_rx_group(esw);
+	if (err)
+		goto create_fg_err;
+
+	for (vport = 0; vport < nvports; vport++) {
+		rep = &esw->offloads.vport_reps[vport];
+		if (!rep->valid)
+			continue;
+
+		err = rep->load(esw, rep);
+		if (err)
+			goto err_reps;
+	}
+	return 0;
+
+err_reps:
+	for (vport--; vport >= 0; vport--) {
+		rep = &esw->offloads.vport_reps[vport];
+		if (!rep->valid)
+			continue;
+		rep->unload(esw, rep);
+	}
+	esw_destroy_vport_rx_group(esw);
+
+create_fg_err:
+	esw_destroy_offloads_table(esw);
+
+create_ft_err:
+	esw_destroy_offloads_fdb_table(esw);
+	return err;
+}
+
+static int esw_offloads_stop(struct mlx5_eswitch *esw)
+{
+	int err, num_vfs = esw->dev->priv.sriov.num_vfs;
+
+	mlx5_eswitch_disable_sriov(esw);
+	err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
+	if (err)
+		esw_warn(esw->dev, "Failed set eswitch legacy mode. err %d\n", err);
+
+	return err;
+}
+
+void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports)
+{
+	struct mlx5_eswitch_rep *rep;
+	int vport;
+
+	for (vport = 0; vport < nvports; vport++) {
+		rep = &esw->offloads.vport_reps[vport];
+		if (!rep->valid)
+			continue;
+		rep->unload(esw, rep);
+	}
+
+	esw_destroy_vport_rx_group(esw);
+	esw_destroy_offloads_table(esw);
+	esw_destroy_offloads_fdb_table(esw);
+}
+
+static int mlx5_esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
+{
+	switch (mode) {
+	case DEVLINK_ESWITCH_MODE_LEGACY:
+		*mlx5_mode = SRIOV_LEGACY;
+		break;
+	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+		*mlx5_mode = SRIOV_OFFLOADS;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
+{
+	struct mlx5_core_dev *dev;
+	u16 cur_mlx5_mode, mlx5_mode = 0;
+
+	dev = devlink_priv(devlink);
+
+	if (!MLX5_CAP_GEN(dev, vport_group_manager))
+		return -EOPNOTSUPP;
+
+	cur_mlx5_mode = dev->priv.eswitch->mode;
+
+	if (cur_mlx5_mode == SRIOV_NONE)
+		return -EOPNOTSUPP;
+
+	if (mlx5_esw_mode_from_devlink(mode, &mlx5_mode))
+		return -EINVAL;
+
+	if (cur_mlx5_mode == mlx5_mode)
+		return 0;
+
+	if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		return esw_offloads_start(dev->priv.eswitch);
+	else if (mode == DEVLINK_ESWITCH_MODE_LEGACY)
+		return esw_offloads_stop(dev->priv.eswitch);
+	else
+		return -EINVAL;
+}
+
+int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+	struct mlx5_core_dev *dev;
+
+	dev = devlink_priv(devlink);
+
+	if (!MLX5_CAP_GEN(dev, vport_group_manager))
+		return -EOPNOTSUPP;
+
+	if (dev->priv.eswitch->mode == SRIOV_NONE)
+		return -EOPNOTSUPP;
+
+	*mode = dev->priv.eswitch->mode;
+
+	return 0;
+}
+
+void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
+				     struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5_esw_offload *offloads = &esw->offloads;
+
+	memcpy(&offloads->vport_reps[rep->vport], rep,
+	       sizeof(struct mlx5_eswitch_rep));
+
+	INIT_LIST_HEAD(&offloads->vport_reps[rep->vport].vport_sqs_list);
+	offloads->vport_reps[rep->vport].valid = true;
+}
+
+void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw,
+				       int vport)
+{
+	struct mlx5_esw_offload *offloads = &esw->offloads;
+	struct mlx5_eswitch_rep *rep;
+
+	rep = &offloads->vport_reps[vport];
+
+	if (esw->mode == SRIOV_OFFLOADS && esw->vports[vport].enabled)
+		rep->unload(esw, rep);
+
+	offloads->vport_reps[vport].valid = false;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 8b5f0b2c0d5c..b0a130479085 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -67,13 +67,21 @@
 #define FS_REQUIRED_CAPS(...) {.arr_sz = INIT_CAPS_ARRAY_SIZE(__VA_ARGS__), \
 			       .caps = (long[]) {__VA_ARGS__} }
 
+#define FS_CHAINING_CAPS  FS_REQUIRED_CAPS(FS_CAP(flow_table_properties_nic_receive.flow_modify_en), \
+					   FS_CAP(flow_table_properties_nic_receive.modify_root), \
+					   FS_CAP(flow_table_properties_nic_receive.identified_miss_table_mode), \
+					   FS_CAP(flow_table_properties_nic_receive.flow_table_modify))
+
 #define LEFTOVERS_NUM_LEVELS 1
 #define LEFTOVERS_NUM_PRIOS 1
 
 #define BY_PASS_PRIO_NUM_LEVELS 1
-#define BY_PASS_MIN_LEVEL (KERNEL_MIN_LEVEL + MLX5_BY_PASS_NUM_PRIOS +\
+#define BY_PASS_MIN_LEVEL (ETHTOOL_MIN_LEVEL + MLX5_BY_PASS_NUM_PRIOS +\
 			   LEFTOVERS_NUM_PRIOS)
 
+#define ETHTOOL_PRIO_NUM_LEVELS 1
+#define ETHTOOL_NUM_PRIOS 10
+#define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS)
 /* Vlan, mac, ttc, aRFS */
 #define KERNEL_NIC_PRIO_NUM_LEVELS 4
 #define KERNEL_NIC_NUM_PRIOS 1
@@ -83,6 +91,11 @@
 #define ANCHOR_NUM_LEVELS 1
 #define ANCHOR_NUM_PRIOS 1
 #define ANCHOR_MIN_LEVEL (BY_PASS_MIN_LEVEL + 1)
+
+#define OFFLOADS_MAX_FT 1
+#define OFFLOADS_NUM_PRIOS 1
+#define OFFLOADS_MIN_LEVEL (ANCHOR_MIN_LEVEL + 1)
+
 struct node_caps {
 	size_t	arr_sz;
 	long	*caps;
@@ -98,24 +111,24 @@ static struct init_tree_node {
 	int num_levels;
 } root_fs = {
 	.type = FS_TYPE_NAMESPACE,
-	.ar_size = 4,
+	.ar_size = 6,
 	.children = (struct init_tree_node[]) {
 		ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0,
-			 FS_REQUIRED_CAPS(FS_CAP(flow_table_properties_nic_receive.flow_modify_en),
-					  FS_CAP(flow_table_properties_nic_receive.modify_root),
-					  FS_CAP(flow_table_properties_nic_receive.identified_miss_table_mode),
-					  FS_CAP(flow_table_properties_nic_receive.flow_table_modify)),
+			 FS_CHAINING_CAPS,
 			 ADD_NS(ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS,
 						  BY_PASS_PRIO_NUM_LEVELS))),
+		ADD_PRIO(0, OFFLOADS_MIN_LEVEL, 0, {},
+			 ADD_NS(ADD_MULTIPLE_PRIO(OFFLOADS_NUM_PRIOS, OFFLOADS_MAX_FT))),
+		ADD_PRIO(0, ETHTOOL_MIN_LEVEL, 0,
+			 FS_CHAINING_CAPS,
+			 ADD_NS(ADD_MULTIPLE_PRIO(ETHTOOL_NUM_PRIOS,
+						  ETHTOOL_PRIO_NUM_LEVELS))),
 		ADD_PRIO(0, KERNEL_MIN_LEVEL, 0, {},
 			 ADD_NS(ADD_MULTIPLE_PRIO(1, 1),
 				ADD_MULTIPLE_PRIO(KERNEL_NIC_NUM_PRIOS,
 						  KERNEL_NIC_PRIO_NUM_LEVELS))),
 		ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0,
-			 FS_REQUIRED_CAPS(FS_CAP(flow_table_properties_nic_receive.flow_modify_en),
-					  FS_CAP(flow_table_properties_nic_receive.modify_root),
-					  FS_CAP(flow_table_properties_nic_receive.identified_miss_table_mode),
-					  FS_CAP(flow_table_properties_nic_receive.flow_table_modify)),
+			 FS_CHAINING_CAPS,
 			 ADD_NS(ADD_MULTIPLE_PRIO(LEFTOVERS_NUM_PRIOS, LEFTOVERS_NUM_LEVELS))),
 		ADD_PRIO(0, ANCHOR_MIN_LEVEL, 0, {},
 			 ADD_NS(ADD_MULTIPLE_PRIO(ANCHOR_NUM_PRIOS, ANCHOR_NUM_LEVELS))),
@@ -1152,9 +1165,7 @@ static bool dest_is_valid(struct mlx5_flow_destination *dest,
 
 static struct mlx5_flow_rule *
 _mlx5_add_flow_rule(struct mlx5_flow_table *ft,
-		    u8 match_criteria_enable,
-		    u32 *match_criteria,
-		    u32 *match_value,
+		   struct mlx5_flow_spec *spec,
 		    u32 action,
 		    u32 flow_tag,
 		    struct mlx5_flow_destination *dest)
@@ -1168,22 +1179,23 @@ _mlx5_add_flow_rule(struct mlx5_flow_table *ft,
 	nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT);
 	fs_for_each_fg(g, ft)
 		if (compare_match_criteria(g->mask.match_criteria_enable,
-					   match_criteria_enable,
+					   spec->match_criteria_enable,
 					   g->mask.match_criteria,
-					   match_criteria)) {
-			rule = add_rule_fg(g, match_value,
+					   spec->match_criteria)) {
+			rule = add_rule_fg(g, spec->match_value,
 					   action, flow_tag, dest);
 			if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOSPC)
 				goto unlock;
 		}
 
-	g = create_autogroup(ft, match_criteria_enable, match_criteria);
+	g = create_autogroup(ft, spec->match_criteria_enable,
+			     spec->match_criteria);
 	if (IS_ERR(g)) {
 		rule = (void *)g;
 		goto unlock;
 	}
 
-	rule = add_rule_fg(g, match_value,
+	rule = add_rule_fg(g, spec->match_value,
 			   action, flow_tag, dest);
 	if (IS_ERR(rule)) {
 		/* Remove assumes refcount > 0 and autogroup creates a group
@@ -1207,9 +1219,7 @@ static bool fwd_next_prio_supported(struct mlx5_flow_table *ft)
 
 struct mlx5_flow_rule *
 mlx5_add_flow_rule(struct mlx5_flow_table *ft,
-		   u8 match_criteria_enable,
-		   u32 *match_criteria,
-		   u32 *match_value,
+		   struct mlx5_flow_spec *spec,
 		   u32 action,
 		   u32 flow_tag,
 		   struct mlx5_flow_destination *dest)
@@ -1240,8 +1250,7 @@ mlx5_add_flow_rule(struct mlx5_flow_table *ft,
 		}
 	}
 
-	rule =	_mlx5_add_flow_rule(ft, match_criteria_enable, match_criteria,
-				    match_value, action, flow_tag, dest);
+	rule = _mlx5_add_flow_rule(ft, spec, action, flow_tag, dest);
 
 	if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		if (!IS_ERR_OR_NULL(rule) &&
@@ -1292,8 +1301,8 @@ static int update_root_ft_destroy(struct mlx5_flow_table *ft)
 				       ft->id);
 			return err;
 		}
-		root->root_ft = new_root_ft;
 	}
+	root->root_ft = new_root_ft;
 	return 0;
 }
 
@@ -1359,40 +1368,47 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg)
 struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 						    enum mlx5_flow_namespace_type type)
 {
-	struct mlx5_flow_root_namespace *root_ns = dev->priv.root_ns;
+	struct mlx5_flow_steering *steering = dev->priv.steering;
+	struct mlx5_flow_root_namespace *root_ns;
 	int prio;
 	struct fs_prio *fs_prio;
 	struct mlx5_flow_namespace *ns;
 
-	if (!root_ns)
+	if (!steering)
 		return NULL;
 
 	switch (type) {
 	case MLX5_FLOW_NAMESPACE_BYPASS:
+	case MLX5_FLOW_NAMESPACE_OFFLOADS:
+	case MLX5_FLOW_NAMESPACE_ETHTOOL:
 	case MLX5_FLOW_NAMESPACE_KERNEL:
 	case MLX5_FLOW_NAMESPACE_LEFTOVERS:
 	case MLX5_FLOW_NAMESPACE_ANCHOR:
 		prio = type;
 		break;
 	case MLX5_FLOW_NAMESPACE_FDB:
-		if (dev->priv.fdb_root_ns)
-			return &dev->priv.fdb_root_ns->ns;
+		if (steering->fdb_root_ns)
+			return &steering->fdb_root_ns->ns;
 		else
 			return NULL;
 	case MLX5_FLOW_NAMESPACE_ESW_EGRESS:
-		if (dev->priv.esw_egress_root_ns)
-			return &dev->priv.esw_egress_root_ns->ns;
+		if (steering->esw_egress_root_ns)
+			return &steering->esw_egress_root_ns->ns;
 		else
 			return NULL;
 	case MLX5_FLOW_NAMESPACE_ESW_INGRESS:
-		if (dev->priv.esw_ingress_root_ns)
-			return &dev->priv.esw_ingress_root_ns->ns;
+		if (steering->esw_ingress_root_ns)
+			return &steering->esw_ingress_root_ns->ns;
 		else
 			return NULL;
 	default:
 		return NULL;
 	}
 
+	root_ns = steering->root_ns;
+	if (!root_ns)
+		return NULL;
+
 	fs_prio = find_prio(&root_ns->ns, prio);
 	if (!fs_prio)
 		return NULL;
@@ -1478,13 +1494,13 @@ static bool has_required_caps(struct mlx5_core_dev *dev, struct node_caps *caps)
 	return true;
 }
 
-static int init_root_tree_recursive(struct mlx5_core_dev *dev,
+static int init_root_tree_recursive(struct mlx5_flow_steering *steering,
 				    struct init_tree_node *init_node,
 				    struct fs_node *fs_parent_node,
 				    struct init_tree_node *init_parent_node,
 				    int prio)
 {
-	int max_ft_level = MLX5_CAP_FLOWTABLE(dev,
+	int max_ft_level = MLX5_CAP_FLOWTABLE(steering->dev,
 					      flow_table_properties_nic_receive.
 					      max_ft_level);
 	struct mlx5_flow_namespace *fs_ns;
@@ -1495,7 +1511,7 @@ static int init_root_tree_recursive(struct mlx5_core_dev *dev,
 
 	if (init_node->type == FS_TYPE_PRIO) {
 		if ((init_node->min_ft_level > max_ft_level) ||
-		    !has_required_caps(dev, &init_node->caps))
+		    !has_required_caps(steering->dev, &init_node->caps))
 			return 0;
 
 		fs_get_obj(fs_ns, fs_parent_node);
@@ -1516,7 +1532,7 @@ static int init_root_tree_recursive(struct mlx5_core_dev *dev,
 	}
 	prio = 0;
 	for (i = 0; i < init_node->ar_size; i++) {
-		err = init_root_tree_recursive(dev, &init_node->children[i],
+		err = init_root_tree_recursive(steering, &init_node->children[i],
 					       base, init_node, prio);
 		if (err)
 			return err;
@@ -1529,7 +1545,7 @@ static int init_root_tree_recursive(struct mlx5_core_dev *dev,
 	return 0;
 }
 
-static int init_root_tree(struct mlx5_core_dev *dev,
+static int init_root_tree(struct mlx5_flow_steering *steering,
 			  struct init_tree_node *init_node,
 			  struct fs_node *fs_parent_node)
 {
@@ -1539,7 +1555,7 @@ static int init_root_tree(struct mlx5_core_dev *dev,
 
 	fs_get_obj(fs_ns, fs_parent_node);
 	for (i = 0; i < init_node->ar_size; i++) {
-		err = init_root_tree_recursive(dev, &init_node->children[i],
+		err = init_root_tree_recursive(steering, &init_node->children[i],
 					       &fs_ns->node,
 					       init_node, i);
 		if (err)
@@ -1548,7 +1564,7 @@ static int init_root_tree(struct mlx5_core_dev *dev,
 	return 0;
 }
 
-static struct mlx5_flow_root_namespace *create_root_ns(struct mlx5_core_dev *dev,
+static struct mlx5_flow_root_namespace *create_root_ns(struct mlx5_flow_steering *steering,
 						       enum fs_flow_table_type
 						       table_type)
 {
@@ -1560,7 +1576,7 @@ static struct mlx5_flow_root_namespace *create_root_ns(struct mlx5_core_dev *dev
 	if (!root_ns)
 		return NULL;
 
-	root_ns->dev = dev;
+	root_ns->dev = steering->dev;
 	root_ns->table_type = table_type;
 
 	ns = &root_ns->ns;
@@ -1615,209 +1631,126 @@ static void set_prio_attrs(struct mlx5_flow_root_namespace *root_ns)
 #define ANCHOR_PRIO 0
 #define ANCHOR_SIZE 1
 #define ANCHOR_LEVEL 0
-static int create_anchor_flow_table(struct mlx5_core_dev
-							*dev)
+static int create_anchor_flow_table(struct mlx5_flow_steering *steering)
 {
 	struct mlx5_flow_namespace *ns = NULL;
 	struct mlx5_flow_table *ft;
 
-	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ANCHOR);
+	ns = mlx5_get_flow_namespace(steering->dev, MLX5_FLOW_NAMESPACE_ANCHOR);
 	if (!ns)
 		return -EINVAL;
 	ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL);
 	if (IS_ERR(ft)) {
-		mlx5_core_err(dev, "Failed to create last anchor flow table");
+		mlx5_core_err(steering->dev, "Failed to create last anchor flow table");
 		return PTR_ERR(ft);
 	}
 	return 0;
 }
 
-static int init_root_ns(struct mlx5_core_dev *dev)
+static int init_root_ns(struct mlx5_flow_steering *steering)
 {
 
-	dev->priv.root_ns = create_root_ns(dev, FS_FT_NIC_RX);
-	if (IS_ERR_OR_NULL(dev->priv.root_ns))
+	steering->root_ns = create_root_ns(steering, FS_FT_NIC_RX);
+	if (IS_ERR_OR_NULL(steering->root_ns))
 		goto cleanup;
 
-	if (init_root_tree(dev, &root_fs, &dev->priv.root_ns->ns.node))
+	if (init_root_tree(steering, &root_fs, &steering->root_ns->ns.node))
 		goto cleanup;
 
-	set_prio_attrs(dev->priv.root_ns);
+	set_prio_attrs(steering->root_ns);
 
-	if (create_anchor_flow_table(dev))
+	if (create_anchor_flow_table(steering))
 		goto cleanup;
 
 	return 0;
 
 cleanup:
-	mlx5_cleanup_fs(dev);
+	mlx5_cleanup_fs(steering->dev);
 	return -ENOMEM;
 }
 
-static void cleanup_single_prio_root_ns(struct mlx5_core_dev *dev,
-					struct mlx5_flow_root_namespace *root_ns)
+static void clean_tree(struct fs_node *node)
 {
-	struct fs_node *prio;
-
-	if (!root_ns)
-		return;
+	if (node) {
+		struct fs_node *iter;
+		struct fs_node *temp;
 
-	if (!list_empty(&root_ns->ns.node.children)) {
-		prio = list_first_entry(&root_ns->ns.node.children,
-					struct fs_node,
-				 list);
-		if (tree_remove_node(prio))
-			mlx5_core_warn(dev,
-				       "Flow steering priority wasn't destroyed, refcount > 1\n");
+		list_for_each_entry_safe(iter, temp, &node->children, list)
+			clean_tree(iter);
+		tree_remove_node(node);
 	}
-	if (tree_remove_node(&root_ns->ns.node))
-		mlx5_core_warn(dev,
-			       "Flow steering namespace wasn't destroyed, refcount > 1\n");
-	root_ns = NULL;
-}
-
-static void destroy_flow_tables(struct fs_prio *prio)
-{
-	struct mlx5_flow_table *iter;
-	struct mlx5_flow_table *tmp;
-
-	fs_for_each_ft_safe(iter, tmp, prio)
-		mlx5_destroy_flow_table(iter);
 }
 
-static void cleanup_root_ns(struct mlx5_core_dev *dev)
+static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns)
 {
-	struct mlx5_flow_root_namespace *root_ns = dev->priv.root_ns;
-	struct fs_prio *iter_prio;
-
-	if (!MLX5_CAP_GEN(dev, nic_flow_table))
-		return;
-
 	if (!root_ns)
 		return;
 
-	/* stage 1 */
-	fs_for_each_prio(iter_prio, &root_ns->ns) {
-		struct fs_node *node;
-		struct mlx5_flow_namespace *iter_ns;
-
-		fs_for_each_ns_or_ft(node, iter_prio) {
-			if (node->type == FS_TYPE_FLOW_TABLE)
-				continue;
-			fs_get_obj(iter_ns, node);
-			while (!list_empty(&iter_ns->node.children)) {
-				struct fs_prio *obj_iter_prio2;
-				struct fs_node *iter_prio2 =
-					list_first_entry(&iter_ns->node.children,
-							 struct fs_node,
-							 list);
-
-				fs_get_obj(obj_iter_prio2, iter_prio2);
-				destroy_flow_tables(obj_iter_prio2);
-				if (tree_remove_node(iter_prio2)) {
-					mlx5_core_warn(dev,
-						       "Priority %d wasn't destroyed, refcount > 1\n",
-						       obj_iter_prio2->prio);
-					return;
-				}
-			}
-		}
-	}
-
-	/* stage 2 */
-	fs_for_each_prio(iter_prio, &root_ns->ns) {
-		while (!list_empty(&iter_prio->node.children)) {
-			struct fs_node *iter_ns =
-				list_first_entry(&iter_prio->node.children,
-						 struct fs_node,
-						 list);
-			if (tree_remove_node(iter_ns)) {
-				mlx5_core_warn(dev,
-					       "Namespace wasn't destroyed, refcount > 1\n");
-				return;
-			}
-		}
-	}
-
-	/* stage 3 */
-	while (!list_empty(&root_ns->ns.node.children)) {
-		struct fs_prio *obj_prio_node;
-		struct fs_node *prio_node =
-			list_first_entry(&root_ns->ns.node.children,
-					 struct fs_node,
-					 list);
-
-		fs_get_obj(obj_prio_node, prio_node);
-		if (tree_remove_node(prio_node)) {
-			mlx5_core_warn(dev,
-				       "Priority %d wasn't destroyed, refcount > 1\n",
-				       obj_prio_node->prio);
-			return;
-		}
-	}
-
-	if (tree_remove_node(&root_ns->ns.node)) {
-		mlx5_core_warn(dev,
-			       "root namespace wasn't destroyed, refcount > 1\n");
-		return;
-	}
-
-	dev->priv.root_ns = NULL;
+	clean_tree(&root_ns->ns.node);
 }
 
 void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
 {
-	cleanup_root_ns(dev);
-	cleanup_single_prio_root_ns(dev, dev->priv.fdb_root_ns);
-	cleanup_single_prio_root_ns(dev, dev->priv.esw_egress_root_ns);
-	cleanup_single_prio_root_ns(dev, dev->priv.esw_ingress_root_ns);
+	struct mlx5_flow_steering *steering = dev->priv.steering;
+
+	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
+		return;
+
+	cleanup_root_ns(steering->root_ns);
+	cleanup_root_ns(steering->esw_egress_root_ns);
+	cleanup_root_ns(steering->esw_ingress_root_ns);
+	cleanup_root_ns(steering->fdb_root_ns);
 	mlx5_cleanup_fc_stats(dev);
+	kfree(steering);
 }
 
-static int init_fdb_root_ns(struct mlx5_core_dev *dev)
+static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 {
 	struct fs_prio *prio;
 
-	dev->priv.fdb_root_ns = create_root_ns(dev, FS_FT_FDB);
-	if (!dev->priv.fdb_root_ns)
+	steering->fdb_root_ns = create_root_ns(steering, FS_FT_FDB);
+	if (!steering->fdb_root_ns)
 		return -ENOMEM;
 
 	/* Create single prio */
-	prio = fs_create_prio(&dev->priv.fdb_root_ns->ns, 0, 1);
+	prio = fs_create_prio(&steering->fdb_root_ns->ns, 0, 1);
 	if (IS_ERR(prio)) {
-		cleanup_single_prio_root_ns(dev, dev->priv.fdb_root_ns);
+		cleanup_root_ns(steering->fdb_root_ns);
+		steering->fdb_root_ns = NULL;
 		return PTR_ERR(prio);
 	} else {
 		return 0;
 	}
 }
 
-static int init_egress_acl_root_ns(struct mlx5_core_dev *dev)
+static int init_ingress_acl_root_ns(struct mlx5_flow_steering *steering)
 {
 	struct fs_prio *prio;
 
-	dev->priv.esw_egress_root_ns = create_root_ns(dev, FS_FT_ESW_EGRESS_ACL);
-	if (!dev->priv.esw_egress_root_ns)
+	steering->esw_egress_root_ns = create_root_ns(steering, FS_FT_ESW_EGRESS_ACL);
+	if (!steering->esw_egress_root_ns)
 		return -ENOMEM;
 
 	/* create 1 prio*/
-	prio = fs_create_prio(&dev->priv.esw_egress_root_ns->ns, 0, MLX5_TOTAL_VPORTS(dev));
+	prio = fs_create_prio(&steering->esw_egress_root_ns->ns, 0,
+			      MLX5_TOTAL_VPORTS(steering->dev));
 	if (IS_ERR(prio))
 		return PTR_ERR(prio);
 	else
 		return 0;
 }
 
-static int init_ingress_acl_root_ns(struct mlx5_core_dev *dev)
+static int init_egress_acl_root_ns(struct mlx5_flow_steering *steering)
 {
 	struct fs_prio *prio;
 
-	dev->priv.esw_ingress_root_ns = create_root_ns(dev, FS_FT_ESW_INGRESS_ACL);
-	if (!dev->priv.esw_ingress_root_ns)
+	steering->esw_ingress_root_ns = create_root_ns(steering, FS_FT_ESW_INGRESS_ACL);
+	if (!steering->esw_ingress_root_ns)
 		return -ENOMEM;
 
 	/* create 1 prio*/
-	prio = fs_create_prio(&dev->priv.esw_ingress_root_ns->ns, 0, MLX5_TOTAL_VPORTS(dev));
+	prio = fs_create_prio(&steering->esw_ingress_root_ns->ns, 0,
+			      MLX5_TOTAL_VPORTS(steering->dev));
 	if (IS_ERR(prio))
 		return PTR_ERR(prio);
 	else
@@ -1826,31 +1759,45 @@ static int init_ingress_acl_root_ns(struct mlx5_core_dev *dev)
 
 int mlx5_init_fs(struct mlx5_core_dev *dev)
 {
+	struct mlx5_flow_steering *steering;
 	int err = 0;
 
+	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
+		return 0;
+
 	err = mlx5_init_fc_stats(dev);
 	if (err)
 		return err;
 
-	if (MLX5_CAP_GEN(dev, nic_flow_table)) {
-		err = init_root_ns(dev);
+	steering = kzalloc(sizeof(*steering), GFP_KERNEL);
+	if (!steering)
+		return -ENOMEM;
+	steering->dev = dev;
+	dev->priv.steering = steering;
+
+	if (MLX5_CAP_GEN(dev, nic_flow_table) &&
+	    MLX5_CAP_FLOWTABLE_NIC_RX(dev, ft_support)) {
+		err = init_root_ns(steering);
 		if (err)
 			goto err;
 	}
+
 	if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
-		err = init_fdb_root_ns(dev);
-		if (err)
-			goto err;
-	}
-	if (MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support)) {
-		err = init_egress_acl_root_ns(dev);
-		if (err)
-			goto err;
-	}
-	if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) {
-		err = init_ingress_acl_root_ns(dev);
-		if (err)
-			goto err;
+		if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) {
+			err = init_fdb_root_ns(steering);
+			if (err)
+				goto err;
+		}
+		if (MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support)) {
+			err = init_egress_acl_root_ns(steering);
+			if (err)
+				goto err;
+		}
+		if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) {
+			err = init_ingress_acl_root_ns(steering);
+			if (err)
+				goto err;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index aa41a7314691..d7ba91a1eea2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -55,6 +55,14 @@ enum fs_fte_status {
 	FS_FTE_STATUS_EXISTING = 1UL << 0,
 };
 
+struct mlx5_flow_steering {
+	struct mlx5_core_dev *dev;
+	struct mlx5_flow_root_namespace *root_ns;
+	struct mlx5_flow_root_namespace *fdb_root_ns;
+	struct mlx5_flow_root_namespace *esw_egress_root_ns;
+	struct mlx5_flow_root_namespace *esw_ingress_root_ns;
+};
+
 struct fs_node {
 	struct list_head	list;
 	struct list_head	children;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 75c7ae6a5cc4..77fc1aa26114 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -151,6 +151,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
+	if (MLX5_CAP_GEN(dev, qos)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_QOS);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a19b59348dd6..1fb3c681df97 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -51,6 +51,7 @@
 #ifdef CONFIG_RFS_ACCEL
 #include <linux/cpu_rmap.h>
 #endif
+#include <net/devlink.h>
 #include "mlx5_core.h"
 #include "fs_core.h"
 #ifdef CONFIG_MLX5_CORE_EN
@@ -1144,6 +1145,13 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 		dev_err(&pdev->dev, "Failed to init flow steering\n");
 		goto err_fs;
 	}
+
+	err = mlx5_init_rl_table(dev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to init rate limiting\n");
+		goto err_rl;
+	}
+
 #ifdef CONFIG_MLX5_CORE_EN
 	err = mlx5_eswitch_init(dev);
 	if (err) {
@@ -1183,6 +1191,8 @@ err_sriov:
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
 #endif
 err_reg_dev:
+	mlx5_cleanup_rl_table(dev);
+err_rl:
 	mlx5_cleanup_fs(dev);
 err_fs:
 	mlx5_cleanup_mkey_table(dev);
@@ -1253,6 +1263,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
 #endif
 
+	mlx5_cleanup_rl_table(dev);
 	mlx5_cleanup_fs(dev);
 	mlx5_cleanup_mkey_table(dev);
 	mlx5_cleanup_srq_table(dev);
@@ -1305,19 +1316,28 @@ struct mlx5_core_event_handler {
 		      void *data);
 };
 
+static const struct devlink_ops mlx5_devlink_ops = {
+#ifdef CONFIG_MLX5_CORE_EN
+	.eswitch_mode_set = mlx5_devlink_eswitch_mode_set,
+	.eswitch_mode_get = mlx5_devlink_eswitch_mode_get,
+#endif
+};
 
 static int init_one(struct pci_dev *pdev,
 		    const struct pci_device_id *id)
 {
 	struct mlx5_core_dev *dev;
+	struct devlink *devlink;
 	struct mlx5_priv *priv;
 	int err;
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev) {
+	devlink = devlink_alloc(&mlx5_devlink_ops, sizeof(*dev));
+	if (!devlink) {
 		dev_err(&pdev->dev, "kzalloc failed\n");
 		return -ENOMEM;
 	}
+
+	dev = devlink_priv(devlink);
 	priv = &dev->priv;
 	priv->pci_dev_data = id->driver_data;
 
@@ -1354,15 +1374,21 @@ static int init_one(struct pci_dev *pdev,
 		goto clean_health;
 	}
 
+	err = devlink_register(devlink, &pdev->dev);
+	if (err)
+		goto clean_load;
+
 	return 0;
 
+clean_load:
+	mlx5_unload_one(dev, priv);
 clean_health:
 	mlx5_health_cleanup(dev);
 close_pci:
 	mlx5_pci_close(dev, priv);
 clean_dev:
 	pci_set_drvdata(pdev, NULL);
-	kfree(dev);
+	devlink_free(devlink);
 
 	return err;
 }
@@ -1370,8 +1396,10 @@ clean_dev:
 static void remove_one(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
+	struct devlink *devlink = priv_to_devlink(dev);
 	struct mlx5_priv *priv = &dev->priv;
 
+	devlink_unregister(devlink);
 	if (mlx5_unload_one(dev, priv)) {
 		dev_err(&dev->pdev->dev, "mlx5_unload_one failed\n");
 		mlx5_health_cleanup(dev);
@@ -1380,7 +1408,7 @@ static void remove_one(struct pci_dev *pdev)
 	mlx5_health_cleanup(dev);
 	mlx5_pci_close(dev, priv);
 	pci_set_drvdata(pdev, NULL);
-	kfree(dev);
+	devlink_free(devlink);
 }
 
 static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
@@ -1508,8 +1536,9 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x1014), MLX5_PCI_DEV_IS_VF},	/* ConnectX-4 VF */
 	{ PCI_VDEVICE(MELLANOX, 0x1015) },			/* ConnectX-4LX */
 	{ PCI_VDEVICE(MELLANOX, 0x1016), MLX5_PCI_DEV_IS_VF},	/* ConnectX-4LX VF */
-	{ PCI_VDEVICE(MELLANOX, 0x1017) },			/* ConnectX-5 */
+	{ PCI_VDEVICE(MELLANOX, 0x1017) },			/* ConnectX-5, PCIe 3.0 */
 	{ PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF},	/* ConnectX-5 VF */
+	{ PCI_VDEVICE(MELLANOX, 0x1019) },			/* ConnectX-5, PCIe 4.0 */
 	{ 0, }
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 3e35611b19c3..752c08127138 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -202,15 +202,24 @@ int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_proto_oper);
 
-int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin,
-			int proto_mask)
+int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable,
+		       u32 proto_admin, int proto_mask)
 {
-	u32 in[MLX5_ST_SZ_DW(ptys_reg)];
 	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	u32 in[MLX5_ST_SZ_DW(ptys_reg)];
+	u8 an_disable_admin;
+	u8 an_disable_cap;
+	u8 an_status;
+
+	mlx5_query_port_autoneg(dev, proto_mask, &an_status,
+				&an_disable_cap, &an_disable_admin);
+	if (!an_disable_cap && an_disable)
+		return -EPERM;
 
 	memset(in, 0, sizeof(in));
 
 	MLX5_SET(ptys_reg, in, local_port, 1);
+	MLX5_SET(ptys_reg, in, an_disable_admin, an_disable);
 	MLX5_SET(ptys_reg, in, proto_mask, proto_mask);
 	if (proto_mask == MLX5_PTYS_EN)
 		MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
@@ -220,7 +229,19 @@ int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin,
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				    sizeof(out), MLX5_REG_PTYS, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_proto);
+EXPORT_SYMBOL_GPL(mlx5_set_port_ptys);
+
+/* This function should be used after setting a port register only */
+void mlx5_toggle_port_link(struct mlx5_core_dev *dev)
+{
+	enum mlx5_port_status ps;
+
+	mlx5_query_port_admin_status(dev, &ps);
+	mlx5_set_port_admin_status(dev, MLX5_PORT_DOWN);
+	if (ps == MLX5_PORT_UP)
+		mlx5_set_port_admin_status(dev, MLX5_PORT_UP);
+}
+EXPORT_SYMBOL_GPL(mlx5_toggle_port_link);
 
 int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 			       enum mlx5_port_status status)
@@ -518,6 +539,25 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_pfc);
 
+void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask,
+			     u8 *an_status,
+			     u8 *an_disable_cap, u8 *an_disable_admin)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+
+	*an_status = 0;
+	*an_disable_cap = 0;
+	*an_disable_admin = 0;
+
+	if (mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1))
+		return;
+
+	*an_status = MLX5_GET(ptys_reg, out, an_status);
+	*an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap);
+	*an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
+}
+EXPORT_SYMBOL_GPL(mlx5_query_port_autoneg);
+
 int mlx5_max_tc(struct mlx5_core_dev *mdev)
 {
 	u8 num_tc = MLX5_CAP_GEN(mdev, max_tc) ? : 8;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index b720a274220d..b82d65802d96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -418,7 +418,7 @@ int mlx5_core_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn)
 	if (out.hdr.status)
 		err = mlx5_cmd_status_to_err(&out.hdr);
 	else
-		*xrcdn = be32_to_cpu(out.xrcdn);
+		*xrcdn = be32_to_cpu(out.xrcdn) & 0xffffff;
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
new file mode 100644
index 000000000000..c07c28bd3d55
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -0,0 +1,209 @@
+/*
+ * Copyright (c) 2013-2016, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/cmd.h>
+#include "mlx5_core.h"
+
+/* Finds an entry where we can register the given rate
+ * If the rate already exists, return the entry where it is registered,
+ * otherwise return the first available entry.
+ * If the table is full, return NULL
+ */
+static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table,
+					   u32 rate)
+{
+	struct mlx5_rl_entry *ret_entry = NULL;
+	bool empty_found = false;
+	int i;
+
+	for (i = 0; i < table->max_size; i++) {
+		if (table->rl_entry[i].rate == rate)
+			return &table->rl_entry[i];
+		if (!empty_found && !table->rl_entry[i].rate) {
+			empty_found = true;
+			ret_entry = &table->rl_entry[i];
+		}
+	}
+
+	return ret_entry;
+}
+
+static int mlx5_set_rate_limit_cmd(struct mlx5_core_dev *dev,
+				   u32 rate, u16 index)
+{
+	u32 in[MLX5_ST_SZ_DW(set_rate_limit_in)];
+	u32 out[MLX5_ST_SZ_DW(set_rate_limit_out)];
+
+	memset(in, 0, sizeof(in));
+	memset(out, 0, sizeof(out));
+
+	MLX5_SET(set_rate_limit_in, in, opcode,
+		 MLX5_CMD_OP_SET_RATE_LIMIT);
+	MLX5_SET(set_rate_limit_in, in, rate_limit_index, index);
+	MLX5_SET(set_rate_limit_in, in, rate_limit, rate);
+
+	return mlx5_cmd_exec_check_status(dev, in, sizeof(in),
+					  out, sizeof(out));
+}
+
+bool mlx5_rl_is_in_range(struct mlx5_core_dev *dev, u32 rate)
+{
+	struct mlx5_rl_table *table = &dev->priv.rl_table;
+
+	return (rate <= table->max_rate && rate >= table->min_rate);
+}
+EXPORT_SYMBOL(mlx5_rl_is_in_range);
+
+int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index)
+{
+	struct mlx5_rl_table *table = &dev->priv.rl_table;
+	struct mlx5_rl_entry *entry;
+	int err = 0;
+
+	mutex_lock(&table->rl_lock);
+
+	if (!rate || !mlx5_rl_is_in_range(dev, rate)) {
+		mlx5_core_err(dev, "Invalid rate: %u, should be %u to %u\n",
+			      rate, table->min_rate, table->max_rate);
+		err = -EINVAL;
+		goto out;
+	}
+
+	entry = find_rl_entry(table, rate);
+	if (!entry) {
+		mlx5_core_err(dev, "Max number of %u rates reached\n",
+			      table->max_size);
+		err = -ENOSPC;
+		goto out;
+	}
+	if (entry->refcount) {
+		/* rate already configured */
+		entry->refcount++;
+	} else {
+		/* new rate limit */
+		err = mlx5_set_rate_limit_cmd(dev, rate, entry->index);
+		if (err) {
+			mlx5_core_err(dev, "Failed configuring rate: %u (%d)\n",
+				      rate, err);
+			goto out;
+		}
+		entry->rate = rate;
+		entry->refcount = 1;
+	}
+	*index = entry->index;
+
+out:
+	mutex_unlock(&table->rl_lock);
+	return err;
+}
+EXPORT_SYMBOL(mlx5_rl_add_rate);
+
+void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate)
+{
+	struct mlx5_rl_table *table = &dev->priv.rl_table;
+	struct mlx5_rl_entry *entry = NULL;
+
+	/* 0 is a reserved value for unlimited rate */
+	if (rate == 0)
+		return;
+
+	mutex_lock(&table->rl_lock);
+	entry = find_rl_entry(table, rate);
+	if (!entry || !entry->refcount) {
+		mlx5_core_warn(dev, "Rate %u is not configured\n", rate);
+		goto out;
+	}
+
+	entry->refcount--;
+	if (!entry->refcount) {
+		/* need to remove rate */
+		mlx5_set_rate_limit_cmd(dev, 0, entry->index);
+		entry->rate = 0;
+	}
+
+out:
+	mutex_unlock(&table->rl_lock);
+}
+EXPORT_SYMBOL(mlx5_rl_remove_rate);
+
+int mlx5_init_rl_table(struct mlx5_core_dev *dev)
+{
+	struct mlx5_rl_table *table = &dev->priv.rl_table;
+	int i;
+
+	mutex_init(&table->rl_lock);
+	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, packet_pacing)) {
+		table->max_size = 0;
+		return 0;
+	}
+
+	/* First entry is reserved for unlimited rate */
+	table->max_size = MLX5_CAP_QOS(dev, packet_pacing_rate_table_size) - 1;
+	table->max_rate = MLX5_CAP_QOS(dev, packet_pacing_max_rate);
+	table->min_rate = MLX5_CAP_QOS(dev, packet_pacing_min_rate);
+
+	table->rl_entry = kcalloc(table->max_size, sizeof(struct mlx5_rl_entry),
+				  GFP_KERNEL);
+	if (!table->rl_entry)
+		return -ENOMEM;
+
+	/* The index represents the index in HW rate limit table
+	 * Index 0 is reserved for unlimited rate
+	 */
+	for (i = 0; i < table->max_size; i++)
+		table->rl_entry[i].index = i + 1;
+
+	/* Index 0 is reserved */
+	mlx5_core_info(dev, "Rate limit: %u rates are supported, range: %uMbps to %uMbps\n",
+		       table->max_size,
+		       table->min_rate >> 10,
+		       table->max_rate >> 10);
+
+	return 0;
+}
+
+void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev)
+{
+	struct mlx5_rl_table *table = &dev->priv.rl_table;
+	int i;
+
+	/* Clear all configured rates */
+	for (i = 0; i < table->max_size; i++)
+		if (table->rl_entry[i].rate)
+			mlx5_set_rate_limit_cmd(dev, 0,
+						table->rl_entry[i].index);
+
+	kfree(dev->priv.rl_table.rl_entry);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index d6a3f412ba9f..b380a6bc1f85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -167,7 +167,7 @@ int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs)
 
 	mlx5_core_init_vfs(dev, num_vfs);
 #ifdef CONFIG_MLX5_CORE_EN
-	mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs);
+	mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY);
 #endif
 
 	return num_vfs;
@@ -209,7 +209,8 @@ int mlx5_sriov_init(struct mlx5_core_dev *dev)
 	mlx5_core_init_vfs(dev, cur_vfs);
 #ifdef CONFIG_MLX5_CORE_EN
 	if (cur_vfs)
-		mlx5_eswitch_enable_sriov(dev->priv.eswitch, cur_vfs);
+		mlx5_eswitch_enable_sriov(dev->priv.eswitch, cur_vfs,
+					  SRIOV_LEGACY);
 #endif
 
 	enable_vfs(dev, cur_vfs);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index b69dadcfb897..daf44cd4c566 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -508,6 +508,44 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid);
 
+int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
+				    u32 vport, u64 node_guid)
+{
+	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
+	void *nic_vport_context;
+	u8 *guid;
+	void *in;
+	int err;
+
+	if (!vport)
+		return -EINVAL;
+	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
+		return -EACCES;
+	if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify))
+		return -ENOTSUPP;
+
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(modify_nic_vport_context_in, in,
+		 field_select.node_guid, 1);
+	MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
+	MLX5_SET(modify_nic_vport_context_in, in, other_vport, !!vport);
+
+	nic_vport_context = MLX5_ADDR_OF(modify_nic_vport_context_in,
+					 in, nic_vport_context);
+	guid = MLX5_ADDR_OF(nic_vport_context, nic_vport_context,
+			    node_guid);
+	MLX5_SET64(nic_vport_context, nic_vport_context, node_guid, node_guid);
+
+	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
+
+	kvfree(in);
+
+	return err;
+}
+
 int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
 					u16 *qkey_viol_cntr)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index f2fd1ef16da7..05de77267d58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -105,6 +105,9 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 	struct mlx5e_vxlan *vxlan;
 	int err;
 
+	if (mlx5e_vxlan_lookup_port(priv, port))
+		goto free_work;
+
 	if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
 		goto free_work;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index ce21ee5b2357..821a087c7ae2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -75,14 +75,14 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err);
 		return err;
 	}
 
 	err = mlx5_buf_alloc_node(mdev, mlx5_wq_cyc_get_byte_size(wq),
 				  &wq_ctrl->buf, param->buf_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
 		goto err_db_free;
 	}
 
@@ -111,14 +111,14 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err);
 		return err;
 	}
 
 	err = mlx5_buf_alloc_node(mdev, mlx5_cqwq_get_byte_size(wq),
 				  &wq_ctrl->buf, param->buf_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
 		goto err_db_free;
 	}
 
@@ -148,13 +148,14 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err);
 		return err;
 	}
 
-	err = mlx5_buf_alloc(mdev, mlx5_wq_ll_get_byte_size(wq), &wq_ctrl->buf);
+	err = mlx5_buf_alloc_node(mdev, mlx5_wq_ll_get_byte_size(wq),
+				  &wq_ctrl->buf, param->buf_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
 		goto err_db_free;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 9b5ebf84c051..d20ae1838a64 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -7,5 +7,6 @@ obj-$(CONFIG_MLXSW_SWITCHX2)	+= mlxsw_switchx2.o
 mlxsw_switchx2-objs		:= switchx2.o
 obj-$(CONFIG_MLXSW_SPECTRUM)	+= mlxsw_spectrum.o
 mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
-				   spectrum_switchdev.o
+				   spectrum_switchdev.o spectrum_router.o \
+				   spectrum_kvdl.o
 mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB)	+= spectrum_dcb.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
index cd63b8263688..f9cd6e3f7709 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
@@ -607,6 +607,24 @@ MLXSW_ITEM32(cmd_mbox, config_profile,
  */
 MLXSW_ITEM32(cmd_mbox, config_profile, set_ar_sec, 0x0C, 15, 1);
 
+/* cmd_mbox_config_set_kvd_linear_size
+ * Capability bit. Setting a bit to 1 configures the profile
+ * according to the mailbox contents.
+ */
+MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_linear_size, 0x0C, 24, 1);
+
+/* cmd_mbox_config_set_kvd_hash_single_size
+ * Capability bit. Setting a bit to 1 configures the profile
+ * according to the mailbox contents.
+ */
+MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_single_size, 0x0C, 25, 1);
+
+/* cmd_mbox_config_set_kvd_hash_double_size
+ * Capability bit. Setting a bit to 1 configures the profile
+ * according to the mailbox contents.
+ */
+MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_double_size, 0x0C, 26, 1);
+
 /* cmd_mbox_config_profile_max_vepa_channels
  * Maximum number of VEPA channels per port (0 through 16)
  * 0 - multi-channel VEPA is disabled
@@ -733,6 +751,31 @@ MLXSW_ITEM32(cmd_mbox, config_profile, adaptive_routing_group_cap, 0x4C, 0, 16);
  */
 MLXSW_ITEM32(cmd_mbox, config_profile, arn, 0x50, 31, 1);
 
+/* cmd_mbox_config_kvd_linear_size
+ * KVD Linear Size
+ * Valid for Spectrum only
+ * Allowed values are 128*N where N=0 or higher
+ */
+MLXSW_ITEM32(cmd_mbox, config_profile, kvd_linear_size, 0x54, 0, 24);
+
+/* cmd_mbox_config_kvd_hash_single_size
+ * KVD Hash single-entries size
+ * Valid for Spectrum only
+ * Allowed values are 128*N where N=0 or higher
+ * Must be greater or equal to cap_min_kvd_hash_single_size
+ * Must be smaller or equal to cap_kvd_size - kvd_linear_size
+ */
+MLXSW_ITEM32(cmd_mbox, config_profile, kvd_hash_single_size, 0x58, 0, 24);
+
+/* cmd_mbox_config_kvd_hash_double_size
+ * KVD Hash double-entries size (units of single-size entries)
+ * Valid for Spectrum only
+ * Allowed values are 128*N where N=0 or higher
+ * Must be either 0 or greater or equal to cap_min_kvd_hash_double_size
+ * Must be smaller or equal to cap_kvd_size - kvd_linear_size
+ */
+MLXSW_ITEM32(cmd_mbox, config_profile, kvd_hash_double_size, 0x5C, 0, 24);
+
 /* cmd_mbox_config_profile_swid_config_mask
  * Modify Switch Partition Configuration mask. When set, the configu-
  * ration value for the Switch Partition are taken from the mailbox.
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index b0a0b01bb4ef..01ae54826d5c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1736,7 +1736,7 @@ static int __init mlxsw_core_module_init(void)
 {
 	int err;
 
-	mlxsw_wq = create_workqueue(mlxsw_core_driver_name);
+	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0);
 	if (!mlxsw_wq)
 		return -ENOMEM;
 	mlxsw_core_dbg_root = debugfs_create_dir(mlxsw_core_driver_name, NULL);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 436bc49df6ab..2fe385cce203 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -190,7 +190,8 @@ struct mlxsw_config_profile {
 		used_max_ib_mc:1,
 		used_max_pkey:1,
 		used_ar_sec:1,
-		used_adaptive_routing_group_cap:1;
+		used_adaptive_routing_group_cap:1,
+		used_kvd_sizes:1;
 	u8	max_vepa_channels;
 	u16	max_lag;
 	u16	max_port_per_lag;
@@ -211,6 +212,9 @@ struct mlxsw_config_profile {
 	u8	ar_sec;
 	u16	adaptive_routing_group_cap;
 	u8	arn;
+	u32	kvd_linear_size;
+	u32	kvd_hash_single_size;
+	u32	kvd_hash_double_size;
 	struct mlxsw_swid_config swid_config[MLXSW_CONFIG_PROFILE_SWID_COUNT];
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 7f4173c8eda3..ddbc9f22278d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1255,6 +1255,20 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox,
 		mlxsw_cmd_mbox_config_profile_adaptive_routing_group_cap_set(
 			mbox, profile->adaptive_routing_group_cap);
 	}
+	if (profile->used_kvd_sizes) {
+		mlxsw_cmd_mbox_config_profile_set_kvd_linear_size_set(
+			mbox, 1);
+		mlxsw_cmd_mbox_config_profile_kvd_linear_size_set(
+			mbox, profile->kvd_linear_size);
+		mlxsw_cmd_mbox_config_profile_set_kvd_hash_single_size_set(
+			mbox, 1);
+		mlxsw_cmd_mbox_config_profile_kvd_hash_single_size_set(
+			mbox, profile->kvd_hash_single_size);
+		mlxsw_cmd_mbox_config_profile_set_kvd_hash_double_size_set(
+			mbox, 1);
+		mlxsw_cmd_mbox_config_profile_kvd_hash_double_size_set(
+			mbox, profile->kvd_hash_double_size);
+	}
 
 	for (i = 0; i < MLXSW_CONFIG_PROFILE_SWID_COUNT; i++)
 		mlxsw_pci_config_profile_swid_config(mlxsw_pci, mbox, i,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 1977e7a5c530..0cc148566677 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -1,9 +1,10 @@
 /*
  * drivers/net/ethernet/mellanox/mlxsw/reg.h
  * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Ido Schimmel <[email protected]>
+ * Copyright (c) 2015-2016 Ido Schimmel <[email protected]>
  * Copyright (c) 2015 Elad Raz <[email protected]>
- * Copyright (c) 2015 Jiri Pirko <[email protected]>
+ * Copyright (c) 2015-2016 Jiri Pirko <[email protected]>
+ * Copyright (c) 2016 Yotam Gigi <[email protected]>
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -386,7 +387,9 @@ enum mlxsw_reg_sfd_rec_action {
 	/* forward and trap, trap_id is FDB_TRAP */
 	MLXSW_REG_SFD_REC_ACTION_MIRROR_TO_CPU = 1,
 	/* trap and do not forward, trap_id is FDB_TRAP */
-	MLXSW_REG_SFD_REC_ACTION_TRAP = 3,
+	MLXSW_REG_SFD_REC_ACTION_TRAP = 2,
+	/* forward to IP router */
+	MLXSW_REG_SFD_REC_ACTION_FORWARD_IP_ROUTER = 3,
 	MLXSW_REG_SFD_REC_ACTION_DISCARD_ERROR = 15,
 };
 
@@ -3186,6 +3189,1183 @@ static inline void mlxsw_reg_hpkt_pack(char *payload, u8 action, u16 trap_id)
 	mlxsw_reg_hpkt_ctrl_set(payload, MLXSW_REG_HPKT_CTRL_PACKET_DEFAULT);
 }
 
+/* RGCR - Router General Configuration Register
+ * --------------------------------------------
+ * The register is used for setting up the router configuration.
+ */
+#define MLXSW_REG_RGCR_ID 0x8001
+#define MLXSW_REG_RGCR_LEN 0x28
+
+static const struct mlxsw_reg_info mlxsw_reg_rgcr = {
+	.id = MLXSW_REG_RGCR_ID,
+	.len = MLXSW_REG_RGCR_LEN,
+};
+
+/* reg_rgcr_ipv4_en
+ * IPv4 router enable.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rgcr, ipv4_en, 0x00, 31, 1);
+
+/* reg_rgcr_ipv6_en
+ * IPv6 router enable.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rgcr, ipv6_en, 0x00, 30, 1);
+
+/* reg_rgcr_max_router_interfaces
+ * Defines the maximum number of active router interfaces for all virtual
+ * routers.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rgcr, max_router_interfaces, 0x10, 0, 16);
+
+/* reg_rgcr_usp
+ * Update switch priority and packet color.
+ * 0 - Preserve the value of Switch Priority and packet color.
+ * 1 - Recalculate the value of Switch Priority and packet color.
+ * Access: RW
+ *
+ * Note: Not supported by SwitchX and SwitchX-2.
+ */
+MLXSW_ITEM32(reg, rgcr, usp, 0x18, 20, 1);
+
+/* reg_rgcr_pcp_rw
+ * Indicates how to handle the pcp_rewrite_en value:
+ * 0 - Preserve the value of pcp_rewrite_en.
+ * 2 - Disable PCP rewrite.
+ * 3 - Enable PCP rewrite.
+ * Access: RW
+ *
+ * Note: Not supported by SwitchX and SwitchX-2.
+ */
+MLXSW_ITEM32(reg, rgcr, pcp_rw, 0x18, 16, 2);
+
+/* reg_rgcr_activity_dis
+ * Activity disable:
+ * 0 - Activity will be set when an entry is hit (default).
+ * 1 - Activity will not be set when an entry is hit.
+ *
+ * Bit 0 - Disable activity bit in Router Algorithmic LPM Unicast Entry
+ * (RALUE).
+ * Bit 1 - Disable activity bit in Router Algorithmic LPM Unicast Host
+ * Entry (RAUHT).
+ * Bits 2:7 are reserved.
+ * Access: RW
+ *
+ * Note: Not supported by SwitchX, SwitchX-2 and Switch-IB.
+ */
+MLXSW_ITEM32(reg, rgcr, activity_dis, 0x20, 0, 8);
+
+static inline void mlxsw_reg_rgcr_pack(char *payload, bool ipv4_en)
+{
+	MLXSW_REG_ZERO(rgcr, payload);
+	mlxsw_reg_rgcr_ipv4_en_set(payload, ipv4_en);
+}
+
+/* RITR - Router Interface Table Register
+ * --------------------------------------
+ * The register is used to configure the router interface table.
+ */
+#define MLXSW_REG_RITR_ID 0x8002
+#define MLXSW_REG_RITR_LEN 0x40
+
+static const struct mlxsw_reg_info mlxsw_reg_ritr = {
+	.id = MLXSW_REG_RITR_ID,
+	.len = MLXSW_REG_RITR_LEN,
+};
+
+/* reg_ritr_enable
+ * Enables routing on the router interface.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, enable, 0x00, 31, 1);
+
+/* reg_ritr_ipv4
+ * IPv4 routing enable. Enables routing of IPv4 traffic on the router
+ * interface.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ipv4, 0x00, 29, 1);
+
+/* reg_ritr_ipv6
+ * IPv6 routing enable. Enables routing of IPv6 traffic on the router
+ * interface.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ipv6, 0x00, 28, 1);
+
+enum mlxsw_reg_ritr_if_type {
+	MLXSW_REG_RITR_VLAN_IF,
+	MLXSW_REG_RITR_FID_IF,
+	MLXSW_REG_RITR_SP_IF,
+};
+
+/* reg_ritr_type
+ * Router interface type.
+ * 0 - VLAN interface.
+ * 1 - FID interface.
+ * 2 - Sub-port interface.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, type, 0x00, 23, 3);
+
+enum {
+	MLXSW_REG_RITR_RIF_CREATE,
+	MLXSW_REG_RITR_RIF_DEL,
+};
+
+/* reg_ritr_op
+ * Opcode:
+ * 0 - Create or edit RIF.
+ * 1 - Delete RIF.
+ * Reserved for SwitchX-2. For Spectrum, editing of interface properties
+ * is not supported. An interface must be deleted and re-created in order
+ * to update properties.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, ritr, op, 0x00, 20, 2);
+
+/* reg_ritr_rif
+ * Router interface index. A pointer to the Router Interface Table.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ritr, rif, 0x00, 0, 16);
+
+/* reg_ritr_ipv4_fe
+ * IPv4 Forwarding Enable.
+ * Enables routing of IPv4 traffic on the router interface. When disabled,
+ * forwarding is blocked but local traffic (traps and IP2ME) will be enabled.
+ * Not supported in SwitchX-2.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ipv4_fe, 0x04, 29, 1);
+
+/* reg_ritr_ipv6_fe
+ * IPv6 Forwarding Enable.
+ * Enables routing of IPv6 traffic on the router interface. When disabled,
+ * forwarding is blocked but local traffic (traps and IP2ME) will be enabled.
+ * Not supported in SwitchX-2.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ipv6_fe, 0x04, 28, 1);
+
+/* reg_ritr_virtual_router
+ * Virtual router ID associated with the router interface.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, virtual_router, 0x04, 0, 16);
+
+/* reg_ritr_mtu
+ * Router interface MTU.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, mtu, 0x34, 0, 16);
+
+/* reg_ritr_if_swid
+ * Switch partition ID.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, if_swid, 0x08, 24, 8);
+
+/* reg_ritr_if_mac
+ * Router interface MAC address.
+ * In Spectrum, all MAC addresses must have the same 38 MSBits.
+ * Access: RW
+ */
+MLXSW_ITEM_BUF(reg, ritr, if_mac, 0x12, 6);
+
+/* VLAN Interface */
+
+/* reg_ritr_vlan_if_vid
+ * VLAN ID.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, vlan_if_vid, 0x08, 0, 12);
+
+/* FID Interface */
+
+/* reg_ritr_fid_if_fid
+ * Filtering ID. Used to connect a bridge to the router. Only FIDs from
+ * the vFID range are supported.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, fid_if_fid, 0x08, 0, 16);
+
+static inline void mlxsw_reg_ritr_fid_set(char *payload,
+					  enum mlxsw_reg_ritr_if_type rif_type,
+					  u16 fid)
+{
+	if (rif_type == MLXSW_REG_RITR_FID_IF)
+		mlxsw_reg_ritr_fid_if_fid_set(payload, fid);
+	else
+		mlxsw_reg_ritr_vlan_if_vid_set(payload, fid);
+}
+
+/* Sub-port Interface */
+
+/* reg_ritr_sp_if_lag
+ * LAG indication. When this bit is set the system_port field holds the
+ * LAG identifier.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, sp_if_lag, 0x08, 24, 1);
+
+/* reg_ritr_sp_system_port
+ * Port unique indentifier. When lag bit is set, this field holds the
+ * lag_id in bits 0:9.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, sp_if_system_port, 0x08, 0, 16);
+
+/* reg_ritr_sp_if_vid
+ * VLAN ID.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, sp_if_vid, 0x18, 0, 12);
+
+static inline void mlxsw_reg_ritr_rif_pack(char *payload, u16 rif)
+{
+	MLXSW_REG_ZERO(ritr, payload);
+	mlxsw_reg_ritr_rif_set(payload, rif);
+}
+
+static inline void mlxsw_reg_ritr_sp_if_pack(char *payload, bool lag,
+					     u16 system_port, u16 vid)
+{
+	mlxsw_reg_ritr_sp_if_lag_set(payload, lag);
+	mlxsw_reg_ritr_sp_if_system_port_set(payload, system_port);
+	mlxsw_reg_ritr_sp_if_vid_set(payload, vid);
+}
+
+static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
+				       enum mlxsw_reg_ritr_if_type type,
+				       u16 rif, u16 mtu, const char *mac)
+{
+	bool op = enable ? MLXSW_REG_RITR_RIF_CREATE : MLXSW_REG_RITR_RIF_DEL;
+
+	MLXSW_REG_ZERO(ritr, payload);
+	mlxsw_reg_ritr_enable_set(payload, enable);
+	mlxsw_reg_ritr_ipv4_set(payload, 1);
+	mlxsw_reg_ritr_type_set(payload, type);
+	mlxsw_reg_ritr_op_set(payload, op);
+	mlxsw_reg_ritr_rif_set(payload, rif);
+	mlxsw_reg_ritr_ipv4_fe_set(payload, 1);
+	mlxsw_reg_ritr_mtu_set(payload, mtu);
+	mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac);
+}
+
+/* RATR - Router Adjacency Table Register
+ * --------------------------------------
+ * The RATR register is used to configure the Router Adjacency (next-hop)
+ * Table.
+ */
+#define MLXSW_REG_RATR_ID 0x8008
+#define MLXSW_REG_RATR_LEN 0x2C
+
+static const struct mlxsw_reg_info mlxsw_reg_ratr = {
+	.id = MLXSW_REG_RATR_ID,
+	.len = MLXSW_REG_RATR_LEN,
+};
+
+enum mlxsw_reg_ratr_op {
+	/* Read */
+	MLXSW_REG_RATR_OP_QUERY_READ = 0,
+	/* Read and clear activity */
+	MLXSW_REG_RATR_OP_QUERY_READ_CLEAR = 2,
+	/* Write Adjacency entry */
+	MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY = 1,
+	/* Write Adjacency entry only if the activity is cleared.
+	 * The write may not succeed if the activity is set. There is not
+	 * direct feedback if the write has succeeded or not, however
+	 * the get will reveal the actual entry (SW can compare the get
+	 * response to the set command).
+	 */
+	MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY_ON_ACTIVITY = 3,
+};
+
+/* reg_ratr_op
+ * Note that Write operation may also be used for updating
+ * counter_set_type and counter_index. In this case all other
+ * fields must not be updated.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, ratr, op, 0x00, 28, 4);
+
+/* reg_ratr_v
+ * Valid bit. Indicates if the adjacency entry is valid.
+ * Note: the device may need some time before reusing an invalidated
+ * entry. During this time the entry can not be reused. It is
+ * recommended to use another entry before reusing an invalidated
+ * entry (e.g. software can put it at the end of the list for
+ * reusing). Trying to access an invalidated entry not yet cleared
+ * by the device results with failure indicating "Try Again" status.
+ * When valid is '0' then egress_router_interface,trap_action,
+ * adjacency_parameters and counters are reserved
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, v, 0x00, 24, 1);
+
+/* reg_ratr_a
+ * Activity. Set for new entries. Set if a packet lookup has hit on
+ * the specific entry. To clear the a bit, use "clear activity".
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ratr, a, 0x00, 16, 1);
+
+/* reg_ratr_adjacency_index_low
+ * Bits 15:0 of index into the adjacency table.
+ * For SwitchX and SwitchX-2, the adjacency table is linear and
+ * used for adjacency entries only.
+ * For Spectrum, the index is to the KVD linear.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ratr, adjacency_index_low, 0x04, 0, 16);
+
+/* reg_ratr_egress_router_interface
+ * Range is 0 .. cap_max_router_interfaces - 1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, egress_router_interface, 0x08, 0, 16);
+
+enum mlxsw_reg_ratr_trap_action {
+	MLXSW_REG_RATR_TRAP_ACTION_NOP,
+	MLXSW_REG_RATR_TRAP_ACTION_TRAP,
+	MLXSW_REG_RATR_TRAP_ACTION_MIRROR_TO_CPU,
+	MLXSW_REG_RATR_TRAP_ACTION_MIRROR,
+	MLXSW_REG_RATR_TRAP_ACTION_DISCARD_ERRORS,
+};
+
+/* reg_ratr_trap_action
+ * see mlxsw_reg_ratr_trap_action
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, trap_action, 0x0C, 28, 4);
+
+enum mlxsw_reg_ratr_trap_id {
+	MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS0 = 0,
+	MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS1 = 1,
+};
+
+/* reg_ratr_adjacency_index_high
+ * Bits 23:16 of the adjacency_index.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ratr, adjacency_index_high, 0x0C, 16, 8);
+
+/* reg_ratr_trap_id
+ * Trap ID to be reported to CPU.
+ * Trap-ID is RTR_EGRESS0 or RTR_EGRESS1.
+ * For trap_action of NOP, MIRROR and DISCARD_ERROR
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, trap_id, 0x0C, 0, 8);
+
+/* reg_ratr_eth_destination_mac
+ * MAC address of the destination next-hop.
+ * Access: RW
+ */
+MLXSW_ITEM_BUF(reg, ratr, eth_destination_mac, 0x12, 6);
+
+static inline void
+mlxsw_reg_ratr_pack(char *payload,
+		    enum mlxsw_reg_ratr_op op, bool valid,
+		    u32 adjacency_index, u16 egress_rif)
+{
+	MLXSW_REG_ZERO(ratr, payload);
+	mlxsw_reg_ratr_op_set(payload, op);
+	mlxsw_reg_ratr_v_set(payload, valid);
+	mlxsw_reg_ratr_adjacency_index_low_set(payload, adjacency_index);
+	mlxsw_reg_ratr_adjacency_index_high_set(payload, adjacency_index >> 16);
+	mlxsw_reg_ratr_egress_router_interface_set(payload, egress_rif);
+}
+
+static inline void mlxsw_reg_ratr_eth_entry_pack(char *payload,
+						 const char *dest_mac)
+{
+	mlxsw_reg_ratr_eth_destination_mac_memcpy_to(payload, dest_mac);
+}
+
+/* RALTA - Router Algorithmic LPM Tree Allocation Register
+ * -------------------------------------------------------
+ * RALTA is used to allocate the LPM trees of the SHSPM method.
+ */
+#define MLXSW_REG_RALTA_ID 0x8010
+#define MLXSW_REG_RALTA_LEN 0x04
+
+static const struct mlxsw_reg_info mlxsw_reg_ralta = {
+	.id = MLXSW_REG_RALTA_ID,
+	.len = MLXSW_REG_RALTA_LEN,
+};
+
+/* reg_ralta_op
+ * opcode (valid for Write, must be 0 on Read)
+ * 0 - allocate a tree
+ * 1 - deallocate a tree
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, ralta, op, 0x00, 28, 2);
+
+enum mlxsw_reg_ralxx_protocol {
+	MLXSW_REG_RALXX_PROTOCOL_IPV4,
+	MLXSW_REG_RALXX_PROTOCOL_IPV6,
+};
+
+/* reg_ralta_protocol
+ * Protocol.
+ * Deallocation opcode: Reserved.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralta, protocol, 0x00, 24, 4);
+
+/* reg_ralta_tree_id
+ * An identifier (numbered from 1..cap_shspm_max_trees-1) representing
+ * the tree identifier (managed by software).
+ * Note that tree_id 0 is allocated for a default-route tree.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ralta, tree_id, 0x00, 0, 8);
+
+static inline void mlxsw_reg_ralta_pack(char *payload, bool alloc,
+					enum mlxsw_reg_ralxx_protocol protocol,
+					u8 tree_id)
+{
+	MLXSW_REG_ZERO(ralta, payload);
+	mlxsw_reg_ralta_op_set(payload, !alloc);
+	mlxsw_reg_ralta_protocol_set(payload, protocol);
+	mlxsw_reg_ralta_tree_id_set(payload, tree_id);
+}
+
+/* RALST - Router Algorithmic LPM Structure Tree Register
+ * ------------------------------------------------------
+ * RALST is used to set and query the structure of an LPM tree.
+ * The structure of the tree must be sorted as a sorted binary tree, while
+ * each node is a bin that is tagged as the length of the prefixes the lookup
+ * will refer to. Therefore, bin X refers to a set of entries with prefixes
+ * of X bits to match with the destination address. The bin 0 indicates
+ * the default action, when there is no match of any prefix.
+ */
+#define MLXSW_REG_RALST_ID 0x8011
+#define MLXSW_REG_RALST_LEN 0x104
+
+static const struct mlxsw_reg_info mlxsw_reg_ralst = {
+	.id = MLXSW_REG_RALST_ID,
+	.len = MLXSW_REG_RALST_LEN,
+};
+
+/* reg_ralst_root_bin
+ * The bin number of the root bin.
+ * 0<root_bin=<(length of IP address)
+ * For a default-route tree configure 0xff
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralst, root_bin, 0x00, 16, 8);
+
+/* reg_ralst_tree_id
+ * Tree identifier numbered from 1..(cap_shspm_max_trees-1).
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ralst, tree_id, 0x00, 0, 8);
+
+#define MLXSW_REG_RALST_BIN_NO_CHILD 0xff
+#define MLXSW_REG_RALST_BIN_OFFSET 0x04
+#define MLXSW_REG_RALST_BIN_COUNT 128
+
+/* reg_ralst_left_child_bin
+ * Holding the children of the bin according to the stored tree's structure.
+ * For trees composed of less than 4 blocks, the bins in excess are reserved.
+ * Note that tree_id 0 is allocated for a default-route tree, bins are 0xff
+ * Access: RW
+ */
+MLXSW_ITEM16_INDEXED(reg, ralst, left_child_bin, 0x04, 8, 8, 0x02, 0x00, false);
+
+/* reg_ralst_right_child_bin
+ * Holding the children of the bin according to the stored tree's structure.
+ * For trees composed of less than 4 blocks, the bins in excess are reserved.
+ * Note that tree_id 0 is allocated for a default-route tree, bins are 0xff
+ * Access: RW
+ */
+MLXSW_ITEM16_INDEXED(reg, ralst, right_child_bin, 0x04, 0, 8, 0x02, 0x00,
+		     false);
+
+static inline void mlxsw_reg_ralst_pack(char *payload, u8 root_bin, u8 tree_id)
+{
+	MLXSW_REG_ZERO(ralst, payload);
+
+	/* Initialize all bins to have no left or right child */
+	memset(payload + MLXSW_REG_RALST_BIN_OFFSET,
+	       MLXSW_REG_RALST_BIN_NO_CHILD, MLXSW_REG_RALST_BIN_COUNT * 2);
+
+	mlxsw_reg_ralst_root_bin_set(payload, root_bin);
+	mlxsw_reg_ralst_tree_id_set(payload, tree_id);
+}
+
+static inline void mlxsw_reg_ralst_bin_pack(char *payload, u8 bin_number,
+					    u8 left_child_bin,
+					    u8 right_child_bin)
+{
+	int bin_index = bin_number - 1;
+
+	mlxsw_reg_ralst_left_child_bin_set(payload, bin_index, left_child_bin);
+	mlxsw_reg_ralst_right_child_bin_set(payload, bin_index,
+					    right_child_bin);
+}
+
+/* RALTB - Router Algorithmic LPM Tree Binding Register
+ * ----------------------------------------------------
+ * RALTB is used to bind virtual router and protocol to an allocated LPM tree.
+ */
+#define MLXSW_REG_RALTB_ID 0x8012
+#define MLXSW_REG_RALTB_LEN 0x04
+
+static const struct mlxsw_reg_info mlxsw_reg_raltb = {
+	.id = MLXSW_REG_RALTB_ID,
+	.len = MLXSW_REG_RALTB_LEN,
+};
+
+/* reg_raltb_virtual_router
+ * Virtual Router ID
+ * Range is 0..cap_max_virtual_routers-1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, raltb, virtual_router, 0x00, 16, 16);
+
+/* reg_raltb_protocol
+ * Protocol.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, raltb, protocol, 0x00, 12, 4);
+
+/* reg_raltb_tree_id
+ * Tree to be used for the {virtual_router, protocol}
+ * Tree identifier numbered from 1..(cap_shspm_max_trees-1).
+ * By default, all Unicast IPv4 and IPv6 are bound to tree_id 0.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, raltb, tree_id, 0x00, 0, 8);
+
+static inline void mlxsw_reg_raltb_pack(char *payload, u16 virtual_router,
+					enum mlxsw_reg_ralxx_protocol protocol,
+					u8 tree_id)
+{
+	MLXSW_REG_ZERO(raltb, payload);
+	mlxsw_reg_raltb_virtual_router_set(payload, virtual_router);
+	mlxsw_reg_raltb_protocol_set(payload, protocol);
+	mlxsw_reg_raltb_tree_id_set(payload, tree_id);
+}
+
+/* RALUE - Router Algorithmic LPM Unicast Entry Register
+ * -----------------------------------------------------
+ * RALUE is used to configure and query LPM entries that serve
+ * the Unicast protocols.
+ */
+#define MLXSW_REG_RALUE_ID 0x8013
+#define MLXSW_REG_RALUE_LEN 0x38
+
+static const struct mlxsw_reg_info mlxsw_reg_ralue = {
+	.id = MLXSW_REG_RALUE_ID,
+	.len = MLXSW_REG_RALUE_LEN,
+};
+
+/* reg_ralue_protocol
+ * Protocol.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ralue, protocol, 0x00, 24, 4);
+
+enum mlxsw_reg_ralue_op {
+	/* Read operation. If entry doesn't exist, the operation fails. */
+	MLXSW_REG_RALUE_OP_QUERY_READ = 0,
+	/* Clear on read operation. Used to read entry and
+	 * clear Activity bit.
+	 */
+	MLXSW_REG_RALUE_OP_QUERY_CLEAR = 1,
+	/* Write operation. Used to write a new entry to the table. All RW
+	 * fields are written for new entry. Activity bit is set
+	 * for new entries.
+	 */
+	MLXSW_REG_RALUE_OP_WRITE_WRITE = 0,
+	/* Update operation. Used to update an existing route entry and
+	 * only update the RW fields that are detailed in the field
+	 * op_u_mask. If entry doesn't exist, the operation fails.
+	 */
+	MLXSW_REG_RALUE_OP_WRITE_UPDATE = 1,
+	/* Clear activity. The Activity bit (the field a) is cleared
+	 * for the entry.
+	 */
+	MLXSW_REG_RALUE_OP_WRITE_CLEAR = 2,
+	/* Delete operation. Used to delete an existing entry. If entry
+	 * doesn't exist, the operation fails.
+	 */
+	MLXSW_REG_RALUE_OP_WRITE_DELETE = 3,
+};
+
+/* reg_ralue_op
+ * Operation.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, ralue, op, 0x00, 20, 3);
+
+/* reg_ralue_a
+ * Activity. Set for new entries. Set if a packet lookup has hit on the
+ * specific entry, only if the entry is a route. To clear the a bit, use
+ * "clear activity" op.
+ * Enabled by activity_dis in RGCR
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ralue, a, 0x00, 16, 1);
+
+/* reg_ralue_virtual_router
+ * Virtual Router ID
+ * Range is 0..cap_max_virtual_routers-1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ralue, virtual_router, 0x04, 16, 16);
+
+#define MLXSW_REG_RALUE_OP_U_MASK_ENTRY_TYPE	BIT(0)
+#define MLXSW_REG_RALUE_OP_U_MASK_BMP_LEN	BIT(1)
+#define MLXSW_REG_RALUE_OP_U_MASK_ACTION	BIT(2)
+
+/* reg_ralue_op_u_mask
+ * opcode update mask.
+ * On read operation, this field is reserved.
+ * This field is valid for update opcode, otherwise - reserved.
+ * This field is a bitmask of the fields that should be updated.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, ralue, op_u_mask, 0x04, 8, 3);
+
+/* reg_ralue_prefix_len
+ * Number of bits in the prefix of the LPM route.
+ * Note that for IPv6 prefixes, if prefix_len>64 the entry consumes
+ * two entries in the physical HW table.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ralue, prefix_len, 0x08, 0, 8);
+
+/* reg_ralue_dip*
+ * The prefix of the route or of the marker that the object of the LPM
+ * is compared with. The most significant bits of the dip are the prefix.
+ * The list significant bits must be '0' if the prefix_len is smaller
+ * than 128 for IPv6 or smaller than 32 for IPv4.
+ * IPv4 address uses bits dip[31:0] and bits dip[127:32] are reserved.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ralue, dip4, 0x18, 0, 32);
+
+enum mlxsw_reg_ralue_entry_type {
+	MLXSW_REG_RALUE_ENTRY_TYPE_MARKER_ENTRY = 1,
+	MLXSW_REG_RALUE_ENTRY_TYPE_ROUTE_ENTRY = 2,
+	MLXSW_REG_RALUE_ENTRY_TYPE_MARKER_AND_ROUTE_ENTRY = 3,
+};
+
+/* reg_ralue_entry_type
+ * Entry type.
+ * Note - for Marker entries, the action_type and action fields are reserved.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralue, entry_type, 0x1C, 30, 2);
+
+/* reg_ralue_bmp_len
+ * The best match prefix length in the case that there is no match for
+ * longer prefixes.
+ * If (entry_type != MARKER_ENTRY), bmp_len must be equal to prefix_len
+ * Note for any update operation with entry_type modification this
+ * field must be set.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralue, bmp_len, 0x1C, 16, 8);
+
+enum mlxsw_reg_ralue_action_type {
+	MLXSW_REG_RALUE_ACTION_TYPE_REMOTE,
+	MLXSW_REG_RALUE_ACTION_TYPE_LOCAL,
+	MLXSW_REG_RALUE_ACTION_TYPE_IP2ME,
+};
+
+/* reg_ralue_action_type
+ * Action Type
+ * Indicates how the IP address is connected.
+ * It can be connected to a local subnet through local_erif or can be
+ * on a remote subnet connected through a next-hop router,
+ * or transmitted to the CPU.
+ * Reserved when entry_type = MARKER_ENTRY
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralue, action_type, 0x1C, 0, 2);
+
+enum mlxsw_reg_ralue_trap_action {
+	MLXSW_REG_RALUE_TRAP_ACTION_NOP,
+	MLXSW_REG_RALUE_TRAP_ACTION_TRAP,
+	MLXSW_REG_RALUE_TRAP_ACTION_MIRROR_TO_CPU,
+	MLXSW_REG_RALUE_TRAP_ACTION_MIRROR,
+	MLXSW_REG_RALUE_TRAP_ACTION_DISCARD_ERROR,
+};
+
+/* reg_ralue_trap_action
+ * Trap action.
+ * For IP2ME action, only NOP and MIRROR are possible.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralue, trap_action, 0x20, 28, 4);
+
+/* reg_ralue_trap_id
+ * Trap ID to be reported to CPU.
+ * Trap ID is RTR_INGRESS0 or RTR_INGRESS1.
+ * For trap_action of NOP, MIRROR and DISCARD_ERROR, trap_id is reserved.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralue, trap_id, 0x20, 0, 9);
+
+/* reg_ralue_adjacency_index
+ * Points to the first entry of the group-based ECMP.
+ * Only relevant in case of REMOTE action.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralue, adjacency_index, 0x24, 0, 24);
+
+/* reg_ralue_ecmp_size
+ * Amount of sequential entries starting
+ * from the adjacency_index (the number of ECMPs).
+ * The valid range is 1-64, 512, 1024, 2048 and 4096.
+ * Reserved when trap_action is TRAP or DISCARD_ERROR.
+ * Only relevant in case of REMOTE action.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralue, ecmp_size, 0x28, 0, 13);
+
+/* reg_ralue_local_erif
+ * Egress Router Interface.
+ * Only relevant in case of LOCAL action.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralue, local_erif, 0x24, 0, 16);
+
+/* reg_ralue_v
+ * Valid bit for the tunnel_ptr field.
+ * If valid = 0 then trap to CPU as IP2ME trap ID.
+ * If valid = 1 and the packet format allows NVE or IPinIP tunnel
+ * decapsulation then tunnel decapsulation is done.
+ * If valid = 1 and packet format does not allow NVE or IPinIP tunnel
+ * decapsulation then trap as IP2ME trap ID.
+ * Only relevant in case of IP2ME action.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralue, v, 0x24, 31, 1);
+
+/* reg_ralue_tunnel_ptr
+ * Tunnel Pointer for NVE or IPinIP tunnel decapsulation.
+ * For Spectrum, pointer to KVD Linear.
+ * Only relevant in case of IP2ME action.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ralue, tunnel_ptr, 0x24, 0, 24);
+
+static inline void mlxsw_reg_ralue_pack(char *payload,
+					enum mlxsw_reg_ralxx_protocol protocol,
+					enum mlxsw_reg_ralue_op op,
+					u16 virtual_router, u8 prefix_len)
+{
+	MLXSW_REG_ZERO(ralue, payload);
+	mlxsw_reg_ralue_protocol_set(payload, protocol);
+	mlxsw_reg_ralue_virtual_router_set(payload, virtual_router);
+	mlxsw_reg_ralue_prefix_len_set(payload, prefix_len);
+	mlxsw_reg_ralue_entry_type_set(payload,
+				       MLXSW_REG_RALUE_ENTRY_TYPE_ROUTE_ENTRY);
+	mlxsw_reg_ralue_bmp_len_set(payload, prefix_len);
+}
+
+static inline void mlxsw_reg_ralue_pack4(char *payload,
+					 enum mlxsw_reg_ralxx_protocol protocol,
+					 enum mlxsw_reg_ralue_op op,
+					 u16 virtual_router, u8 prefix_len,
+					 u32 dip)
+{
+	mlxsw_reg_ralue_pack(payload, protocol, op, virtual_router, prefix_len);
+	mlxsw_reg_ralue_dip4_set(payload, dip);
+}
+
+static inline void
+mlxsw_reg_ralue_act_remote_pack(char *payload,
+				enum mlxsw_reg_ralue_trap_action trap_action,
+				u16 trap_id, u32 adjacency_index, u16 ecmp_size)
+{
+	mlxsw_reg_ralue_action_type_set(payload,
+					MLXSW_REG_RALUE_ACTION_TYPE_REMOTE);
+	mlxsw_reg_ralue_trap_action_set(payload, trap_action);
+	mlxsw_reg_ralue_trap_id_set(payload, trap_id);
+	mlxsw_reg_ralue_adjacency_index_set(payload, adjacency_index);
+	mlxsw_reg_ralue_ecmp_size_set(payload, ecmp_size);
+}
+
+static inline void
+mlxsw_reg_ralue_act_local_pack(char *payload,
+			       enum mlxsw_reg_ralue_trap_action trap_action,
+			       u16 trap_id, u16 local_erif)
+{
+	mlxsw_reg_ralue_action_type_set(payload,
+					MLXSW_REG_RALUE_ACTION_TYPE_LOCAL);
+	mlxsw_reg_ralue_trap_action_set(payload, trap_action);
+	mlxsw_reg_ralue_trap_id_set(payload, trap_id);
+	mlxsw_reg_ralue_local_erif_set(payload, local_erif);
+}
+
+static inline void
+mlxsw_reg_ralue_act_ip2me_pack(char *payload)
+{
+	mlxsw_reg_ralue_action_type_set(payload,
+					MLXSW_REG_RALUE_ACTION_TYPE_IP2ME);
+}
+
+/* RAUHT - Router Algorithmic LPM Unicast Host Table Register
+ * ----------------------------------------------------------
+ * The RAUHT register is used to configure and query the Unicast Host table in
+ * devices that implement the Algorithmic LPM.
+ */
+#define MLXSW_REG_RAUHT_ID 0x8014
+#define MLXSW_REG_RAUHT_LEN 0x74
+
+static const struct mlxsw_reg_info mlxsw_reg_rauht = {
+	.id = MLXSW_REG_RAUHT_ID,
+	.len = MLXSW_REG_RAUHT_LEN,
+};
+
+enum mlxsw_reg_rauht_type {
+	MLXSW_REG_RAUHT_TYPE_IPV4,
+	MLXSW_REG_RAUHT_TYPE_IPV6,
+};
+
+/* reg_rauht_type
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rauht, type, 0x00, 24, 2);
+
+enum mlxsw_reg_rauht_op {
+	MLXSW_REG_RAUHT_OP_QUERY_READ = 0,
+	/* Read operation */
+	MLXSW_REG_RAUHT_OP_QUERY_CLEAR_ON_READ = 1,
+	/* Clear on read operation. Used to read entry and clear
+	 * activity bit.
+	 */
+	MLXSW_REG_RAUHT_OP_WRITE_ADD = 0,
+	/* Add. Used to write a new entry to the table. All R/W fields are
+	 * relevant for new entry. Activity bit is set for new entries.
+	 */
+	MLXSW_REG_RAUHT_OP_WRITE_UPDATE = 1,
+	/* Update action. Used to update an existing route entry and
+	 * only update the following fields:
+	 * trap_action, trap_id, mac, counter_set_type, counter_index
+	 */
+	MLXSW_REG_RAUHT_OP_WRITE_CLEAR_ACTIVITY = 2,
+	/* Clear activity. A bit is cleared for the entry. */
+	MLXSW_REG_RAUHT_OP_WRITE_DELETE = 3,
+	/* Delete entry */
+	MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL = 4,
+	/* Delete all host entries on a RIF. In this command, dip
+	 * field is reserved.
+	 */
+};
+
+/* reg_rauht_op
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, rauht, op, 0x00, 20, 3);
+
+/* reg_rauht_a
+ * Activity. Set for new entries. Set if a packet lookup has hit on
+ * the specific entry.
+ * To clear the a bit, use "clear activity" op.
+ * Enabled by activity_dis in RGCR
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, rauht, a, 0x00, 16, 1);
+
+/* reg_rauht_rif
+ * Router Interface
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rauht, rif, 0x00, 0, 16);
+
+/* reg_rauht_dip*
+ * Destination address.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rauht, dip4, 0x1C, 0x0, 32);
+
+enum mlxsw_reg_rauht_trap_action {
+	MLXSW_REG_RAUHT_TRAP_ACTION_NOP,
+	MLXSW_REG_RAUHT_TRAP_ACTION_TRAP,
+	MLXSW_REG_RAUHT_TRAP_ACTION_MIRROR_TO_CPU,
+	MLXSW_REG_RAUHT_TRAP_ACTION_MIRROR,
+	MLXSW_REG_RAUHT_TRAP_ACTION_DISCARD_ERRORS,
+};
+
+/* reg_rauht_trap_action
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rauht, trap_action, 0x60, 28, 4);
+
+enum mlxsw_reg_rauht_trap_id {
+	MLXSW_REG_RAUHT_TRAP_ID_RTR_EGRESS0,
+	MLXSW_REG_RAUHT_TRAP_ID_RTR_EGRESS1,
+};
+
+/* reg_rauht_trap_id
+ * Trap ID to be reported to CPU.
+ * Trap-ID is RTR_EGRESS0 or RTR_EGRESS1.
+ * For trap_action of NOP, MIRROR and DISCARD_ERROR,
+ * trap_id is reserved.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rauht, trap_id, 0x60, 0, 9);
+
+/* reg_rauht_counter_set_type
+ * Counter set type for flow counters
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rauht, counter_set_type, 0x68, 24, 8);
+
+/* reg_rauht_counter_index
+ * Counter index for flow counters
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rauht, counter_index, 0x68, 0, 24);
+
+/* reg_rauht_mac
+ * MAC address.
+ * Access: RW
+ */
+MLXSW_ITEM_BUF(reg, rauht, mac, 0x6E, 6);
+
+static inline void mlxsw_reg_rauht_pack(char *payload,
+					enum mlxsw_reg_rauht_op op, u16 rif,
+					const char *mac)
+{
+	MLXSW_REG_ZERO(rauht, payload);
+	mlxsw_reg_rauht_op_set(payload, op);
+	mlxsw_reg_rauht_rif_set(payload, rif);
+	mlxsw_reg_rauht_mac_memcpy_to(payload, mac);
+}
+
+static inline void mlxsw_reg_rauht_pack4(char *payload,
+					 enum mlxsw_reg_rauht_op op, u16 rif,
+					 const char *mac, u32 dip)
+{
+	mlxsw_reg_rauht_pack(payload, op, rif, mac);
+	mlxsw_reg_rauht_dip4_set(payload, dip);
+}
+
+/* RALEU - Router Algorithmic LPM ECMP Update Register
+ * ---------------------------------------------------
+ * The register enables updating the ECMP section in the action for multiple
+ * LPM Unicast entries in a single operation. The update is executed to
+ * all entries of a {virtual router, protocol} tuple using the same ECMP group.
+ */
+#define MLXSW_REG_RALEU_ID 0x8015
+#define MLXSW_REG_RALEU_LEN 0x28
+
+static const struct mlxsw_reg_info mlxsw_reg_raleu = {
+	.id = MLXSW_REG_RALEU_ID,
+	.len = MLXSW_REG_RALEU_LEN,
+};
+
+/* reg_raleu_protocol
+ * Protocol.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, raleu, protocol, 0x00, 24, 4);
+
+/* reg_raleu_virtual_router
+ * Virtual Router ID
+ * Range is 0..cap_max_virtual_routers-1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, raleu, virtual_router, 0x00, 0, 16);
+
+/* reg_raleu_adjacency_index
+ * Adjacency Index used for matching on the existing entries.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, raleu, adjacency_index, 0x10, 0, 24);
+
+/* reg_raleu_ecmp_size
+ * ECMP Size used for matching on the existing entries.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, raleu, ecmp_size, 0x14, 0, 13);
+
+/* reg_raleu_new_adjacency_index
+ * New Adjacency Index.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, raleu, new_adjacency_index, 0x20, 0, 24);
+
+/* reg_raleu_new_ecmp_size
+ * New ECMP Size.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, raleu, new_ecmp_size, 0x24, 0, 13);
+
+static inline void mlxsw_reg_raleu_pack(char *payload,
+					enum mlxsw_reg_ralxx_protocol protocol,
+					u16 virtual_router,
+					u32 adjacency_index, u16 ecmp_size,
+					u32 new_adjacency_index,
+					u16 new_ecmp_size)
+{
+	MLXSW_REG_ZERO(raleu, payload);
+	mlxsw_reg_raleu_protocol_set(payload, protocol);
+	mlxsw_reg_raleu_virtual_router_set(payload, virtual_router);
+	mlxsw_reg_raleu_adjacency_index_set(payload, adjacency_index);
+	mlxsw_reg_raleu_ecmp_size_set(payload, ecmp_size);
+	mlxsw_reg_raleu_new_adjacency_index_set(payload, new_adjacency_index);
+	mlxsw_reg_raleu_new_ecmp_size_set(payload, new_ecmp_size);
+}
+
+/* RAUHTD - Router Algorithmic LPM Unicast Host Table Dump Register
+ * ----------------------------------------------------------------
+ * The RAUHTD register allows dumping entries from the Router Unicast Host
+ * Table. For a given session an entry is dumped no more than one time. The
+ * first RAUHTD access after reset is a new session. A session ends when the
+ * num_rec response is smaller than num_rec request or for IPv4 when the
+ * num_entries is smaller than 4. The clear activity affect the current session
+ * or the last session if a new session has not started.
+ */
+#define MLXSW_REG_RAUHTD_ID 0x8018
+#define MLXSW_REG_RAUHTD_BASE_LEN 0x20
+#define MLXSW_REG_RAUHTD_REC_LEN 0x20
+#define MLXSW_REG_RAUHTD_REC_MAX_NUM 32
+#define MLXSW_REG_RAUHTD_LEN (MLXSW_REG_RAUHTD_BASE_LEN + \
+		MLXSW_REG_RAUHTD_REC_MAX_NUM * MLXSW_REG_RAUHTD_REC_LEN)
+#define MLXSW_REG_RAUHTD_IPV4_ENT_PER_REC 4
+
+static const struct mlxsw_reg_info mlxsw_reg_rauhtd = {
+	.id = MLXSW_REG_RAUHTD_ID,
+	.len = MLXSW_REG_RAUHTD_LEN,
+};
+
+#define MLXSW_REG_RAUHTD_FILTER_A BIT(0)
+#define MLXSW_REG_RAUHTD_FILTER_RIF BIT(3)
+
+/* reg_rauhtd_filter_fields
+ * if a bit is '0' then the relevant field is ignored and dump is done
+ * regardless of the field value
+ * Bit0 - filter by activity: entry_a
+ * Bit3 - filter by entry rip: entry_rif
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rauhtd, filter_fields, 0x00, 0, 8);
+
+enum mlxsw_reg_rauhtd_op {
+	MLXSW_REG_RAUHTD_OP_DUMP,
+	MLXSW_REG_RAUHTD_OP_DUMP_AND_CLEAR,
+};
+
+/* reg_rauhtd_op
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, rauhtd, op, 0x04, 24, 2);
+
+/* reg_rauhtd_num_rec
+ * At request: number of records requested
+ * At response: number of records dumped
+ * For IPv4, each record has 4 entries at request and up to 4 entries
+ * at response
+ * Range is 0..MLXSW_REG_RAUHTD_REC_MAX_NUM
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rauhtd, num_rec, 0x04, 0, 8);
+
+/* reg_rauhtd_entry_a
+ * Dump only if activity has value of entry_a
+ * Reserved if filter_fields bit0 is '0'
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rauhtd, entry_a, 0x08, 16, 1);
+
+enum mlxsw_reg_rauhtd_type {
+	MLXSW_REG_RAUHTD_TYPE_IPV4,
+	MLXSW_REG_RAUHTD_TYPE_IPV6,
+};
+
+/* reg_rauhtd_type
+ * Dump only if record type is:
+ * 0 - IPv4
+ * 1 - IPv6
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rauhtd, type, 0x08, 0, 4);
+
+/* reg_rauhtd_entry_rif
+ * Dump only if RIF has value of entry_rif
+ * Reserved if filter_fields bit3 is '0'
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rauhtd, entry_rif, 0x0C, 0, 16);
+
+static inline void mlxsw_reg_rauhtd_pack(char *payload,
+					 enum mlxsw_reg_rauhtd_type type)
+{
+	MLXSW_REG_ZERO(rauhtd, payload);
+	mlxsw_reg_rauhtd_filter_fields_set(payload, MLXSW_REG_RAUHTD_FILTER_A);
+	mlxsw_reg_rauhtd_op_set(payload, MLXSW_REG_RAUHTD_OP_DUMP_AND_CLEAR);
+	mlxsw_reg_rauhtd_num_rec_set(payload, MLXSW_REG_RAUHTD_REC_MAX_NUM);
+	mlxsw_reg_rauhtd_entry_a_set(payload, 1);
+	mlxsw_reg_rauhtd_type_set(payload, type);
+}
+
+/* reg_rauhtd_ipv4_rec_num_entries
+ * Number of valid entries in this record:
+ * 0 - 1 valid entry
+ * 1 - 2 valid entries
+ * 2 - 3 valid entries
+ * 3 - 4 valid entries
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv4_rec_num_entries,
+		     MLXSW_REG_RAUHTD_BASE_LEN, 28, 2,
+		     MLXSW_REG_RAUHTD_REC_LEN, 0x00, false);
+
+/* reg_rauhtd_rec_type
+ * Record type.
+ * 0 - IPv4
+ * 1 - IPv6
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, rauhtd, rec_type, MLXSW_REG_RAUHTD_BASE_LEN, 24, 2,
+		     MLXSW_REG_RAUHTD_REC_LEN, 0x00, false);
+
+#define MLXSW_REG_RAUHTD_IPV4_ENT_LEN 0x8
+
+/* reg_rauhtd_ipv4_ent_a
+ * Activity. Set for new entries. Set if a packet lookup has hit on the
+ * specific entry.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv4_ent_a, MLXSW_REG_RAUHTD_BASE_LEN, 16, 1,
+		     MLXSW_REG_RAUHTD_IPV4_ENT_LEN, 0x00, false);
+
+/* reg_rauhtd_ipv4_ent_rif
+ * Router interface.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv4_ent_rif, MLXSW_REG_RAUHTD_BASE_LEN, 0,
+		     16, MLXSW_REG_RAUHTD_IPV4_ENT_LEN, 0x00, false);
+
+/* reg_rauhtd_ipv4_ent_dip
+ * Destination IPv4 address.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv4_ent_dip, MLXSW_REG_RAUHTD_BASE_LEN, 0,
+		     32, MLXSW_REG_RAUHTD_IPV4_ENT_LEN, 0x04, false);
+
+static inline void mlxsw_reg_rauhtd_ent_ipv4_unpack(char *payload,
+						    int ent_index, u16 *p_rif,
+						    u32 *p_dip)
+{
+	*p_rif = mlxsw_reg_rauhtd_ipv4_ent_rif_get(payload, ent_index);
+	*p_dip = mlxsw_reg_rauhtd_ipv4_ent_dip_get(payload, ent_index);
+}
+
 /* MFCR - Management Fan Control Register
  * --------------------------------------
  * This register controls the settings of the Fan Speed PWM mechanism.
@@ -3924,6 +5104,26 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id)
 		return "HTGT";
 	case MLXSW_REG_HPKT_ID:
 		return "HPKT";
+	case MLXSW_REG_RGCR_ID:
+		return "RGCR";
+	case MLXSW_REG_RITR_ID:
+		return "RITR";
+	case MLXSW_REG_RATR_ID:
+		return "RATR";
+	case MLXSW_REG_RALTA_ID:
+		return "RALTA";
+	case MLXSW_REG_RALST_ID:
+		return "RALST";
+	case MLXSW_REG_RALTB_ID:
+		return "RALTB";
+	case MLXSW_REG_RALUE_ID:
+		return "RALUE";
+	case MLXSW_REG_RAUHT_ID:
+		return "RAUHT";
+	case MLXSW_REG_RALEU_ID:
+		return "RALEU";
+	case MLXSW_REG_RAUHTD_ID:
+		return "RAUHTD";
 	case MLXSW_REG_MFCR_ID:
 		return "MFCR";
 	case MLXSW_REG_MFSC_ID:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 4a7273771028..c812513e079d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -49,7 +49,9 @@
 #include <linux/jiffies.h>
 #include <linux/bitops.h>
 #include <linux/list.h>
+#include <linux/notifier.h>
 #include <linux/dcbnl.h>
+#include <linux/inetdevice.h>
 #include <net/switchdev.h>
 #include <generated/utsrelease.h>
 
@@ -209,23 +211,6 @@ static int mlxsw_sp_port_dev_addr_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	return mlxsw_sp_port_dev_addr_set(mlxsw_sp_port, addr);
 }
 
-static int mlxsw_sp_port_stp_state_set(struct mlxsw_sp_port *mlxsw_sp_port,
-				       u16 vid, enum mlxsw_reg_spms_state state)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char *spms_pl;
-	int err;
-
-	spms_pl = kmalloc(MLXSW_REG_SPMS_LEN, GFP_KERNEL);
-	if (!spms_pl)
-		return -ENOMEM;
-	mlxsw_reg_spms_pack(spms_pl, mlxsw_sp_port->local_port);
-	mlxsw_reg_spms_vid_pack(spms_pl, vid, state);
-	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spms), spms_pl);
-	kfree(spms_pl);
-	return err;
-}
-
 static int mlxsw_sp_port_mtu_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
@@ -247,15 +232,23 @@ static int mlxsw_sp_port_mtu_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmtu), pmtu_pl);
 }
 
-static int mlxsw_sp_port_swid_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 swid)
+static int __mlxsw_sp_port_swid_set(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				    u8 swid)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char pspa_pl[MLXSW_REG_PSPA_LEN];
 
-	mlxsw_reg_pspa_pack(pspa_pl, swid, mlxsw_sp_port->local_port);
+	mlxsw_reg_pspa_pack(pspa_pl, swid, local_port);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pspa), pspa_pl);
 }
 
+static int mlxsw_sp_port_swid_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 swid)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+
+	return __mlxsw_sp_port_swid_set(mlxsw_sp, mlxsw_sp_port->local_port,
+					swid);
+}
+
 static int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port,
 				     bool enable)
 {
@@ -305,9 +298,9 @@ mlxsw_sp_port_system_port_mapping_set(struct mlxsw_sp_port *mlxsw_sp_port)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sspr), sspr_pl);
 }
 
-static int __mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
-					   u8 local_port, u8 *p_module,
-					   u8 *p_width, u8 *p_lane)
+static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
+					 u8 local_port, u8 *p_module,
+					 u8 *p_width, u8 *p_lane)
 {
 	char pmlp_pl[MLXSW_REG_PMLP_LEN];
 	int err;
@@ -322,16 +315,6 @@ static int __mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
-static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
-					 u8 local_port, u8 *p_module,
-					 u8 *p_width)
-{
-	u8 lane;
-
-	return __mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, p_module,
-					       p_width, &lane);
-}
-
 static int mlxsw_sp_port_module_map(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				    u8 module, u8 width, u8 lane)
 {
@@ -410,7 +393,11 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	}
 
 	mlxsw_sp_txhdr_construct(skb, &tx_info);
-	len = skb->len;
+	/* TX header is consumed by HW on the way so we shouldn't count its
+	 * bytes as being sent.
+	 */
+	len = skb->len - MLXSW_TXHDR_LEN;
+
 	/* Due to a race we might fail here because of a full queue. In that
 	 * unlikely case we simply drop the packet.
 	 */
@@ -634,94 +621,8 @@ static int mlxsw_sp_port_vlan_mode_trans(struct mlxsw_sp_port *mlxsw_sp_port)
 	return 0;
 }
 
-static struct mlxsw_sp_vfid *
-mlxsw_sp_vfid_find(const struct mlxsw_sp *mlxsw_sp, u16 vid)
-{
-	struct mlxsw_sp_vfid *vfid;
-
-	list_for_each_entry(vfid, &mlxsw_sp->port_vfids.list, list) {
-		if (vfid->vid == vid)
-			return vfid;
-	}
-
-	return NULL;
-}
-
-static u16 mlxsw_sp_avail_vfid_get(const struct mlxsw_sp *mlxsw_sp)
-{
-	return find_first_zero_bit(mlxsw_sp->port_vfids.mapped,
-				   MLXSW_SP_VFID_PORT_MAX);
-}
-
-static int __mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp, u16 vfid)
-{
-	u16 fid = mlxsw_sp_vfid_to_fid(vfid);
-	char sfmr_pl[MLXSW_REG_SFMR_LEN];
-
-	mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_CREATE_FID, fid, 0);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
-}
-
-static void __mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp, u16 vfid)
-{
-	u16 fid = mlxsw_sp_vfid_to_fid(vfid);
-	char sfmr_pl[MLXSW_REG_SFMR_LEN];
-
-	mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_DESTROY_FID, fid, 0);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
-}
-
-static struct mlxsw_sp_vfid *mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp,
-						  u16 vid)
-{
-	struct device *dev = mlxsw_sp->bus_info->dev;
-	struct mlxsw_sp_vfid *vfid;
-	u16 n_vfid;
-	int err;
-
-	n_vfid = mlxsw_sp_avail_vfid_get(mlxsw_sp);
-	if (n_vfid == MLXSW_SP_VFID_PORT_MAX) {
-		dev_err(dev, "No available vFIDs\n");
-		return ERR_PTR(-ERANGE);
-	}
-
-	err = __mlxsw_sp_vfid_create(mlxsw_sp, n_vfid);
-	if (err) {
-		dev_err(dev, "Failed to create vFID=%d\n", n_vfid);
-		return ERR_PTR(err);
-	}
-
-	vfid = kzalloc(sizeof(*vfid), GFP_KERNEL);
-	if (!vfid)
-		goto err_allocate_vfid;
-
-	vfid->vfid = n_vfid;
-	vfid->vid = vid;
-
-	list_add(&vfid->list, &mlxsw_sp->port_vfids.list);
-	set_bit(n_vfid, mlxsw_sp->port_vfids.mapped);
-
-	return vfid;
-
-err_allocate_vfid:
-	__mlxsw_sp_vfid_destroy(mlxsw_sp, n_vfid);
-	return ERR_PTR(-ENOMEM);
-}
-
-static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp,
-				  struct mlxsw_sp_vfid *vfid)
-{
-	clear_bit(vfid->vfid, mlxsw_sp->port_vfids.mapped);
-	list_del(&vfid->list);
-
-	__mlxsw_sp_vfid_destroy(mlxsw_sp, vfid->vfid);
-
-	kfree(vfid);
-}
-
 static struct mlxsw_sp_port *
-mlxsw_sp_port_vport_create(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct mlxsw_sp_vfid *vfid)
+mlxsw_sp_port_vport_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 {
 	struct mlxsw_sp_port *mlxsw_sp_vport;
 
@@ -739,8 +640,7 @@ mlxsw_sp_port_vport_create(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_vport->stp_state = BR_STATE_FORWARDING;
 	mlxsw_sp_vport->lagged = mlxsw_sp_port->lagged;
 	mlxsw_sp_vport->lag_id = mlxsw_sp_port->lag_id;
-	mlxsw_sp_vport->vport.vfid = vfid;
-	mlxsw_sp_vport->vport.vid = vfid->vid;
+	mlxsw_sp_vport->vport.vid = vid;
 
 	list_add(&mlxsw_sp_vport->vport.list, &mlxsw_sp_port->vports_list);
 
@@ -757,9 +657,8 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto,
 			  u16 vid)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_port *mlxsw_sp_vport;
-	struct mlxsw_sp_vfid *vfid;
+	bool untagged = vid == 1;
 	int err;
 
 	/* VLAN 0 is added to HW filter when device goes up, but it is
@@ -773,31 +672,10 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto,
 		return 0;
 	}
 
-	vfid = mlxsw_sp_vfid_find(mlxsw_sp, vid);
-	if (!vfid) {
-		vfid = mlxsw_sp_vfid_create(mlxsw_sp, vid);
-		if (IS_ERR(vfid)) {
-			netdev_err(dev, "Failed to create vFID for VID=%d\n",
-				   vid);
-			return PTR_ERR(vfid);
-		}
-	}
-
-	mlxsw_sp_vport = mlxsw_sp_port_vport_create(mlxsw_sp_port, vfid);
+	mlxsw_sp_vport = mlxsw_sp_port_vport_create(mlxsw_sp_port, vid);
 	if (!mlxsw_sp_vport) {
 		netdev_err(dev, "Failed to create vPort for VID=%d\n", vid);
-		err = -ENOMEM;
-		goto err_port_vport_create;
-	}
-
-	if (!vfid->nr_vports) {
-		err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid,
-					       true, false);
-		if (err) {
-			netdev_err(dev, "Failed to setup flooding for vFID=%d\n",
-				   vfid->vfid);
-			goto err_vport_flood_set;
-		}
+		return -ENOMEM;
 	}
 
 	/* When adding the first VLAN interface on a bridged port we need to
@@ -812,70 +690,37 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto,
 		}
 	}
 
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   true,
-					   mlxsw_sp_vfid_to_fid(vfid->vfid),
-					   vid);
-	if (err) {
-		netdev_err(dev, "Failed to map {Port, VID=%d} to vFID=%d\n",
-			   vid, vfid->vfid);
-		goto err_port_vid_to_fid_set;
-	}
-
 	err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false);
 	if (err) {
 		netdev_err(dev, "Failed to disable learning for VID=%d\n", vid);
 		goto err_port_vid_learning_set;
 	}
 
-	err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, true, false);
+	err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, true, untagged);
 	if (err) {
 		netdev_err(dev, "Failed to set VLAN membership for VID=%d\n",
 			   vid);
 		goto err_port_add_vid;
 	}
 
-	err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid,
-					  MLXSW_REG_SPMS_STATE_FORWARDING);
-	if (err) {
-		netdev_err(dev, "Failed to set STP state for VID=%d\n", vid);
-		goto err_port_stp_state_set;
-	}
-
-	vfid->nr_vports++;
-
 	return 0;
 
-err_port_stp_state_set:
-	mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false);
 err_port_add_vid:
 	mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true);
 err_port_vid_learning_set:
-	mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-				     MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, false,
-				     mlxsw_sp_vfid_to_fid(vfid->vfid), vid);
-err_port_vid_to_fid_set:
 	if (list_is_singular(&mlxsw_sp_port->vports_list))
 		mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port);
 err_port_vp_mode_trans:
-	if (!vfid->nr_vports)
-		mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false,
-					 false);
-err_vport_flood_set:
 	mlxsw_sp_port_vport_destroy(mlxsw_sp_vport);
-err_port_vport_create:
-	if (!vfid->nr_vports)
-		mlxsw_sp_vfid_destroy(mlxsw_sp, vfid);
 	return err;
 }
 
-int mlxsw_sp_port_kill_vid(struct net_device *dev,
-			   __be16 __always_unused proto, u16 vid)
+static int mlxsw_sp_port_kill_vid(struct net_device *dev,
+				  __be16 __always_unused proto, u16 vid)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp_port *mlxsw_sp_vport;
-	struct mlxsw_sp_vfid *vfid;
+	struct mlxsw_sp_fid *f;
 	int err;
 
 	/* VLAN 0 is removed from HW filter when device goes down, but
@@ -890,15 +735,6 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev,
 		return 0;
 	}
 
-	vfid = mlxsw_sp_vport->vport.vfid;
-
-	err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid,
-					  MLXSW_REG_SPMS_STATE_DISCARDING);
-	if (err) {
-		netdev_err(dev, "Failed to set STP state for VID=%d\n", vid);
-		return err;
-	}
-
 	err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false);
 	if (err) {
 		netdev_err(dev, "Failed to set VLAN membership for VID=%d\n",
@@ -912,16 +748,12 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev,
 		return err;
 	}
 
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   false,
-					   mlxsw_sp_vfid_to_fid(vfid->vfid),
-					   vid);
-	if (err) {
-		netdev_err(dev, "Failed to invalidate {Port, VID=%d} to vFID=%d mapping\n",
-			   vid, vfid->vfid);
-		return err;
-	}
+	/* Drop FID reference. If this was the last reference the
+	 * resources will be freed.
+	 */
+	f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+	if (f && !WARN_ON(!f->leave))
+		f->leave(mlxsw_sp_vport);
 
 	/* When removing the last VLAN interface on a bridged port we need to
 	 * transition all active 802.1Q bridge VLANs to use VID to FID
@@ -935,13 +767,8 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev,
 		}
 	}
 
-	vfid->nr_vports--;
 	mlxsw_sp_port_vport_destroy(mlxsw_sp_vport);
 
-	/* Destroy the vFID if no vPorts are assigned to it anymore. */
-	if (!vfid->nr_vports)
-		mlxsw_sp_vfid_destroy(mlxsw_sp_port->mlxsw_sp, vfid);
-
 	return 0;
 }
 
@@ -949,17 +776,11 @@ static int mlxsw_sp_port_get_phys_port_name(struct net_device *dev, char *name,
 					    size_t len)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
-	u8 module, width, lane;
+	u8 module = mlxsw_sp_port->mapping.module;
+	u8 width = mlxsw_sp_port->mapping.width;
+	u8 lane = mlxsw_sp_port->mapping.lane;
 	int err;
 
-	err = __mlxsw_sp_port_module_info_get(mlxsw_sp_port->mlxsw_sp,
-					      mlxsw_sp_port->local_port,
-					      &module, &width, &lane);
-	if (err) {
-		netdev_err(dev, "Failed to retrieve module information\n");
-		return err;
-	}
-
 	if (!mlxsw_sp_port->split)
 		err = snprintf(name, len, "p%d", module + 1);
 	else
@@ -982,6 +803,8 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_get_stats64	= mlxsw_sp_port_get_stats64,
 	.ndo_vlan_rx_add_vid	= mlxsw_sp_port_add_vid,
 	.ndo_vlan_rx_kill_vid	= mlxsw_sp_port_kill_vid,
+	.ndo_neigh_construct	= mlxsw_sp_router_neigh_construct,
+	.ndo_neigh_destroy	= mlxsw_sp_router_neigh_destroy,
 	.ndo_fdb_add		= switchdev_port_fdb_add,
 	.ndo_fdb_del		= switchdev_port_fdb_del,
 	.ndo_fdb_dump		= switchdev_port_fdb_dump,
@@ -1681,8 +1504,8 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	return 0;
 }
 
-static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
-				  bool split, u8 module, u8 width)
+static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				bool split, u8 module, u8 width, u8 lane)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct net_device *dev;
@@ -1697,6 +1520,9 @@ static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	mlxsw_sp_port->mlxsw_sp = mlxsw_sp;
 	mlxsw_sp_port->local_port = local_port;
 	mlxsw_sp_port->split = split;
+	mlxsw_sp_port->mapping.module = module;
+	mlxsw_sp_port->mapping.width = width;
+	mlxsw_sp_port->mapping.lane = lane;
 	bytes = DIV_ROUND_UP(VLAN_N_VID, BITS_PER_BYTE);
 	mlxsw_sp_port->active_vlans = kzalloc(bytes, GFP_KERNEL);
 	if (!mlxsw_sp_port->active_vlans) {
@@ -1839,45 +1665,6 @@ err_port_active_vlans_alloc:
 	return err;
 }
 
-static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
-				bool split, u8 module, u8 width, u8 lane)
-{
-	int err;
-
-	err = mlxsw_sp_port_module_map(mlxsw_sp, local_port, module, width,
-				       lane);
-	if (err)
-		return err;
-
-	err = __mlxsw_sp_port_create(mlxsw_sp, local_port, split, module,
-				     width);
-	if (err)
-		goto err_port_create;
-
-	return 0;
-
-err_port_create:
-	mlxsw_sp_port_module_unmap(mlxsw_sp, local_port);
-	return err;
-}
-
-static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port)
-{
-	struct net_device *dev = mlxsw_sp_port->dev;
-	struct mlxsw_sp_port *mlxsw_sp_vport, *tmp;
-
-	list_for_each_entry_safe(mlxsw_sp_vport, tmp,
-				 &mlxsw_sp_port->vports_list, vport.list) {
-		u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
-
-		/* vPorts created for VLAN devices should already be gone
-		 * by now, since we unregistered the port netdev.
-		 */
-		WARN_ON(is_vlan_dev(mlxsw_sp_vport->dev));
-		mlxsw_sp_port_kill_vid(dev, 0, vid);
-	}
-}
-
 static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port];
@@ -1888,13 +1675,14 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 	mlxsw_core_port_fini(&mlxsw_sp_port->core_port);
 	unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
 	mlxsw_sp_port_dcb_fini(mlxsw_sp_port);
-	mlxsw_sp_port_vports_fini(mlxsw_sp_port);
+	mlxsw_sp_port_kill_vid(mlxsw_sp_port->dev, 0, 1);
 	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
 	mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
 	mlxsw_sp_port_module_unmap(mlxsw_sp, mlxsw_sp_port->local_port);
 	free_percpu(mlxsw_sp_port->pcpu_stats);
 	kfree(mlxsw_sp_port->untagged_vlans);
 	kfree(mlxsw_sp_port->active_vlans);
+	WARN_ON_ONCE(!list_empty(&mlxsw_sp_port->vports_list));
 	free_netdev(mlxsw_sp_port->dev);
 }
 
@@ -1909,8 +1697,8 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp)
 
 static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
 {
+	u8 module, width, lane;
 	size_t alloc_size;
-	u8 module, width;
 	int i;
 	int err;
 
@@ -1921,13 +1709,14 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
 
 	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
 		err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &module,
-						    &width);
+						    &width, &lane);
 		if (err)
 			goto err_port_module_info_get;
 		if (!width)
 			continue;
 		mlxsw_sp->port_to_module[i] = module;
-		err = __mlxsw_sp_port_create(mlxsw_sp, i, false, module, width);
+		err = mlxsw_sp_port_create(mlxsw_sp, i, false, module, width,
+					   lane);
 		if (err)
 			goto err_port_create;
 	}
@@ -1948,12 +1737,85 @@ static u8 mlxsw_sp_cluster_base_port_get(u8 local_port)
 	return local_port - offset;
 }
 
+static int mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port,
+				      u8 module, unsigned int count)
+{
+	u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count;
+	int err, i;
+
+	for (i = 0; i < count; i++) {
+		err = mlxsw_sp_port_module_map(mlxsw_sp, base_port + i, module,
+					       width, i * width);
+		if (err)
+			goto err_port_module_map;
+	}
+
+	for (i = 0; i < count; i++) {
+		err = __mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i, 0);
+		if (err)
+			goto err_port_swid_set;
+	}
+
+	for (i = 0; i < count; i++) {
+		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i, true,
+					   module, width, i * width);
+		if (err)
+			goto err_port_create;
+	}
+
+	return 0;
+
+err_port_create:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+	i = count;
+err_port_swid_set:
+	for (i--; i >= 0; i--)
+		__mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i,
+					 MLXSW_PORT_SWID_DISABLED_PORT);
+	i = count;
+err_port_module_map:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_port_module_unmap(mlxsw_sp, base_port + i);
+	return err;
+}
+
+static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp,
+					 u8 base_port, unsigned int count)
+{
+	u8 local_port, module, width = MLXSW_PORT_MODULE_MAX_WIDTH;
+	int i;
+
+	/* Split by four means we need to re-create two ports, otherwise
+	 * only one.
+	 */
+	count = count / 2;
+
+	for (i = 0; i < count; i++) {
+		local_port = base_port + i * 2;
+		module = mlxsw_sp->port_to_module[local_port];
+
+		mlxsw_sp_port_module_map(mlxsw_sp, local_port, module, width,
+					 0);
+	}
+
+	for (i = 0; i < count; i++)
+		__mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i * 2, 0);
+
+	for (i = 0; i < count; i++) {
+		local_port = base_port + i * 2;
+		module = mlxsw_sp->port_to_module[local_port];
+
+		mlxsw_sp_port_create(mlxsw_sp, local_port, false, module,
+				     width, 0);
+	}
+}
+
 static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
 			       unsigned int count)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
-	u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count;
 	u8 module, cur_width, base_port;
 	int i;
 	int err;
@@ -1965,18 +1827,14 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
 		return -EINVAL;
 	}
 
+	module = mlxsw_sp_port->mapping.module;
+	cur_width = mlxsw_sp_port->mapping.width;
+
 	if (count != 2 && count != 4) {
 		netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n");
 		return -EINVAL;
 	}
 
-	err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module,
-					    &cur_width);
-	if (err) {
-		netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n");
-		return err;
-	}
-
 	if (cur_width != MLXSW_PORT_MODULE_MAX_WIDTH) {
 		netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n");
 		return -EINVAL;
@@ -2001,25 +1859,16 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
 	for (i = 0; i < count; i++)
 		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
 
-	for (i = 0; i < count; i++) {
-		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i, true,
-					   module, width, i * width);
-		if (err) {
-			dev_err(mlxsw_sp->bus_info->dev, "Failed to create split port\n");
-			goto err_port_create;
-		}
+	err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, module, count);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to create split ports\n");
+		goto err_port_split_create;
 	}
 
 	return 0;
 
-err_port_create:
-	for (i--; i >= 0; i--)
-		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
-	for (i = 0; i < count / 2; i++) {
-		module = mlxsw_sp->port_to_module[base_port + i * 2];
-		mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false,
-				     module, MLXSW_PORT_MODULE_MAX_WIDTH, 0);
-	}
+err_port_split_create:
+	mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count);
 	return err;
 }
 
@@ -2027,10 +1876,9 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
-	u8 module, cur_width, base_port;
+	u8 cur_width, base_port;
 	unsigned int count;
 	int i;
-	int err;
 
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port) {
@@ -2044,12 +1892,7 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port)
 		return -EINVAL;
 	}
 
-	err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module,
-					    &cur_width);
-	if (err) {
-		netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n");
-		return err;
-	}
+	cur_width = mlxsw_sp_port->mapping.width;
 	count = cur_width == 1 ? 4 : 2;
 
 	base_port = mlxsw_sp_cluster_base_port_get(local_port);
@@ -2061,14 +1904,7 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port)
 	for (i = 0; i < count; i++)
 		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
 
-	for (i = 0; i < count / 2; i++) {
-		module = mlxsw_sp->port_to_module[base_port + i * 2];
-		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false,
-					   module, MLXSW_PORT_MODULE_MAX_WIDTH,
-					   0);
-		if (err)
-			dev_err(mlxsw_sp->bus_info->dev, "Failed to reinstantiate port\n");
-	}
+	mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count);
 
 	return 0;
 }
@@ -2083,11 +1919,8 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg,
 
 	local_port = mlxsw_reg_pude_local_port_get(pude_pl);
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
-	if (!mlxsw_sp_port) {
-		dev_warn(mlxsw_sp->bus_info->dev, "Port %d: Link event received for non-existent port\n",
-			 local_port);
+	if (!mlxsw_sp_port)
 		return;
-	}
 
 	status = mlxsw_reg_pude_oper_status_get(pude_pl);
 	if (status == MLXSW_PORT_OPER_STATUS_UP) {
@@ -2242,6 +2075,31 @@ static const struct mlxsw_rx_listener mlxsw_sp_rx_listener[] = {
 		.local_port = MLXSW_PORT_DONT_CARE,
 		.trap_id = MLXSW_TRAP_ID_IGMP_V3_REPORT,
 	},
+	{
+		.func = mlxsw_sp_rx_listener_func,
+		.local_port = MLXSW_PORT_DONT_CARE,
+		.trap_id = MLXSW_TRAP_ID_ARPBC,
+	},
+	{
+		.func = mlxsw_sp_rx_listener_func,
+		.local_port = MLXSW_PORT_DONT_CARE,
+		.trap_id = MLXSW_TRAP_ID_ARPUC,
+	},
+	{
+		.func = mlxsw_sp_rx_listener_func,
+		.local_port = MLXSW_PORT_DONT_CARE,
+		.trap_id = MLXSW_TRAP_ID_IP2ME,
+	},
+	{
+		.func = mlxsw_sp_rx_listener_func,
+		.local_port = MLXSW_PORT_DONT_CARE,
+		.trap_id = MLXSW_TRAP_ID_RTR_INGRESS0,
+	},
+	{
+		.func = mlxsw_sp_rx_listener_func,
+		.local_port = MLXSW_PORT_DONT_CARE,
+		.trap_id = MLXSW_TRAP_ID_HOST_MISS_IPV4,
+	},
 };
 
 static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp)
@@ -2282,7 +2140,7 @@ err_rx_trap_set:
 					  mlxsw_sp);
 err_rx_listener_register:
 	for (i--; i >= 0; i--) {
-		mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD,
+		mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_DISCARD,
 				    mlxsw_sp_rx_listener[i].trap_id);
 		mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(hpkt), hpkt_pl);
 
@@ -2299,7 +2157,7 @@ static void mlxsw_sp_traps_fini(struct mlxsw_sp *mlxsw_sp)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_rx_listener); i++) {
-		mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD,
+		mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_DISCARD,
 				    mlxsw_sp_rx_listener[i].trap_id);
 		mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(hpkt), hpkt_pl);
 
@@ -2378,8 +2236,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 
 	mlxsw_sp->core = mlxsw_core;
 	mlxsw_sp->bus_info = mlxsw_bus_info;
-	INIT_LIST_HEAD(&mlxsw_sp->port_vfids.list);
-	INIT_LIST_HEAD(&mlxsw_sp->br_vfids.list);
+	INIT_LIST_HEAD(&mlxsw_sp->fids);
+	INIT_LIST_HEAD(&mlxsw_sp->vfids.list);
 	INIT_LIST_HEAD(&mlxsw_sp->br_mids.list);
 
 	err = mlxsw_sp_base_mac_get(mlxsw_sp);
@@ -2388,16 +2246,10 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		return err;
 	}
 
-	err = mlxsw_sp_ports_create(mlxsw_sp);
-	if (err) {
-		dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n");
-		return err;
-	}
-
 	err = mlxsw_sp_event_register(mlxsw_sp, MLXSW_TRAP_ID_PUDE);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to register for PUDE events\n");
-		goto err_event_register;
+		return err;
 	}
 
 	err = mlxsw_sp_traps_init(mlxsw_sp);
@@ -2430,8 +2282,24 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_switchdev_init;
 	}
 
+	err = mlxsw_sp_router_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n");
+		goto err_router_init;
+	}
+
+	err = mlxsw_sp_ports_create(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n");
+		goto err_ports_create;
+	}
+
 	return 0;
 
+err_ports_create:
+	mlxsw_sp_router_fini(mlxsw_sp);
+err_router_init:
+	mlxsw_sp_switchdev_fini(mlxsw_sp);
 err_switchdev_init:
 err_lag_init:
 	mlxsw_sp_buffers_fini(mlxsw_sp);
@@ -2440,20 +2308,24 @@ err_flood_init:
 	mlxsw_sp_traps_fini(mlxsw_sp);
 err_rx_listener_register:
 	mlxsw_sp_event_unregister(mlxsw_sp, MLXSW_TRAP_ID_PUDE);
-err_event_register:
-	mlxsw_sp_ports_remove(mlxsw_sp);
 	return err;
 }
 
 static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	int i;
 
+	mlxsw_sp_ports_remove(mlxsw_sp);
+	mlxsw_sp_router_fini(mlxsw_sp);
 	mlxsw_sp_switchdev_fini(mlxsw_sp);
 	mlxsw_sp_buffers_fini(mlxsw_sp);
 	mlxsw_sp_traps_fini(mlxsw_sp);
 	mlxsw_sp_event_unregister(mlxsw_sp, MLXSW_TRAP_ID_PUDE);
-	mlxsw_sp_ports_remove(mlxsw_sp);
+	WARN_ON(!list_empty(&mlxsw_sp->vfids.list));
+	WARN_ON(!list_empty(&mlxsw_sp->fids));
+	for (i = 0; i < MLXSW_SP_RIF_MAX; i++)
+		WARN_ON_ONCE(mlxsw_sp->rifs[i]);
 }
 
 static struct mlxsw_config_profile mlxsw_sp_config_profile = {
@@ -2484,6 +2356,10 @@ static struct mlxsw_config_profile mlxsw_sp_config_profile = {
 	.max_ib_mc			= 0,
 	.used_max_pkey			= 1,
 	.max_pkey			= 0,
+	.used_kvd_sizes			= 1,
+	.kvd_linear_size		= MLXSW_SP_KVD_LINEAR_SIZE,
+	.kvd_hash_single_size		= MLXSW_SP_KVD_HASH_SINGLE_SIZE,
+	.kvd_hash_double_size		= MLXSW_SP_KVD_HASH_DOUBLE_SIZE,
 	.swid_config			= {
 		{
 			.used_type	= 1,
@@ -2515,16 +2391,590 @@ static struct mlxsw_driver mlxsw_sp_driver = {
 	.profile			= &mlxsw_sp_config_profile,
 };
 
-static int
-mlxsw_sp_port_fdb_flush_by_port(const struct mlxsw_sp_port *mlxsw_sp_port)
+static bool mlxsw_sp_port_dev_check(const struct net_device *dev)
+{
+	return dev->netdev_ops == &mlxsw_sp_port_netdev_ops;
+}
+
+static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+
+	if (mlxsw_sp_port_dev_check(dev))
+		return netdev_priv(dev);
+
+	netdev_for_each_all_lower_dev(dev, lower_dev, iter) {
+		if (mlxsw_sp_port_dev_check(lower_dev))
+			return netdev_priv(lower_dev);
+	}
+	return NULL;
+}
+
+static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port;
+
+	mlxsw_sp_port = mlxsw_sp_port_dev_lower_find(dev);
+	return mlxsw_sp_port ? mlxsw_sp_port->mlxsw_sp : NULL;
+}
+
+static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+
+	if (mlxsw_sp_port_dev_check(dev))
+		return netdev_priv(dev);
+
+	netdev_for_each_all_lower_dev_rcu(dev, lower_dev, iter) {
+		if (mlxsw_sp_port_dev_check(lower_dev))
+			return netdev_priv(lower_dev);
+	}
+	return NULL;
+}
+
+struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port;
+
+	rcu_read_lock();
+	mlxsw_sp_port = mlxsw_sp_port_dev_lower_find_rcu(dev);
+	if (mlxsw_sp_port)
+		dev_hold(mlxsw_sp_port->dev);
+	rcu_read_unlock();
+	return mlxsw_sp_port;
+}
+
+void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	dev_put(mlxsw_sp_port->dev);
+}
+
+static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r,
+				       unsigned long event)
+{
+	switch (event) {
+	case NETDEV_UP:
+		if (!r)
+			return true;
+		r->ref_count++;
+		return false;
+	case NETDEV_DOWN:
+		if (r && --r->ref_count == 0)
+			return true;
+		/* It is possible we already removed the RIF ourselves
+		 * if it was assigned to a netdev that is now a bridge
+		 * or LAG slave.
+		 */
+		return false;
+	}
+
+	return false;
+}
+
+static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP_RIF_MAX; i++)
+		if (!mlxsw_sp->rifs[i])
+			return i;
+
+	return MLXSW_SP_RIF_MAX;
+}
+
+static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport,
+					   bool *p_lagged, u16 *p_system_port)
+{
+	u8 local_port = mlxsw_sp_vport->local_port;
+
+	*p_lagged = mlxsw_sp_vport->lagged;
+	*p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port;
+}
+
+static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport,
+				    struct net_device *l3_dev, u16 rif,
+				    bool create)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	bool lagged = mlxsw_sp_vport->lagged;
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	u16 system_port;
+
+	mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif,
+			    l3_dev->mtu, l3_dev->dev_addr);
+
+	mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port);
+	mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port,
+				  mlxsw_sp_vport_vid_get(mlxsw_sp_vport));
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
+
+static struct mlxsw_sp_fid *
+mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev)
+{
+	struct mlxsw_sp_fid *f;
+
+	f = kzalloc(sizeof(*f), GFP_KERNEL);
+	if (!f)
+		return NULL;
+
+	f->leave = mlxsw_sp_vport_rif_sp_leave;
+	f->ref_count = 0;
+	f->dev = l3_dev;
+	f->fid = fid;
+
+	return f;
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_alloc(u16 rif, struct net_device *l3_dev, struct mlxsw_sp_fid *f)
+{
+	struct mlxsw_sp_rif *r;
+
+	r = kzalloc(sizeof(*r), GFP_KERNEL);
+	if (!r)
+		return NULL;
+
+	ether_addr_copy(r->addr, l3_dev->dev_addr);
+	r->mtu = l3_dev->mtu;
+	r->ref_count = 1;
+	r->dev = l3_dev;
+	r->rif = rif;
+	r->f = f;
+
+	return r;
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport,
+			     struct net_device *l3_dev)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	struct mlxsw_sp_fid *f;
+	struct mlxsw_sp_rif *r;
+	u16 fid, rif;
+	int err;
+
+	rif = mlxsw_sp_avail_rif_get(mlxsw_sp);
+	if (rif == MLXSW_SP_RIF_MAX)
+		return ERR_PTR(-ERANGE);
+
+	err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, true);
+	if (err)
+		return ERR_PTR(err);
+
+	fid = mlxsw_sp_rif_sp_to_fid(rif);
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true);
+	if (err)
+		goto err_rif_fdb_op;
+
+	f = mlxsw_sp_rfid_alloc(fid, l3_dev);
+	if (!f) {
+		err = -ENOMEM;
+		goto err_rfid_alloc;
+	}
+
+	r = mlxsw_sp_rif_alloc(rif, l3_dev, f);
+	if (!r) {
+		err = -ENOMEM;
+		goto err_rif_alloc;
+	}
+
+	f->r = r;
+	mlxsw_sp->rifs[rif] = r;
+
+	return r;
+
+err_rif_alloc:
+	kfree(f);
+err_rfid_alloc:
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
+err_rif_fdb_op:
+	mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport,
+					  struct mlxsw_sp_rif *r)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	struct net_device *l3_dev = r->dev;
+	struct mlxsw_sp_fid *f = r->f;
+	u16 fid = f->fid;
+	u16 rif = r->rif;
+
+	mlxsw_sp->rifs[rif] = NULL;
+	f->r = NULL;
+
+	kfree(r);
+
+	kfree(f);
+
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
+
+	mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false);
+}
+
+static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport,
+				      struct net_device *l3_dev)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	struct mlxsw_sp_rif *r;
+
+	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
+	if (!r) {
+		r = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev);
+		if (IS_ERR(r))
+			return PTR_ERR(r);
+	}
+
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, r->f);
+	r->f->ref_count++;
+
+	netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", r->f->fid);
+
+	return 0;
+}
+
+static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+
+	netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid);
+
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL);
+	if (--f->ref_count == 0)
+		mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->r);
+}
+
+static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev,
+					 struct net_device *port_dev,
+					 unsigned long event, u16 vid)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev);
+	struct mlxsw_sp_port *mlxsw_sp_vport;
+
+	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
+	if (WARN_ON(!mlxsw_sp_vport))
+		return -EINVAL;
+
+	switch (event) {
+	case NETDEV_UP:
+		return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev);
+	case NETDEV_DOWN:
+		mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport);
+		break;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev,
+					unsigned long event)
+{
+	if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev))
+		return 0;
+
+	return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1);
+}
+
+static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
+					 struct net_device *lag_dev,
+					 unsigned long event, u16 vid)
+{
+	struct net_device *port_dev;
+	struct list_head *iter;
+	int err;
+
+	netdev_for_each_lower_dev(lag_dev, port_dev, iter) {
+		if (mlxsw_sp_port_dev_check(port_dev)) {
+			err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev,
+							    event, vid);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
+				       unsigned long event)
+{
+	if (netif_is_bridge_port(lag_dev))
+		return 0;
+
+	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1);
+}
+
+static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
+						    struct net_device *l3_dev)
+{
+	u16 fid;
+
+	if (is_vlan_dev(l3_dev))
+		fid = vlan_dev_vlan_id(l3_dev);
+	else if (mlxsw_sp->master_bridge.dev == l3_dev)
+		fid = 1;
+	else
+		return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev);
+
+	return mlxsw_sp_fid_find(mlxsw_sp, fid);
+}
+
+static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid)
+{
+	if (mlxsw_sp_fid_is_vfid(fid))
+		return MLXSW_REG_RITR_FID_IF;
+	else
+		return MLXSW_REG_RITR_VLAN_IF;
+}
+
+static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp,
+				  struct net_device *l3_dev,
+				  u16 fid, u16 rif,
+				  bool create)
+{
+	enum mlxsw_reg_ritr_if_type rif_type;
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+
+	rif_type = mlxsw_sp_rif_type_get(fid);
+	mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, l3_dev->mtu,
+			    l3_dev->dev_addr);
+	mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp,
+				      struct net_device *l3_dev,
+				      struct mlxsw_sp_fid *f)
+{
+	struct mlxsw_sp_rif *r;
+	u16 rif;
+	int err;
+
+	rif = mlxsw_sp_avail_rif_get(mlxsw_sp);
+	if (rif == MLXSW_SP_RIF_MAX)
+		return -ERANGE;
+
+	err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true);
+	if (err)
+		goto err_rif_fdb_op;
+
+	r = mlxsw_sp_rif_alloc(rif, l3_dev, f);
+	if (!r) {
+		err = -ENOMEM;
+		goto err_rif_alloc;
+	}
+
+	f->r = r;
+	mlxsw_sp->rifs[rif] = r;
+
+	netdev_dbg(l3_dev, "RIF=%d created\n", rif);
+
+	return 0;
+
+err_rif_alloc:
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
+err_rif_fdb_op:
+	mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
+	return err;
+}
+
+void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_rif *r)
+{
+	struct net_device *l3_dev = r->dev;
+	struct mlxsw_sp_fid *f = r->f;
+	u16 rif = r->rif;
+
+	mlxsw_sp->rifs[rif] = NULL;
+	f->r = NULL;
+
+	kfree(r);
+
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
+
+	mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
+
+	netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif);
+}
+
+static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
+					  struct net_device *br_dev,
+					  unsigned long event)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
+	struct mlxsw_sp_fid *f;
+
+	/* FID can either be an actual FID if the L3 device is the
+	 * VLAN-aware bridge or a VLAN device on top. Otherwise, the
+	 * L3 device is a VLAN-unaware bridge and we get a vFID.
+	 */
+	f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev);
+	if (WARN_ON(!f))
+		return -EINVAL;
+
+	switch (event) {
+	case NETDEV_UP:
+		return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f);
+	case NETDEV_DOWN:
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+		break;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
+					unsigned long event)
+{
+	struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
+	u16 vid = vlan_dev_vlan_id(vlan_dev);
+
+	if (mlxsw_sp_port_dev_check(real_dev))
+		return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event,
+						     vid);
+	else if (netif_is_lag_master(real_dev))
+		return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
+						     vid);
+	else if (netif_is_bridge_master(real_dev) &&
+		 mlxsw_sp->master_bridge.dev == real_dev)
+		return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev,
+						      event);
+
+	return 0;
+}
+
+static int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
+				   unsigned long event, void *ptr)
+{
+	struct in_ifaddr *ifa = (struct in_ifaddr *) ptr;
+	struct net_device *dev = ifa->ifa_dev->dev;
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_rif *r;
+	int err = 0;
+
+	mlxsw_sp = mlxsw_sp_lower_get(dev);
+	if (!mlxsw_sp)
+		goto out;
+
+	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!mlxsw_sp_rif_should_config(r, event))
+		goto out;
+
+	if (mlxsw_sp_port_dev_check(dev))
+		err = mlxsw_sp_inetaddr_port_event(dev, event);
+	else if (netif_is_lag_master(dev))
+		err = mlxsw_sp_inetaddr_lag_event(dev, event);
+	else if (netif_is_bridge_master(dev))
+		err = mlxsw_sp_inetaddr_bridge_event(dev, dev, event);
+	else if (is_vlan_dev(dev))
+		err = mlxsw_sp_inetaddr_vlan_event(dev, event);
+
+out:
+	return notifier_from_errno(err);
+}
+
+static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif,
+			     const char *mac, int mtu)
+{
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	int err;
+
+	mlxsw_reg_ritr_rif_pack(ritr_pl, rif);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_ritr_mtu_set(ritr_pl, mtu);
+	mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac);
+	mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static int mlxsw_sp_netdevice_router_port_event(struct net_device *dev)
+{
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_rif *r;
+	int err;
+
+	mlxsw_sp = mlxsw_sp_lower_get(dev);
+	if (!mlxsw_sp)
+		return 0;
+
+	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!r)
+		return 0;
+
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, false);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_rif_edit(mlxsw_sp, r->rif, dev->dev_addr, dev->mtu);
+	if (err)
+		goto err_rif_edit;
+
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, r->f->fid, true);
+	if (err)
+		goto err_rif_fdb_op;
+
+	ether_addr_copy(r->addr, dev->dev_addr);
+	r->mtu = dev->mtu;
+
+	netdev_dbg(dev, "Updated RIF=%d\n", r->rif);
+
+	return 0;
+
+err_rif_fdb_op:
+	mlxsw_sp_rif_edit(mlxsw_sp, r->rif, r->addr, r->mtu);
+err_rif_edit:
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, true);
+	return err;
+}
+
+static bool mlxsw_sp_lag_port_fid_member(struct mlxsw_sp_port *lag_port,
+					 u16 fid)
+{
+	if (mlxsw_sp_fid_is_vfid(fid))
+		return mlxsw_sp_port_vport_find_by_fid(lag_port, fid);
+	else
+		return test_bit(fid, lag_port->active_vlans);
+}
+
+static bool mlxsw_sp_port_fdb_should_flush(struct mlxsw_sp_port *mlxsw_sp_port,
+					   u16 fid)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char sfdf_pl[MLXSW_REG_SFDF_LEN];
+	u8 local_port = mlxsw_sp_port->local_port;
+	u16 lag_id = mlxsw_sp_port->lag_id;
+	int i, count = 0;
 
-	mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_PORT);
-	mlxsw_reg_sfdf_system_port_set(sfdf_pl, mlxsw_sp_port->local_port);
+	if (!mlxsw_sp_port->lagged)
+		return true;
 
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
+	for (i = 0; i < MLXSW_SP_PORT_PER_LAG_MAX; i++) {
+		struct mlxsw_sp_port *lag_port;
+
+		lag_port = mlxsw_sp_port_lagged_get(mlxsw_sp, lag_id, i);
+		if (!lag_port || lag_port->local_port == local_port)
+			continue;
+		if (mlxsw_sp_lag_port_fid_member(lag_port, fid))
+			count++;
+	}
+
+	return !count;
 }
 
 static int
@@ -2539,17 +2989,8 @@ mlxsw_sp_port_fdb_flush_by_port_fid(const struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_reg_sfdf_port_fid_system_port_set(sfdf_pl,
 						mlxsw_sp_port->local_port);
 
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
-}
-
-static int
-mlxsw_sp_port_fdb_flush_by_lag_id(const struct mlxsw_sp_port *mlxsw_sp_port)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char sfdf_pl[MLXSW_REG_SFDF_LEN];
-
-	mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_LAG);
-	mlxsw_reg_sfdf_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id);
+	netdev_dbg(mlxsw_sp_port->dev, "FDB flushed using Port=%d, FID=%d\n",
+		   mlxsw_sp_port->local_port, fid);
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
 }
@@ -2565,71 +3006,64 @@ mlxsw_sp_port_fdb_flush_by_lag_id_fid(const struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_reg_sfdf_fid_set(sfdf_pl, fid);
 	mlxsw_reg_sfdf_lag_fid_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id);
 
+	netdev_dbg(mlxsw_sp_port->dev, "FDB flushed using LAG ID=%d, FID=%d\n",
+		   mlxsw_sp_port->lag_id, fid);
+
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
 }
 
-static int
-__mlxsw_sp_port_fdb_flush(const struct mlxsw_sp_port *mlxsw_sp_port)
+int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid)
 {
-	int err, last_err = 0;
-	u16 vid;
-
-	for (vid = 1; vid < VLAN_N_VID - 1; vid++) {
-		err = mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_port, vid);
-		if (err)
-			last_err = err;
-	}
+	if (!mlxsw_sp_port_fdb_should_flush(mlxsw_sp_port, fid))
+		return 0;
 
-	return last_err;
+	if (mlxsw_sp_port->lagged)
+		return mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_port,
+							     fid);
+	else
+		return mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_port, fid);
 }
 
-static int
-__mlxsw_sp_port_fdb_flush_lagged(const struct mlxsw_sp_port *mlxsw_sp_port)
+static void mlxsw_sp_master_bridge_gone_sync(struct mlxsw_sp *mlxsw_sp)
 {
-	int err, last_err = 0;
-	u16 vid;
+	struct mlxsw_sp_fid *f, *tmp;
 
-	for (vid = 1; vid < VLAN_N_VID - 1; vid++) {
-		err = mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_port, vid);
-		if (err)
-			last_err = err;
-	}
-
-	return last_err;
+	list_for_each_entry_safe(f, tmp, &mlxsw_sp->fids, list)
+		if (--f->ref_count == 0)
+			mlxsw_sp_fid_destroy(mlxsw_sp, f);
+		else
+			WARN_ON_ONCE(1);
 }
 
-static int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port)
+static bool mlxsw_sp_master_bridge_check(struct mlxsw_sp *mlxsw_sp,
+					 struct net_device *br_dev)
 {
-	if (!list_empty(&mlxsw_sp_port->vports_list))
-		if (mlxsw_sp_port->lagged)
-			return __mlxsw_sp_port_fdb_flush_lagged(mlxsw_sp_port);
-		else
-			return __mlxsw_sp_port_fdb_flush(mlxsw_sp_port);
-	else
-		if (mlxsw_sp_port->lagged)
-			return mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port);
-		else
-			return mlxsw_sp_port_fdb_flush_by_port(mlxsw_sp_port);
+	return !mlxsw_sp->master_bridge.dev ||
+	       mlxsw_sp->master_bridge.dev == br_dev;
 }
 
-static int mlxsw_sp_vport_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_vport)
+static void mlxsw_sp_master_bridge_inc(struct mlxsw_sp *mlxsw_sp,
+				       struct net_device *br_dev)
 {
-	u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_vport);
-	u16 fid = mlxsw_sp_vfid_to_fid(vfid);
-
-	if (mlxsw_sp_vport->lagged)
-		return mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_vport,
-							     fid);
-	else
-		return mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_vport, fid);
+	mlxsw_sp->master_bridge.dev = br_dev;
+	mlxsw_sp->master_bridge.ref_count++;
 }
 
-static bool mlxsw_sp_port_dev_check(const struct net_device *dev)
+static void mlxsw_sp_master_bridge_dec(struct mlxsw_sp *mlxsw_sp)
 {
-	return dev->netdev_ops == &mlxsw_sp_port_netdev_ops;
+	if (--mlxsw_sp->master_bridge.ref_count == 0) {
+		mlxsw_sp->master_bridge.dev = NULL;
+		/* It's possible upper VLAN devices are still holding
+		 * references to underlying FIDs. Drop the reference
+		 * and release the resources if it was the last one.
+		 * If it wasn't, then something bad happened.
+		 */
+		mlxsw_sp_master_bridge_gone_sync(mlxsw_sp);
+	}
 }
 
-static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port)
+static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port,
+				     struct net_device *br_dev)
 {
 	struct net_device *dev = mlxsw_sp_port->dev;
 	int err;
@@ -2643,6 +3077,8 @@ static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port)
 	if (err)
 		return err;
 
+	mlxsw_sp_master_bridge_inc(mlxsw_sp_port->mlxsw_sp, br_dev);
+
 	mlxsw_sp_port->learning = 1;
 	mlxsw_sp_port->learning_sync = 1;
 	mlxsw_sp_port->uc_flood = 1;
@@ -2651,16 +3087,14 @@ static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port)
 	return 0;
 }
 
-static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
-				      bool flush_fdb)
+static void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port)
 {
 	struct net_device *dev = mlxsw_sp_port->dev;
 
-	if (flush_fdb && mlxsw_sp_port_fdb_flush(mlxsw_sp_port))
-		netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n");
-
 	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
 
+	mlxsw_sp_master_bridge_dec(mlxsw_sp_port->mlxsw_sp);
+
 	mlxsw_sp_port->learning = 0;
 	mlxsw_sp_port->learning_sync = 0;
 	mlxsw_sp_port->uc_flood = 0;
@@ -2669,28 +3103,7 @@ static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	/* Add implicit VLAN interface in the device, so that untagged
 	 * packets will be classified to the default vFID.
 	 */
-	return mlxsw_sp_port_add_vid(dev, 0, 1);
-}
-
-static bool mlxsw_sp_master_bridge_check(struct mlxsw_sp *mlxsw_sp,
-					 struct net_device *br_dev)
-{
-	return !mlxsw_sp->master_bridge.dev ||
-	       mlxsw_sp->master_bridge.dev == br_dev;
-}
-
-static void mlxsw_sp_master_bridge_inc(struct mlxsw_sp *mlxsw_sp,
-				       struct net_device *br_dev)
-{
-	mlxsw_sp->master_bridge.dev = br_dev;
-	mlxsw_sp->master_bridge.ref_count++;
-}
-
-static void mlxsw_sp_master_bridge_dec(struct mlxsw_sp *mlxsw_sp,
-				       struct net_device *br_dev)
-{
-	if (--mlxsw_sp->master_bridge.ref_count == 0)
-		mlxsw_sp->master_bridge.dev = NULL;
+	mlxsw_sp_port_add_vid(dev, 0, 1);
 }
 
 static int mlxsw_sp_lag_create(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
@@ -2806,6 +3219,45 @@ static int mlxsw_sp_port_lag_index_get(struct mlxsw_sp *mlxsw_sp,
 	return -EBUSY;
 }
 
+static void
+mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
+				  u16 lag_id)
+{
+	struct mlxsw_sp_port *mlxsw_sp_vport;
+	struct mlxsw_sp_fid *f;
+
+	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1);
+	if (WARN_ON(!mlxsw_sp_vport))
+		return;
+
+	/* If vPort is assigned a RIF, then leave it since it's no
+	 * longer valid.
+	 */
+	f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+	if (f)
+		f->leave(mlxsw_sp_vport);
+
+	mlxsw_sp_vport->lag_id = lag_id;
+	mlxsw_sp_vport->lagged = 1;
+}
+
+static void
+mlxsw_sp_port_pvid_vport_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct mlxsw_sp_port *mlxsw_sp_vport;
+	struct mlxsw_sp_fid *f;
+
+	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1);
+	if (WARN_ON(!mlxsw_sp_vport))
+		return;
+
+	f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+	if (f)
+		f->leave(mlxsw_sp_vport);
+
+	mlxsw_sp_vport->lagged = 0;
+}
+
 static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 				  struct net_device *lag_dev)
 {
@@ -2841,6 +3293,9 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->lag_id = lag_id;
 	mlxsw_sp_port->lagged = 1;
 	lag->ref_count++;
+
+	mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_id);
+
 	return 0;
 
 err_col_port_enable:
@@ -2851,65 +3306,35 @@ err_col_port_add:
 	return err;
 }
 
-static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport,
-				       struct net_device *br_dev,
-				       bool flush_fdb);
-
-static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
-				   struct net_device *lag_dev)
+static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
+				    struct net_device *lag_dev)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	struct mlxsw_sp_port *mlxsw_sp_vport;
-	struct mlxsw_sp_upper *lag;
 	u16 lag_id = mlxsw_sp_port->lag_id;
-	int err;
+	struct mlxsw_sp_upper *lag;
 
 	if (!mlxsw_sp_port->lagged)
-		return 0;
+		return;
 	lag = mlxsw_sp_lag_get(mlxsw_sp, lag_id);
 	WARN_ON(lag->ref_count == 0);
 
-	err = mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id);
-	if (err)
-		return err;
-	err = mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
-	if (err)
-		return err;
-
-	/* In case we leave a LAG device that has bridges built on top,
-	 * then their teardown sequence is never issued and we need to
-	 * invoke the necessary cleanup routines ourselves.
-	 */
-	list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list,
-			    vport.list) {
-		struct net_device *br_dev;
-
-		if (!mlxsw_sp_vport->bridged)
-			continue;
-
-		br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport);
-		mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, false);
-	}
+	mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id);
+	mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
 
 	if (mlxsw_sp_port->bridged) {
 		mlxsw_sp_port_active_vlans_del(mlxsw_sp_port);
-		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false);
-		mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL);
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port);
 	}
 
-	if (lag->ref_count == 1) {
-		if (mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port))
-			netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n");
-		err = mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
-		if (err)
-			return err;
-	}
+	if (lag->ref_count == 1)
+		mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
 
 	mlxsw_core_lag_mapping_clear(mlxsw_sp->core, lag_id,
 				     mlxsw_sp_port->local_port);
 	mlxsw_sp_port->lagged = 0;
 	lag->ref_count--;
-	return 0;
+
+	mlxsw_sp_port_pvid_vport_lag_leave(mlxsw_sp_port);
 }
 
 static int mlxsw_sp_lag_dist_port_add(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -2958,42 +3383,25 @@ static int mlxsw_sp_port_vlan_link(struct mlxsw_sp_port *mlxsw_sp_port,
 	u16 vid = vlan_dev_vlan_id(vlan_dev);
 
 	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
-	if (!mlxsw_sp_vport) {
-		WARN_ON(!mlxsw_sp_vport);
+	if (WARN_ON(!mlxsw_sp_vport))
 		return -EINVAL;
-	}
 
 	mlxsw_sp_vport->dev = vlan_dev;
 
 	return 0;
 }
 
-static int mlxsw_sp_port_vlan_unlink(struct mlxsw_sp_port *mlxsw_sp_port,
-				     struct net_device *vlan_dev)
+static void mlxsw_sp_port_vlan_unlink(struct mlxsw_sp_port *mlxsw_sp_port,
+				      struct net_device *vlan_dev)
 {
 	struct mlxsw_sp_port *mlxsw_sp_vport;
 	u16 vid = vlan_dev_vlan_id(vlan_dev);
 
 	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
-	if (!mlxsw_sp_vport) {
-		WARN_ON(!mlxsw_sp_vport);
-		return -EINVAL;
-	}
-
-	/* When removing a VLAN device while still bridged we should first
-	 * remove it from the bridge, as we receive the bridge's notification
-	 * when the vPort is already gone.
-	 */
-	if (mlxsw_sp_vport->bridged) {
-		struct net_device *br_dev;
-
-		br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport);
-		mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, true);
-	}
+	if (WARN_ON(!mlxsw_sp_vport))
+		return;
 
 	mlxsw_sp_vport->dev = mlxsw_sp_port->dev;
-
-	return 0;
 }
 
 static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
@@ -3003,7 +3411,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct net_device *upper_dev;
 	struct mlxsw_sp *mlxsw_sp;
-	int err;
+	int err = 0;
 
 	mlxsw_sp_port = netdev_priv(dev);
 	mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
@@ -3012,73 +3420,56 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (!info->master || !info->linking)
+		if (!is_vlan_dev(upper_dev) &&
+		    !netif_is_lag_master(upper_dev) &&
+		    !netif_is_bridge_master(upper_dev))
+			return -EINVAL;
+		if (!info->linking)
 			break;
 		/* HW limitation forbids to put ports to multiple bridges. */
 		if (netif_is_bridge_master(upper_dev) &&
 		    !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev))
-			return NOTIFY_BAD;
+			return -EINVAL;
 		if (netif_is_lag_master(upper_dev) &&
 		    !mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev,
 					       info->upper_info))
-			return NOTIFY_BAD;
+			return -EINVAL;
+		if (netif_is_lag_master(upper_dev) && vlan_uses_dev(dev))
+			return -EINVAL;
+		if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) &&
+		    !netif_is_lag_master(vlan_dev_real_dev(upper_dev)))
+			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
 		if (is_vlan_dev(upper_dev)) {
-			if (info->linking) {
+			if (info->linking)
 				err = mlxsw_sp_port_vlan_link(mlxsw_sp_port,
 							      upper_dev);
-				if (err) {
-					netdev_err(dev, "Failed to link VLAN device\n");
-					return NOTIFY_BAD;
-				}
-			} else {
-				err = mlxsw_sp_port_vlan_unlink(mlxsw_sp_port,
-								upper_dev);
-				if (err) {
-					netdev_err(dev, "Failed to unlink VLAN device\n");
-					return NOTIFY_BAD;
-				}
-			}
+			else
+				 mlxsw_sp_port_vlan_unlink(mlxsw_sp_port,
+							   upper_dev);
 		} else if (netif_is_bridge_master(upper_dev)) {
-			if (info->linking) {
-				err = mlxsw_sp_port_bridge_join(mlxsw_sp_port);
-				if (err) {
-					netdev_err(dev, "Failed to join bridge\n");
-					return NOTIFY_BAD;
-				}
-				mlxsw_sp_master_bridge_inc(mlxsw_sp, upper_dev);
-			} else {
-				err = mlxsw_sp_port_bridge_leave(mlxsw_sp_port,
-								 true);
-				mlxsw_sp_master_bridge_dec(mlxsw_sp, upper_dev);
-				if (err) {
-					netdev_err(dev, "Failed to leave bridge\n");
-					return NOTIFY_BAD;
-				}
-			}
+			if (info->linking)
+				err = mlxsw_sp_port_bridge_join(mlxsw_sp_port,
+								upper_dev);
+			else
+				mlxsw_sp_port_bridge_leave(mlxsw_sp_port);
 		} else if (netif_is_lag_master(upper_dev)) {
-			if (info->linking) {
+			if (info->linking)
 				err = mlxsw_sp_port_lag_join(mlxsw_sp_port,
 							     upper_dev);
-				if (err) {
-					netdev_err(dev, "Failed to join link aggregation\n");
-					return NOTIFY_BAD;
-				}
-			} else {
-				err = mlxsw_sp_port_lag_leave(mlxsw_sp_port,
-							      upper_dev);
-				if (err) {
-					netdev_err(dev, "Failed to leave link aggregation\n");
-					return NOTIFY_BAD;
-				}
-			}
+			else
+				mlxsw_sp_port_lag_leave(mlxsw_sp_port,
+							upper_dev);
+		} else {
+			err = -EINVAL;
+			WARN_ON(1);
 		}
 		break;
 	}
 
-	return NOTIFY_DONE;
+	return err;
 }
 
 static int mlxsw_sp_netdevice_port_lower_event(struct net_device *dev,
@@ -3102,7 +3493,7 @@ static int mlxsw_sp_netdevice_port_lower_event(struct net_device *dev,
 		break;
 	}
 
-	return NOTIFY_DONE;
+	return 0;
 }
 
 static int mlxsw_sp_netdevice_port_event(struct net_device *dev,
@@ -3116,7 +3507,7 @@ static int mlxsw_sp_netdevice_port_event(struct net_device *dev,
 		return mlxsw_sp_netdevice_port_lower_event(dev, event, ptr);
 	}
 
-	return NOTIFY_DONE;
+	return 0;
 }
 
 static int mlxsw_sp_netdevice_lag_event(struct net_device *lag_dev,
@@ -3129,218 +3520,230 @@ static int mlxsw_sp_netdevice_lag_event(struct net_device *lag_dev,
 	netdev_for_each_lower_dev(lag_dev, dev, iter) {
 		if (mlxsw_sp_port_dev_check(dev)) {
 			ret = mlxsw_sp_netdevice_port_event(dev, event, ptr);
-			if (ret == NOTIFY_BAD)
+			if (ret)
 				return ret;
 		}
 	}
 
-	return NOTIFY_DONE;
+	return 0;
 }
 
-static struct mlxsw_sp_vfid *
-mlxsw_sp_br_vfid_find(const struct mlxsw_sp *mlxsw_sp,
-		      const struct net_device *br_dev)
+static int mlxsw_sp_master_bridge_vlan_link(struct mlxsw_sp *mlxsw_sp,
+					    struct net_device *vlan_dev)
 {
-	struct mlxsw_sp_vfid *vfid;
+	u16 fid = vlan_dev_vlan_id(vlan_dev);
+	struct mlxsw_sp_fid *f;
 
-	list_for_each_entry(vfid, &mlxsw_sp->br_vfids.list, list) {
-		if (vfid->br_dev == br_dev)
-			return vfid;
+	f = mlxsw_sp_fid_find(mlxsw_sp, fid);
+	if (!f) {
+		f = mlxsw_sp_fid_create(mlxsw_sp, fid);
+		if (IS_ERR(f))
+			return PTR_ERR(f);
 	}
 
-	return NULL;
+	f->ref_count++;
+
+	return 0;
+}
+
+static void mlxsw_sp_master_bridge_vlan_unlink(struct mlxsw_sp *mlxsw_sp,
+					       struct net_device *vlan_dev)
+{
+	u16 fid = vlan_dev_vlan_id(vlan_dev);
+	struct mlxsw_sp_fid *f;
+
+	f = mlxsw_sp_fid_find(mlxsw_sp, fid);
+	if (f && f->r)
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+	if (f && --f->ref_count == 0)
+		mlxsw_sp_fid_destroy(mlxsw_sp, f);
 }
 
-static u16 mlxsw_sp_vfid_to_br_vfid(u16 vfid)
+static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev,
+					   unsigned long event, void *ptr)
 {
-	return vfid - MLXSW_SP_VFID_PORT_MAX;
+	struct netdev_notifier_changeupper_info *info;
+	struct net_device *upper_dev;
+	struct mlxsw_sp *mlxsw_sp;
+	int err;
+
+	mlxsw_sp = mlxsw_sp_lower_get(br_dev);
+	if (!mlxsw_sp)
+		return 0;
+	if (br_dev != mlxsw_sp->master_bridge.dev)
+		return 0;
+
+	info = ptr;
+
+	switch (event) {
+	case NETDEV_CHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (!is_vlan_dev(upper_dev))
+			break;
+		if (info->linking) {
+			err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp,
+							       upper_dev);
+			if (err)
+				return err;
+		} else {
+			mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp, upper_dev);
+		}
+		break;
+	}
+
+	return 0;
 }
 
-static u16 mlxsw_sp_br_vfid_to_vfid(u16 br_vfid)
+static u16 mlxsw_sp_avail_vfid_get(const struct mlxsw_sp *mlxsw_sp)
 {
-	return MLXSW_SP_VFID_PORT_MAX + br_vfid;
+	return find_first_zero_bit(mlxsw_sp->vfids.mapped,
+				   MLXSW_SP_VFID_MAX);
 }
 
-static u16 mlxsw_sp_avail_br_vfid_get(const struct mlxsw_sp *mlxsw_sp)
+static int mlxsw_sp_vfid_op(struct mlxsw_sp *mlxsw_sp, u16 fid, bool create)
 {
-	return find_first_zero_bit(mlxsw_sp->br_vfids.mapped,
-				   MLXSW_SP_VFID_BR_MAX);
+	char sfmr_pl[MLXSW_REG_SFMR_LEN];
+
+	mlxsw_reg_sfmr_pack(sfmr_pl, !create, fid, 0);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
 }
 
-static struct mlxsw_sp_vfid *mlxsw_sp_br_vfid_create(struct mlxsw_sp *mlxsw_sp,
-						     struct net_device *br_dev)
+static void mlxsw_sp_vport_vfid_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
+
+static struct mlxsw_sp_fid *mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp,
+						 struct net_device *br_dev)
 {
 	struct device *dev = mlxsw_sp->bus_info->dev;
-	struct mlxsw_sp_vfid *vfid;
-	u16 n_vfid;
+	struct mlxsw_sp_fid *f;
+	u16 vfid, fid;
 	int err;
 
-	n_vfid = mlxsw_sp_br_vfid_to_vfid(mlxsw_sp_avail_br_vfid_get(mlxsw_sp));
-	if (n_vfid == MLXSW_SP_VFID_MAX) {
+	vfid = mlxsw_sp_avail_vfid_get(mlxsw_sp);
+	if (vfid == MLXSW_SP_VFID_MAX) {
 		dev_err(dev, "No available vFIDs\n");
 		return ERR_PTR(-ERANGE);
 	}
 
-	err = __mlxsw_sp_vfid_create(mlxsw_sp, n_vfid);
+	fid = mlxsw_sp_vfid_to_fid(vfid);
+	err = mlxsw_sp_vfid_op(mlxsw_sp, fid, true);
 	if (err) {
-		dev_err(dev, "Failed to create vFID=%d\n", n_vfid);
+		dev_err(dev, "Failed to create FID=%d\n", fid);
 		return ERR_PTR(err);
 	}
 
-	vfid = kzalloc(sizeof(*vfid), GFP_KERNEL);
-	if (!vfid)
+	f = kzalloc(sizeof(*f), GFP_KERNEL);
+	if (!f)
 		goto err_allocate_vfid;
 
-	vfid->vfid = n_vfid;
-	vfid->br_dev = br_dev;
+	f->leave = mlxsw_sp_vport_vfid_leave;
+	f->fid = fid;
+	f->dev = br_dev;
 
-	list_add(&vfid->list, &mlxsw_sp->br_vfids.list);
-	set_bit(mlxsw_sp_vfid_to_br_vfid(n_vfid), mlxsw_sp->br_vfids.mapped);
+	list_add(&f->list, &mlxsw_sp->vfids.list);
+	set_bit(vfid, mlxsw_sp->vfids.mapped);
 
-	return vfid;
+	return f;
 
 err_allocate_vfid:
-	__mlxsw_sp_vfid_destroy(mlxsw_sp, n_vfid);
+	mlxsw_sp_vfid_op(mlxsw_sp, fid, false);
 	return ERR_PTR(-ENOMEM);
 }
 
-static void mlxsw_sp_br_vfid_destroy(struct mlxsw_sp *mlxsw_sp,
-				     struct mlxsw_sp_vfid *vfid)
+static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_fid *f)
 {
-	u16 br_vfid = mlxsw_sp_vfid_to_br_vfid(vfid->vfid);
+	u16 vfid = mlxsw_sp_fid_to_vfid(f->fid);
+	u16 fid = f->fid;
+
+	clear_bit(vfid, mlxsw_sp->vfids.mapped);
+	list_del(&f->list);
 
-	clear_bit(br_vfid, mlxsw_sp->br_vfids.mapped);
-	list_del(&vfid->list);
+	if (f->r)
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
 
-	__mlxsw_sp_vfid_destroy(mlxsw_sp, vfid->vfid);
+	kfree(f);
 
-	kfree(vfid);
+	mlxsw_sp_vfid_op(mlxsw_sp, fid, false);
 }
 
-static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport,
-				       struct net_device *br_dev,
-				       bool flush_fdb)
+static int mlxsw_sp_vport_fid_map(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid,
+				  bool valid)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID;
 	u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
-	struct net_device *dev = mlxsw_sp_vport->dev;
-	struct mlxsw_sp_vfid *vfid, *new_vfid;
-	int err;
-
-	vfid = mlxsw_sp_br_vfid_find(mlxsw_sp, br_dev);
-	if (!vfid) {
-		WARN_ON(!vfid);
-		return -EINVAL;
-	}
-
-	/* We need a vFID to go back to after leaving the bridge's vFID. */
-	new_vfid = mlxsw_sp_vfid_find(mlxsw_sp, vid);
-	if (!new_vfid) {
-		new_vfid = mlxsw_sp_vfid_create(mlxsw_sp, vid);
-		if (IS_ERR(new_vfid)) {
-			netdev_err(dev, "Failed to create vFID for VID=%d\n",
-				   vid);
-			return PTR_ERR(new_vfid);
-		}
-	}
 
-	/* Invalidate existing {Port, VID} to vFID mapping and create a new
-	 * one for the new vFID.
-	 */
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   false,
-					   mlxsw_sp_vfid_to_fid(vfid->vfid),
-					   vid);
-	if (err) {
-		netdev_err(dev, "Failed to invalidate {Port, VID} to vFID=%d mapping\n",
-			   vfid->vfid);
-		goto err_port_vid_to_fid_invalidate;
-	}
+	return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, mt, valid, fid,
+					    vid);
+}
 
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   true,
-					   mlxsw_sp_vfid_to_fid(new_vfid->vfid),
-					   vid);
-	if (err) {
-		netdev_err(dev, "Failed to map {Port, VID} to vFID=%d\n",
-			   new_vfid->vfid);
-		goto err_port_vid_to_fid_validate;
-	}
+static int mlxsw_sp_vport_vfid_join(struct mlxsw_sp_port *mlxsw_sp_vport,
+				    struct net_device *br_dev)
+{
+	struct mlxsw_sp_fid *f;
+	int err;
 
-	err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false);
-	if (err) {
-		netdev_err(dev, "Failed to disable learning\n");
-		goto err_port_vid_learning_set;
+	f = mlxsw_sp_vfid_find(mlxsw_sp_vport->mlxsw_sp, br_dev);
+	if (!f) {
+		f = mlxsw_sp_vfid_create(mlxsw_sp_vport->mlxsw_sp, br_dev);
+		if (IS_ERR(f))
+			return PTR_ERR(f);
 	}
 
-	err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false,
-				       false);
-	if (err) {
-		netdev_err(dev, "Failed clear to clear flooding\n");
+	err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, true);
+	if (err)
 		goto err_vport_flood_set;
-	}
 
-	err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid,
-					  MLXSW_REG_SPMS_STATE_FORWARDING);
-	if (err) {
-		netdev_err(dev, "Failed to set STP state\n");
-		goto err_port_stp_state_set;
-	}
-
-	if (flush_fdb && mlxsw_sp_vport_fdb_flush(mlxsw_sp_vport))
-		netdev_err(dev, "Failed to flush FDB\n");
+	err = mlxsw_sp_vport_fid_map(mlxsw_sp_vport, f->fid, true);
+	if (err)
+		goto err_vport_fid_map;
 
-	/* Switch between the vFIDs and destroy the old one if needed. */
-	new_vfid->nr_vports++;
-	mlxsw_sp_vport->vport.vfid = new_vfid;
-	vfid->nr_vports--;
-	if (!vfid->nr_vports)
-		mlxsw_sp_br_vfid_destroy(mlxsw_sp, vfid);
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, f);
+	f->ref_count++;
 
-	mlxsw_sp_vport->learning = 0;
-	mlxsw_sp_vport->learning_sync = 0;
-	mlxsw_sp_vport->uc_flood = 0;
-	mlxsw_sp_vport->bridged = 0;
+	netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", f->fid);
 
 	return 0;
 
-err_port_stp_state_set:
+err_vport_fid_map:
+	mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, false);
 err_vport_flood_set:
-err_port_vid_learning_set:
-err_port_vid_to_fid_validate:
-err_port_vid_to_fid_invalidate:
-	/* Rollback vFID only if new. */
-	if (!new_vfid->nr_vports)
-		mlxsw_sp_vfid_destroy(mlxsw_sp, new_vfid);
+	if (!f->ref_count)
+		mlxsw_sp_vfid_destroy(mlxsw_sp_vport->mlxsw_sp, f);
 	return err;
 }
 
+static void mlxsw_sp_vport_vfid_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+
+	netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid);
+
+	mlxsw_sp_vport_fid_map(mlxsw_sp_vport, f->fid, false);
+
+	mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, false);
+
+	mlxsw_sp_port_fdb_flush(mlxsw_sp_vport, f->fid);
+
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL);
+	if (--f->ref_count == 0)
+		mlxsw_sp_vfid_destroy(mlxsw_sp_vport->mlxsw_sp, f);
+}
+
 static int mlxsw_sp_vport_bridge_join(struct mlxsw_sp_port *mlxsw_sp_vport,
 				      struct net_device *br_dev)
 {
-	struct mlxsw_sp_vfid *old_vfid = mlxsw_sp_vport->vport.vfid;
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
 	u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
 	struct net_device *dev = mlxsw_sp_vport->dev;
-	struct mlxsw_sp_vfid *vfid;
 	int err;
 
-	vfid = mlxsw_sp_br_vfid_find(mlxsw_sp, br_dev);
-	if (!vfid) {
-		vfid = mlxsw_sp_br_vfid_create(mlxsw_sp, br_dev);
-		if (IS_ERR(vfid)) {
-			netdev_err(dev, "Failed to create bridge vFID\n");
-			return PTR_ERR(vfid);
-		}
-	}
+	if (f && !WARN_ON(!f->leave))
+		f->leave(mlxsw_sp_vport);
 
-	err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, true, false);
+	err = mlxsw_sp_vport_vfid_join(mlxsw_sp_vport, br_dev);
 	if (err) {
-		netdev_err(dev, "Failed to setup flooding for vFID=%d\n",
-			   vfid->vfid);
-		goto err_port_flood_set;
+		netdev_err(dev, "Failed to join vFID\n");
+		return err;
 	}
 
 	err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true);
@@ -3349,38 +3752,6 @@ static int mlxsw_sp_vport_bridge_join(struct mlxsw_sp_port *mlxsw_sp_vport,
 		goto err_port_vid_learning_set;
 	}
 
-	/* We need to invalidate existing {Port, VID} to vFID mapping and
-	 * create a new one for the bridge's vFID.
-	 */
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   false,
-					   mlxsw_sp_vfid_to_fid(old_vfid->vfid),
-					   vid);
-	if (err) {
-		netdev_err(dev, "Failed to invalidate {Port, VID} to vFID=%d mapping\n",
-			   old_vfid->vfid);
-		goto err_port_vid_to_fid_invalidate;
-	}
-
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   true,
-					   mlxsw_sp_vfid_to_fid(vfid->vfid),
-					   vid);
-	if (err) {
-		netdev_err(dev, "Failed to map {Port, VID} to vFID=%d\n",
-			   vfid->vfid);
-		goto err_port_vid_to_fid_validate;
-	}
-
-	/* Switch between the vFIDs and destroy the old one if needed. */
-	vfid->nr_vports++;
-	mlxsw_sp_vport->vport.vfid = vfid;
-	old_vfid->nr_vports--;
-	if (!old_vfid->nr_vports)
-		mlxsw_sp_vfid_destroy(mlxsw_sp, old_vfid);
-
 	mlxsw_sp_vport->learning = 1;
 	mlxsw_sp_vport->learning_sync = 1;
 	mlxsw_sp_vport->uc_flood = 1;
@@ -3388,20 +3759,25 @@ static int mlxsw_sp_vport_bridge_join(struct mlxsw_sp_port *mlxsw_sp_vport,
 
 	return 0;
 
-err_port_vid_to_fid_validate:
-	mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-				     MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, false,
-				     mlxsw_sp_vfid_to_fid(old_vfid->vfid), vid);
-err_port_vid_to_fid_invalidate:
-	mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false);
 err_port_vid_learning_set:
-	mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false, false);
-err_port_flood_set:
-	if (!vfid->nr_vports)
-		mlxsw_sp_br_vfid_destroy(mlxsw_sp, vfid);
+	mlxsw_sp_vport_vfid_leave(mlxsw_sp_vport);
 	return err;
 }
 
+static void mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
+
+	mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false);
+
+	mlxsw_sp_vport_vfid_leave(mlxsw_sp_vport);
+
+	mlxsw_sp_vport->learning = 0;
+	mlxsw_sp_vport->learning_sync = 0;
+	mlxsw_sp_vport->uc_flood = 0;
+	mlxsw_sp_vport->bridged = 0;
+}
+
 static bool
 mlxsw_sp_port_master_bridge_check(const struct mlxsw_sp_port *mlxsw_sp_port,
 				  const struct net_device *br_dev)
@@ -3410,7 +3786,9 @@ mlxsw_sp_port_master_bridge_check(const struct mlxsw_sp_port *mlxsw_sp_port,
 
 	list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list,
 			    vport.list) {
-		if (mlxsw_sp_vport_br_get(mlxsw_sp_vport) == br_dev)
+		struct net_device *dev = mlxsw_sp_vport_dev_get(mlxsw_sp_vport);
+
+		if (dev && dev == br_dev)
 			return false;
 	}
 
@@ -3425,56 +3803,39 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev,
 	struct netdev_notifier_changeupper_info *info = ptr;
 	struct mlxsw_sp_port *mlxsw_sp_vport;
 	struct net_device *upper_dev;
-	int err;
+	int err = 0;
 
 	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
 
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (!info->master || !info->linking)
-			break;
 		if (!netif_is_bridge_master(upper_dev))
-			return NOTIFY_BAD;
+			return -EINVAL;
+		if (!info->linking)
+			break;
 		/* We can't have multiple VLAN interfaces configured on
 		 * the same port and being members in the same bridge.
 		 */
 		if (!mlxsw_sp_port_master_bridge_check(mlxsw_sp_port,
 						       upper_dev))
-			return NOTIFY_BAD;
+			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (!info->master)
-			break;
 		if (info->linking) {
-			if (!mlxsw_sp_vport) {
-				WARN_ON(!mlxsw_sp_vport);
-				return NOTIFY_BAD;
-			}
+			if (WARN_ON(!mlxsw_sp_vport))
+				return -EINVAL;
 			err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport,
 							 upper_dev);
-			if (err) {
-				netdev_err(dev, "Failed to join bridge\n");
-				return NOTIFY_BAD;
-			}
 		} else {
-			/* We ignore bridge's unlinking notifications if vPort
-			 * is gone, since we already left the bridge when the
-			 * VLAN device was unlinked from the real device.
-			 */
 			if (!mlxsw_sp_vport)
-				return NOTIFY_DONE;
-			err = mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport,
-							  upper_dev, true);
-			if (err) {
-				netdev_err(dev, "Failed to leave bridge\n");
-				return NOTIFY_BAD;
-			}
+				return 0;
+			mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport);
 		}
 	}
 
-	return NOTIFY_DONE;
+	return err;
 }
 
 static int mlxsw_sp_netdevice_lag_vport_event(struct net_device *lag_dev,
@@ -3489,12 +3850,12 @@ static int mlxsw_sp_netdevice_lag_vport_event(struct net_device *lag_dev,
 		if (mlxsw_sp_port_dev_check(dev)) {
 			ret = mlxsw_sp_netdevice_vport_event(dev, event, ptr,
 							     vid);
-			if (ret == NOTIFY_BAD)
+			if (ret)
 				return ret;
 		}
 	}
 
-	return NOTIFY_DONE;
+	return 0;
 }
 
 static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
@@ -3510,35 +3871,44 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 		return mlxsw_sp_netdevice_lag_vport_event(real_dev, event, ptr,
 							  vid);
 
-	return NOTIFY_DONE;
+	return 0;
 }
 
 static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
 				    unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	int err = 0;
 
-	if (mlxsw_sp_port_dev_check(dev))
-		return mlxsw_sp_netdevice_port_event(dev, event, ptr);
-
-	if (netif_is_lag_master(dev))
-		return mlxsw_sp_netdevice_lag_event(dev, event, ptr);
+	if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU)
+		err = mlxsw_sp_netdevice_router_port_event(dev);
+	else if (mlxsw_sp_port_dev_check(dev))
+		err = mlxsw_sp_netdevice_port_event(dev, event, ptr);
+	else if (netif_is_lag_master(dev))
+		err = mlxsw_sp_netdevice_lag_event(dev, event, ptr);
+	else if (netif_is_bridge_master(dev))
+		err = mlxsw_sp_netdevice_bridge_event(dev, event, ptr);
+	else if (is_vlan_dev(dev))
+		err = mlxsw_sp_netdevice_vlan_event(dev, event, ptr);
 
-	if (is_vlan_dev(dev))
-		return mlxsw_sp_netdevice_vlan_event(dev, event, ptr);
-
-	return NOTIFY_DONE;
+	return notifier_from_errno(err);
 }
 
 static struct notifier_block mlxsw_sp_netdevice_nb __read_mostly = {
 	.notifier_call = mlxsw_sp_netdevice_event,
 };
 
+static struct notifier_block mlxsw_sp_inetaddr_nb __read_mostly = {
+	.notifier_call = mlxsw_sp_inetaddr_event,
+	.priority = 10,	/* Must be called before FIB notifier block */
+};
+
 static int __init mlxsw_sp_module_init(void)
 {
 	int err;
 
 	register_netdevice_notifier(&mlxsw_sp_netdevice_nb);
+	register_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
 	err = mlxsw_core_driver_register(&mlxsw_sp_driver);
 	if (err)
 		goto err_core_driver_register;
@@ -3552,6 +3922,7 @@ err_core_driver_register:
 static void __exit mlxsw_sp_module_exit(void)
 {
 	mlxsw_core_driver_unregister(&mlxsw_sp_driver);
+	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
 	unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index e2c022d3e2f3..ef4ac8987a2a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -39,19 +39,22 @@
 
 #include <linux/types.h>
 #include <linux/netdevice.h>
+#include <linux/rhashtable.h>
 #include <linux/bitops.h>
 #include <linux/if_vlan.h>
 #include <linux/list.h>
 #include <linux/dcbnl.h>
+#include <linux/in6.h>
 #include <net/switchdev.h>
 
 #include "port.h"
 #include "core.h"
 
 #define MLXSW_SP_VFID_BASE VLAN_N_VID
-#define MLXSW_SP_VFID_PORT_MAX 512	/* Non-bridged VLAN interfaces */
-#define MLXSW_SP_VFID_BR_MAX 6144	/* Bridged VLAN interfaces */
-#define MLXSW_SP_VFID_MAX (MLXSW_SP_VFID_PORT_MAX + MLXSW_SP_VFID_BR_MAX)
+#define MLXSW_SP_VFID_MAX 6656	/* Bridged VLAN interfaces */
+
+#define MLXSW_SP_RFID_BASE 15360
+#define MLXSW_SP_RIF_MAX 800
 
 #define MLXSW_SP_LAG_MAX 64
 #define MLXSW_SP_PORT_PER_LAG_MAX 16
@@ -60,6 +63,12 @@
 
 #define MLXSW_SP_PORTS_PER_CLUSTER_MAX 4
 
+#define MLXSW_SP_LPM_TREE_MIN 2 /* trees 0 and 1 are reserved */
+#define MLXSW_SP_LPM_TREE_MAX 22
+#define MLXSW_SP_LPM_TREE_COUNT (MLXSW_SP_LPM_TREE_MAX - MLXSW_SP_LPM_TREE_MIN)
+
+#define MLXSW_SP_VIRTUAL_ROUTER_MAX 256
+
 #define MLXSW_SP_PORT_BASE_SPEED 25000	/* Mb/s */
 
 #define MLXSW_SP_BYTES_PER_CELL 96
@@ -67,6 +76,10 @@
 #define MLXSW_SP_BYTES_TO_CELLS(b) DIV_ROUND_UP(b, MLXSW_SP_BYTES_PER_CELL)
 #define MLXSW_SP_CELLS_TO_BYTES(c) (c * MLXSW_SP_BYTES_PER_CELL)
 
+#define MLXSW_SP_KVD_LINEAR_SIZE 65536 /* entries */
+#define MLXSW_SP_KVD_HASH_SINGLE_SIZE 163840 /* entries */
+#define MLXSW_SP_KVD_HASH_DOUBLE_SIZE 32768 /* entries */
+
 /* Maximum delay buffer needed in case of PAUSE frames, in cells.
  * Assumes 100m cable and maximum MTU.
  */
@@ -87,12 +100,22 @@ struct mlxsw_sp_upper {
 	unsigned int ref_count;
 };
 
-struct mlxsw_sp_vfid {
+struct mlxsw_sp_fid {
+	void (*leave)(struct mlxsw_sp_port *mlxsw_sp_vport);
 	struct list_head list;
-	u16 nr_vports;
-	u16 vfid;	/* Starting at 0 */
-	struct net_device *br_dev;
-	u16 vid;
+	unsigned int ref_count;
+	struct net_device *dev;
+	struct mlxsw_sp_rif *r;
+	u16 fid;
+};
+
+struct mlxsw_sp_rif {
+	struct net_device *dev;
+	unsigned int ref_count;
+	struct mlxsw_sp_fid *f;
+	unsigned char addr[ETH_ALEN];
+	int mtu;
+	u16 rif;
 };
 
 struct mlxsw_sp_mid {
@@ -115,7 +138,17 @@ static inline u16 mlxsw_sp_fid_to_vfid(u16 fid)
 
 static inline bool mlxsw_sp_fid_is_vfid(u16 fid)
 {
-	return fid >= MLXSW_SP_VFID_BASE;
+	return fid >= MLXSW_SP_VFID_BASE && fid < MLXSW_SP_RFID_BASE;
+}
+
+static inline bool mlxsw_sp_fid_is_rfid(u16 fid)
+{
+	return fid >= MLXSW_SP_RFID_BASE;
+}
+
+static inline u16 mlxsw_sp_rif_sp_to_fid(u16 rif)
+{
+	return MLXSW_SP_RFID_BASE + rif;
 }
 
 struct mlxsw_sp_sb_pr {
@@ -152,20 +185,60 @@ struct mlxsw_sp_sb {
 	} ports[MLXSW_PORT_MAX_PORTS];
 };
 
-struct mlxsw_sp {
+#define MLXSW_SP_PREFIX_COUNT (sizeof(struct in6_addr) * BITS_PER_BYTE)
+
+struct mlxsw_sp_prefix_usage {
+	DECLARE_BITMAP(b, MLXSW_SP_PREFIX_COUNT);
+};
+
+enum mlxsw_sp_l3proto {
+	MLXSW_SP_L3_PROTO_IPV4,
+	MLXSW_SP_L3_PROTO_IPV6,
+};
+
+struct mlxsw_sp_lpm_tree {
+	u8 id; /* tree ID */
+	unsigned int ref_count;
+	enum mlxsw_sp_l3proto proto;
+	struct mlxsw_sp_prefix_usage prefix_usage;
+};
+
+struct mlxsw_sp_fib;
+
+struct mlxsw_sp_vr {
+	u16 id; /* virtual router ID */
+	bool used;
+	enum mlxsw_sp_l3proto proto;
+	u32 tb_id; /* kernel fib table id */
+	struct mlxsw_sp_lpm_tree *lpm_tree;
+	struct mlxsw_sp_fib *fib;
+};
+
+struct mlxsw_sp_router {
+	struct mlxsw_sp_lpm_tree lpm_trees[MLXSW_SP_LPM_TREE_COUNT];
+	struct mlxsw_sp_vr vrs[MLXSW_SP_VIRTUAL_ROUTER_MAX];
+	struct rhashtable neigh_ht;
 	struct {
-		struct list_head list;
-		unsigned long mapped[BITS_TO_LONGS(MLXSW_SP_VFID_PORT_MAX)];
-	} port_vfids;
+		struct delayed_work dw;
+		unsigned long interval;	/* ms */
+	} neighs_update;
+	struct delayed_work nexthop_probe_dw;
+#define MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL 5000 /* ms */
+	struct list_head nexthop_group_list;
+	struct list_head nexthop_neighs_list;
+};
+
+struct mlxsw_sp {
 	struct {
 		struct list_head list;
-		unsigned long mapped[BITS_TO_LONGS(MLXSW_SP_VFID_BR_MAX)];
-	} br_vfids;
+		DECLARE_BITMAP(mapped, MLXSW_SP_VFID_MAX);
+	} vfids;
 	struct {
 		struct list_head list;
-		unsigned long mapped[BITS_TO_LONGS(MLXSW_SP_MID_MAX)];
+		DECLARE_BITMAP(mapped, MLXSW_SP_MID_MAX);
 	} br_mids;
-	unsigned long active_fids[BITS_TO_LONGS(VLAN_N_VID)];
+	struct list_head fids;	/* VLAN-aware bridge FIDs */
+	struct mlxsw_sp_rif *rifs[MLXSW_SP_RIF_MAX];
 	struct mlxsw_sp_port **ports;
 	struct mlxsw_core *core;
 	const struct mlxsw_bus_info *bus_info;
@@ -183,6 +256,10 @@ struct mlxsw_sp {
 	struct mlxsw_sp_upper lags[MLXSW_SP_LAG_MAX];
 	u8 port_to_module[MLXSW_PORT_MAX_PORTS];
 	struct mlxsw_sp_sb sb;
+	struct mlxsw_sp_router router;
+	struct {
+		DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE);
+	} kvdl;
 };
 
 static inline struct mlxsw_sp_upper *
@@ -217,7 +294,7 @@ struct mlxsw_sp_port {
 	u16 lag_id;
 	struct {
 		struct list_head list;
-		struct mlxsw_sp_vfid *vfid;
+		struct mlxsw_sp_fid *f;
 		u16 vid;
 	} vport;
 	struct {
@@ -229,6 +306,11 @@ struct mlxsw_sp_port {
 		struct ieee_maxrate *maxrate;
 		struct ieee_pfc *pfc;
 	} dcb;
+	struct {
+		u8 module;
+		u8 width;
+		u8 lane;
+	} mapping;
 	/* 802.1Q bridge VLANs */
 	unsigned long *active_vlans;
 	unsigned long *untagged_vlans;
@@ -236,6 +318,9 @@ struct mlxsw_sp_port {
 	struct list_head vports_list;
 };
 
+struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev);
+void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port);
+
 static inline bool
 mlxsw_sp_port_is_pause_en(const struct mlxsw_sp_port *mlxsw_sp_port)
 {
@@ -254,28 +339,38 @@ mlxsw_sp_port_lagged_get(struct mlxsw_sp *mlxsw_sp, u16 lag_id, u8 port_index)
 	return mlxsw_sp_port && mlxsw_sp_port->lagged ? mlxsw_sp_port : NULL;
 }
 
+static inline u16
+mlxsw_sp_vport_vid_get(const struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	return mlxsw_sp_vport->vport.vid;
+}
+
 static inline bool
 mlxsw_sp_port_is_vport(const struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	return mlxsw_sp_port->vport.vfid;
+	u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_port);
+
+	return vid != 0;
 }
 
-static inline struct net_device *
-mlxsw_sp_vport_br_get(const struct mlxsw_sp_port *mlxsw_sp_vport)
+static inline void mlxsw_sp_vport_fid_set(struct mlxsw_sp_port *mlxsw_sp_vport,
+					  struct mlxsw_sp_fid *f)
 {
-	return mlxsw_sp_vport->vport.vfid->br_dev;
+	mlxsw_sp_vport->vport.f = f;
 }
 
-static inline u16
-mlxsw_sp_vport_vid_get(const struct mlxsw_sp_port *mlxsw_sp_vport)
+static inline struct mlxsw_sp_fid *
+mlxsw_sp_vport_fid_get(const struct mlxsw_sp_port *mlxsw_sp_vport)
 {
-	return mlxsw_sp_vport->vport.vid;
+	return mlxsw_sp_vport->vport.f;
 }
 
-static inline u16
-mlxsw_sp_vport_vfid_get(const struct mlxsw_sp_port *mlxsw_sp_vport)
+static inline struct net_device *
+mlxsw_sp_vport_dev_get(const struct mlxsw_sp_port *mlxsw_sp_vport)
 {
-	return mlxsw_sp_vport->vport.vfid->vfid;
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+
+	return f ? f->dev : NULL;
 }
 
 static inline struct mlxsw_sp_port *
@@ -293,20 +388,60 @@ mlxsw_sp_port_vport_find(const struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 }
 
 static inline struct mlxsw_sp_port *
-mlxsw_sp_port_vport_find_by_vfid(const struct mlxsw_sp_port *mlxsw_sp_port,
-				 u16 vfid)
+mlxsw_sp_port_vport_find_by_fid(const struct mlxsw_sp_port *mlxsw_sp_port,
+				u16 fid)
 {
 	struct mlxsw_sp_port *mlxsw_sp_vport;
 
 	list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list,
 			    vport.list) {
-		if (mlxsw_sp_vport_vfid_get(mlxsw_sp_vport) == vfid)
+		struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+
+		if (f && f->fid == fid)
 			return mlxsw_sp_vport;
 	}
 
 	return NULL;
 }
 
+static inline struct mlxsw_sp_fid *mlxsw_sp_fid_find(struct mlxsw_sp *mlxsw_sp,
+						     u16 fid)
+{
+	struct mlxsw_sp_fid *f;
+
+	list_for_each_entry(f, &mlxsw_sp->fids, list)
+		if (f->fid == fid)
+			return f;
+
+	return NULL;
+}
+
+static inline struct mlxsw_sp_fid *
+mlxsw_sp_vfid_find(const struct mlxsw_sp *mlxsw_sp,
+		   const struct net_device *br_dev)
+{
+	struct mlxsw_sp_fid *f;
+
+	list_for_each_entry(f, &mlxsw_sp->vfids.list, list)
+		if (f->dev == br_dev)
+			return f;
+
+	return NULL;
+}
+
+static inline struct mlxsw_sp_rif *
+mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
+			 const struct net_device *dev)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP_RIF_MAX; i++)
+		if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev)
+			return mlxsw_sp->rifs[i];
+
+	return NULL;
+}
+
 enum mlxsw_sp_flood_table {
 	MLXSW_SP_FLOOD_TABLE_UC,
 	MLXSW_SP_FLOOD_TABLE_BM,
@@ -359,12 +494,17 @@ int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin,
 			   u16 vid_end, bool is_member, bool untagged);
 int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto,
 			  u16 vid);
-int mlxsw_sp_port_kill_vid(struct net_device *dev,
-			   __be16 __always_unused proto, u16 vid);
-int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid,
-			     bool set, bool only_uc);
+int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid,
+			     bool set);
 void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port);
 int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
+int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid);
+int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
+			bool adding);
+struct mlxsw_sp_fid *mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid);
+void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f);
+void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_rif *r);
 int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
 			  enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
 			  bool dwrr, u8 dwrr_weight);
@@ -394,4 +534,19 @@ static inline void mlxsw_sp_port_dcb_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 
 #endif
 
+int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_router_fib4_add(struct mlxsw_sp_port *mlxsw_sp_port,
+			     const struct switchdev_obj_ipv4_fib *fib4,
+			     struct switchdev_trans *trans);
+int mlxsw_sp_router_fib4_del(struct mlxsw_sp_port *mlxsw_sp_port,
+			     const struct switchdev_obj_ipv4_fib *fib4);
+int mlxsw_sp_router_neigh_construct(struct net_device *dev,
+				    struct neighbour *n);
+void mlxsw_sp_router_neigh_destroy(struct net_device *dev,
+				   struct neighbour *n);
+
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count);
+void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
new file mode 100644
index 000000000000..ac321e8e5c1a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -0,0 +1,91 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <[email protected]>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+
+#include "spectrum.h"
+
+#define MLXSW_SP_KVDL_SINGLE_BASE 0
+#define MLXSW_SP_KVDL_SINGLE_SIZE 16384
+#define MLXSW_SP_KVDL_CHUNKS_BASE \
+	(MLXSW_SP_KVDL_SINGLE_BASE + MLXSW_SP_KVDL_SINGLE_SIZE)
+#define MLXSW_SP_KVDL_CHUNKS_SIZE \
+	(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_CHUNKS_BASE)
+#define MLXSW_SP_CHUNK_MAX 32
+
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count)
+{
+	int entry_index;
+	int size;
+	int type_base;
+	int type_size;
+	int type_entries;
+
+	if (entry_count == 0 || entry_count > MLXSW_SP_CHUNK_MAX) {
+		return -EINVAL;
+	} else if (entry_count == 1) {
+		type_base = MLXSW_SP_KVDL_SINGLE_BASE;
+		type_size = MLXSW_SP_KVDL_SINGLE_SIZE;
+		type_entries = 1;
+	} else {
+		type_base = MLXSW_SP_KVDL_CHUNKS_BASE;
+		type_size = MLXSW_SP_KVDL_CHUNKS_SIZE;
+		type_entries = MLXSW_SP_CHUNK_MAX;
+	}
+
+	entry_index = type_base;
+	size = type_base + type_size;
+	for_each_clear_bit_from(entry_index, mlxsw_sp->kvdl.usage, size) {
+		int i;
+
+		for (i = 0; i < type_entries; i++)
+			set_bit(entry_index + i, mlxsw_sp->kvdl.usage);
+		return entry_index;
+	}
+	return -ENOBUFS;
+}
+
+void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index)
+{
+	int type_entries;
+	int i;
+
+	if (entry_index < MLXSW_SP_KVDL_CHUNKS_BASE)
+		type_entries = 1;
+	else
+		type_entries = MLXSW_SP_CHUNK_MAX;
+	for (i = 0; i < type_entries; i++)
+		clear_bit(entry_index + i, mlxsw_sp->kvdl.usage);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
new file mode 100644
index 000000000000..e084ea5448ac
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -0,0 +1,1814 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <[email protected]>
+ * Copyright (c) 2016 Ido Schimmel <[email protected]>
+ * Copyright (c) 2016 Yotam Gigi <[email protected]>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/rhashtable.h>
+#include <linux/bitops.h>
+#include <linux/in6.h>
+#include <linux/notifier.h>
+#include <net/netevent.h>
+#include <net/neighbour.h>
+#include <net/arp.h>
+
+#include "spectrum.h"
+#include "core.h"
+#include "reg.h"
+
+#define mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) \
+	for_each_set_bit(prefix, (prefix_usage)->b, MLXSW_SP_PREFIX_COUNT)
+
+static bool
+mlxsw_sp_prefix_usage_subset(struct mlxsw_sp_prefix_usage *prefix_usage1,
+			     struct mlxsw_sp_prefix_usage *prefix_usage2)
+{
+	unsigned char prefix;
+
+	mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage1) {
+		if (!test_bit(prefix, prefix_usage2->b))
+			return false;
+	}
+	return true;
+}
+
+static bool
+mlxsw_sp_prefix_usage_eq(struct mlxsw_sp_prefix_usage *prefix_usage1,
+			 struct mlxsw_sp_prefix_usage *prefix_usage2)
+{
+	return !memcmp(prefix_usage1, prefix_usage2, sizeof(*prefix_usage1));
+}
+
+static bool
+mlxsw_sp_prefix_usage_none(struct mlxsw_sp_prefix_usage *prefix_usage)
+{
+	struct mlxsw_sp_prefix_usage prefix_usage_none = {{ 0 } };
+
+	return mlxsw_sp_prefix_usage_eq(prefix_usage, &prefix_usage_none);
+}
+
+static void
+mlxsw_sp_prefix_usage_cpy(struct mlxsw_sp_prefix_usage *prefix_usage1,
+			  struct mlxsw_sp_prefix_usage *prefix_usage2)
+{
+	memcpy(prefix_usage1, prefix_usage2, sizeof(*prefix_usage1));
+}
+
+static void
+mlxsw_sp_prefix_usage_zero(struct mlxsw_sp_prefix_usage *prefix_usage)
+{
+	memset(prefix_usage, 0, sizeof(*prefix_usage));
+}
+
+static void
+mlxsw_sp_prefix_usage_set(struct mlxsw_sp_prefix_usage *prefix_usage,
+			  unsigned char prefix_len)
+{
+	set_bit(prefix_len, prefix_usage->b);
+}
+
+static void
+mlxsw_sp_prefix_usage_clear(struct mlxsw_sp_prefix_usage *prefix_usage,
+			    unsigned char prefix_len)
+{
+	clear_bit(prefix_len, prefix_usage->b);
+}
+
+struct mlxsw_sp_fib_key {
+	unsigned char addr[sizeof(struct in6_addr)];
+	unsigned char prefix_len;
+};
+
+enum mlxsw_sp_fib_entry_type {
+	MLXSW_SP_FIB_ENTRY_TYPE_REMOTE,
+	MLXSW_SP_FIB_ENTRY_TYPE_LOCAL,
+	MLXSW_SP_FIB_ENTRY_TYPE_TRAP,
+};
+
+struct mlxsw_sp_nexthop_group;
+
+struct mlxsw_sp_fib_entry {
+	struct rhash_head ht_node;
+	struct mlxsw_sp_fib_key key;
+	enum mlxsw_sp_fib_entry_type type;
+	u8 added:1;
+	u16 rif; /* used for action local */
+	struct mlxsw_sp_vr *vr;
+	struct list_head nexthop_group_node;
+	struct mlxsw_sp_nexthop_group *nh_group;
+};
+
+struct mlxsw_sp_fib {
+	struct rhashtable ht;
+	unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT];
+	struct mlxsw_sp_prefix_usage prefix_usage;
+};
+
+static const struct rhashtable_params mlxsw_sp_fib_ht_params = {
+	.key_offset = offsetof(struct mlxsw_sp_fib_entry, key),
+	.head_offset = offsetof(struct mlxsw_sp_fib_entry, ht_node),
+	.key_len = sizeof(struct mlxsw_sp_fib_key),
+	.automatic_shrinking = true,
+};
+
+static int mlxsw_sp_fib_entry_insert(struct mlxsw_sp_fib *fib,
+				     struct mlxsw_sp_fib_entry *fib_entry)
+{
+	unsigned char prefix_len = fib_entry->key.prefix_len;
+	int err;
+
+	err = rhashtable_insert_fast(&fib->ht, &fib_entry->ht_node,
+				     mlxsw_sp_fib_ht_params);
+	if (err)
+		return err;
+	if (fib->prefix_ref_count[prefix_len]++ == 0)
+		mlxsw_sp_prefix_usage_set(&fib->prefix_usage, prefix_len);
+	return 0;
+}
+
+static void mlxsw_sp_fib_entry_remove(struct mlxsw_sp_fib *fib,
+				      struct mlxsw_sp_fib_entry *fib_entry)
+{
+	unsigned char prefix_len = fib_entry->key.prefix_len;
+
+	if (--fib->prefix_ref_count[prefix_len] == 0)
+		mlxsw_sp_prefix_usage_clear(&fib->prefix_usage, prefix_len);
+	rhashtable_remove_fast(&fib->ht, &fib_entry->ht_node,
+			       mlxsw_sp_fib_ht_params);
+}
+
+static struct mlxsw_sp_fib_entry *
+mlxsw_sp_fib_entry_create(struct mlxsw_sp_fib *fib, const void *addr,
+			  size_t addr_len, unsigned char prefix_len)
+{
+	struct mlxsw_sp_fib_entry *fib_entry;
+
+	fib_entry = kzalloc(sizeof(*fib_entry), GFP_KERNEL);
+	if (!fib_entry)
+		return NULL;
+	memcpy(fib_entry->key.addr, addr, addr_len);
+	fib_entry->key.prefix_len = prefix_len;
+	return fib_entry;
+}
+
+static void mlxsw_sp_fib_entry_destroy(struct mlxsw_sp_fib_entry *fib_entry)
+{
+	kfree(fib_entry);
+}
+
+static struct mlxsw_sp_fib_entry *
+mlxsw_sp_fib_entry_lookup(struct mlxsw_sp_fib *fib, const void *addr,
+			  size_t addr_len, unsigned char prefix_len)
+{
+	struct mlxsw_sp_fib_key key = {{ 0 } };
+
+	memcpy(key.addr, addr, addr_len);
+	key.prefix_len = prefix_len;
+	return rhashtable_lookup_fast(&fib->ht, &key, mlxsw_sp_fib_ht_params);
+}
+
+static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void)
+{
+	struct mlxsw_sp_fib *fib;
+	int err;
+
+	fib = kzalloc(sizeof(*fib), GFP_KERNEL);
+	if (!fib)
+		return ERR_PTR(-ENOMEM);
+	err = rhashtable_init(&fib->ht, &mlxsw_sp_fib_ht_params);
+	if (err)
+		goto err_rhashtable_init;
+	return fib;
+
+err_rhashtable_init:
+	kfree(fib);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_fib_destroy(struct mlxsw_sp_fib *fib)
+{
+	rhashtable_destroy(&fib->ht);
+	kfree(fib);
+}
+
+static struct mlxsw_sp_lpm_tree *
+mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp, bool one_reserved)
+{
+	static struct mlxsw_sp_lpm_tree *lpm_tree;
+	int i;
+
+	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
+		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
+		if (lpm_tree->ref_count == 0) {
+			if (one_reserved)
+				one_reserved = false;
+			else
+				return lpm_tree;
+		}
+	}
+	return NULL;
+}
+
+static int mlxsw_sp_lpm_tree_alloc(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_lpm_tree *lpm_tree)
+{
+	char ralta_pl[MLXSW_REG_RALTA_LEN];
+
+	mlxsw_reg_ralta_pack(ralta_pl, true, lpm_tree->proto, lpm_tree->id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl);
+}
+
+static int mlxsw_sp_lpm_tree_free(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_lpm_tree *lpm_tree)
+{
+	char ralta_pl[MLXSW_REG_RALTA_LEN];
+
+	mlxsw_reg_ralta_pack(ralta_pl, false, lpm_tree->proto, lpm_tree->id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl);
+}
+
+static int
+mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_prefix_usage *prefix_usage,
+				  struct mlxsw_sp_lpm_tree *lpm_tree)
+{
+	char ralst_pl[MLXSW_REG_RALST_LEN];
+	u8 root_bin = 0;
+	u8 prefix;
+	u8 last_prefix = MLXSW_REG_RALST_BIN_NO_CHILD;
+
+	mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage)
+		root_bin = prefix;
+
+	mlxsw_reg_ralst_pack(ralst_pl, root_bin, lpm_tree->id);
+	mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) {
+		if (prefix == 0)
+			continue;
+		mlxsw_reg_ralst_bin_pack(ralst_pl, prefix, last_prefix,
+					 MLXSW_REG_RALST_BIN_NO_CHILD);
+		last_prefix = prefix;
+	}
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl);
+}
+
+static struct mlxsw_sp_lpm_tree *
+mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp,
+			 struct mlxsw_sp_prefix_usage *prefix_usage,
+			 enum mlxsw_sp_l3proto proto, bool one_reserved)
+{
+	struct mlxsw_sp_lpm_tree *lpm_tree;
+	int err;
+
+	lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp, one_reserved);
+	if (!lpm_tree)
+		return ERR_PTR(-EBUSY);
+	lpm_tree->proto = proto;
+	err = mlxsw_sp_lpm_tree_alloc(mlxsw_sp, lpm_tree);
+	if (err)
+		return ERR_PTR(err);
+
+	err = mlxsw_sp_lpm_tree_left_struct_set(mlxsw_sp, prefix_usage,
+						lpm_tree);
+	if (err)
+		goto err_left_struct_set;
+	return lpm_tree;
+
+err_left_struct_set:
+	mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree);
+	return ERR_PTR(err);
+}
+
+static int mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_lpm_tree *lpm_tree)
+{
+	return mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree);
+}
+
+static struct mlxsw_sp_lpm_tree *
+mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp,
+		      struct mlxsw_sp_prefix_usage *prefix_usage,
+		      enum mlxsw_sp_l3proto proto, bool one_reserved)
+{
+	struct mlxsw_sp_lpm_tree *lpm_tree;
+	int i;
+
+	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
+		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
+		if (lpm_tree->proto == proto &&
+		    mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage,
+					     prefix_usage))
+			goto inc_ref_count;
+	}
+	lpm_tree = mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage,
+					    proto, one_reserved);
+	if (IS_ERR(lpm_tree))
+		return lpm_tree;
+
+inc_ref_count:
+	lpm_tree->ref_count++;
+	return lpm_tree;
+}
+
+static int mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_lpm_tree *lpm_tree)
+{
+	if (--lpm_tree->ref_count == 0)
+		return mlxsw_sp_lpm_tree_destroy(mlxsw_sp, lpm_tree);
+	return 0;
+}
+
+static void mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_lpm_tree *lpm_tree;
+	int i;
+
+	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
+		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
+		lpm_tree->id = i + MLXSW_SP_LPM_TREE_MIN;
+	}
+}
+
+static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_vr *vr;
+	int i;
+
+	for (i = 0; i < MLXSW_SP_VIRTUAL_ROUTER_MAX; i++) {
+		vr = &mlxsw_sp->router.vrs[i];
+		if (!vr->used)
+			return vr;
+	}
+	return NULL;
+}
+
+static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_vr *vr)
+{
+	char raltb_pl[MLXSW_REG_RALTB_LEN];
+
+	mlxsw_reg_raltb_pack(raltb_pl, vr->id, vr->proto, vr->lpm_tree->id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
+}
+
+static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_vr *vr)
+{
+	char raltb_pl[MLXSW_REG_RALTB_LEN];
+
+	/* Bind to tree 0 which is default */
+	mlxsw_reg_raltb_pack(raltb_pl, vr->id, vr->proto, 0);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
+}
+
+static u32 mlxsw_sp_fix_tb_id(u32 tb_id)
+{
+	/* For our purpose, squash main and local table into one */
+	if (tb_id == RT_TABLE_LOCAL)
+		tb_id = RT_TABLE_MAIN;
+	return tb_id;
+}
+
+static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp,
+					    u32 tb_id,
+					    enum mlxsw_sp_l3proto proto)
+{
+	struct mlxsw_sp_vr *vr;
+	int i;
+
+	tb_id = mlxsw_sp_fix_tb_id(tb_id);
+	for (i = 0; i < MLXSW_SP_VIRTUAL_ROUTER_MAX; i++) {
+		vr = &mlxsw_sp->router.vrs[i];
+		if (vr->used && vr->proto == proto && vr->tb_id == tb_id)
+			return vr;
+	}
+	return NULL;
+}
+
+static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
+					      unsigned char prefix_len,
+					      u32 tb_id,
+					      enum mlxsw_sp_l3proto proto)
+{
+	struct mlxsw_sp_prefix_usage req_prefix_usage;
+	struct mlxsw_sp_lpm_tree *lpm_tree;
+	struct mlxsw_sp_vr *vr;
+	int err;
+
+	vr = mlxsw_sp_vr_find_unused(mlxsw_sp);
+	if (!vr)
+		return ERR_PTR(-EBUSY);
+	vr->fib = mlxsw_sp_fib_create();
+	if (IS_ERR(vr->fib))
+		return ERR_CAST(vr->fib);
+
+	vr->proto = proto;
+	vr->tb_id = tb_id;
+	mlxsw_sp_prefix_usage_zero(&req_prefix_usage);
+	mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len);
+	lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage,
+					 proto, true);
+	if (IS_ERR(lpm_tree)) {
+		err = PTR_ERR(lpm_tree);
+		goto err_tree_get;
+	}
+	vr->lpm_tree = lpm_tree;
+	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+	if (err)
+		goto err_tree_bind;
+
+	vr->used = true;
+	return vr;
+
+err_tree_bind:
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
+err_tree_get:
+	mlxsw_sp_fib_destroy(vr->fib);
+
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_vr_destroy(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_vr *vr)
+{
+	mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr);
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
+	mlxsw_sp_fib_destroy(vr->fib);
+	vr->used = false;
+}
+
+static int
+mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
+			   struct mlxsw_sp_prefix_usage *req_prefix_usage)
+{
+	struct mlxsw_sp_lpm_tree *lpm_tree;
+
+	if (mlxsw_sp_prefix_usage_eq(req_prefix_usage,
+				     &vr->lpm_tree->prefix_usage))
+		return 0;
+
+	lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
+					 vr->proto, false);
+	if (IS_ERR(lpm_tree)) {
+		/* We failed to get a tree according to the required
+		 * prefix usage. However, the current tree might be still good
+		 * for us if our requirement is subset of the prefixes used
+		 * in the tree.
+		 */
+		if (mlxsw_sp_prefix_usage_subset(req_prefix_usage,
+						 &vr->lpm_tree->prefix_usage))
+			return 0;
+		return PTR_ERR(lpm_tree);
+	}
+
+	mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr);
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
+	vr->lpm_tree = lpm_tree;
+	return mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+}
+
+static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp,
+					   unsigned char prefix_len,
+					   u32 tb_id,
+					   enum mlxsw_sp_l3proto proto)
+{
+	struct mlxsw_sp_vr *vr;
+	int err;
+
+	tb_id = mlxsw_sp_fix_tb_id(tb_id);
+	vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id, proto);
+	if (!vr) {
+		vr = mlxsw_sp_vr_create(mlxsw_sp, prefix_len, tb_id, proto);
+		if (IS_ERR(vr))
+			return vr;
+	} else {
+		struct mlxsw_sp_prefix_usage req_prefix_usage;
+
+		mlxsw_sp_prefix_usage_cpy(&req_prefix_usage,
+					  &vr->fib->prefix_usage);
+		mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len);
+		/* Need to replace LPM tree in case new prefix is required. */
+		err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr,
+						 &req_prefix_usage);
+		if (err)
+			return ERR_PTR(err);
+	}
+	return vr;
+}
+
+static void mlxsw_sp_vr_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr)
+{
+	/* Destroy virtual router entity in case the associated FIB is empty
+	 * and allow it to be used for other tables in future. Otherwise,
+	 * check if some prefix usage did not disappear and change tree if
+	 * that is the case. Note that in case new, smaller tree cannot be
+	 * allocated, the original one will be kept being used.
+	 */
+	if (mlxsw_sp_prefix_usage_none(&vr->fib->prefix_usage))
+		mlxsw_sp_vr_destroy(mlxsw_sp, vr);
+	else
+		mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr,
+					   &vr->fib->prefix_usage);
+}
+
+static void mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_vr *vr;
+	int i;
+
+	for (i = 0; i < MLXSW_SP_VIRTUAL_ROUTER_MAX; i++) {
+		vr = &mlxsw_sp->router.vrs[i];
+		vr->id = i;
+	}
+}
+
+struct mlxsw_sp_neigh_key {
+	unsigned char addr[sizeof(struct in6_addr)];
+	struct net_device *dev;
+};
+
+struct mlxsw_sp_neigh_entry {
+	struct rhash_head ht_node;
+	struct mlxsw_sp_neigh_key key;
+	u16 rif;
+	struct neighbour *n;
+	bool offloaded;
+	struct delayed_work dw;
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	unsigned char ha[ETH_ALEN];
+	struct list_head nexthop_list; /* list of nexthops using
+					* this neigh entry
+					*/
+	struct list_head nexthop_neighs_list_node;
+};
+
+static const struct rhashtable_params mlxsw_sp_neigh_ht_params = {
+	.key_offset = offsetof(struct mlxsw_sp_neigh_entry, key),
+	.head_offset = offsetof(struct mlxsw_sp_neigh_entry, ht_node),
+	.key_len = sizeof(struct mlxsw_sp_neigh_key),
+};
+
+static int
+mlxsw_sp_neigh_entry_insert(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	return rhashtable_insert_fast(&mlxsw_sp->router.neigh_ht,
+				      &neigh_entry->ht_node,
+				      mlxsw_sp_neigh_ht_params);
+}
+
+static void
+mlxsw_sp_neigh_entry_remove(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	rhashtable_remove_fast(&mlxsw_sp->router.neigh_ht,
+			       &neigh_entry->ht_node,
+			       mlxsw_sp_neigh_ht_params);
+}
+
+static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work);
+
+static struct mlxsw_sp_neigh_entry *
+mlxsw_sp_neigh_entry_create(const void *addr, size_t addr_len,
+			    struct net_device *dev, u16 rif,
+			    struct neighbour *n)
+{
+	struct mlxsw_sp_neigh_entry *neigh_entry;
+
+	neigh_entry = kzalloc(sizeof(*neigh_entry), GFP_ATOMIC);
+	if (!neigh_entry)
+		return NULL;
+	memcpy(neigh_entry->key.addr, addr, addr_len);
+	neigh_entry->key.dev = dev;
+	neigh_entry->rif = rif;
+	neigh_entry->n = n;
+	INIT_DELAYED_WORK(&neigh_entry->dw, mlxsw_sp_router_neigh_update_hw);
+	INIT_LIST_HEAD(&neigh_entry->nexthop_list);
+	return neigh_entry;
+}
+
+static void
+mlxsw_sp_neigh_entry_destroy(struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	kfree(neigh_entry);
+}
+
+static struct mlxsw_sp_neigh_entry *
+mlxsw_sp_neigh_entry_lookup(struct mlxsw_sp *mlxsw_sp, const void *addr,
+			    size_t addr_len, struct net_device *dev)
+{
+	struct mlxsw_sp_neigh_key key = {{ 0 } };
+
+	memcpy(key.addr, addr, addr_len);
+	key.dev = dev;
+	return rhashtable_lookup_fast(&mlxsw_sp->router.neigh_ht,
+				      &key, mlxsw_sp_neigh_ht_params);
+}
+
+int mlxsw_sp_router_neigh_construct(struct net_device *dev,
+				    struct neighbour *n)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_neigh_entry *neigh_entry;
+	struct mlxsw_sp_rif *r;
+	u32 dip;
+	int err;
+
+	if (n->tbl != &arp_tbl)
+		return 0;
+
+	dip = ntohl(*((__be32 *) n->primary_key));
+	neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &dip, sizeof(dip),
+						  n->dev);
+	if (neigh_entry) {
+		WARN_ON(neigh_entry->n != n);
+		return 0;
+	}
+
+	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (WARN_ON(!r))
+		return -EINVAL;
+
+	neigh_entry = mlxsw_sp_neigh_entry_create(&dip, sizeof(dip), n->dev,
+						  r->rif, n);
+	if (!neigh_entry)
+		return -ENOMEM;
+	err = mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry);
+	if (err)
+		goto err_neigh_entry_insert;
+	return 0;
+
+err_neigh_entry_insert:
+	mlxsw_sp_neigh_entry_destroy(neigh_entry);
+	return err;
+}
+
+void mlxsw_sp_router_neigh_destroy(struct net_device *dev,
+				   struct neighbour *n)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_neigh_entry *neigh_entry;
+	u32 dip;
+
+	if (n->tbl != &arp_tbl)
+		return;
+
+	dip = ntohl(*((__be32 *) n->primary_key));
+	neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &dip, sizeof(dip),
+						  n->dev);
+	if (!neigh_entry)
+		return;
+	mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry);
+	mlxsw_sp_neigh_entry_destroy(neigh_entry);
+}
+
+static void
+mlxsw_sp_router_neighs_update_interval_init(struct mlxsw_sp *mlxsw_sp)
+{
+	unsigned long interval = NEIGH_VAR(&arp_tbl.parms, DELAY_PROBE_TIME);
+
+	mlxsw_sp->router.neighs_update.interval = jiffies_to_msecs(interval);
+}
+
+static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp,
+						   char *rauhtd_pl,
+						   int ent_index)
+{
+	struct net_device *dev;
+	struct neighbour *n;
+	__be32 dipn;
+	u32 dip;
+	u16 rif;
+
+	mlxsw_reg_rauhtd_ent_ipv4_unpack(rauhtd_pl, ent_index, &rif, &dip);
+
+	if (!mlxsw_sp->rifs[rif]) {
+		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect RIF in neighbour entry\n");
+		return;
+	}
+
+	dipn = htonl(dip);
+	dev = mlxsw_sp->rifs[rif]->dev;
+	n = neigh_lookup(&arp_tbl, &dipn, dev);
+	if (!n) {
+		netdev_err(dev, "Failed to find matching neighbour for IP=%pI4h\n",
+			   &dip);
+		return;
+	}
+
+	netdev_dbg(dev, "Updating neighbour with IP=%pI4h\n", &dip);
+	neigh_event_send(n, NULL);
+	neigh_release(n);
+}
+
+static void mlxsw_sp_router_neigh_rec_ipv4_process(struct mlxsw_sp *mlxsw_sp,
+						   char *rauhtd_pl,
+						   int rec_index)
+{
+	u8 num_entries;
+	int i;
+
+	num_entries = mlxsw_reg_rauhtd_ipv4_rec_num_entries_get(rauhtd_pl,
+								rec_index);
+	/* Hardware starts counting at 0, so add 1. */
+	num_entries++;
+
+	/* Each record consists of several neighbour entries. */
+	for (i = 0; i < num_entries; i++) {
+		int ent_index;
+
+		ent_index = rec_index * MLXSW_REG_RAUHTD_IPV4_ENT_PER_REC + i;
+		mlxsw_sp_router_neigh_ent_ipv4_process(mlxsw_sp, rauhtd_pl,
+						       ent_index);
+	}
+
+}
+
+static void mlxsw_sp_router_neigh_rec_process(struct mlxsw_sp *mlxsw_sp,
+					      char *rauhtd_pl, int rec_index)
+{
+	switch (mlxsw_reg_rauhtd_rec_type_get(rauhtd_pl, rec_index)) {
+	case MLXSW_REG_RAUHTD_TYPE_IPV4:
+		mlxsw_sp_router_neigh_rec_ipv4_process(mlxsw_sp, rauhtd_pl,
+						       rec_index);
+		break;
+	case MLXSW_REG_RAUHTD_TYPE_IPV6:
+		WARN_ON_ONCE(1);
+		break;
+	}
+}
+
+static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp)
+{
+	char *rauhtd_pl;
+	u8 num_rec;
+	int i, err;
+
+	rauhtd_pl = kmalloc(MLXSW_REG_RAUHTD_LEN, GFP_KERNEL);
+	if (!rauhtd_pl)
+		return -ENOMEM;
+
+	/* Make sure the neighbour's netdev isn't removed in the
+	 * process.
+	 */
+	rtnl_lock();
+	do {
+		mlxsw_reg_rauhtd_pack(rauhtd_pl, MLXSW_REG_RAUHTD_TYPE_IPV4);
+		err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(rauhtd),
+				      rauhtd_pl);
+		if (err) {
+			dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to dump neighbour talbe\n");
+			break;
+		}
+		num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl);
+		for (i = 0; i < num_rec; i++)
+			mlxsw_sp_router_neigh_rec_process(mlxsw_sp, rauhtd_pl,
+							  i);
+	} while (num_rec);
+	rtnl_unlock();
+
+	kfree(rauhtd_pl);
+	return err;
+}
+
+static void mlxsw_sp_router_neighs_update_nh(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_neigh_entry *neigh_entry;
+
+	/* Take RTNL mutex here to prevent lists from changes */
+	rtnl_lock();
+	list_for_each_entry(neigh_entry, &mlxsw_sp->router.nexthop_neighs_list,
+			    nexthop_neighs_list_node) {
+		/* If this neigh have nexthops, make the kernel think this neigh
+		 * is active regardless of the traffic.
+		 */
+		if (!list_empty(&neigh_entry->nexthop_list))
+			neigh_event_send(neigh_entry->n, NULL);
+	}
+	rtnl_unlock();
+}
+
+static void
+mlxsw_sp_router_neighs_update_work_schedule(struct mlxsw_sp *mlxsw_sp)
+{
+	unsigned long interval = mlxsw_sp->router.neighs_update.interval;
+
+	mlxsw_core_schedule_dw(&mlxsw_sp->router.neighs_update.dw,
+			       msecs_to_jiffies(interval));
+}
+
+static void mlxsw_sp_router_neighs_update_work(struct work_struct *work)
+{
+	struct mlxsw_sp *mlxsw_sp = container_of(work, struct mlxsw_sp,
+						 router.neighs_update.dw.work);
+	int err;
+
+	err = mlxsw_sp_router_neighs_update_rauhtd(mlxsw_sp);
+	if (err)
+		dev_err(mlxsw_sp->bus_info->dev, "Could not update kernel for neigh activity");
+
+	mlxsw_sp_router_neighs_update_nh(mlxsw_sp);
+
+	mlxsw_sp_router_neighs_update_work_schedule(mlxsw_sp);
+}
+
+static void mlxsw_sp_router_probe_unresolved_nexthops(struct work_struct *work)
+{
+	struct mlxsw_sp_neigh_entry *neigh_entry;
+	struct mlxsw_sp *mlxsw_sp = container_of(work, struct mlxsw_sp,
+						 router.nexthop_probe_dw.work);
+
+	/* Iterate over nexthop neighbours, find those who are unresolved and
+	 * send arp on them. This solves the chicken-egg problem when
+	 * the nexthop wouldn't get offloaded until the neighbor is resolved
+	 * but it wouldn't get resolved ever in case traffic is flowing in HW
+	 * using different nexthop.
+	 *
+	 * Take RTNL mutex here to prevent lists from changes.
+	 */
+	rtnl_lock();
+	list_for_each_entry(neigh_entry, &mlxsw_sp->router.nexthop_neighs_list,
+			    nexthop_neighs_list_node) {
+		if (!(neigh_entry->n->nud_state & NUD_VALID) &&
+		    !list_empty(&neigh_entry->nexthop_list))
+			neigh_event_send(neigh_entry->n, NULL);
+	}
+	rtnl_unlock();
+
+	mlxsw_core_schedule_dw(&mlxsw_sp->router.nexthop_probe_dw,
+			       MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL);
+}
+
+static void
+mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
+			      struct mlxsw_sp_neigh_entry *neigh_entry,
+			      bool removing);
+
+static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work)
+{
+	struct mlxsw_sp_neigh_entry *neigh_entry =
+		container_of(work, struct mlxsw_sp_neigh_entry, dw.work);
+	struct neighbour *n = neigh_entry->n;
+	struct mlxsw_sp_port *mlxsw_sp_port = neigh_entry->mlxsw_sp_port;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char rauht_pl[MLXSW_REG_RAUHT_LEN];
+	struct net_device *dev;
+	bool entry_connected;
+	u8 nud_state;
+	bool updating;
+	bool removing;
+	bool adding;
+	u32 dip;
+	int err;
+
+	read_lock_bh(&n->lock);
+	dip = ntohl(*((__be32 *) n->primary_key));
+	memcpy(neigh_entry->ha, n->ha, sizeof(neigh_entry->ha));
+	nud_state = n->nud_state;
+	dev = n->dev;
+	read_unlock_bh(&n->lock);
+
+	entry_connected = nud_state & NUD_VALID;
+	adding = (!neigh_entry->offloaded) && entry_connected;
+	updating = neigh_entry->offloaded && entry_connected;
+	removing = neigh_entry->offloaded && !entry_connected;
+
+	if (adding || updating) {
+		mlxsw_reg_rauht_pack4(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_ADD,
+				      neigh_entry->rif,
+				      neigh_entry->ha, dip);
+		err = mlxsw_reg_write(mlxsw_sp->core,
+				      MLXSW_REG(rauht), rauht_pl);
+		if (err) {
+			netdev_err(dev, "Could not add neigh %pI4h\n", &dip);
+			neigh_entry->offloaded = false;
+		} else {
+			neigh_entry->offloaded = true;
+		}
+		mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, false);
+	} else if (removing) {
+		mlxsw_reg_rauht_pack4(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE,
+				      neigh_entry->rif,
+				      neigh_entry->ha, dip);
+		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht),
+				      rauht_pl);
+		if (err) {
+			netdev_err(dev, "Could not delete neigh %pI4h\n", &dip);
+			neigh_entry->offloaded = true;
+		} else {
+			neigh_entry->offloaded = false;
+		}
+		mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, true);
+	}
+
+	neigh_release(n);
+	mlxsw_sp_port_dev_put(mlxsw_sp_port);
+}
+
+static int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
+					  unsigned long event, void *ptr)
+{
+	struct mlxsw_sp_neigh_entry *neigh_entry;
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	struct mlxsw_sp *mlxsw_sp;
+	unsigned long interval;
+	struct net_device *dev;
+	struct neigh_parms *p;
+	struct neighbour *n;
+	u32 dip;
+
+	switch (event) {
+	case NETEVENT_DELAY_PROBE_TIME_UPDATE:
+		p = ptr;
+
+		/* We don't care about changes in the default table. */
+		if (!p->dev || p->tbl != &arp_tbl)
+			return NOTIFY_DONE;
+
+		/* We are in atomic context and can't take RTNL mutex,
+		 * so use RCU variant to walk the device chain.
+		 */
+		mlxsw_sp_port = mlxsw_sp_port_lower_dev_hold(p->dev);
+		if (!mlxsw_sp_port)
+			return NOTIFY_DONE;
+
+		mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+		interval = jiffies_to_msecs(NEIGH_VAR(p, DELAY_PROBE_TIME));
+		mlxsw_sp->router.neighs_update.interval = interval;
+
+		mlxsw_sp_port_dev_put(mlxsw_sp_port);
+		break;
+	case NETEVENT_NEIGH_UPDATE:
+		n = ptr;
+		dev = n->dev;
+
+		if (n->tbl != &arp_tbl)
+			return NOTIFY_DONE;
+
+		mlxsw_sp_port = mlxsw_sp_port_lower_dev_hold(dev);
+		if (!mlxsw_sp_port)
+			return NOTIFY_DONE;
+
+		mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+		dip = ntohl(*((__be32 *) n->primary_key));
+		neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp,
+							  &dip,
+							  sizeof(__be32),
+							  dev);
+		if (WARN_ON(!neigh_entry) || WARN_ON(neigh_entry->n != n)) {
+			mlxsw_sp_port_dev_put(mlxsw_sp_port);
+			return NOTIFY_DONE;
+		}
+		neigh_entry->mlxsw_sp_port = mlxsw_sp_port;
+
+		/* Take a reference to ensure the neighbour won't be
+		 * destructed until we drop the reference in delayed
+		 * work.
+		 */
+		neigh_clone(n);
+		if (!mlxsw_core_schedule_dw(&neigh_entry->dw, 0)) {
+			neigh_release(n);
+			mlxsw_sp_port_dev_put(mlxsw_sp_port);
+		}
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block mlxsw_sp_router_netevent_nb __read_mostly = {
+	.notifier_call = mlxsw_sp_router_netevent_event,
+};
+
+static int mlxsw_sp_neigh_init(struct mlxsw_sp *mlxsw_sp)
+{
+	int err;
+
+	err = rhashtable_init(&mlxsw_sp->router.neigh_ht,
+			      &mlxsw_sp_neigh_ht_params);
+	if (err)
+		return err;
+
+	/* Initialize the polling interval according to the default
+	 * table.
+	 */
+	mlxsw_sp_router_neighs_update_interval_init(mlxsw_sp);
+
+	err = register_netevent_notifier(&mlxsw_sp_router_netevent_nb);
+	if (err)
+		goto err_register_netevent_notifier;
+
+	/* Create the delayed works for the activity_update */
+	INIT_DELAYED_WORK(&mlxsw_sp->router.neighs_update.dw,
+			  mlxsw_sp_router_neighs_update_work);
+	INIT_DELAYED_WORK(&mlxsw_sp->router.nexthop_probe_dw,
+			  mlxsw_sp_router_probe_unresolved_nexthops);
+	mlxsw_core_schedule_dw(&mlxsw_sp->router.neighs_update.dw, 0);
+	mlxsw_core_schedule_dw(&mlxsw_sp->router.nexthop_probe_dw, 0);
+	return 0;
+
+err_register_netevent_notifier:
+	rhashtable_destroy(&mlxsw_sp->router.neigh_ht);
+	return err;
+}
+
+static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	cancel_delayed_work_sync(&mlxsw_sp->router.neighs_update.dw);
+	cancel_delayed_work_sync(&mlxsw_sp->router.nexthop_probe_dw);
+	unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb);
+	rhashtable_destroy(&mlxsw_sp->router.neigh_ht);
+}
+
+struct mlxsw_sp_nexthop {
+	struct list_head neigh_list_node; /* member of neigh entry list */
+	struct mlxsw_sp_nexthop_group *nh_grp; /* pointer back to the group
+						* this belongs to
+						*/
+	u8 should_offload:1, /* set indicates this neigh is connected and
+			      * should be put to KVD linear area of this group.
+			      */
+	   offloaded:1, /* set in case the neigh is actually put into
+			 * KVD linear area of this group.
+			 */
+	   update:1; /* set indicates that MAC of this neigh should be
+		      * updated in HW
+		      */
+	struct mlxsw_sp_neigh_entry *neigh_entry;
+};
+
+struct mlxsw_sp_nexthop_group {
+	struct list_head list; /* node in mlxsw->router.nexthop_group_list */
+	struct list_head fib_list; /* list of fib entries that use this group */
+	u8 adj_index_valid:1;
+	u32 adj_index;
+	u16 ecmp_size;
+	u16 count;
+	struct mlxsw_sp_nexthop nexthops[0];
+};
+
+static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp,
+					     struct mlxsw_sp_vr *vr,
+					     u32 adj_index, u16 ecmp_size,
+					     u32 new_adj_index,
+					     u16 new_ecmp_size)
+{
+	char raleu_pl[MLXSW_REG_RALEU_LEN];
+
+	mlxsw_reg_raleu_pack(raleu_pl, vr->proto, vr->id,
+			     adj_index, ecmp_size,
+			     new_adj_index, new_ecmp_size);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raleu), raleu_pl);
+}
+
+static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp,
+					  struct mlxsw_sp_nexthop_group *nh_grp,
+					  u32 old_adj_index, u16 old_ecmp_size)
+{
+	struct mlxsw_sp_fib_entry *fib_entry;
+	struct mlxsw_sp_vr *vr = NULL;
+	int err;
+
+	list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) {
+		if (vr == fib_entry->vr)
+			continue;
+		vr = fib_entry->vr;
+		err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, vr,
+							old_adj_index,
+							old_ecmp_size,
+							nh_grp->adj_index,
+							nh_grp->ecmp_size);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
+				       struct mlxsw_sp_nexthop *nh)
+{
+	struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry;
+	char ratr_pl[MLXSW_REG_RATR_LEN];
+
+	mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY,
+			    true, adj_index, neigh_entry->rif);
+	mlxsw_reg_ratr_eth_entry_pack(ratr_pl, neigh_entry->ha);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl);
+}
+
+static int
+mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_nexthop_group *nh_grp)
+{
+	u32 adj_index = nh_grp->adj_index; /* base */
+	struct mlxsw_sp_nexthop *nh;
+	int i;
+	int err;
+
+	for (i = 0; i < nh_grp->count; i++) {
+		nh = &nh_grp->nexthops[i];
+
+		if (!nh->should_offload) {
+			nh->offloaded = 0;
+			continue;
+		}
+
+		if (nh->update) {
+			err = mlxsw_sp_nexthop_mac_update(mlxsw_sp,
+							  adj_index, nh);
+			if (err)
+				return err;
+			nh->update = 0;
+			nh->offloaded = 1;
+		}
+		adj_index++;
+	}
+	return 0;
+}
+
+static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_fib_entry *fib_entry);
+
+static int
+mlxsw_sp_nexthop_fib_entries_update(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_nexthop_group *nh_grp)
+{
+	struct mlxsw_sp_fib_entry *fib_entry;
+	int err;
+
+	list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) {
+		err = mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static void
+mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_nexthop_group *nh_grp)
+{
+	struct mlxsw_sp_nexthop *nh;
+	bool offload_change = false;
+	u32 adj_index;
+	u16 ecmp_size = 0;
+	bool old_adj_index_valid;
+	u32 old_adj_index;
+	u16 old_ecmp_size;
+	int ret;
+	int i;
+	int err;
+
+	for (i = 0; i < nh_grp->count; i++) {
+		nh = &nh_grp->nexthops[i];
+
+		if (nh->should_offload ^ nh->offloaded) {
+			offload_change = true;
+			if (nh->should_offload)
+				nh->update = 1;
+		}
+		if (nh->should_offload)
+			ecmp_size++;
+	}
+	if (!offload_change) {
+		/* Nothing was added or removed, so no need to reallocate. Just
+		 * update MAC on existing adjacency indexes.
+		 */
+		err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp);
+		if (err) {
+			dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
+			goto set_trap;
+		}
+		return;
+	}
+	if (!ecmp_size)
+		/* No neigh of this group is connected so we just set
+		 * the trap and let everthing flow through kernel.
+		 */
+		goto set_trap;
+
+	ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size);
+	if (ret < 0) {
+		/* We ran out of KVD linear space, just set the
+		 * trap and let everything flow through kernel.
+		 */
+		dev_warn(mlxsw_sp->bus_info->dev, "Failed to allocate KVD linear area for nexthop group.\n");
+		goto set_trap;
+	}
+	adj_index = ret;
+	old_adj_index_valid = nh_grp->adj_index_valid;
+	old_adj_index = nh_grp->adj_index;
+	old_ecmp_size = nh_grp->ecmp_size;
+	nh_grp->adj_index_valid = 1;
+	nh_grp->adj_index = adj_index;
+	nh_grp->ecmp_size = ecmp_size;
+	err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp);
+	if (err) {
+		dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
+		goto set_trap;
+	}
+
+	if (!old_adj_index_valid) {
+		/* The trap was set for fib entries, so we have to call
+		 * fib entry update to unset it and use adjacency index.
+		 */
+		err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
+		if (err) {
+			dev_warn(mlxsw_sp->bus_info->dev, "Failed to add adjacency index to fib entries.\n");
+			goto set_trap;
+		}
+		return;
+	}
+
+	err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, nh_grp,
+					     old_adj_index, old_ecmp_size);
+	mlxsw_sp_kvdl_free(mlxsw_sp, old_adj_index);
+	if (err) {
+		dev_warn(mlxsw_sp->bus_info->dev, "Failed to mass-update adjacency index for nexthop group.\n");
+		goto set_trap;
+	}
+	return;
+
+set_trap:
+	old_adj_index_valid = nh_grp->adj_index_valid;
+	nh_grp->adj_index_valid = 0;
+	for (i = 0; i < nh_grp->count; i++) {
+		nh = &nh_grp->nexthops[i];
+		nh->offloaded = 0;
+	}
+	err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
+	if (err)
+		dev_warn(mlxsw_sp->bus_info->dev, "Failed to set traps for fib entries.\n");
+	if (old_adj_index_valid)
+		mlxsw_sp_kvdl_free(mlxsw_sp, nh_grp->adj_index);
+}
+
+static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh,
+					    bool removing)
+{
+	if (!removing && !nh->should_offload)
+		nh->should_offload = 1;
+	else if (removing && nh->offloaded)
+		nh->should_offload = 0;
+	nh->update = 1;
+}
+
+static void
+mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
+			      struct mlxsw_sp_neigh_entry *neigh_entry,
+			      bool removing)
+{
+	struct mlxsw_sp_nexthop *nh;
+
+	/* Take RTNL mutex here to prevent lists from changes */
+	rtnl_lock();
+	list_for_each_entry(nh, &neigh_entry->nexthop_list,
+			    neigh_list_node) {
+		__mlxsw_sp_nexthop_neigh_update(nh, removing);
+		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
+	}
+	rtnl_unlock();
+}
+
+static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_nexthop_group *nh_grp,
+				 struct mlxsw_sp_nexthop *nh,
+				 struct fib_nh *fib_nh)
+{
+	struct mlxsw_sp_neigh_entry *neigh_entry;
+	u32 gwip = ntohl(fib_nh->nh_gw);
+	struct net_device *dev = fib_nh->nh_dev;
+	struct neighbour *n;
+	u8 nud_state;
+
+	neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &gwip,
+						  sizeof(gwip), dev);
+	if (!neigh_entry) {
+		__be32 gwipn = htonl(gwip);
+
+		n = neigh_create(&arp_tbl, &gwipn, dev);
+		if (IS_ERR(n))
+			return PTR_ERR(n);
+		neigh_event_send(n, NULL);
+		neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &gwip,
+							  sizeof(gwip), dev);
+		if (!neigh_entry) {
+			neigh_release(n);
+			return -EINVAL;
+		}
+	} else {
+		/* Take a reference of neigh here ensuring that neigh would
+		 * not be detructed before the nexthop entry is finished.
+		 * The second branch takes the reference in neith_create()
+		 */
+		n = neigh_entry->n;
+		neigh_clone(n);
+	}
+
+	/* If that is the first nexthop connected to that neigh, add to
+	 * nexthop_neighs_list
+	 */
+	if (list_empty(&neigh_entry->nexthop_list))
+		list_add_tail(&neigh_entry->nexthop_neighs_list_node,
+			      &mlxsw_sp->router.nexthop_neighs_list);
+
+	nh->nh_grp = nh_grp;
+	nh->neigh_entry = neigh_entry;
+	list_add_tail(&nh->neigh_list_node, &neigh_entry->nexthop_list);
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	read_unlock_bh(&n->lock);
+	__mlxsw_sp_nexthop_neigh_update(nh, !(nud_state & NUD_VALID));
+
+	return 0;
+}
+
+static void mlxsw_sp_nexthop_fini(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_nexthop *nh)
+{
+	struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry;
+
+	list_del(&nh->neigh_list_node);
+
+	/* If that is the last nexthop connected to that neigh, remove from
+	 * nexthop_neighs_list
+	 */
+	if (list_empty(&nh->neigh_entry->nexthop_list))
+		list_del(&nh->neigh_entry->nexthop_neighs_list_node);
+
+	neigh_release(neigh_entry->n);
+}
+
+static struct mlxsw_sp_nexthop_group *
+mlxsw_sp_nexthop_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
+{
+	struct mlxsw_sp_nexthop_group *nh_grp;
+	struct mlxsw_sp_nexthop *nh;
+	struct fib_nh *fib_nh;
+	size_t alloc_size;
+	int i;
+	int err;
+
+	alloc_size = sizeof(*nh_grp) +
+		     fi->fib_nhs * sizeof(struct mlxsw_sp_nexthop);
+	nh_grp = kzalloc(alloc_size, GFP_KERNEL);
+	if (!nh_grp)
+		return ERR_PTR(-ENOMEM);
+	INIT_LIST_HEAD(&nh_grp->fib_list);
+	nh_grp->count = fi->fib_nhs;
+	for (i = 0; i < nh_grp->count; i++) {
+		nh = &nh_grp->nexthops[i];
+		fib_nh = &fi->fib_nh[i];
+		err = mlxsw_sp_nexthop_init(mlxsw_sp, nh_grp, nh, fib_nh);
+		if (err)
+			goto err_nexthop_init;
+	}
+	list_add_tail(&nh_grp->list, &mlxsw_sp->router.nexthop_group_list);
+	mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
+	return nh_grp;
+
+err_nexthop_init:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_nexthop_fini(mlxsw_sp, nh);
+	kfree(nh_grp);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_nexthop_group_destroy(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_nexthop_group *nh_grp)
+{
+	struct mlxsw_sp_nexthop *nh;
+	int i;
+
+	list_del(&nh_grp->list);
+	for (i = 0; i < nh_grp->count; i++) {
+		nh = &nh_grp->nexthops[i];
+		mlxsw_sp_nexthop_fini(mlxsw_sp, nh);
+	}
+	kfree(nh_grp);
+}
+
+static bool mlxsw_sp_nexthop_match(struct mlxsw_sp_nexthop *nh,
+				   struct fib_info *fi)
+{
+	int i;
+
+	for (i = 0; i < fi->fib_nhs; i++) {
+		struct fib_nh *fib_nh = &fi->fib_nh[i];
+		u32 gwip = ntohl(fib_nh->nh_gw);
+
+		if (memcmp(nh->neigh_entry->key.addr,
+			   &gwip, sizeof(u32)) == 0 &&
+		    nh->neigh_entry->key.dev == fib_nh->nh_dev)
+			return true;
+	}
+	return false;
+}
+
+static bool mlxsw_sp_nexthop_group_match(struct mlxsw_sp_nexthop_group *nh_grp,
+					 struct fib_info *fi)
+{
+	int i;
+
+	if (nh_grp->count != fi->fib_nhs)
+		return false;
+	for (i = 0; i < nh_grp->count; i++) {
+		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
+
+		if (!mlxsw_sp_nexthop_match(nh, fi))
+			return false;
+	}
+	return true;
+}
+
+static struct mlxsw_sp_nexthop_group *
+mlxsw_sp_nexthop_group_find(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
+{
+	struct mlxsw_sp_nexthop_group *nh_grp;
+
+	list_for_each_entry(nh_grp, &mlxsw_sp->router.nexthop_group_list,
+			    list) {
+		if (mlxsw_sp_nexthop_group_match(nh_grp, fi))
+			return nh_grp;
+	}
+	return NULL;
+}
+
+static int mlxsw_sp_nexthop_group_get(struct mlxsw_sp *mlxsw_sp,
+				      struct mlxsw_sp_fib_entry *fib_entry,
+				      struct fib_info *fi)
+{
+	struct mlxsw_sp_nexthop_group *nh_grp;
+
+	nh_grp = mlxsw_sp_nexthop_group_find(mlxsw_sp, fi);
+	if (!nh_grp) {
+		nh_grp = mlxsw_sp_nexthop_group_create(mlxsw_sp, fi);
+		if (IS_ERR(nh_grp))
+			return PTR_ERR(nh_grp);
+	}
+	list_add_tail(&fib_entry->nexthop_group_node, &nh_grp->fib_list);
+	fib_entry->nh_group = nh_grp;
+	return 0;
+}
+
+static void mlxsw_sp_nexthop_group_put(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_fib_entry *fib_entry)
+{
+	struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
+
+	list_del(&fib_entry->nexthop_group_node);
+	if (!list_empty(&nh_grp->fib_list))
+		return;
+	mlxsw_sp_nexthop_group_destroy(mlxsw_sp, nh_grp);
+}
+
+static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
+{
+	char rgcr_pl[MLXSW_REG_RGCR_LEN];
+
+	mlxsw_reg_rgcr_pack(rgcr_pl, true);
+	mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, MLXSW_SP_RIF_MAX);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
+}
+
+static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	char rgcr_pl[MLXSW_REG_RGCR_LEN];
+
+	mlxsw_reg_rgcr_pack(rgcr_pl, false);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
+}
+
+int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
+{
+	int err;
+
+	INIT_LIST_HEAD(&mlxsw_sp->router.nexthop_neighs_list);
+	INIT_LIST_HEAD(&mlxsw_sp->router.nexthop_group_list);
+	err = __mlxsw_sp_router_init(mlxsw_sp);
+	if (err)
+		return err;
+	mlxsw_sp_lpm_init(mlxsw_sp);
+	mlxsw_sp_vrs_init(mlxsw_sp);
+	return mlxsw_sp_neigh_init(mlxsw_sp);
+}
+
+void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	mlxsw_sp_neigh_fini(mlxsw_sp);
+	__mlxsw_sp_router_fini(mlxsw_sp);
+}
+
+static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp,
+					 struct mlxsw_sp_fib_entry *fib_entry,
+					 enum mlxsw_reg_ralue_op op)
+{
+	char ralue_pl[MLXSW_REG_RALUE_LEN];
+	u32 *p_dip = (u32 *) fib_entry->key.addr;
+	struct mlxsw_sp_vr *vr = fib_entry->vr;
+	enum mlxsw_reg_ralue_trap_action trap_action;
+	u16 trap_id = 0;
+	u32 adjacency_index = 0;
+	u16 ecmp_size = 0;
+
+	/* In case the nexthop group adjacency index is valid, use it
+	 * with provided ECMP size. Otherwise, setup trap and pass
+	 * traffic to kernel.
+	 */
+	if (fib_entry->nh_group->adj_index_valid) {
+		trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP;
+		adjacency_index = fib_entry->nh_group->adj_index;
+		ecmp_size = fib_entry->nh_group->ecmp_size;
+	} else {
+		trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP;
+		trap_id = MLXSW_TRAP_ID_RTR_INGRESS0;
+	}
+
+	mlxsw_reg_ralue_pack4(ralue_pl, vr->proto, op, vr->id,
+			      fib_entry->key.prefix_len, *p_dip);
+	mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id,
+					adjacency_index, ecmp_size);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+}
+
+static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_fib_entry *fib_entry,
+					enum mlxsw_reg_ralue_op op)
+{
+	char ralue_pl[MLXSW_REG_RALUE_LEN];
+	u32 *p_dip = (u32 *) fib_entry->key.addr;
+	struct mlxsw_sp_vr *vr = fib_entry->vr;
+
+	mlxsw_reg_ralue_pack4(ralue_pl, vr->proto, op, vr->id,
+			      fib_entry->key.prefix_len, *p_dip);
+	mlxsw_reg_ralue_act_local_pack(ralue_pl,
+				       MLXSW_REG_RALUE_TRAP_ACTION_NOP, 0,
+				       fib_entry->rif);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+}
+
+static int mlxsw_sp_fib_entry_op4_trap(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_fib_entry *fib_entry,
+				       enum mlxsw_reg_ralue_op op)
+{
+	char ralue_pl[MLXSW_REG_RALUE_LEN];
+	u32 *p_dip = (u32 *) fib_entry->key.addr;
+	struct mlxsw_sp_vr *vr = fib_entry->vr;
+
+	mlxsw_reg_ralue_pack4(ralue_pl, vr->proto, op, vr->id,
+			      fib_entry->key.prefix_len, *p_dip);
+	mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+}
+
+static int mlxsw_sp_fib_entry_op4(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_fib_entry *fib_entry,
+				  enum mlxsw_reg_ralue_op op)
+{
+	switch (fib_entry->type) {
+	case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE:
+		return mlxsw_sp_fib_entry_op4_remote(mlxsw_sp, fib_entry, op);
+	case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL:
+		return mlxsw_sp_fib_entry_op4_local(mlxsw_sp, fib_entry, op);
+	case MLXSW_SP_FIB_ENTRY_TYPE_TRAP:
+		return mlxsw_sp_fib_entry_op4_trap(mlxsw_sp, fib_entry, op);
+	}
+	return -EINVAL;
+}
+
+static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_fib_entry *fib_entry,
+				 enum mlxsw_reg_ralue_op op)
+{
+	switch (fib_entry->vr->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		return mlxsw_sp_fib_entry_op4(mlxsw_sp, fib_entry, op);
+	case MLXSW_SP_L3_PROTO_IPV6:
+		return -EINVAL;
+	}
+	return -EINVAL;
+}
+
+static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_fib_entry *fib_entry)
+{
+	enum mlxsw_reg_ralue_op op;
+
+	op = !fib_entry->added ? MLXSW_REG_RALUE_OP_WRITE_WRITE :
+				 MLXSW_REG_RALUE_OP_WRITE_UPDATE;
+	return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, op);
+}
+
+static int mlxsw_sp_fib_entry_del(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_fib_entry *fib_entry)
+{
+	return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry,
+				     MLXSW_REG_RALUE_OP_WRITE_DELETE);
+}
+
+struct mlxsw_sp_router_fib4_add_info {
+	struct switchdev_trans_item tritem;
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_fib_entry *fib_entry;
+};
+
+static void mlxsw_sp_router_fib4_add_info_destroy(void const *data)
+{
+	const struct mlxsw_sp_router_fib4_add_info *info = data;
+	struct mlxsw_sp_fib_entry *fib_entry = info->fib_entry;
+	struct mlxsw_sp *mlxsw_sp = info->mlxsw_sp;
+
+	mlxsw_sp_fib_entry_destroy(fib_entry);
+	mlxsw_sp_vr_put(mlxsw_sp, fib_entry->vr);
+	kfree(info);
+}
+
+static int
+mlxsw_sp_router_fib4_entry_init(struct mlxsw_sp *mlxsw_sp,
+				const struct switchdev_obj_ipv4_fib *fib4,
+				struct mlxsw_sp_fib_entry *fib_entry)
+{
+	struct fib_info *fi = fib4->fi;
+
+	if (fib4->type == RTN_LOCAL || fib4->type == RTN_BROADCAST) {
+		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
+		return 0;
+	}
+	if (fib4->type != RTN_UNICAST)
+		return -EINVAL;
+
+	if (fi->fib_scope != RT_SCOPE_UNIVERSE) {
+		struct mlxsw_sp_rif *r;
+
+		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
+		r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fi->fib_dev);
+		if (!r)
+			return -EINVAL;
+		fib_entry->rif = r->rif;
+		return 0;
+	}
+	fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
+	return mlxsw_sp_nexthop_group_get(mlxsw_sp, fib_entry, fi);
+}
+
+static void
+mlxsw_sp_router_fib4_entry_fini(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_fib_entry *fib_entry)
+{
+	if (fib_entry->type != MLXSW_SP_FIB_ENTRY_TYPE_REMOTE)
+		return;
+	mlxsw_sp_nexthop_group_put(mlxsw_sp, fib_entry);
+}
+
+static int
+mlxsw_sp_router_fib4_add_prepare(struct mlxsw_sp_port *mlxsw_sp_port,
+				 const struct switchdev_obj_ipv4_fib *fib4,
+				 struct switchdev_trans *trans)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_router_fib4_add_info *info;
+	struct mlxsw_sp_fib_entry *fib_entry;
+	struct mlxsw_sp_vr *vr;
+	int err;
+
+	vr = mlxsw_sp_vr_get(mlxsw_sp, fib4->dst_len, fib4->tb_id,
+			     MLXSW_SP_L3_PROTO_IPV4);
+	if (IS_ERR(vr))
+		return PTR_ERR(vr);
+
+	fib_entry = mlxsw_sp_fib_entry_create(vr->fib, &fib4->dst,
+					      sizeof(fib4->dst), fib4->dst_len);
+	if (!fib_entry) {
+		err = -ENOMEM;
+		goto err_fib_entry_create;
+	}
+	fib_entry->vr = vr;
+
+	err = mlxsw_sp_router_fib4_entry_init(mlxsw_sp, fib4, fib_entry);
+	if (err)
+		goto err_fib4_entry_init;
+
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		err = -ENOMEM;
+		goto err_alloc_info;
+	}
+	info->mlxsw_sp = mlxsw_sp;
+	info->fib_entry = fib_entry;
+	switchdev_trans_item_enqueue(trans, info,
+				     mlxsw_sp_router_fib4_add_info_destroy,
+				     &info->tritem);
+	return 0;
+
+err_alloc_info:
+	mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry);
+err_fib4_entry_init:
+	mlxsw_sp_fib_entry_destroy(fib_entry);
+err_fib_entry_create:
+	mlxsw_sp_vr_put(mlxsw_sp, vr);
+	return err;
+}
+
+static int
+mlxsw_sp_router_fib4_add_commit(struct mlxsw_sp_port *mlxsw_sp_port,
+				const struct switchdev_obj_ipv4_fib *fib4,
+				struct switchdev_trans *trans)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_router_fib4_add_info *info;
+	struct mlxsw_sp_fib_entry *fib_entry;
+	struct mlxsw_sp_vr *vr;
+	int err;
+
+	info = switchdev_trans_item_dequeue(trans);
+	fib_entry = info->fib_entry;
+	kfree(info);
+
+	vr = fib_entry->vr;
+	err = mlxsw_sp_fib_entry_insert(fib_entry->vr->fib, fib_entry);
+	if (err)
+		goto err_fib_entry_insert;
+	err = mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry);
+	if (err)
+		goto err_fib_entry_add;
+	return 0;
+
+err_fib_entry_add:
+	mlxsw_sp_fib_entry_remove(vr->fib, fib_entry);
+err_fib_entry_insert:
+	mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry);
+	mlxsw_sp_fib_entry_destroy(fib_entry);
+	mlxsw_sp_vr_put(mlxsw_sp, vr);
+	return err;
+}
+
+int mlxsw_sp_router_fib4_add(struct mlxsw_sp_port *mlxsw_sp_port,
+			     const struct switchdev_obj_ipv4_fib *fib4,
+			     struct switchdev_trans *trans)
+{
+	if (switchdev_trans_ph_prepare(trans))
+		return mlxsw_sp_router_fib4_add_prepare(mlxsw_sp_port,
+							fib4, trans);
+	return mlxsw_sp_router_fib4_add_commit(mlxsw_sp_port,
+					       fib4, trans);
+}
+
+int mlxsw_sp_router_fib4_del(struct mlxsw_sp_port *mlxsw_sp_port,
+			     const struct switchdev_obj_ipv4_fib *fib4)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_fib_entry *fib_entry;
+	struct mlxsw_sp_vr *vr;
+
+	vr = mlxsw_sp_vr_find(mlxsw_sp, fib4->tb_id, MLXSW_SP_L3_PROTO_IPV4);
+	if (!vr) {
+		dev_warn(mlxsw_sp->bus_info->dev, "Failed to find virtual router for FIB4 entry being removed.\n");
+		return -ENOENT;
+	}
+	fib_entry = mlxsw_sp_fib_entry_lookup(vr->fib, &fib4->dst,
+					      sizeof(fib4->dst), fib4->dst_len);
+	if (!fib_entry) {
+		dev_warn(mlxsw_sp->bus_info->dev, "Failed to find FIB4 entry being removed.\n");
+		return PTR_ERR(vr);
+	}
+	mlxsw_sp_fib_entry_del(mlxsw_sp_port->mlxsw_sp, fib_entry);
+	mlxsw_sp_fib_entry_remove(vr->fib, fib_entry);
+	mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry);
+	mlxsw_sp_fib_entry_destroy(fib_entry);
+	mlxsw_sp_vr_put(mlxsw_sp, vr);
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 3710f19ed6bb..a1ad5e6bdfa8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -55,13 +55,10 @@
 static u16 mlxsw_sp_port_vid_to_fid_get(struct mlxsw_sp_port *mlxsw_sp_port,
 					u16 vid)
 {
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_port);
 	u16 fid = vid;
 
-	if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) {
-		u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_port);
-
-		fid = mlxsw_sp_vfid_to_fid(vfid);
-	}
+	fid = f ? f->fid : fid;
 
 	if (!fid)
 		fid = mlxsw_sp_port->pvid;
@@ -169,11 +166,6 @@ static int mlxsw_sp_port_attr_stp_state_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	return mlxsw_sp_port_stp_state_set(mlxsw_sp_port, state);
 }
 
-static bool mlxsw_sp_vfid_is_vport_br(u16 vfid)
-{
-	return vfid >= MLXSW_SP_VFID_PORT_MAX;
-}
-
 static int __mlxsw_sp_port_flood_set(struct mlxsw_sp_port *mlxsw_sp_port,
 				     u16 idx_begin, u16 idx_end, bool set,
 				     bool only_uc)
@@ -185,15 +177,10 @@ static int __mlxsw_sp_port_flood_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	char *sftr_pl;
 	int err;
 
-	if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) {
+	if (mlxsw_sp_port_is_vport(mlxsw_sp_port))
 		table_type = MLXSW_REG_SFGC_TABLE_TYPE_FID;
-		if (mlxsw_sp_vfid_is_vport_br(idx_begin))
-			local_port = mlxsw_sp_port->local_port;
-		else
-			local_port = MLXSW_PORT_CPU_PORT;
-	} else {
+	else
 		table_type = MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST;
-	}
 
 	sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL);
 	if (!sftr_pl)
@@ -236,7 +223,8 @@ static int mlxsw_sp_port_uc_flood_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	int err;
 
 	if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) {
-		u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_port);
+		u16 fid = mlxsw_sp_vport_fid_get(mlxsw_sp_port)->fid;
+		u16 vfid = mlxsw_sp_fid_to_vfid(fid);
 
 		return  __mlxsw_sp_port_flood_set(mlxsw_sp_port, vfid, vfid,
 						  set, true);
@@ -260,14 +248,17 @@ err_port_flood_set:
 	return err;
 }
 
-int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid,
-			     bool set, bool only_uc)
+int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid,
+			     bool set)
 {
+	u16 vfid;
+
 	/* In case of vFIDs, index into the flooding table is relative to
 	 * the start of the vFIDs range.
 	 */
+	vfid = mlxsw_sp_fid_to_vfid(fid);
 	return __mlxsw_sp_port_flood_set(mlxsw_sp_vport, vfid, vfid, set,
-					 only_uc);
+					 false);
 }
 
 static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -383,6 +374,187 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
 	return err;
 }
 
+static int mlxsw_sp_fid_op(struct mlxsw_sp *mlxsw_sp, u16 fid, bool create)
+{
+	char sfmr_pl[MLXSW_REG_SFMR_LEN];
+
+	mlxsw_reg_sfmr_pack(sfmr_pl, !create, fid, fid);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
+}
+
+static int mlxsw_sp_fid_map(struct mlxsw_sp *mlxsw_sp, u16 fid, bool valid)
+{
+	enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_VID_TO_FID;
+	char svfa_pl[MLXSW_REG_SVFA_LEN];
+
+	mlxsw_reg_svfa_pack(svfa_pl, 0, mt, valid, fid, fid);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(svfa), svfa_pl);
+}
+
+static struct mlxsw_sp_fid *mlxsw_sp_fid_alloc(u16 fid)
+{
+	struct mlxsw_sp_fid *f;
+
+	f = kzalloc(sizeof(*f), GFP_KERNEL);
+	if (!f)
+		return NULL;
+
+	f->fid = fid;
+
+	return f;
+}
+
+struct mlxsw_sp_fid *mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid)
+{
+	struct mlxsw_sp_fid *f;
+	int err;
+
+	err = mlxsw_sp_fid_op(mlxsw_sp, fid, true);
+	if (err)
+		return ERR_PTR(err);
+
+	/* Although all the ports member in the FID might be using a
+	 * {Port, VID} to FID mapping, we create a global VID-to-FID
+	 * mapping. This allows a port to transition to VLAN mode,
+	 * knowing the global mapping exists.
+	 */
+	err = mlxsw_sp_fid_map(mlxsw_sp, fid, true);
+	if (err)
+		goto err_fid_map;
+
+	f = mlxsw_sp_fid_alloc(fid);
+	if (!f) {
+		err = -ENOMEM;
+		goto err_allocate_fid;
+	}
+
+	list_add(&f->list, &mlxsw_sp->fids);
+
+	return f;
+
+err_allocate_fid:
+	mlxsw_sp_fid_map(mlxsw_sp, fid, false);
+err_fid_map:
+	mlxsw_sp_fid_op(mlxsw_sp, fid, false);
+	return ERR_PTR(err);
+}
+
+void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f)
+{
+	u16 fid = f->fid;
+
+	list_del(&f->list);
+
+	if (f->r)
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+
+	kfree(f);
+
+	mlxsw_sp_fid_op(mlxsw_sp, fid, false);
+}
+
+static int __mlxsw_sp_port_fid_join(struct mlxsw_sp_port *mlxsw_sp_port,
+				    u16 fid)
+{
+	struct mlxsw_sp_fid *f;
+
+	f = mlxsw_sp_fid_find(mlxsw_sp_port->mlxsw_sp, fid);
+	if (!f) {
+		f = mlxsw_sp_fid_create(mlxsw_sp_port->mlxsw_sp, fid);
+		if (IS_ERR(f))
+			return PTR_ERR(f);
+	}
+
+	f->ref_count++;
+
+	netdev_dbg(mlxsw_sp_port->dev, "Joined FID=%d\n", fid);
+
+	return 0;
+}
+
+static void __mlxsw_sp_port_fid_leave(struct mlxsw_sp_port *mlxsw_sp_port,
+				      u16 fid)
+{
+	struct mlxsw_sp_fid *f;
+
+	f = mlxsw_sp_fid_find(mlxsw_sp_port->mlxsw_sp, fid);
+	if (WARN_ON(!f))
+		return;
+
+	netdev_dbg(mlxsw_sp_port->dev, "Left FID=%d\n", fid);
+
+	mlxsw_sp_port_fdb_flush(mlxsw_sp_port, fid);
+
+	if (--f->ref_count == 0)
+		mlxsw_sp_fid_destroy(mlxsw_sp_port->mlxsw_sp, f);
+}
+
+static int mlxsw_sp_port_fid_map(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid,
+				 bool valid)
+{
+	enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID;
+
+	/* If port doesn't have vPorts, then it can use the global
+	 * VID-to-FID mapping.
+	 */
+	if (list_empty(&mlxsw_sp_port->vports_list))
+		return 0;
+
+	return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, valid, fid, fid);
+}
+
+static int mlxsw_sp_port_fid_join(struct mlxsw_sp_port *mlxsw_sp_port,
+				  u16 fid_begin, u16 fid_end)
+{
+	int fid, err;
+
+	for (fid = fid_begin; fid <= fid_end; fid++) {
+		err = __mlxsw_sp_port_fid_join(mlxsw_sp_port, fid);
+		if (err)
+			goto err_port_fid_join;
+	}
+
+	err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, fid_begin, fid_end,
+					true, false);
+	if (err)
+		goto err_port_flood_set;
+
+	for (fid = fid_begin; fid <= fid_end; fid++) {
+		err = mlxsw_sp_port_fid_map(mlxsw_sp_port, fid, true);
+		if (err)
+			goto err_port_fid_map;
+	}
+
+	return 0;
+
+err_port_fid_map:
+	for (fid--; fid >= fid_begin; fid--)
+		mlxsw_sp_port_fid_map(mlxsw_sp_port, fid, false);
+	__mlxsw_sp_port_flood_set(mlxsw_sp_port, fid_begin, fid_end, false,
+				  false);
+err_port_flood_set:
+	fid = fid_end;
+err_port_fid_join:
+	for (fid--; fid >= fid_begin; fid--)
+		__mlxsw_sp_port_fid_leave(mlxsw_sp_port, fid);
+	return err;
+}
+
+static void mlxsw_sp_port_fid_leave(struct mlxsw_sp_port *mlxsw_sp_port,
+				    u16 fid_begin, u16 fid_end)
+{
+	int fid;
+
+	for (fid = fid_begin; fid <= fid_end; fid++)
+		mlxsw_sp_port_fid_map(mlxsw_sp_port, fid, false);
+
+	__mlxsw_sp_port_flood_set(mlxsw_sp_port, fid_begin, fid_end, false,
+				  false);
+
+	for (fid = fid_begin; fid <= fid_end; fid++)
+		__mlxsw_sp_port_fid_leave(mlxsw_sp_port, fid);
+}
+
 static int __mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port,
 				    u16 vid)
 {
@@ -440,74 +612,6 @@ err_port_allow_untagged_set:
 	return err;
 }
 
-static int mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid)
-{
-	char sfmr_pl[MLXSW_REG_SFMR_LEN];
-	int err;
-
-	mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_CREATE_FID, fid, fid);
-	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
-
-	if (err)
-		return err;
-
-	set_bit(fid, mlxsw_sp->active_fids);
-	return 0;
-}
-
-static void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, u16 fid)
-{
-	char sfmr_pl[MLXSW_REG_SFMR_LEN];
-
-	clear_bit(fid, mlxsw_sp->active_fids);
-
-	mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_DESTROY_FID,
-			    fid, fid);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
-}
-
-static int mlxsw_sp_port_fid_map(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid)
-{
-	enum mlxsw_reg_svfa_mt mt;
-
-	if (!list_empty(&mlxsw_sp_port->vports_list))
-		mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID;
-	else
-		mt = MLXSW_REG_SVFA_MT_VID_TO_FID;
-
-	return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, true, fid, fid);
-}
-
-static int mlxsw_sp_port_fid_unmap(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid)
-{
-	enum mlxsw_reg_svfa_mt mt;
-
-	if (list_empty(&mlxsw_sp_port->vports_list))
-		return 0;
-
-	mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID;
-	return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, false, fid, fid);
-}
-
-static int mlxsw_sp_port_add_vids(struct net_device *dev, u16 vid_begin,
-				  u16 vid_end)
-{
-	u16 vid;
-	int err;
-
-	for (vid = vid_begin; vid <= vid_end; vid++) {
-		err = mlxsw_sp_port_add_vid(dev, 0, vid);
-		if (err)
-			goto err_port_add_vid;
-	}
-	return 0;
-
-err_port_add_vid:
-	for (vid--; vid >= vid_begin; vid--)
-		mlxsw_sp_port_kill_vid(dev, 0, vid);
-	return err;
-}
-
 static int __mlxsw_sp_port_vlans_set(struct mlxsw_sp_port *mlxsw_sp_port,
 				     u16 vid_begin, u16 vid_end, bool is_member,
 				     bool untagged)
@@ -533,57 +637,17 @@ static int __mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 				     u16 vid_begin, u16 vid_end,
 				     bool flag_untagged, bool flag_pvid)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct net_device *dev = mlxsw_sp_port->dev;
-	u16 vid, last_visited_vid, old_pvid;
-	enum mlxsw_reg_svfa_mt mt;
+	u16 vid, old_pvid;
 	int err;
 
-	/* In case this is invoked with BRIDGE_FLAGS_SELF and port is
-	 * not bridged, then packets ingressing through the port with
-	 * the specified VIDs will be directed to CPU.
-	 */
 	if (!mlxsw_sp_port->bridged)
-		return mlxsw_sp_port_add_vids(dev, vid_begin, vid_end);
-
-	for (vid = vid_begin; vid <= vid_end; vid++) {
-		if (!test_bit(vid, mlxsw_sp->active_fids)) {
-			err = mlxsw_sp_fid_create(mlxsw_sp, vid);
-			if (err) {
-				netdev_err(dev, "Failed to create FID=%d\n",
-					   vid);
-				return err;
-			}
-
-			/* When creating a FID, we set a VID to FID mapping
-			 * regardless of the port's mode.
-			 */
-			mt = MLXSW_REG_SVFA_MT_VID_TO_FID;
-			err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt,
-							   true, vid, vid);
-			if (err) {
-				netdev_err(dev, "Failed to create FID=VID=%d mapping\n",
-					   vid);
-				goto err_port_vid_to_fid_set;
-			}
-		}
-	}
-
-	/* Set FID mapping according to port's mode */
-	for (vid = vid_begin; vid <= vid_end; vid++) {
-		err = mlxsw_sp_port_fid_map(mlxsw_sp_port, vid);
-		if (err) {
-			netdev_err(dev, "Failed to map FID=%d", vid);
-			last_visited_vid = --vid;
-			goto err_port_fid_map;
-		}
-	}
+		return -EINVAL;
 
-	err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end,
-					true, false);
+	err = mlxsw_sp_port_fid_join(mlxsw_sp_port, vid_begin, vid_end);
 	if (err) {
-		netdev_err(dev, "Failed to configure flooding\n");
-		goto err_port_flood_set;
+		netdev_err(dev, "Failed to join FIDs\n");
+		return err;
 	}
 
 	err = __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end,
@@ -628,10 +692,6 @@ static int __mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	return 0;
 
-err_port_vid_to_fid_set:
-	mlxsw_sp_fid_destroy(mlxsw_sp, vid);
-	return err;
-
 err_port_stp_state_set:
 	for (vid = vid_begin; vid <= vid_end; vid++)
 		clear_bit(vid, mlxsw_sp_port->active_vlans);
@@ -641,13 +701,7 @@ err_port_pvid_set:
 	__mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, false,
 				  false);
 err_port_vlans_set:
-	__mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end, false,
-				  false);
-err_port_flood_set:
-	last_visited_vid = vid_end;
-err_port_fid_map:
-	for (vid = last_visited_vid; vid >= vid_begin; vid--)
-		mlxsw_sp_port_fid_unmap(mlxsw_sp_port, vid);
+	mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end);
 	return err;
 }
 
@@ -678,9 +732,10 @@ static enum mlxsw_reg_sfd_op mlxsw_sp_sfd_op(bool adding)
 			MLXSW_REG_SFD_OP_WRITE_REMOVE;
 }
 
-static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
-				   const char *mac, u16 fid, bool adding,
-				   bool dynamic)
+static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				     const char *mac, u16 fid, bool adding,
+				     enum mlxsw_reg_sfd_rec_action action,
+				     bool dynamic)
 {
 	char *sfd_pl;
 	int err;
@@ -691,14 +746,29 @@ static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 
 	mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
 	mlxsw_reg_sfd_uc_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic),
-			      mac, fid, MLXSW_REG_SFD_REC_ACTION_NOP,
-			      local_port);
+			      mac, fid, action, local_port);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
 	kfree(sfd_pl);
 
 	return err;
 }
 
+static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				   const char *mac, u16 fid, bool adding,
+				   bool dynamic)
+{
+	return __mlxsw_sp_port_fdb_uc_op(mlxsw_sp, local_port, mac, fid, adding,
+					 MLXSW_REG_SFD_REC_ACTION_NOP, dynamic);
+}
+
+int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
+			bool adding)
+{
+	return __mlxsw_sp_port_fdb_uc_op(mlxsw_sp, 0, mac, fid, adding,
+					 MLXSW_REG_SFD_REC_ACTION_FORWARD_IP_ROUTER,
+					 false);
+}
+
 static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id,
 				       const char *mac, u16 fid, u16 lag_vid,
 				       bool adding, bool dynamic)
@@ -903,6 +973,11 @@ static int mlxsw_sp_port_obj_add(struct net_device *dev,
 					      SWITCHDEV_OBJ_PORT_VLAN(obj),
 					      trans);
 		break;
+	case SWITCHDEV_OBJ_ID_IPV4_FIB:
+		err = mlxsw_sp_router_fib4_add(mlxsw_sp_port,
+					       SWITCHDEV_OBJ_IPV4_FIB(obj),
+					       trans);
+		break;
 	case SWITCHDEV_OBJ_ID_PORT_FDB:
 		err = mlxsw_sp_port_fdb_static_add(mlxsw_sp_port,
 						   SWITCHDEV_OBJ_PORT_FDB(obj),
@@ -921,21 +996,6 @@ static int mlxsw_sp_port_obj_add(struct net_device *dev,
 	return err;
 }
 
-static int mlxsw_sp_port_kill_vids(struct net_device *dev, u16 vid_begin,
-				   u16 vid_end)
-{
-	u16 vid;
-	int err;
-
-	for (vid = vid_begin; vid <= vid_end; vid++) {
-		err = mlxsw_sp_port_kill_vid(dev, 0, vid);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
 static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
 				     u16 vid_begin, u16 vid_end, bool init)
 {
@@ -943,12 +1003,8 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	u16 vid, pvid;
 	int err;
 
-	/* In case this is invoked with BRIDGE_FLAGS_SELF and port is
-	 * not bridged, then prevent packets ingressing through the
-	 * port with the specified VIDs from being trapped to CPU.
-	 */
 	if (!init && !mlxsw_sp_port->bridged)
-		return mlxsw_sp_port_kill_vids(dev, vid_begin, vid_end);
+		return -EINVAL;
 
 	err = __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end,
 					false, false);
@@ -970,21 +1026,7 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
 		}
 	}
 
-	err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end,
-					false, false);
-	if (err) {
-		netdev_err(dev, "Failed to clear flooding\n");
-		return err;
-	}
-
-	for (vid = vid_begin; vid <= vid_end; vid++) {
-		/* Remove FID mapping in case of Virtual mode */
-		err = mlxsw_sp_port_fid_unmap(mlxsw_sp_port, vid);
-		if (err) {
-			netdev_err(dev, "Failed to unmap FID=%d", vid);
-			return err;
-		}
-	}
+	mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end);
 
 out:
 	/* Changing activity bits only if HW operation succeded */
@@ -1081,6 +1123,10 @@ static int mlxsw_sp_port_obj_del(struct net_device *dev,
 		err = mlxsw_sp_port_vlans_del(mlxsw_sp_port,
 					      SWITCHDEV_OBJ_PORT_VLAN(obj));
 		break;
+	case SWITCHDEV_OBJ_ID_IPV4_FIB:
+		err = mlxsw_sp_router_fib4_del(mlxsw_sp_port,
+					       SWITCHDEV_OBJ_IPV4_FIB(obj));
+		break;
 	case SWITCHDEV_OBJ_ID_PORT_FDB:
 		err = mlxsw_sp_port_fdb_static_del(mlxsw_sp_port,
 						   SWITCHDEV_OBJ_PORT_FDB(obj));
@@ -1118,7 +1164,8 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port,
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_port *tmp;
-	u16 vport_fid = 0;
+	struct mlxsw_sp_fid *f;
+	u16 vport_fid;
 	char *sfd_pl;
 	char mac[ETH_ALEN];
 	u16 fid;
@@ -1133,12 +1180,8 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (!sfd_pl)
 		return -ENOMEM;
 
-	if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) {
-		u16 tmp;
-
-		tmp = mlxsw_sp_vport_vfid_get(mlxsw_sp_port);
-		vport_fid = mlxsw_sp_vfid_to_fid(tmp);
-	}
+	f = mlxsw_sp_vport_fid_get(mlxsw_sp_port);
+	vport_fid = f ? f->fid : 0;
 
 	mlxsw_reg_sfd_pack(sfd_pl, MLXSW_REG_SFD_OP_QUERY_DUMP, 0);
 	do {
@@ -1310,11 +1353,10 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	if (mlxsw_sp_fid_is_vfid(fid)) {
-		u16 vfid = mlxsw_sp_fid_to_vfid(fid);
 		struct mlxsw_sp_port *mlxsw_sp_vport;
 
-		mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_vfid(mlxsw_sp_port,
-								  vfid);
+		mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_fid(mlxsw_sp_port,
+								 fid);
 		if (!mlxsw_sp_vport) {
 			netdev_err(mlxsw_sp_port->dev, "Failed to find a matching vPort following FDB notification\n");
 			goto just_remove;
@@ -1370,11 +1412,10 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	if (mlxsw_sp_fid_is_vfid(fid)) {
-		u16 vfid = mlxsw_sp_fid_to_vfid(fid);
 		struct mlxsw_sp_port *mlxsw_sp_vport;
 
-		mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_vfid(mlxsw_sp_port,
-								  vfid);
+		mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_fid(mlxsw_sp_port,
+								 fid);
 		if (!mlxsw_sp_vport) {
 			netdev_err(mlxsw_sp_port->dev, "Failed to find a matching vPort following FDB notification\n");
 			goto just_remove;
@@ -1495,14 +1536,6 @@ static void mlxsw_sp_fdb_fini(struct mlxsw_sp *mlxsw_sp)
 	cancel_delayed_work_sync(&mlxsw_sp->fdb_notify.dw);
 }
 
-static void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp)
-{
-	u16 fid;
-
-	for_each_set_bit(fid, mlxsw_sp->active_fids, VLAN_N_VID)
-		mlxsw_sp_fid_destroy(mlxsw_sp, fid);
-}
-
 int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
 {
 	return mlxsw_sp_fdb_init(mlxsw_sp);
@@ -1511,7 +1544,6 @@ int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
 void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	mlxsw_sp_fdb_fini(mlxsw_sp);
-	mlxsw_sp_fids_fini(mlxsw_sp);
 }
 
 int mlxsw_sp_port_vlan_init(struct mlxsw_sp_port *mlxsw_sp_port)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 3842eab9449a..25f658b3849a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -316,7 +316,10 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
 		}
 	}
 	mlxsw_sx_txhdr_construct(skb, &tx_info);
-	len = skb->len;
+	/* TX header is consumed by HW on the way so we shouldn't count its
+	 * bytes as being sent.
+	 */
+	len = skb->len - MLXSW_TXHDR_LEN;
 	/* Due to a race we might fail here because of a full queue. In that
 	 * unlikely case we simply drop the packet.
 	 */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 53a9550be75e..470d7696e9fe 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -54,6 +54,11 @@ enum {
 	MLXSW_TRAP_ID_IGMP_V2_REPORT = 0x32,
 	MLXSW_TRAP_ID_IGMP_V2_LEAVE = 0x33,
 	MLXSW_TRAP_ID_IGMP_V3_REPORT = 0x34,
+	MLXSW_TRAP_ID_ARPBC = 0x50,
+	MLXSW_TRAP_ID_ARPUC = 0x51,
+	MLXSW_TRAP_ID_IP2ME = 0x5F,
+	MLXSW_TRAP_ID_RTR_INGRESS0 = 0x70,
+	MLXSW_TRAP_ID_HOST_MISS_IPV4 = 0x90,
 
 	MLXSW_TRAP_ID_MAX = 0x1FF
 };
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index e744acc18ef4..690635660195 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -63,7 +63,7 @@
 #define NFP_NET_POLL_TIMEOUT	5
 
 /* Bar allocation */
-#define NFP_NET_CRTL_BAR	0
+#define NFP_NET_CTRL_BAR	0
 #define NFP_NET_Q0_BAR		2
 #define NFP_NET_Q1_BAR		4	/* OBSOLETE */
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index fa47c14c743a..1e74b911accb 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1845,13 +1845,14 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn)
 }
 
 /**
- * nfp_net_write_mac_addr() - Write mac address to device registers
+ * nfp_net_write_mac_addr() - Write mac address to the device control BAR
  * @nn:      NFP Net device to reconfigure
- * @mac:     Six-byte MAC address to be written
  *
- * We do a bit of byte swapping dance because firmware is LE.
+ * Writes the MAC address from the netdev to the device control BAR.  Does not
+ * perform the required reconfig.  We do a bit of byte swapping dance because
+ * firmware is LE.
  */
-static void nfp_net_write_mac_addr(struct nfp_net *nn, const u8 *mac)
+static void nfp_net_write_mac_addr(struct nfp_net *nn)
 {
 	nn_writel(nn, NFP_NET_CFG_MACADDR + 0,
 		  get_unaligned_be32(nn->netdev->dev_addr));
@@ -1952,7 +1953,7 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
 	nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->num_rx_rings == 64 ?
 		  0xffffffffffffffffULL : ((u64)1 << nn->num_rx_rings) - 1);
 
-	nfp_net_write_mac_addr(nn, nn->netdev->dev_addr);
+	nfp_net_write_mac_addr(nn);
 
 	nn_writel(nn, NFP_NET_CFG_MTU, nn->netdev->mtu);
 	nn_writel(nn, NFP_NET_CFG_FLBUFSZ, nn->fl_bufsz);
@@ -1979,7 +1980,7 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
 	if (nn->ctrl & NFP_NET_CFG_CTRL_VXLAN) {
 		memset(&nn->vxlan_ports, 0, sizeof(nn->vxlan_ports));
 		memset(&nn->vxlan_usecnt, 0, sizeof(nn->vxlan_usecnt));
-		vxlan_get_rx_port(nn->netdev);
+		udp_tunnel_get_rx_info(nn->netdev);
 	}
 
 	return err;
@@ -2015,7 +2016,7 @@ static void nfp_net_open_stack(struct nfp_net *nn)
 
 	netif_tx_wake_all_queues(nn->netdev);
 
-	enable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
+	enable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
 	nfp_net_read_link_status(nn);
 }
 
@@ -2044,7 +2045,7 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 				      NFP_NET_IRQ_LSC_IDX, nn->lsc_handler);
 	if (err)
 		goto err_free_exn;
-	disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
+	disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
 
 	nn->rx_rings = kcalloc(nn->num_rx_rings, sizeof(*nn->rx_rings),
 			       GFP_KERNEL);
@@ -2133,7 +2134,7 @@ static void nfp_net_close_stack(struct nfp_net *nn)
 {
 	unsigned int r;
 
-	disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
+	disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
 	netif_carrier_off(nn->netdev);
 	nn->link_up = false;
 
@@ -2551,26 +2552,32 @@ static int nfp_net_find_vxlan_idx(struct nfp_net *nn, __be16 port)
 }
 
 static void nfp_net_add_vxlan_port(struct net_device *netdev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	int idx;
 
-	idx = nfp_net_find_vxlan_idx(nn, port);
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
+	idx = nfp_net_find_vxlan_idx(nn, ti->port);
 	if (idx == -ENOSPC)
 		return;
 
 	if (!nn->vxlan_usecnt[idx]++)
-		nfp_net_set_vxlan_port(nn, idx, port);
+		nfp_net_set_vxlan_port(nn, idx, ti->port);
 }
 
 static void nfp_net_del_vxlan_port(struct net_device *netdev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	int idx;
 
-	idx = nfp_net_find_vxlan_idx(nn, port);
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
+	idx = nfp_net_find_vxlan_idx(nn, ti->port);
 	if (!nn->vxlan_usecnt[idx] || idx == -ENOSPC)
 		return;
 
@@ -2589,8 +2596,8 @@ static const struct net_device_ops nfp_net_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_set_features	= nfp_net_set_features,
 	.ndo_features_check	= nfp_net_features_check,
-	.ndo_add_vxlan_port     = nfp_net_add_vxlan_port,
-	.ndo_del_vxlan_port     = nfp_net_del_vxlan_port,
+	.ndo_udp_tunnel_add	= nfp_net_add_vxlan_port,
+	.ndo_udp_tunnel_del	= nfp_net_del_vxlan_port,
 };
 
 /**
@@ -2733,7 +2740,7 @@ int nfp_net_netdev_init(struct net_device *netdev)
 	nn->cap = nn_readl(nn, NFP_NET_CFG_CAP);
 	nn->max_mtu = nn_readl(nn, NFP_NET_CFG_MAX_MTU);
 
-	nfp_net_write_mac_addr(nn, nn->netdev->dev_addr);
+	nfp_net_write_mac_addr(nn);
 
 	/* Set default MTU and Freelist buffer size */
 	if (nn->max_mtu < NFP_NET_DEFAULT_MTU)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index ccfef1f17627..7d7933d00b8f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -605,6 +605,7 @@ static int nfp_net_set_coalesce(struct net_device *netdev,
 
 static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.get_drvinfo		= nfp_net_get_drvinfo,
+	.get_link		= ethtool_op_get_link,
 	.get_ringparam		= nfp_net_get_ringparam,
 	.set_ringparam		= nfp_net_set_ringparam,
 	.get_strings		= nfp_net_get_strings,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
index e2b22b8a20f1..37abef016a0a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
@@ -124,11 +124,11 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	 * first NFP_NET_CFG_BAR_SZ of the BAR.  This keeps the code
 	 * the identical for PF and VF drivers.
 	 */
-	ctrl_bar = ioremap_nocache(pci_resource_start(pdev, NFP_NET_CRTL_BAR),
+	ctrl_bar = ioremap_nocache(pci_resource_start(pdev, NFP_NET_CTRL_BAR),
 				   NFP_NET_CFG_BAR_SZ);
 	if (!ctrl_bar) {
 		dev_err(&pdev->dev,
-			"Failed to map resource %d\n", NFP_NET_CRTL_BAR);
+			"Failed to map resource %d\n", NFP_NET_CTRL_BAR);
 		err = -EIO;
 		goto err_pci_regions;
 	}
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index b1ce7aaa8f8b..4d4ecba0aad9 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -425,7 +425,6 @@ struct netdata_local {
 	unsigned int		last_tx_idx;
 	unsigned int		num_used_tx_buffs;
 	struct mii_bus		*mii_bus;
-	struct phy_device	*phy_dev;
 	struct clk		*clk;
 	dma_addr_t		dma_buff_base_p;
 	void			*dma_buff_base_v;
@@ -750,7 +749,7 @@ static int lpc_mdio_reset(struct mii_bus *bus)
 static void lpc_handle_link_change(struct net_device *ndev)
 {
 	struct netdata_local *pldat = netdev_priv(ndev);
-	struct phy_device *phydev = pldat->phy_dev;
+	struct phy_device *phydev = ndev->phydev;
 	unsigned long flags;
 
 	bool status_change = false;
@@ -814,7 +813,6 @@ static int lpc_mii_probe(struct net_device *ndev)
 	pldat->link = 0;
 	pldat->speed = 0;
 	pldat->duplex = -1;
-	pldat->phy_dev = phydev;
 
 	phy_attached_info(phydev);
 
@@ -1048,8 +1046,8 @@ static int lpc_eth_close(struct net_device *ndev)
 	napi_disable(&pldat->napi);
 	netif_stop_queue(ndev);
 
-	if (pldat->phy_dev)
-		phy_stop(pldat->phy_dev);
+	if (ndev->phydev)
+		phy_stop(ndev->phydev);
 
 	spin_lock_irqsave(&pldat->lock, flags);
 	__lpc_eth_reset(pldat);
@@ -1185,8 +1183,7 @@ static void lpc_eth_set_multicast_list(struct net_device *ndev)
 
 static int lpc_eth_ioctl(struct net_device *ndev, struct ifreq *req, int cmd)
 {
-	struct netdata_local *pldat = netdev_priv(ndev);
-	struct phy_device *phydev = pldat->phy_dev;
+	struct phy_device *phydev = ndev->phydev;
 
 	if (!netif_running(ndev))
 		return -EINVAL;
@@ -1207,14 +1204,14 @@ static int lpc_eth_open(struct net_device *ndev)
 	__lpc_eth_clock_enable(pldat, true);
 
 	/* Suspended PHY makes LPC ethernet core block, so resume now */
-	phy_resume(pldat->phy_dev);
+	phy_resume(ndev->phydev);
 
 	/* Reset and initialize */
 	__lpc_eth_reset(pldat);
 	__lpc_eth_init(pldat);
 
 	/* schedule a link state check */
-	phy_start(pldat->phy_dev);
+	phy_start(ndev->phydev);
 	netif_start_queue(ndev);
 	napi_enable(&pldat->napi);
 
@@ -1247,37 +1244,13 @@ static void lpc_eth_ethtool_setmsglevel(struct net_device *ndev, u32 level)
 	pldat->msg_enable = level;
 }
 
-static int lpc_eth_ethtool_getsettings(struct net_device *ndev,
-	struct ethtool_cmd *cmd)
-{
-	struct netdata_local *pldat = netdev_priv(ndev);
-	struct phy_device *phydev = pldat->phy_dev;
-
-	if (!phydev)
-		return -EOPNOTSUPP;
-
-	return phy_ethtool_gset(phydev, cmd);
-}
-
-static int lpc_eth_ethtool_setsettings(struct net_device *ndev,
-	struct ethtool_cmd *cmd)
-{
-	struct netdata_local *pldat = netdev_priv(ndev);
-	struct phy_device *phydev = pldat->phy_dev;
-
-	if (!phydev)
-		return -EOPNOTSUPP;
-
-	return phy_ethtool_sset(phydev, cmd);
-}
-
 static const struct ethtool_ops lpc_eth_ethtool_ops = {
 	.get_drvinfo	= lpc_eth_ethtool_getdrvinfo,
-	.get_settings	= lpc_eth_ethtool_getsettings,
-	.set_settings	= lpc_eth_ethtool_setsettings,
 	.get_msglevel	= lpc_eth_ethtool_getmsglevel,
 	.set_msglevel	= lpc_eth_ethtool_setmsglevel,
 	.get_link	= ethtool_op_get_link,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 static const struct net_device_ops lpc_netdev_ops = {
@@ -1460,7 +1433,7 @@ static int lpc_eth_drv_probe(struct platform_device *pdev)
 	netdev_info(ndev, "LPC mac at 0x%08x irq %d\n",
 	       res->start, ndev->irq);
 
-	phydev = pldat->phy_dev;
+	phydev = ndev->phydev;
 
 	device_init_wakeup(&pdev->dev, 1);
 	device_set_wakeup_enable(&pdev->dev, 0);
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index 680d8c736d2b..6ba48406899e 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -54,16 +54,6 @@ config QLCNIC_DCB
 	  mode of DCB is supported. PG and PFC values are related only
 	  to Tx.
 
-config QLCNIC_VXLAN
-	bool "Virtual eXtensible Local Area Network (VXLAN) offload support"
-	default n
-	depends on QLCNIC && VXLAN && !(QLCNIC=y && VXLAN=m)
-	---help---
-	  This enables hardware offload support for VXLAN protocol over QLogic's
-	  84XX series adapters.
-	  Say Y here if you want to enable hardware offload support for
-	  Virtual eXtensible Local Area Network (VXLAN) in the driver.
-
 config QLCNIC_HWMON
 	bool "QLOGIC QLCNIC 82XX and 83XX family HWMON support"
 	depends on QLCNIC && HWMON && !(QLCNIC=y && HWMON=m)
@@ -114,24 +104,4 @@ config QEDE
 	---help---
 	  This enables the support for ...
 
-config QEDE_VXLAN
-	bool "Virtual eXtensible Local Area Network support"
-	default n
-	depends on QEDE && VXLAN && !(QEDE=y && VXLAN=m)
-	---help---
-	  This enables hardware offload support for VXLAN protocol over
-	  qede module. Say Y here if you want to enable hardware offload
-	  support for Virtual eXtensible Local Area Network (VXLAN)
-	  in the driver.
-
-config QEDE_GENEVE
-	bool "Generic Network Virtualization Encapsulation (GENEVE) support"
-	depends on QEDE && GENEVE && !(QEDE=y && GENEVE=m)
-	---help---
-	  This allows one to create GENEVE virtual interfaces that provide
-	  Layer 2 Networks over Layer 3 Networks. GENEVE is often used
-	  to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to enable hardware offload support for
-	  Generic Network Virtualization Encapsulation (GENEVE) in the driver.
-
 endif # NET_VENDOR_QLOGIC
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 9a63df1184f1..35e53771533f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -489,8 +489,8 @@ struct qed_dev {
 
 	u32				int_mode;
 	enum qed_coalescing_mode	int_coalescing_mode;
-	u8				rx_coalesce_usecs;
-	u8				tx_coalesce_usecs;
+	u16				rx_coalesce_usecs;
+	u16				tx_coalesce_usecs;
 
 	/* Start Bar offset of first hwfn */
 	void __iomem			*regview;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index d85b7ba8cb9a..1c35f376143e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -850,7 +850,7 @@ static int qed_cxt_src_t2_alloc(struct qed_hwfn *p_hwfn)
 			val = 0;
 		entries[j].next = cpu_to_be64(val);
 
-		conn_num -= ent_per_page;
+		conn_num -= ent_num;
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 21ec1c2df2c7..d0dc28f93c0e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <linux/bitops.h>
+#include <linux/dcbnl.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -18,6 +19,9 @@
 #include "qed_dcbx.h"
 #include "qed_hsi.h"
 #include "qed_sp.h"
+#ifdef CONFIG_DCB
+#include <linux/qed/qed_eth_if.h>
+#endif
 
 #define QED_DCBX_MAX_MIB_READ_TRY       (100)
 #define QED_ETH_TYPE_DEFAULT            (0)
@@ -252,7 +256,7 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn,
 		if (p_data->arr[type].update)
 			continue;
 
-		enable = (type == DCBX_PROTOCOL_ETH) ? false : dcbx_enabled;
+		enable = !(type == DCBX_PROTOCOL_ETH);
 		qed_dcbx_update_app_info(p_data, p_hwfn, enable, true,
 					 priority, tc, type);
 	}
@@ -351,6 +355,293 @@ qed_dcbx_copy_mib(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
+#ifdef CONFIG_DCB
+static void
+qed_dcbx_get_priority_info(struct qed_hwfn *p_hwfn,
+			   struct qed_dcbx_app_prio *p_prio,
+			   struct qed_dcbx_results *p_results)
+{
+	u8 val;
+
+	p_prio->roce = QED_DCBX_INVALID_PRIORITY;
+	p_prio->roce_v2 = QED_DCBX_INVALID_PRIORITY;
+	p_prio->iscsi = QED_DCBX_INVALID_PRIORITY;
+	p_prio->fcoe = QED_DCBX_INVALID_PRIORITY;
+
+	if (p_results->arr[DCBX_PROTOCOL_ROCE].update &&
+	    p_results->arr[DCBX_PROTOCOL_ROCE].enable)
+		p_prio->roce = p_results->arr[DCBX_PROTOCOL_ROCE].priority;
+
+	if (p_results->arr[DCBX_PROTOCOL_ROCE_V2].update &&
+	    p_results->arr[DCBX_PROTOCOL_ROCE_V2].enable) {
+		val = p_results->arr[DCBX_PROTOCOL_ROCE_V2].priority;
+		p_prio->roce_v2 = val;
+	}
+
+	if (p_results->arr[DCBX_PROTOCOL_ISCSI].update &&
+	    p_results->arr[DCBX_PROTOCOL_ISCSI].enable)
+		p_prio->iscsi = p_results->arr[DCBX_PROTOCOL_ISCSI].priority;
+
+	if (p_results->arr[DCBX_PROTOCOL_FCOE].update &&
+	    p_results->arr[DCBX_PROTOCOL_FCOE].enable)
+		p_prio->fcoe = p_results->arr[DCBX_PROTOCOL_FCOE].priority;
+
+	if (p_results->arr[DCBX_PROTOCOL_ETH].update &&
+	    p_results->arr[DCBX_PROTOCOL_ETH].enable)
+		p_prio->eth = p_results->arr[DCBX_PROTOCOL_ETH].priority;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+		   "Priorities: iscsi %d, roce %d, roce v2 %d, fcoe %d, eth %d\n",
+		   p_prio->iscsi, p_prio->roce, p_prio->roce_v2, p_prio->fcoe,
+		   p_prio->eth);
+}
+
+static void
+qed_dcbx_get_app_data(struct qed_hwfn *p_hwfn,
+		      struct dcbx_app_priority_feature *p_app,
+		      struct dcbx_app_priority_entry *p_tbl,
+		      struct qed_dcbx_params *p_params)
+{
+	struct qed_app_entry *entry;
+	u8 pri_map;
+	int i;
+
+	p_params->app_willing = QED_MFW_GET_FIELD(p_app->flags,
+						  DCBX_APP_WILLING);
+	p_params->app_valid = QED_MFW_GET_FIELD(p_app->flags, DCBX_APP_ENABLED);
+	p_params->app_error = QED_MFW_GET_FIELD(p_app->flags, DCBX_APP_ERROR);
+	p_params->num_app_entries = QED_MFW_GET_FIELD(p_app->flags,
+						      DCBX_APP_NUM_ENTRIES);
+	for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &p_params->app_entry[i];
+		entry->ethtype = !(QED_MFW_GET_FIELD(p_tbl[i].entry,
+						     DCBX_APP_SF));
+		pri_map = QED_MFW_GET_FIELD(p_tbl[i].entry, DCBX_APP_PRI_MAP);
+		entry->prio = ffs(pri_map) - 1;
+		entry->proto_id = QED_MFW_GET_FIELD(p_tbl[i].entry,
+						    DCBX_APP_PROTOCOL_ID);
+		qed_dcbx_get_app_protocol_type(p_hwfn, p_tbl[i].entry,
+					       entry->proto_id,
+					       &entry->proto_type);
+	}
+
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+		   "APP params: willing %d, valid %d error = %d\n",
+		   p_params->app_willing, p_params->app_valid,
+		   p_params->app_error);
+}
+
+static void
+qed_dcbx_get_pfc_data(struct qed_hwfn *p_hwfn,
+		      u32 pfc, struct qed_dcbx_params *p_params)
+{
+	u8 pfc_map;
+
+	p_params->pfc.willing = QED_MFW_GET_FIELD(pfc, DCBX_PFC_WILLING);
+	p_params->pfc.max_tc = QED_MFW_GET_FIELD(pfc, DCBX_PFC_CAPS);
+	p_params->pfc.enabled = QED_MFW_GET_FIELD(pfc, DCBX_PFC_ENABLED);
+	pfc_map = QED_MFW_GET_FIELD(pfc, DCBX_PFC_PRI_EN_BITMAP);
+	p_params->pfc.prio[0] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_0);
+	p_params->pfc.prio[1] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_1);
+	p_params->pfc.prio[2] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_2);
+	p_params->pfc.prio[3] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_3);
+	p_params->pfc.prio[4] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_4);
+	p_params->pfc.prio[5] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_5);
+	p_params->pfc.prio[6] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_6);
+	p_params->pfc.prio[7] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_7);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+		   "PFC params: willing %d, pfc_bitmap %d\n",
+		   p_params->pfc.willing, pfc_map);
+}
+
+static void
+qed_dcbx_get_ets_data(struct qed_hwfn *p_hwfn,
+		      struct dcbx_ets_feature *p_ets,
+		      struct qed_dcbx_params *p_params)
+{
+	u32 bw_map[2], tsa_map[2], pri_map;
+	int i;
+
+	p_params->ets_willing = QED_MFW_GET_FIELD(p_ets->flags,
+						  DCBX_ETS_WILLING);
+	p_params->ets_enabled = QED_MFW_GET_FIELD(p_ets->flags,
+						  DCBX_ETS_ENABLED);
+	p_params->ets_cbs = QED_MFW_GET_FIELD(p_ets->flags, DCBX_ETS_CBS);
+	p_params->max_ets_tc = QED_MFW_GET_FIELD(p_ets->flags,
+						 DCBX_ETS_MAX_TCS);
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+		   "ETS params: willing %d, ets_cbs %d pri_tc_tbl_0 %x max_ets_tc %d\n",
+		   p_params->ets_willing,
+		   p_params->ets_cbs,
+		   p_ets->pri_tc_tbl[0], p_params->max_ets_tc);
+
+	/* 8 bit tsa and bw data corresponding to each of the 8 TC's are
+	 * encoded in a type u32 array of size 2.
+	 */
+	bw_map[0] = be32_to_cpu(p_ets->tc_bw_tbl[0]);
+	bw_map[1] = be32_to_cpu(p_ets->tc_bw_tbl[1]);
+	tsa_map[0] = be32_to_cpu(p_ets->tc_tsa_tbl[0]);
+	tsa_map[1] = be32_to_cpu(p_ets->tc_tsa_tbl[1]);
+	pri_map = be32_to_cpu(p_ets->pri_tc_tbl[0]);
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) {
+		p_params->ets_tc_bw_tbl[i] = ((u8 *)bw_map)[i];
+		p_params->ets_tc_tsa_tbl[i] = ((u8 *)tsa_map)[i];
+		p_params->ets_pri_tc_tbl[i] = QED_DCBX_PRIO2TC(pri_map, i);
+		DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+			   "elem %d  bw_tbl %x tsa_tbl %x\n",
+			   i, p_params->ets_tc_bw_tbl[i],
+			   p_params->ets_tc_tsa_tbl[i]);
+	}
+}
+
+static void
+qed_dcbx_get_common_params(struct qed_hwfn *p_hwfn,
+			   struct dcbx_app_priority_feature *p_app,
+			   struct dcbx_app_priority_entry *p_tbl,
+			   struct dcbx_ets_feature *p_ets,
+			   u32 pfc, struct qed_dcbx_params *p_params)
+{
+	qed_dcbx_get_app_data(p_hwfn, p_app, p_tbl, p_params);
+	qed_dcbx_get_ets_data(p_hwfn, p_ets, p_params);
+	qed_dcbx_get_pfc_data(p_hwfn, pfc, p_params);
+}
+
+static void
+qed_dcbx_get_local_params(struct qed_hwfn *p_hwfn,
+			  struct qed_ptt *p_ptt, struct qed_dcbx_get *params)
+{
+	struct dcbx_features *p_feat;
+
+	p_feat = &p_hwfn->p_dcbx_info->local_admin.features;
+	qed_dcbx_get_common_params(p_hwfn, &p_feat->app,
+				   p_feat->app.app_pri_tbl, &p_feat->ets,
+				   p_feat->pfc, &params->local.params);
+	params->local.valid = true;
+}
+
+static void
+qed_dcbx_get_remote_params(struct qed_hwfn *p_hwfn,
+			   struct qed_ptt *p_ptt, struct qed_dcbx_get *params)
+{
+	struct dcbx_features *p_feat;
+
+	p_feat = &p_hwfn->p_dcbx_info->remote.features;
+	qed_dcbx_get_common_params(p_hwfn, &p_feat->app,
+				   p_feat->app.app_pri_tbl, &p_feat->ets,
+				   p_feat->pfc, &params->remote.params);
+	params->remote.valid = true;
+}
+
+static void
+qed_dcbx_get_operational_params(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt,
+				struct qed_dcbx_get *params)
+{
+	struct qed_dcbx_operational_params *p_operational;
+	struct qed_dcbx_results *p_results;
+	struct dcbx_features *p_feat;
+	bool enabled, err;
+	u32 flags;
+	bool val;
+
+	flags = p_hwfn->p_dcbx_info->operational.flags;
+
+	/* If DCBx version is non zero, then negotiation
+	 * was successfuly performed
+	 */
+	p_operational = &params->operational;
+	enabled = !!(QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION) !=
+		     DCBX_CONFIG_VERSION_DISABLED);
+	if (!enabled) {
+		p_operational->enabled = enabled;
+		p_operational->valid = false;
+		return;
+	}
+
+	p_feat = &p_hwfn->p_dcbx_info->operational.features;
+	p_results = &p_hwfn->p_dcbx_info->results;
+
+	val = !!(QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION) ==
+		 DCBX_CONFIG_VERSION_IEEE);
+	p_operational->ieee = val;
+	val = !!(QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION) ==
+		 DCBX_CONFIG_VERSION_CEE);
+	p_operational->cee = val;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB, "Version support: ieee %d, cee %d\n",
+		   p_operational->ieee, p_operational->cee);
+
+	qed_dcbx_get_common_params(p_hwfn, &p_feat->app,
+				   p_feat->app.app_pri_tbl, &p_feat->ets,
+				   p_feat->pfc, &params->operational.params);
+	qed_dcbx_get_priority_info(p_hwfn, &p_operational->app_prio, p_results);
+	err = QED_MFW_GET_FIELD(p_feat->app.flags, DCBX_APP_ERROR);
+	p_operational->err = err;
+	p_operational->enabled = enabled;
+	p_operational->valid = true;
+}
+
+static void
+qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn,
+			       struct qed_ptt *p_ptt,
+			       struct qed_dcbx_get *params)
+{
+	struct lldp_config_params_s *p_local;
+
+	p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE];
+
+	memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id,
+	       ARRAY_SIZE(p_local->local_chassis_id));
+	memcpy(params->lldp_local.local_port_id, p_local->local_port_id,
+	       ARRAY_SIZE(p_local->local_port_id));
+}
+
+static void
+qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt,
+				struct qed_dcbx_get *params)
+{
+	struct lldp_status_params_s *p_remote;
+
+	p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE];
+
+	memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id,
+	       ARRAY_SIZE(p_remote->peer_chassis_id));
+	memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id,
+	       ARRAY_SIZE(p_remote->peer_port_id));
+}
+
+static int
+qed_dcbx_get_params(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+		    struct qed_dcbx_get *p_params,
+		    enum qed_mib_read_type type)
+{
+	switch (type) {
+	case QED_DCBX_REMOTE_MIB:
+		qed_dcbx_get_remote_params(p_hwfn, p_ptt, p_params);
+		break;
+	case QED_DCBX_LOCAL_MIB:
+		qed_dcbx_get_local_params(p_hwfn, p_ptt, p_params);
+		break;
+	case QED_DCBX_OPERATIONAL_MIB:
+		qed_dcbx_get_operational_params(p_hwfn, p_ptt, p_params);
+		break;
+	case QED_DCBX_REMOTE_LLDP_MIB:
+		qed_dcbx_get_remote_lldp_params(p_hwfn, p_ptt, p_params);
+		break;
+	case QED_DCBX_LOCAL_LLDP_MIB:
+		qed_dcbx_get_local_lldp_params(p_hwfn, p_ptt, p_params);
+		break;
+	default:
+		DP_ERR(p_hwfn, "MIB read err, unknown mib type %d\n", type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+#endif
+
 static int
 qed_dcbx_read_local_lldp_mib(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
@@ -561,3 +852,1333 @@ void qed_dcbx_set_pf_update_params(struct qed_dcbx_results *p_src,
 	p_dcb_data = &p_dest->eth_dcb_data;
 	qed_dcbx_update_protocol_data(p_dcb_data, p_src, DCBX_PROTOCOL_ETH);
 }
+
+#ifdef CONFIG_DCB
+static int qed_dcbx_query_params(struct qed_hwfn *p_hwfn,
+				 struct qed_dcbx_get *p_get,
+				 enum qed_mib_read_type type)
+{
+	struct qed_ptt *p_ptt;
+	int rc;
+
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt)
+		return -EBUSY;
+
+	rc = qed_dcbx_read_mib(p_hwfn, p_ptt, type);
+	if (rc)
+		goto out;
+
+	rc = qed_dcbx_get_params(p_hwfn, p_ptt, p_get, type);
+
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
+	return rc;
+}
+
+static void
+qed_dcbx_set_pfc_data(struct qed_hwfn *p_hwfn,
+		      u32 *pfc, struct qed_dcbx_params *p_params)
+{
+	u8 pfc_map = 0;
+	int i;
+
+	if (p_params->pfc.willing)
+		*pfc |= DCBX_PFC_WILLING_MASK;
+	else
+		*pfc &= ~DCBX_PFC_WILLING_MASK;
+
+	if (p_params->pfc.enabled)
+		*pfc |= DCBX_PFC_ENABLED_MASK;
+	else
+		*pfc &= ~DCBX_PFC_ENABLED_MASK;
+
+	*pfc &= ~DCBX_PFC_CAPS_MASK;
+	*pfc |= (u32)p_params->pfc.max_tc << DCBX_PFC_CAPS_SHIFT;
+
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++)
+		if (p_params->pfc.prio[i])
+			pfc_map |= BIT(i);
+
+	*pfc |= (pfc_map << DCBX_PFC_PRI_EN_BITMAP_SHIFT);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB, "pfc = 0x%x\n", *pfc);
+}
+
+static void
+qed_dcbx_set_ets_data(struct qed_hwfn *p_hwfn,
+		      struct dcbx_ets_feature *p_ets,
+		      struct qed_dcbx_params *p_params)
+{
+	u8 *bw_map, *tsa_map;
+	u32 val;
+	int i;
+
+	if (p_params->ets_willing)
+		p_ets->flags |= DCBX_ETS_WILLING_MASK;
+	else
+		p_ets->flags &= ~DCBX_ETS_WILLING_MASK;
+
+	if (p_params->ets_cbs)
+		p_ets->flags |= DCBX_ETS_CBS_MASK;
+	else
+		p_ets->flags &= ~DCBX_ETS_CBS_MASK;
+
+	if (p_params->ets_enabled)
+		p_ets->flags |= DCBX_ETS_ENABLED_MASK;
+	else
+		p_ets->flags &= ~DCBX_ETS_ENABLED_MASK;
+
+	p_ets->flags &= ~DCBX_ETS_MAX_TCS_MASK;
+	p_ets->flags |= (u32)p_params->max_ets_tc << DCBX_ETS_MAX_TCS_SHIFT;
+
+	bw_map = (u8 *)&p_ets->tc_bw_tbl[0];
+	tsa_map = (u8 *)&p_ets->tc_tsa_tbl[0];
+	p_ets->pri_tc_tbl[0] = 0;
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) {
+		bw_map[i] = p_params->ets_tc_bw_tbl[i];
+		tsa_map[i] = p_params->ets_tc_tsa_tbl[i];
+		/* Copy the priority value to the corresponding 4 bits in the
+		 * traffic class table.
+		 */
+		val = (((u32)p_params->ets_pri_tc_tbl[i]) << ((7 - i) * 4));
+		p_ets->pri_tc_tbl[0] |= val;
+	}
+	p_ets->pri_tc_tbl[0] = cpu_to_be32(p_ets->pri_tc_tbl[0]);
+	for (i = 0; i < 2; i++) {
+		p_ets->tc_bw_tbl[i] = cpu_to_be32(p_ets->tc_bw_tbl[i]);
+		p_ets->tc_tsa_tbl[i] = cpu_to_be32(p_ets->tc_tsa_tbl[i]);
+	}
+}
+
+static void
+qed_dcbx_set_app_data(struct qed_hwfn *p_hwfn,
+		      struct dcbx_app_priority_feature *p_app,
+		      struct qed_dcbx_params *p_params)
+{
+	u32 *entry;
+	int i;
+
+	if (p_params->app_willing)
+		p_app->flags |= DCBX_APP_WILLING_MASK;
+	else
+		p_app->flags &= ~DCBX_APP_WILLING_MASK;
+
+	if (p_params->app_valid)
+		p_app->flags |= DCBX_APP_ENABLED_MASK;
+	else
+		p_app->flags &= ~DCBX_APP_ENABLED_MASK;
+
+	p_app->flags &= ~DCBX_APP_NUM_ENTRIES_MASK;
+	p_app->flags |= (u32)p_params->num_app_entries <<
+	    DCBX_APP_NUM_ENTRIES_SHIFT;
+
+	for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &p_app->app_pri_tbl[i].entry;
+		*entry &= ~DCBX_APP_SF_MASK;
+		if (p_params->app_entry[i].ethtype)
+			*entry |= ((u32)DCBX_APP_SF_ETHTYPE <<
+				   DCBX_APP_SF_SHIFT);
+		else
+			*entry |= ((u32)DCBX_APP_SF_PORT << DCBX_APP_SF_SHIFT);
+		*entry &= ~DCBX_APP_PROTOCOL_ID_MASK;
+		*entry |= ((u32)p_params->app_entry[i].proto_id <<
+			   DCBX_APP_PROTOCOL_ID_SHIFT);
+		*entry &= ~DCBX_APP_PRI_MAP_MASK;
+		*entry |= ((u32)(p_params->app_entry[i].prio) <<
+			   DCBX_APP_PRI_MAP_SHIFT);
+	}
+}
+
+static void
+qed_dcbx_set_local_params(struct qed_hwfn *p_hwfn,
+			  struct dcbx_local_params *local_admin,
+			  struct qed_dcbx_set *params)
+{
+	local_admin->flags = 0;
+	memcpy(&local_admin->features,
+	       &p_hwfn->p_dcbx_info->operational.features,
+	       sizeof(local_admin->features));
+
+	if (params->enabled)
+		local_admin->config = params->ver_num;
+	else
+		local_admin->config = DCBX_CONFIG_VERSION_DISABLED;
+
+	if (params->override_flags & QED_DCBX_OVERRIDE_PFC_CFG)
+		qed_dcbx_set_pfc_data(p_hwfn, &local_admin->features.pfc,
+				      &params->config.params);
+
+	if (params->override_flags & QED_DCBX_OVERRIDE_ETS_CFG)
+		qed_dcbx_set_ets_data(p_hwfn, &local_admin->features.ets,
+				      &params->config.params);
+
+	if (params->override_flags & QED_DCBX_OVERRIDE_APP_CFG)
+		qed_dcbx_set_app_data(p_hwfn, &local_admin->features.app,
+				      &params->config.params);
+}
+
+int qed_dcbx_config_params(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			   struct qed_dcbx_set *params, bool hw_commit)
+{
+	struct dcbx_local_params local_admin;
+	struct qed_dcbx_mib_meta_data data;
+	u32 resp = 0, param = 0;
+	int rc = 0;
+
+	if (!hw_commit) {
+		memcpy(&p_hwfn->p_dcbx_info->set, params,
+		       sizeof(struct qed_dcbx_set));
+		return 0;
+	}
+
+	/* clear set-parmas cache */
+	memset(&p_hwfn->p_dcbx_info->set, 0, sizeof(p_hwfn->p_dcbx_info->set));
+
+	memset(&local_admin, 0, sizeof(local_admin));
+	qed_dcbx_set_local_params(p_hwfn, &local_admin, params);
+
+	data.addr = p_hwfn->mcp_info->port_addr +
+	    offsetof(struct public_port, local_admin_dcbx_mib);
+	data.local_admin = &local_admin;
+	data.size = sizeof(struct dcbx_local_params);
+	qed_memcpy_to(p_hwfn, p_ptt, data.addr, data.local_admin, data.size);
+
+	rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_SET_DCBX,
+			 1 << DRV_MB_PARAM_LLDP_SEND_SHIFT, &resp, &param);
+	if (rc)
+		DP_NOTICE(p_hwfn, "Failed to send DCBX update request\n");
+
+	return rc;
+}
+
+int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn,
+			       struct qed_dcbx_set *params)
+{
+	struct qed_dcbx_get *dcbx_info;
+	int rc;
+
+	if (p_hwfn->p_dcbx_info->set.config.valid) {
+		memcpy(params, &p_hwfn->p_dcbx_info->set,
+		       sizeof(struct qed_dcbx_set));
+		return 0;
+	}
+
+	dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_KERNEL);
+	if (!dcbx_info) {
+		DP_ERR(p_hwfn, "Failed to allocate struct qed_dcbx_info\n");
+		return -ENOMEM;
+	}
+
+	rc = qed_dcbx_query_params(p_hwfn, dcbx_info, QED_DCBX_OPERATIONAL_MIB);
+	if (rc) {
+		kfree(dcbx_info);
+		return rc;
+	}
+
+	p_hwfn->p_dcbx_info->set.override_flags = 0;
+	p_hwfn->p_dcbx_info->set.ver_num = DCBX_CONFIG_VERSION_DISABLED;
+	if (dcbx_info->operational.cee)
+		p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_CEE;
+	if (dcbx_info->operational.ieee)
+		p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_IEEE;
+
+	p_hwfn->p_dcbx_info->set.enabled = dcbx_info->operational.enabled;
+	memcpy(&p_hwfn->p_dcbx_info->set.config.params,
+	       &dcbx_info->operational.params,
+	       sizeof(struct qed_dcbx_admin_params));
+	p_hwfn->p_dcbx_info->set.config.valid = true;
+
+	memcpy(params, &p_hwfn->p_dcbx_info->set, sizeof(struct qed_dcbx_set));
+
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static struct qed_dcbx_get *qed_dcbnl_get_dcbx(struct qed_hwfn *hwfn,
+					       enum qed_mib_read_type type)
+{
+	struct qed_dcbx_get *dcbx_info;
+
+	dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_KERNEL);
+	if (!dcbx_info) {
+		DP_ERR(hwfn->cdev, "Failed to allocate memory for dcbx_info\n");
+		return NULL;
+	}
+
+	if (qed_dcbx_query_params(hwfn, dcbx_info, type)) {
+		kfree(dcbx_info);
+		return NULL;
+	}
+
+	if ((type == QED_DCBX_OPERATIONAL_MIB) &&
+	    !dcbx_info->operational.enabled) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational\n");
+		kfree(dcbx_info);
+		return NULL;
+	}
+
+	return dcbx_info;
+}
+
+static u8 qed_dcbnl_getstate(struct qed_dev *cdev)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	bool enabled;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return 0;
+
+	enabled = dcbx_info->operational.enabled;
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "DCB state = %d\n", enabled);
+	kfree(dcbx_info);
+
+	return enabled;
+}
+
+static u8 qed_dcbnl_setstate(struct qed_dev *cdev, u8 state)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "DCB state = %d\n", state);
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return 1;
+
+	dcbx_set.enabled = !!state;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return 1;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc ? 1 : 0;
+}
+
+static void qed_dcbnl_getpgtccfgtx(struct qed_dev *cdev, int tc, u8 *prio_type,
+				   u8 *pgid, u8 *bw_pct, u8 *up_map)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "tc = %d\n", tc);
+	*prio_type = *pgid = *bw_pct = *up_map = 0;
+	if (tc < 0 || tc >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid tc %d\n", tc);
+		return;
+	}
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return;
+
+	*pgid = dcbx_info->operational.params.ets_pri_tc_tbl[tc];
+	kfree(dcbx_info);
+}
+
+static void qed_dcbnl_getpgbwgcfgtx(struct qed_dev *cdev, int pgid, u8 *bw_pct)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+
+	*bw_pct = 0;
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "pgid = %d\n", pgid);
+	if (pgid < 0 || pgid >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid pgid %d\n", pgid);
+		return;
+	}
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return;
+
+	*bw_pct = dcbx_info->operational.params.ets_tc_bw_tbl[pgid];
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "bw_pct = %d\n", *bw_pct);
+	kfree(dcbx_info);
+}
+
+static void qed_dcbnl_getpgtccfgrx(struct qed_dev *cdev, int tc, u8 *prio,
+				   u8 *bwg_id, u8 *bw_pct, u8 *up_map)
+{
+	DP_INFO(QED_LEADING_HWFN(cdev), "Rx ETS is not supported\n");
+	*prio = *bwg_id = *bw_pct = *up_map = 0;
+}
+
+static void qed_dcbnl_getpgbwgcfgrx(struct qed_dev *cdev,
+				    int bwg_id, u8 *bw_pct)
+{
+	DP_INFO(QED_LEADING_HWFN(cdev), "Rx ETS is not supported\n");
+	*bw_pct = 0;
+}
+
+static void qed_dcbnl_getpfccfg(struct qed_dev *cdev,
+				int priority, u8 *setting)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "priority = %d\n", priority);
+	if (priority < 0 || priority >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid priority %d\n", priority);
+		return;
+	}
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return;
+
+	*setting = dcbx_info->operational.params.pfc.prio[priority];
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "setting = %d\n", *setting);
+	kfree(dcbx_info);
+}
+
+static void qed_dcbnl_setpfccfg(struct qed_dev *cdev, int priority, u8 setting)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "priority = %d setting = %d\n",
+		   priority, setting);
+	if (priority < 0 || priority >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid priority %d\n", priority);
+		return;
+	}
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_PFC_CFG;
+	dcbx_set.config.params.pfc.prio[priority] = !!setting;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+}
+
+static u8 qed_dcbnl_getcap(struct qed_dev *cdev, int capid, u8 *cap)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	int rc = 0;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "capid = %d\n", capid);
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return 1;
+
+	switch (capid) {
+	case DCB_CAP_ATTR_PG:
+	case DCB_CAP_ATTR_PFC:
+	case DCB_CAP_ATTR_UP2TC:
+	case DCB_CAP_ATTR_GSP:
+		*cap = true;
+		break;
+	case DCB_CAP_ATTR_PG_TCS:
+	case DCB_CAP_ATTR_PFC_TCS:
+		*cap = 0x80;
+		break;
+	case DCB_CAP_ATTR_DCBX:
+		*cap = (DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_CEE |
+			DCB_CAP_DCBX_VER_IEEE);
+		break;
+	default:
+		*cap = false;
+		rc = 1;
+	}
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "id = %d caps = %d\n", capid, *cap);
+	kfree(dcbx_info);
+
+	return rc;
+}
+
+static int qed_dcbnl_getnumtcs(struct qed_dev *cdev, int tcid, u8 *num)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	int rc = 0;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "tcid = %d\n", tcid);
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	switch (tcid) {
+	case DCB_NUMTCS_ATTR_PG:
+		*num = dcbx_info->operational.params.max_ets_tc;
+		break;
+	case DCB_NUMTCS_ATTR_PFC:
+		*num = dcbx_info->operational.params.pfc.max_tc;
+		break;
+	default:
+		rc = -EINVAL;
+	}
+
+	kfree(dcbx_info);
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "numtcs = %d\n", *num);
+
+	return rc;
+}
+
+static u8 qed_dcbnl_getpfcstate(struct qed_dev *cdev)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	bool enabled;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return 0;
+
+	enabled = dcbx_info->operational.params.pfc.enabled;
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "pfc state = %d\n", enabled);
+	kfree(dcbx_info);
+
+	return enabled;
+}
+
+static u8 qed_dcbnl_getdcbx(struct qed_dev *cdev)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	u8 mode = 0;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return 0;
+
+	if (dcbx_info->operational.enabled)
+		mode |= DCB_CAP_DCBX_LLD_MANAGED;
+	if (dcbx_info->operational.ieee)
+		mode |= DCB_CAP_DCBX_VER_IEEE;
+	if (dcbx_info->operational.cee)
+		mode |= DCB_CAP_DCBX_VER_CEE;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "dcb mode = %d\n", mode);
+	kfree(dcbx_info);
+
+	return mode;
+}
+
+static void qed_dcbnl_setpgtccfgtx(struct qed_dev *cdev,
+				   int tc,
+				   u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB,
+		   "tc = %d pri_type = %d pgid = %d bw_pct = %d up_map = %d\n",
+		   tc, pri_type, pgid, bw_pct, up_map);
+
+	if (tc < 0 || tc >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid tc %d\n", tc);
+		return;
+	}
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_ETS_CFG;
+	dcbx_set.config.params.ets_pri_tc_tbl[tc] = pgid;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+}
+
+static void qed_dcbnl_setpgtccfgrx(struct qed_dev *cdev, int prio,
+				   u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map)
+{
+	DP_INFO(QED_LEADING_HWFN(cdev), "Rx ETS is not supported\n");
+}
+
+static void qed_dcbnl_setpgbwgcfgtx(struct qed_dev *cdev, int pgid, u8 bw_pct)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "pgid = %d bw_pct = %d\n", pgid, bw_pct);
+	if (pgid < 0 || pgid >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid pgid %d\n", pgid);
+		return;
+	}
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_ETS_CFG;
+	dcbx_set.config.params.ets_tc_bw_tbl[pgid] = bw_pct;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+}
+
+static void qed_dcbnl_setpgbwgcfgrx(struct qed_dev *cdev, int pgid, u8 bw_pct)
+{
+	DP_INFO(QED_LEADING_HWFN(cdev), "Rx ETS is not supported\n");
+}
+
+static u8 qed_dcbnl_setall(struct qed_dev *cdev)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return 1;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return 1;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 1);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
+static int qed_dcbnl_setnumtcs(struct qed_dev *cdev, int tcid, u8 num)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "tcid = %d num = %d\n", tcid, num);
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return 1;
+
+	switch (tcid) {
+	case DCB_NUMTCS_ATTR_PG:
+		dcbx_set.override_flags |= QED_DCBX_OVERRIDE_ETS_CFG;
+		dcbx_set.config.params.max_ets_tc = num;
+		break;
+	case DCB_NUMTCS_ATTR_PFC:
+		dcbx_set.override_flags |= QED_DCBX_OVERRIDE_PFC_CFG;
+		dcbx_set.config.params.pfc.max_tc = num;
+		break;
+	default:
+		DP_INFO(hwfn, "Invalid tcid %d\n", tcid);
+		return -EINVAL;
+	}
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EINVAL;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return 0;
+}
+
+static void qed_dcbnl_setpfcstate(struct qed_dev *cdev, u8 state)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "new state = %d\n", state);
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_PFC_CFG;
+	dcbx_set.config.params.pfc.enabled = !!state;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+}
+
+static int qed_dcbnl_getapp(struct qed_dev *cdev, u8 idtype, u16 idval)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_app_entry *entry;
+	bool ethtype;
+	u8 prio = 0;
+	int i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	ethtype = !!(idtype == DCB_APP_IDTYPE_ETHTYPE);
+	for (i = 0; i < QED_DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &dcbx_info->operational.params.app_entry[i];
+		if ((entry->ethtype == ethtype) && (entry->proto_id == idval)) {
+			prio = entry->prio;
+			break;
+		}
+	}
+
+	if (i == QED_DCBX_MAX_APP_PROTOCOL) {
+		DP_ERR(cdev, "App entry (%d, %d) not found\n", idtype, idval);
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	kfree(dcbx_info);
+
+	return prio;
+}
+
+static int qed_dcbnl_setapp(struct qed_dev *cdev,
+			    u8 idtype, u16 idval, u8 pri_map)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_app_entry *entry;
+	struct qed_ptt *ptt;
+	bool ethtype;
+	int rc, i;
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return -EINVAL;
+
+	ethtype = !!(idtype == DCB_APP_IDTYPE_ETHTYPE);
+	for (i = 0; i < QED_DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &dcbx_set.config.params.app_entry[i];
+		if ((entry->ethtype == ethtype) && (entry->proto_id == idval))
+			break;
+		/* First empty slot */
+		if (!entry->proto_id)
+			break;
+	}
+
+	if (i == QED_DCBX_MAX_APP_PROTOCOL) {
+		DP_ERR(cdev, "App table is full\n");
+		return -EBUSY;
+	}
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_APP_CFG;
+	dcbx_set.config.params.app_entry[i].ethtype = ethtype;
+	dcbx_set.config.params.app_entry[i].proto_id = idval;
+	dcbx_set.config.params.app_entry[i].prio = pri_map;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EBUSY;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
+static u8 qed_dcbnl_setdcbx(struct qed_dev *cdev, u8 mode)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "new mode = %x\n", mode);
+
+	if (!(mode & DCB_CAP_DCBX_VER_IEEE) && !(mode & DCB_CAP_DCBX_VER_CEE)) {
+		DP_INFO(hwfn, "Allowed mode is cee, ieee or both\n");
+		return 1;
+	}
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return 1;
+
+	dcbx_set.ver_num = 0;
+	if (mode & DCB_CAP_DCBX_VER_CEE) {
+		dcbx_set.ver_num |= DCBX_CONFIG_VERSION_CEE;
+		dcbx_set.enabled = true;
+	}
+
+	if (mode & DCB_CAP_DCBX_VER_IEEE) {
+		dcbx_set.ver_num |= DCBX_CONFIG_VERSION_IEEE;
+		dcbx_set.enabled = true;
+	}
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return 1;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return 0;
+}
+
+static u8 qed_dcbnl_getfeatcfg(struct qed_dev *cdev, int featid, u8 *flags)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "Feature id  = %d\n", featid);
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return 1;
+
+	*flags = 0;
+	switch (featid) {
+	case DCB_FEATCFG_ATTR_PG:
+		if (dcbx_info->operational.params.ets_enabled)
+			*flags = DCB_FEATCFG_ENABLE;
+		else
+			*flags = DCB_FEATCFG_ERROR;
+		break;
+	case DCB_FEATCFG_ATTR_PFC:
+		if (dcbx_info->operational.params.pfc.enabled)
+			*flags = DCB_FEATCFG_ENABLE;
+		else
+			*flags = DCB_FEATCFG_ERROR;
+		break;
+	case DCB_FEATCFG_ATTR_APP:
+		if (dcbx_info->operational.params.app_valid)
+			*flags = DCB_FEATCFG_ENABLE;
+		else
+			*flags = DCB_FEATCFG_ERROR;
+		break;
+	default:
+		DP_INFO(hwfn, "Invalid feature-ID %d\n", featid);
+		kfree(dcbx_info);
+		return 1;
+	}
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "flags = %d\n", *flags);
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static u8 qed_dcbnl_setfeatcfg(struct qed_dev *cdev, int featid, u8 flags)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	bool enabled, willing;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "featid = %d flags = %d\n",
+		   featid, flags);
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return 1;
+
+	enabled = !!(flags & DCB_FEATCFG_ENABLE);
+	willing = !!(flags & DCB_FEATCFG_WILLING);
+	switch (featid) {
+	case DCB_FEATCFG_ATTR_PG:
+		dcbx_set.override_flags |= QED_DCBX_OVERRIDE_ETS_CFG;
+		dcbx_set.config.params.ets_enabled = enabled;
+		dcbx_set.config.params.ets_willing = willing;
+		break;
+	case DCB_FEATCFG_ATTR_PFC:
+		dcbx_set.override_flags |= QED_DCBX_OVERRIDE_PFC_CFG;
+		dcbx_set.config.params.pfc.enabled = enabled;
+		dcbx_set.config.params.pfc.willing = willing;
+		break;
+	case DCB_FEATCFG_ATTR_APP:
+		dcbx_set.override_flags |= QED_DCBX_OVERRIDE_APP_CFG;
+		dcbx_set.config.params.app_willing = willing;
+		break;
+	default:
+		DP_INFO(hwfn, "Invalid feature-ID %d\n", featid);
+		return 1;
+	}
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return 1;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return 0;
+}
+
+static int qed_dcbnl_peer_getappinfo(struct qed_dev *cdev,
+				     struct dcb_peer_app_info *info,
+				     u16 *app_count)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_REMOTE_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	info->willing = dcbx_info->remote.params.app_willing;
+	info->error = dcbx_info->remote.params.app_error;
+	*app_count = dcbx_info->remote.params.num_app_entries;
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_peer_getapptable(struct qed_dev *cdev,
+				      struct dcb_app *table)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	int i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_REMOTE_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	for (i = 0; i < dcbx_info->remote.params.num_app_entries; i++) {
+		if (dcbx_info->remote.params.app_entry[i].ethtype)
+			table[i].selector = DCB_APP_IDTYPE_ETHTYPE;
+		else
+			table[i].selector = DCB_APP_IDTYPE_PORTNUM;
+		table[i].priority = dcbx_info->remote.params.app_entry[i].prio;
+		table[i].protocol =
+		    dcbx_info->remote.params.app_entry[i].proto_id;
+	}
+
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_cee_peer_getpfc(struct qed_dev *cdev, struct cee_pfc *pfc)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	int i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_REMOTE_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++)
+		if (dcbx_info->remote.params.pfc.prio[i])
+			pfc->pfc_en |= BIT(i);
+
+	pfc->tcs_supported = dcbx_info->remote.params.pfc.max_tc;
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "pfc state = %d tcs_supported = %d\n",
+		   pfc->pfc_en, pfc->tcs_supported);
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_cee_peer_getpg(struct qed_dev *cdev, struct cee_pg *pg)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	int i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_REMOTE_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	pg->willing = dcbx_info->remote.params.ets_willing;
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) {
+		pg->pg_bw[i] = dcbx_info->remote.params.ets_tc_bw_tbl[i];
+		pg->prio_pg[i] = dcbx_info->remote.params.ets_pri_tc_tbl[i];
+	}
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "willing = %d", pg->willing);
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_get_ieee_pfc(struct qed_dev *cdev,
+				  struct ieee_pfc *pfc, bool remote)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_params *params;
+	struct qed_dcbx_get *dcbx_info;
+	int rc, i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		return -EINVAL;
+	}
+
+	if (remote) {
+		memset(dcbx_info, 0, sizeof(*dcbx_info));
+		rc = qed_dcbx_query_params(hwfn, dcbx_info,
+					   QED_DCBX_REMOTE_MIB);
+		if (rc) {
+			kfree(dcbx_info);
+			return -EINVAL;
+		}
+
+		params = &dcbx_info->remote.params;
+	} else {
+		params = &dcbx_info->operational.params;
+	}
+
+	pfc->pfc_cap = params->pfc.max_tc;
+	pfc->pfc_en = 0;
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++)
+		if (params->pfc.prio[i])
+			pfc->pfc_en |= BIT(i);
+
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_ieee_getpfc(struct qed_dev *cdev, struct ieee_pfc *pfc)
+{
+	return qed_dcbnl_get_ieee_pfc(cdev, pfc, false);
+}
+
+static int qed_dcbnl_ieee_setpfc(struct qed_dev *cdev, struct ieee_pfc *pfc)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc, i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	kfree(dcbx_info);
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return -EINVAL;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_PFC_CFG;
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++)
+		dcbx_set.config.params.pfc.prio[i] = !!(pfc->pfc_en & BIT(i));
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EINVAL;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
+static int qed_dcbnl_get_ieee_ets(struct qed_dev *cdev,
+				  struct ieee_ets *ets, bool remote)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_dcbx_params *params;
+	int rc;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	if (remote) {
+		memset(dcbx_info, 0, sizeof(*dcbx_info));
+		rc = qed_dcbx_query_params(hwfn, dcbx_info,
+					   QED_DCBX_REMOTE_MIB);
+		if (rc) {
+			kfree(dcbx_info);
+			return -EINVAL;
+		}
+
+		params = &dcbx_info->remote.params;
+	} else {
+		params = &dcbx_info->operational.params;
+	}
+
+	ets->ets_cap = params->max_ets_tc;
+	ets->willing = params->ets_willing;
+	ets->cbs = params->ets_cbs;
+	memcpy(ets->tc_tx_bw, params->ets_tc_bw_tbl, sizeof(ets->tc_tx_bw));
+	memcpy(ets->tc_tsa, params->ets_tc_tsa_tbl, sizeof(ets->tc_tsa));
+	memcpy(ets->prio_tc, params->ets_pri_tc_tbl, sizeof(ets->prio_tc));
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_ieee_getets(struct qed_dev *cdev, struct ieee_ets *ets)
+{
+	return qed_dcbnl_get_ieee_ets(cdev, ets, false);
+}
+
+static int qed_dcbnl_ieee_setets(struct qed_dev *cdev, struct ieee_ets *ets)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	kfree(dcbx_info);
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return -EINVAL;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_ETS_CFG;
+	dcbx_set.config.params.max_ets_tc = ets->ets_cap;
+	dcbx_set.config.params.ets_willing = ets->willing;
+	dcbx_set.config.params.ets_cbs = ets->cbs;
+	memcpy(dcbx_set.config.params.ets_tc_bw_tbl, ets->tc_tx_bw,
+	       sizeof(ets->tc_tx_bw));
+	memcpy(dcbx_set.config.params.ets_tc_tsa_tbl, ets->tc_tsa,
+	       sizeof(ets->tc_tsa));
+	memcpy(dcbx_set.config.params.ets_pri_tc_tbl, ets->prio_tc,
+	       sizeof(ets->prio_tc));
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EINVAL;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
+int qed_dcbnl_ieee_peer_getets(struct qed_dev *cdev, struct ieee_ets *ets)
+{
+	return qed_dcbnl_get_ieee_ets(cdev, ets, true);
+}
+
+int qed_dcbnl_ieee_peer_getpfc(struct qed_dev *cdev, struct ieee_pfc *pfc)
+{
+	return qed_dcbnl_get_ieee_pfc(cdev, pfc, true);
+}
+
+int qed_dcbnl_ieee_getapp(struct qed_dev *cdev, struct dcb_app *app)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_app_entry *entry;
+	bool ethtype;
+	u8 prio = 0;
+	int i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	/* ieee defines the selector field value for ethertype to be 1 */
+	ethtype = !!((app->selector - 1) == DCB_APP_IDTYPE_ETHTYPE);
+	for (i = 0; i < QED_DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &dcbx_info->operational.params.app_entry[i];
+		if ((entry->ethtype == ethtype) &&
+		    (entry->proto_id == app->protocol)) {
+			prio = entry->prio;
+			break;
+		}
+	}
+
+	if (i == QED_DCBX_MAX_APP_PROTOCOL) {
+		DP_ERR(cdev, "App entry (%d, %d) not found\n", app->selector,
+		       app->protocol);
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	app->priority = ffs(prio) - 1;
+
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+int qed_dcbnl_ieee_setapp(struct qed_dev *cdev, struct dcb_app *app)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_dcbx_set dcbx_set;
+	struct qed_app_entry *entry;
+	struct qed_ptt *ptt;
+	bool ethtype;
+	int rc, i;
+
+	if (app->priority < 0 || app->priority >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid priority %d\n", app->priority);
+		return -EINVAL;
+	}
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	kfree(dcbx_info);
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return -EINVAL;
+
+	/* ieee defines the selector field value for ethertype to be 1 */
+	ethtype = !!((app->selector - 1) == DCB_APP_IDTYPE_ETHTYPE);
+	for (i = 0; i < QED_DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &dcbx_set.config.params.app_entry[i];
+		if ((entry->ethtype == ethtype) &&
+		    (entry->proto_id == app->protocol))
+			break;
+		/* First empty slot */
+		if (!entry->proto_id)
+			break;
+	}
+
+	if (i == QED_DCBX_MAX_APP_PROTOCOL) {
+		DP_ERR(cdev, "App table is full\n");
+		return -EBUSY;
+	}
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_APP_CFG;
+	dcbx_set.config.params.app_entry[i].ethtype = ethtype;
+	dcbx_set.config.params.app_entry[i].proto_id = app->protocol;
+	dcbx_set.config.params.app_entry[i].prio = BIT(app->priority);
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EBUSY;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
+const struct qed_eth_dcbnl_ops qed_dcbnl_ops_pass = {
+	.getstate = qed_dcbnl_getstate,
+	.setstate = qed_dcbnl_setstate,
+	.getpgtccfgtx = qed_dcbnl_getpgtccfgtx,
+	.getpgbwgcfgtx = qed_dcbnl_getpgbwgcfgtx,
+	.getpgtccfgrx = qed_dcbnl_getpgtccfgrx,
+	.getpgbwgcfgrx = qed_dcbnl_getpgbwgcfgrx,
+	.getpfccfg = qed_dcbnl_getpfccfg,
+	.setpfccfg = qed_dcbnl_setpfccfg,
+	.getcap = qed_dcbnl_getcap,
+	.getnumtcs = qed_dcbnl_getnumtcs,
+	.getpfcstate = qed_dcbnl_getpfcstate,
+	.getdcbx = qed_dcbnl_getdcbx,
+	.setpgtccfgtx = qed_dcbnl_setpgtccfgtx,
+	.setpgtccfgrx = qed_dcbnl_setpgtccfgrx,
+	.setpgbwgcfgtx = qed_dcbnl_setpgbwgcfgtx,
+	.setpgbwgcfgrx = qed_dcbnl_setpgbwgcfgrx,
+	.setall = qed_dcbnl_setall,
+	.setnumtcs = qed_dcbnl_setnumtcs,
+	.setpfcstate = qed_dcbnl_setpfcstate,
+	.setapp = qed_dcbnl_setapp,
+	.setdcbx = qed_dcbnl_setdcbx,
+	.setfeatcfg = qed_dcbnl_setfeatcfg,
+	.getfeatcfg = qed_dcbnl_getfeatcfg,
+	.getapp = qed_dcbnl_getapp,
+	.peer_getappinfo = qed_dcbnl_peer_getappinfo,
+	.peer_getapptable = qed_dcbnl_peer_getapptable,
+	.cee_peer_getpfc = qed_dcbnl_cee_peer_getpfc,
+	.cee_peer_getpg = qed_dcbnl_cee_peer_getpg,
+	.ieee_getpfc = qed_dcbnl_ieee_getpfc,
+	.ieee_setpfc = qed_dcbnl_ieee_setpfc,
+	.ieee_getets = qed_dcbnl_ieee_getets,
+	.ieee_setets = qed_dcbnl_ieee_setets,
+	.ieee_peer_getpfc = qed_dcbnl_ieee_peer_getpfc,
+	.ieee_peer_getets = qed_dcbnl_ieee_peer_getets,
+	.ieee_getapp = qed_dcbnl_ieee_getapp,
+	.ieee_setapp = qed_dcbnl_ieee_setapp,
+};
+
+#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
index e7f834dbda2d..9ba681643d05 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
@@ -33,6 +33,24 @@ struct qed_dcbx_app_data {
 	u8 tc;			/* Traffic Class */
 };
 
+#ifdef CONFIG_DCB
+#define QED_DCBX_VERSION_DISABLED       0
+#define QED_DCBX_VERSION_IEEE           1
+#define QED_DCBX_VERSION_CEE            2
+
+struct qed_dcbx_set {
+#define QED_DCBX_OVERRIDE_STATE	        BIT(0)
+#define QED_DCBX_OVERRIDE_PFC_CFG       BIT(1)
+#define QED_DCBX_OVERRIDE_ETS_CFG       BIT(2)
+#define QED_DCBX_OVERRIDE_APP_CFG       BIT(3)
+#define QED_DCBX_OVERRIDE_DSCP_CFG      BIT(4)
+	u32 override_flags;
+	bool enabled;
+	struct qed_dcbx_admin_params config;
+	u32 ver_num;
+};
+#endif
+
 struct qed_dcbx_results {
 	bool dcbx_enabled;
 	u8 pf_id;
@@ -55,6 +73,9 @@ struct qed_dcbx_info {
 	struct qed_dcbx_results results;
 	struct dcbx_mib operational;
 	struct dcbx_mib remote;
+#ifdef CONFIG_DCB
+	struct qed_dcbx_set set;
+#endif
 	u8 dcbx_cap;
 };
 
@@ -67,6 +88,13 @@ struct qed_dcbx_mib_meta_data {
 	u32 addr;
 };
 
+#ifdef CONFIG_DCB
+int qed_dcbx_get_config_params(struct qed_hwfn *, struct qed_dcbx_set *);
+
+int qed_dcbx_config_params(struct qed_hwfn *,
+			   struct qed_ptt *, struct qed_dcbx_set *, bool);
+#endif
+
 /* QED local interface routines */
 int
 qed_dcbx_mib_update_event(struct qed_hwfn *,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index e45cff4df280..b26fe267a150 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -2222,6 +2222,110 @@ int qed_fw_rss_eng(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+static int qed_set_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			    u32 hw_addr, void *p_eth_qzone,
+			    size_t eth_qzone_size, u8 timeset)
+{
+	struct coalescing_timeset *p_coal_timeset;
+
+	if (p_hwfn->cdev->int_coalescing_mode != QED_COAL_MODE_ENABLE) {
+		DP_NOTICE(p_hwfn, "Coalescing configuration not enabled\n");
+		return -EINVAL;
+	}
+
+	p_coal_timeset = p_eth_qzone;
+	memset(p_coal_timeset, 0, eth_qzone_size);
+	SET_FIELD(p_coal_timeset->value, COALESCING_TIMESET_TIMESET, timeset);
+	SET_FIELD(p_coal_timeset->value, COALESCING_TIMESET_VALID, 1);
+	qed_memcpy_to(p_hwfn, p_ptt, hw_addr, p_eth_qzone, eth_qzone_size);
+
+	return 0;
+}
+
+int qed_set_rxq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			 u16 coalesce, u8 qid, u16 sb_id)
+{
+	struct ustorm_eth_queue_zone eth_qzone;
+	u8 timeset, timer_res;
+	u16 fw_qid = 0;
+	u32 address;
+	int rc;
+
+	/* Coalesce = (timeset << timer-resolution), timeset is 7bit wide */
+	if (coalesce <= 0x7F) {
+		timer_res = 0;
+	} else if (coalesce <= 0xFF) {
+		timer_res = 1;
+	} else if (coalesce <= 0x1FF) {
+		timer_res = 2;
+	} else {
+		DP_ERR(p_hwfn, "Invalid coalesce value - %d\n", coalesce);
+		return -EINVAL;
+	}
+	timeset = (u8)(coalesce >> timer_res);
+
+	rc = qed_fw_l2_queue(p_hwfn, (u16)qid, &fw_qid);
+	if (rc)
+		return rc;
+
+	rc = qed_int_set_timer_res(p_hwfn, p_ptt, timer_res, sb_id, false);
+	if (rc)
+		goto out;
+
+	address = BAR0_MAP_REG_USDM_RAM + USTORM_ETH_QUEUE_ZONE_OFFSET(fw_qid);
+
+	rc = qed_set_coalesce(p_hwfn, p_ptt, address, &eth_qzone,
+			      sizeof(struct ustorm_eth_queue_zone), timeset);
+	if (rc)
+		goto out;
+
+	p_hwfn->cdev->rx_coalesce_usecs = coalesce;
+out:
+	return rc;
+}
+
+int qed_set_txq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			 u16 coalesce, u8 qid, u16 sb_id)
+{
+	struct xstorm_eth_queue_zone eth_qzone;
+	u8 timeset, timer_res;
+	u16 fw_qid = 0;
+	u32 address;
+	int rc;
+
+	/* Coalesce = (timeset << timer-resolution), timeset is 7bit wide */
+	if (coalesce <= 0x7F) {
+		timer_res = 0;
+	} else if (coalesce <= 0xFF) {
+		timer_res = 1;
+	} else if (coalesce <= 0x1FF) {
+		timer_res = 2;
+	} else {
+		DP_ERR(p_hwfn, "Invalid coalesce value - %d\n", coalesce);
+		return -EINVAL;
+	}
+	timeset = (u8)(coalesce >> timer_res);
+
+	rc = qed_fw_l2_queue(p_hwfn, (u16)qid, &fw_qid);
+	if (rc)
+		return rc;
+
+	rc = qed_int_set_timer_res(p_hwfn, p_ptt, timer_res, sb_id, true);
+	if (rc)
+		goto out;
+
+	address = BAR0_MAP_REG_XSDM_RAM + XSTORM_ETH_QUEUE_ZONE_OFFSET(fw_qid);
+
+	rc = qed_set_coalesce(p_hwfn, p_ptt, address, &eth_qzone,
+			      sizeof(struct xstorm_eth_queue_zone), timeset);
+	if (rc)
+		goto out;
+
+	p_hwfn->cdev->tx_coalesce_usecs = coalesce;
+out:
+	return rc;
+}
+
 /* Calculate final WFQ values for all vports and configure them.
  * After this configuration each vport will have
  * approx min rate =  min_pf_rate * (vport_wfq / QED_WFQ_UNIT)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
index f810ce45d463..343bb0344f62 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
@@ -212,6 +212,20 @@ qed_dmae_host2grc(struct qed_hwfn *p_hwfn,
 		  u32 size_in_dwords,
 		  u32 flags);
 
+ /**
+ * @brief qed_dmae_grc2host - Read data from dmae data offset
+ * to source address using the given ptt
+ *
+ * @param p_ptt
+ * @param grc_addr (dmae_data_offset)
+ * @param dest_addr
+ * @param size_in_dwords
+ * @param flags - one of the flags defined above
+ */
+int qed_dmae_grc2host(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+		      u32 grc_addr, dma_addr_t dest_addr, u32 size_in_dwords,
+		      u32 flags);
+
 /**
  * @brief qed_dmae_host2host - copy data from to source address
  * to a destination adress (for SRIOV) using the given ptt
@@ -308,4 +322,37 @@ int qed_fw_rss_eng(struct qed_hwfn *p_hwfn,
 int qed_final_cleanup(struct qed_hwfn *p_hwfn,
 		      struct qed_ptt *p_ptt, u16 id, bool is_vf);
 
+/**
+ * @brief qed_set_rxq_coalesce - Configure coalesce parameters for an Rx queue
+ * The fact that we can configure coalescing to up to 511, but on varying
+ * accuracy [the bigger the value the less accurate] up to a mistake of 3usec
+ * for the highest values.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param coalesce - Coalesce value in micro seconds.
+ * @param qid - Queue index.
+ * @param qid - SB Id
+ *
+ * @return int
+ */
+int qed_set_rxq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			 u16 coalesce, u8 qid, u16 sb_id);
+
+/**
+ * @brief qed_set_txq_coalesce - Configure coalesce parameters for a Tx queue
+ * While the API allows setting coalescing per-qid, all tx queues sharing a
+ * SB should be in same range [i.e., either 0-0x7f, 0x80-0xff or 0x100-0x1ff]
+ * otherwise configuration would break.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param coalesce - Coalesce value in micro seconds.
+ * @param qid - Queue index.
+ * @param qid - SB Id
+ *
+ * @return int
+ */
+int qed_set_txq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			 u16 coalesce, u8 qid, u16 sb_id);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 72e0ad6d16c6..592784019994 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -7244,6 +7244,9 @@ struct public_drv_mb {
 #define DRV_MB_PARAM_CFG_VF_MSIX_VF_ID_MASK	0x000000FF
 #define DRV_MB_PARAM_CFG_VF_MSIX_SB_NUM_SHIFT	8
 #define DRV_MB_PARAM_CFG_VF_MSIX_SB_NUM_MASK	0x0000FF00
+#define DRV_MB_PARAM_LLDP_SEND_MASK		0x00000001
+#define DRV_MB_PARAM_LLDP_SEND_SHIFT		0
+
 
 #define DRV_MB_PARAM_SET_LED_MODE_OPER		0x0
 #define DRV_MB_PARAM_SET_LED_MODE_ON		0x1
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 2693c30981eb..e17885321faf 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -769,6 +769,29 @@ int qed_dmae_host2grc(struct qed_hwfn *p_hwfn,
 }
 
 int
+qed_dmae_grc2host(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 grc_addr,
+		  dma_addr_t dest_addr, u32 size_in_dwords, u32 flags)
+{
+	u32 grc_addr_in_dw = grc_addr / sizeof(u32);
+	struct qed_dmae_params params;
+	int rc;
+
+	memset(&params, 0, sizeof(struct qed_dmae_params));
+	params.flags = flags;
+
+	mutex_lock(&p_hwfn->dmae_info.mutex);
+
+	rc = qed_dmae_execute_command(p_hwfn, p_ptt, grc_addr_in_dw,
+				      dest_addr, QED_DMAE_ADDRESS_GRC,
+				      QED_DMAE_ADDRESS_HOST_VIRT,
+				      size_in_dwords, &params);
+
+	mutex_unlock(&p_hwfn->dmae_info.mutex);
+
+	return rc;
+}
+
+int
 qed_dmae_host2host(struct qed_hwfn *p_hwfn,
 		   struct qed_ptt *p_ptt,
 		   dma_addr_t source_addr,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 09a6ad3d22dd..8fa50fa23c8d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -2418,6 +2418,7 @@ void qed_init_cau_sb_entry(struct qed_hwfn *p_hwfn,
 {
 	struct qed_dev *cdev = p_hwfn->cdev;
 	u32 cau_state;
+	u8 timer_res;
 
 	memset(p_sb_entry, 0, sizeof(*p_sb_entry));
 
@@ -2443,6 +2444,23 @@ void qed_init_cau_sb_entry(struct qed_hwfn *p_hwfn,
 			cdev->tx_coalesce_usecs = QED_CAU_DEF_TX_USECS;
 	}
 
+	/* Coalesce = (timeset << timer-res), timeset is 7bit wide */
+	if (cdev->rx_coalesce_usecs <= 0x7F)
+		timer_res = 0;
+	else if (cdev->rx_coalesce_usecs <= 0xFF)
+		timer_res = 1;
+	else
+		timer_res = 2;
+	SET_FIELD(p_sb_entry->params, CAU_SB_ENTRY_TIMER_RES0, timer_res);
+
+	if (cdev->tx_coalesce_usecs <= 0x7F)
+		timer_res = 0;
+	else if (cdev->tx_coalesce_usecs <= 0xFF)
+		timer_res = 1;
+	else
+		timer_res = 2;
+	SET_FIELD(p_sb_entry->params, CAU_SB_ENTRY_TIMER_RES1, timer_res);
+
 	SET_FIELD(p_sb_entry->data, CAU_SB_ENTRY_STATE0, cau_state);
 	SET_FIELD(p_sb_entry->data, CAU_SB_ENTRY_STATE1, cau_state);
 }
@@ -2484,17 +2502,28 @@ void qed_int_cau_conf_sb(struct qed_hwfn *p_hwfn,
 
 	/* Configure pi coalescing if set */
 	if (p_hwfn->cdev->int_coalescing_mode == QED_COAL_MODE_ENABLE) {
-		u8 timeset = p_hwfn->cdev->rx_coalesce_usecs >>
-			     (QED_CAU_DEF_RX_TIMER_RES + 1);
+		u8 timeset, timer_res;
 		u8 num_tc = 1, i;
 
+		/* timeset = (coalesce >> timer-res), timeset is 7bit wide */
+		if (p_hwfn->cdev->rx_coalesce_usecs <= 0x7F)
+			timer_res = 0;
+		else if (p_hwfn->cdev->rx_coalesce_usecs <= 0xFF)
+			timer_res = 1;
+		else
+			timer_res = 2;
+		timeset = (u8)(p_hwfn->cdev->rx_coalesce_usecs >> timer_res);
 		qed_int_cau_conf_pi(p_hwfn, p_ptt, igu_sb_id, RX_PI,
 				    QED_COAL_RX_STATE_MACHINE,
 				    timeset);
 
-		timeset = p_hwfn->cdev->tx_coalesce_usecs >>
-			  (QED_CAU_DEF_TX_TIMER_RES + 1);
-
+		if (p_hwfn->cdev->tx_coalesce_usecs <= 0x7F)
+			timer_res = 0;
+		else if (p_hwfn->cdev->tx_coalesce_usecs <= 0xFF)
+			timer_res = 1;
+		else
+			timer_res = 2;
+		timeset = (u8)(p_hwfn->cdev->tx_coalesce_usecs >> timer_res);
 		for (i = 0; i < num_tc; i++) {
 			qed_int_cau_conf_pi(p_hwfn, p_ptt,
 					    igu_sb_id, TX_PI(i),
@@ -3199,3 +3228,39 @@ void qed_int_disable_post_isr_release(struct qed_dev *cdev)
 	for_each_hwfn(cdev, i)
 		cdev->hwfns[i].b_int_requested = false;
 }
+
+int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			  u8 timer_res, u16 sb_id, bool tx)
+{
+	struct cau_sb_entry sb_entry;
+	int rc;
+
+	if (!p_hwfn->hw_init_done) {
+		DP_ERR(p_hwfn, "hardware not initialized yet\n");
+		return -EINVAL;
+	}
+
+	rc = qed_dmae_grc2host(p_hwfn, p_ptt, CAU_REG_SB_VAR_MEMORY +
+			       sb_id * sizeof(u64),
+			       (u64)(uintptr_t)&sb_entry, 2, 0);
+	if (rc) {
+		DP_ERR(p_hwfn, "dmae_grc2host failed %d\n", rc);
+		return rc;
+	}
+
+	if (tx)
+		SET_FIELD(sb_entry.params, CAU_SB_ENTRY_TIMER_RES1, timer_res);
+	else
+		SET_FIELD(sb_entry.params, CAU_SB_ENTRY_TIMER_RES0, timer_res);
+
+	rc = qed_dmae_host2grc(p_hwfn, p_ptt,
+			       (u64)(uintptr_t)&sb_entry,
+			       CAU_REG_SB_VAR_MEMORY +
+			       sb_id * sizeof(u64), 2, 0);
+	if (rc) {
+		DP_ERR(p_hwfn, "dmae_host2grc failed %d\n", rc);
+		return rc;
+	}
+
+	return rc;
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h
index 20b468637504..0948be64dc78 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.h
@@ -389,6 +389,9 @@ void qed_init_cau_sb_entry(struct qed_hwfn *p_hwfn,
 			   u16 vf_number,
 			   u8 vf_valid);
 
+int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			  u8 timer_res, u16 sb_id, bool tx);
+
 #define QED_MAPPING_MEMORY_SIZE(dev)	(NUM_OF_SBS(dev))
 
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 2ee496e26df6..a12c6caa6c66 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -72,6 +72,7 @@ int qed_sp_eth_vport_start(struct qed_hwfn *p_hwfn,
 	p_ramrod->mtu			= cpu_to_le16(p_params->mtu);
 	p_ramrod->inner_vlan_removal_en	= p_params->remove_inner_vlan;
 	p_ramrod->drop_ttl0_en		= p_params->drop_ttl0;
+	p_ramrod->untagged		= p_params->only_untagged;
 
 	SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_UCAST_DROP_ALL, 1);
 	SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_MCAST_DROP_ALL, 1);
@@ -247,10 +248,6 @@ qed_sp_update_accept_mode(struct qed_hwfn *p_hwfn,
 		SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_DROP_ALL,
 			  !!(accept_filter & QED_ACCEPT_NONE));
 
-		SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_ACCEPT_ALL,
-			  (!!(accept_filter & QED_ACCEPT_UCAST_MATCHED) &&
-			   !!(accept_filter & QED_ACCEPT_UCAST_UNMATCHED)));
-
 		SET_FIELD(state, ETH_VPORT_TX_MODE_MCAST_DROP_ALL,
 			  !!(accept_filter & QED_ACCEPT_NONE));
 
@@ -1756,7 +1753,8 @@ static int qed_start_vport(struct qed_dev *cdev,
 			   start.vport_id, start.mtu);
 	}
 
-	qed_reset_vport_stats(cdev);
+	if (params->clear_stats)
+		qed_reset_vport_stats(cdev);
 
 	return 0;
 }
@@ -2166,11 +2164,18 @@ static int qed_fp_cqe_completion(struct qed_dev *dev,
 extern const struct qed_iov_hv_ops qed_iov_ops_pass;
 #endif
 
+#ifdef CONFIG_DCB
+extern const struct qed_eth_dcbnl_ops qed_dcbnl_ops_pass;
+#endif
+
 static const struct qed_eth_ops qed_eth_ops_pass = {
 	.common = &qed_common_ops_pass,
 #ifdef CONFIG_QED_SRIOV
 	.iov = &qed_iov_ops_pass,
 #endif
+#ifdef CONFIG_DCB
+	.dcb = &qed_dcbnl_ops_pass,
+#endif
 	.fill_dev_info = &qed_fill_eth_dev_info,
 	.register_ops = &qed_register_eth_ops,
 	.check_mac = &qed_check_mac,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index f41f78d6a3f9..1f13abb5c316 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -1088,6 +1088,7 @@ static int qed_get_port_type(u32 media_type)
 	case MEDIA_SFPP_10G_FIBER:
 	case MEDIA_SFP_1G_FIBER:
 	case MEDIA_XFP_FIBER:
+	case MEDIA_MODULE_FIBER:
 	case MEDIA_KR:
 		port_type = PORT_FIBRE;
 		break;
@@ -1108,6 +1109,39 @@ static int qed_get_port_type(u32 media_type)
 	return port_type;
 }
 
+static int qed_get_link_data(struct qed_hwfn *hwfn,
+			     struct qed_mcp_link_params *params,
+			     struct qed_mcp_link_state *link,
+			     struct qed_mcp_link_capabilities *link_caps)
+{
+	void *p;
+
+	if (!IS_PF(hwfn->cdev)) {
+		qed_vf_get_link_params(hwfn, params);
+		qed_vf_get_link_state(hwfn, link);
+		qed_vf_get_link_caps(hwfn, link_caps);
+
+		return 0;
+	}
+
+	p = qed_mcp_get_link_params(hwfn);
+	if (!p)
+		return -ENXIO;
+	memcpy(params, p, sizeof(*params));
+
+	p = qed_mcp_get_link_state(hwfn);
+	if (!p)
+		return -ENXIO;
+	memcpy(link, p, sizeof(*link));
+
+	p = qed_mcp_get_link_capabilities(hwfn);
+	if (!p)
+		return -ENXIO;
+	memcpy(link_caps, p, sizeof(*link_caps));
+
+	return 0;
+}
+
 static void qed_fill_link(struct qed_hwfn *hwfn,
 			  struct qed_link_output *if_link)
 {
@@ -1119,15 +1153,9 @@ static void qed_fill_link(struct qed_hwfn *hwfn,
 	memset(if_link, 0, sizeof(*if_link));
 
 	/* Prepare source inputs */
-	if (IS_PF(hwfn->cdev)) {
-		memcpy(&params, qed_mcp_get_link_params(hwfn), sizeof(params));
-		memcpy(&link, qed_mcp_get_link_state(hwfn), sizeof(link));
-		memcpy(&link_caps, qed_mcp_get_link_capabilities(hwfn),
-		       sizeof(link_caps));
-	} else {
-		qed_vf_get_link_params(hwfn, &params);
-		qed_vf_get_link_state(hwfn, &link);
-		qed_vf_get_link_caps(hwfn, &link_caps);
+	if (qed_get_link_data(hwfn, &params, &link, &link_caps)) {
+		dev_warn(&hwfn->cdev->pdev->dev, "no link data available\n");
+		return;
 	}
 
 	/* Set the link parameters to pass to protocol driver */
@@ -1276,6 +1304,38 @@ static int qed_drain(struct qed_dev *cdev)
 	return 0;
 }
 
+static void qed_get_coalesce(struct qed_dev *cdev, u16 *rx_coal, u16 *tx_coal)
+{
+	*rx_coal = cdev->rx_coalesce_usecs;
+	*tx_coal = cdev->tx_coalesce_usecs;
+}
+
+static int qed_set_coalesce(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal,
+			    u8 qid, u16 sb_id)
+{
+	struct qed_hwfn *hwfn;
+	struct qed_ptt *ptt;
+	int hwfn_index;
+	int status = 0;
+
+	hwfn_index = qid % cdev->num_hwfns;
+	hwfn = &cdev->hwfns[hwfn_index];
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EAGAIN;
+
+	status = qed_set_rxq_coalesce(hwfn, ptt, rx_coal,
+				      qid / cdev->num_hwfns, sb_id);
+	if (status)
+		goto out;
+	status = qed_set_txq_coalesce(hwfn, ptt, tx_coal,
+				      qid / cdev->num_hwfns, sb_id);
+out:
+	qed_ptt_release(hwfn, ptt);
+
+	return status;
+}
+
 static int qed_set_led(struct qed_dev *cdev, enum qed_led_mode mode)
 {
 	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
@@ -1322,5 +1382,7 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.update_msglvl = &qed_init_dp,
 	.chain_alloc = &qed_chain_alloc,
 	.chain_free = &qed_chain_free,
+	.get_coalesce = &qed_get_coalesce,
+	.set_coalesce = &qed_set_coalesce,
 	.set_led = &qed_set_led,
 };
diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
index aa08ddbd95df..f6b86ca1ff79 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
@@ -80,6 +80,8 @@
 	0x1f00000UL
 #define  BAR0_MAP_REG_TSDM_RAM \
 	0x1c80000UL
+#define BAR0_MAP_REG_XSDM_RAM \
+	0x1e00000UL
 #define  NIG_REG_RX_LLH_BRB_GATE_DNTFWD_PERPF \
 	0x5011f4UL
 #define  PRS_REG_SEARCH_TCP \
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index ad9bf5c85c3f..97ffeae262bb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -213,19 +213,15 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn,
 	SET_FIELD(db.params, CORE_DB_DATA_AGG_VAL_SEL,
 		  DQ_XCM_CORE_SPQ_PROD_CMD);
 	db.agg_flags = DQ_XCM_CORE_DQ_CF_CMD;
-
-	/* validate producer is up to-date */
-	rmb();
-
 	db.spq_prod = cpu_to_le16(qed_chain_get_prod_idx(p_chain));
 
-	/* do not reorder */
-	barrier();
+	/* make sure the SPQE is updated before the doorbell */
+	wmb();
 
 	DOORBELL(p_hwfn, qed_db_addr(p_spq->cid, DQ_DEMS_LEGACY), *(u32 *)&db);
 
 	/* make sure doorbell is rang */
-	mmiowb();
+	wmb();
 
 	DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
 		   "Doorbelled [0x%08x, CID 0x%08x] with Flags: %02x agg_params: %02x, prod: %04x\n",
@@ -620,7 +616,9 @@ qed_spq_add_entry(struct qed_hwfn *p_hwfn,
 
 			*p_en2 = *p_ent;
 
-			kfree(p_ent);
+			/* EBLOCK responsible to free the allocated p_ent */
+			if (p_ent->comp_mode != QED_SPQ_MODE_EBLOCK)
+				kfree(p_ent);
 
 			p_ent = p_en2;
 		}
@@ -755,6 +753,15 @@ int qed_spq_post(struct qed_hwfn *p_hwfn,
 		 * Thus, after gaining the answer perform the cleanup here.
 		 */
 		rc = qed_spq_block(p_hwfn, p_ent, fw_return_code);
+
+		if (p_ent->queue == &p_spq->unlimited_pending) {
+			/* This is an allocated p_ent which does not need to
+			 * return to pool.
+			 */
+			kfree(p_ent);
+			return rc;
+		}
+
 		if (rc)
 			goto spq_post_fail2;
 
@@ -850,8 +857,12 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 		found->comp_cb.function(p_hwfn, found->comp_cb.cookie, p_data,
 					fw_return_code);
 
-	if (found->comp_mode != QED_SPQ_MODE_EBLOCK)
-		/* EBLOCK is responsible for freeing its own entry */
+	if ((found->comp_mode != QED_SPQ_MODE_EBLOCK) ||
+	    (found->queue == &p_spq->unlimited_pending))
+		/* EBLOCK  is responsible for returning its own entry into the
+		 * free list, unless it originally added the entry into the
+		 * unlimited pending list.
+		 */
 		qed_spq_return_entry(p_hwfn, found);
 
 	/* Attempt to post pending requests */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index eb75b8234a7c..4d161c751c12 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -21,18 +21,18 @@
 #include "qed_vf.h"
 
 /* IOV ramrods */
-static int qed_sp_vf_start(struct qed_hwfn *p_hwfn,
-			   u32 concrete_vfid, u16 opaque_vfid)
+static int qed_sp_vf_start(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf)
 {
 	struct vf_start_ramrod_data *p_ramrod = NULL;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
 	int rc = -EINVAL;
+	u8 fp_minor;
 
 	/* Get SPQ entry */
 	memset(&init_data, 0, sizeof(init_data));
 	init_data.cid = qed_spq_get_cid(p_hwfn);
-	init_data.opaque_fid = opaque_vfid;
+	init_data.opaque_fid = p_vf->opaque_fid;
 	init_data.comp_mode = QED_SPQ_MODE_EBLOCK;
 
 	rc = qed_sp_init_request(p_hwfn, &p_ent,
@@ -43,12 +43,39 @@ static int qed_sp_vf_start(struct qed_hwfn *p_hwfn,
 
 	p_ramrod = &p_ent->ramrod.vf_start;
 
-	p_ramrod->vf_id = GET_FIELD(concrete_vfid, PXP_CONCRETE_FID_VFID);
-	p_ramrod->opaque_fid = cpu_to_le16(opaque_vfid);
+	p_ramrod->vf_id = GET_FIELD(p_vf->concrete_fid, PXP_CONCRETE_FID_VFID);
+	p_ramrod->opaque_fid = cpu_to_le16(p_vf->opaque_fid);
+
+	switch (p_hwfn->hw_info.personality) {
+	case QED_PCI_ETH:
+		p_ramrod->personality = PERSONALITY_ETH;
+		break;
+	case QED_PCI_ETH_ROCE:
+		p_ramrod->personality = PERSONALITY_RDMA_AND_ETH;
+		break;
+	default:
+		DP_NOTICE(p_hwfn, "Unknown VF personality %d\n",
+			  p_hwfn->hw_info.personality);
+		return -EINVAL;
+	}
+
+	fp_minor = p_vf->acquire.vfdev_info.eth_fp_hsi_minor;
+	if (fp_minor > ETH_HSI_VER_MINOR) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "VF [%d] - Requested fp hsi %02x.%02x which is slightly newer than PF's %02x.%02x; Configuring PFs version\n",
+			   p_vf->abs_vf_id,
+			   ETH_HSI_VER_MAJOR,
+			   fp_minor, ETH_HSI_VER_MAJOR, ETH_HSI_VER_MINOR);
+		fp_minor = ETH_HSI_VER_MINOR;
+	}
 
-	p_ramrod->personality = PERSONALITY_ETH;
 	p_ramrod->hsi_fp_ver.major_ver_arr[ETH_VER_KEY] = ETH_HSI_VER_MAJOR;
-	p_ramrod->hsi_fp_ver.minor_ver_arr[ETH_VER_KEY] = ETH_HSI_VER_MINOR;
+	p_ramrod->hsi_fp_ver.minor_ver_arr[ETH_VER_KEY] = fp_minor;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+		   "VF[%d] - Starting using HSI %02x.%02x\n",
+		   p_vf->abs_vf_id, ETH_HSI_VER_MAJOR, fp_minor);
 
 	return qed_spq_post(p_hwfn, p_ent, NULL);
 }
@@ -119,6 +146,45 @@ static struct qed_vf_info *qed_iov_get_vf_info(struct qed_hwfn *p_hwfn,
 	return vf;
 }
 
+static bool qed_iov_validate_rxq(struct qed_hwfn *p_hwfn,
+				 struct qed_vf_info *p_vf, u16 rx_qid)
+{
+	if (rx_qid >= p_vf->num_rxqs)
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "VF[0x%02x] - can't touch Rx queue[%04x]; Only 0x%04x are allocated\n",
+			   p_vf->abs_vf_id, rx_qid, p_vf->num_rxqs);
+	return rx_qid < p_vf->num_rxqs;
+}
+
+static bool qed_iov_validate_txq(struct qed_hwfn *p_hwfn,
+				 struct qed_vf_info *p_vf, u16 tx_qid)
+{
+	if (tx_qid >= p_vf->num_txqs)
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "VF[0x%02x] - can't touch Tx queue[%04x]; Only 0x%04x are allocated\n",
+			   p_vf->abs_vf_id, tx_qid, p_vf->num_txqs);
+	return tx_qid < p_vf->num_txqs;
+}
+
+static bool qed_iov_validate_sb(struct qed_hwfn *p_hwfn,
+				struct qed_vf_info *p_vf, u16 sb_idx)
+{
+	int i;
+
+	for (i = 0; i < p_vf->num_sbs; i++)
+		if (p_vf->igu_sbs[i] == sb_idx)
+			return true;
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_IOV,
+		   "VF[0%02x] - tried using sb_idx %04x which doesn't exist as one of its 0x%02x SBs\n",
+		   p_vf->abs_vf_id, sb_idx, p_vf->num_sbs);
+
+	return false;
+}
+
 int qed_iov_post_vf_bulletin(struct qed_hwfn *p_hwfn,
 			     int vfid, struct qed_ptt *p_ptt)
 {
@@ -295,6 +361,9 @@ static void qed_iov_setup_vfdb(struct qed_hwfn *p_hwfn)
 		vf->opaque_fid = (p_hwfn->hw_info.opaque_fid & 0xff) |
 				 (vf->abs_vf_id << 8);
 		vf->vport_id = idx + 1;
+
+		vf->num_mac_filters = QED_ETH_VF_NUM_MAC_FILTERS;
+		vf->num_vlan_filters = QED_ETH_VF_NUM_VLAN_FILTERS;
 	}
 }
 
@@ -600,17 +669,6 @@ static int qed_iov_enable_vf_access(struct qed_hwfn *p_hwfn,
 	/* unpretend */
 	qed_fid_pretend(p_hwfn, p_ptt, (u16) p_hwfn->hw_info.concrete_fid);
 
-	if (vf->state != VF_STOPPED) {
-		DP_NOTICE(p_hwfn, "VF[%02x] is already started\n",
-			  vf->abs_vf_id);
-		return -EINVAL;
-	}
-
-	/* Start VF */
-	rc = qed_sp_vf_start(p_hwfn, vf->concrete_fid, vf->opaque_fid);
-	if (rc)
-		DP_NOTICE(p_hwfn, "Failed to start VF[%02x]\n", vf->abs_vf_id);
-
 	vf->state = VF_FREE;
 
 	return rc;
@@ -854,7 +912,6 @@ static int qed_iov_release_hw_for_vf(struct qed_hwfn *p_hwfn,
 	struct qed_mcp_link_params params;
 	struct qed_mcp_link_state link;
 	struct qed_vf_info *vf = NULL;
-	int rc = 0;
 
 	vf = qed_iov_get_vf_info(p_hwfn, rel_vf_id, true);
 	if (!vf) {
@@ -876,18 +933,8 @@ static int qed_iov_release_hw_for_vf(struct qed_hwfn *p_hwfn,
 	memcpy(&caps, qed_mcp_get_link_capabilities(p_hwfn), sizeof(caps));
 	qed_iov_set_link(p_hwfn, rel_vf_id, &params, &link, &caps);
 
-	if (vf->state != VF_STOPPED) {
-		/* Stopping the VF */
-		rc = qed_sp_vf_stop(p_hwfn, vf->concrete_fid, vf->opaque_fid);
-
-		if (rc != 0) {
-			DP_ERR(p_hwfn, "qed_sp_vf_stop returned error %d\n",
-			       rc);
-			return rc;
-		}
-
-		vf->state = VF_STOPPED;
-	}
+	/* Forget the VF's acquisition message */
+	memset(&vf->acquire, 0, sizeof(vf->acquire));
 
 	/* disablng interrupts and resetting permission table was done during
 	 * vf-close, however, we could get here without going through vf_close
@@ -1118,8 +1165,6 @@ static void qed_iov_vf_cleanup(struct qed_hwfn *p_hwfn,
 
 	p_vf->vf_bulletin = 0;
 	p_vf->vport_instance = 0;
-	p_vf->num_mac_filters = 0;
-	p_vf->num_vlan_filters = 0;
 	p_vf->configured_features = 0;
 
 	/* If VF previously requested less resources, go back to default */
@@ -1132,9 +1177,95 @@ static void qed_iov_vf_cleanup(struct qed_hwfn *p_hwfn,
 		p_vf->vf_queues[i].rxq_active = 0;
 
 	memset(&p_vf->shadow_config, 0, sizeof(p_vf->shadow_config));
+	memset(&p_vf->acquire, 0, sizeof(p_vf->acquire));
 	qed_iov_clean_vf(p_hwfn, p_vf->relative_vf_id);
 }
 
+static u8 qed_iov_vf_mbx_acquire_resc(struct qed_hwfn *p_hwfn,
+				      struct qed_ptt *p_ptt,
+				      struct qed_vf_info *p_vf,
+				      struct vf_pf_resc_request *p_req,
+				      struct pf_vf_resc *p_resp)
+{
+	int i;
+
+	/* Queue related information */
+	p_resp->num_rxqs = p_vf->num_rxqs;
+	p_resp->num_txqs = p_vf->num_txqs;
+	p_resp->num_sbs = p_vf->num_sbs;
+
+	for (i = 0; i < p_resp->num_sbs; i++) {
+		p_resp->hw_sbs[i].hw_sb_id = p_vf->igu_sbs[i];
+		p_resp->hw_sbs[i].sb_qid = 0;
+	}
+
+	/* These fields are filled for backward compatibility.
+	 * Unused by modern vfs.
+	 */
+	for (i = 0; i < p_resp->num_rxqs; i++) {
+		qed_fw_l2_queue(p_hwfn, p_vf->vf_queues[i].fw_rx_qid,
+				(u16 *)&p_resp->hw_qid[i]);
+		p_resp->cid[i] = p_vf->vf_queues[i].fw_cid;
+	}
+
+	/* Filter related information */
+	p_resp->num_mac_filters = min_t(u8, p_vf->num_mac_filters,
+					p_req->num_mac_filters);
+	p_resp->num_vlan_filters = min_t(u8, p_vf->num_vlan_filters,
+					 p_req->num_vlan_filters);
+
+	/* This isn't really needed/enforced, but some legacy VFs might depend
+	 * on the correct filling of this field.
+	 */
+	p_resp->num_mc_filters = QED_MAX_MC_ADDRS;
+
+	/* Validate sufficient resources for VF */
+	if (p_resp->num_rxqs < p_req->num_rxqs ||
+	    p_resp->num_txqs < p_req->num_txqs ||
+	    p_resp->num_sbs < p_req->num_sbs ||
+	    p_resp->num_mac_filters < p_req->num_mac_filters ||
+	    p_resp->num_vlan_filters < p_req->num_vlan_filters ||
+	    p_resp->num_mc_filters < p_req->num_mc_filters) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "VF[%d] - Insufficient resources: rxq [%02x/%02x] txq [%02x/%02x] sbs [%02x/%02x] mac [%02x/%02x] vlan [%02x/%02x] mc [%02x/%02x]\n",
+			   p_vf->abs_vf_id,
+			   p_req->num_rxqs,
+			   p_resp->num_rxqs,
+			   p_req->num_rxqs,
+			   p_resp->num_txqs,
+			   p_req->num_sbs,
+			   p_resp->num_sbs,
+			   p_req->num_mac_filters,
+			   p_resp->num_mac_filters,
+			   p_req->num_vlan_filters,
+			   p_resp->num_vlan_filters,
+			   p_req->num_mc_filters, p_resp->num_mc_filters);
+		return PFVF_STATUS_NO_RESOURCE;
+	}
+
+	return PFVF_STATUS_SUCCESS;
+}
+
+static void qed_iov_vf_mbx_acquire_stats(struct qed_hwfn *p_hwfn,
+					 struct pfvf_stats_info *p_stats)
+{
+	p_stats->mstats.address = PXP_VF_BAR0_START_MSDM_ZONE_B +
+				  offsetof(struct mstorm_vf_zone,
+					   non_trigger.eth_queue_stat);
+	p_stats->mstats.len = sizeof(struct eth_mstorm_per_queue_stat);
+	p_stats->ustats.address = PXP_VF_BAR0_START_USDM_ZONE_B +
+				  offsetof(struct ustorm_vf_zone,
+					   non_trigger.eth_queue_stat);
+	p_stats->ustats.len = sizeof(struct eth_ustorm_per_queue_stat);
+	p_stats->pstats.address = PXP_VF_BAR0_START_PSDM_ZONE_B +
+				  offsetof(struct pstorm_vf_zone,
+					   non_trigger.eth_queue_stat);
+	p_stats->pstats.len = sizeof(struct eth_pstorm_per_queue_stat);
+	p_stats->tstats.address = 0;
+	p_stats->tstats.len = 0;
+}
+
 static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn,
 				   struct qed_ptt *p_ptt,
 				   struct qed_vf_info *vf)
@@ -1143,25 +1274,27 @@ static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn,
 	struct pfvf_acquire_resp_tlv *resp = &mbx->reply_virt->acquire_resp;
 	struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info;
 	struct vfpf_acquire_tlv *req = &mbx->req_virt->acquire;
-	u8 i, vfpf_status = PFVF_STATUS_SUCCESS;
+	u8 vfpf_status = PFVF_STATUS_NOT_SUPPORTED;
 	struct pf_vf_resc *resc = &resp->resc;
+	int rc;
+
+	memset(resp, 0, sizeof(*resp));
 
 	/* Validate FW compatibility */
-	if (req->vfdev_info.fw_major != FW_MAJOR_VERSION ||
-	    req->vfdev_info.fw_minor != FW_MINOR_VERSION ||
-	    req->vfdev_info.fw_revision != FW_REVISION_VERSION ||
-	    req->vfdev_info.fw_engineering != FW_ENGINEERING_VERSION) {
+	if (req->vfdev_info.eth_fp_hsi_major != ETH_HSI_VER_MAJOR) {
 		DP_INFO(p_hwfn,
-			"VF[%d] is running an incompatible driver [VF needs FW %02x:%02x:%02x:%02x but Hypervisor is using %02x:%02x:%02x:%02x]\n",
+			"VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's faspath HSI %02x.%02x\n",
 			vf->abs_vf_id,
-			req->vfdev_info.fw_major,
-			req->vfdev_info.fw_minor,
-			req->vfdev_info.fw_revision,
-			req->vfdev_info.fw_engineering,
-			FW_MAJOR_VERSION,
-			FW_MINOR_VERSION,
-			FW_REVISION_VERSION, FW_ENGINEERING_VERSION);
-		vfpf_status = PFVF_STATUS_NOT_SUPPORTED;
+			req->vfdev_info.eth_fp_hsi_major,
+			req->vfdev_info.eth_fp_hsi_minor,
+			ETH_HSI_VER_MAJOR, ETH_HSI_VER_MINOR);
+
+		/* Write the PF version so that VF would know which version
+		 * is supported.
+		 */
+		pfdev_info->major_fp_hsi = ETH_HSI_VER_MAJOR;
+		pfdev_info->minor_fp_hsi = ETH_HSI_VER_MINOR;
+
 		goto out;
 	}
 
@@ -1171,16 +1304,13 @@ static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn,
 		DP_INFO(p_hwfn,
 			"VF[%d] is running an old driver that doesn't support 100g\n",
 			vf->abs_vf_id);
-		vfpf_status = PFVF_STATUS_NOT_SUPPORTED;
 		goto out;
 	}
 
-	memset(resp, 0, sizeof(*resp));
+	/* Store the acquire message */
+	memcpy(&vf->acquire, req, sizeof(vf->acquire));
 
-	/* Fill in vf info stuff */
 	vf->opaque_fid = req->vfdev_info.opaque_fid;
-	vf->num_mac_filters = 1;
-	vf->num_vlan_filters = QED_ETH_VF_NUM_VLAN_FILTERS;
 
 	vf->vf_bulletin = req->bulletin_addr;
 	vf->bulletin.size = (vf->bulletin.size < req->bulletin_size) ?
@@ -1196,26 +1326,7 @@ static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn,
 	if (p_hwfn->cdev->num_hwfns > 1)
 		pfdev_info->capabilities |= PFVF_ACQUIRE_CAP_100G;
 
-	pfdev_info->stats_info.mstats.address =
-	    PXP_VF_BAR0_START_MSDM_ZONE_B +
-	    offsetof(struct mstorm_vf_zone, non_trigger.eth_queue_stat);
-	pfdev_info->stats_info.mstats.len =
-	    sizeof(struct eth_mstorm_per_queue_stat);
-
-	pfdev_info->stats_info.ustats.address =
-	    PXP_VF_BAR0_START_USDM_ZONE_B +
-	    offsetof(struct ustorm_vf_zone, non_trigger.eth_queue_stat);
-	pfdev_info->stats_info.ustats.len =
-	    sizeof(struct eth_ustorm_per_queue_stat);
-
-	pfdev_info->stats_info.pstats.address =
-	    PXP_VF_BAR0_START_PSDM_ZONE_B +
-	    offsetof(struct pstorm_vf_zone, non_trigger.eth_queue_stat);
-	pfdev_info->stats_info.pstats.len =
-	    sizeof(struct eth_pstorm_per_queue_stat);
-
-	pfdev_info->stats_info.tstats.address = 0;
-	pfdev_info->stats_info.tstats.len = 0;
+	qed_iov_vf_mbx_acquire_stats(p_hwfn, &pfdev_info->stats_info);
 
 	memcpy(pfdev_info->port_mac, p_hwfn->hw_info.hw_mac_addr, ETH_ALEN);
 
@@ -1223,36 +1334,31 @@ static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn,
 	pfdev_info->fw_minor = FW_MINOR_VERSION;
 	pfdev_info->fw_rev = FW_REVISION_VERSION;
 	pfdev_info->fw_eng = FW_ENGINEERING_VERSION;
+	pfdev_info->minor_fp_hsi = min_t(u8,
+					 ETH_HSI_VER_MINOR,
+					 req->vfdev_info.eth_fp_hsi_minor);
 	pfdev_info->os_type = VFPF_ACQUIRE_OS_LINUX;
 	qed_mcp_get_mfw_ver(p_hwfn, p_ptt, &pfdev_info->mfw_ver, NULL);
 
 	pfdev_info->dev_type = p_hwfn->cdev->type;
 	pfdev_info->chip_rev = p_hwfn->cdev->chip_rev;
 
-	resc->num_rxqs = vf->num_rxqs;
-	resc->num_txqs = vf->num_txqs;
-	resc->num_sbs = vf->num_sbs;
-	for (i = 0; i < resc->num_sbs; i++) {
-		resc->hw_sbs[i].hw_sb_id = vf->igu_sbs[i];
-		resc->hw_sbs[i].sb_qid = 0;
-	}
+	/* Fill resources available to VF; Make sure there are enough to
+	 * satisfy the VF's request.
+	 */
+	vfpf_status = qed_iov_vf_mbx_acquire_resc(p_hwfn, p_ptt, vf,
+						  &req->resc_request, resc);
+	if (vfpf_status != PFVF_STATUS_SUCCESS)
+		goto out;
 
-	for (i = 0; i < resc->num_rxqs; i++) {
-		qed_fw_l2_queue(p_hwfn, vf->vf_queues[i].fw_rx_qid,
-				(u16 *)&resc->hw_qid[i]);
-		resc->cid[i] = vf->vf_queues[i].fw_cid;
+	/* Start the VF in FW */
+	rc = qed_sp_vf_start(p_hwfn, vf);
+	if (rc) {
+		DP_NOTICE(p_hwfn, "Failed to start VF[%02x]\n", vf->abs_vf_id);
+		vfpf_status = PFVF_STATUS_FAILURE;
+		goto out;
 	}
 
-	resc->num_mac_filters = min_t(u8, vf->num_mac_filters,
-				      req->resc_request.num_mac_filters);
-	resc->num_vlan_filters = min_t(u8, vf->num_vlan_filters,
-				       req->resc_request.num_vlan_filters);
-
-	/* This isn't really required as VF isn't limited, but some VFs might
-	 * actually test this value, so need to provide it.
-	 */
-	resc->num_mc_filters = req->resc_request.num_mc_filters;
-
 	/* Fill agreed size of bulletin board in response */
 	resp->bulletin_size = vf->bulletin.size;
 	qed_iov_post_vf_bulletin(p_hwfn, vf->relative_vf_id, p_ptt);
@@ -1620,12 +1726,17 @@ static void qed_iov_vf_mbx_start_rxq(struct qed_hwfn *p_hwfn,
 {
 	struct qed_queue_start_common_params params;
 	struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
-	u8 status = PFVF_STATUS_SUCCESS;
+	u8 status = PFVF_STATUS_NO_RESOURCE;
 	struct vfpf_start_rxq_tlv *req;
 	int rc;
 
 	memset(&params, 0, sizeof(params));
 	req = &mbx->req_virt->start_rxq;
+
+	if (!qed_iov_validate_rxq(p_hwfn, vf, req->rx_qid) ||
+	    !qed_iov_validate_sb(p_hwfn, vf, req->hw_sb))
+		goto out;
+
 	params.queue_id =  vf->vf_queues[req->rx_qid].fw_rx_qid;
 	params.vf_qid = req->rx_qid;
 	params.vport_id = vf->vport_id;
@@ -1643,22 +1754,48 @@ static void qed_iov_vf_mbx_start_rxq(struct qed_hwfn *p_hwfn,
 	if (rc) {
 		status = PFVF_STATUS_FAILURE;
 	} else {
+		status = PFVF_STATUS_SUCCESS;
 		vf->vf_queues[req->rx_qid].rxq_active = true;
 		vf->num_active_rxqs++;
 	}
 
+out:
 	qed_iov_vf_mbx_start_rxq_resp(p_hwfn, p_ptt, vf, status);
 }
 
+static void qed_iov_vf_mbx_start_txq_resp(struct qed_hwfn *p_hwfn,
+					  struct qed_ptt *p_ptt,
+					  struct qed_vf_info *p_vf, u8 status)
+{
+	struct qed_iov_vf_mbx *mbx = &p_vf->vf_mbx;
+	struct pfvf_start_queue_resp_tlv *p_tlv;
+
+	mbx->offset = (u8 *)mbx->reply_virt;
+
+	p_tlv = qed_add_tlv(p_hwfn, &mbx->offset, CHANNEL_TLV_START_TXQ,
+			    sizeof(*p_tlv));
+	qed_add_tlv(p_hwfn, &mbx->offset, CHANNEL_TLV_LIST_END,
+		    sizeof(struct channel_list_end_tlv));
+
+	/* Update the TLV with the response */
+	if (status == PFVF_STATUS_SUCCESS) {
+		u16 qid = mbx->req_virt->start_txq.tx_qid;
+
+		p_tlv->offset = qed_db_addr(p_vf->vf_queues[qid].fw_cid,
+					    DQ_DEMS_LEGACY);
+	}
+
+	qed_iov_send_response(p_hwfn, p_ptt, p_vf, sizeof(*p_tlv), status);
+}
+
 static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn,
 				     struct qed_ptt *p_ptt,
 				     struct qed_vf_info *vf)
 {
-	u16 length = sizeof(struct pfvf_def_resp_tlv);
 	struct qed_queue_start_common_params params;
 	struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
+	u8 status = PFVF_STATUS_NO_RESOURCE;
 	union qed_qm_pq_params pq_params;
-	u8 status = PFVF_STATUS_SUCCESS;
 	struct vfpf_start_txq_tlv *req;
 	int rc;
 
@@ -1669,6 +1806,11 @@ static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn,
 
 	memset(&params, 0, sizeof(params));
 	req = &mbx->req_virt->start_txq;
+
+	if (!qed_iov_validate_txq(p_hwfn, vf, req->tx_qid) ||
+	    !qed_iov_validate_sb(p_hwfn, vf, req->hw_sb))
+		goto out;
+
 	params.queue_id =  vf->vf_queues[req->tx_qid].fw_tx_qid;
 	params.vport_id = vf->vport_id;
 	params.sb = req->hw_sb;
@@ -1682,13 +1824,15 @@ static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn,
 					 req->pbl_addr,
 					 req->pbl_size, &pq_params);
 
-	if (rc)
+	if (rc) {
 		status = PFVF_STATUS_FAILURE;
-	else
+	} else {
+		status = PFVF_STATUS_SUCCESS;
 		vf->vf_queues[req->tx_qid].txq_active = true;
+	}
 
-	qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_START_TXQ,
-			     length, status);
+out:
+	qed_iov_vf_mbx_start_txq_resp(p_hwfn, p_ptt, vf, status);
 }
 
 static int qed_iov_vf_stop_rxqs(struct qed_hwfn *p_hwfn,
@@ -2113,6 +2257,16 @@ static void qed_iov_vf_mbx_vport_update(struct qed_hwfn *p_hwfn,
 	u16 length;
 	int rc;
 
+	/* Valiate PF can send such a request */
+	if (!vf->vport_instance) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "No VPORT instance available for VF[%d], failing vport update\n",
+			   vf->abs_vf_id);
+		status = PFVF_STATUS_FAILURE;
+		goto out;
+	}
+
 	memset(&params, 0, sizeof(params));
 	params.opaque_fid = vf->opaque_fid;
 	params.vport_id = vf->vport_id;
@@ -2155,15 +2309,12 @@ out:
 	qed_iov_send_response(p_hwfn, p_ptt, vf, length, status);
 }
 
-static int qed_iov_vf_update_unicast_shadow(struct qed_hwfn *p_hwfn,
-					    struct qed_vf_info *p_vf,
-					    struct qed_filter_ucast *p_params)
+static int qed_iov_vf_update_vlan_shadow(struct qed_hwfn *p_hwfn,
+					 struct qed_vf_info *p_vf,
+					 struct qed_filter_ucast *p_params)
 {
 	int i;
 
-	if (p_params->type == QED_FILTER_MAC)
-		return 0;
-
 	/* First remove entries and then add new ones */
 	if (p_params->opcode == QED_FILTER_REMOVE) {
 		for (i = 0; i < QED_ETH_VF_NUM_VLAN_FILTERS + 1; i++)
@@ -2216,6 +2367,80 @@ static int qed_iov_vf_update_unicast_shadow(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+static int qed_iov_vf_update_mac_shadow(struct qed_hwfn *p_hwfn,
+					struct qed_vf_info *p_vf,
+					struct qed_filter_ucast *p_params)
+{
+	int i;
+
+	/* If we're in forced-mode, we don't allow any change */
+	if (p_vf->bulletin.p_virt->valid_bitmap & (1 << MAC_ADDR_FORCED))
+		return 0;
+
+	/* First remove entries and then add new ones */
+	if (p_params->opcode == QED_FILTER_REMOVE) {
+		for (i = 0; i < QED_ETH_VF_NUM_MAC_FILTERS; i++) {
+			if (ether_addr_equal(p_vf->shadow_config.macs[i],
+					     p_params->mac)) {
+				memset(p_vf->shadow_config.macs[i], 0,
+				       ETH_ALEN);
+				break;
+			}
+		}
+
+		if (i == QED_ETH_VF_NUM_MAC_FILTERS) {
+			DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+				   "MAC isn't configured\n");
+			return -EINVAL;
+		}
+	} else if (p_params->opcode == QED_FILTER_REPLACE ||
+		   p_params->opcode == QED_FILTER_FLUSH) {
+		for (i = 0; i < QED_ETH_VF_NUM_MAC_FILTERS; i++)
+			memset(p_vf->shadow_config.macs[i], 0, ETH_ALEN);
+	}
+
+	/* List the new MAC address */
+	if (p_params->opcode != QED_FILTER_ADD &&
+	    p_params->opcode != QED_FILTER_REPLACE)
+		return 0;
+
+	for (i = 0; i < QED_ETH_VF_NUM_MAC_FILTERS; i++) {
+		if (is_zero_ether_addr(p_vf->shadow_config.macs[i])) {
+			ether_addr_copy(p_vf->shadow_config.macs[i],
+					p_params->mac);
+			DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+				   "Added MAC at %d entry in shadow\n", i);
+			break;
+		}
+	}
+
+	if (i == QED_ETH_VF_NUM_MAC_FILTERS) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV, "No available place for MAC\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+qed_iov_vf_update_unicast_shadow(struct qed_hwfn *p_hwfn,
+				 struct qed_vf_info *p_vf,
+				 struct qed_filter_ucast *p_params)
+{
+	int rc = 0;
+
+	if (p_params->type == QED_FILTER_MAC) {
+		rc = qed_iov_vf_update_mac_shadow(p_hwfn, p_vf, p_params);
+		if (rc)
+			return rc;
+	}
+
+	if (p_params->type == QED_FILTER_VLAN)
+		rc = qed_iov_vf_update_vlan_shadow(p_hwfn, p_vf, p_params);
+
+	return rc;
+}
+
 int qed_iov_chk_ucast(struct qed_hwfn *hwfn,
 		      int vfid, struct qed_filter_ucast *params)
 {
@@ -2360,11 +2585,27 @@ static void qed_iov_vf_mbx_release(struct qed_hwfn *p_hwfn,
 				   struct qed_vf_info *p_vf)
 {
 	u16 length = sizeof(struct pfvf_def_resp_tlv);
+	u8 status = PFVF_STATUS_SUCCESS;
+	int rc = 0;
 
 	qed_iov_vf_cleanup(p_hwfn, p_vf);
 
+	if (p_vf->state != VF_STOPPED && p_vf->state != VF_FREE) {
+		/* Stopping the VF */
+		rc = qed_sp_vf_stop(p_hwfn, p_vf->concrete_fid,
+				    p_vf->opaque_fid);
+
+		if (rc) {
+			DP_ERR(p_hwfn, "qed_sp_vf_stop returned error %d\n",
+			       rc);
+			status = PFVF_STATUS_FAILURE;
+		}
+
+		p_vf->state = VF_STOPPED;
+	}
+
 	qed_iov_prepare_resp(p_hwfn, p_ptt, p_vf, CHANNEL_TLV_RELEASE,
-			     length, PFVF_STATUS_SUCCESS);
+			     length, status);
 }
 
 static int
@@ -2616,7 +2857,6 @@ static void qed_iov_process_mbx_req(struct qed_hwfn *p_hwfn,
 {
 	struct qed_iov_vf_mbx *mbx;
 	struct qed_vf_info *p_vf;
-	int i;
 
 	p_vf = qed_iov_get_vf_info(p_hwfn, (u16) vfid, true);
 	if (!p_vf)
@@ -2625,9 +2865,8 @@ static void qed_iov_process_mbx_req(struct qed_hwfn *p_hwfn,
 	mbx = &p_vf->vf_mbx;
 
 	/* qed_iov_process_mbx_request */
-	DP_VERBOSE(p_hwfn,
-		   QED_MSG_IOV,
-		   "qed_iov_process_mbx_req vfid %d\n", p_vf->abs_vf_id);
+	DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+		   "VF[%02x]: Processing mailbox message\n", p_vf->abs_vf_id);
 
 	mbx->first_tlv = mbx->req_virt->first_tlv;
 
@@ -2681,15 +2920,28 @@ static void qed_iov_process_mbx_req(struct qed_hwfn *p_hwfn,
 		 * support them. Or this may be because someone wrote a crappy
 		 * VF driver and is sending garbage over the channel.
 		 */
-		DP_ERR(p_hwfn,
-		       "unknown TLV. type %d length %d. first 20 bytes of mailbox buffer:\n",
-		       mbx->first_tlv.tl.type, mbx->first_tlv.tl.length);
-
-		for (i = 0; i < 20; i++) {
+		DP_NOTICE(p_hwfn,
+			  "VF[%02x]: unknown TLV. type %04x length %04x padding %08x reply address %llu\n",
+			  p_vf->abs_vf_id,
+			  mbx->first_tlv.tl.type,
+			  mbx->first_tlv.tl.length,
+			  mbx->first_tlv.padding, mbx->first_tlv.reply_address);
+
+		/* Try replying in case reply address matches the acquisition's
+		 * posted address.
+		 */
+		if (p_vf->acquire.first_tlv.reply_address &&
+		    (mbx->first_tlv.reply_address ==
+		     p_vf->acquire.first_tlv.reply_address)) {
+			qed_iov_prepare_resp(p_hwfn, p_ptt, p_vf,
+					     mbx->first_tlv.tl.type,
+					     sizeof(struct pfvf_def_resp_tlv),
+					     PFVF_STATUS_NOT_SUPPORTED);
+		} else {
 			DP_VERBOSE(p_hwfn,
 				   QED_MSG_IOV,
-				   "%x ",
-				   mbx->req_virt->tlv_buf_size.tlv_buffer[i]);
+				   "VF[%02x]: Can't respond to TLV - no valid reply address\n",
+				   p_vf->abs_vf_id);
 		}
 	}
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
index c8667c65e685..0dd23e409b3f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
@@ -10,19 +10,23 @@
 #define _QED_SRIOV_H
 #include <linux/types.h>
 #include "qed_vf.h"
+
+#define QED_ETH_VF_NUM_MAC_FILTERS 1
+#define QED_ETH_VF_NUM_VLAN_FILTERS 2
 #define QED_VF_ARRAY_LENGTH (3)
 
+#ifdef CONFIG_QED_SRIOV
 #define IS_VF(cdev)             ((cdev)->b_is_vf)
 #define IS_PF(cdev)             (!((cdev)->b_is_vf))
-#ifdef CONFIG_QED_SRIOV
 #define IS_PF_SRIOV(p_hwfn)     (!!((p_hwfn)->cdev->p_iov_info))
 #else
+#define IS_VF(cdev)             (0)
+#define IS_PF(cdev)             (1)
 #define IS_PF_SRIOV(p_hwfn)     (0)
 #endif
 #define IS_PF_SRIOV_ALLOC(p_hwfn)       (!!((p_hwfn)->pf_iov_info))
 
 #define QED_MAX_VF_CHAINS_PER_PF 16
-#define QED_ETH_VF_NUM_VLAN_FILTERS 2
 
 #define QED_ETH_MAX_VF_NUM_VLAN_FILTERS	\
 	(MAX_NUM_VFS * QED_ETH_VF_NUM_VLAN_FILTERS)
@@ -118,6 +122,8 @@ struct qed_vf_shadow_config {
 	/* Shadow copy of all guest vlans */
 	struct qed_vf_vlan_shadow vlans[QED_ETH_VF_NUM_VLAN_FILTERS + 1];
 
+	/* Shadow copy of all configured MACs; Empty if forcing MACs */
+	u8 macs[QED_ETH_VF_NUM_MAC_FILTERS][ETH_ALEN];
 	u8 inner_vlan_removal;
 };
 
@@ -131,6 +137,9 @@ struct qed_vf_info {
 	struct qed_bulletin bulletin;
 	dma_addr_t vf_bulletin;
 
+	/* PF saves a copy of the last VF acquire message */
+	struct vfpf_acquire_tlv acquire;
+
 	u32 concrete_fid;
 	u16 opaque_fid;
 	u16 mtu;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 72e69c0ec10d..9819230947bf 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -117,36 +117,64 @@ exit:
 }
 
 #define VF_ACQUIRE_THRESH 3
-#define VF_ACQUIRE_MAC_FILTERS 1
+static void qed_vf_pf_acquire_reduce_resc(struct qed_hwfn *p_hwfn,
+					  struct vf_pf_resc_request *p_req,
+					  struct pf_vf_resc *p_resp)
+{
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_IOV,
+		   "PF unwilling to fullill resource request: rxq [%02x/%02x] txq [%02x/%02x] sbs [%02x/%02x] mac [%02x/%02x] vlan [%02x/%02x] mc [%02x/%02x]. Try PF recommended amount\n",
+		   p_req->num_rxqs,
+		   p_resp->num_rxqs,
+		   p_req->num_rxqs,
+		   p_resp->num_txqs,
+		   p_req->num_sbs,
+		   p_resp->num_sbs,
+		   p_req->num_mac_filters,
+		   p_resp->num_mac_filters,
+		   p_req->num_vlan_filters,
+		   p_resp->num_vlan_filters,
+		   p_req->num_mc_filters, p_resp->num_mc_filters);
+
+	/* humble our request */
+	p_req->num_txqs = p_resp->num_txqs;
+	p_req->num_rxqs = p_resp->num_rxqs;
+	p_req->num_sbs = p_resp->num_sbs;
+	p_req->num_mac_filters = p_resp->num_mac_filters;
+	p_req->num_vlan_filters = p_resp->num_vlan_filters;
+	p_req->num_mc_filters = p_resp->num_mc_filters;
+}
 
 static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
 {
 	struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info;
 	struct pfvf_acquire_resp_tlv *resp = &p_iov->pf2vf_reply->acquire_resp;
 	struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info;
-	u8 rx_count = 1, tx_count = 1, num_sbs = 1;
-	u8 num_mac = VF_ACQUIRE_MAC_FILTERS;
+	struct vf_pf_resc_request *p_resc;
 	bool resources_acquired = false;
 	struct vfpf_acquire_tlv *req;
 	int rc = 0, attempts = 0;
 
 	/* clear mailbox and prep first tlv */
 	req = qed_vf_pf_prep(p_hwfn, CHANNEL_TLV_ACQUIRE, sizeof(*req));
+	p_resc = &req->resc_request;
 
 	/* starting filling the request */
 	req->vfdev_info.opaque_fid = p_hwfn->hw_info.opaque_fid;
 
-	req->resc_request.num_rxqs = rx_count;
-	req->resc_request.num_txqs = tx_count;
-	req->resc_request.num_sbs = num_sbs;
-	req->resc_request.num_mac_filters = num_mac;
-	req->resc_request.num_vlan_filters = QED_ETH_VF_NUM_VLAN_FILTERS;
+	p_resc->num_rxqs = QED_MAX_VF_CHAINS_PER_PF;
+	p_resc->num_txqs = QED_MAX_VF_CHAINS_PER_PF;
+	p_resc->num_sbs = QED_MAX_VF_CHAINS_PER_PF;
+	p_resc->num_mac_filters = QED_ETH_VF_NUM_MAC_FILTERS;
+	p_resc->num_vlan_filters = QED_ETH_VF_NUM_VLAN_FILTERS;
 
 	req->vfdev_info.os_type = VFPF_ACQUIRE_OS_LINUX;
 	req->vfdev_info.fw_major = FW_MAJOR_VERSION;
 	req->vfdev_info.fw_minor = FW_MINOR_VERSION;
 	req->vfdev_info.fw_revision = FW_REVISION_VERSION;
 	req->vfdev_info.fw_engineering = FW_ENGINEERING_VERSION;
+	req->vfdev_info.eth_fp_hsi_major = ETH_HSI_VER_MAJOR;
+	req->vfdev_info.eth_fp_hsi_minor = ETH_HSI_VER_MINOR;
 
 	/* Fill capability field with any non-deprecated config we support */
 	req->vfdev_info.capabilities |= VFPF_ACQUIRE_CAP_100G;
@@ -185,21 +213,21 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
 			resources_acquired = true;
 		} else if (resp->hdr.status == PFVF_STATUS_NO_RESOURCE &&
 			   attempts < VF_ACQUIRE_THRESH) {
-			DP_VERBOSE(p_hwfn,
-				   QED_MSG_IOV,
-				   "PF unwilling to fullfill resource request. Try PF recommended amount\n");
-
-			/* humble our request */
-			req->resc_request.num_txqs = resp->resc.num_txqs;
-			req->resc_request.num_rxqs = resp->resc.num_rxqs;
-			req->resc_request.num_sbs = resp->resc.num_sbs;
-			req->resc_request.num_mac_filters =
-			    resp->resc.num_mac_filters;
-			req->resc_request.num_vlan_filters =
-			    resp->resc.num_vlan_filters;
+			qed_vf_pf_acquire_reduce_resc(p_hwfn, p_resc,
+						      &resp->resc);
 
 			/* Clear response buffer */
 			memset(p_iov->pf2vf_reply, 0, sizeof(union pfvf_tlvs));
+		} else if ((resp->hdr.status == PFVF_STATUS_NOT_SUPPORTED) &&
+			   pfdev_info->major_fp_hsi &&
+			   (pfdev_info->major_fp_hsi != ETH_HSI_VER_MAJOR)) {
+			DP_NOTICE(p_hwfn,
+				  "PF uses an incompatible fastpath HSI %02x.%02x [VF requires %02x.%02x]. Please change to a VF driver using %02x.xx.\n",
+				  pfdev_info->major_fp_hsi,
+				  pfdev_info->minor_fp_hsi,
+				  ETH_HSI_VER_MAJOR,
+				  ETH_HSI_VER_MINOR, pfdev_info->major_fp_hsi);
+			return -EINVAL;
 		} else {
 			DP_ERR(p_hwfn,
 			       "PF returned error %d to VF acquisition request\n",
@@ -225,6 +253,13 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
 		}
 	}
 
+	if (ETH_HSI_VER_MINOR &&
+	    (resp->pfdev_info.minor_fp_hsi < ETH_HSI_VER_MINOR)) {
+		DP_INFO(p_hwfn,
+			"PF is using older fastpath HSI; %02x.%02x is configured\n",
+			ETH_HSI_VER_MAJOR, resp->pfdev_info.minor_fp_hsi);
+	}
+
 	return 0;
 }
 
@@ -405,8 +440,8 @@ int qed_vf_pf_txq_start(struct qed_hwfn *p_hwfn,
 			u16 pbl_size, void __iomem **pp_doorbell)
 {
 	struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info;
+	struct pfvf_start_queue_resp_tlv *resp;
 	struct vfpf_start_txq_tlv *req;
-	struct pfvf_def_resp_tlv *resp;
 	int rc;
 
 	/* clear mailbox and prep first tlv */
@@ -424,20 +459,24 @@ int qed_vf_pf_txq_start(struct qed_hwfn *p_hwfn,
 	qed_add_tlv(p_hwfn, &p_iov->offset,
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
-	resp = &p_iov->pf2vf_reply->default_resp;
+	resp = &p_iov->pf2vf_reply->queue_start;
 	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
 	if (rc)
-		return rc;
+		goto exit;
 
-	if (resp->hdr.status != PFVF_STATUS_SUCCESS)
-		return -EINVAL;
+	if (resp->hdr.status != PFVF_STATUS_SUCCESS) {
+		rc = -EINVAL;
+		goto exit;
+	}
 
 	if (pp_doorbell) {
-		u8 cid = p_iov->acquire_resp.resc.cid[tx_queue_id];
+		*pp_doorbell = (u8 __iomem *)p_hwfn->doorbells + resp->offset;
 
-		*pp_doorbell = (u8 __iomem *)p_hwfn->doorbells +
-					     qed_db_addr(cid, DQ_DEMS_LEGACY);
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+			   "Txq[0x%02x]: doorbell at %p [offset 0x%08x]\n",
+			   tx_queue_id, *pp_doorbell, resp->offset);
 	}
+exit:
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h
index b82fda964bbd..b23ce58e932f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h
@@ -96,7 +96,9 @@ struct vfpf_acquire_tlv {
 		u32 driver_version;
 		u16 opaque_fid;	/* ME register value */
 		u8 os_type;	/* VFPF_ACQUIRE_OS_* value */
-		u8 padding[5];
+		u8 eth_fp_hsi_major;
+		u8 eth_fp_hsi_minor;
+		u8 padding[3];
 	} vfdev_info;
 
 	struct vf_pf_resc_request resc_request;
@@ -171,7 +173,14 @@ struct pfvf_acquire_resp_tlv {
 		struct pfvf_stats_info stats_info;
 
 		u8 port_mac[ETH_ALEN];
-		u8 padding2[2];
+
+		/* It's possible PF had to configure an older fastpath HSI
+		 * [in case VF is newer than PF]. This is communicated back
+		 * to the VF. It can also be used in case of error due to
+		 * non-matching versions to shed light in VF about failure.
+		 */
+		u8 major_fp_hsi;
+		u8 minor_fp_hsi;
 	} pfdev_info;
 
 	struct pf_vf_resc {
diff --git a/drivers/net/ethernet/qlogic/qede/Makefile b/drivers/net/ethernet/qlogic/qede/Makefile
index 06ff90d87572..74a49850d74d 100644
--- a/drivers/net/ethernet/qlogic/qede/Makefile
+++ b/drivers/net/ethernet/qlogic/qede/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_QEDE) := qede.o
 
 qede-y := qede_main.o qede_ethtool.o
+qede-$(CONFIG_DCB) += qede_dcbnl.o
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 47d6b22252f6..02b06d4e40ae 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -24,7 +24,7 @@
 #include <linux/qed/qed_eth_if.h>
 
 #define QEDE_MAJOR_VERSION		8
-#define QEDE_MINOR_VERSION		7
+#define QEDE_MINOR_VERSION		10
 #define QEDE_REVISION_VERSION		1
 #define QEDE_ENGINEERING_VERSION	20
 #define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "."	\
@@ -143,6 +143,8 @@ struct qede_dev {
 	struct mutex			qede_lock;
 	u32				state; /* Protected by qede_lock */
 	u16				rx_buf_size;
+	u32				rx_copybreak;
+
 	/* L2 header size + 2*VLANs (8 bytes) + LLC SNAP (8 bytes) */
 #define ETH_OVERHEAD			(ETH_HLEN + 8 + 8)
 	/* Max supported alignment is 256 (8 shift)
@@ -235,6 +237,7 @@ struct qede_rx_queue {
 
 	u64			rx_hw_errors;
 	u64			rx_alloc_errors;
+	u64			rx_ip_frags;
 };
 
 union db_prod {
@@ -304,6 +307,9 @@ union qede_reload_args {
 	u16 mtu;
 };
 
+#ifdef CONFIG_DCB
+void qede_set_dcbnl_ops(struct net_device *ndev);
+#endif
 void qede_config_debug(uint debug, u32 *p_dp_module, u8 *p_dp_level);
 void qede_set_ethtool_ops(struct net_device *netdev);
 void qede_reload(struct qede_dev *edev,
@@ -329,6 +335,7 @@ void qede_recycle_rx_bd_ring(struct qede_rx_queue *rxq, struct qede_dev *edev,
 #define NUM_TX_BDS_MIN		128
 #define NUM_TX_BDS_DEF		NUM_TX_BDS_MAX
 
+#define QEDE_MIN_PKT_LEN	64
 #define QEDE_RX_HDR_SIZE	256
 #define	for_each_rss(i) for (i = 0; i < edev->num_rss; i++)
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c b/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c
new file mode 100644
index 000000000000..03e8c0212433
--- /dev/null
+++ b/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c
@@ -0,0 +1,348 @@
+/* QLogic qede NIC Driver
+* Copyright (c) 2015 QLogic Corporation
+*
+* This software is available under the terms of the GNU General Public License
+* (GPL) Version 2, available from the file COPYING in the main directory of
+* this source tree.
+*/
+
+#include <linux/types.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <net/dcbnl.h>
+#include "qede.h"
+
+static u8 qede_dcbnl_getstate(struct net_device *netdev)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getstate(edev->cdev);
+}
+
+static u8 qede_dcbnl_setstate(struct net_device *netdev, u8 state)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setstate(edev->cdev, state);
+}
+
+static void qede_dcbnl_getpermhwaddr(struct net_device *netdev,
+				     u8 *perm_addr)
+{
+	memcpy(perm_addr, netdev->dev_addr, netdev->addr_len);
+}
+
+static void qede_dcbnl_getpgtccfgtx(struct net_device *netdev, int prio,
+				    u8 *prio_type, u8 *pgid, u8 *bw_pct,
+				    u8 *up_map)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->getpgtccfgtx(edev->cdev, prio, prio_type,
+				     pgid, bw_pct, up_map);
+}
+
+static void qede_dcbnl_getpgbwgcfgtx(struct net_device *netdev,
+				     int pgid, u8 *bw_pct)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->getpgbwgcfgtx(edev->cdev, pgid, bw_pct);
+}
+
+static void qede_dcbnl_getpgtccfgrx(struct net_device *netdev, int prio,
+				    u8 *prio_type, u8 *pgid, u8 *bw_pct,
+				    u8 *up_map)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->getpgtccfgrx(edev->cdev, prio, prio_type, pgid, bw_pct,
+				     up_map);
+}
+
+static void qede_dcbnl_getpgbwgcfgrx(struct net_device *netdev,
+				     int pgid, u8 *bw_pct)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->getpgbwgcfgrx(edev->cdev, pgid, bw_pct);
+}
+
+static void qede_dcbnl_getpfccfg(struct net_device *netdev, int prio,
+				 u8 *setting)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->getpfccfg(edev->cdev, prio, setting);
+}
+
+static void qede_dcbnl_setpfccfg(struct net_device *netdev, int prio,
+				 u8 setting)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->setpfccfg(edev->cdev, prio, setting);
+}
+
+static u8 qede_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getcap(edev->cdev, capid, cap);
+}
+
+static int qede_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getnumtcs(edev->cdev, tcid, num);
+}
+
+static u8 qede_dcbnl_getpfcstate(struct net_device *netdev)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getpfcstate(edev->cdev);
+}
+
+static int qede_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getapp(edev->cdev, idtype, id);
+}
+
+static u8 qede_dcbnl_getdcbx(struct net_device *netdev)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getdcbx(edev->cdev);
+}
+
+static void qede_dcbnl_setpgtccfgtx(struct net_device *netdev, int prio,
+				    u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setpgtccfgtx(edev->cdev, prio, pri_type, pgid,
+					    bw_pct, up_map);
+}
+
+static void qede_dcbnl_setpgtccfgrx(struct net_device *netdev, int prio,
+				    u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setpgtccfgrx(edev->cdev, prio, pri_type, pgid,
+					    bw_pct, up_map);
+}
+
+static void qede_dcbnl_setpgbwgcfgtx(struct net_device *netdev, int pgid,
+				     u8 bw_pct)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setpgbwgcfgtx(edev->cdev, pgid, bw_pct);
+}
+
+static void qede_dcbnl_setpgbwgcfgrx(struct net_device *netdev, int pgid,
+				     u8 bw_pct)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setpgbwgcfgrx(edev->cdev, pgid, bw_pct);
+}
+
+static u8 qede_dcbnl_setall(struct net_device *netdev)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setall(edev->cdev);
+}
+
+static int qede_dcbnl_setnumtcs(struct net_device *netdev, int tcid, u8 num)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setnumtcs(edev->cdev, tcid, num);
+}
+
+static void qede_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setpfcstate(edev->cdev, state);
+}
+
+static int qede_dcbnl_setapp(struct net_device *netdev, u8 idtype, u16 idval,
+			     u8 up)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setapp(edev->cdev, idtype, idval, up);
+}
+
+static u8 qede_dcbnl_setdcbx(struct net_device *netdev, u8 state)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setdcbx(edev->cdev, state);
+}
+
+static u8 qede_dcbnl_getfeatcfg(struct net_device *netdev, int featid,
+				u8 *flags)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getfeatcfg(edev->cdev, featid, flags);
+}
+
+static u8 qede_dcbnl_setfeatcfg(struct net_device *netdev, int featid, u8 flags)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setfeatcfg(edev->cdev, featid, flags);
+}
+
+static int qede_dcbnl_peer_getappinfo(struct net_device *netdev,
+				      struct dcb_peer_app_info *info,
+				      u16 *count)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->peer_getappinfo(edev->cdev, info, count);
+}
+
+static int qede_dcbnl_peer_getapptable(struct net_device *netdev,
+				       struct dcb_app *app)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->peer_getapptable(edev->cdev, app);
+}
+
+static int qede_dcbnl_cee_peer_getpfc(struct net_device *netdev,
+				      struct cee_pfc *pfc)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->cee_peer_getpfc(edev->cdev, pfc);
+}
+
+static int qede_dcbnl_cee_peer_getpg(struct net_device *netdev,
+				     struct cee_pg *pg)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->cee_peer_getpg(edev->cdev, pg);
+}
+
+static int qede_dcbnl_ieee_getpfc(struct net_device *netdev,
+				  struct ieee_pfc *pfc)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_getpfc(edev->cdev, pfc);
+}
+
+static int qede_dcbnl_ieee_setpfc(struct net_device *netdev,
+				  struct ieee_pfc *pfc)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_setpfc(edev->cdev, pfc);
+}
+
+static int qede_dcbnl_ieee_getets(struct net_device *netdev,
+				  struct ieee_ets *ets)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_getets(edev->cdev, ets);
+}
+
+static int qede_dcbnl_ieee_setets(struct net_device *netdev,
+				  struct ieee_ets *ets)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_setets(edev->cdev, ets);
+}
+
+static int qede_dcbnl_ieee_getapp(struct net_device *netdev,
+				  struct dcb_app *app)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_getapp(edev->cdev, app);
+}
+
+static int qede_dcbnl_ieee_setapp(struct net_device *netdev,
+				  struct dcb_app *app)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_setapp(edev->cdev, app);
+}
+
+static int qede_dcbnl_ieee_peer_getpfc(struct net_device *netdev,
+				       struct ieee_pfc *pfc)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_peer_getpfc(edev->cdev, pfc);
+}
+
+static int qede_dcbnl_ieee_peer_getets(struct net_device *netdev,
+				       struct ieee_ets *ets)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_peer_getets(edev->cdev, ets);
+}
+
+static const struct dcbnl_rtnl_ops qede_dcbnl_ops = {
+	.ieee_getpfc = qede_dcbnl_ieee_getpfc,
+	.ieee_setpfc = qede_dcbnl_ieee_setpfc,
+	.ieee_getets = qede_dcbnl_ieee_getets,
+	.ieee_setets = qede_dcbnl_ieee_setets,
+	.ieee_getapp = qede_dcbnl_ieee_getapp,
+	.ieee_setapp = qede_dcbnl_ieee_setapp,
+	.getdcbx = qede_dcbnl_getdcbx,
+	.ieee_peer_getpfc = qede_dcbnl_ieee_peer_getpfc,
+	.ieee_peer_getets = qede_dcbnl_ieee_peer_getets,
+	.getstate = qede_dcbnl_getstate,
+	.setstate = qede_dcbnl_setstate,
+	.getpermhwaddr = qede_dcbnl_getpermhwaddr,
+	.getpgtccfgtx = qede_dcbnl_getpgtccfgtx,
+	.getpgbwgcfgtx = qede_dcbnl_getpgbwgcfgtx,
+	.getpgtccfgrx = qede_dcbnl_getpgtccfgrx,
+	.getpgbwgcfgrx = qede_dcbnl_getpgbwgcfgrx,
+	.getpfccfg = qede_dcbnl_getpfccfg,
+	.setpfccfg = qede_dcbnl_setpfccfg,
+	.getcap = qede_dcbnl_getcap,
+	.getnumtcs = qede_dcbnl_getnumtcs,
+	.getpfcstate = qede_dcbnl_getpfcstate,
+	.getapp = qede_dcbnl_getapp,
+	.getdcbx = qede_dcbnl_getdcbx,
+	.setpgtccfgtx = qede_dcbnl_setpgtccfgtx,
+	.setpgtccfgrx = qede_dcbnl_setpgtccfgrx,
+	.setpgbwgcfgtx = qede_dcbnl_setpgbwgcfgtx,
+	.setpgbwgcfgrx = qede_dcbnl_setpgbwgcfgrx,
+	.setall = qede_dcbnl_setall,
+	.setnumtcs = qede_dcbnl_setnumtcs,
+	.setpfcstate = qede_dcbnl_setpfcstate,
+	.setapp = qede_dcbnl_setapp,
+	.setdcbx = qede_dcbnl_setdcbx,
+	.setfeatcfg = qede_dcbnl_setfeatcfg,
+	.getfeatcfg = qede_dcbnl_getfeatcfg,
+	.peer_getappinfo = qede_dcbnl_peer_getappinfo,
+	.peer_getapptable = qede_dcbnl_peer_getapptable,
+	.cee_peer_getpfc = qede_dcbnl_cee_peer_getpfc,
+	.cee_peer_getpg = qede_dcbnl_cee_peer_getpg,
+};
+
+void qede_set_dcbnl_ops(struct net_device *dev)
+{
+	dev->dcbnl_ops = &qede_dcbnl_ops;
+}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 6836d44b6b89..f8492cac9290 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -37,6 +37,7 @@ static const struct {
 } qede_rqstats_arr[] = {
 	QEDE_RQSTAT(rx_hw_errors),
 	QEDE_RQSTAT(rx_alloc_errors),
+	QEDE_RQSTAT(rx_ip_frags),
 };
 
 #define QEDE_NUM_RQSTATS ARRAY_SIZE(qede_rqstats_arr)
@@ -426,6 +427,59 @@ static u32 qede_get_link(struct net_device *dev)
 	return current_link.link_up;
 }
 
+static int qede_get_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *coal)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	u16 rxc, txc;
+
+	memset(coal, 0, sizeof(struct ethtool_coalesce));
+	edev->ops->common->get_coalesce(edev->cdev, &rxc, &txc);
+
+	coal->rx_coalesce_usecs = rxc;
+	coal->tx_coalesce_usecs = txc;
+
+	return 0;
+}
+
+static int qede_set_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *coal)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	int i, rc = 0;
+	u16 rxc, txc;
+	u8 sb_id;
+
+	if (!netif_running(dev)) {
+		DP_INFO(edev, "Interface is down\n");
+		return -EINVAL;
+	}
+
+	if (coal->rx_coalesce_usecs > QED_COALESCE_MAX ||
+	    coal->tx_coalesce_usecs > QED_COALESCE_MAX) {
+		DP_INFO(edev,
+			"Can't support requested %s coalesce value [max supported value %d]\n",
+			coal->rx_coalesce_usecs > QED_COALESCE_MAX ? "rx"
+								   : "tx",
+			QED_COALESCE_MAX);
+		return -EINVAL;
+	}
+
+	rxc = (u16)coal->rx_coalesce_usecs;
+	txc = (u16)coal->tx_coalesce_usecs;
+	for_each_rss(i) {
+		sb_id = edev->fp_array[i].sb_info->igu_sb_id;
+		rc = edev->ops->common->set_coalesce(edev->cdev, rxc, txc,
+						     (u8)i, sb_id);
+		if (rc) {
+			DP_INFO(edev, "Set coalesce error, rc = %d\n", rc);
+			return rc;
+		}
+	}
+
+	return rc;
+}
+
 static void qede_get_ringparam(struct net_device *dev,
 			       struct ethtool_ringparam *ering)
 {
@@ -1131,6 +1185,48 @@ static void qede_self_test(struct net_device *dev,
 	}
 }
 
+static int qede_set_tunable(struct net_device *dev,
+			    const struct ethtool_tunable *tuna,
+			    const void *data)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	u32 val;
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		val = *(u32 *)data;
+		if (val < QEDE_MIN_PKT_LEN || val > QEDE_RX_HDR_SIZE) {
+			DP_VERBOSE(edev, QED_MSG_DEBUG,
+				   "Invalid rx copy break value, range is [%u, %u]",
+				   QEDE_MIN_PKT_LEN, QEDE_RX_HDR_SIZE);
+			return -EINVAL;
+		}
+
+		edev->rx_copybreak = *(u32 *)data;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int qede_get_tunable(struct net_device *dev,
+			    const struct ethtool_tunable *tuna, void *data)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		*(u32 *)data = edev->rx_copybreak;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static const struct ethtool_ops qede_ethtool_ops = {
 	.get_settings = qede_get_settings,
 	.set_settings = qede_set_settings,
@@ -1139,6 +1235,8 @@ static const struct ethtool_ops qede_ethtool_ops = {
 	.set_msglevel = qede_set_msglevel,
 	.nway_reset = qede_nway_reset,
 	.get_link = qede_get_link,
+	.get_coalesce = qede_get_coalesce,
+	.set_coalesce = qede_set_coalesce,
 	.get_ringparam = qede_get_ringparam,
 	.set_ringparam = qede_set_ringparam,
 	.get_pauseparam = qede_get_pauseparam,
@@ -1157,6 +1255,8 @@ static const struct ethtool_ops qede_ethtool_ops = {
 	.get_channels = qede_get_channels,
 	.set_channels = qede_set_channels,
 	.self_test = qede_self_test,
+	.get_tunable = qede_get_tunable,
+	.set_tunable = qede_set_tunable,
 };
 
 static const struct ethtool_ops qede_vf_ethtool_ops = {
@@ -1179,6 +1279,8 @@ static const struct ethtool_ops qede_vf_ethtool_ops = {
 	.set_rxfh = qede_set_rxfh,
 	.get_channels = qede_get_channels,
 	.set_channels = qede_set_channels,
+	.get_tunable = qede_get_tunable,
+	.set_tunable = qede_set_tunable,
 };
 
 void qede_set_ethtool_ops(struct net_device *dev)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index edd2d908c52e..91e7bb0b85c8 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -24,12 +24,7 @@
 #include <linux/netdev_features.h>
 #include <linux/udp.h>
 #include <linux/tcp.h>
-#ifdef CONFIG_QEDE_VXLAN
-#include <net/vxlan.h>
-#endif
-#ifdef CONFIG_QEDE_GENEVE
-#include <net/geneve.h>
-#endif
+#include <net/udp_tunnel.h>
 #include <linux/ip.h>
 #include <net/ipv6.h>
 #include <net/tcp.h>
@@ -87,7 +82,9 @@ static const struct pci_device_id qede_pci_tbl[] = {
 	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_100), QEDE_PRIVATE_PF},
 	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_50), QEDE_PRIVATE_PF},
 	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_25), QEDE_PRIVATE_PF},
+#ifdef CONFIG_QED_SRIOV
 	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_IOV), QEDE_PRIVATE_VF},
+#endif
 	{ 0 }
 };
 
@@ -488,6 +485,24 @@ static bool qede_pkt_req_lin(struct qede_dev *edev, struct sk_buff *skb,
 }
 #endif
 
+static inline void qede_update_tx_producer(struct qede_tx_queue *txq)
+{
+	/* wmb makes sure that the BDs data is updated before updating the
+	 * producer, otherwise FW may read old data from the BDs.
+	 */
+	wmb();
+	barrier();
+	writel(txq->tx_db.raw, txq->doorbell_addr);
+
+	/* mmiowb is needed to synchronize doorbell writes from more than one
+	 * processor. It guarantees that the write arrives to the device before
+	 * the queue lock is released and another start_xmit is called (possibly
+	 * on another CPU). Without this barrier, the next doorbell can bypass
+	 * this doorbell. This is applicable to IA64/Altix systems.
+	 */
+	mmiowb();
+}
+
 /* Main transmit function */
 static
 netdev_tx_t qede_start_xmit(struct sk_buff *skb,
@@ -546,6 +561,7 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb,
 	if (unlikely(dma_mapping_error(&edev->pdev->dev, mapping))) {
 		DP_NOTICE(edev, "SKB mapping failed\n");
 		qede_free_failed_tx_pkt(edev, txq, first_bd, 0, false);
+		qede_update_tx_producer(txq);
 		return NETDEV_TX_OK;
 	}
 	nbd++;
@@ -660,6 +676,7 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb,
 		if (rc) {
 			qede_free_failed_tx_pkt(edev, txq, first_bd, nbd,
 						data_split);
+			qede_update_tx_producer(txq);
 			return NETDEV_TX_OK;
 		}
 
@@ -684,6 +701,7 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb,
 		if (rc) {
 			qede_free_failed_tx_pkt(edev, txq, first_bd, nbd,
 						data_split);
+			qede_update_tx_producer(txq);
 			return NETDEV_TX_OK;
 		}
 	}
@@ -704,20 +722,8 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb,
 	txq->tx_db.data.bd_prod =
 		cpu_to_le16(qed_chain_get_prod_idx(&txq->tx_pbl));
 
-	/* wmb makes sure that the BDs data is updated before updating the
-	 * producer, otherwise FW may read old data from the BDs.
-	 */
-	wmb();
-	barrier();
-	writel(txq->tx_db.raw, txq->doorbell_addr);
-
-	/* mmiowb is needed to synchronize doorbell writes from more than one
-	 * processor. It guarantees that the write arrives to the device before
-	 * the queue lock is released and another start_xmit is called (possibly
-	 * on another CPU). Without this barrier, the next doorbell can bypass
-	 * this doorbell. This is applicable to IA64/Altix systems.
-	 */
-	mmiowb();
+	if (!skb->xmit_more || netif_tx_queue_stopped(netdev_txq))
+		qede_update_tx_producer(txq);
 
 	if (unlikely(qed_chain_get_elem_left(&txq->tx_pbl)
 		      < (MAX_SKB_FRAGS + 1))) {
@@ -1351,6 +1357,20 @@ static u8 qede_check_csum(u16 flag)
 		return qede_check_tunn_csum(flag);
 }
 
+static bool qede_pkt_is_ip_fragmented(struct eth_fast_path_rx_reg_cqe *cqe,
+				      u16 flag)
+{
+	u8 tun_pars_flg = cqe->tunnel_pars_flags.flags;
+
+	if ((tun_pars_flg & (ETH_TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_MASK <<
+			     ETH_TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_SHIFT)) ||
+	    (flag & (PARSING_AND_ERR_FLAGS_IPV4FRAG_MASK <<
+		     PARSING_AND_ERR_FLAGS_IPV4FRAG_SHIFT)))
+		return true;
+
+	return false;
+}
+
 static int qede_rx_int(struct qede_fastpath *fp, int budget)
 {
 	struct qede_dev *edev = fp->edev;
@@ -1429,6 +1449,12 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget)
 
 		csum_flag = qede_check_csum(parse_flag);
 		if (unlikely(csum_flag == QEDE_CSUM_ERROR)) {
+			if (qede_pkt_is_ip_fragmented(&cqe->fast_path_regular,
+						      parse_flag)) {
+				rxq->rx_ip_frags++;
+				goto alloc_skb;
+			}
+
 			DP_NOTICE(edev,
 				  "CQE in CONS = %u has error, flags = %x, dropping incoming packet\n",
 				  sw_comp_cons, parse_flag);
@@ -1437,6 +1463,7 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget)
 			goto next_cqe;
 		}
 
+alloc_skb:
 		skb = netdev_alloc_skb(edev->ndev, QEDE_RX_HDR_SIZE);
 		if (unlikely(!skb)) {
 			DP_NOTICE(edev,
@@ -1447,7 +1474,7 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget)
 		}
 
 		/* Copy data into SKB */
-		if (len + pad <= QEDE_RX_HDR_SIZE) {
+		if (len + pad <= edev->rx_copybreak) {
 			memcpy(skb_put(skb, len),
 			       page_address(data) + pad +
 				sw_rx_data->page_offset, len);
@@ -1579,56 +1606,49 @@ next_cqe: /* don't consume bd rx buffer */
 
 static int qede_poll(struct napi_struct *napi, int budget)
 {
-	int work_done = 0;
 	struct qede_fastpath *fp = container_of(napi, struct qede_fastpath,
-						 napi);
+						napi);
 	struct qede_dev *edev = fp->edev;
+	int rx_work_done = 0;
+	u8 tc;
 
-	while (1) {
-		u8 tc;
-
-		for (tc = 0; tc < edev->num_tc; tc++)
-			if (qede_txq_has_work(&fp->txqs[tc]))
-				qede_tx_int(edev, &fp->txqs[tc]);
-
-		if (qede_has_rx_work(fp->rxq)) {
-			work_done += qede_rx_int(fp, budget - work_done);
-
-			/* must not complete if we consumed full budget */
-			if (work_done >= budget)
-				break;
-		}
+	for (tc = 0; tc < edev->num_tc; tc++)
+		if (qede_txq_has_work(&fp->txqs[tc]))
+			qede_tx_int(edev, &fp->txqs[tc]);
+
+	rx_work_done = qede_has_rx_work(fp->rxq) ?
+			qede_rx_int(fp, budget) : 0;
+	if (rx_work_done < budget) {
+		qed_sb_update_sb_idx(fp->sb_info);
+		/* *_has_*_work() reads the status block,
+		 * thus we need to ensure that status block indices
+		 * have been actually read (qed_sb_update_sb_idx)
+		 * prior to this check (*_has_*_work) so that
+		 * we won't write the "newer" value of the status block
+		 * to HW (if there was a DMA right after
+		 * qede_has_rx_work and if there is no rmb, the memory
+		 * reading (qed_sb_update_sb_idx) may be postponed
+		 * to right before *_ack_sb). In this case there
+		 * will never be another interrupt until there is
+		 * another update of the status block, while there
+		 * is still unhandled work.
+		 */
+		rmb();
 
 		/* Fall out from the NAPI loop if needed */
-		if (!(qede_has_rx_work(fp->rxq) || qede_has_tx_work(fp))) {
-			qed_sb_update_sb_idx(fp->sb_info);
-			/* *_has_*_work() reads the status block,
-			 * thus we need to ensure that status block indices
-			 * have been actually read (qed_sb_update_sb_idx)
-			 * prior to this check (*_has_*_work) so that
-			 * we won't write the "newer" value of the status block
-			 * to HW (if there was a DMA right after
-			 * qede_has_rx_work and if there is no rmb, the memory
-			 * reading (qed_sb_update_sb_idx) may be postponed
-			 * to right before *_ack_sb). In this case there
-			 * will never be another interrupt until there is
-			 * another update of the status block, while there
-			 * is still unhandled work.
-			 */
-			rmb();
-
-			if (!(qede_has_rx_work(fp->rxq) ||
-			      qede_has_tx_work(fp))) {
-				napi_complete(napi);
-				/* Update and reenable interrupts */
-				qed_sb_ack(fp->sb_info, IGU_INT_ENABLE,
-					   1 /*update*/);
-				break;
-			}
+		if (!(qede_has_rx_work(fp->rxq) ||
+		      qede_has_tx_work(fp))) {
+			napi_complete(napi);
+
+			/* Update and reenable interrupts */
+			qed_sb_ack(fp->sb_info, IGU_INT_ENABLE,
+				   1 /*update*/);
+		} else {
+			rx_work_done = budget;
 		}
 	}
 
-	return work_done;
+	return rx_work_done;
 }
 
 static irqreturn_t qede_msix_fp_int(int irq, void *fp_cookie)
@@ -2110,75 +2130,75 @@ int qede_set_features(struct net_device *dev, netdev_features_t features)
 	return 0;
 }
 
-#ifdef CONFIG_QEDE_VXLAN
-static void qede_add_vxlan_port(struct net_device *dev,
-				sa_family_t sa_family, __be16 port)
+static void qede_udp_tunnel_add(struct net_device *dev,
+				struct udp_tunnel_info *ti)
 {
 	struct qede_dev *edev = netdev_priv(dev);
-	u16 t_port = ntohs(port);
+	u16 t_port = ntohs(ti->port);
 
-	if (edev->vxlan_dst_port)
-		return;
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		if (edev->vxlan_dst_port)
+			return;
 
-	edev->vxlan_dst_port = t_port;
+		edev->vxlan_dst_port = t_port;
 
-	DP_VERBOSE(edev, QED_MSG_DEBUG, "Added vxlan port=%d", t_port);
+		DP_VERBOSE(edev, QED_MSG_DEBUG, "Added vxlan port=%d",
+			   t_port);
 
-	set_bit(QEDE_SP_VXLAN_PORT_CONFIG, &edev->sp_flags);
-	schedule_delayed_work(&edev->sp_task, 0);
-}
+		set_bit(QEDE_SP_VXLAN_PORT_CONFIG, &edev->sp_flags);
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (edev->geneve_dst_port)
+			return;
 
-static void qede_del_vxlan_port(struct net_device *dev,
-				sa_family_t sa_family, __be16 port)
-{
-	struct qede_dev *edev = netdev_priv(dev);
-	u16 t_port = ntohs(port);
+		edev->geneve_dst_port = t_port;
 
-	if (t_port != edev->vxlan_dst_port)
+		DP_VERBOSE(edev, QED_MSG_DEBUG, "Added geneve port=%d",
+			   t_port);
+		set_bit(QEDE_SP_GENEVE_PORT_CONFIG, &edev->sp_flags);
+		break;
+	default:
 		return;
+	}
 
-	edev->vxlan_dst_port = 0;
-
-	DP_VERBOSE(edev, QED_MSG_DEBUG, "Deleted vxlan port=%d", t_port);
-
-	set_bit(QEDE_SP_VXLAN_PORT_CONFIG, &edev->sp_flags);
 	schedule_delayed_work(&edev->sp_task, 0);
 }
-#endif
 
-#ifdef CONFIG_QEDE_GENEVE
-static void qede_add_geneve_port(struct net_device *dev,
-				 sa_family_t sa_family, __be16 port)
+static void qede_udp_tunnel_del(struct net_device *dev,
+				struct udp_tunnel_info *ti)
 {
 	struct qede_dev *edev = netdev_priv(dev);
-	u16 t_port = ntohs(port);
+	u16 t_port = ntohs(ti->port);
 
-	if (edev->geneve_dst_port)
-		return;
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		if (t_port != edev->vxlan_dst_port)
+			return;
 
-	edev->geneve_dst_port = t_port;
+		edev->vxlan_dst_port = 0;
 
-	DP_VERBOSE(edev, QED_MSG_DEBUG, "Added geneve port=%d", t_port);
-	set_bit(QEDE_SP_GENEVE_PORT_CONFIG, &edev->sp_flags);
-	schedule_delayed_work(&edev->sp_task, 0);
-}
+		DP_VERBOSE(edev, QED_MSG_DEBUG, "Deleted vxlan port=%d",
+			   t_port);
 
-static void qede_del_geneve_port(struct net_device *dev,
-				 sa_family_t sa_family, __be16 port)
-{
-	struct qede_dev *edev = netdev_priv(dev);
-	u16 t_port = ntohs(port);
+		set_bit(QEDE_SP_VXLAN_PORT_CONFIG, &edev->sp_flags);
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (t_port != edev->geneve_dst_port)
+			return;
 
-	if (t_port != edev->geneve_dst_port)
-		return;
+		edev->geneve_dst_port = 0;
 
-	edev->geneve_dst_port = 0;
+		DP_VERBOSE(edev, QED_MSG_DEBUG, "Deleted geneve port=%d",
+			   t_port);
+		set_bit(QEDE_SP_GENEVE_PORT_CONFIG, &edev->sp_flags);
+		break;
+	default:
+		return;
+	}
 
-	DP_VERBOSE(edev, QED_MSG_DEBUG, "Deleted geneve port=%d", t_port);
-	set_bit(QEDE_SP_GENEVE_PORT_CONFIG, &edev->sp_flags);
 	schedule_delayed_work(&edev->sp_task, 0);
 }
-#endif
 
 static const struct net_device_ops qede_netdev_ops = {
 	.ndo_open = qede_open,
@@ -2202,14 +2222,8 @@ static const struct net_device_ops qede_netdev_ops = {
 	.ndo_get_vf_config = qede_get_vf_config,
 	.ndo_set_vf_rate = qede_set_vf_rate,
 #endif
-#ifdef CONFIG_QEDE_VXLAN
-	.ndo_add_vxlan_port = qede_add_vxlan_port,
-	.ndo_del_vxlan_port = qede_del_vxlan_port,
-#endif
-#ifdef CONFIG_QEDE_GENEVE
-	.ndo_add_geneve_port = qede_add_geneve_port,
-	.ndo_del_geneve_port = qede_del_geneve_port,
-#endif
+	.ndo_udp_tunnel_add = qede_udp_tunnel_add,
+	.ndo_udp_tunnel_del = qede_udp_tunnel_del,
 };
 
 /* -------------------------------------------------------------------------
@@ -2499,8 +2513,13 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 
 	edev->ops->register_ops(cdev, &qede_ll_ops, edev);
 
+#ifdef CONFIG_DCB
+	qede_set_dcbnl_ops(edev->ndev);
+#endif
+
 	INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task);
 	mutex_init(&edev->qede_lock);
+	edev->rx_copybreak = QEDE_RX_HDR_SIZE;
 
 	DP_INFO(edev, "Ending successfully qede probe\n");
 
@@ -3227,7 +3246,7 @@ static int qede_stop_queues(struct qede_dev *edev)
 	return rc;
 }
 
-static int qede_start_queues(struct qede_dev *edev)
+static int qede_start_queues(struct qede_dev *edev, bool clear_stats)
 {
 	int rc, tc, i;
 	int vlan_removal_en = 1;
@@ -3458,6 +3477,7 @@ out:
 
 enum qede_load_mode {
 	QEDE_LOAD_NORMAL,
+	QEDE_LOAD_RELOAD,
 };
 
 static int qede_load(struct qede_dev *edev, enum qede_load_mode mode)
@@ -3496,7 +3516,7 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode)
 		goto err3;
 	DP_INFO(edev, "Setup IRQs succeeded\n");
 
-	rc = qede_start_queues(edev);
+	rc = qede_start_queues(edev, mode != QEDE_LOAD_RELOAD);
 	if (rc)
 		goto err4;
 	DP_INFO(edev, "Start VPORT, RXQ and TXQ succeeded\n");
@@ -3551,7 +3571,7 @@ void qede_reload(struct qede_dev *edev,
 	if (func)
 		func(edev, args);
 
-	qede_load(edev, QEDE_LOAD_NORMAL);
+	qede_load(edev, QEDE_LOAD_RELOAD);
 
 	mutex_lock(&edev->qede_lock);
 	qede_config_rx_mode(edev->ndev);
@@ -3573,12 +3593,8 @@ static int qede_open(struct net_device *ndev)
 	if (rc)
 		return rc;
 
-#ifdef CONFIG_QEDE_VXLAN
-	vxlan_get_rx_port(ndev);
-#endif
-#ifdef CONFIG_QEDE_GENEVE
-	geneve_get_rx_port(ndev);
-#endif
+	udp_tunnel_get_rx_info(ndev);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index caf6ddb7ea76..fd973f4f16c7 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1026,10 +1026,8 @@ struct qlcnic_ipaddr {
 #define QLCNIC_HAS_PHYS_PORT_ID		0x40000
 #define QLCNIC_TSS_RSS			0x80000
 
-#ifdef CONFIG_QLCNIC_VXLAN
 #define QLCNIC_ADD_VXLAN_PORT		0x100000
 #define QLCNIC_DEL_VXLAN_PORT		0x200000
-#endif
 
 #define QLCNIC_VLAN_FILTERING		0x800000
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index f9640d5ce6ba..bdbcd2b088a0 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -2159,7 +2159,6 @@ int qlcnic_83xx_get_mac_address(struct qlcnic_adapter *adapter, u8 *mac,
 	struct qlcnic_cmd_args cmd;
 	u32 mac_low, mac_high;
 
-	function = 0;
 	err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_MAC_ADDRESS);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index bf892160dd5f..a496390b8632 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -1020,7 +1020,6 @@ static int qlcnic_83xx_idc_check_state_validity(struct qlcnic_adapter *adapter,
 	return 0;
 }
 
-#ifdef CONFIG_QLCNIC_VXLAN
 #define QLC_83XX_ENCAP_TYPE_VXLAN	BIT_1
 #define QLC_83XX_MATCH_ENCAP_ID		BIT_2
 #define QLC_83XX_SET_VXLAN_UDP_DPORT	BIT_3
@@ -1089,14 +1088,12 @@ static int qlcnic_set_vxlan_parsing(struct qlcnic_adapter *adapter,
 
 	return ret;
 }
-#endif
 
 static void qlcnic_83xx_periodic_tasks(struct qlcnic_adapter *adapter)
 {
 	if (adapter->fhash.fnum)
 		qlcnic_prune_lb_filters(adapter);
 
-#ifdef CONFIG_QLCNIC_VXLAN
 	if (adapter->flags & QLCNIC_ADD_VXLAN_PORT) {
 		if (qlcnic_set_vxlan_port(adapter))
 			return;
@@ -1112,7 +1109,6 @@ static void qlcnic_83xx_periodic_tasks(struct qlcnic_adapter *adapter)
 		adapter->ahw->vxlan_port = 0;
 		adapter->flags &= ~QLCNIC_DEL_VXLAN_PORT;
 	}
-#endif
 }
 
 /**
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 7bd6f25b4625..607bb7d4514d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -2220,7 +2220,7 @@ void qlcnic_83xx_process_rcv_ring_diag(struct qlcnic_host_sds_ring *sds_ring)
 	if (!opcode)
 		return;
 
-	ring = QLCNIC_FETCH_RING_ID(qlcnic_83xx_hndl(sts_data[0]));
+	ring = QLCNIC_FETCH_RING_ID(sts_data[0]);
 	qlcnic_83xx_process_rcv_diag(adapter, ring, sts_data);
 	desc = &sds_ring->desc_head[consumer];
 	desc->status_desc_data[0] = cpu_to_le64(STATUS_OWNER_PHANTOM);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 1c29105b6c36..3ebef27e0964 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -16,9 +16,7 @@
 #include <linux/aer.h>
 #include <linux/log2.h>
 #include <linux/pci.h>
-#ifdef CONFIG_QLCNIC_VXLAN
 #include <net/vxlan.h>
-#endif
 
 #include "qlcnic.h"
 #include "qlcnic_sriov.h"
@@ -474,13 +472,15 @@ static int qlcnic_get_phys_port_id(struct net_device *netdev,
 	return 0;
 }
 
-#ifdef CONFIG_QLCNIC_VXLAN
 static void qlcnic_add_vxlan_port(struct net_device *netdev,
-				  sa_family_t sa_family, __be16 port)
+				  struct udp_tunnel_info *ti)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
 	/* Adapter supports only one VXLAN port. Use very first port
 	 * for enabling offload
 	 */
@@ -488,23 +488,26 @@ static void qlcnic_add_vxlan_port(struct net_device *netdev,
 		return;
 	if (!ahw->vxlan_port_count) {
 		ahw->vxlan_port_count = 1;
-		ahw->vxlan_port = ntohs(port);
+		ahw->vxlan_port = ntohs(ti->port);
 		adapter->flags |= QLCNIC_ADD_VXLAN_PORT;
 		return;
 	}
-	if (ahw->vxlan_port == ntohs(port))
+	if (ahw->vxlan_port == ntohs(ti->port))
 		ahw->vxlan_port_count++;
 
 }
 
 static void qlcnic_del_vxlan_port(struct net_device *netdev,
-				  sa_family_t sa_family, __be16 port)
+				  struct udp_tunnel_info *ti)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
 	if (!qlcnic_encap_rx_offload(adapter) || !ahw->vxlan_port_count ||
-	    (ahw->vxlan_port != ntohs(port)))
+	    (ahw->vxlan_port != ntohs(ti->port)))
 		return;
 
 	ahw->vxlan_port_count--;
@@ -519,7 +522,6 @@ static netdev_features_t qlcnic_features_check(struct sk_buff *skb,
 	features = vlan_features_check(skb, features);
 	return vxlan_features_check(skb, features);
 }
-#endif
 
 static const struct net_device_ops qlcnic_netdev_ops = {
 	.ndo_open	   = qlcnic_open,
@@ -539,11 +541,9 @@ static const struct net_device_ops qlcnic_netdev_ops = {
 	.ndo_fdb_del		= qlcnic_fdb_del,
 	.ndo_fdb_dump		= qlcnic_fdb_dump,
 	.ndo_get_phys_port_id	= qlcnic_get_phys_port_id,
-#ifdef CONFIG_QLCNIC_VXLAN
-	.ndo_add_vxlan_port	= qlcnic_add_vxlan_port,
-	.ndo_del_vxlan_port	= qlcnic_del_vxlan_port,
+	.ndo_udp_tunnel_add	= qlcnic_add_vxlan_port,
+	.ndo_udp_tunnel_del	= qlcnic_del_vxlan_port,
 	.ndo_features_check	= qlcnic_features_check,
-#endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = qlcnic_poll_controller,
 #endif
@@ -2015,10 +2015,8 @@ qlcnic_attach(struct qlcnic_adapter *adapter)
 
 	qlcnic_create_sysfs_entries(adapter);
 
-#ifdef CONFIG_QLCNIC_VXLAN
 	if (qlcnic_encap_rx_offload(adapter))
-		vxlan_get_rx_port(netdev);
-#endif
+		udp_tunnel_get_rx_info(netdev);
 
 	adapter->is_up = QLCNIC_ADAPTER_UP_MAGIC;
 	return 0;
diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c
index 6b541e57c96a..cb29ee24cf1b 100644
--- a/drivers/net/ethernet/rdc/r6040.c
+++ b/drivers/net/ethernet/rdc/r6040.c
@@ -4,7 +4,7 @@
  * Copyright (C) 2004 Sten Wang <[email protected]>
  * Copyright (C) 2007
  *	Daniel Gimpelevich <[email protected]>
- * Copyright (C) 2007-2012 Florian Fainelli <[email protected]>
+ * Copyright (C) 2007-2012 Florian Fainelli <[email protected]>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -48,8 +48,8 @@
 #include <asm/processor.h>
 
 #define DRV_NAME	"r6040"
-#define DRV_VERSION	"0.28"
-#define DRV_RELDATE	"07Oct2011"
+#define DRV_VERSION	"0.29"
+#define DRV_RELDATE	"04Jul2016"
 
 /* Time in jiffies before concluding the transmitter is hung. */
 #define TX_TIMEOUT	(6000 * HZ / 1000)
@@ -162,7 +162,7 @@
 
 MODULE_AUTHOR("Sten Wang <[email protected]>,"
 	"Daniel Gimpelevich <[email protected]>,"
-	"Florian Fainelli <[email protected]>");
+	"Florian Fainelli <[email protected]>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("RDC R6040 NAPI PCI FastEthernet driver");
 MODULE_VERSION(DRV_VERSION " " DRV_RELDATE);
@@ -200,7 +200,6 @@ struct r6040_private {
 	struct mii_bus *mii_bus;
 	struct napi_struct napi;
 	void __iomem *base;
-	struct phy_device *phydev;
 	int old_link;
 	int old_duplex;
 };
@@ -474,7 +473,7 @@ static void r6040_down(struct net_device *dev)
 	iowrite16(adrp[1], ioaddr + MID_0M);
 	iowrite16(adrp[2], ioaddr + MID_0H);
 
-	phy_stop(lp->phydev);
+	phy_stop(dev->phydev);
 }
 
 static int r6040_close(struct net_device *dev)
@@ -515,12 +514,10 @@ static int r6040_close(struct net_device *dev)
 
 static int r6040_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct r6040_private *lp = netdev_priv(dev);
-
-	if (!lp->phydev)
+	if (!dev->phydev)
 		return -EINVAL;
 
-	return phy_mii_ioctl(lp->phydev, rq, cmd);
+	return phy_mii_ioctl(dev->phydev, rq, cmd);
 }
 
 static int r6040_rx(struct net_device *dev, int limit)
@@ -617,10 +614,15 @@ static void r6040_tx(struct net_device *dev)
 		if (descptr->status & DSC_OWNER_MAC)
 			break; /* Not complete */
 		skb_ptr = descptr->skb_ptr;
+
+		/* Statistic Counter */
+		dev->stats.tx_packets++;
+		dev->stats.tx_bytes += skb_ptr->len;
+
 		pci_unmap_single(priv->pdev, le32_to_cpu(descptr->buf),
 			skb_ptr->len, PCI_DMA_TODEVICE);
 		/* Free buffer */
-		dev_kfree_skb_irq(skb_ptr);
+		dev_kfree_skb(skb_ptr);
 		descptr->skb_ptr = NULL;
 		/* To next descriptor */
 		descptr = descptr->vndescp;
@@ -641,12 +643,15 @@ static int r6040_poll(struct napi_struct *napi, int budget)
 	void __iomem *ioaddr = priv->base;
 	int work_done;
 
+	r6040_tx(dev);
+
 	work_done = r6040_rx(dev, budget);
 
 	if (work_done < budget) {
-		napi_complete(napi);
-		/* Enable RX interrupt */
-		iowrite16(ioread16(ioaddr + MIER) | RX_INTS, ioaddr + MIER);
+		napi_complete_done(napi, work_done);
+		/* Enable RX/TX interrupt */
+		iowrite16(ioread16(ioaddr + MIER) | RX_INTS | TX_INTS,
+			  ioaddr + MIER);
 	}
 	return work_done;
 }
@@ -673,7 +678,7 @@ static irqreturn_t r6040_interrupt(int irq, void *dev_id)
 	}
 
 	/* RX interrupt request */
-	if (status & RX_INTS) {
+	if (status & (RX_INTS | TX_INTS)) {
 		if (status & RX_NO_DESC) {
 			/* RX descriptor unavailable */
 			dev->stats.rx_dropped++;
@@ -684,15 +689,11 @@ static irqreturn_t r6040_interrupt(int irq, void *dev_id)
 
 		if (likely(napi_schedule_prep(&lp->napi))) {
 			/* Mask off RX interrupt */
-			misr &= ~RX_INTS;
-			__napi_schedule(&lp->napi);
+			misr &= ~(RX_INTS | TX_INTS);
+			__napi_schedule_irqoff(&lp->napi);
 		}
 	}
 
-	/* TX interrupt request */
-	if (status & TX_INTS)
-		r6040_tx(dev);
-
 	/* Restore RDC MAC interrupt */
 	iowrite16(misr, ioaddr + MIER);
 
@@ -732,7 +733,7 @@ static int r6040_up(struct net_device *dev)
 	/* Initialize all MAC registers */
 	r6040_init_mac_regs(dev);
 
-	phy_start(lp->phydev);
+	phy_start(dev->phydev);
 
 	return 0;
 }
@@ -813,6 +814,9 @@ static netdev_tx_t r6040_start_xmit(struct sk_buff *skb,
 	void __iomem *ioaddr = lp->base;
 	unsigned long flags;
 
+	if (skb_put_padto(skb, ETH_ZLEN) < 0)
+		return NETDEV_TX_OK;
+
 	/* Critical Section */
 	spin_lock_irqsave(&lp->lock, flags);
 
@@ -824,17 +828,10 @@ static netdev_tx_t r6040_start_xmit(struct sk_buff *skb,
 		return NETDEV_TX_BUSY;
 	}
 
-	/* Statistic Counter */
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
 	/* Set TX descriptor & Transmit it */
 	lp->tx_free_desc--;
 	descptr = lp->tx_insert_ptr;
-	if (skb->len < ETH_ZLEN)
-		descptr->len = ETH_ZLEN;
-	else
-		descptr->len = skb->len;
-
+	descptr->len = skb->len;
 	descptr->skb_ptr = skb;
 	descptr->buf = cpu_to_le32(pci_map_single(lp->pdev,
 		skb->data, skb->len, PCI_DMA_TODEVICE));
@@ -843,7 +840,8 @@ static netdev_tx_t r6040_start_xmit(struct sk_buff *skb,
 	skb_tx_timestamp(skb);
 
 	/* Trigger the MAC to check the TX descriptor */
-	iowrite16(TM2TX, ioaddr + MTPR);
+	if (!skb->xmit_more || netif_queue_stopped(dev))
+		iowrite16(TM2TX, ioaddr + MTPR);
 	lp->tx_insert_ptr = descptr->vndescp;
 
 	/* If no tx resource, stop */
@@ -957,26 +955,12 @@ static void netdev_get_drvinfo(struct net_device *dev,
 	strlcpy(info->bus_info, pci_name(rp->pdev), sizeof(info->bus_info));
 }
 
-static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct r6040_private *rp = netdev_priv(dev);
-
-	return  phy_ethtool_gset(rp->phydev, cmd);
-}
-
-static int netdev_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct r6040_private *rp = netdev_priv(dev);
-
-	return phy_ethtool_sset(rp->phydev, cmd);
-}
-
 static const struct ethtool_ops netdev_ethtool_ops = {
 	.get_drvinfo		= netdev_get_drvinfo,
-	.get_settings		= netdev_get_settings,
-	.set_settings		= netdev_set_settings,
 	.get_link		= ethtool_op_get_link,
 	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
 static const struct net_device_ops r6040_netdev_ops = {
@@ -998,7 +982,7 @@ static const struct net_device_ops r6040_netdev_ops = {
 static void r6040_adjust_link(struct net_device *dev)
 {
 	struct r6040_private *lp = netdev_priv(dev);
-	struct phy_device *phydev = lp->phydev;
+	struct phy_device *phydev = dev->phydev;
 	int status_changed = 0;
 	void __iomem *ioaddr = lp->base;
 
@@ -1018,14 +1002,8 @@ static void r6040_adjust_link(struct net_device *dev)
 		lp->old_duplex = phydev->duplex;
 	}
 
-	if (status_changed) {
-		pr_info("%s: link %s", dev->name, phydev->link ?
-			"UP" : "DOWN");
-		if (phydev->link)
-			pr_cont(" - %d/%s", phydev->speed,
-			DUPLEX_FULL == phydev->duplex ? "full" : "half");
-		pr_cont("\n");
-	}
+	if (status_changed)
+		phy_print_status(phydev);
 }
 
 static int r6040_mii_probe(struct net_device *dev)
@@ -1057,7 +1035,6 @@ static int r6040_mii_probe(struct net_device *dev)
 				| SUPPORTED_TP);
 
 	phydev->advertising = phydev->supported;
-	lp->phydev = phydev;
 	lp->old_link = 0;
 	lp->old_duplex = -1;
 
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 28b775e5a9ad..f0b09b05ed3f 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -1996,7 +1996,8 @@ static int rocker_port_change_proto_down(struct net_device *dev,
 	return 0;
 }
 
-static void rocker_port_neigh_destroy(struct neighbour *n)
+static void rocker_port_neigh_destroy(struct net_device *dev,
+				      struct neighbour *n)
 {
 	struct rocker_port *rocker_port = netdev_priv(n->dev);
 	int err;
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h
index 45019649bbbd..5cb51b609f02 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h
@@ -475,7 +475,6 @@ struct sxgbe_priv_data {
 	int rxcsum_insertion;
 	spinlock_t stats_lock;	/* lock for tx/rx statatics */
 
-	struct phy_device *phydev;
 	int oldlink;
 	int speed;
 	int oldduplex;
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
index c0981ae45874..542b67d436df 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
@@ -147,7 +147,7 @@ static int sxgbe_get_eee(struct net_device *dev,
 	edata->eee_active = priv->eee_active;
 	edata->tx_lpi_timer = priv->tx_lpi_timer;
 
-	return phy_ethtool_get_eee(priv->phydev, edata);
+	return phy_ethtool_get_eee(dev->phydev, edata);
 }
 
 static int sxgbe_set_eee(struct net_device *dev,
@@ -172,7 +172,7 @@ static int sxgbe_set_eee(struct net_device *dev,
 		priv->tx_lpi_timer = edata->tx_lpi_timer;
 	}
 
-	return phy_ethtool_set_eee(priv->phydev, edata);
+	return phy_ethtool_set_eee(dev->phydev, edata);
 }
 
 static void sxgbe_getdrvinfo(struct net_device *dev,
@@ -182,27 +182,6 @@ static void sxgbe_getdrvinfo(struct net_device *dev,
 	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 }
 
-static int sxgbe_getsettings(struct net_device *dev,
-			     struct ethtool_cmd *cmd)
-{
-	struct sxgbe_priv_data *priv = netdev_priv(dev);
-
-	if (priv->phydev)
-		return phy_ethtool_gset(priv->phydev, cmd);
-
-	return -EOPNOTSUPP;
-}
-
-static int sxgbe_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct sxgbe_priv_data *priv = netdev_priv(dev);
-
-	if (priv->phydev)
-		return phy_ethtool_sset(priv->phydev, cmd);
-
-	return -EOPNOTSUPP;
-}
-
 static u32 sxgbe_getmsglevel(struct net_device *dev)
 {
 	struct sxgbe_priv_data *priv = netdev_priv(dev);
@@ -255,7 +234,7 @@ static void sxgbe_get_ethtool_stats(struct net_device *dev,
 	char *p;
 
 	if (priv->eee_enabled) {
-		int val = phy_get_eee_err(priv->phydev);
+		int val = phy_get_eee_err(dev->phydev);
 
 		if (val)
 			priv->xstats.eee_wakeup_error_n = val;
@@ -499,8 +478,6 @@ static int sxgbe_get_regs_len(struct net_device *dev)
 
 static const struct ethtool_ops sxgbe_ethtool_ops = {
 	.get_drvinfo = sxgbe_getdrvinfo,
-	.get_settings = sxgbe_getsettings,
-	.set_settings = sxgbe_setsettings,
 	.get_msglevel = sxgbe_getmsglevel,
 	.set_msglevel = sxgbe_setmsglevel,
 	.get_link = ethtool_op_get_link,
@@ -516,6 +493,8 @@ static const struct ethtool_ops sxgbe_ethtool_ops = {
 	.get_regs_len = sxgbe_get_regs_len,
 	.get_eee = sxgbe_get_eee,
 	.set_eee = sxgbe_set_eee,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 void sxgbe_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index 413ea14ab91f..ea44a2456ce1 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -124,12 +124,13 @@ static void sxgbe_eee_ctrl_timer(unsigned long arg)
  */
 bool sxgbe_eee_init(struct sxgbe_priv_data * const priv)
 {
+	struct net_device *ndev = priv->dev;
 	bool ret = false;
 
 	/* MAC core supports the EEE feature. */
 	if (priv->hw_cap.eee) {
 		/* Check if the PHY supports EEE */
-		if (phy_init_eee(priv->phydev, 1))
+		if (phy_init_eee(ndev->phydev, 1))
 			return false;
 
 		priv->eee_active = 1;
@@ -152,12 +153,14 @@ bool sxgbe_eee_init(struct sxgbe_priv_data * const priv)
 
 static void sxgbe_eee_adjust(const struct sxgbe_priv_data *priv)
 {
+	struct net_device *ndev = priv->dev;
+
 	/* When the EEE has been already initialised we have to
 	 * modify the PLS bit in the LPI ctrl & status reg according
 	 * to the PHY link status. For this reason.
 	 */
 	if (priv->eee_enabled)
-		priv->hw->mac->set_eee_pls(priv->ioaddr, priv->phydev->link);
+		priv->hw->mac->set_eee_pls(priv->ioaddr, ndev->phydev->link);
 }
 
 /**
@@ -203,7 +206,7 @@ static inline u32 sxgbe_tx_avail(struct sxgbe_tx_queue *queue, int tx_qsize)
 static void sxgbe_adjust_link(struct net_device *dev)
 {
 	struct sxgbe_priv_data *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	u8 new_state = 0;
 	u8 speed = 0xff;
 
@@ -306,9 +309,6 @@ static int sxgbe_init_phy(struct net_device *ndev)
 	netdev_dbg(ndev, "%s: attached to PHY (UID 0x%x) Link = %d\n",
 		   __func__, phydev->phy_id, phydev->link);
 
-	/* save phy device in private structure */
-	priv->phydev = phydev;
-
 	return 0;
 }
 
@@ -1173,8 +1173,8 @@ static int sxgbe_open(struct net_device *dev)
 	priv->hw->dma->start_tx(priv->ioaddr, SXGBE_TX_QUEUES);
 	priv->hw->dma->start_rx(priv->ioaddr, SXGBE_RX_QUEUES);
 
-	if (priv->phydev)
-		phy_start(priv->phydev);
+	if (dev->phydev)
+		phy_start(dev->phydev);
 
 	/* initialise TX coalesce parameters */
 	sxgbe_tx_init_coalesce(priv);
@@ -1194,8 +1194,8 @@ static int sxgbe_open(struct net_device *dev)
 
 init_error:
 	free_dma_desc_resources(priv);
-	if (priv->phydev)
-		phy_disconnect(priv->phydev);
+	if (dev->phydev)
+		phy_disconnect(dev->phydev);
 phy_error:
 	clk_disable_unprepare(priv->sxgbe_clk);
 
@@ -1216,10 +1216,9 @@ static int sxgbe_release(struct net_device *dev)
 		del_timer_sync(&priv->eee_ctrl_timer);
 
 	/* Stop and disconnect the PHY */
-	if (priv->phydev) {
-		phy_stop(priv->phydev);
-		phy_disconnect(priv->phydev);
-		priv->phydev = NULL;
+	if (dev->phydev) {
+		phy_stop(dev->phydev);
+		phy_disconnect(dev->phydev);
 	}
 
 	netif_tx_stop_all_queues(dev);
@@ -1969,7 +1968,6 @@ static void sxgbe_poll_controller(struct net_device *dev)
  */
 static int sxgbe_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct sxgbe_priv_data *priv = netdev_priv(dev);
 	int ret = -EOPNOTSUPP;
 
 	if (!netif_running(dev))
@@ -1979,9 +1977,9 @@ static int sxgbe_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
-		if (!priv->phydev)
+		if (!dev->phydev)
 			return -EINVAL;
-		ret = phy_mii_ioctl(priv->phydev, rq, cmd);
+		ret = phy_mii_ioctl(dev->phydev, rq, cmd);
 		break;
 	default:
 		break;
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 1f309127457d..f658fee74f18 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -50,14 +50,34 @@ enum {
 #define HUNT_FILTER_TBL_ROWS 8192
 
 #define EFX_EF10_FILTER_ID_INVALID 0xffff
+
+#define EFX_EF10_FILTER_DEV_UC_MAX	32
+#define EFX_EF10_FILTER_DEV_MC_MAX	256
+
+/* VLAN list entry */
+struct efx_ef10_vlan {
+	struct list_head list;
+	u16 vid;
+};
+
+/* Per-VLAN filters information */
+struct efx_ef10_filter_vlan {
+	struct list_head list;
+	u16 vid;
+	u16 uc[EFX_EF10_FILTER_DEV_UC_MAX];
+	u16 mc[EFX_EF10_FILTER_DEV_MC_MAX];
+	u16 ucdef;
+	u16 bcast;
+	u16 mcdef;
+};
+
 struct efx_ef10_dev_addr {
 	u8 addr[ETH_ALEN];
-	u16 id;
 };
 
 struct efx_ef10_filter_table {
-/* The RX match field masks supported by this fw & hw, in order of priority */
-	enum efx_filter_match_flags rx_match_flags[
+/* The MCDI match masks supported by this fw & hw, in order of priority */
+	u32 rx_match_mcdi_flags[
 		MC_CMD_GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES_MAXNUM];
 	unsigned int rx_match_count;
 
@@ -73,16 +93,16 @@ struct efx_ef10_filter_table {
 	} *entry;
 	wait_queue_head_t waitq;
 /* Shadow of net_device address lists, guarded by mac_lock */
-#define EFX_EF10_FILTER_DEV_UC_MAX	32
-#define EFX_EF10_FILTER_DEV_MC_MAX	256
 	struct efx_ef10_dev_addr dev_uc_list[EFX_EF10_FILTER_DEV_UC_MAX];
 	struct efx_ef10_dev_addr dev_mc_list[EFX_EF10_FILTER_DEV_MC_MAX];
 	int dev_uc_count;
 	int dev_mc_count;
-/* Indices (like efx_ef10_dev_addr.id) for promisc/allmulti filters */
-	u16 ucdef_id;
-	u16 bcast_id;
-	u16 mcdef_id;
+	bool uc_promisc;
+	bool mc_promisc;
+/* Whether in multicast promiscuous mode when last changed */
+	bool mc_promisc_last;
+	bool vlan_filter;
+	struct list_head vlan_list;
 };
 
 /* An arbitrary search limit for the software hash table */
@@ -90,6 +110,10 @@ struct efx_ef10_filter_table {
 
 static void efx_ef10_rx_free_indir_table(struct efx_nic *efx);
 static void efx_ef10_filter_table_remove(struct efx_nic *efx);
+static int efx_ef10_filter_add_vlan(struct efx_nic *efx, u16 vid);
+static void efx_ef10_filter_del_vlan_internal(struct efx_nic *efx,
+					      struct efx_ef10_filter_vlan *vlan);
+static void efx_ef10_filter_del_vlan(struct efx_nic *efx, u16 vid);
 
 static int efx_ef10_get_warm_boot_count(struct efx_nic *efx)
 {
@@ -275,6 +299,131 @@ static ssize_t efx_ef10_show_primary_flag(struct device *dev,
 		       ? 1 : 0);
 }
 
+static struct efx_ef10_vlan *efx_ef10_find_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct efx_ef10_vlan *vlan;
+
+	WARN_ON(!mutex_is_locked(&nic_data->vlan_lock));
+
+	list_for_each_entry(vlan, &nic_data->vlan_list, list) {
+		if (vlan->vid == vid)
+			return vlan;
+	}
+
+	return NULL;
+}
+
+static int efx_ef10_add_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct efx_ef10_vlan *vlan;
+	int rc;
+
+	mutex_lock(&nic_data->vlan_lock);
+
+	vlan = efx_ef10_find_vlan(efx, vid);
+	if (vlan) {
+		/* We add VID 0 on init. 8021q adds it on module init
+		 * for all interfaces with VLAN filtring feature.
+		 */
+		if (vid == 0)
+			goto done_unlock;
+		netif_warn(efx, drv, efx->net_dev,
+			   "VLAN %u already added\n", vid);
+		rc = -EALREADY;
+		goto fail_exist;
+	}
+
+	rc = -ENOMEM;
+	vlan = kzalloc(sizeof(*vlan), GFP_KERNEL);
+	if (!vlan)
+		goto fail_alloc;
+
+	vlan->vid = vid;
+
+	list_add_tail(&vlan->list, &nic_data->vlan_list);
+
+	if (efx->filter_state) {
+		mutex_lock(&efx->mac_lock);
+		down_write(&efx->filter_sem);
+		rc = efx_ef10_filter_add_vlan(efx, vlan->vid);
+		up_write(&efx->filter_sem);
+		mutex_unlock(&efx->mac_lock);
+		if (rc)
+			goto fail_filter_add_vlan;
+	}
+
+done_unlock:
+	mutex_unlock(&nic_data->vlan_lock);
+	return 0;
+
+fail_filter_add_vlan:
+	list_del(&vlan->list);
+	kfree(vlan);
+fail_alloc:
+fail_exist:
+	mutex_unlock(&nic_data->vlan_lock);
+	return rc;
+}
+
+static void efx_ef10_del_vlan_internal(struct efx_nic *efx,
+				       struct efx_ef10_vlan *vlan)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	WARN_ON(!mutex_is_locked(&nic_data->vlan_lock));
+
+	if (efx->filter_state) {
+		down_write(&efx->filter_sem);
+		efx_ef10_filter_del_vlan(efx, vlan->vid);
+		up_write(&efx->filter_sem);
+	}
+
+	list_del(&vlan->list);
+	kfree(vlan);
+}
+
+static int efx_ef10_del_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct efx_ef10_vlan *vlan;
+	int rc = 0;
+
+	/* 8021q removes VID 0 on module unload for all interfaces
+	 * with VLAN filtering feature. We need to keep it to receive
+	 * untagged traffic.
+	 */
+	if (vid == 0)
+		return 0;
+
+	mutex_lock(&nic_data->vlan_lock);
+
+	vlan = efx_ef10_find_vlan(efx, vid);
+	if (!vlan) {
+		netif_err(efx, drv, efx->net_dev,
+			  "VLAN %u to be deleted not found\n", vid);
+		rc = -ENOENT;
+	} else {
+		efx_ef10_del_vlan_internal(efx, vlan);
+	}
+
+	mutex_unlock(&nic_data->vlan_lock);
+
+	return rc;
+}
+
+static void efx_ef10_cleanup_vlans(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct efx_ef10_vlan *vlan, *next_vlan;
+
+	mutex_lock(&nic_data->vlan_lock);
+	list_for_each_entry_safe(vlan, next_vlan, &nic_data->vlan_list, list)
+		efx_ef10_del_vlan_internal(efx, vlan);
+	mutex_unlock(&nic_data->vlan_lock);
+}
+
 static DEVICE_ATTR(link_control_flag, 0444, efx_ef10_show_link_control_flag,
 		   NULL);
 static DEVICE_ATTR(primary_flag, 0444, efx_ef10_show_primary_flag, NULL);
@@ -421,8 +570,30 @@ static int efx_ef10_probe(struct efx_nic *efx)
 #endif
 		ether_addr_copy(nic_data->port_id, efx->net_dev->perm_addr);
 
+	INIT_LIST_HEAD(&nic_data->vlan_list);
+	mutex_init(&nic_data->vlan_lock);
+
+	/* Add unspecified VID to support VLAN filtering being disabled */
+	rc = efx_ef10_add_vlan(efx, EFX_FILTER_VID_UNSPEC);
+	if (rc)
+		goto fail_add_vid_unspec;
+
+	/* If VLAN filtering is enabled, we need VID 0 to get untagged
+	 * traffic.  It is added automatically if 8021q module is loaded,
+	 * but we can't rely on it since module may be not loaded.
+	 */
+	rc = efx_ef10_add_vlan(efx, 0);
+	if (rc)
+		goto fail_add_vid_0;
+
 	return 0;
 
+fail_add_vid_0:
+	efx_ef10_cleanup_vlans(efx);
+fail_add_vid_unspec:
+	mutex_destroy(&nic_data->vlan_lock);
+	efx_ptp_remove(efx);
+	efx_mcdi_mon_remove(efx);
 fail5:
 	device_remove_file(&efx->pci_dev->dev, &dev_attr_primary_flag);
 fail4:
@@ -676,6 +847,9 @@ static void efx_ef10_remove(struct efx_nic *efx)
 	}
 #endif
 
+	efx_ef10_cleanup_vlans(efx);
+	mutex_destroy(&nic_data->vlan_lock);
+
 	efx_ptp_remove(efx);
 
 	efx_mcdi_mon_remove(efx);
@@ -704,6 +878,45 @@ static int efx_ef10_probe_pf(struct efx_nic *efx)
 	return efx_ef10_probe(efx);
 }
 
+int efx_ef10_vadaptor_query(struct efx_nic *efx, unsigned int port_id,
+			    u32 *port_flags, u32 *vadaptor_flags,
+			    unsigned int *vlan_tags)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_QUERY_IN_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_VADAPTOR_QUERY_OUT_LEN);
+	size_t outlen;
+	int rc;
+
+	if (nic_data->datapath_caps &
+	    (1 << MC_CMD_GET_CAPABILITIES_OUT_VADAPTOR_QUERY_LBN)) {
+		MCDI_SET_DWORD(inbuf, VADAPTOR_QUERY_IN_UPSTREAM_PORT_ID,
+			       port_id);
+
+		rc = efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_QUERY, inbuf, sizeof(inbuf),
+				  outbuf, sizeof(outbuf), &outlen);
+		if (rc)
+			return rc;
+
+		if (outlen < sizeof(outbuf)) {
+			rc = -EIO;
+			return rc;
+		}
+	}
+
+	if (port_flags)
+		*port_flags = MCDI_DWORD(outbuf, VADAPTOR_QUERY_OUT_PORT_FLAGS);
+	if (vadaptor_flags)
+		*vadaptor_flags =
+			MCDI_DWORD(outbuf, VADAPTOR_QUERY_OUT_VADAPTOR_FLAGS);
+	if (vlan_tags)
+		*vlan_tags =
+			MCDI_DWORD(outbuf,
+				   VADAPTOR_QUERY_OUT_NUM_AVAILABLE_VLAN_TAGS);
+
+	return 0;
+}
+
 int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_ALLOC_IN_LEN);
@@ -3040,15 +3253,55 @@ static int efx_ef10_filter_push(struct efx_nic *efx,
 	return rc;
 }
 
-static int efx_ef10_filter_rx_match_pri(struct efx_ef10_filter_table *table,
-					enum efx_filter_match_flags match_flags)
+static u32 efx_ef10_filter_mcdi_flags_from_spec(const struct efx_filter_spec *spec)
 {
+	unsigned int match_flags = spec->match_flags;
+	u32 mcdi_flags = 0;
+
+	if (match_flags & EFX_FILTER_MATCH_LOC_MAC_IG) {
+		match_flags &= ~EFX_FILTER_MATCH_LOC_MAC_IG;
+		mcdi_flags |=
+			is_multicast_ether_addr(spec->loc_mac) ?
+			(1 << MC_CMD_FILTER_OP_IN_MATCH_UNKNOWN_MCAST_DST_LBN) :
+			(1 << MC_CMD_FILTER_OP_IN_MATCH_UNKNOWN_UCAST_DST_LBN);
+	}
+
+#define MAP_FILTER_TO_MCDI_FLAG(gen_flag, mcdi_field) {			\
+		unsigned int old_match_flags = match_flags;		\
+		match_flags &= ~EFX_FILTER_MATCH_ ## gen_flag;		\
+		if (match_flags != old_match_flags)			\
+			mcdi_flags |=					\
+				(1 << MC_CMD_FILTER_OP_IN_MATCH_ ##	\
+				 mcdi_field ## _LBN);			\
+	}
+	MAP_FILTER_TO_MCDI_FLAG(REM_HOST, SRC_IP);
+	MAP_FILTER_TO_MCDI_FLAG(LOC_HOST, DST_IP);
+	MAP_FILTER_TO_MCDI_FLAG(REM_MAC, SRC_MAC);
+	MAP_FILTER_TO_MCDI_FLAG(REM_PORT, SRC_PORT);
+	MAP_FILTER_TO_MCDI_FLAG(LOC_MAC, DST_MAC);
+	MAP_FILTER_TO_MCDI_FLAG(LOC_PORT, DST_PORT);
+	MAP_FILTER_TO_MCDI_FLAG(ETHER_TYPE, ETHER_TYPE);
+	MAP_FILTER_TO_MCDI_FLAG(INNER_VID, INNER_VLAN);
+	MAP_FILTER_TO_MCDI_FLAG(OUTER_VID, OUTER_VLAN);
+	MAP_FILTER_TO_MCDI_FLAG(IP_PROTO, IP_PROTO);
+#undef MAP_FILTER_TO_MCDI_FLAG
+
+	/* Did we map them all? */
+	WARN_ON_ONCE(match_flags);
+
+	return mcdi_flags;
+}
+
+static int efx_ef10_filter_pri(struct efx_ef10_filter_table *table,
+			       const struct efx_filter_spec *spec)
+{
+	u32 mcdi_flags = efx_ef10_filter_mcdi_flags_from_spec(spec);
 	unsigned int match_pri;
 
 	for (match_pri = 0;
 	     match_pri < table->rx_match_count;
 	     match_pri++)
-		if (table->rx_match_flags[match_pri] == match_flags)
+		if (table->rx_match_mcdi_flags[match_pri] == mcdi_flags)
 			return match_pri;
 
 	return -EPROTONOSUPPORT;
@@ -3074,7 +3327,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx,
 	    EFX_FILTER_FLAG_RX)
 		return -EINVAL;
 
-	rc = efx_ef10_filter_rx_match_pri(table, spec->match_flags);
+	rc = efx_ef10_filter_pri(table, spec);
 	if (rc < 0)
 		return rc;
 	match_pri = rc;
@@ -3313,7 +3566,7 @@ static int efx_ef10_filter_remove_internal(struct efx_nic *efx,
 	spec = efx_ef10_filter_entry_spec(table, filter_idx);
 	if (!spec ||
 	    (!by_index &&
-	     efx_ef10_filter_rx_match_pri(table, spec->match_flags) !=
+	     efx_ef10_filter_pri(table, spec) !=
 	     filter_id / HUNT_FILTER_TBL_ROWS)) {
 		rc = -ENOENT;
 		goto out_unlock;
@@ -3394,12 +3647,13 @@ static u32 efx_ef10_filter_get_unsafe_id(struct efx_nic *efx, u32 filter_id)
 	return filter_id % HUNT_FILTER_TBL_ROWS;
 }
 
-static int efx_ef10_filter_remove_unsafe(struct efx_nic *efx,
-					 enum efx_filter_priority priority,
-					 u32 filter_id)
+static void efx_ef10_filter_remove_unsafe(struct efx_nic *efx,
+					  enum efx_filter_priority priority,
+					  u32 filter_id)
 {
-	return efx_ef10_filter_remove_internal(efx, 1U << priority,
-					       filter_id, true);
+	if (filter_id == EFX_EF10_FILTER_ID_INVALID)
+		return;
+	efx_ef10_filter_remove_internal(efx, 1U << priority, filter_id, true);
 }
 
 static int efx_ef10_filter_get_safe(struct efx_nic *efx,
@@ -3414,7 +3668,7 @@ static int efx_ef10_filter_get_safe(struct efx_nic *efx,
 	spin_lock_bh(&efx->filter_lock);
 	saved_spec = efx_ef10_filter_entry_spec(table, filter_idx);
 	if (saved_spec && saved_spec->priority == priority &&
-	    efx_ef10_filter_rx_match_pri(table, saved_spec->match_flags) ==
+	    efx_ef10_filter_pri(table, saved_spec) ==
 	    filter_id / HUNT_FILTER_TBL_ROWS) {
 		*spec = *saved_spec;
 		rc = 0;
@@ -3487,8 +3741,7 @@ static s32 efx_ef10_filter_get_rx_ids(struct efx_nic *efx,
 				count = -EMSGSIZE;
 				break;
 			}
-			buf[count++] = (efx_ef10_filter_rx_match_pri(
-						table, spec->match_flags) *
+			buf[count++] = (efx_ef10_filter_pri(table, spec) *
 					HUNT_FILTER_TBL_ROWS +
 					filter_idx);
 		}
@@ -3724,15 +3977,58 @@ static int efx_ef10_filter_match_flags_from_mcdi(u32 mcdi_flags)
 	return match_flags;
 }
 
+static void efx_ef10_filter_cleanup_vlans(struct efx_nic *efx)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
+	struct efx_ef10_filter_vlan *vlan, *next_vlan;
+
+	/* See comment in efx_ef10_filter_table_remove() */
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return;
+
+	if (!table)
+		return;
+
+	list_for_each_entry_safe(vlan, next_vlan, &table->vlan_list, list)
+		efx_ef10_filter_del_vlan_internal(efx, vlan);
+}
+
+static bool efx_ef10_filter_match_supported(struct efx_ef10_filter_table *table,
+					    enum efx_filter_match_flags match_flags)
+{
+	unsigned int match_pri;
+	int mf;
+
+	for (match_pri = 0;
+	     match_pri < table->rx_match_count;
+	     match_pri++) {
+		mf = efx_ef10_filter_match_flags_from_mcdi(
+				table->rx_match_mcdi_flags[match_pri]);
+		if (mf == match_flags)
+			return true;
+	}
+
+	return false;
+}
+
 static int efx_ef10_filter_table_probe(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_GET_PARSER_DISP_INFO_IN_LEN);
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PARSER_DISP_INFO_OUT_LENMAX);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct net_device *net_dev = efx->net_dev;
 	unsigned int pd_match_pri, pd_match_count;
 	struct efx_ef10_filter_table *table;
+	struct efx_ef10_vlan *vlan;
 	size_t outlen;
 	int rc;
 
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return -EINVAL;
+
+	if (efx->filter_state) /* already probed */
+		return 0;
+
 	table = kzalloc(sizeof(*table), GFP_KERNEL);
 	if (!table)
 		return -ENOMEM;
@@ -3765,24 +4061,48 @@ static int efx_ef10_filter_table_probe(struct efx_nic *efx)
 				  "%s: fw flags %#x pri %u supported as driver flags %#x pri %u\n",
 				  __func__, mcdi_flags, pd_match_pri,
 				  rc, table->rx_match_count);
-			table->rx_match_flags[table->rx_match_count++] = rc;
+			table->rx_match_mcdi_flags[table->rx_match_count] = mcdi_flags;
+			table->rx_match_count++;
 		}
 	}
 
+	if ((efx_supported_features(efx) & NETIF_F_HW_VLAN_CTAG_FILTER) &&
+	    !(efx_ef10_filter_match_supported(table,
+		(EFX_FILTER_MATCH_OUTER_VID | EFX_FILTER_MATCH_LOC_MAC)) &&
+	      efx_ef10_filter_match_supported(table,
+		(EFX_FILTER_MATCH_OUTER_VID | EFX_FILTER_MATCH_LOC_MAC_IG)))) {
+		netif_info(efx, probe, net_dev,
+			   "VLAN filters are not supported in this firmware variant\n");
+		net_dev->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+		efx->fixed_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+		net_dev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+	}
+
 	table->entry = vzalloc(HUNT_FILTER_TBL_ROWS * sizeof(*table->entry));
 	if (!table->entry) {
 		rc = -ENOMEM;
 		goto fail;
 	}
 
-	table->ucdef_id = EFX_EF10_FILTER_ID_INVALID;
-	table->bcast_id = EFX_EF10_FILTER_ID_INVALID;
-	table->mcdef_id = EFX_EF10_FILTER_ID_INVALID;
+	table->mc_promisc_last = false;
+	table->vlan_filter =
+		!!(efx->net_dev->features & NETIF_F_HW_VLAN_CTAG_FILTER);
+	INIT_LIST_HEAD(&table->vlan_list);
 
 	efx->filter_state = table;
 	init_waitqueue_head(&table->waitq);
+
+	list_for_each_entry(vlan, &nic_data->vlan_list, list) {
+		rc = efx_ef10_filter_add_vlan(efx, vlan->vid);
+		if (rc)
+			goto fail_add_vlan;
+	}
+
 	return 0;
 
+fail_add_vlan:
+	efx_ef10_filter_cleanup_vlans(efx);
+	efx->filter_state = NULL;
 fail:
 	kfree(table);
 	return rc;
@@ -3843,7 +4163,6 @@ static void efx_ef10_filter_table_restore(struct efx_nic *efx)
 		nic_data->must_restore_filters = false;
 }
 
-/* Caller must hold efx->filter_sem for write */
 static void efx_ef10_filter_table_remove(struct efx_nic *efx)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
@@ -3852,7 +4171,17 @@ static void efx_ef10_filter_table_remove(struct efx_nic *efx)
 	unsigned int filter_idx;
 	int rc;
 
+	efx_ef10_filter_cleanup_vlans(efx);
 	efx->filter_state = NULL;
+	/* If we were called without locking, then it's not safe to free
+	 * the table as others might be using it.  So we just WARN, leak
+	 * the memory, and potentially get an inconsistent filter table
+	 * state.
+	 * This should never actually happen.
+	 */
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return;
+
 	if (!table)
 		return;
 
@@ -3880,37 +4209,54 @@ static void efx_ef10_filter_table_remove(struct efx_nic *efx)
 	kfree(table);
 }
 
-#define EFX_EF10_FILTER_DO_MARK_OLD(id) \
-	if (id != EFX_EF10_FILTER_ID_INVALID) { \
-		filter_idx = efx_ef10_filter_get_unsafe_id(efx, id); \
-		if (!table->entry[filter_idx].spec) \
-			netif_dbg(efx, drv, efx->net_dev, \
-				  "%s: marked null spec old %04x:%04x\n", \
-				  __func__, id, filter_idx); \
-		table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD;\
-	}
-static void efx_ef10_filter_mark_old(struct efx_nic *efx)
+static void efx_ef10_filter_mark_one_old(struct efx_nic *efx, uint16_t *id)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
-	unsigned int filter_idx, i;
+	unsigned int filter_idx;
 
-	if (!table)
-		return;
+	if (*id != EFX_EF10_FILTER_ID_INVALID) {
+		filter_idx = efx_ef10_filter_get_unsafe_id(efx, *id);
+		if (!table->entry[filter_idx].spec)
+			netif_dbg(efx, drv, efx->net_dev,
+				  "marked null spec old %04x:%04x\n", *id,
+				  filter_idx);
+		table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD;
+		*id = EFX_EF10_FILTER_ID_INVALID;
+	}
+}
+
+/* Mark old per-VLAN filters that may need to be removed */
+static void _efx_ef10_filter_vlan_mark_old(struct efx_nic *efx,
+					   struct efx_ef10_filter_vlan *vlan)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
+	unsigned int i;
 
-	/* Mark old filters that may need to be removed */
-	spin_lock_bh(&efx->filter_lock);
 	for (i = 0; i < table->dev_uc_count; i++)
-		EFX_EF10_FILTER_DO_MARK_OLD(table->dev_uc_list[i].id);
+		efx_ef10_filter_mark_one_old(efx, &vlan->uc[i]);
 	for (i = 0; i < table->dev_mc_count; i++)
-		EFX_EF10_FILTER_DO_MARK_OLD(table->dev_mc_list[i].id);
-	EFX_EF10_FILTER_DO_MARK_OLD(table->ucdef_id);
-	EFX_EF10_FILTER_DO_MARK_OLD(table->bcast_id);
-	EFX_EF10_FILTER_DO_MARK_OLD(table->mcdef_id);
+		efx_ef10_filter_mark_one_old(efx, &vlan->mc[i]);
+	efx_ef10_filter_mark_one_old(efx, &vlan->ucdef);
+	efx_ef10_filter_mark_one_old(efx, &vlan->bcast);
+	efx_ef10_filter_mark_one_old(efx, &vlan->mcdef);
+}
+
+/* Mark old filters that may need to be removed.
+ * Caller must hold efx->filter_sem for read if race against
+ * efx_ef10_filter_table_remove() is possible
+ */
+static void efx_ef10_filter_mark_old(struct efx_nic *efx)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
+	struct efx_ef10_filter_vlan *vlan;
+
+	spin_lock_bh(&efx->filter_lock);
+	list_for_each_entry(vlan, &table->vlan_list, list)
+		_efx_ef10_filter_vlan_mark_old(efx, vlan);
 	spin_unlock_bh(&efx->filter_lock);
 }
-#undef EFX_EF10_FILTER_DO_MARK_OLD
 
-static void efx_ef10_filter_uc_addr_list(struct efx_nic *efx, bool *promisc)
+static void efx_ef10_filter_uc_addr_list(struct efx_nic *efx)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct net_device *net_dev = efx->net_dev;
@@ -3918,45 +4264,38 @@ static void efx_ef10_filter_uc_addr_list(struct efx_nic *efx, bool *promisc)
 	int addr_count;
 	unsigned int i;
 
-	table->ucdef_id = EFX_EF10_FILTER_ID_INVALID;
 	addr_count = netdev_uc_count(net_dev);
-	if (net_dev->flags & IFF_PROMISC)
-		*promisc = true;
+	table->uc_promisc = !!(net_dev->flags & IFF_PROMISC);
 	table->dev_uc_count = 1 + addr_count;
 	ether_addr_copy(table->dev_uc_list[0].addr, net_dev->dev_addr);
 	i = 1;
 	netdev_for_each_uc_addr(uc, net_dev) {
 		if (i >= EFX_EF10_FILTER_DEV_UC_MAX) {
-			*promisc = true;
+			table->uc_promisc = true;
 			break;
 		}
 		ether_addr_copy(table->dev_uc_list[i].addr, uc->addr);
-		table->dev_uc_list[i].id = EFX_EF10_FILTER_ID_INVALID;
 		i++;
 	}
 }
 
-static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx, bool *promisc)
+static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct net_device *net_dev = efx->net_dev;
 	struct netdev_hw_addr *mc;
 	unsigned int i, addr_count;
 
-	table->mcdef_id = EFX_EF10_FILTER_ID_INVALID;
-	table->bcast_id = EFX_EF10_FILTER_ID_INVALID;
-	if (net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI))
-		*promisc = true;
+	table->mc_promisc = !!(net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI));
 
 	addr_count = netdev_mc_count(net_dev);
 	i = 0;
 	netdev_for_each_mc_addr(mc, net_dev) {
 		if (i >= EFX_EF10_FILTER_DEV_MC_MAX) {
-			*promisc = true;
+			table->mc_promisc = true;
 			break;
 		}
 		ether_addr_copy(table->dev_mc_list[i].addr, mc->addr);
-		table->dev_mc_list[i].id = EFX_EF10_FILTER_ID_INVALID;
 		i++;
 	}
 
@@ -3964,7 +4303,8 @@ static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx, bool *promisc)
 }
 
 static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
-					     bool multicast, bool rollback)
+					    struct efx_ef10_filter_vlan *vlan,
+					    bool multicast, bool rollback)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct efx_ef10_dev_addr *addr_list;
@@ -3973,14 +4313,17 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
 	u8 baddr[ETH_ALEN];
 	unsigned int i, j;
 	int addr_count;
+	u16 *ids;
 	int rc;
 
 	if (multicast) {
 		addr_list = table->dev_mc_list;
 		addr_count = table->dev_mc_count;
+		ids = vlan->mc;
 	} else {
 		addr_list = table->dev_uc_list;
 		addr_count = table->dev_uc_count;
+		ids = vlan->uc;
 	}
 
 	filter_flags = efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0;
@@ -3988,8 +4331,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
 	/* Insert/renew filters */
 	for (i = 0; i < addr_count; i++) {
 		efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
-		efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC,
-					 addr_list[i].addr);
+		efx_filter_set_eth_local(&spec, vlan->vid, addr_list[i].addr);
 		rc = efx_ef10_filter_insert(efx, &spec, true);
 		if (rc < 0) {
 			if (rollback) {
@@ -3998,12 +4340,10 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
 					   rc);
 				/* Fall back to promiscuous */
 				for (j = 0; j < i; j++) {
-					if (addr_list[j].id == EFX_EF10_FILTER_ID_INVALID)
-						continue;
 					efx_ef10_filter_remove_unsafe(
 						efx, EFX_FILTER_PRI_AUTO,
-						addr_list[j].id);
-					addr_list[j].id = EFX_EF10_FILTER_ID_INVALID;
+						ids[j]);
+					ids[j] = EFX_EF10_FILTER_ID_INVALID;
 				}
 				return rc;
 			} else {
@@ -4011,40 +4351,40 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
 				rc = EFX_EF10_FILTER_ID_INVALID;
 			}
 		}
-		addr_list[i].id = efx_ef10_filter_get_unsafe_id(efx, rc);
+		ids[i] = efx_ef10_filter_get_unsafe_id(efx, rc);
 	}
 
 	if (multicast && rollback) {
 		/* Also need an Ethernet broadcast filter */
 		efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
 		eth_broadcast_addr(baddr);
-		efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, baddr);
+		efx_filter_set_eth_local(&spec, vlan->vid, baddr);
 		rc = efx_ef10_filter_insert(efx, &spec, true);
 		if (rc < 0) {
 			netif_warn(efx, drv, efx->net_dev,
 				   "Broadcast filter insert failed rc=%d\n", rc);
 			/* Fall back to promiscuous */
 			for (j = 0; j < i; j++) {
-				if (addr_list[j].id == EFX_EF10_FILTER_ID_INVALID)
-					continue;
 				efx_ef10_filter_remove_unsafe(
 					efx, EFX_FILTER_PRI_AUTO,
-					addr_list[j].id);
-				addr_list[j].id = EFX_EF10_FILTER_ID_INVALID;
+					ids[j]);
+				ids[j] = EFX_EF10_FILTER_ID_INVALID;
 			}
 			return rc;
 		} else {
-			table->bcast_id = efx_ef10_filter_get_unsafe_id(efx, rc);
+			EFX_WARN_ON_PARANOID(vlan->bcast !=
+					     EFX_EF10_FILTER_ID_INVALID);
+			vlan->bcast = efx_ef10_filter_get_unsafe_id(efx, rc);
 		}
 	}
 
 	return 0;
 }
 
-static int efx_ef10_filter_insert_def(struct efx_nic *efx, bool multicast,
-				      bool rollback)
+static int efx_ef10_filter_insert_def(struct efx_nic *efx,
+				      struct efx_ef10_filter_vlan *vlan,
+				      bool multicast, bool rollback)
 {
-	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	enum efx_filter_flags filter_flags;
 	struct efx_filter_spec spec;
@@ -4060,6 +4400,9 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, bool multicast,
 	else
 		efx_filter_set_uc_def(&spec);
 
+	if (vlan->vid != EFX_FILTER_VID_UNSPEC)
+		efx_filter_set_eth_local(&spec, vlan->vid, NULL);
+
 	rc = efx_ef10_filter_insert(efx, &spec, true);
 	if (rc < 0) {
 		netif_printk(efx, drv, rc == -EPERM ? KERN_DEBUG : KERN_WARNING,
@@ -4067,14 +4410,14 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, bool multicast,
 			     "%scast mismatch filter insert failed rc=%d\n",
 			     multicast ? "Multi" : "Uni", rc);
 	} else if (multicast) {
-		table->mcdef_id = efx_ef10_filter_get_unsafe_id(efx, rc);
+		EFX_WARN_ON_PARANOID(vlan->mcdef != EFX_EF10_FILTER_ID_INVALID);
+		vlan->mcdef = efx_ef10_filter_get_unsafe_id(efx, rc);
 		if (!nic_data->workaround_26807) {
 			/* Also need an Ethernet broadcast filter */
 			efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO,
 					   filter_flags, 0);
 			eth_broadcast_addr(baddr);
-			efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC,
-						 baddr);
+			efx_filter_set_eth_local(&spec, vlan->vid, baddr);
 			rc = efx_ef10_filter_insert(efx, &spec, true);
 			if (rc < 0) {
 				netif_warn(efx, drv, efx->net_dev,
@@ -4084,17 +4427,20 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, bool multicast,
 					/* Roll back the mc_def filter */
 					efx_ef10_filter_remove_unsafe(
 							efx, EFX_FILTER_PRI_AUTO,
-							table->mcdef_id);
-					table->mcdef_id = EFX_EF10_FILTER_ID_INVALID;
+							vlan->mcdef);
+					vlan->mcdef = EFX_EF10_FILTER_ID_INVALID;
 					return rc;
 				}
 			} else {
-				table->bcast_id = efx_ef10_filter_get_unsafe_id(efx, rc);
+				EFX_WARN_ON_PARANOID(vlan->bcast !=
+						     EFX_EF10_FILTER_ID_INVALID);
+				vlan->bcast = efx_ef10_filter_get_unsafe_id(efx, rc);
 			}
 		}
 		rc = 0;
 	} else {
-		table->ucdef_id = rc;
+		EFX_WARN_ON_PARANOID(vlan->ucdef != EFX_EF10_FILTER_ID_INVALID);
+		vlan->ucdef = rc;
 		rc = 0;
 	}
 	return rc;
@@ -4203,64 +4549,55 @@ reset_nic:
 /* Caller must hold efx->filter_sem for read if race against
  * efx_ef10_filter_table_remove() is possible
  */
-static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx)
+static void efx_ef10_filter_vlan_sync_rx_mode(struct efx_nic *efx,
+					      struct efx_ef10_filter_vlan *vlan)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
-	struct net_device *net_dev = efx->net_dev;
-	bool uc_promisc = false, mc_promisc = false;
 
-	if (!efx_dev_registered(efx))
-		return;
-
-	if (!table)
-		return;
-
-	efx_ef10_filter_mark_old(efx);
-
-	/* Copy/convert the address lists; add the primary station
-	 * address and broadcast address
+	/* Do not install unspecified VID if VLAN filtering is enabled.
+	 * Do not install all specified VIDs if VLAN filtering is disabled.
 	 */
-	netif_addr_lock_bh(net_dev);
-	efx_ef10_filter_uc_addr_list(efx, &uc_promisc);
-	efx_ef10_filter_mc_addr_list(efx, &mc_promisc);
-	netif_addr_unlock_bh(net_dev);
+	if ((vlan->vid == EFX_FILTER_VID_UNSPEC) == table->vlan_filter)
+		return;
 
 	/* Insert/renew unicast filters */
-	if (uc_promisc) {
-		efx_ef10_filter_insert_def(efx, false, false);
-		efx_ef10_filter_insert_addr_list(efx, false, false);
+	if (table->uc_promisc) {
+		efx_ef10_filter_insert_def(efx, vlan, false, false);
+		efx_ef10_filter_insert_addr_list(efx, vlan, false, false);
 	} else {
 		/* If any of the filters failed to insert, fall back to
 		 * promiscuous mode - add in the uc_def filter.  But keep
 		 * our individual unicast filters.
 		 */
-		if (efx_ef10_filter_insert_addr_list(efx, false, false))
-			efx_ef10_filter_insert_def(efx, false, false);
+		if (efx_ef10_filter_insert_addr_list(efx, vlan, false, false))
+			efx_ef10_filter_insert_def(efx, vlan, false, false);
 	}
 
 	/* Insert/renew multicast filters */
 	/* If changing promiscuous state with cascaded multicast filters, remove
 	 * old filters first, so that packets are dropped rather than duplicated
 	 */
-	if (nic_data->workaround_26807 && efx->mc_promisc != mc_promisc)
+	if (nic_data->workaround_26807 &&
+	    table->mc_promisc_last != table->mc_promisc)
 		efx_ef10_filter_remove_old(efx);
-	if (mc_promisc) {
+	if (table->mc_promisc) {
 		if (nic_data->workaround_26807) {
 			/* If we failed to insert promiscuous filters, rollback
 			 * and fall back to individual multicast filters
 			 */
-			if (efx_ef10_filter_insert_def(efx, true, true)) {
+			if (efx_ef10_filter_insert_def(efx, vlan, true, true)) {
 				/* Changing promisc state, so remove old filters */
 				efx_ef10_filter_remove_old(efx);
-				efx_ef10_filter_insert_addr_list(efx, true, false);
+				efx_ef10_filter_insert_addr_list(efx, vlan,
+								 true, false);
 			}
 		} else {
 			/* If we failed to insert promiscuous filters, don't
 			 * rollback.  Regardless, also insert the mc_list
 			 */
-			efx_ef10_filter_insert_def(efx, true, false);
-			efx_ef10_filter_insert_addr_list(efx, true, false);
+			efx_ef10_filter_insert_def(efx, vlan, true, false);
+			efx_ef10_filter_insert_addr_list(efx, vlan, true, false);
 		}
 	} else {
 		/* If any filters failed to insert, rollback and fall back to
@@ -4268,17 +4605,153 @@ static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx)
 		 * that fails, roll back again and insert as many of our
 		 * individual multicast filters as we can.
 		 */
-		if (efx_ef10_filter_insert_addr_list(efx, true, true)) {
+		if (efx_ef10_filter_insert_addr_list(efx, vlan, true, true)) {
 			/* Changing promisc state, so remove old filters */
 			if (nic_data->workaround_26807)
 				efx_ef10_filter_remove_old(efx);
-			if (efx_ef10_filter_insert_def(efx, true, true))
-				efx_ef10_filter_insert_addr_list(efx, true, false);
+			if (efx_ef10_filter_insert_def(efx, vlan, true, true))
+				efx_ef10_filter_insert_addr_list(efx, vlan,
+								 true, false);
 		}
 	}
+}
+
+/* Caller must hold efx->filter_sem for read if race against
+ * efx_ef10_filter_table_remove() is possible
+ */
+static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
+	struct net_device *net_dev = efx->net_dev;
+	struct efx_ef10_filter_vlan *vlan;
+	bool vlan_filter;
+
+	if (!efx_dev_registered(efx))
+		return;
+
+	if (!table)
+		return;
+
+	efx_ef10_filter_mark_old(efx);
+
+	/* Copy/convert the address lists; add the primary station
+	 * address and broadcast address
+	 */
+	netif_addr_lock_bh(net_dev);
+	efx_ef10_filter_uc_addr_list(efx);
+	efx_ef10_filter_mc_addr_list(efx);
+	netif_addr_unlock_bh(net_dev);
+
+	/* If VLAN filtering changes, all old filters are finally removed.
+	 * Do it in advance to avoid conflicts for unicast untagged and
+	 * VLAN 0 tagged filters.
+	 */
+	vlan_filter = !!(net_dev->features & NETIF_F_HW_VLAN_CTAG_FILTER);
+	if (table->vlan_filter != vlan_filter) {
+		table->vlan_filter = vlan_filter;
+		efx_ef10_filter_remove_old(efx);
+	}
+
+	list_for_each_entry(vlan, &table->vlan_list, list)
+		efx_ef10_filter_vlan_sync_rx_mode(efx, vlan);
 
 	efx_ef10_filter_remove_old(efx);
-	efx->mc_promisc = mc_promisc;
+	table->mc_promisc_last = table->mc_promisc;
+}
+
+static struct efx_ef10_filter_vlan *efx_ef10_filter_find_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
+	struct efx_ef10_filter_vlan *vlan;
+
+	WARN_ON(!rwsem_is_locked(&efx->filter_sem));
+
+	list_for_each_entry(vlan, &table->vlan_list, list) {
+		if (vlan->vid == vid)
+			return vlan;
+	}
+
+	return NULL;
+}
+
+static int efx_ef10_filter_add_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
+	struct efx_ef10_filter_vlan *vlan;
+	unsigned int i;
+
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return -EINVAL;
+
+	vlan = efx_ef10_filter_find_vlan(efx, vid);
+	if (WARN_ON(vlan)) {
+		netif_err(efx, drv, efx->net_dev,
+			  "VLAN %u already added\n", vid);
+		return -EALREADY;
+	}
+
+	vlan = kzalloc(sizeof(*vlan), GFP_KERNEL);
+	if (!vlan)
+		return -ENOMEM;
+
+	vlan->vid = vid;
+
+	for (i = 0; i < ARRAY_SIZE(vlan->uc); i++)
+		vlan->uc[i] = EFX_EF10_FILTER_ID_INVALID;
+	for (i = 0; i < ARRAY_SIZE(vlan->mc); i++)
+		vlan->mc[i] = EFX_EF10_FILTER_ID_INVALID;
+	vlan->ucdef = EFX_EF10_FILTER_ID_INVALID;
+	vlan->bcast = EFX_EF10_FILTER_ID_INVALID;
+	vlan->mcdef = EFX_EF10_FILTER_ID_INVALID;
+
+	list_add_tail(&vlan->list, &table->vlan_list);
+
+	if (efx_dev_registered(efx))
+		efx_ef10_filter_vlan_sync_rx_mode(efx, vlan);
+
+	return 0;
+}
+
+static void efx_ef10_filter_del_vlan_internal(struct efx_nic *efx,
+					      struct efx_ef10_filter_vlan *vlan)
+{
+	unsigned int i;
+
+	/* See comment in efx_ef10_filter_table_remove() */
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return;
+
+	list_del(&vlan->list);
+
+	for (i = 0; i < ARRAY_SIZE(vlan->uc); i++)
+		efx_ef10_filter_remove_unsafe(efx, EFX_FILTER_PRI_AUTO,
+					      vlan->uc[i]);
+	for (i = 0; i < ARRAY_SIZE(vlan->mc); i++)
+		efx_ef10_filter_remove_unsafe(efx, EFX_FILTER_PRI_AUTO,
+					      vlan->mc[i]);
+	efx_ef10_filter_remove_unsafe(efx, EFX_FILTER_PRI_AUTO, vlan->ucdef);
+	efx_ef10_filter_remove_unsafe(efx, EFX_FILTER_PRI_AUTO, vlan->bcast);
+	efx_ef10_filter_remove_unsafe(efx, EFX_FILTER_PRI_AUTO, vlan->mcdef);
+
+	kfree(vlan);
+}
+
+static void efx_ef10_filter_del_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_filter_vlan *vlan;
+
+	/* See comment in efx_ef10_filter_table_remove() */
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return;
+
+	vlan = efx_ef10_filter_find_vlan(efx, vid);
+	if (!vlan) {
+		netif_err(efx, drv, efx->net_dev,
+			  "VLAN %u not found in filter state\n", vid);
+		return;
+	}
+
+	efx_ef10_filter_del_vlan_internal(efx, vlan);
 }
 
 static int efx_ef10_set_mac_address(struct efx_nic *efx)
@@ -4290,6 +4763,8 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx)
 
 	efx_device_detach_sync(efx);
 	efx_net_stop(efx->net_dev);
+
+	mutex_lock(&efx->mac_lock);
 	down_write(&efx->filter_sem);
 	efx_ef10_filter_table_remove(efx);
 
@@ -4302,6 +4777,8 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx)
 
 	efx_ef10_filter_table_probe(efx);
 	up_write(&efx->filter_sem);
+	mutex_unlock(&efx->mac_lock);
+
 	if (was_enabled)
 		efx_net_open(efx->net_dev);
 	netif_device_attach(efx->net_dev);
@@ -4703,6 +5180,29 @@ static int efx_ef10_ptp_set_ts_config(struct efx_nic *efx,
 	}
 }
 
+static int efx_ef10_vlan_rx_add_vid(struct efx_nic *efx, __be16 proto, u16 vid)
+{
+	if (proto != htons(ETH_P_8021Q))
+		return -EINVAL;
+
+	return efx_ef10_add_vlan(efx, vid);
+}
+
+static int efx_ef10_vlan_rx_kill_vid(struct efx_nic *efx, __be16 proto, u16 vid)
+{
+	if (proto != htons(ETH_P_8021Q))
+		return -EINVAL;
+
+	return efx_ef10_del_vlan(efx, vid);
+}
+
+#define EF10_OFFLOAD_FEATURES		\
+	(NETIF_F_IP_CSUM |		\
+	 NETIF_F_HW_VLAN_CTAG_FILTER |	\
+	 NETIF_F_IPV6_CSUM |		\
+	 NETIF_F_RXHASH |		\
+	 NETIF_F_NTUPLE)
+
 const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
 	.is_vf = true,
 	.mem_bar = EFX_MEM_VF_BAR,
@@ -4780,6 +5280,8 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
 #endif
 	.ptp_write_host_time = efx_ef10_ptp_write_host_time_vf,
 	.ptp_set_ts_config = efx_ef10_ptp_set_ts_config_vf,
+	.vlan_rx_add_vid = efx_ef10_vlan_rx_add_vid,
+	.vlan_rx_kill_vid = efx_ef10_vlan_rx_kill_vid,
 #ifdef CONFIG_SFC_SRIOV
 	.vswitching_probe = efx_ef10_vswitching_probe_vf,
 	.vswitching_restore = efx_ef10_vswitching_restore_vf,
@@ -4798,8 +5300,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
 	.always_rx_scatter = true,
 	.max_interrupt_mode = EFX_INT_MODE_MSIX,
 	.timer_period_max = 1 << ERF_DD_EVQ_IND_TIMER_VAL_WIDTH,
-	.offload_features = (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			     NETIF_F_RXHASH | NETIF_F_NTUPLE),
+	.offload_features = EF10_OFFLOAD_FEATURES,
 	.mcdi_max_ver = 2,
 	.max_rx_ip_filters = HUNT_FILTER_TBL_ROWS,
 	.hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
@@ -4891,6 +5392,8 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.ptp_write_host_time = efx_ef10_ptp_write_host_time,
 	.ptp_set_ts_sync_events = efx_ef10_ptp_set_ts_sync_events,
 	.ptp_set_ts_config = efx_ef10_ptp_set_ts_config,
+	.vlan_rx_add_vid = efx_ef10_vlan_rx_add_vid,
+	.vlan_rx_kill_vid = efx_ef10_vlan_rx_kill_vid,
 #ifdef CONFIG_SFC_SRIOV
 	.sriov_configure = efx_ef10_sriov_configure,
 	.sriov_init = efx_ef10_sriov_init,
@@ -4919,8 +5422,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.always_rx_scatter = true,
 	.max_interrupt_mode = EFX_INT_MODE_MSIX,
 	.timer_period_max = 1 << ERF_DD_EVQ_IND_TIMER_VAL_WIDTH,
-	.offload_features = (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			     NETIF_F_RXHASH | NETIF_F_NTUPLE),
+	.offload_features = EF10_OFFLOAD_FEATURES,
 	.mcdi_max_ver = 2,
 	.max_rx_ip_filters = HUNT_FILTER_TBL_ROWS,
 	.hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c
index 3c17f274e802..a949b9d27329 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.c
+++ b/drivers/net/ethernet/sfc/ef10_sriov.c
@@ -232,6 +232,35 @@ fail:
 	return rc;
 }
 
+static int efx_ef10_vadaptor_alloc_set_features(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	u32 port_flags;
+	int rc;
+
+	rc = efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+	if (rc)
+		goto fail_vadaptor_alloc;
+
+	rc = efx_ef10_vadaptor_query(efx, nic_data->vport_id,
+				     &port_flags, NULL, NULL);
+	if (rc)
+		goto fail_vadaptor_query;
+
+	if (port_flags &
+	    (1 << MC_CMD_VPORT_ALLOC_IN_FLAG_VLAN_RESTRICT_LBN))
+		efx->fixed_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+	else
+		efx->fixed_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	return 0;
+
+fail_vadaptor_query:
+	efx_ef10_vadaptor_free(efx, EVB_PORT_ID_ASSIGNED);
+fail_vadaptor_alloc:
+	return rc;
+}
+
 /* On top of the default firmware vswitch setup, create a VEB vswitch and
  * expansion vport for use by this function.
  */
@@ -243,7 +272,7 @@ int efx_ef10_vswitching_probe_pf(struct efx_nic *efx)
 
 	if (pci_sriov_get_totalvfs(efx->pci_dev) <= 0) {
 		/* vswitch not needed as we have no VFs */
-		efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+		efx_ef10_vadaptor_alloc_set_features(efx);
 		return 0;
 	}
 
@@ -263,7 +292,7 @@ int efx_ef10_vswitching_probe_pf(struct efx_nic *efx)
 		goto fail3;
 	ether_addr_copy(nic_data->vport_mac, net_dev->dev_addr);
 
-	rc = efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+	rc = efx_ef10_vadaptor_alloc_set_features(efx);
 	if (rc)
 		goto fail4;
 
@@ -282,9 +311,7 @@ fail1:
 
 int efx_ef10_vswitching_probe_vf(struct efx_nic *efx)
 {
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
-
-	return efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+	return efx_ef10_vadaptor_alloc_set_features(efx);
 }
 
 int efx_ef10_vswitching_restore_pf(struct efx_nic *efx)
@@ -554,6 +581,7 @@ int efx_ef10_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i, u16 vlan,
 		efx_device_detach_sync(vf->efx);
 		efx_net_stop(vf->efx->net_dev);
 
+		mutex_lock(&vf->efx->mac_lock);
 		down_write(&vf->efx->filter_sem);
 		vf->efx->type->filter_table_remove(vf->efx);
 
@@ -630,6 +658,7 @@ restore_filters:
 			goto reset_nic_up_write;
 
 		up_write(&vf->efx->filter_sem);
+		mutex_unlock(&vf->efx->mac_lock);
 
 		up_write(&vf->efx->filter_sem);
 
@@ -642,9 +671,10 @@ restore_filters:
 	return rc;
 
 reset_nic_up_write:
-	if (vf->efx)
+	if (vf->efx) {
 		up_write(&vf->efx->filter_sem);
-
+		mutex_unlock(&vf->efx->mac_lock);
+	}
 reset_nic:
 	if (vf->efx) {
 		netif_err(efx, drv, efx->net_dev,
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.h b/drivers/net/ethernet/sfc/ef10_sriov.h
index 6d25b92cb45e..9ceb7ef0a210 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.h
+++ b/drivers/net/ethernet/sfc/ef10_sriov.h
@@ -70,6 +70,9 @@ int efx_ef10_vport_add_mac(struct efx_nic *efx,
 int efx_ef10_vport_del_mac(struct efx_nic *efx,
 			   unsigned int port_id, u8 *mac);
 int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id);
+int efx_ef10_vadaptor_query(struct efx_nic *efx, unsigned int port_id,
+			    u32 *port_flags, u32 *vadaptor_flags,
+			    unsigned int *vlan_tags);
 int efx_ef10_vadaptor_free(struct efx_nic *efx, unsigned int port_id);
 
 #endif /* EF10_SRIOV_H */
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 097f363f1630..14b821b1c880 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -600,6 +600,7 @@ fail:
  */
 static void efx_start_datapath(struct efx_nic *efx)
 {
+	netdev_features_t old_features = efx->net_dev->features;
 	bool old_rx_scatter = efx->rx_scatter;
 	struct efx_tx_queue *tx_queue;
 	struct efx_rx_queue *rx_queue;
@@ -644,6 +645,15 @@ static void efx_start_datapath(struct efx_nic *efx)
 			  efx->rx_dma_len, efx->rx_page_buf_step,
 			  efx->rx_bufs_per_page, efx->rx_pages_per_batch);
 
+	/* Restore previously fixed features in hw_features and remove
+	 * features which are fixed now
+	 */
+	efx->net_dev->hw_features |= efx->net_dev->features;
+	efx->net_dev->hw_features &= ~efx->fixed_features;
+	efx->net_dev->features |= efx->fixed_features;
+	if (efx->net_dev->features != old_features)
+		netdev_features_change(efx->net_dev);
+
 	/* RX filters may also have scatter-enabled flags */
 	if (efx->rx_scatter != old_rx_scatter)
 		efx->type->filter_update_rx_scatter(efx);
@@ -1719,6 +1729,7 @@ static int efx_probe_filters(struct efx_nic *efx)
 
 	spin_lock_init(&efx->filter_lock);
 	init_rwsem(&efx->filter_sem);
+	mutex_lock(&efx->mac_lock);
 	down_write(&efx->filter_sem);
 	rc = efx->type->filter_table_probe(efx);
 	if (rc)
@@ -1757,6 +1768,7 @@ static int efx_probe_filters(struct efx_nic *efx)
 #endif
 out_unlock:
 	up_write(&efx->filter_sem);
+	mutex_unlock(&efx->mac_lock);
 	return rc;
 }
 
@@ -2312,14 +2324,46 @@ static void efx_set_rx_mode(struct net_device *net_dev)
 static int efx_set_features(struct net_device *net_dev, netdev_features_t data)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
+	int rc;
 
 	/* If disabling RX n-tuple filtering, clear existing filters */
-	if (net_dev->features & ~data & NETIF_F_NTUPLE)
-		return efx->type->filter_clear_rx(efx, EFX_FILTER_PRI_MANUAL);
+	if (net_dev->features & ~data & NETIF_F_NTUPLE) {
+		rc = efx->type->filter_clear_rx(efx, EFX_FILTER_PRI_MANUAL);
+		if (rc)
+			return rc;
+	}
+
+	/* If Rx VLAN filter is changed, update filters via mac_reconfigure */
+	if ((net_dev->features ^ data) & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		/* efx_set_rx_mode() will schedule MAC work to update filters
+		 * when a new features are finally set in net_dev.
+		 */
+		efx_set_rx_mode(net_dev);
+	}
 
 	return 0;
 }
 
+static int efx_vlan_rx_add_vid(struct net_device *net_dev, __be16 proto, u16 vid)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (efx->type->vlan_rx_add_vid)
+		return efx->type->vlan_rx_add_vid(efx, proto, vid);
+	else
+		return -EOPNOTSUPP;
+}
+
+static int efx_vlan_rx_kill_vid(struct net_device *net_dev, __be16 proto, u16 vid)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (efx->type->vlan_rx_kill_vid)
+		return efx->type->vlan_rx_kill_vid(efx, proto, vid);
+	else
+		return -EOPNOTSUPP;
+}
+
 static const struct net_device_ops efx_netdev_ops = {
 	.ndo_open		= efx_net_open,
 	.ndo_stop		= efx_net_stop,
@@ -2332,6 +2376,8 @@ static const struct net_device_ops efx_netdev_ops = {
 	.ndo_set_mac_address	= efx_set_mac_address,
 	.ndo_set_rx_mode	= efx_set_rx_mode,
 	.ndo_set_features	= efx_set_features,
+	.ndo_vlan_rx_add_vid	= efx_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= efx_vlan_rx_kill_vid,
 #ifdef CONFIG_SFC_SRIOV
 	.ndo_set_vf_mac		= efx_sriov_set_vf_mac,
 	.ndo_set_vf_vlan	= efx_sriov_set_vf_vlan,
@@ -3147,17 +3193,25 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 		return -ENOMEM;
 	efx = netdev_priv(net_dev);
 	efx->type = (const struct efx_nic_type *) entry->driver_data;
+	efx->fixed_features |= NETIF_F_HIGHDMA;
 	net_dev->features |= (efx->type->offload_features | NETIF_F_SG |
-			      NETIF_F_HIGHDMA | NETIF_F_TSO |
-			      NETIF_F_RXCSUM);
+			      NETIF_F_TSO | NETIF_F_RXCSUM);
 	if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
 		net_dev->features |= NETIF_F_TSO6;
 	/* Mask for features that also apply to VLAN devices */
 	net_dev->vlan_features |= (NETIF_F_HW_CSUM | NETIF_F_SG |
 				   NETIF_F_HIGHDMA | NETIF_F_ALL_TSO |
 				   NETIF_F_RXCSUM);
-	/* All offloads can be toggled */
-	net_dev->hw_features = net_dev->features & ~NETIF_F_HIGHDMA;
+
+	net_dev->hw_features = net_dev->features & ~efx->fixed_features;
+
+	/* Disable VLAN filtering by default.  It may be enforced if
+	 * the feature is fixed (i.e. VLAN filters are required to
+	 * receive VLAN tagged packets due to vPort restrictions).
+	 */
+	net_dev->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+	net_dev->features |= efx->fixed_features;
+
 	pci_set_drvdata(pci_dev, efx);
 	SET_NETDEV_DEV(net_dev, &pci_dev->dev);
 	rc = efx_init_struct(efx, pci_dev, net_dev);
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index 5e3f93f04e62..c3ae739e9c7a 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -274,4 +274,13 @@ static inline void efx_device_detach_sync(struct efx_nic *efx)
 	netif_tx_unlock_bh(dev);
 }
 
+static inline bool efx_rwsem_assert_write_locked(struct rw_semaphore *sem)
+{
+	if (WARN_ON(down_read_trylock(sem))) {
+		up_read(sem);
+		return false;
+	}
+	return true;
+}
+
 #endif /* EFX_EFX_H */
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index 133e9e35be9e..4c83739d158f 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -104,7 +104,8 @@ int efx_farch_test_registers(struct efx_nic *efx,
 			     const struct efx_farch_register_test *regs,
 			     size_t n_regs)
 {
-	unsigned address = 0, i, j;
+	unsigned address = 0;
+	int i, j;
 	efx_oword_t mask, imask, original, reg, buf;
 
 	for (i = 0; i < n_regs; ++i) {
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index 4cc772164a79..c9a5b003caaf 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -273,6 +273,9 @@
  * have already installed filters. See the comment at
  * MC_CMD_WORKAROUND_BUG26807. */
 #define MC_CMD_ERR_FILTERS_PRESENT 0x1014
+/* The clock whose frequency you've attempted to set set
+ * doesn't exist on this NIC */
+#define MC_CMD_ERR_NO_CLOCK 0x1015
 
 #define MC_CMD_ERR_CODE_OFST 0
 
@@ -292,9 +295,11 @@
 /* Point to the copycode entry point. */
 #define SIENA_MC_BOOTROM_COPYCODE_VEC (0x800 - 3 * 0x4)
 #define HUNT_MC_BOOTROM_COPYCODE_VEC (0x8000 - 3 * 0x4)
+#define MEDFORD_MC_BOOTROM_COPYCODE_VEC (0x10000 - 3 * 0x4)
 /* Points to the recovery mode entry point. */
 #define SIENA_MC_BOOTROM_NOFLASH_VEC (0x800 - 2 * 0x4)
 #define HUNT_MC_BOOTROM_NOFLASH_VEC (0x8000 - 2 * 0x4)
+#define MEDFORD_MC_BOOTROM_NOFLASH_VEC (0x10000 - 2 * 0x4)
 
 /* The command set exported by the boot ROM (MCDI v0) */
 #define MC_CMD_GET_VERSION_V0_SUPPORTED_FUNCS {		\
@@ -686,6 +691,12 @@
 #define          FCDI_EVENT_CODE_PTP_STATUS 0x9
 /* enum: Port id config to map MC-FC port idx */
 #define          FCDI_EVENT_CODE_PORT_CONFIG 0xa
+/* enum: Boot result or error code */
+#define          FCDI_EVENT_CODE_BOOT_RESULT 0xb
+#define       FCDI_EVENT_REBOOT_SRC_LBN 36
+#define       FCDI_EVENT_REBOOT_SRC_WIDTH 8
+#define          FCDI_EVENT_REBOOT_FC_FW 0x0 /* enum */
+#define          FCDI_EVENT_REBOOT_FC_BOOTLOADER 0x1 /* enum */
 #define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_OFST 0
 #define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_LBN 0
 #define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_WIDTH 32
@@ -717,6 +728,11 @@
 #define       FCDI_EVENT_PORT_CONFIG_DATA_OFST 0
 #define       FCDI_EVENT_PORT_CONFIG_DATA_LBN 0
 #define       FCDI_EVENT_PORT_CONFIG_DATA_WIDTH 32
+#define       FCDI_EVENT_BOOT_RESULT_OFST 0
+/*            Enum values, see field(s): */
+/*               MC_CMD_AOE/MC_CMD_AOE_OUT_INFO/FC_BOOT_RESULT */
+#define       FCDI_EVENT_BOOT_RESULT_LBN 0
+#define       FCDI_EVENT_BOOT_RESULT_WIDTH 32
 
 /* FCDI_EXTENDED_EVENT_PPS structuredef: Extended FCDI event to send PPS events
  * to the MC. Note that this structure | is overlayed over a normal FCDI event
@@ -1649,15 +1665,30 @@
 
 /* MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS msgresponse */
 #define    MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_LEN 16
-/* Uncorrected error on transmit timestamps in NIC clock format */
+/* Uncorrected error on PTP transmit timestamps in NIC clock format */
 #define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_TRANSMIT_OFST 0
-/* Uncorrected error on receive timestamps in NIC clock format */
+/* Uncorrected error on PTP receive timestamps in NIC clock format */
 #define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_RECEIVE_OFST 4
 /* Uncorrected error on PPS output in NIC clock format */
 #define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_OUT_OFST 8
 /* Uncorrected error on PPS input in NIC clock format */
 #define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_IN_OFST 12
 
+/* MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2 msgresponse */
+#define    MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_LEN 24
+/* Uncorrected error on PTP transmit timestamps in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_PTP_TX_OFST 0
+/* Uncorrected error on PTP receive timestamps in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_PTP_RX_OFST 4
+/* Uncorrected error on PPS output in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_PPS_OUT_OFST 8
+/* Uncorrected error on PPS input in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_PPS_IN_OFST 12
+/* Uncorrected error on non-PTP transmit timestamps in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_GENERAL_TX_OFST 16
+/* Uncorrected error on non-PTP receive timestamps in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_GENERAL_RX_OFST 20
+
 /* MC_CMD_PTP_OUT_MANFTEST_PPS msgresponse */
 #define    MC_CMD_PTP_OUT_MANFTEST_PPS_LEN 4
 /* Results of testing */
@@ -2158,8 +2189,12 @@
 
 /* MC_CMD_DRV_ATTACH_IN msgrequest */
 #define    MC_CMD_DRV_ATTACH_IN_LEN 12
-/* new state (0=detached, 1=attached) to set if UPDATE=1 */
+/* new state to set if UPDATE=1 */
 #define       MC_CMD_DRV_ATTACH_IN_NEW_STATE_OFST 0
+#define        MC_CMD_DRV_ATTACH_LBN 0
+#define        MC_CMD_DRV_ATTACH_WIDTH 1
+#define        MC_CMD_DRV_PREBOOT_LBN 1
+#define        MC_CMD_DRV_PREBOOT_WIDTH 1
 /* 1 to set new state, or 0 to just report the existing state */
 #define       MC_CMD_DRV_ATTACH_IN_UPDATE_OFST 4
 /* preferred datapath firmware (for Huntington; ignored for Siena) */
@@ -2181,12 +2216,12 @@
 
 /* MC_CMD_DRV_ATTACH_OUT msgresponse */
 #define    MC_CMD_DRV_ATTACH_OUT_LEN 4
-/* previous or existing state (0=detached, 1=attached) */
+/* previous or existing state, see the bitmask at NEW_STATE */
 #define       MC_CMD_DRV_ATTACH_OUT_OLD_STATE_OFST 0
 
 /* MC_CMD_DRV_ATTACH_EXT_OUT msgresponse */
 #define    MC_CMD_DRV_ATTACH_EXT_OUT_LEN 8
-/* previous or existing state (0=detached, 1=attached) */
+/* previous or existing state, see the bitmask at NEW_STATE */
 #define       MC_CMD_DRV_ATTACH_EXT_OUT_OLD_STATE_OFST 0
 /* Flags associated with this function */
 #define       MC_CMD_DRV_ATTACH_EXT_OUT_FUNC_FLAGS_OFST 4
@@ -2198,6 +2233,10 @@
 #define          MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL 0x1
 /* enum: The function can perform privileged operations */
 #define          MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED 0x2
+/* enum: The function does not have an active port associated with it. The port
+ * refers to the Sorrento external FPGA port.
+ */
+#define          MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_NO_ACTIVE_PORT 0x3
 
 
 /***********************************/
@@ -2892,7 +2931,7 @@
  */
 #define MC_CMD_SET_MAC 0x2c
 
-#define MC_CMD_0x2c_PRIVILEGE_CTG SRIOV_CTG_LINK
+#define MC_CMD_0x2c_PRIVILEGE_CTG SRIOV_CTG_GENERAL
 
 /* MC_CMD_SET_MAC_IN msgrequest */
 #define    MC_CMD_SET_MAC_IN_LEN 28
@@ -2927,9 +2966,66 @@
 #define        MC_CMD_SET_MAC_IN_FLAG_INCLUDE_FCS_LBN 0
 #define        MC_CMD_SET_MAC_IN_FLAG_INCLUDE_FCS_WIDTH 1
 
+/* MC_CMD_SET_MAC_EXT_IN msgrequest */
+#define    MC_CMD_SET_MAC_EXT_IN_LEN 32
+/* The MTU is the MTU programmed directly into the XMAC/GMAC (inclusive of
+ * EtherII, VLAN, bug16011 padding).
+ */
+#define       MC_CMD_SET_MAC_EXT_IN_MTU_OFST 0
+#define       MC_CMD_SET_MAC_EXT_IN_DRAIN_OFST 4
+#define       MC_CMD_SET_MAC_EXT_IN_ADDR_OFST 8
+#define       MC_CMD_SET_MAC_EXT_IN_ADDR_LEN 8
+#define       MC_CMD_SET_MAC_EXT_IN_ADDR_LO_OFST 8
+#define       MC_CMD_SET_MAC_EXT_IN_ADDR_HI_OFST 12
+#define       MC_CMD_SET_MAC_EXT_IN_REJECT_OFST 16
+#define        MC_CMD_SET_MAC_EXT_IN_REJECT_UNCST_LBN 0
+#define        MC_CMD_SET_MAC_EXT_IN_REJECT_UNCST_WIDTH 1
+#define        MC_CMD_SET_MAC_EXT_IN_REJECT_BRDCST_LBN 1
+#define        MC_CMD_SET_MAC_EXT_IN_REJECT_BRDCST_WIDTH 1
+#define       MC_CMD_SET_MAC_EXT_IN_FCNTL_OFST 20
+/* enum: Flow control is off. */
+/*               MC_CMD_FCNTL_OFF 0x0 */
+/* enum: Respond to flow control. */
+/*               MC_CMD_FCNTL_RESPOND 0x1 */
+/* enum: Respond to and Issue flow control. */
+/*               MC_CMD_FCNTL_BIDIR 0x2 */
+/* enum: Auto neg flow control. */
+/*               MC_CMD_FCNTL_AUTO 0x3 */
+/* enum: Priority flow control (eftest builds only). */
+/*               MC_CMD_FCNTL_QBB 0x4 */
+/* enum: Issue flow control. */
+/*               MC_CMD_FCNTL_GENERATE 0x5 */
+#define       MC_CMD_SET_MAC_EXT_IN_FLAGS_OFST 24
+#define        MC_CMD_SET_MAC_EXT_IN_FLAG_INCLUDE_FCS_LBN 0
+#define        MC_CMD_SET_MAC_EXT_IN_FLAG_INCLUDE_FCS_WIDTH 1
+/* Select which parameters to configure. A parameter will only be modified if
+ * the corresponding control flag is set. If SET_MAC_ENHANCED is not set in
+ * capabilities then this field is ignored (and all flags are assumed to be
+ * set).
+ */
+#define       MC_CMD_SET_MAC_EXT_IN_CONTROL_OFST 28
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_MTU_LBN 0
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_MTU_WIDTH 1
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_DRAIN_LBN 1
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_DRAIN_WIDTH 1
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_REJECT_LBN 2
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_REJECT_WIDTH 1
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_FCNTL_LBN 3
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_FCNTL_WIDTH 1
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_FCS_LBN 4
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_FCS_WIDTH 1
+
 /* MC_CMD_SET_MAC_OUT msgresponse */
 #define    MC_CMD_SET_MAC_OUT_LEN 0
 
+/* MC_CMD_SET_MAC_V2_OUT msgresponse */
+#define    MC_CMD_SET_MAC_V2_OUT_LEN 4
+/* MTU as configured after processing the request. See comment at
+ * MC_CMD_SET_MAC_IN/MTU. To query MTU without doing any changes, set CONTROL
+ * to 0.
+ */
+#define       MC_CMD_SET_MAC_V2_OUT_MTU_OFST 0
+
 
 /***********************************/
 /* MC_CMD_PHY_STATS
@@ -3521,6 +3617,26 @@
 #define       MC_CMD_NVRAM_INFO_OUT_PHYSDEV_OFST 16
 #define       MC_CMD_NVRAM_INFO_OUT_PHYSADDR_OFST 20
 
+/* MC_CMD_NVRAM_INFO_V2_OUT msgresponse */
+#define    MC_CMD_NVRAM_INFO_V2_OUT_LEN 28
+#define       MC_CMD_NVRAM_INFO_V2_OUT_TYPE_OFST 0
+/*            Enum values, see field(s): */
+/*               MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+#define       MC_CMD_NVRAM_INFO_V2_OUT_SIZE_OFST 4
+#define       MC_CMD_NVRAM_INFO_V2_OUT_ERASESIZE_OFST 8
+#define       MC_CMD_NVRAM_INFO_V2_OUT_FLAGS_OFST 12
+#define        MC_CMD_NVRAM_INFO_V2_OUT_PROTECTED_LBN 0
+#define        MC_CMD_NVRAM_INFO_V2_OUT_PROTECTED_WIDTH 1
+#define        MC_CMD_NVRAM_INFO_V2_OUT_TLV_LBN 1
+#define        MC_CMD_NVRAM_INFO_V2_OUT_TLV_WIDTH 1
+#define        MC_CMD_NVRAM_INFO_V2_OUT_A_B_LBN 7
+#define        MC_CMD_NVRAM_INFO_V2_OUT_A_B_WIDTH 1
+#define       MC_CMD_NVRAM_INFO_V2_OUT_PHYSDEV_OFST 16
+#define       MC_CMD_NVRAM_INFO_V2_OUT_PHYSADDR_OFST 20
+/* Writes must be multiples of this size. Added to support the MUM on Sorrento.
+ */
+#define       MC_CMD_NVRAM_INFO_V2_OUT_WRITESIZE_OFST 24
+
 
 /***********************************/
 /* MC_CMD_NVRAM_UPDATE_START
@@ -3561,6 +3677,37 @@
 /* amount to read in bytes */
 #define       MC_CMD_NVRAM_READ_IN_LENGTH_OFST 8
 
+/* MC_CMD_NVRAM_READ_IN_V2 msgrequest */
+#define    MC_CMD_NVRAM_READ_IN_V2_LEN 16
+#define       MC_CMD_NVRAM_READ_IN_V2_TYPE_OFST 0
+/*            Enum values, see field(s): */
+/*               MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+#define       MC_CMD_NVRAM_READ_IN_V2_OFFSET_OFST 4
+/* amount to read in bytes */
+#define       MC_CMD_NVRAM_READ_IN_V2_LENGTH_OFST 8
+/* Optional control info. If a partition is stored with an A/B versioning
+ * scheme (i.e. in more than one physical partition in NVRAM) the host can set
+ * this to control which underlying physical partition is used to read data
+ * from. This allows it to perform a read-modify-write-verify with the write
+ * lock continuously held by calling NVRAM_UPDATE_START, reading the old
+ * contents using MODE=TARGET_CURRENT, overwriting the old partition and then
+ * verifying by reading with MODE=TARGET_BACKUP.
+ */
+#define       MC_CMD_NVRAM_READ_IN_V2_MODE_OFST 12
+/* enum: Same as omitting MODE: caller sees data in current partition unless it
+ * holds the write lock in which case it sees data in the partition it is
+ * updating.
+ */
+#define          MC_CMD_NVRAM_READ_IN_V2_DEFAULT 0x0
+/* enum: Read from the current partition of an A/B pair, even if holding the
+ * write lock.
+ */
+#define          MC_CMD_NVRAM_READ_IN_V2_TARGET_CURRENT 0x1
+/* enum: Read from the non-current (i.e. to be updated) partition of an A/B
+ * pair
+ */
+#define          MC_CMD_NVRAM_READ_IN_V2_TARGET_BACKUP 0x2
+
 /* MC_CMD_NVRAM_READ_OUT msgresponse */
 #define    MC_CMD_NVRAM_READ_OUT_LENMIN 1
 #define    MC_CMD_NVRAM_READ_OUT_LENMAX 252
@@ -3895,6 +4042,8 @@
 #define          MC_CMD_SENSOR_CCOM_AVREG_1V8_SUPPLY  0x39
 /* enum: CCOM AVREG 1v8 supply (external ADC): mV */
 #define          MC_CMD_SENSOR_CCOM_AVREG_1V8_SUPPLY_EXTADC  0x3a
+/* enum: CCOM RTS temperature: degC */
+#define          MC_CMD_SENSOR_CONTROLLER_RTS  0x3b
 /* enum: Not a sensor: reserved for the next page flag */
 #define          MC_CMD_SENSOR_PAGE1_NEXT  0x3f
 /* enum: controller internal temperature sensor voltage on master core
@@ -3931,6 +4080,12 @@
 #define          MC_CMD_SENSOR_PHY0_VCC  0x4c
 /* enum: Voltage supplied to the QSFP #1 from their power supply: mV */
 #define          MC_CMD_SENSOR_PHY1_VCC  0x4d
+/* enum: Controller die temperature (TDIODE): degC */
+#define          MC_CMD_SENSOR_CONTROLLER_TDIODE_TEMP  0x4e
+/* enum: Board temperature (front): degC */
+#define          MC_CMD_SENSOR_BOARD_FRONT_TEMP  0x4f
+/* enum: Board temperature (back): degC */
+#define          MC_CMD_SENSOR_BOARD_BACK_TEMP  0x50
 /* MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF */
 #define       MC_CMD_SENSOR_ENTRY_OFST 4
 #define       MC_CMD_SENSOR_ENTRY_LEN 8
@@ -4007,7 +4162,7 @@
 
 /* MC_CMD_READ_SENSORS_EXT_IN msgrequest */
 #define    MC_CMD_READ_SENSORS_EXT_IN_LEN 12
-/* DMA address of host buffer for sensor readings */
+/* DMA address of host buffer for sensor readings (must be 4Kbyte aligned). */
 #define       MC_CMD_READ_SENSORS_EXT_IN_DMA_ADDR_OFST 0
 #define       MC_CMD_READ_SENSORS_EXT_IN_DMA_ADDR_LEN 8
 #define       MC_CMD_READ_SENSORS_EXT_IN_DMA_ADDR_LO_OFST 0
@@ -4608,6 +4763,10 @@
  * operations
  */
 #define          MC_CMD_MUM_OP_QSFP 0xc
+/* enum: Request discrete and SODIMM DDR info (type, size, speed grade, voltage
+ * level) from MUM
+ */
+#define          MC_CMD_MUM_OP_READ_DDR_INFO 0xd
 
 /* MC_CMD_MUM_IN_NULL msgrequest */
 #define    MC_CMD_MUM_IN_NULL_LEN 4
@@ -4793,6 +4952,10 @@
 #define       MC_CMD_MUM_IN_PROGRAM_CLOCKS_FLAGS_OFST 8
 #define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_LBN 0
 #define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_WIDTH 1
+#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_NIC_FROM_FPGA_LBN 1
+#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_NIC_FROM_FPGA_WIDTH 1
+#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_REF_FROM_XO_LBN 2
+#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_REF_FROM_XO_WIDTH 1
 
 /* MC_CMD_MUM_IN_FPGA_LOAD msgrequest */
 #define    MC_CMD_MUM_IN_FPGA_LOAD_LEN 8
@@ -4862,6 +5025,11 @@
 #define       MC_CMD_MUM_IN_QSFP_POLL_BIST_HDR_OFST 4
 #define       MC_CMD_MUM_IN_QSFP_POLL_BIST_IDX_OFST 8
 
+/* MC_CMD_MUM_IN_READ_DDR_INFO msgrequest */
+#define    MC_CMD_MUM_IN_READ_DDR_INFO_LEN 4
+/* MUM cmd header */
+/*            MC_CMD_MUM_IN_CMD_OFST 0 */
+
 /* MC_CMD_MUM_OUT msgresponse */
 #define    MC_CMD_MUM_OUT_LEN 0
 
@@ -5004,6 +5172,69 @@
 #define    MC_CMD_MUM_OUT_QSFP_POLL_BIST_LEN 4
 #define       MC_CMD_MUM_OUT_QSFP_POLL_BIST_TEST_OFST 0
 
+/* MC_CMD_MUM_OUT_READ_DDR_INFO msgresponse */
+#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LENMIN 24
+#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LENMAX 248
+#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LEN(num) (8+8*(num))
+/* Discrete (soldered) DDR resistor strap info */
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_DISCRETE_DDR_INFO_OFST 0
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VRATIO_LBN 0
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VRATIO_WIDTH 16
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED1_LBN 16
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED1_WIDTH 16
+/* Number of SODIMM info records */
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_NUM_RECORDS_OFST 4
+/* Array of SODIMM info records */
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_OFST 8
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LEN 8
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LO_OFST 8
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_HI_OFST 12
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_MINNUM 2
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_MAXNUM 30
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_BANK_ID_LBN 0
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_BANK_ID_WIDTH 8
+/* enum: SODIMM bank 1 (Top SODIMM for Sorrento) */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_BANK1 0x0
+/* enum: SODIMM bank 2 (Bottom SODDIMM for Sorrento) */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_BANK2 0x1
+/* enum: Total number of SODIMM banks */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NUM_BANKS 0x2
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_TYPE_LBN 8
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_TYPE_WIDTH 8
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RANK_LBN 16
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RANK_WIDTH 4
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VOLTAGE_LBN 20
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VOLTAGE_WIDTH 4
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NOT_POWERED 0x0 /* enum */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V25 0x1 /* enum */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V35 0x2 /* enum */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V5 0x3 /* enum */
+/* enum: Values 5-15 are reserved for future usage */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V8 0x4
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SIZE_LBN 24
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SIZE_WIDTH 8
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SPEED_LBN 32
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SPEED_WIDTH 16
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_STATE_LBN 48
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_STATE_WIDTH 4
+/* enum: No module present */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_ABSENT 0x0
+/* enum: Module present supported and powered on */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_POWERED 0x1
+/* enum: Module present but bad type */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_TYPE 0x2
+/* enum: Module present but incompatible voltage */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_VOLTAGE 0x3
+/* enum: Module present but unknown SPD */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_SPD 0x4
+/* enum: Module present but slot cannot support it */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_SLOT 0x5
+/* enum: Modules may or may not be present, but cannot establish contact by I2C
+ */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NOT_REACHABLE 0x6
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED2_LBN 52
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED2_WIDTH 12
+
 /* MC_CMD_RESOURCE_SPECIFIER enum */
 /* enum: Any */
 #define          MC_CMD_RESOURCE_INSTANCE_ANY 0xffffffff
@@ -5076,6 +5307,8 @@
 #define          NVRAM_PARTITION_TYPE_DYNAMIC_CONFIG       0x500
 /* enum: Expansion ROM configuration data for port 0 */
 #define          NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT0  0x600
+/* enum: Synonym for EXPROM_CONFIG_PORT0 as used in pmap files */
+#define          NVRAM_PARTITION_TYPE_EXPROM_CONFIG        0x600
 /* enum: Expansion ROM configuration data for port 1 */
 #define          NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT1  0x601
 /* enum: Expansion ROM configuration data for port 2 */
@@ -5084,6 +5317,8 @@
 #define          NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT3  0x603
 /* enum: Non-volatile log output partition */
 #define          NVRAM_PARTITION_TYPE_LOG                  0x700
+/* enum: Non-volatile log output of second core on dual-core device */
+#define          NVRAM_PARTITION_TYPE_LOG_SLAVE            0x701
 /* enum: Device state dump output partition */
 #define          NVRAM_PARTITION_TYPE_DUMP                 0x800
 /* enum: Application license key storage partition */
@@ -5116,6 +5351,20 @@
 #define          NVRAM_PARTITION_TYPE_MUM_USER_ROM         0xc05
 /* enum: MUM fuses and lockbits partition. */
 #define          NVRAM_PARTITION_TYPE_MUM_FUSELOCK         0xc06
+/* enum: UEFI expansion ROM if separate from PXE */
+#define          NVRAM_PARTITION_TYPE_EXPANSION_UEFI       0xd00
+/* enum: Spare partition 0 */
+#define          NVRAM_PARTITION_TYPE_SPARE_0              0x1000
+/* enum: Spare partition 1 */
+#define          NVRAM_PARTITION_TYPE_SPARE_1              0x1100
+/* enum: Spare partition 2 */
+#define          NVRAM_PARTITION_TYPE_SPARE_2              0x1200
+/* enum: Spare partition 3 */
+#define          NVRAM_PARTITION_TYPE_SPARE_3              0x1300
+/* enum: Spare partition 4 */
+#define          NVRAM_PARTITION_TYPE_SPARE_4              0x1400
+/* enum: Spare partition 5 */
+#define          NVRAM_PARTITION_TYPE_SPARE_5              0x1500
 /* enum: Start of reserved value range (firmware may use for any purpose) */
 #define          NVRAM_PARTITION_TYPE_RESERVED_VALUES_MIN  0xff00
 /* enum: End of reserved value range (firmware may use for any purpose) */
@@ -5149,6 +5398,90 @@
 #define       LICENSED_APP_ID_ID_LBN 0
 #define       LICENSED_APP_ID_ID_WIDTH 32
 
+/* LICENSED_FEATURES structuredef */
+#define    LICENSED_FEATURES_LEN 8
+/* Bitmask of licensed firmware features */
+#define       LICENSED_FEATURES_MASK_OFST 0
+#define       LICENSED_FEATURES_MASK_LEN 8
+#define       LICENSED_FEATURES_MASK_LO_OFST 0
+#define       LICENSED_FEATURES_MASK_HI_OFST 4
+#define        LICENSED_FEATURES_RX_CUT_THROUGH_LBN 0
+#define        LICENSED_FEATURES_RX_CUT_THROUGH_WIDTH 1
+#define        LICENSED_FEATURES_PIO_LBN 1
+#define        LICENSED_FEATURES_PIO_WIDTH 1
+#define        LICENSED_FEATURES_EVQ_TIMER_LBN 2
+#define        LICENSED_FEATURES_EVQ_TIMER_WIDTH 1
+#define        LICENSED_FEATURES_CLOCK_LBN 3
+#define        LICENSED_FEATURES_CLOCK_WIDTH 1
+#define        LICENSED_FEATURES_RX_TIMESTAMPS_LBN 4
+#define        LICENSED_FEATURES_RX_TIMESTAMPS_WIDTH 1
+#define        LICENSED_FEATURES_TX_TIMESTAMPS_LBN 5
+#define        LICENSED_FEATURES_TX_TIMESTAMPS_WIDTH 1
+#define        LICENSED_FEATURES_RX_SNIFF_LBN 6
+#define        LICENSED_FEATURES_RX_SNIFF_WIDTH 1
+#define        LICENSED_FEATURES_TX_SNIFF_LBN 7
+#define        LICENSED_FEATURES_TX_SNIFF_WIDTH 1
+#define        LICENSED_FEATURES_PROXY_FILTER_OPS_LBN 8
+#define        LICENSED_FEATURES_PROXY_FILTER_OPS_WIDTH 1
+#define        LICENSED_FEATURES_EVENT_CUT_THROUGH_LBN 9
+#define        LICENSED_FEATURES_EVENT_CUT_THROUGH_WIDTH 1
+#define       LICENSED_FEATURES_MASK_LBN 0
+#define       LICENSED_FEATURES_MASK_WIDTH 64
+
+/* LICENSED_V3_APPS structuredef */
+#define    LICENSED_V3_APPS_LEN 8
+/* Bitmask of licensed applications */
+#define       LICENSED_V3_APPS_MASK_OFST 0
+#define       LICENSED_V3_APPS_MASK_LEN 8
+#define       LICENSED_V3_APPS_MASK_LO_OFST 0
+#define       LICENSED_V3_APPS_MASK_HI_OFST 4
+#define        LICENSED_V3_APPS_ONLOAD_LBN 0
+#define        LICENSED_V3_APPS_ONLOAD_WIDTH 1
+#define        LICENSED_V3_APPS_PTP_LBN 1
+#define        LICENSED_V3_APPS_PTP_WIDTH 1
+#define        LICENSED_V3_APPS_SOLARCAPTURE_PRO_LBN 2
+#define        LICENSED_V3_APPS_SOLARCAPTURE_PRO_WIDTH 1
+#define        LICENSED_V3_APPS_SOLARSECURE_LBN 3
+#define        LICENSED_V3_APPS_SOLARSECURE_WIDTH 1
+#define        LICENSED_V3_APPS_PERF_MONITOR_LBN 4
+#define        LICENSED_V3_APPS_PERF_MONITOR_WIDTH 1
+#define        LICENSED_V3_APPS_SOLARCAPTURE_LIVE_LBN 5
+#define        LICENSED_V3_APPS_SOLARCAPTURE_LIVE_WIDTH 1
+#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_LBN 6
+#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_WIDTH 1
+#define        LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_LBN 7
+#define        LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_WIDTH 1
+#define       LICENSED_V3_APPS_MASK_LBN 0
+#define       LICENSED_V3_APPS_MASK_WIDTH 64
+
+/* LICENSED_V3_FEATURES structuredef */
+#define    LICENSED_V3_FEATURES_LEN 8
+/* Bitmask of licensed firmware features */
+#define       LICENSED_V3_FEATURES_MASK_OFST 0
+#define       LICENSED_V3_FEATURES_MASK_LEN 8
+#define       LICENSED_V3_FEATURES_MASK_LO_OFST 0
+#define       LICENSED_V3_FEATURES_MASK_HI_OFST 4
+#define        LICENSED_V3_FEATURES_RX_CUT_THROUGH_LBN 0
+#define        LICENSED_V3_FEATURES_RX_CUT_THROUGH_WIDTH 1
+#define        LICENSED_V3_FEATURES_PIO_LBN 1
+#define        LICENSED_V3_FEATURES_PIO_WIDTH 1
+#define        LICENSED_V3_FEATURES_EVQ_TIMER_LBN 2
+#define        LICENSED_V3_FEATURES_EVQ_TIMER_WIDTH 1
+#define        LICENSED_V3_FEATURES_CLOCK_LBN 3
+#define        LICENSED_V3_FEATURES_CLOCK_WIDTH 1
+#define        LICENSED_V3_FEATURES_RX_TIMESTAMPS_LBN 4
+#define        LICENSED_V3_FEATURES_RX_TIMESTAMPS_WIDTH 1
+#define        LICENSED_V3_FEATURES_TX_TIMESTAMPS_LBN 5
+#define        LICENSED_V3_FEATURES_TX_TIMESTAMPS_WIDTH 1
+#define        LICENSED_V3_FEATURES_RX_SNIFF_LBN 6
+#define        LICENSED_V3_FEATURES_RX_SNIFF_WIDTH 1
+#define        LICENSED_V3_FEATURES_TX_SNIFF_LBN 7
+#define        LICENSED_V3_FEATURES_TX_SNIFF_WIDTH 1
+#define        LICENSED_V3_FEATURES_PROXY_FILTER_OPS_LBN 8
+#define        LICENSED_V3_FEATURES_PROXY_FILTER_OPS_WIDTH 1
+#define       LICENSED_V3_FEATURES_MASK_LBN 0
+#define       LICENSED_V3_FEATURES_MASK_WIDTH 64
+
 /* TX_TIMESTAMP_EVENT structuredef */
 #define    TX_TIMESTAMP_EVENT_LEN 6
 /* lower 16 bits of timestamp data */
@@ -5258,6 +5591,8 @@
 #define        MC_CMD_INIT_EVQ_IN_FLAG_RX_MERGE_WIDTH 1
 #define        MC_CMD_INIT_EVQ_IN_FLAG_TX_MERGE_LBN 5
 #define        MC_CMD_INIT_EVQ_IN_FLAG_TX_MERGE_WIDTH 1
+#define        MC_CMD_INIT_EVQ_IN_FLAG_USE_TIMER_LBN 6
+#define        MC_CMD_INIT_EVQ_IN_FLAG_USE_TIMER_WIDTH 1
 #define       MC_CMD_INIT_EVQ_IN_TMR_MODE_OFST 20
 /* enum: Disabled */
 #define          MC_CMD_INIT_EVQ_IN_TMR_MODE_DIS 0x0
@@ -5362,6 +5697,8 @@
 #define        MC_CMD_INIT_RXQ_IN_FLAG_PREFIX_WIDTH 1
 #define        MC_CMD_INIT_RXQ_IN_FLAG_DISABLE_SCATTER_LBN 9
 #define        MC_CMD_INIT_RXQ_IN_FLAG_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_INIT_RXQ_IN_FLAG_FORCE_EV_MERGING_LBN 10
+#define        MC_CMD_INIT_RXQ_IN_FLAG_FORCE_EV_MERGING_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_IN_OWNER_ID_OFST 20
 /* The port ID associated with the v-adaptor which should contain this DMAQ. */
@@ -5422,6 +5759,8 @@
 #define          MC_CMD_INIT_RXQ_EXT_IN_PS_BUFF_64K  0x4 /* enum */
 #define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_WANT_OUTER_CLASSES_LBN 18
 #define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_WANT_OUTER_CLASSES_WIDTH 1
+#define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_FORCE_EV_MERGING_LBN 19
+#define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_FORCE_EV_MERGING_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_EXT_IN_OWNER_ID_OFST 20
 /* The port ID associated with the v-adaptor which should contain this DMAQ. */
@@ -5535,6 +5874,8 @@
 #define        MC_CMD_INIT_TXQ_EXT_IN_FLAG_INNER_IP_CSUM_EN_WIDTH 1
 #define        MC_CMD_INIT_TXQ_EXT_IN_FLAG_INNER_TCP_CSUM_EN_LBN 11
 #define        MC_CMD_INIT_TXQ_EXT_IN_FLAG_INNER_TCP_CSUM_EN_WIDTH 1
+#define        MC_CMD_INIT_TXQ_EXT_IN_FLAG_TSOV2_EN_LBN 12
+#define        MC_CMD_INIT_TXQ_EXT_IN_FLAG_TSOV2_EN_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_TXQ_EXT_IN_OWNER_ID_OFST 20
 /* The port ID associated with the v-adaptor which should contain this DMAQ. */
@@ -5747,6 +6088,46 @@
 #define       MC_CMD_PROXY_CONFIGURE_IN_ALLOWED_MCDI_MASK_OFST 44
 #define       MC_CMD_PROXY_CONFIGURE_IN_ALLOWED_MCDI_MASK_LEN 64
 
+/* MC_CMD_PROXY_CONFIGURE_EXT_IN msgrequest */
+#define    MC_CMD_PROXY_CONFIGURE_EXT_IN_LEN 112
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_FLAGS_OFST 0
+#define        MC_CMD_PROXY_CONFIGURE_EXT_IN_ENABLE_LBN 0
+#define        MC_CMD_PROXY_CONFIGURE_EXT_IN_ENABLE_WIDTH 1
+/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
+ * of blocks, each of the size REQUEST_BLOCK_SIZE.
+ */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_OFST 4
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LEN 8
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LO_OFST 4
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_HI_OFST 8
+/* Must be a power of 2 */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BLOCK_SIZE_OFST 12
+/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
+ * of blocks, each of the size REPLY_BLOCK_SIZE.
+ */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_OFST 16
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LEN 8
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LO_OFST 16
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_HI_OFST 20
+/* Must be a power of 2 */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BLOCK_SIZE_OFST 24
+/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
+ * of blocks, each of the size STATUS_BLOCK_SIZE. This buffer is only needed if
+ * host intends to complete proxied operations by using MC_CMD_PROXY_CMD.
+ */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_OFST 28
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LEN 8
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LO_OFST 28
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_HI_OFST 32
+/* Must be a power of 2, or zero if this buffer is not provided */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BLOCK_SIZE_OFST 36
+/* Applies to all three buffers */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_NUM_BLOCKS_OFST 40
+/* A bit mask defining which MCDI operations may be proxied */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_ALLOWED_MCDI_MASK_OFST 44
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_ALLOWED_MCDI_MASK_LEN 64
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_RESERVED_OFST 108
+
 /* MC_CMD_PROXY_CONFIGURE_OUT msgresponse */
 #define    MC_CMD_PROXY_CONFIGURE_OUT_LEN 0
 
@@ -6323,6 +6704,15 @@
  * client
  */
 #define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_RESTRICTIONS  0x2
+/* enum: read properties relating to security rules (Medford-only; for use by
+ * SolarSecure apps, not directly by drivers. See SF-114946-SW.)
+ */
+#define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SECURITY_RULE_INFO  0x3
+/* enum: read the list of supported RX filter matches for VXLAN/NVGRE
+ * encapsulated frames, which follow a different match sequence to normal
+ * frames (Medford only)
+ */
+#define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SUPPORTED_ENCAP_RX_MATCHES  0x4
 
 /* MC_CMD_GET_PARSER_DISP_INFO_OUT msgresponse */
 #define    MC_CMD_GET_PARSER_DISP_INFO_OUT_LENMIN 8
@@ -6356,7 +6746,10 @@
 
 /***********************************/
 /* MC_CMD_PARSER_DISP_RW
- * Direct read/write of parser-dispatcher state (DICPUs and LUE) for debugging
+ * Direct read/write of parser-dispatcher state (DICPUs and LUE) for debugging.
+ * Please note that this interface is only of use to debug tools which have
+ * knowledge of firmware and hardware data structures; nothing here is intended
+ * for use by normal driver code.
  */
 #define MC_CMD_PARSER_DISP_RW 0xe5
 
@@ -6374,6 +6767,12 @@
 #define          MC_CMD_PARSER_DISP_RW_IN_LUE  0x2
 /* enum: Lookup engine (with requested metadata format) */
 #define          MC_CMD_PARSER_DISP_RW_IN_LUE_VERSIONED_METADATA  0x3
+/* enum: RX0 dispatcher CPU (alias for RX_DICPU; Medford has 2 RX DICPUs) */
+#define          MC_CMD_PARSER_DISP_RW_IN_RX0_DICPU  0x0
+/* enum: RX1 dispatcher CPU (only valid for Medford) */
+#define          MC_CMD_PARSER_DISP_RW_IN_RX1_DICPU  0x4
+/* enum: Miscellaneous other state (only valid for Medford) */
+#define          MC_CMD_PARSER_DISP_RW_IN_MISC_STATE  0x5
 /* identifies the type of operation requested */
 #define       MC_CMD_PARSER_DISP_RW_IN_OP_OFST 4
 /* enum: read a word of DICPU DMEM or a LUE entry */
@@ -6382,8 +6781,12 @@
 #define          MC_CMD_PARSER_DISP_RW_IN_WRITE  0x1
 /* enum: read-modify-write a word of DICPU DMEM (not valid for LUE) */
 #define          MC_CMD_PARSER_DISP_RW_IN_RMW  0x2
-/* data memory address or LUE index */
+/* data memory address (DICPU targets) or LUE index (LUE targets) */
 #define       MC_CMD_PARSER_DISP_RW_IN_ADDRESS_OFST 8
+/* selector (for MISC_STATE target) */
+#define       MC_CMD_PARSER_DISP_RW_IN_SELECTOR_OFST 8
+/* enum: Port to datapath mapping */
+#define          MC_CMD_PARSER_DISP_RW_IN_PORT_DP_MAPPING  0x1
 /* value to write (for DMEM writes) */
 #define       MC_CMD_PARSER_DISP_RW_IN_DMEM_WRITE_VALUE_OFST 12
 /* XOR value (for DMEM read-modify-writes: new = (old & mask) ^ value) */
@@ -6408,6 +6811,12 @@
  */
 #define       MC_CMD_PARSER_DISP_RW_OUT_LUE_MGR_STATE_OFST 20
 #define       MC_CMD_PARSER_DISP_RW_OUT_LUE_MGR_STATE_LEN 32
+/* datapath(s) used for each port (for MISC_STATE PORT_DP_MAPPING selector) */
+#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_OFST 0
+#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_LEN 4
+#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_NUM 4
+#define          MC_CMD_PARSER_DISP_RW_OUT_DP0  0x1 /* enum */
+#define          MC_CMD_PARSER_DISP_RW_OUT_DP1  0x2 /* enum */
 
 
 /***********************************/
@@ -7071,6 +7480,24 @@
 #define    MC_CMD_GET_CAPABILITIES_OUT_LEN 20
 /* First word of flags. */
 #define       MC_CMD_GET_CAPABILITIES_OUT_FLAGS1_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
 #define        MC_CMD_GET_CAPABILITIES_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
 #define        MC_CMD_GET_CAPABILITIES_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
 #define        MC_CMD_GET_CAPABILITIES_OUT_ADDITIONAL_RSS_MODES_LBN 13
@@ -7138,6 +7565,8 @@
 #define          MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_RX_HDR_SPLIT  0x107
 /* enum: RXDP Test firmware image 8 */
 #define          MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_DISABLE_DL  0x108
+/* enum: RXDP Test firmware image 9 */
+#define          MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_DOORBELL_DELAY  0x10b
 /* TxDPCPU firmware id. */
 #define       MC_CMD_GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID_OFST 6
 #define       MC_CMD_GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID_LEN 2
@@ -7153,6 +7582,8 @@
 #define          MC_CMD_GET_CAPABILITIES_OUT_TXDP_TEST_FW_TSO_EDIT  0x101
 /* enum: TXDP Test firmware image 2 */
 #define          MC_CMD_GET_CAPABILITIES_OUT_TXDP_TEST_FW_PACKET_EDITS  0x102
+/* enum: TXDP CSR bus test firmware */
+#define          MC_CMD_GET_CAPABILITIES_OUT_TXDP_TEST_FW_CSR  0x103
 #define       MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_OFST 8
 #define       MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_LEN 2
 #define        MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_REV_LBN 0
@@ -7227,6 +7658,258 @@
 /* Licensed capabilities */
 #define       MC_CMD_GET_CAPABILITIES_OUT_LICENSE_CAPABILITIES_OFST 16
 
+/* MC_CMD_GET_CAPABILITIES_V2_IN msgrequest */
+#define    MC_CMD_GET_CAPABILITIES_V2_IN_LEN 0
+
+/* MC_CMD_GET_CAPABILITIES_V2_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V2_OUT_LEN 72
+/* First word of flags. */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_FLAGS1_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VXLAN_NVGRE_WIDTH 1
+/* RxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DPCPU_FW_ID_LEN 2
+/* enum: Standard RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP  0x0
+/* enum: Low latency RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_LOW_LATENCY  0x1
+/* enum: Packed stream RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_PACKED_STREAM  0x2
+/* enum: BIST RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_BIST  0x10a
+/* enum: RXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH  0x101
+/* enum: RXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD  0x102
+/* enum: RXDP Test firmware image 3 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST  0x103
+/* enum: RXDP Test firmware image 4 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE  0x104
+/* enum: RXDP Test firmware image 5 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_BACKPRESSURE  0x105
+/* enum: RXDP Test firmware image 6 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_PACKET_EDITS  0x106
+/* enum: RXDP Test firmware image 7 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_RX_HDR_SPLIT  0x107
+/* enum: RXDP Test firmware image 8 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_DISABLE_DL  0x108
+/* enum: RXDP Test firmware image 9 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_DOORBELL_DELAY  0x10b
+/* TxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DPCPU_FW_ID_LEN 2
+/* enum: Standard TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP  0x0
+/* enum: Low latency TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_LOW_LATENCY  0x1
+/* enum: High packet rate TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_HIGH_PACKET_RATE  0x3
+/* enum: BIST TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_BIST  0x12d
+/* enum: TXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_TSO_EDIT  0x101
+/* enum: TXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_PACKET_EDITS  0x102
+/* enum: TXDP CSR bus test firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_CSR  0x103
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_RESERVED  0x0
+/* enum: Trivial RX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_FIRST_PKT  0x1
+/* enum: RX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_SIENA_COMPAT  0x2
+/* enum: Virtual switching (full feature) RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_VSWITCH  0x3
+/* enum: siena_compat variant RX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM  0x4
+/* enum: Low latency RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_LOW_LATENCY  0x5
+/* enum: Packed stream RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_PACKED_STREAM  0x6
+/* enum: RX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_LAYER2_PERF  0x7
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE  0xe
+/* enum: RX PD firmware parsing but not filtering network overlay tunnel
+ * encapsulations (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY  0xf
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_RESERVED  0x0
+/* enum: Trivial TX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_FIRST_PKT  0x1
+/* enum: TX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_SIENA_COMPAT  0x2
+/* enum: Virtual switching (full feature) TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_VSWITCH  0x3
+/* enum: siena_compat variant TX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM  0x4
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_LOW_LATENCY  0x5 /* enum */
+/* enum: TX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_LAYER2_PERF  0x7
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE  0xe
+/* Hardware capabilities of NIC */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_HW_CAPABILITIES_OFST 12
+/* Licensed capabilities */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_LICENSE_CAPABILITIES_OFST 16
+/* Second word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_FLAGS2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_CUT_THROUGH_WIDTH 1
+/* Number of FATSOv2 contexts per datapath supported by this NIC. Not present
+ * on older firmware (check the length).
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+/* One byte per PF containing the number of the external port assigned to this
+ * PF, indexed by PF number. Special values indicate that a PF is either not
+ * present or not assigned.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_ACCESS_NOT_PERMITTED  0xff
+/* enum: PF does not exist. */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_PRESENT  0xfe
+/* enum: PF does exist but is not assigned to any external port. */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_ASSIGNED  0xfd
+/* enum: This value indicates that PF is assigned, but it cannot be expressed
+ * in this field. It is intended for a possible future situation where a more
+ * complex scheme of PFs to ports mapping is being used. The future driver
+ * should look for a new field supporting the new scheme. The current/old
+ * driver should treat this value as PF_NOT_ASSIGNED.
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_INCOMPATIBLE_ASSIGNMENT  0xfc
+/* One byte per PF containing the number of its VFs, indexed by PF number. A
+ * special value indicates that a PF is not present.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+/*               MC_CMD_GET_CAPABILITIES_V2_OUT_ACCESS_NOT_PERMITTED  0xff */
+/* enum: PF does not exist. */
+/*               MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_PRESENT  0xfe */
+/* Number of VIs available for each external port */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_NUM 4
+/* Size of RX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ RX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DESC_CACHE_SIZE_LEN 1
+/* Size of TX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ TX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DESC_CACHE_SIZE_LEN 1
+/* Total number of available PIO buffers */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_PIO_BUFFS_LEN 2
+/* Size of a single PIO buffer */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_SIZE_PIO_BUFF_LEN 2
+
 
 /***********************************/
 /* MC_CMD_V2_EXTN
@@ -7475,6 +8158,25 @@
 
 
 /***********************************/
+/* MC_CMD_VSWITCH_QUERY
+ * read some config of v-switch. For now this command is an empty placeholder.
+ * It may be used to check if a v-switch is connected to a given EVB port (if
+ * not, then the command returns ENOENT).
+ */
+#define MC_CMD_VSWITCH_QUERY 0x63
+
+#define MC_CMD_0x63_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_VSWITCH_QUERY_IN msgrequest */
+#define    MC_CMD_VSWITCH_QUERY_IN_LEN 4
+/* The port to which the v-switch is connected. */
+#define       MC_CMD_VSWITCH_QUERY_IN_UPSTREAM_PORT_ID_OFST 0
+
+/* MC_CMD_VSWITCH_QUERY_OUT msgresponse */
+#define    MC_CMD_VSWITCH_QUERY_OUT_LEN 0
+
+
+/***********************************/
 /* MC_CMD_VPORT_ALLOC
  * allocate a v-port.
  */
@@ -7510,6 +8212,8 @@
 #define       MC_CMD_VPORT_ALLOC_IN_FLAGS_OFST 8
 #define        MC_CMD_VPORT_ALLOC_IN_FLAG_AUTO_PORT_LBN 0
 #define        MC_CMD_VPORT_ALLOC_IN_FLAG_AUTO_PORT_WIDTH 1
+#define        MC_CMD_VPORT_ALLOC_IN_FLAG_VLAN_RESTRICT_LBN 1
+#define        MC_CMD_VPORT_ALLOC_IN_FLAG_VLAN_RESTRICT_WIDTH 1
 /* The number of VLAN tags to insert/remove. An error will be returned if
  * incompatible with the number of VLAN tags specified for the upstream
  * v-switch.
@@ -7561,6 +8265,8 @@
 #define       MC_CMD_VADAPTOR_ALLOC_IN_FLAGS_OFST 8
 #define        MC_CMD_VADAPTOR_ALLOC_IN_FLAG_AUTO_VADAPTOR_LBN 0
 #define        MC_CMD_VADAPTOR_ALLOC_IN_FLAG_AUTO_VADAPTOR_WIDTH 1
+#define        MC_CMD_VADAPTOR_ALLOC_IN_FLAG_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 1
+#define        MC_CMD_VADAPTOR_ALLOC_IN_FLAG_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
 /* The number of VLAN tags to strip on receive */
 #define       MC_CMD_VADAPTOR_ALLOC_IN_NUM_VLANS_OFST 12
 /* The number of VLAN tags to transparently insert/remove. */
@@ -7639,6 +8345,29 @@
 
 
 /***********************************/
+/* MC_CMD_VADAPTOR_QUERY
+ * read some config of v-adaptor.
+ */
+#define MC_CMD_VADAPTOR_QUERY 0x61
+
+#define MC_CMD_0x61_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_VADAPTOR_QUERY_IN msgrequest */
+#define    MC_CMD_VADAPTOR_QUERY_IN_LEN 4
+/* The port to which the v-adaptor is connected. */
+#define       MC_CMD_VADAPTOR_QUERY_IN_UPSTREAM_PORT_ID_OFST 0
+
+/* MC_CMD_VADAPTOR_QUERY_OUT msgresponse */
+#define    MC_CMD_VADAPTOR_QUERY_OUT_LEN 12
+/* The EVB port flags as defined at MC_CMD_VPORT_ALLOC. */
+#define       MC_CMD_VADAPTOR_QUERY_OUT_PORT_FLAGS_OFST 0
+/* The v-adaptor flags as defined at MC_CMD_VADAPTOR_ALLOC. */
+#define       MC_CMD_VADAPTOR_QUERY_OUT_VADAPTOR_FLAGS_OFST 4
+/* The number of VLAN tags that may still be added */
+#define       MC_CMD_VADAPTOR_QUERY_OUT_NUM_AVAILABLE_VLAN_TAGS_OFST 8
+
+
+/***********************************/
 /* MC_CMD_EVB_PORT_ASSIGN
  * assign a port to a PCI function.
  */
@@ -7875,10 +8604,17 @@
 #define    MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_LEN 8
 /* The handle of the RSS context */
 #define       MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_RSS_CONTEXT_ID_OFST 0
-/* Hash control flags. The _EN bits are always supported. The _MODE bits only
- * work when the firmware reports ADDITIONAL_RSS_MODES in
- * MC_CMD_GET_CAPABILITIES and override the _EN bits if any of them are not 0.
- * See the RSS_MODE structure for the meaning of the mode bits.
+/* Hash control flags. The _EN bits are always supported, but new modes are
+ * available when ADDITIONAL_RSS_MODES is reported by MC_CMD_GET_CAPABILITIES:
+ * in this case, the MODE fields may be set to non-zero values, and will take
+ * effect regardless of the settings of the _EN flags. See the RSS_MODE
+ * structure for the meaning of the mode bits. Drivers must check the
+ * capability before trying to set any _MODE fields, as older firmware will
+ * reject any attempt to set the FLAGS field to a value > 0xff with EINVAL. In
+ * the case where all the _MODE flags are zero, the _EN flags take effect,
+ * providing backward compatibility for existing drivers. (Setting all _MODE
+ * *and* all _EN flags to zero is valid, to disable RSS spreading for that
+ * particular packet type.)
  */
 #define       MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_FLAGS_OFST 4
 #define        MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_IPV4_EN_LBN 0
@@ -7923,11 +8659,18 @@
 
 /* MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT msgresponse */
 #define    MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_LEN 8
-/* Hash control flags. If any _MODE bits are non-zero (which will only be true
- * when the firmware reports ADDITIONAL_RSS_MODES) then the _EN bits should be
- * disregarded (but are guaranteed to be consistent with the _MODE bits if
- * RSS_CONTEXT_SET_FLAGS has never been called for this context since it was
- * allocated).
+/* Hash control flags. If all _MODE bits are zero (which will always be true
+ * for older firmware which does not report the ADDITIONAL_RSS_MODES
+ * capability), the _EN bits report the state. If any _MODE bits are non-zero
+ * (which will only be true when the firmware reports ADDITIONAL_RSS_MODES)
+ * then the _EN bits should be disregarded, although the _MODE flags are
+ * guaranteed to be consistent with the _EN flags for a freshly-allocated RSS
+ * context and in the case where the _EN flags were used in the SET. This
+ * provides backward compatibility: old drivers will not be attempting to
+ * derive any meaning from the _MODE bits (and can never set them to any value
+ * not representable by the _EN bits); new drivers can always determine the
+ * mode by looking only at the _MODE bits; the value returned by a GET can
+ * always be used for a SET regardless of old/new driver vs. old/new firmware.
  */
 #define       MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_FLAGS_OFST 4
 #define        MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV4_EN_LBN 0
@@ -8155,6 +8898,74 @@
 
 
 /***********************************/
+/* MC_CMD_VPORT_RECONFIGURE
+ * Replace VLAN tags and/or MAC addresses of an existing v-port. If the v-port
+ * has already been passed to another function (v-port's user), then that
+ * function will be reset before applying the changes.
+ */
+#define MC_CMD_VPORT_RECONFIGURE 0xeb
+
+#define MC_CMD_0xeb_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_VPORT_RECONFIGURE_IN msgrequest */
+#define    MC_CMD_VPORT_RECONFIGURE_IN_LEN 44
+/* The handle of the v-port */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_VPORT_ID_OFST 0
+/* Flags requesting what should be changed. */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_FLAGS_OFST 4
+#define        MC_CMD_VPORT_RECONFIGURE_IN_REPLACE_VLAN_TAGS_LBN 0
+#define        MC_CMD_VPORT_RECONFIGURE_IN_REPLACE_VLAN_TAGS_WIDTH 1
+#define        MC_CMD_VPORT_RECONFIGURE_IN_REPLACE_MACADDRS_LBN 1
+#define        MC_CMD_VPORT_RECONFIGURE_IN_REPLACE_MACADDRS_WIDTH 1
+/* The number of VLAN tags to insert/remove. An error will be returned if
+ * incompatible with the number of VLAN tags specified for the upstream
+ * v-switch.
+ */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_NUM_VLAN_TAGS_OFST 8
+/* The actual VLAN tags to insert/remove */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_VLAN_TAGS_OFST 12
+#define        MC_CMD_VPORT_RECONFIGURE_IN_VLAN_TAG_0_LBN 0
+#define        MC_CMD_VPORT_RECONFIGURE_IN_VLAN_TAG_0_WIDTH 16
+#define        MC_CMD_VPORT_RECONFIGURE_IN_VLAN_TAG_1_LBN 16
+#define        MC_CMD_VPORT_RECONFIGURE_IN_VLAN_TAG_1_WIDTH 16
+/* The number of MAC addresses to add */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_NUM_MACADDRS_OFST 16
+/* MAC addresses to add */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_MACADDRS_OFST 20
+#define       MC_CMD_VPORT_RECONFIGURE_IN_MACADDRS_LEN 6
+#define       MC_CMD_VPORT_RECONFIGURE_IN_MACADDRS_NUM 4
+
+/* MC_CMD_VPORT_RECONFIGURE_OUT msgresponse */
+#define    MC_CMD_VPORT_RECONFIGURE_OUT_LEN 4
+#define       MC_CMD_VPORT_RECONFIGURE_OUT_FLAGS_OFST 0
+#define        MC_CMD_VPORT_RECONFIGURE_OUT_RESET_DONE_LBN 0
+#define        MC_CMD_VPORT_RECONFIGURE_OUT_RESET_DONE_WIDTH 1
+
+
+/***********************************/
+/* MC_CMD_EVB_PORT_QUERY
+ * read some config of v-port.
+ */
+#define MC_CMD_EVB_PORT_QUERY 0x62
+
+#define MC_CMD_0x62_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_EVB_PORT_QUERY_IN msgrequest */
+#define    MC_CMD_EVB_PORT_QUERY_IN_LEN 4
+/* The handle of the v-port */
+#define       MC_CMD_EVB_PORT_QUERY_IN_PORT_ID_OFST 0
+
+/* MC_CMD_EVB_PORT_QUERY_OUT msgresponse */
+#define    MC_CMD_EVB_PORT_QUERY_OUT_LEN 8
+/* The EVB port flags as defined at MC_CMD_VPORT_ALLOC. */
+#define       MC_CMD_EVB_PORT_QUERY_OUT_PORT_FLAGS_OFST 0
+/* The number of VLAN tags that may be used on a v-adaptor connected to this
+ * EVB port.
+ */
+#define       MC_CMD_EVB_PORT_QUERY_OUT_NUM_AVAILABLE_VLAN_TAGS_OFST 4
+
+
+/***********************************/
 /* MC_CMD_DUMP_BUFTBL_ENTRIES
  * Dump buffer table entries, mainly for command client debug use. Dumps
  * absolute entries, and does not use chunk handles. All entries must be in
@@ -8196,6 +9007,14 @@
 #define       MC_CMD_SET_RXDP_CONFIG_IN_DATA_OFST 0
 #define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_LBN 0
 #define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_WIDTH 1
+#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_LEN_LBN 1
+#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_LEN_WIDTH 2
+/* enum: pad to 64 bytes */
+#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_64  0x0
+/* enum: pad to 128 bytes (Medford only) */
+#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_128  0x1
+/* enum: pad to 256 bytes (Medford only) */
+#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_256   0x2
 
 /* MC_CMD_SET_RXDP_CONFIG_OUT msgresponse */
 #define    MC_CMD_SET_RXDP_CONFIG_OUT_LEN 0
@@ -8217,6 +9036,10 @@
 #define       MC_CMD_GET_RXDP_CONFIG_OUT_DATA_OFST 0
 #define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_LBN 0
 #define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_WIDTH 1
+#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_LEN_LBN 1
+#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_LEN_WIDTH 2
+/*             Enum values, see field(s): */
+/*                MC_CMD_SET_RXDP_CONFIG/MC_CMD_SET_RXDP_CONFIG_IN/PAD_HOST_LEN */
 
 
 /***********************************/
@@ -8788,32 +9611,38 @@
 #define       MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_MAXNUM 63
 #define        MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_ID_LBN 0
 #define        MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_ID_WIDTH 8
-/* enum: Attenuation (0-15, TBD for Medford) */
+/* enum: Attenuation (0-15, Huntington) */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_ATT  0x0
-/* enum: CTLE Boost (0-15, TBD for Medford) */
+/* enum: CTLE Boost (0-15, Huntington) */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_BOOST  0x1
-/* enum: Edge DFE Tap1 (0 - max negative, 64 - zero, 127 - max positive, TBD
- * for Medford)
+/* enum: Edge DFE Tap1 (Huntington - 0 - max negative, 64 - zero, 127 - max
+ * positive, Medford - 0-31)
  */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP1  0x2
-/* enum: Edge DFE Tap2 (0 - max negative, 32 - zero, 63 - max positive, TBD for
- * Medford)
+/* enum: Edge DFE Tap2 (Huntington - 0 - max negative, 32 - zero, 63 - max
+ * positive, Medford - 0-31)
  */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP2  0x3
-/* enum: Edge DFE Tap3 (0 - max negative, 32 - zero, 63 - max positive, TBD for
- * Medford)
+/* enum: Edge DFE Tap3 (Huntington - 0 - max negative, 32 - zero, 63 - max
+ * positive, Medford - 0-16)
  */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP3  0x4
-/* enum: Edge DFE Tap4 (0 - max negative, 32 - zero, 63 - max positive, TBD for
- * Medford)
+/* enum: Edge DFE Tap4 (Huntington - 0 - max negative, 32 - zero, 63 - max
+ * positive, Medford - 0-16)
  */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP4  0x5
-/* enum: Edge DFE Tap5 (0 - max negative, 32 - zero, 63 - max positive, TBD for
- * Medford)
+/* enum: Edge DFE Tap5 (Huntington - 0 - max negative, 32 - zero, 63 - max
+ * positive, Medford - 0-16)
  */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP5  0x6
-/* enum: Edge DFE DLEV (TBD for Medford) */
+/* enum: Edge DFE DLEV (0-128 for Medford) */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_DLEV  0x7
+/* enum: Variable Gain Amplifier (0-15, Medford) */
+#define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_VGA  0x8
+/* enum: CTLE EQ Capacitor (0-15, Medford) */
+#define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_CTLE_EQC  0x9
+/* enum: CTLE EQ Resistor (0-7, Medford) */
+#define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_CTLE_EQRES  0xa
 #define        MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_LANE_LBN 8
 #define        MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_LANE_WIDTH 3
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_LANE_0  0x0 /* enum */
@@ -8885,26 +9714,32 @@
 #define       MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_MAXNUM 63
 #define        MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_ID_LBN 0
 #define        MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_ID_WIDTH 8
-/* enum: TX Amplitude */
+/* enum: TX Amplitude (Huntington, Medford) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_LEV  0x0
-/* enum: De-Emphasis Tap1 Magnitude (0-7) */
+/* enum: De-Emphasis Tap1 Magnitude (0-7) (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_MODE  0x1
 /* enum: De-Emphasis Tap1 Fine */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_DTLEV  0x2
-/* enum: De-Emphasis Tap2 Magnitude (0-6) */
+/* enum: De-Emphasis Tap2 Magnitude (0-6) (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_D2  0x3
-/* enum: De-Emphasis Tap2 Fine */
+/* enum: De-Emphasis Tap2 Fine (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_D2TLEV  0x4
-/* enum: Pre-Emphasis Magnitude */
+/* enum: Pre-Emphasis Magnitude (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_E  0x5
-/* enum: Pre-Emphasis Fine */
+/* enum: Pre-Emphasis Fine (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_ETLEV  0x6
-/* enum: TX Slew Rate Coarse control */
+/* enum: TX Slew Rate Coarse control (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_PREDRV_DLY  0x7
-/* enum: TX Slew Rate Fine control */
+/* enum: TX Slew Rate Fine control (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_SR_SET  0x8
-/* enum: TX Termination Impedance control */
+/* enum: TX Termination Impedance control (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_RT_SET  0x9
+/* enum: TX Amplitude Fine control (Medford) */
+#define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_LEV_FINE  0xa
+/* enum: Pre-shoot Tap (Medford) */
+#define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TAP_ADV  0xb
+/* enum: De-emphasis Tap (Medford) */
+#define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TAP_DLY  0xc
 #define        MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LANE_LBN 8
 #define        MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LANE_WIDTH 3
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_0  0x0 /* enum */
@@ -9086,8 +9921,16 @@
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP4  0x5
 /* enum: DFE Tap5 (0 - max negative, 32 - zero, 63 - max positive) */
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP5  0x6
+/* enum: DFE DLev */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_DLEV  0x7
+/* enum: Figure of Merit */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_FOM  0x8
+/* enum: CTLE EQ Capacitor (HF Gain) */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_CTLE_EQC  0x9
+/* enum: CTLE EQ Resistor (DC Gain) */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_CTLE_EQRES  0xa
 #define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_LBN 8
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_WIDTH 4
+#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_WIDTH 5
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_0  0x0 /* enum */
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_1  0x1 /* enum */
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_2  0x2 /* enum */
@@ -9096,12 +9939,57 @@
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_5  0x5 /* enum */
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_6  0x6 /* enum */
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_7  0x7 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_ALL  0x8 /* enum */
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_LBN 12
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_WIDTH 12
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_8  0x8 /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_9  0x9 /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_10  0xa /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_11  0xb /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_12  0xc /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_13  0xd /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_14  0xe /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_15  0xf /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_ALL  0x10 /* enum */
+#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_LBN 13
+#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_WIDTH 1
+#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_LBN 14
+#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_WIDTH 10
 #define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_LBN 24
 #define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_WIDTH 8
 
+/* MC_CMD_PCIE_TUNE_RXEQ_SET_IN msgrequest */
+#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LENMIN 8
+#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LENMAX 252
+#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LEN(num) (4+4*(num))
+/* Requested operation */
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_OP_OFST 0
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_RSVD_OFST 1
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_RSVD_LEN 3
+/* RXEQ Parameter */
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_OFST 4
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LEN 4
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_MINNUM 1
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_MAXNUM 62
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_ID_LBN 0
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_ID_WIDTH 8
+/*             Enum values, see field(s): */
+/*                MC_CMD_PCIE_TUNE_RXEQ_GET_OUT/PARAM_ID */
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LANE_LBN 8
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LANE_WIDTH 5
+/*             Enum values, see field(s): */
+/*                MC_CMD_PCIE_TUNE_RXEQ_GET_OUT/PARAM_LANE */
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_LBN 13
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_WIDTH 1
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED_LBN 14
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED_WIDTH 2
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_INITIAL_LBN 16
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_INITIAL_WIDTH 8
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED2_LBN 24
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED2_WIDTH 8
+
+/* MC_CMD_PCIE_TUNE_RXEQ_SET_OUT msgresponse */
+#define    MC_CMD_PCIE_TUNE_RXEQ_SET_OUT_LEN 0
+
 /* MC_CMD_PCIE_TUNE_TXEQ_GET_IN msgrequest */
 #define    MC_CMD_PCIE_TUNE_TXEQ_GET_IN_LEN 4
 /* Requested operation */
@@ -9176,6 +10064,7 @@
 /***********************************/
 /* MC_CMD_LICENSING
  * Operations on the NVRAM_PARTITION_TYPE_LICENSE application license partition
+ * - not used for V3 licensing
  */
 #define MC_CMD_LICENSING 0xf3
 
@@ -9220,6 +10109,93 @@
 
 
 /***********************************/
+/* MC_CMD_LICENSING_V3
+ * Operations on the NVRAM_PARTITION_TYPE_LICENSE application license partition
+ * - V3 licensing (Medford)
+ */
+#define MC_CMD_LICENSING_V3 0xd0
+
+#define MC_CMD_0xd0_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_LICENSING_V3_IN msgrequest */
+#define    MC_CMD_LICENSING_V3_IN_LEN 4
+/* identifies the type of operation requested */
+#define       MC_CMD_LICENSING_V3_IN_OP_OFST 0
+/* enum: re-read and apply licenses after a license key partition update; note
+ * that this operation returns a zero-length response
+ */
+#define          MC_CMD_LICENSING_V3_IN_OP_UPDATE_LICENSE  0x0
+/* enum: report counts of installed licenses */
+#define          MC_CMD_LICENSING_V3_IN_OP_REPORT_LICENSE  0x1
+
+/* MC_CMD_LICENSING_V3_OUT msgresponse */
+#define    MC_CMD_LICENSING_V3_OUT_LEN 88
+/* count of keys which are valid */
+#define       MC_CMD_LICENSING_V3_OUT_VALID_KEYS_OFST 0
+/* sum of UNVERIFIABLE_KEYS + WRONG_NODE_KEYS (for compatibility with
+ * MC_CMD_FC_OP_LICENSE)
+ */
+#define       MC_CMD_LICENSING_V3_OUT_INVALID_KEYS_OFST 4
+/* count of keys which are invalid due to being unverifiable */
+#define       MC_CMD_LICENSING_V3_OUT_UNVERIFIABLE_KEYS_OFST 8
+/* count of keys which are invalid due to being for the wrong node */
+#define       MC_CMD_LICENSING_V3_OUT_WRONG_NODE_KEYS_OFST 12
+/* licensing state (for diagnostics; the exact meaning of the bits in this
+ * field are private to the firmware)
+ */
+#define       MC_CMD_LICENSING_V3_OUT_LICENSING_STATE_OFST 16
+/* licensing subsystem self-test report (for manftest) */
+#define       MC_CMD_LICENSING_V3_OUT_LICENSING_SELF_TEST_OFST 20
+/* enum: licensing subsystem self-test failed */
+#define          MC_CMD_LICENSING_V3_OUT_SELF_TEST_FAIL  0x0
+/* enum: licensing subsystem self-test passed */
+#define          MC_CMD_LICENSING_V3_OUT_SELF_TEST_PASS  0x1
+/* bitmask of licensed applications */
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_APPS_OFST 24
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_APPS_LEN 8
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_APPS_LO_OFST 24
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_APPS_HI_OFST 28
+/* reserved for future use */
+#define       MC_CMD_LICENSING_V3_OUT_RESERVED_0_OFST 32
+#define       MC_CMD_LICENSING_V3_OUT_RESERVED_0_LEN 24
+/* bitmask of licensed features */
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_FEATURES_OFST 56
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_FEATURES_LEN 8
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_FEATURES_LO_OFST 56
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_FEATURES_HI_OFST 60
+/* reserved for future use */
+#define       MC_CMD_LICENSING_V3_OUT_RESERVED_1_OFST 64
+#define       MC_CMD_LICENSING_V3_OUT_RESERVED_1_LEN 24
+
+
+/***********************************/
+/* MC_CMD_LICENSING_GET_ID_V3
+ * Get ID and type from the NVRAM_PARTITION_TYPE_LICENSE application license
+ * partition - V3 licensing (Medford)
+ */
+#define MC_CMD_LICENSING_GET_ID_V3 0xd1
+
+#define MC_CMD_0xd1_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_LICENSING_GET_ID_V3_IN msgrequest */
+#define    MC_CMD_LICENSING_GET_ID_V3_IN_LEN 0
+
+/* MC_CMD_LICENSING_GET_ID_V3_OUT msgresponse */
+#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LENMIN 8
+#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LENMAX 252
+#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LEN(num) (8+1*(num))
+/* type of license (eg 3) */
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_TYPE_OFST 0
+/* length of the license ID (in bytes) */
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_LENGTH_OFST 4
+/* the unique license ID of the adapter */
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_OFST 8
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_LEN 1
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_MINNUM 0
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_MAXNUM 244
+
+
+/***********************************/
 /* MC_CMD_MC2MC_PROXY
  * Execute an arbitrary MCDI command on the slave MC of a dual-core device.
  * This will fail on a single-core system.
@@ -9239,7 +10215,7 @@
 /* MC_CMD_GET_LICENSED_APP_STATE
  * Query the state of an individual licensed application. (Note that the actual
  * state may be invalidated by the MC_CMD_LICENSING OP_UPDATE_LICENSE operation
- * or a reboot of the MC.)
+ * or a reboot of the MC.) Not used for V3 licensing
  */
 #define MC_CMD_GET_LICENSED_APP_STATE 0xf5
 
@@ -9261,8 +10237,68 @@
 
 
 /***********************************/
+/* MC_CMD_GET_LICENSED_V3_APP_STATE
+ * Query the state of an individual licensed application. (Note that the actual
+ * state may be invalidated by the MC_CMD_LICENSING_V3 OP_UPDATE_LICENSE
+ * operation or a reboot of the MC.) Used for V3 licensing (Medford)
+ */
+#define MC_CMD_GET_LICENSED_V3_APP_STATE 0xd2
+
+#define MC_CMD_0xd2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_GET_LICENSED_V3_APP_STATE_IN msgrequest */
+#define    MC_CMD_GET_LICENSED_V3_APP_STATE_IN_LEN 8
+/* application ID to query (LICENSED_V3_APPS_xxx) expressed as a single bit
+ * mask
+ */
+#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LEN 8
+#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LO_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_HI_OFST 4
+
+/* MC_CMD_GET_LICENSED_V3_APP_STATE_OUT msgresponse */
+#define    MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_LEN 4
+/* state of this application */
+#define       MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_STATE_OFST 0
+/* enum: no (or invalid) license is present for the application */
+#define          MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_NOT_LICENSED  0x0
+/* enum: a valid license is present for the application */
+#define          MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_LICENSED  0x1
+
+
+/***********************************/
+/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES
+ * Query the state of an one or more licensed features. (Note that the actual
+ * state may be invalidated by the MC_CMD_LICENSING_V3 OP_UPDATE_LICENSE
+ * operation or a reboot of the MC.) Used for V3 licensing (Medford)
+ */
+#define MC_CMD_GET_LICENSED_V3_FEATURE_STATES 0xd3
+
+#define MC_CMD_0xd3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN msgrequest */
+#define    MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_LEN 8
+/* features to query (LICENSED_V3_FEATURES_xxx) expressed as a mask with one or
+ * more bits set
+ */
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LEN 8
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LO_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_HI_OFST 4
+
+/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT msgresponse */
+#define    MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_LEN 8
+/* states of these features - bit set for licensed, clear for not licensed */
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LEN 8
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LO_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_HI_OFST 4
+
+
+/***********************************/
 /* MC_CMD_LICENSED_APP_OP
- * Perform an action for an individual licensed application.
+ * Perform an action for an individual licensed application - not used for V3
+ * licensing.
  */
 #define MC_CMD_LICENSED_APP_OP 0xf6
 
@@ -9328,6 +10364,67 @@
 
 
 /***********************************/
+/* MC_CMD_LICENSED_V3_VALIDATE_APP
+ * Perform validation for an individual licensed application - V3 licensing
+ * (Medford)
+ */
+#define MC_CMD_LICENSED_V3_VALIDATE_APP 0xd4
+
+#define MC_CMD_0xd4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_LICENSED_V3_VALIDATE_APP_IN msgrequest */
+#define    MC_CMD_LICENSED_V3_VALIDATE_APP_IN_LEN 72
+/* application ID expressed as a single bit mask */
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_OFST 0
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LEN 8
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_OFST 0
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_OFST 4
+/* challenge for validation */
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_OFST 8
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_LEN 64
+
+/* MC_CMD_LICENSED_V3_VALIDATE_APP_OUT msgresponse */
+#define    MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_LEN 72
+/* application expiry time */
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_TIME_OFST 0
+/* application expiry units */
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNITS_OFST 4
+/* enum: expiry units are accounting units */
+#define          MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNIT_ACC  0x0
+/* enum: expiry units are calendar days */
+#define          MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNIT_DAYS  0x1
+/* validation response to challenge */
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_OFST 8
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_LEN 64
+
+
+/***********************************/
+/* MC_CMD_LICENSED_V3_MASK_FEATURES
+ * Mask features - V3 licensing (Medford)
+ */
+#define MC_CMD_LICENSED_V3_MASK_FEATURES 0xd5
+
+#define MC_CMD_0xd5_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_LICENSED_V3_MASK_FEATURES_IN msgrequest */
+#define    MC_CMD_LICENSED_V3_MASK_FEATURES_IN_LEN 12
+/* mask to be applied to features to be changed */
+#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_OFST 0
+#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LEN 8
+#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LO_OFST 0
+#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_HI_OFST 4
+/* whether to turn on or turn off the masked features */
+#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_FLAG_OFST 8
+/* enum: turn the features off */
+#define          MC_CMD_LICENSED_V3_MASK_FEATURES_IN_OFF  0x0
+/* enum: turn the features back on */
+#define          MC_CMD_LICENSED_V3_MASK_FEATURES_IN_ON  0x1
+
+/* MC_CMD_LICENSED_V3_MASK_FEATURES_OUT msgresponse */
+#define    MC_CMD_LICENSED_V3_MASK_FEATURES_OUT_LEN 0
+
+
+/***********************************/
 /* MC_CMD_SET_PORT_SNIFF_CONFIG
  * Configure RX port sniffing for the physical port associated with the calling
  * function. Only a privileged function may change the port sniffing
@@ -9696,12 +10793,27 @@
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_ONLOAD            0x4 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_PTP               0x8 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_INSECURE_FILTERS  0x10 /* enum */
-#define          MC_CMD_PRIVILEGE_MASK_IN_GRP_MAC_SPOOFING      0x20 /* enum */
+/* enum: Deprecated. Equivalent to MAC_SPOOFING_TX combined with CHANGE_MAC. */
+#define          MC_CMD_PRIVILEGE_MASK_IN_GRP_MAC_SPOOFING      0x20
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_UNICAST           0x40 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_MULTICAST         0x80 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_BROADCAST         0x100 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_ALL_MULTICAST     0x200 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_PROMISCUOUS       0x400 /* enum */
+/* enum: Allows to set the TX packets' source MAC address to any arbitrary MAC
+ * adress.
+ */
+#define          MC_CMD_PRIVILEGE_MASK_IN_GRP_MAC_SPOOFING_TX   0x800
+/* enum: Privilege that allows a Function to change the MAC address configured
+ * in its associated vAdapter/vPort.
+ */
+#define          MC_CMD_PRIVILEGE_MASK_IN_GRP_CHANGE_MAC        0x1000
+/* enum: Privilege that allows a Function to install filters that specify VLANs
+ * that are not in the permit list for the associated vPort. This privilege is
+ * primarily to support ESX where vPorts are created that restrict traffic to
+ * only a set of permitted VLANs. See the vPort flag FLAG_VLAN_RESTRICT.
+ */
+#define          MC_CMD_PRIVILEGE_MASK_IN_GRP_UNRESTRICTED_VLAN  0x2000
 /* enum: Set this bit to indicate that a new privilege mask is to be set,
  * otherwise the command will only read the existing mask.
  */
@@ -9951,7 +11063,7 @@
 /* Sector type */
 #define       MC_CMD_XPM_WRITE_SECTOR_IN_TYPE_OFST 4
 /*            Enum values, see field(s): */
-/*               MC_CMD_XPM_READ_SECTOR_OUT/TYPE */
+/*               MC_CMD_XPM_READ_SECTOR/MC_CMD_XPM_READ_SECTOR_OUT/TYPE */
 /* Sector size */
 #define       MC_CMD_XPM_WRITE_SECTOR_IN_SIZE_OFST 8
 /* Sector data */
@@ -10067,4 +11179,123 @@
 #define    MC_CMD_XPM_WRITE_TEST_OUT_LEN 0
 
 
+/***********************************/
+/* MC_CMD_EXEC_SIGNED
+ * Check the CMAC of the contents of IMEM and DMEM against the value supplied
+ * and if correct begin execution from the start of IMEM. The caller supplies a
+ * key ID, the length of IMEM and DMEM to validate and the expected CMAC. CMAC
+ * computation runs from the start of IMEM, and from the start of DMEM + 16k,
+ * to match flash booting. The command will respond with EINVAL if the CMAC
+ * does match, otherwise it will respond with success before it jumps to IMEM.
+ */
+#define MC_CMD_EXEC_SIGNED 0x10c
+
+#define MC_CMD_0x10c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_EXEC_SIGNED_IN msgrequest */
+#define    MC_CMD_EXEC_SIGNED_IN_LEN 28
+/* the length of code to include in the CMAC */
+#define       MC_CMD_EXEC_SIGNED_IN_CODELEN_OFST 0
+/* the length of date to include in the CMAC */
+#define       MC_CMD_EXEC_SIGNED_IN_DATALEN_OFST 4
+/* the XPM sector containing the key to use */
+#define       MC_CMD_EXEC_SIGNED_IN_KEYSECTOR_OFST 8
+/* the expected CMAC value */
+#define       MC_CMD_EXEC_SIGNED_IN_CMAC_OFST 12
+#define       MC_CMD_EXEC_SIGNED_IN_CMAC_LEN 16
+
+/* MC_CMD_EXEC_SIGNED_OUT msgresponse */
+#define    MC_CMD_EXEC_SIGNED_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_PREPARE_SIGNED
+ * Prepare to upload a signed image. This will scrub the specified length of
+ * the data region, which must be at least as large as the DATALEN supplied to
+ * MC_CMD_EXEC_SIGNED.
+ */
+#define MC_CMD_PREPARE_SIGNED 0x10d
+
+#define MC_CMD_0x10d_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_PREPARE_SIGNED_IN msgrequest */
+#define    MC_CMD_PREPARE_SIGNED_IN_LEN 4
+/* the length of data area to clear */
+#define       MC_CMD_PREPARE_SIGNED_IN_DATALEN_OFST 0
+
+/* MC_CMD_PREPARE_SIGNED_OUT msgresponse */
+#define    MC_CMD_PREPARE_SIGNED_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS
+ * Configure UDP ports for tunnel encapsulation hardware acceleration. The
+ * parser-dispatcher will attempt to parse traffic on these ports as tunnel
+ * encapsulation PDUs and filter them using the tunnel encapsulation filter
+ * chain rather than the standard filter chain. Note that this command can
+ * cause all functions to see a reset. (Available on Medford only.)
+ */
+#define MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS 0x117
+
+#define MC_CMD_0x117_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN msgrequest */
+#define    MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_LENMIN 4
+#define    MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_LENMAX 68
+#define    MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_LEN(num) (4+4*(num))
+/* Flags */
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_FLAGS_OFST 0
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_FLAGS_LEN 2
+#define        MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_UNLOADING_LBN 0
+#define        MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_UNLOADING_WIDTH 1
+/* The number of entries in the ENTRIES array */
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_NUM_ENTRIES_OFST 2
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_NUM_ENTRIES_LEN 2
+/* Entries defining the UDP port to protocol mapping, each laid out as a
+ * TUNNEL_ENCAP_UDP_PORT_ENTRY
+ */
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_ENTRIES_OFST 4
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_ENTRIES_LEN 4
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_ENTRIES_MINNUM 0
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_ENTRIES_MAXNUM 16
+
+/* MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT msgresponse */
+#define    MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_LEN 2
+/* Flags */
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_FLAGS_OFST 0
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_FLAGS_LEN 2
+#define        MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_RESETTING_LBN 0
+#define        MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_RESETTING_WIDTH 1
+
+
+/***********************************/
+/* MC_CMD_RX_BALANCING
+ * Configure a port upconverter to distribute the packets on both RX engines.
+ * Packets are distributed based on a table with the destination vFIFO. The
+ * index of the table is a hash of source and destination of IPV4 and VLAN
+ * priority.
+ */
+#define MC_CMD_RX_BALANCING 0x118
+
+#define MC_CMD_0x118_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_RX_BALANCING_IN msgrequest */
+#define    MC_CMD_RX_BALANCING_IN_LEN 4
+/* The RX port whose upconverter table will be modified */
+#define       MC_CMD_RX_BALANCING_IN_PORT_OFST 0
+#define       MC_CMD_RX_BALANCING_IN_PORT_LEN 1
+/* The VLAN priority associated to the table index and vFIFO */
+#define       MC_CMD_RX_BALANCING_IN_PRIORITY_OFST 1
+#define       MC_CMD_RX_BALANCING_IN_PRIORITY_LEN 1
+/* The resulting bit of SRC^DST for indexing the table */
+#define       MC_CMD_RX_BALANCING_IN_SRC_DST_OFST 2
+#define       MC_CMD_RX_BALANCING_IN_SRC_DST_LEN 1
+/* The RX engine to which the vFIFO in the table entry will point to */
+#define       MC_CMD_RX_BALANCING_IN_ENG_OFST 3
+#define       MC_CMD_RX_BALANCING_IN_ENG_LEN 1
+
+/* MC_CMD_RX_BALANCING_OUT msgresponse */
+#define    MC_CMD_RX_BALANCING_OUT_LEN 0
+
+
 #endif /* MCDI_PCOL_H */
diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c
index 7f295c4d7b80..2a9228a6e4a0 100644
--- a/drivers/net/ethernet/sfc/mcdi_port.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -189,11 +189,12 @@ static u32 mcdi_to_ethtool_cap(u32 media, u32 cap)
 
 	case MC_CMD_MEDIA_XFP:
 	case MC_CMD_MEDIA_SFP_PLUS:
-		result |= SUPPORTED_FIBRE;
-		break;
-
 	case MC_CMD_MEDIA_QSFP_PLUS:
 		result |= SUPPORTED_FIBRE;
+		if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN))
+			result |= SUPPORTED_1000baseT_Full;
+		if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN))
+			result |= SUPPORTED_10000baseT_Full;
 		if (cap & (1 << MC_CMD_PHY_CAP_40000FDX_LBN))
 			result |= SUPPORTED_40000baseCR4_Full;
 		break;
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index d13ddf9703ff..9ff062a36ea8 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -868,6 +868,7 @@ struct vfdi_status;
  *	be held to modify it.
  * @port_initialized: Port initialized?
  * @net_dev: Operating system network device. Consider holding the rtnl lock
+ * @fixed_features: Features which cannot be turned off
  * @stats_buffer: DMA buffer for statistics
  * @phy_type: PHY type
  * @phy_op: PHY interface
@@ -916,7 +917,6 @@ struct vfdi_status;
  * @stats_lock: Statistics update lock. Must be held when calling
  *	efx_nic_type::{update,start,stop}_stats.
  * @n_rx_noskb_drops: Count of RX packets dropped due to failure to allocate an skb
- * @mc_promisc: Whether in multicast promiscuous mode when last changed
  *
  * This is stored in the private area of the &struct net_device.
  */
@@ -1008,6 +1008,8 @@ struct efx_nic {
 	bool port_initialized;
 	struct net_device *net_dev;
 
+	netdev_features_t fixed_features;
+
 	struct efx_buffer stats_buffer;
 	u64 rx_nodesc_drops_total;
 	u64 rx_nodesc_drops_while_down;
@@ -1065,7 +1067,6 @@ struct efx_nic {
 	int last_irq_cpu;
 	spinlock_t stats_lock;
 	atomic_t n_rx_noskb_drops;
-	bool mc_promisc;
 };
 
 static inline int efx_dev_registered(struct efx_nic *efx)
@@ -1333,6 +1334,8 @@ struct efx_nic_type {
 	int (*ptp_set_ts_config)(struct efx_nic *efx,
 				 struct hwtstamp_config *init);
 	int (*sriov_configure)(struct efx_nic *efx, int num_vfs);
+	int (*vlan_rx_add_vid)(struct efx_nic *efx, __be16 proto, u16 vid);
+	int (*vlan_rx_kill_vid)(struct efx_nic *efx, __be16 proto, u16 vid);
 	int (*sriov_init)(struct efx_nic *efx);
 	void (*sriov_fini)(struct efx_nic *efx);
 	bool (*sriov_wanted)(struct efx_nic *efx);
@@ -1521,4 +1524,16 @@ static inline void efx_xmit_hwtstamp_pending(struct sk_buff *skb)
 	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 }
 
+/* Get all supported features.
+ * If a feature is not fixed, it is present in hw_features.
+ * If a feature is fixed, it does not present in hw_features, but
+ * always in features.
+ */
+static inline netdev_features_t efx_supported_features(const struct efx_nic *efx)
+{
+	const struct net_device *net_dev = efx->net_dev;
+
+	return net_dev->features | net_dev->hw_features;
+}
+
 #endif /* EFX_NET_DRIVER_H */
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 0b536e27d3b2..96944c3c9d14 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -519,6 +519,9 @@ enum {
 #ifdef CONFIG_SFC_SRIOV
  * @vf: Pointer to VF data structure
 #endif
+ * @vport_mac: The MAC address on the vport, only for PFs; VFs will be zero
+ * @vlan_list: List of VLANs added over the interface. Serialised by vlan_lock.
+ * @vlan_lock: Lock to serialize access to vlan_list.
  */
 struct efx_ef10_nic_data {
 	struct efx_buffer mcdi_buf;
@@ -550,6 +553,8 @@ struct efx_ef10_nic_data {
 	struct ef10_vf *vf;
 #endif
 	u8 vport_mac[ETH_ALEN];
+	struct list_head vlan_list;
+	struct mutex vlan_lock;
 };
 
 int efx_init_sriov(void);
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 8af25563f627..ca3134540d2d 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -114,9 +114,7 @@ struct smsc911x_data {
 	/* spinlock to ensure register accesses are serialised */
 	spinlock_t dev_lock;
 
-	struct phy_device *phy_dev;
 	struct mii_bus *mii_bus;
-	int phy_irq[PHY_MAX_ADDR];
 	unsigned int using_extphy;
 	int last_duplex;
 	int last_carrier;
@@ -834,7 +832,7 @@ static int smsc911x_phy_reset(struct smsc911x_data *pdata)
 static int smsc911x_phy_loopbacktest(struct net_device *dev)
 {
 	struct smsc911x_data *pdata = netdev_priv(dev);
-	struct phy_device *phy_dev = pdata->phy_dev;
+	struct phy_device *phy_dev = dev->phydev;
 	int result = -EIO;
 	unsigned int i, val;
 	unsigned long flags;
@@ -904,7 +902,8 @@ static int smsc911x_phy_loopbacktest(struct net_device *dev)
 
 static void smsc911x_phy_update_flowcontrol(struct smsc911x_data *pdata)
 {
-	struct phy_device *phy_dev = pdata->phy_dev;
+	struct net_device *ndev = pdata->dev;
+	struct phy_device *phy_dev = ndev->phydev;
 	u32 afc = smsc911x_reg_read(pdata, AFC_CFG);
 	u32 flow;
 	unsigned long flags;
@@ -945,7 +944,7 @@ static void smsc911x_phy_update_flowcontrol(struct smsc911x_data *pdata)
 static void smsc911x_phy_adjust_link(struct net_device *dev)
 {
 	struct smsc911x_data *pdata = netdev_priv(dev);
-	struct phy_device *phy_dev = pdata->phy_dev;
+	struct phy_device *phy_dev = dev->phydev;
 	unsigned long flags;
 	int carrier;
 
@@ -1038,7 +1037,6 @@ static int smsc911x_mii_probe(struct net_device *dev)
 			      SUPPORTED_Asym_Pause);
 	phydev->advertising = phydev->supported;
 
-	pdata->phy_dev = phydev;
 	pdata->last_duplex = -1;
 	pdata->last_carrier = -1;
 
@@ -1073,7 +1071,6 @@ static int smsc911x_mii_init(struct platform_device *pdev,
 	pdata->mii_bus->priv = pdata;
 	pdata->mii_bus->read = smsc911x_mii_read;
 	pdata->mii_bus->write = smsc911x_mii_write;
-	memcpy(pdata->mii_bus->irq, pdata->phy_irq, sizeof(pdata->mii_bus));
 
 	pdata->mii_bus->parent = &pdev->dev;
 
@@ -1340,9 +1337,11 @@ static void smsc911x_rx_multicast_update_workaround(struct smsc911x_data *pdata)
 
 static int smsc911x_phy_general_power_up(struct smsc911x_data *pdata)
 {
+	struct net_device *ndev = pdata->dev;
+	struct phy_device *phy_dev = ndev->phydev;
 	int rc = 0;
 
-	if (!pdata->phy_dev)
+	if (!phy_dev)
 		return rc;
 
 	/* If the internal PHY is in General Power-Down mode, all, except the
@@ -1352,7 +1351,7 @@ static int smsc911x_phy_general_power_up(struct smsc911x_data *pdata)
 	 * In that case, clear the bit 0.11, so the PHY powers up and we can
 	 * access to the phy registers.
 	 */
-	rc = phy_read(pdata->phy_dev, MII_BMCR);
+	rc = phy_read(phy_dev, MII_BMCR);
 	if (rc < 0) {
 		SMSC_WARN(pdata, drv, "Failed reading PHY control reg");
 		return rc;
@@ -1362,7 +1361,7 @@ static int smsc911x_phy_general_power_up(struct smsc911x_data *pdata)
 	 * disable the general power down-mode.
 	 */
 	if (rc & BMCR_PDOWN) {
-		rc = phy_write(pdata->phy_dev, MII_BMCR, rc & ~BMCR_PDOWN);
+		rc = phy_write(phy_dev, MII_BMCR, rc & ~BMCR_PDOWN);
 		if (rc < 0) {
 			SMSC_WARN(pdata, drv, "Failed writing PHY control reg");
 			return rc;
@@ -1376,12 +1375,14 @@ static int smsc911x_phy_general_power_up(struct smsc911x_data *pdata)
 
 static int smsc911x_phy_disable_energy_detect(struct smsc911x_data *pdata)
 {
+	struct net_device *ndev = pdata->dev;
+	struct phy_device *phy_dev = ndev->phydev;
 	int rc = 0;
 
-	if (!pdata->phy_dev)
+	if (!phy_dev)
 		return rc;
 
-	rc = phy_read(pdata->phy_dev, MII_LAN83C185_CTRL_STATUS);
+	rc = phy_read(phy_dev, MII_LAN83C185_CTRL_STATUS);
 
 	if (rc < 0) {
 		SMSC_WARN(pdata, drv, "Failed reading PHY control reg");
@@ -1391,7 +1392,7 @@ static int smsc911x_phy_disable_energy_detect(struct smsc911x_data *pdata)
 	/* Only disable if energy detect mode is already enabled */
 	if (rc & MII_LAN83C185_EDPWRDOWN) {
 		/* Disable energy detect mode for this SMSC Transceivers */
-		rc = phy_write(pdata->phy_dev, MII_LAN83C185_CTRL_STATUS,
+		rc = phy_write(phy_dev, MII_LAN83C185_CTRL_STATUS,
 			       rc & (~MII_LAN83C185_EDPWRDOWN));
 
 		if (rc < 0) {
@@ -1407,12 +1408,14 @@ static int smsc911x_phy_disable_energy_detect(struct smsc911x_data *pdata)
 
 static int smsc911x_phy_enable_energy_detect(struct smsc911x_data *pdata)
 {
+	struct net_device *ndev = pdata->dev;
+	struct phy_device *phy_dev = ndev->phydev;
 	int rc = 0;
 
-	if (!pdata->phy_dev)
+	if (!phy_dev)
 		return rc;
 
-	rc = phy_read(pdata->phy_dev, MII_LAN83C185_CTRL_STATUS);
+	rc = phy_read(phy_dev, MII_LAN83C185_CTRL_STATUS);
 
 	if (rc < 0) {
 		SMSC_WARN(pdata, drv, "Failed reading PHY control reg");
@@ -1422,7 +1425,7 @@ static int smsc911x_phy_enable_energy_detect(struct smsc911x_data *pdata)
 	/* Only enable if energy detect mode is already disabled */
 	if (!(rc & MII_LAN83C185_EDPWRDOWN)) {
 		/* Enable energy detect mode for this SMSC Transceivers */
-		rc = phy_write(pdata->phy_dev, MII_LAN83C185_CTRL_STATUS,
+		rc = phy_write(phy_dev, MII_LAN83C185_CTRL_STATUS,
 			       rc | MII_LAN83C185_EDPWRDOWN);
 
 		if (rc < 0) {
@@ -1519,7 +1522,7 @@ static int smsc911x_open(struct net_device *dev)
 	unsigned int intcfg;
 
 	/* if the phy is not yet registered, retry later*/
-	if (!pdata->phy_dev) {
+	if (!dev->phydev) {
 		SMSC_WARN(pdata, hw, "phy_dev is NULL");
 		return -EAGAIN;
 	}
@@ -1610,7 +1613,7 @@ static int smsc911x_open(struct net_device *dev)
 	pdata->last_carrier = -1;
 
 	/* Bring the PHY up */
-	phy_start(pdata->phy_dev);
+	phy_start(dev->phydev);
 
 	temp = smsc911x_reg_read(pdata, HW_CFG);
 	/* Preserve TX FIFO size and external PHY configuration */
@@ -1665,8 +1668,8 @@ static int smsc911x_stop(struct net_device *dev)
 	smsc911x_tx_update_txcounters(dev);
 
 	/* Bring the PHY down */
-	if (pdata->phy_dev)
-		phy_stop(pdata->phy_dev);
+	if (dev->phydev)
+		phy_stop(dev->phydev);
 
 	SMSC_TRACE(pdata, ifdown, "Interface stopped");
 	return 0;
@@ -1906,30 +1909,10 @@ static int smsc911x_set_mac_address(struct net_device *dev, void *p)
 /* Standard ioctls for mii-tool */
 static int smsc911x_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
-	struct smsc911x_data *pdata = netdev_priv(dev);
-
-	if (!netif_running(dev) || !pdata->phy_dev)
+	if (!netif_running(dev) || !dev->phydev)
 		return -EINVAL;
 
-	return phy_mii_ioctl(pdata->phy_dev, ifr, cmd);
-}
-
-static int
-smsc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct smsc911x_data *pdata = netdev_priv(dev);
-
-	cmd->maxtxpkt = 1;
-	cmd->maxrxpkt = 1;
-	return phy_ethtool_gset(pdata->phy_dev, cmd);
-}
-
-static int
-smsc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct smsc911x_data *pdata = netdev_priv(dev);
-
-	return phy_ethtool_sset(pdata->phy_dev, cmd);
+	return phy_mii_ioctl(dev->phydev, ifr, cmd);
 }
 
 static void smsc911x_ethtool_getdrvinfo(struct net_device *dev,
@@ -1943,9 +1926,7 @@ static void smsc911x_ethtool_getdrvinfo(struct net_device *dev,
 
 static int smsc911x_ethtool_nwayreset(struct net_device *dev)
 {
-	struct smsc911x_data *pdata = netdev_priv(dev);
-
-	return phy_start_aneg(pdata->phy_dev);
+	return phy_start_aneg(dev->phydev);
 }
 
 static u32 smsc911x_ethtool_getmsglevel(struct net_device *dev)
@@ -1971,7 +1952,7 @@ smsc911x_ethtool_getregs(struct net_device *dev, struct ethtool_regs *regs,
 			 void *buf)
 {
 	struct smsc911x_data *pdata = netdev_priv(dev);
-	struct phy_device *phy_dev = pdata->phy_dev;
+	struct phy_device *phy_dev = dev->phydev;
 	unsigned long flags;
 	unsigned int i;
 	unsigned int j = 0;
@@ -2117,8 +2098,6 @@ static int smsc911x_ethtool_set_eeprom(struct net_device *dev,
 }
 
 static const struct ethtool_ops smsc911x_ethtool_ops = {
-	.get_settings = smsc911x_ethtool_getsettings,
-	.set_settings = smsc911x_ethtool_setsettings,
 	.get_link = ethtool_op_get_link,
 	.get_drvinfo = smsc911x_ethtool_getdrvinfo,
 	.nway_reset = smsc911x_ethtool_nwayreset,
@@ -2130,6 +2109,8 @@ static const struct ethtool_ops smsc911x_ethtool_ops = {
 	.get_eeprom = smsc911x_ethtool_get_eeprom,
 	.set_eeprom = smsc911x_ethtool_set_eeprom,
 	.get_ts_info = ethtool_op_get_ts_info,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 static const struct net_device_ops smsc911x_netdev_ops = {
@@ -2310,12 +2291,11 @@ static int smsc911x_drv_remove(struct platform_device *pdev)
 	pdata = netdev_priv(dev);
 	BUG_ON(!pdata);
 	BUG_ON(!pdata->ioaddr);
-	BUG_ON(!pdata->phy_dev);
+	BUG_ON(!dev->phydev);
 
 	SMSC_TRACE(pdata, ifdown, "Stopping driver");
 
-	phy_disconnect(pdata->phy_dev);
-	pdata->phy_dev = NULL;
+	phy_disconnect(dev->phydev);
 	mdiobus_unregister(pdata->mii_bus);
 	mdiobus_free(pdata->mii_bus);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index fc60368df2e7..2533b91f1421 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -232,6 +232,11 @@ struct stmmac_extra_stats {
 #define DMA_HW_FEAT_ACTPHYIF	0x70000000	/* Active/selected PHY iface */
 #define DEFAULT_DMA_PBL		8
 
+/* PCS status and mask defines */
+#define	PCS_ANE_IRQ		BIT(2)	/* PCS Auto-Negotiation */
+#define	PCS_LINK_IRQ		BIT(1)	/* PCS Link */
+#define	PCS_RGSMIIIS_IRQ	BIT(0)	/* RGMII or SMII Interrupt */
+
 /* Max/Min RI Watchdog Timer count value */
 #define MAX_DMA_RIWT		0xff
 #define MIN_DMA_RIWT		0x20
@@ -272,9 +277,6 @@ enum dma_irq_status {
 #define	CORE_IRQ_RX_PATH_IN_LPI_MODE	(1 << 2)
 #define	CORE_IRQ_RX_PATH_EXIT_LPI_MODE	(1 << 3)
 
-#define	CORE_PCS_ANE_COMPLETE		(1 << 5)
-#define	CORE_PCS_LINK_STATUS		(1 << 6)
-#define	CORE_RGMII_IRQ			(1 << 7)
 #define CORE_IRQ_MTL_RX_OVERFLOW	BIT(8)
 
 /* Physical Coding Sublayer */
@@ -469,9 +471,12 @@ struct stmmac_ops {
 	void (*reset_eee_mode)(struct mac_device_info *hw);
 	void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw);
 	void (*set_eee_pls)(struct mac_device_info *hw, int link);
-	void (*ctrl_ane)(struct mac_device_info *hw, bool restart);
-	void (*get_adv)(struct mac_device_info *hw, struct rgmii_adv *adv);
 	void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x);
+	/* PCS calls */
+	void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral,
+			     bool loopback);
+	void (*pcs_rane)(void __iomem *ioaddr, bool restart);
+	void (*pcs_get_adv_lp)(void __iomem *ioaddr, struct rgmii_adv *adv);
 };
 
 /* PTP and HW Timer helpers */
@@ -524,6 +529,9 @@ struct mac_device_info {
 	int unicast_filter_entries;
 	int mcast_bits_log2;
 	unsigned int rx_csum;
+	unsigned int pcs;
+	unsigned int pmt;
+	unsigned int ps;
 };
 
 struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins,
@@ -546,6 +554,7 @@ void stmmac_dwmac4_get_mac_addr(void __iomem *ioaddr, unsigned char *addr,
 void stmmac_dwmac4_set_mac(void __iomem *ioaddr, bool enable);
 
 void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr);
+
 extern const struct stmmac_mode_ops ring_mode_ops;
 extern const struct stmmac_mode_ops chain_mode_ops;
 extern const struct stmmac_desc_ops dwmac4_desc_ops;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 0cd3ecff768b..92105916ef40 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -46,6 +46,7 @@ struct rk_priv_data {
 	struct platform_device *pdev;
 	int phy_iface;
 	struct regulator *regulator;
+	bool suspended;
 	const struct rk_gmac_ops *ops;
 
 	bool clk_enabled;
@@ -72,6 +73,122 @@ struct rk_priv_data {
 #define GRF_BIT(nr)	(BIT(nr) | BIT(nr+16))
 #define GRF_CLR_BIT(nr)	(BIT(nr+16))
 
+#define RK3228_GRF_MAC_CON0	0x0900
+#define RK3228_GRF_MAC_CON1	0x0904
+
+/* RK3228_GRF_MAC_CON0 */
+#define RK3228_GMAC_CLK_RX_DL_CFG(val)	HIWORD_UPDATE(val, 0x7F, 7)
+#define RK3228_GMAC_CLK_TX_DL_CFG(val)	HIWORD_UPDATE(val, 0x7F, 0)
+
+/* RK3228_GRF_MAC_CON1 */
+#define RK3228_GMAC_PHY_INTF_SEL_RGMII	\
+		(GRF_BIT(4) | GRF_CLR_BIT(5) | GRF_CLR_BIT(6))
+#define RK3228_GMAC_PHY_INTF_SEL_RMII	\
+		(GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | GRF_BIT(6))
+#define RK3228_GMAC_FLOW_CTRL		GRF_BIT(3)
+#define RK3228_GMAC_FLOW_CTRL_CLR	GRF_CLR_BIT(3)
+#define RK3228_GMAC_SPEED_10M		GRF_CLR_BIT(2)
+#define RK3228_GMAC_SPEED_100M		GRF_BIT(2)
+#define RK3228_GMAC_RMII_CLK_25M	GRF_BIT(7)
+#define RK3228_GMAC_RMII_CLK_2_5M	GRF_CLR_BIT(7)
+#define RK3228_GMAC_CLK_125M		(GRF_CLR_BIT(8) | GRF_CLR_BIT(9))
+#define RK3228_GMAC_CLK_25M		(GRF_BIT(8) | GRF_BIT(9))
+#define RK3228_GMAC_CLK_2_5M		(GRF_CLR_BIT(8) | GRF_BIT(9))
+#define RK3228_GMAC_RMII_MODE		GRF_BIT(10)
+#define RK3228_GMAC_RMII_MODE_CLR	GRF_CLR_BIT(10)
+#define RK3228_GMAC_TXCLK_DLY_ENABLE	GRF_BIT(0)
+#define RK3228_GMAC_TXCLK_DLY_DISABLE	GRF_CLR_BIT(0)
+#define RK3228_GMAC_RXCLK_DLY_ENABLE	GRF_BIT(1)
+#define RK3228_GMAC_RXCLK_DLY_DISABLE	GRF_CLR_BIT(1)
+
+static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv,
+				int tx_delay, int rx_delay)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
+		     RK3228_GMAC_PHY_INTF_SEL_RGMII |
+		     RK3228_GMAC_RMII_MODE_CLR |
+		     RK3228_GMAC_RXCLK_DLY_ENABLE |
+		     RK3228_GMAC_TXCLK_DLY_ENABLE);
+
+	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON0,
+		     RK3228_GMAC_CLK_RX_DL_CFG(rx_delay) |
+		     RK3228_GMAC_CLK_TX_DL_CFG(tx_delay));
+}
+
+static void rk3228_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
+		     RK3228_GMAC_PHY_INTF_SEL_RMII |
+		     RK3228_GMAC_RMII_MODE);
+
+	/* set MAC to RMII mode */
+	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1, GRF_BIT(11));
+}
+
+static void rk3228_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	if (speed == 10)
+		regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
+			     RK3228_GMAC_CLK_2_5M);
+	else if (speed == 100)
+		regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
+			     RK3228_GMAC_CLK_25M);
+	else if (speed == 1000)
+		regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
+			     RK3228_GMAC_CLK_125M);
+	else
+		dev_err(dev, "unknown speed value for RGMII! speed=%d", speed);
+}
+
+static void rk3228_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	if (speed == 10)
+		regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
+			     RK3228_GMAC_RMII_CLK_2_5M |
+			     RK3228_GMAC_SPEED_10M);
+	else if (speed == 100)
+		regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
+			     RK3228_GMAC_RMII_CLK_25M |
+			     RK3228_GMAC_SPEED_100M);
+	else
+		dev_err(dev, "unknown speed value for RMII! speed=%d", speed);
+}
+
+static const struct rk_gmac_ops rk3228_ops = {
+	.set_to_rgmii = rk3228_set_to_rgmii,
+	.set_to_rmii = rk3228_set_to_rmii,
+	.set_rgmii_speed = rk3228_set_rgmii_speed,
+	.set_rmii_speed = rk3228_set_rmii_speed,
+};
+
 #define RK3288_GRF_SOC_CON1	0x0248
 #define RK3288_GRF_SOC_CON3	0x0250
 
@@ -529,9 +646,8 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
 	return bsp_priv;
 }
 
-static int rk_gmac_init(struct platform_device *pdev, void *priv)
+static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
 {
-	struct rk_priv_data *bsp_priv = priv;
 	int ret;
 
 	ret = phy_power_on(bsp_priv, true);
@@ -545,14 +661,50 @@ static int rk_gmac_init(struct platform_device *pdev, void *priv)
 	return 0;
 }
 
-static void rk_gmac_exit(struct platform_device *pdev, void *priv)
+static void rk_gmac_powerdown(struct rk_priv_data *gmac)
 {
-	struct rk_priv_data *gmac = priv;
-
 	phy_power_on(gmac, false);
 	gmac_clk_enable(gmac, false);
 }
 
+static int rk_gmac_init(struct platform_device *pdev, void *priv)
+{
+	struct rk_priv_data *bsp_priv = priv;
+
+	return rk_gmac_powerup(bsp_priv);
+}
+
+static void rk_gmac_exit(struct platform_device *pdev, void *priv)
+{
+	struct rk_priv_data *bsp_priv = priv;
+
+	rk_gmac_powerdown(bsp_priv);
+}
+
+static void rk_gmac_suspend(struct platform_device *pdev, void *priv)
+{
+	struct rk_priv_data *bsp_priv = priv;
+
+	/* Keep the PHY up if we use Wake-on-Lan. */
+	if (device_may_wakeup(&pdev->dev))
+		return;
+
+	rk_gmac_powerdown(bsp_priv);
+	bsp_priv->suspended = true;
+}
+
+static void rk_gmac_resume(struct platform_device *pdev, void *priv)
+{
+	struct rk_priv_data *bsp_priv = priv;
+
+	/* The PHY was up for Wake-on-Lan. */
+	if (!bsp_priv->suspended)
+		return;
+
+	rk_gmac_powerup(bsp_priv);
+	bsp_priv->suspended = false;
+}
+
 static void rk_fix_speed(void *priv, unsigned int speed)
 {
 	struct rk_priv_data *bsp_priv = priv;
@@ -591,6 +743,8 @@ static int rk_gmac_probe(struct platform_device *pdev)
 	plat_dat->init = rk_gmac_init;
 	plat_dat->exit = rk_gmac_exit;
 	plat_dat->fix_mac_speed = rk_fix_speed;
+	plat_dat->suspend = rk_gmac_suspend;
+	plat_dat->resume = rk_gmac_resume;
 
 	plat_dat->bsp_priv = rk_gmac_setup(pdev, data);
 	if (IS_ERR(plat_dat->bsp_priv))
@@ -604,6 +758,7 @@ static int rk_gmac_probe(struct platform_device *pdev)
 }
 
 static const struct of_device_id rk_gmac_dwmac_match[] = {
+	{ .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops },
 	{ .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops },
 	{ .compatible = "rockchip,rk3368-gmac", .data = &rk3368_ops },
 	{ }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index b0593a4268ee..ff3e5ab39bd0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -38,19 +38,26 @@
 #define GMAC_WAKEUP_FILTER	0x00000028	/* Wake-up Frame Filter */
 
 #define GMAC_INT_STATUS		0x00000038	/* interrupt status register */
-enum dwmac1000_irq_status {
-	lpiis_irq = 0x400,
-	time_stamp_irq = 0x0200,
-	mmc_rx_csum_offload_irq = 0x0080,
-	mmc_tx_irq = 0x0040,
-	mmc_rx_irq = 0x0020,
-	mmc_irq = 0x0010,
-	pmt_irq = 0x0008,
-	pcs_ane_irq = 0x0004,
-	pcs_link_irq = 0x0002,
-	rgmii_irq = 0x0001,
-};
-#define GMAC_INT_MASK		0x0000003c	/* interrupt mask register */
+#define GMAC_INT_STATUS_PMT	BIT(3)
+#define GMAC_INT_STATUS_MMCIS	BIT(4)
+#define GMAC_INT_STATUS_MMCRIS	BIT(5)
+#define GMAC_INT_STATUS_MMCTIS	BIT(6)
+#define GMAC_INT_STATUS_MMCCSUM	BIT(7)
+#define GMAC_INT_STATUS_TSTAMP	BIT(9)
+#define GMAC_INT_STATUS_LPIIS	BIT(10)
+
+/* interrupt mask register */
+#define	GMAC_INT_MASK		0x0000003c
+#define	GMAC_INT_DISABLE_RGMII		BIT(0)
+#define	GMAC_INT_DISABLE_PCSLINK	BIT(1)
+#define	GMAC_INT_DISABLE_PCSAN		BIT(2)
+#define	GMAC_INT_DISABLE_PMT		BIT(3)
+#define	GMAC_INT_DISABLE_TIMESTAMP	BIT(9)
+#define	GMAC_INT_DISABLE_PCS	(GMAC_INT_DISABLE_RGMII | \
+				 GMAC_INT_DISABLE_PCSLINK | \
+				 GMAC_INT_DISABLE_PCSAN)
+#define	GMAC_INT_DEFAULT_MASK	(GMAC_INT_DISABLE_TIMESTAMP | \
+				 GMAC_INT_DISABLE_PCS)
 
 /* PMT Control and Status */
 #define GMAC_PMT		0x0000002c
@@ -90,42 +97,23 @@ enum power_event {
 				(reg * 8))
 #define GMAC_MAX_PERFECT_ADDRESSES	1
 
-/* PCS registers (AN/TBI/SGMII/RGMII) offset */
-#define GMAC_AN_CTRL	0x000000c0	/* AN control */
-#define GMAC_AN_STATUS	0x000000c4	/* AN status */
-#define GMAC_ANE_ADV	0x000000c8	/* Auto-Neg. Advertisement */
-#define GMAC_ANE_LPA	0x000000cc	/* Auto-Neg. link partener ability */
-#define GMAC_ANE_EXP	0x000000d0	/* ANE expansion */
-#define GMAC_TBI	0x000000d4	/* TBI extend status */
-#define GMAC_S_R_GMII	0x000000d8	/* SGMII RGMII status */
-
-/* AN Configuration defines */
-#define GMAC_AN_CTRL_RAN	0x00000200	/* Restart Auto-Negotiation */
-#define GMAC_AN_CTRL_ANE	0x00001000	/* Auto-Negotiation Enable */
-#define GMAC_AN_CTRL_ELE	0x00004000	/* External Loopback Enable */
-#define GMAC_AN_CTRL_ECD	0x00010000	/* Enable Comma Detect */
-#define GMAC_AN_CTRL_LR		0x00020000	/* Lock to Reference */
-#define GMAC_AN_CTRL_SGMRAL	0x00040000	/* SGMII RAL Control */
-
-/* AN Status defines */
-#define GMAC_AN_STATUS_LS	0x00000004	/* Link Status 0:down 1:up */
-#define GMAC_AN_STATUS_ANA	0x00000008	/* Auto-Negotiation Ability */
-#define GMAC_AN_STATUS_ANC	0x00000020	/* Auto-Negotiation Complete */
-#define GMAC_AN_STATUS_ES	0x00000100	/* Extended Status */
-
-/* Register 54 (SGMII/RGMII status register) */
-#define GMAC_S_R_GMII_LINK		0x8
-#define GMAC_S_R_GMII_SPEED		0x5
-#define GMAC_S_R_GMII_SPEED_SHIFT	0x1
-#define GMAC_S_R_GMII_MODE		0x1
-#define GMAC_S_R_GMII_SPEED_125		2
-#define GMAC_S_R_GMII_SPEED_25		1
-
-/* Common ADV and LPA defines */
-#define GMAC_ANE_FD		(1 << 5)
-#define GMAC_ANE_HD		(1 << 6)
-#define GMAC_ANE_PSE		(3 << 7)
-#define GMAC_ANE_PSE_SHIFT	7
+#define GMAC_PCS_BASE		0x000000c0	/* PCS register base */
+#define GMAC_RGSMIIIS		0x000000d8	/* RGMII/SMII status */
+
+/* SGMII/RGMII status register */
+#define GMAC_RGSMIIIS_LNKMODE		BIT(0)
+#define GMAC_RGSMIIIS_SPEED		GENMASK(2, 1)
+#define GMAC_RGSMIIIS_SPEED_SHIFT	1
+#define GMAC_RGSMIIIS_LNKSTS		BIT(3)
+#define GMAC_RGSMIIIS_JABTO		BIT(4)
+#define GMAC_RGSMIIIS_FALSECARDET	BIT(5)
+#define GMAC_RGSMIIIS_SMIDRXS		BIT(16)
+/* LNKMOD */
+#define GMAC_RGSMIIIS_LNKMOD_MASK	0x1
+/* LNKSPEED */
+#define GMAC_RGSMIIIS_SPEED_125		0x2
+#define GMAC_RGSMIIIS_SPEED_25		0x1
+#define GMAC_RGSMIIIS_SPEED_2_5		0x0
 
 /* GMAC Configuration defines */
 #define GMAC_CONTROL_2K 0x08000000	/* IEEE 802.3as 2K packets */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index fb1eb578e34e..cbefe9e2207c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -30,22 +30,48 @@
 #include <linux/slab.h>
 #include <linux/ethtool.h>
 #include <asm/io.h>
+#include "stmmac_pcs.h"
 #include "dwmac1000.h"
 
 static void dwmac1000_core_init(struct mac_device_info *hw, int mtu)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_CONTROL);
+
+	/* Configure GMAC core */
 	value |= GMAC_CORE_INIT;
+
 	if (mtu > 1500)
 		value |= GMAC_CONTROL_2K;
 	if (mtu > 2000)
 		value |= GMAC_CONTROL_JE;
 
+	if (hw->ps) {
+		value |= GMAC_CONTROL_TE;
+
+		if (hw->ps == SPEED_1000) {
+			value &= ~GMAC_CONTROL_PS;
+		} else {
+			value |= GMAC_CONTROL_PS;
+
+			if (hw->ps == SPEED_10)
+				value &= ~GMAC_CONTROL_FES;
+			else
+				value |= GMAC_CONTROL_FES;
+		}
+	}
+
 	writel(value, ioaddr + GMAC_CONTROL);
 
 	/* Mask GMAC interrupts */
-	writel(0x207, ioaddr + GMAC_INT_MASK);
+	value = GMAC_INT_DEFAULT_MASK;
+
+	if (hw->pmt)
+		value &= ~GMAC_INT_DISABLE_PMT;
+	if (hw->pcs)
+		value &= ~GMAC_INT_DISABLE_PCS;
+
+	writel(value, ioaddr + GMAC_INT_MASK);
 
 #ifdef STMMAC_VLAN_TAG_USED
 	/* Tag detection without filtering */
@@ -241,6 +267,39 @@ static void dwmac1000_pmt(struct mac_device_info *hw, unsigned long mode)
 	writel(pmt, ioaddr + GMAC_PMT);
 }
 
+/* RGMII or SMII interface */
+static void dwmac1000_rgsmii(void __iomem *ioaddr, struct stmmac_extra_stats *x)
+{
+	u32 status;
+
+	status = readl(ioaddr + GMAC_RGSMIIIS);
+	x->irq_rgmii_n++;
+
+	/* Check the link status */
+	if (status & GMAC_RGSMIIIS_LNKSTS) {
+		int speed_value;
+
+		x->pcs_link = 1;
+
+		speed_value = ((status & GMAC_RGSMIIIS_SPEED) >>
+			       GMAC_RGSMIIIS_SPEED_SHIFT);
+		if (speed_value == GMAC_RGSMIIIS_SPEED_125)
+			x->pcs_speed = SPEED_1000;
+		else if (speed_value == GMAC_RGSMIIIS_SPEED_25)
+			x->pcs_speed = SPEED_100;
+		else
+			x->pcs_speed = SPEED_10;
+
+		x->pcs_duplex = (status & GMAC_RGSMIIIS_LNKMOD_MASK);
+
+		pr_info("Link is Up - %d/%s\n", (int)x->pcs_speed,
+			x->pcs_duplex ? "Full" : "Half");
+	} else {
+		x->pcs_link = 0;
+		pr_info("Link is Down\n");
+	}
+}
+
 static int dwmac1000_irq_status(struct mac_device_info *hw,
 				struct stmmac_extra_stats *x)
 {
@@ -249,19 +308,20 @@ static int dwmac1000_irq_status(struct mac_device_info *hw,
 	int ret = 0;
 
 	/* Not used events (e.g. MMC interrupts) are not handled. */
-	if ((intr_status & mmc_tx_irq))
+	if ((intr_status & GMAC_INT_STATUS_MMCTIS))
 		x->mmc_tx_irq_n++;
-	if (unlikely(intr_status & mmc_rx_irq))
+	if (unlikely(intr_status & GMAC_INT_STATUS_MMCRIS))
 		x->mmc_rx_irq_n++;
-	if (unlikely(intr_status & mmc_rx_csum_offload_irq))
+	if (unlikely(intr_status & GMAC_INT_STATUS_MMCCSUM))
 		x->mmc_rx_csum_offload_irq_n++;
-	if (unlikely(intr_status & pmt_irq)) {
+	if (unlikely(intr_status & GMAC_INT_DISABLE_PMT)) {
 		/* clear the PMT bits 5 and 6 by reading the PMT status reg */
 		readl(ioaddr + GMAC_PMT);
 		x->irq_receive_pmt_irq_n++;
 	}
-	/* MAC trx/rx EEE LPI entry/exit interrupts */
-	if (intr_status & lpiis_irq) {
+
+	/* MAC tx/rx EEE LPI entry/exit interrupts */
+	if (intr_status & GMAC_INT_STATUS_LPIIS) {
 		/* Clean LPI interrupt by reading the Reg 12 */
 		ret = readl(ioaddr + LPI_CTRL_STATUS);
 
@@ -275,36 +335,10 @@ static int dwmac1000_irq_status(struct mac_device_info *hw,
 			x->irq_rx_path_exit_lpi_mode_n++;
 	}
 
-	if ((intr_status & pcs_ane_irq) || (intr_status & pcs_link_irq)) {
-		readl(ioaddr + GMAC_AN_STATUS);
-		x->irq_pcs_ane_n++;
-	}
-	if (intr_status & rgmii_irq) {
-		u32 status = readl(ioaddr + GMAC_S_R_GMII);
-		x->irq_rgmii_n++;
-
-		/* Save and dump the link status. */
-		if (status & GMAC_S_R_GMII_LINK) {
-			int speed_value = (status & GMAC_S_R_GMII_SPEED) >>
-			    GMAC_S_R_GMII_SPEED_SHIFT;
-			x->pcs_duplex = (status & GMAC_S_R_GMII_MODE);
-
-			if (speed_value == GMAC_S_R_GMII_SPEED_125)
-				x->pcs_speed = SPEED_1000;
-			else if (speed_value == GMAC_S_R_GMII_SPEED_25)
-				x->pcs_speed = SPEED_100;
-			else
-				x->pcs_speed = SPEED_10;
+	dwmac_pcs_isr(ioaddr, GMAC_PCS_BASE, intr_status, x);
 
-			x->pcs_link = 1;
-			pr_debug("%s: Link is Up - %d/%s\n", __func__,
-				 (int)x->pcs_speed,
-				 x->pcs_duplex ? "Full" : "Half");
-		} else {
-			x->pcs_link = 0;
-			pr_debug("%s: Link is Down\n", __func__);
-		}
-	}
+	if (intr_status & PCS_RGSMIIIS_IRQ)
+		dwmac1000_rgsmii(ioaddr, x);
 
 	return ret;
 }
@@ -363,38 +397,20 @@ static void dwmac1000_set_eee_timer(struct mac_device_info *hw, int ls, int tw)
 	writel(value, ioaddr + LPI_TIMER_CTRL);
 }
 
-static void dwmac1000_ctrl_ane(struct mac_device_info *hw, bool restart)
+static void dwmac1000_ctrl_ane(void __iomem *ioaddr, bool ane, bool srgmi_ral,
+			       bool loopback)
 {
-	void __iomem *ioaddr = hw->pcsr;
-	/* auto negotiation enable and External Loopback enable */
-	u32 value = GMAC_AN_CTRL_ANE | GMAC_AN_CTRL_ELE;
-
-	if (restart)
-		value |= GMAC_AN_CTRL_RAN;
-
-	writel(value, ioaddr + GMAC_AN_CTRL);
+	dwmac_ctrl_ane(ioaddr, GMAC_PCS_BASE, ane, srgmi_ral, loopback);
 }
 
-static void dwmac1000_get_adv(struct mac_device_info *hw, struct rgmii_adv *adv)
+static void dwmac1000_rane(void __iomem *ioaddr, bool restart)
 {
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value = readl(ioaddr + GMAC_ANE_ADV);
-
-	if (value & GMAC_ANE_FD)
-		adv->duplex = DUPLEX_FULL;
-	if (value & GMAC_ANE_HD)
-		adv->duplex |= DUPLEX_HALF;
-
-	adv->pause = (value & GMAC_ANE_PSE) >> GMAC_ANE_PSE_SHIFT;
-
-	value = readl(ioaddr + GMAC_ANE_LPA);
-
-	if (value & GMAC_ANE_FD)
-		adv->lp_duplex = DUPLEX_FULL;
-	if (value & GMAC_ANE_HD)
-		adv->lp_duplex = DUPLEX_HALF;
+	dwmac_rane(ioaddr, GMAC_PCS_BASE, restart);
+}
 
-	adv->lp_pause = (value & GMAC_ANE_PSE) >> GMAC_ANE_PSE_SHIFT;
+static void dwmac1000_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv)
+{
+	dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv);
 }
 
 static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
@@ -485,9 +501,10 @@ static const struct stmmac_ops dwmac1000_ops = {
 	.reset_eee_mode = dwmac1000_reset_eee_mode,
 	.set_eee_timer = dwmac1000_set_eee_timer,
 	.set_eee_pls = dwmac1000_set_eee_pls,
-	.ctrl_ane = dwmac1000_ctrl_ane,
-	.get_adv = dwmac1000_get_adv,
 	.debug = dwmac1000_debug,
+	.pcs_ctrl_ane = dwmac1000_ctrl_ane,
+	.pcs_rane = dwmac1000_rane,
+	.pcs_get_adv_lp = dwmac1000_get_adv_lp,
 };
 
 struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index bc50952a18e7..6f4f5ce25114 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -24,10 +24,8 @@
 #define GMAC_QX_TX_FLOW_CTRL(x)		(0x70 + x * 4)
 #define GMAC_INT_STATUS			0x000000b0
 #define GMAC_INT_EN			0x000000b4
-#define GMAC_AN_CTRL			0x000000e0
-#define GMAC_AN_STATUS			0x000000e4
-#define GMAC_AN_ADV			0x000000e8
-#define GMAC_AN_LPA			0x000000ec
+#define GMAC_PCS_BASE			0x000000e0
+#define GMAC_PHYIF_CONTROL_STATUS	0x000000f8
 #define GMAC_PMT			0x000000c0
 #define GMAC_VERSION			0x00000110
 #define GMAC_DEBUG			0x00000114
@@ -54,9 +52,18 @@
 #define GMAC_TX_FLOW_CTRL_PT_SHIFT	16
 
 /*  MAC Interrupt bitmap*/
+#define GMAC_INT_RGSMIIS		BIT(0)
+#define GMAC_INT_PCS_LINK		BIT(1)
+#define GMAC_INT_PCS_ANE		BIT(2)
+#define GMAC_INT_PCS_PHYIS		BIT(3)
 #define GMAC_INT_PMT_EN			BIT(4)
 #define GMAC_INT_LPI_EN			BIT(5)
 
+#define	GMAC_PCS_IRQ_DEFAULT	(GMAC_INT_RGSMIIS | GMAC_INT_PCS_LINK |	\
+				 GMAC_INT_PCS_ANE)
+
+#define	GMAC_INT_DEFAULT_MASK	GMAC_INT_PMT_EN
+
 enum dwmac4_irq_status {
 	time_stamp_irq = 0x00001000,
 	mmc_rx_csum_offload_irq = 0x00000800,
@@ -64,19 +71,8 @@ enum dwmac4_irq_status {
 	mmc_rx_irq = 0x00000200,
 	mmc_irq = 0x00000100,
 	pmt_irq = 0x00000010,
-	pcs_ane_irq = 0x00000004,
-	pcs_link_irq = 0x00000002,
 };
 
-/* MAC Auto-Neg bitmap*/
-#define	GMAC_AN_CTRL_RAN		BIT(9)
-#define	GMAC_AN_CTRL_ANE		BIT(12)
-#define GMAC_AN_CTRL_ELE		BIT(14)
-#define GMAC_AN_FD			BIT(5)
-#define GMAC_AN_HD			BIT(6)
-#define GMAC_AN_PSE_MASK		GENMASK(8, 7)
-#define GMAC_AN_PSE_SHIFT		7
-
 /* MAC PMT bitmap */
 enum power_event {
 	pointer_reset =	0x80000000,
@@ -250,6 +246,23 @@ enum power_event {
 #define MTL_DEBUG_RRCSTS_FLUSH		3
 #define MTL_DEBUG_RWCSTS		BIT(0)
 
+/* SGMII/RGMII status register */
+#define GMAC_PHYIF_CTRLSTATUS_TC		BIT(0)
+#define GMAC_PHYIF_CTRLSTATUS_LUD		BIT(1)
+#define GMAC_PHYIF_CTRLSTATUS_SMIDRXS		BIT(4)
+#define GMAC_PHYIF_CTRLSTATUS_LNKMOD		BIT(16)
+#define GMAC_PHYIF_CTRLSTATUS_SPEED		GENMASK(18, 17)
+#define GMAC_PHYIF_CTRLSTATUS_SPEED_SHIFT	17
+#define GMAC_PHYIF_CTRLSTATUS_LNKSTS		BIT(19)
+#define GMAC_PHYIF_CTRLSTATUS_JABTO		BIT(20)
+#define GMAC_PHYIF_CTRLSTATUS_FALSECARDET	BIT(21)
+/* LNKMOD */
+#define GMAC_PHYIF_CTRLSTATUS_LNKMOD_MASK	0x1
+/* LNKSPEED */
+#define GMAC_PHYIF_CTRLSTATUS_SPEED_125		0x2
+#define GMAC_PHYIF_CTRLSTATUS_SPEED_25		0x1
+#define GMAC_PHYIF_CTRLSTATUS_SPEED_2_5		0x0
+
 extern const struct stmmac_dma_ops dwmac4_dma_ops;
 extern const struct stmmac_dma_ops dwmac410_dma_ops;
 #endif /* __DWMAC4_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 4f7283d05588..df5580dcdfed 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/ethtool.h>
 #include <linux/io.h>
+#include "stmmac_pcs.h"
 #include "dwmac4.h"
 
 static void dwmac4_core_init(struct mac_device_info *hw, int mtu)
@@ -31,10 +32,31 @@ static void dwmac4_core_init(struct mac_device_info *hw, int mtu)
 	if (mtu > 2000)
 		value |= GMAC_CONFIG_JE;
 
+	if (hw->ps) {
+		value |= GMAC_CONFIG_TE;
+
+		if (hw->ps == SPEED_1000) {
+			value &= ~GMAC_CONFIG_PS;
+		} else {
+			value |= GMAC_CONFIG_PS;
+
+			if (hw->ps == SPEED_10)
+				value &= ~GMAC_CONFIG_FES;
+			else
+				value |= GMAC_CONFIG_FES;
+		}
+	}
+
 	writel(value, ioaddr + GMAC_CONFIG);
 
 	/* Mask GMAC interrupts */
-	writel(GMAC_INT_PMT_EN, ioaddr + GMAC_INT_EN);
+	value = GMAC_INT_DEFAULT_MASK;
+	if (hw->pmt)
+		value |= GMAC_INT_PMT_EN;
+	if (hw->pcs)
+		value |= GMAC_PCS_IRQ_DEFAULT;
+
+	writel(value, ioaddr + GMAC_INT_EN);
 }
 
 static void dwmac4_dump_regs(struct mac_device_info *hw)
@@ -156,7 +178,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 		struct netdev_hw_addr *ha;
 
 		netdev_for_each_uc_addr(ha, dev) {
-			dwmac4_set_umac_addr(ioaddr, ha->addr, reg);
+			dwmac4_set_umac_addr(hw, ha->addr, reg);
 			reg++;
 		}
 	}
@@ -190,39 +212,53 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
 	}
 }
 
-static void dwmac4_ctrl_ane(struct mac_device_info *hw, bool restart)
+static void dwmac4_ctrl_ane(void __iomem *ioaddr, bool ane, bool srgmi_ral,
+			    bool loopback)
 {
-	void __iomem *ioaddr = hw->pcsr;
-
-	/* auto negotiation enable and External Loopback enable */
-	u32 value = GMAC_AN_CTRL_ANE | GMAC_AN_CTRL_ELE;
+	dwmac_ctrl_ane(ioaddr, GMAC_PCS_BASE, ane, srgmi_ral, loopback);
+}
 
-	if (restart)
-		value |= GMAC_AN_CTRL_RAN;
+static void dwmac4_rane(void __iomem *ioaddr, bool restart)
+{
+	dwmac_rane(ioaddr, GMAC_PCS_BASE, restart);
+}
 
-	writel(value, ioaddr + GMAC_AN_CTRL);
+static void dwmac4_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv)
+{
+	dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv);
 }
 
-static void dwmac4_get_adv(struct mac_device_info *hw, struct rgmii_adv *adv)
+/* RGMII or SMII interface */
+static void dwmac4_phystatus(void __iomem *ioaddr, struct stmmac_extra_stats *x)
 {
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value = readl(ioaddr + GMAC_AN_ADV);
+	u32 status;
 
-	if (value & GMAC_AN_FD)
-		adv->duplex = DUPLEX_FULL;
-	if (value & GMAC_AN_HD)
-		adv->duplex |= DUPLEX_HALF;
+	status = readl(ioaddr + GMAC_PHYIF_CONTROL_STATUS);
+	x->irq_rgmii_n++;
 
-	adv->pause = (value & GMAC_AN_PSE_MASK) >> GMAC_AN_PSE_SHIFT;
+	/* Check the link status */
+	if (status & GMAC_PHYIF_CTRLSTATUS_LNKSTS) {
+		int speed_value;
 
-	value = readl(ioaddr + GMAC_AN_LPA);
+		x->pcs_link = 1;
+
+		speed_value = ((status & GMAC_PHYIF_CTRLSTATUS_SPEED) >>
+			       GMAC_PHYIF_CTRLSTATUS_SPEED_SHIFT);
+		if (speed_value == GMAC_PHYIF_CTRLSTATUS_SPEED_125)
+			x->pcs_speed = SPEED_1000;
+		else if (speed_value == GMAC_PHYIF_CTRLSTATUS_SPEED_25)
+			x->pcs_speed = SPEED_100;
+		else
+			x->pcs_speed = SPEED_10;
 
-	if (value & GMAC_AN_FD)
-		adv->lp_duplex = DUPLEX_FULL;
-	if (value & GMAC_AN_HD)
-		adv->lp_duplex = DUPLEX_HALF;
+		x->pcs_duplex = (status & GMAC_PHYIF_CTRLSTATUS_LNKMOD_MASK);
 
-	adv->lp_pause = (value & GMAC_AN_PSE_MASK) >> GMAC_AN_PSE_SHIFT;
+		pr_info("Link is Up - %d/%s\n", (int)x->pcs_speed,
+			x->pcs_duplex ? "Full" : "Half");
+	} else {
+		x->pcs_link = 0;
+		pr_info("Link is Down\n");
+	}
 }
 
 static int dwmac4_irq_status(struct mac_device_info *hw,
@@ -248,11 +284,6 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
 		x->irq_receive_pmt_irq_n++;
 	}
 
-	if ((intr_status & pcs_ane_irq) || (intr_status & pcs_link_irq)) {
-		readl(ioaddr + GMAC_AN_STATUS);
-		x->irq_pcs_ane_n++;
-	}
-
 	mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS);
 	/* Check MTL Interrupt: Currently only one queue is used: Q0. */
 	if (mtl_int_qx_status & MTL_INT_Q0) {
@@ -267,6 +298,10 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
 		}
 	}
 
+	dwmac_pcs_isr(ioaddr, GMAC_PCS_BASE, intr_status, x);
+	if (intr_status & PCS_RGSMIIIS_IRQ)
+		dwmac4_phystatus(ioaddr, x);
+
 	return ret;
 }
 
@@ -363,8 +398,9 @@ static const struct stmmac_ops dwmac4_ops = {
 	.pmt = dwmac4_pmt,
 	.set_umac_addr = dwmac4_set_umac_addr,
 	.get_umac_addr = dwmac4_get_umac_addr,
-	.ctrl_ane = dwmac4_ctrl_ane,
-	.get_adv = dwmac4_get_adv,
+	.pcs_ctrl_ane = dwmac4_ctrl_ane,
+	.pcs_rane = dwmac4_rane,
+	.pcs_get_adv_lp = dwmac4_get_adv_lp,
 	.debug = dwmac4_debug,
 	.set_filter = dwmac4_set_filter,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 59ae6088cd22..8dc9056c1001 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -117,7 +117,6 @@ struct stmmac_priv {
 	int eee_enabled;
 	int eee_active;
 	int tx_lpi_timer;
-	int pcs;
 	unsigned int mode;
 	int extend_desc;
 	struct ptp_clock *ptp_clock;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index e2b98b01647e..1e06173fc9d7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -276,7 +276,8 @@ static int stmmac_ethtool_getsettings(struct net_device *dev,
 	struct phy_device *phy = priv->phydev;
 	int rc;
 
-	if ((priv->pcs & STMMAC_PCS_RGMII) || (priv->pcs & STMMAC_PCS_SGMII)) {
+	if (priv->hw->pcs & STMMAC_PCS_RGMII ||
+	    priv->hw->pcs & STMMAC_PCS_SGMII) {
 		struct rgmii_adv adv;
 
 		if (!priv->xstats.pcs_link) {
@@ -289,10 +290,10 @@ static int stmmac_ethtool_getsettings(struct net_device *dev,
 		ethtool_cmd_speed_set(cmd, priv->xstats.pcs_speed);
 
 		/* Get and convert ADV/LP_ADV from the HW AN registers */
-		if (!priv->hw->mac->get_adv)
+		if (!priv->hw->mac->pcs_get_adv_lp)
 			return -EOPNOTSUPP;	/* should never happen indeed */
 
-		priv->hw->mac->get_adv(priv->hw, &adv);
+		priv->hw->mac->pcs_get_adv_lp(priv->ioaddr, &adv);
 
 		/* Encoding of PSE bits is defined in 802.3z, 37.2.1.4 */
 
@@ -361,7 +362,8 @@ static int stmmac_ethtool_setsettings(struct net_device *dev,
 	struct phy_device *phy = priv->phydev;
 	int rc;
 
-	if ((priv->pcs & STMMAC_PCS_RGMII) || (priv->pcs & STMMAC_PCS_SGMII)) {
+	if (priv->hw->pcs & STMMAC_PCS_RGMII ||
+	    priv->hw->pcs & STMMAC_PCS_SGMII) {
 		u32 mask = ADVERTISED_Autoneg | ADVERTISED_Pause;
 
 		/* Only support ANE */
@@ -376,8 +378,11 @@ static int stmmac_ethtool_setsettings(struct net_device *dev,
 			ADVERTISED_10baseT_Full);
 
 		spin_lock(&priv->lock);
-		if (priv->hw->mac->ctrl_ane)
-			priv->hw->mac->ctrl_ane(priv->hw, 1);
+
+		if (priv->hw->mac->pcs_ctrl_ane)
+			priv->hw->mac->pcs_ctrl_ane(priv->ioaddr, 1,
+						    priv->hw->ps, 0);
+
 		spin_unlock(&priv->lock);
 
 		return 0;
@@ -452,11 +457,22 @@ stmmac_get_pauseparam(struct net_device *netdev,
 {
 	struct stmmac_priv *priv = netdev_priv(netdev);
 
-	if (priv->pcs)	/* FIXME */
-		return;
-
 	pause->rx_pause = 0;
 	pause->tx_pause = 0;
+
+	if (priv->hw->pcs && priv->hw->mac->pcs_get_adv_lp) {
+		struct rgmii_adv adv_lp;
+
+		pause->autoneg = 1;
+		priv->hw->mac->pcs_get_adv_lp(priv->ioaddr, &adv_lp);
+		if (!adv_lp.pause)
+			return;
+	} else {
+		if (!(priv->phydev->supported & SUPPORTED_Pause) ||
+		    !(priv->phydev->supported & SUPPORTED_Asym_Pause))
+			return;
+	}
+
 	pause->autoneg = priv->phydev->autoneg;
 
 	if (priv->flow_ctrl & FLOW_RX)
@@ -473,10 +489,19 @@ stmmac_set_pauseparam(struct net_device *netdev,
 	struct stmmac_priv *priv = netdev_priv(netdev);
 	struct phy_device *phy = priv->phydev;
 	int new_pause = FLOW_OFF;
-	int ret = 0;
 
-	if (priv->pcs)	/* FIXME */
-		return -EOPNOTSUPP;
+	if (priv->hw->pcs && priv->hw->mac->pcs_get_adv_lp) {
+		struct rgmii_adv adv_lp;
+
+		pause->autoneg = 1;
+		priv->hw->mac->pcs_get_adv_lp(priv->ioaddr, &adv_lp);
+		if (!adv_lp.pause)
+			return -EOPNOTSUPP;
+	} else {
+		if (!(phy->supported & SUPPORTED_Pause) ||
+		    !(phy->supported & SUPPORTED_Asym_Pause))
+			return -EOPNOTSUPP;
+	}
 
 	if (pause->rx_pause)
 		new_pause |= FLOW_RX;
@@ -488,11 +513,12 @@ stmmac_set_pauseparam(struct net_device *netdev,
 
 	if (phy->autoneg) {
 		if (netif_running(netdev))
-			ret = phy_start_aneg(phy);
-	} else
-		priv->hw->mac->flow_ctrl(priv->hw, phy->duplex,
-					 priv->flow_ctrl, priv->pause);
-	return ret;
+			return phy_start_aneg(phy);
+	}
+
+	priv->hw->mac->flow_ctrl(priv->hw, phy->duplex, priv->flow_ctrl,
+				 priv->pause);
+	return 0;
 }
 
 static void stmmac_get_ethtool_stats(struct net_device *dev,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index eac45d0c75e2..aab777c1ba33 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -285,8 +285,9 @@ bool stmmac_eee_init(struct stmmac_priv *priv)
 	/* Using PCS we cannot dial with the phy registers at this stage
 	 * so we do not support extra feature like EEE.
 	 */
-	if ((priv->pcs == STMMAC_PCS_RGMII) || (priv->pcs == STMMAC_PCS_TBI) ||
-	    (priv->pcs == STMMAC_PCS_RTBI))
+	if ((priv->hw->pcs == STMMAC_PCS_RGMII) ||
+	    (priv->hw->pcs == STMMAC_PCS_TBI) ||
+	    (priv->hw->pcs == STMMAC_PCS_RTBI))
 		goto out;
 
 	/* MAC core supports the EEE feature. */
@@ -799,10 +800,10 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv)
 		    (interface == PHY_INTERFACE_MODE_RGMII_RXID) ||
 		    (interface == PHY_INTERFACE_MODE_RGMII_TXID)) {
 			pr_debug("STMMAC: PCS RGMII support enable\n");
-			priv->pcs = STMMAC_PCS_RGMII;
+			priv->hw->pcs = STMMAC_PCS_RGMII;
 		} else if (interface == PHY_INTERFACE_MODE_SGMII) {
 			pr_debug("STMMAC: PCS SGMII support enable\n");
-			priv->pcs = STMMAC_PCS_SGMII;
+			priv->hw->pcs = STMMAC_PCS_SGMII;
 		}
 	}
 }
@@ -1665,6 +1666,19 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	if (priv->plat->bus_setup)
 		priv->plat->bus_setup(priv->ioaddr);
 
+	/* PS and related bits will be programmed according to the speed */
+	if (priv->hw->pcs) {
+		int speed = priv->plat->mac_port_sel_speed;
+
+		if ((speed == SPEED_10) || (speed == SPEED_100) ||
+		    (speed == SPEED_1000)) {
+			priv->hw->ps = speed;
+		} else {
+			dev_warn(priv->device, "invalid port speed\n");
+			priv->hw->ps = 0;
+		}
+	}
+
 	/* Initialize the MAC Core */
 	priv->hw->mac->core_init(priv->hw, dev->mtu);
 
@@ -1714,8 +1728,8 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 		priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT);
 	}
 
-	if (priv->pcs && priv->hw->mac->ctrl_ane)
-		priv->hw->mac->ctrl_ane(priv->hw, 0);
+	if (priv->hw->pcs && priv->hw->mac->pcs_ctrl_ane)
+		priv->hw->mac->pcs_ctrl_ane(priv->hw, 1, priv->hw->ps, 0);
 
 	/*  set TX ring length */
 	if (priv->hw->dma->set_tx_ring_len)
@@ -1748,8 +1762,9 @@ static int stmmac_open(struct net_device *dev)
 
 	stmmac_check_ether_addr(priv);
 
-	if (priv->pcs != STMMAC_PCS_RGMII && priv->pcs != STMMAC_PCS_TBI &&
-	    priv->pcs != STMMAC_PCS_RTBI) {
+	if (priv->hw->pcs != STMMAC_PCS_RGMII &&
+	    priv->hw->pcs != STMMAC_PCS_TBI &&
+	    priv->hw->pcs != STMMAC_PCS_RTBI) {
 		ret = stmmac_init_phy(dev);
 		if (ret) {
 			pr_err("%s: Cannot attach to PHY (error: %d)\n",
@@ -2809,6 +2824,14 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 							priv->rx_tail_addr,
 							STMMAC_CHAN0);
 		}
+
+		/* PCS link status */
+		if (priv->hw->pcs) {
+			if (priv->xstats.pcs_link)
+				netif_carrier_on(dev);
+			else
+				netif_carrier_off(dev);
+		}
 	}
 
 	/* To handle DMA interrupts */
@@ -3130,6 +3153,7 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 		 */
 		priv->plat->enh_desc = priv->dma_cap.enh_desc;
 		priv->plat->pmt = priv->dma_cap.pmt_remote_wake_up;
+		priv->hw->pmt = priv->plat->pmt;
 
 		/* TXCOE doesn't work in thresh DMA mode */
 		if (priv->plat->force_thresh_dma_mode)
@@ -3325,8 +3349,9 @@ int stmmac_dvr_probe(struct device *device,
 
 	stmmac_check_pcs_mode(priv);
 
-	if (priv->pcs != STMMAC_PCS_RGMII && priv->pcs != STMMAC_PCS_TBI &&
-	    priv->pcs != STMMAC_PCS_RTBI) {
+	if (priv->hw->pcs != STMMAC_PCS_RGMII  &&
+	    priv->hw->pcs != STMMAC_PCS_TBI &&
+	    priv->hw->pcs != STMMAC_PCS_RTBI) {
 		/* MDIO bus Registration */
 		ret = stmmac_mdio_register(ndev);
 		if (ret < 0) {
@@ -3376,8 +3401,9 @@ int stmmac_dvr_remove(struct device *dev)
 		reset_control_assert(priv->stmmac_rst);
 	clk_disable_unprepare(priv->pclk);
 	clk_disable_unprepare(priv->stmmac_clk);
-	if (priv->pcs != STMMAC_PCS_RGMII && priv->pcs != STMMAC_PCS_TBI &&
-	    priv->pcs != STMMAC_PCS_RTBI)
+	if (priv->hw->pcs != STMMAC_PCS_RGMII &&
+	    priv->hw->pcs != STMMAC_PCS_TBI &&
+	    priv->hw->pcs != STMMAC_PCS_RTBI)
 		stmmac_mdio_unregister(ndev);
 	free_netdev(ndev);
 
@@ -3450,8 +3476,6 @@ int stmmac_resume(struct device *dev)
 	if (!netif_running(ndev))
 		return 0;
 
-	spin_lock_irqsave(&priv->lock, flags);
-
 	/* Power Down bit, into the PM register, is cleared
 	 * automatically as soon as a magic packet or a Wake-up frame
 	 * is received. Anyway, it's better to manually clear
@@ -3459,7 +3483,9 @@ int stmmac_resume(struct device *dev)
 	 * from another devices (e.g. serial console).
 	 */
 	if (device_may_wakeup(priv->device)) {
+		spin_lock_irqsave(&priv->lock, flags);
 		priv->hw->mac->pmt(priv->hw, 0);
+		spin_unlock_irqrestore(&priv->lock, flags);
 		priv->irq_wake = 0;
 	} else {
 		pinctrl_pm_select_default_state(priv->device);
@@ -3473,6 +3499,8 @@ int stmmac_resume(struct device *dev)
 
 	netif_device_attach(ndev);
 
+	spin_lock_irqsave(&priv->lock, flags);
+
 	priv->cur_rx = 0;
 	priv->dirty_rx = 0;
 	priv->dirty_tx = 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h
new file mode 100644
index 000000000000..eba41c24b7a7
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h
@@ -0,0 +1,159 @@
+/*
+ * stmmac_pcs.h: Physical Coding Sublayer Header File
+ *
+ * Copyright (C) 2016 STMicroelectronics (R&D) Limited
+ * Author: Giuseppe Cavallaro <[email protected]>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __STMMAC_PCS_H__
+#define __STMMAC_PCS_H__
+
+#include <linux/slab.h>
+#include <linux/io.h>
+#include "common.h"
+
+/* PCS registers (AN/TBI/SGMII/RGMII) offsets */
+#define GMAC_AN_CTRL(x)		(x)		/* AN control */
+#define GMAC_AN_STATUS(x)	(x + 0x4)	/* AN status */
+#define GMAC_ANE_ADV(x)		(x + 0x8)	/* ANE Advertisement */
+#define GMAC_ANE_LPA(x)		(x + 0xc)	/* ANE link partener ability */
+#define GMAC_ANE_EXP(x)		(x + 0x10)	/* ANE expansion */
+#define GMAC_TBI(x)		(x + 0x14)	/* TBI extend status */
+
+/* AN Configuration defines */
+#define GMAC_AN_CTRL_RAN	BIT(9)	/* Restart Auto-Negotiation */
+#define GMAC_AN_CTRL_ANE	BIT(12)	/* Auto-Negotiation Enable */
+#define GMAC_AN_CTRL_ELE	BIT(14)	/* External Loopback Enable */
+#define GMAC_AN_CTRL_ECD	BIT(16)	/* Enable Comma Detect */
+#define GMAC_AN_CTRL_LR		BIT(17)	/* Lock to Reference */
+#define GMAC_AN_CTRL_SGMRAL	BIT(18)	/* SGMII RAL Control */
+
+/* AN Status defines */
+#define GMAC_AN_STATUS_LS	BIT(2)	/* Link Status 0:down 1:up */
+#define GMAC_AN_STATUS_ANA	BIT(3)	/* Auto-Negotiation Ability */
+#define GMAC_AN_STATUS_ANC	BIT(5)	/* Auto-Negotiation Complete */
+#define GMAC_AN_STATUS_ES	BIT(8)	/* Extended Status */
+
+/* ADV and LPA defines */
+#define GMAC_ANE_FD		BIT(5)
+#define GMAC_ANE_HD		BIT(6)
+#define GMAC_ANE_PSE		GENMASK(8, 7)
+#define GMAC_ANE_PSE_SHIFT	7
+#define GMAC_ANE_RFE		GENMASK(13, 12)
+#define GMAC_ANE_RFE_SHIFT	12
+#define GMAC_ANE_ACK		BIT(14)
+
+/**
+ * dwmac_pcs_isr - TBI, RTBI, or SGMII PHY ISR
+ * @ioaddr: IO registers pointer
+ * @reg: Base address of the AN Control Register.
+ * @intr_status: GMAC core interrupt status
+ * @x: pointer to log these events as stats
+ * Description: it is the ISR for PCS events: Auto-Negotiation Completed and
+ * Link status.
+ */
+static inline void dwmac_pcs_isr(void __iomem *ioaddr, u32 reg,
+				 unsigned int intr_status,
+				 struct stmmac_extra_stats *x)
+{
+	u32 val = readl(ioaddr + GMAC_AN_STATUS(reg));
+
+	if (intr_status & PCS_ANE_IRQ) {
+		x->irq_pcs_ane_n++;
+		if (val & GMAC_AN_STATUS_ANC)
+			pr_info("stmmac_pcs: ANE process completed\n");
+	}
+
+	if (intr_status & PCS_LINK_IRQ) {
+		x->irq_pcs_link_n++;
+		if (val & GMAC_AN_STATUS_LS)
+			pr_info("stmmac_pcs: Link Up\n");
+		else
+			pr_info("stmmac_pcs: Link Down\n");
+	}
+}
+
+/**
+ * dwmac_rane - To restart ANE
+ * @ioaddr: IO registers pointer
+ * @reg: Base address of the AN Control Register.
+ * @restart: to restart ANE
+ * Description: this is to just restart the Auto-Negotiation.
+ */
+static inline void dwmac_rane(void __iomem *ioaddr, u32 reg, bool restart)
+{
+	u32 value = readl(ioaddr + GMAC_AN_CTRL(reg));
+
+	if (restart)
+		value |= GMAC_AN_CTRL_RAN;
+
+	writel(value, ioaddr + GMAC_AN_CTRL(reg));
+}
+
+/**
+ * dwmac_ctrl_ane - To program the AN Control Register.
+ * @ioaddr: IO registers pointer
+ * @reg: Base address of the AN Control Register.
+ * @ane: to enable the auto-negotiation
+ * @srgmi_ral: to manage MAC-2-MAC SGMII connections.
+ * @loopback: to cause the PHY to loopback tx data into rx path.
+ * Description: this is the main function to configure the AN control register
+ * and init the ANE, select loopback (usually for debugging purpose) and
+ * configure SGMII RAL.
+ */
+static inline void dwmac_ctrl_ane(void __iomem *ioaddr, u32 reg, bool ane,
+				  bool srgmi_ral, bool loopback)
+{
+	u32 value = readl(ioaddr + GMAC_AN_CTRL(reg));
+
+	/* Enable and restart the Auto-Negotiation */
+	if (ane)
+		value |= GMAC_AN_CTRL_ANE | GMAC_AN_CTRL_RAN;
+
+	/* In case of MAC-2-MAC connection, block is configured to operate
+	 * according to MAC conf register.
+	 */
+	if (srgmi_ral)
+		value |= GMAC_AN_CTRL_SGMRAL;
+
+	if (loopback)
+		value |= GMAC_AN_CTRL_ELE;
+
+	writel(value, ioaddr + GMAC_AN_CTRL(reg));
+}
+
+/**
+ * dwmac_get_adv_lp - Get ADV and LP cap
+ * @ioaddr: IO registers pointer
+ * @reg: Base address of the AN Control Register.
+ * @adv_lp: structure to store the adv,lp status
+ * Description: this is to expose the ANE advertisement and Link partner ability
+ * status to ethtool support.
+ */
+static inline void dwmac_get_adv_lp(void __iomem *ioaddr, u32 reg,
+				    struct rgmii_adv *adv_lp)
+{
+	u32 value = readl(ioaddr + GMAC_ANE_ADV(reg));
+
+	if (value & GMAC_ANE_FD)
+		adv_lp->duplex = DUPLEX_FULL;
+	if (value & GMAC_ANE_HD)
+		adv_lp->duplex |= DUPLEX_HALF;
+
+	adv_lp->pause = (value & GMAC_ANE_PSE) >> GMAC_ANE_PSE_SHIFT;
+
+	value = readl(ioaddr + GMAC_ANE_LPA(reg));
+
+	if (value & GMAC_ANE_FD)
+		adv_lp->lp_duplex = DUPLEX_FULL;
+	if (value & GMAC_ANE_HD)
+		adv_lp->lp_duplex = DUPLEX_HALF;
+
+	adv_lp->lp_pause = (value & GMAC_ANE_PSE) >> GMAC_ANE_PSE_SHIFT;
+}
+#endif /* __STMMAC_PCS_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 409db913b117..f7dfc0ae8e9c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -319,6 +319,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 		pr_warn("force_sf_dma_mode is ignored if force_thresh_dma_mode is set.");
 	}
 
+	of_property_read_u32(np, "snps,ps-speed", &plat->mac_port_sel_speed);
+
 	plat->axi = stmmac_axi_setup(pdev);
 
 	return plat;
@@ -411,7 +413,9 @@ static int stmmac_pltfr_suspend(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 
 	ret = stmmac_suspend(dev);
-	if (priv->plat->exit)
+	if (priv->plat->suspend)
+		priv->plat->suspend(pdev, priv->plat->bsp_priv);
+	else if (priv->plat->exit)
 		priv->plat->exit(pdev, priv->plat->bsp_priv);
 
 	return ret;
@@ -430,7 +434,9 @@ static int stmmac_pltfr_resume(struct device *dev)
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	struct platform_device *pdev = to_platform_device(dev);
 
-	if (priv->plat->init)
+	if (priv->plat->resume)
+		priv->plat->resume(pdev, priv->plat->bsp_priv);
+	else if (priv->plat->init)
 		priv->plat->init(pdev, priv->plat->bsp_priv);
 
 	return stmmac_resume(dev);
diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
index 158213cd6cdd..c34111b390c7 100644
--- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c
+++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
@@ -46,7 +46,6 @@
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/vmalloc.h>
-#include <linux/version.h>
 
 #include <linux/device.h>
 #include <linux/bitrev.h>
@@ -598,7 +597,6 @@ struct net_local {
 	struct work_struct txtimeout_reinit;
 
 	phy_interface_t phy_interface;
-	struct phy_device *phy_dev;
 	struct mii_bus *mii_bus;
 
 	unsigned int link;
@@ -816,7 +814,7 @@ static int dwceqos_mdio_write(struct mii_bus *bus, int mii_id, int phyreg,
 static int dwceqos_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
 {
 	struct net_local *lp = netdev_priv(ndev);
-	struct phy_device *phydev = lp->phy_dev;
+	struct phy_device *phydev = ndev->phydev;
 
 	if (!netif_running(ndev))
 		return -EINVAL;
@@ -850,6 +848,7 @@ static void dwceqos_link_down(struct net_local *lp)
 
 static void dwceqos_link_up(struct net_local *lp)
 {
+	struct net_device *ndev = lp->ndev;
 	u32 regval;
 	unsigned long flags;
 
@@ -860,7 +859,7 @@ static void dwceqos_link_up(struct net_local *lp)
 	dwceqos_write(lp, REG_DWCEQOS_MAC_LPI_CTRL_STATUS, regval);
 	spin_unlock_irqrestore(&lp->hw_lock, flags);
 
-	lp->eee_active = !phy_init_eee(lp->phy_dev, 0);
+	lp->eee_active = !phy_init_eee(ndev->phydev, 0);
 
 	/* Check for changed EEE capability */
 	if (!lp->eee_active && lp->eee_enabled) {
@@ -876,7 +875,8 @@ static void dwceqos_link_up(struct net_local *lp)
 
 static void dwceqos_set_speed(struct net_local *lp)
 {
-	struct phy_device *phydev = lp->phy_dev;
+	struct net_device *ndev = lp->ndev;
+	struct phy_device *phydev = ndev->phydev;
 	u32 regval;
 
 	regval = dwceqos_read(lp, REG_DWCEQOS_MAC_CFG);
@@ -903,7 +903,7 @@ static void dwceqos_set_speed(struct net_local *lp)
 static void dwceqos_adjust_link(struct net_device *ndev)
 {
 	struct net_local *lp = netdev_priv(ndev);
-	struct phy_device *phydev = lp->phy_dev;
+	struct phy_device *phydev = ndev->phydev;
 	int status_change = 0;
 
 	if (lp->phy_defer)
@@ -987,7 +987,6 @@ static int dwceqos_mii_probe(struct net_device *ndev)
 	lp->link    = 0;
 	lp->speed   = 0;
 	lp->duplex  = DUPLEX_UNKNOWN;
-	lp->phy_dev = phydev;
 
 	return 0;
 }
@@ -1531,6 +1530,7 @@ static void dwceqos_configure_bus(struct net_local *lp)
 
 static void dwceqos_init_hw(struct net_local *lp)
 {
+	struct net_device *ndev = lp->ndev;
 	u32 regval;
 	u32 buswidth;
 	u32 dma_skip;
@@ -1645,10 +1645,10 @@ static void dwceqos_init_hw(struct net_local *lp)
 		      regval | DWCEQOS_MAC_CFG_TE | DWCEQOS_MAC_CFG_RE);
 
 	lp->phy_defer = false;
-	mutex_lock(&lp->phy_dev->lock);
-	phy_read_status(lp->phy_dev);
+	mutex_lock(&ndev->phydev->lock);
+	phy_read_status(ndev->phydev);
 	dwceqos_adjust_link(lp->ndev);
-	mutex_unlock(&lp->phy_dev->lock);
+	mutex_unlock(&ndev->phydev->lock);
 }
 
 static void dwceqos_tx_reclaim(unsigned long data)
@@ -1898,7 +1898,7 @@ static int dwceqos_open(struct net_device *ndev)
 	 * hence the unusual init order with phy_start first.
 	 */
 	lp->phy_defer = true;
-	phy_start(lp->phy_dev);
+	phy_start(ndev->phydev);
 	dwceqos_init_hw(lp);
 	napi_enable(&lp->napi);
 
@@ -1943,7 +1943,7 @@ static int dwceqos_stop(struct net_device *ndev)
 
 	dwceqos_drain_dma(lp);
 	dwceqos_reset_hw(lp);
-	phy_stop(lp->phy_dev);
+	phy_stop(ndev->phydev);
 
 	dwceqos_descriptor_free(lp);
 
@@ -2523,30 +2523,6 @@ dwceqos_get_stats64(struct net_device *ndev, struct rtnl_link_stats64 *s)
 	return s;
 }
 
-static int
-dwceqos_get_settings(struct net_device *ndev, struct ethtool_cmd *ecmd)
-{
-	struct net_local *lp = netdev_priv(ndev);
-	struct phy_device *phydev = lp->phy_dev;
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_ethtool_gset(phydev, ecmd);
-}
-
-static int
-dwceqos_set_settings(struct net_device *ndev, struct ethtool_cmd *ecmd)
-{
-	struct net_local *lp = netdev_priv(ndev);
-	struct phy_device *phydev = lp->phy_dev;
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_ethtool_sset(phydev, ecmd);
-}
-
 static void
 dwceqos_get_drvinfo(struct net_device *ndev, struct ethtool_drvinfo *ed)
 {
@@ -2574,17 +2550,17 @@ static int dwceqos_set_pauseparam(struct net_device *ndev,
 
 	lp->flowcontrol.autoneg = pp->autoneg;
 	if (pp->autoneg) {
-		lp->phy_dev->advertising |= ADVERTISED_Pause;
-		lp->phy_dev->advertising |= ADVERTISED_Asym_Pause;
+		ndev->phydev->advertising |= ADVERTISED_Pause;
+		ndev->phydev->advertising |= ADVERTISED_Asym_Pause;
 	} else {
-		lp->phy_dev->advertising &= ~ADVERTISED_Pause;
-		lp->phy_dev->advertising &= ~ADVERTISED_Asym_Pause;
+		ndev->phydev->advertising &= ~ADVERTISED_Pause;
+		ndev->phydev->advertising &= ~ADVERTISED_Asym_Pause;
 		lp->flowcontrol.rx = pp->rx_pause;
 		lp->flowcontrol.tx = pp->tx_pause;
 	}
 
 	if (netif_running(ndev))
-		ret = phy_start_aneg(lp->phy_dev);
+		ret = phy_start_aneg(ndev->phydev);
 
 	return ret;
 }
@@ -2705,7 +2681,7 @@ static int dwceqos_get_eee(struct net_device *ndev, struct ethtool_eee *edata)
 			    dwceqos_get_tx_lpi_state(regval));
 	}
 
-	return phy_ethtool_get_eee(lp->phy_dev, edata);
+	return phy_ethtool_get_eee(ndev->phydev, edata);
 }
 
 static int dwceqos_set_eee(struct net_device *ndev, struct ethtool_eee *edata)
@@ -2747,7 +2723,7 @@ static int dwceqos_set_eee(struct net_device *ndev, struct ethtool_eee *edata)
 		spin_unlock_irqrestore(&lp->hw_lock, flags);
 	}
 
-	return phy_ethtool_set_eee(lp->phy_dev, edata);
+	return phy_ethtool_set_eee(ndev->phydev, edata);
 }
 
 static u32 dwceqos_get_msglevel(struct net_device *ndev)
@@ -2765,8 +2741,6 @@ static void dwceqos_set_msglevel(struct net_device *ndev, u32 msglevel)
 }
 
 static struct ethtool_ops dwceqos_ethtool_ops = {
-	.get_settings   = dwceqos_get_settings,
-	.set_settings   = dwceqos_set_settings,
 	.get_drvinfo    = dwceqos_get_drvinfo,
 	.get_link       = ethtool_op_get_link,
 	.get_pauseparam = dwceqos_get_pauseparam,
@@ -2780,6 +2754,8 @@ static struct ethtool_ops dwceqos_ethtool_ops = {
 	.set_eee        = dwceqos_set_eee,
 	.get_msglevel   = dwceqos_get_msglevel,
 	.set_msglevel   = dwceqos_set_msglevel,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 static struct net_device_ops netdev_ops = {
@@ -2981,8 +2957,8 @@ static int dwceqos_remove(struct platform_device *pdev)
 	if (ndev) {
 		lp = netdev_priv(ndev);
 
-		if (lp->phy_dev)
-			phy_disconnect(lp->phy_dev);
+		if (ndev->phydev)
+			phy_disconnect(ndev->phydev);
 		mdiobus_unregister(lp->mii_bus);
 		mdiobus_free(lp->mii_bus);
 
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 635979bddd34..1a93a1f28433 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1243,6 +1243,7 @@ static void cpsw_slave_stop(struct cpsw_slave *slave, struct cpsw_priv *priv)
 	slave->phy = NULL;
 	cpsw_ale_control_set(priv->ale, slave_port,
 			     ALE_PORT_STATE, ALE_PORT_STATE_DISABLE);
+	soft_reset_slave(slave);
 }
 
 static int cpsw_ndo_open(struct net_device *ndev)
@@ -1251,7 +1252,11 @@ static int cpsw_ndo_open(struct net_device *ndev)
 	int i, ret;
 	u32 reg;
 
-	pm_runtime_get_sync(&priv->pdev->dev);
+	ret = pm_runtime_get_sync(&priv->pdev->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(&priv->pdev->dev);
+		return ret;
+	}
 
 	if (!cpsw_common_res_usage_state(priv))
 		cpsw_intr_disable(priv);
@@ -1277,6 +1282,7 @@ static int cpsw_ndo_open(struct net_device *ndev)
 
 	if (!cpsw_common_res_usage_state(priv)) {
 		struct cpsw_priv *priv_sl0 = cpsw_get_slave_priv(priv, 0);
+		int buf_num;
 
 		/* setup tx dma to fixed prio and zero offset */
 		cpdma_control_set(priv->dma, CPDMA_TX_PRIO_FIXED, 1);
@@ -1304,10 +1310,8 @@ static int cpsw_ndo_open(struct net_device *ndev)
 			enable_irq(priv->irqs_table[0]);
 		}
 
-		if (WARN_ON(!priv->data.rx_descs))
-			priv->data.rx_descs = 128;
-
-		for (i = 0; i < priv->data.rx_descs; i++) {
+		buf_num = cpdma_chan_get_rx_buf_num(priv->dma);
+		for (i = 0; i < buf_num; i++) {
 			struct sk_buff *skb;
 
 			ret = -ENOMEM;
@@ -1338,7 +1342,7 @@ static int cpsw_ndo_open(struct net_device *ndev)
 	if (priv->coal_intvl != 0) {
 		struct ethtool_coalesce coal;
 
-		coal.rx_coalesce_usecs = (priv->coal_intvl << 4);
+		coal.rx_coalesce_usecs = priv->coal_intvl;
 		cpsw_set_coalesce(ndev, &coal);
 	}
 
@@ -1610,10 +1614,17 @@ static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p)
 	struct sockaddr *addr = (struct sockaddr *)p;
 	int flags = 0;
 	u16 vid = 0;
+	int ret;
 
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
+	ret = pm_runtime_get_sync(&priv->pdev->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(&priv->pdev->dev);
+		return ret;
+	}
+
 	if (priv->data.dual_emac) {
 		vid = priv->slaves[priv->emac_port].port_vlan;
 		flags = ALE_VLAN;
@@ -1628,6 +1639,8 @@ static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p)
 	memcpy(ndev->dev_addr, priv->mac_addr, ETH_ALEN);
 	for_each_slave(priv, cpsw_set_slave_mac, priv);
 
+	pm_runtime_put(&priv->pdev->dev);
+
 	return 0;
 }
 
@@ -1692,10 +1705,17 @@ static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
 				    __be16 proto, u16 vid)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
+	int ret;
 
 	if (vid == priv->data.default_vlan)
 		return 0;
 
+	ret = pm_runtime_get_sync(&priv->pdev->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(&priv->pdev->dev);
+		return ret;
+	}
+
 	if (priv->data.dual_emac) {
 		/* In dual EMAC, reserved VLAN id should not be used for
 		 * creating VLAN interfaces as this can break the dual
@@ -1710,7 +1730,10 @@ static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
 	}
 
 	dev_info(priv->dev, "Adding vlanid %d to vlan filter\n", vid);
-	return cpsw_add_vlan_ale_entry(priv, vid);
+	ret = cpsw_add_vlan_ale_entry(priv, vid);
+
+	pm_runtime_put(&priv->pdev->dev);
+	return ret;
 }
 
 static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev,
@@ -1722,6 +1745,12 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev,
 	if (vid == priv->data.default_vlan)
 		return 0;
 
+	ret = pm_runtime_get_sync(&priv->pdev->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(&priv->pdev->dev);
+		return ret;
+	}
+
 	if (priv->data.dual_emac) {
 		int i;
 
@@ -1741,8 +1770,10 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev,
 	if (ret != 0)
 		return ret;
 
-	return cpsw_ale_del_mcast(priv->ale, priv->ndev->broadcast,
-				  0, ALE_VLAN, vid);
+	ret = cpsw_ale_del_mcast(priv->ale, priv->ndev->broadcast,
+				 0, ALE_VLAN, vid);
+	pm_runtime_put(&priv->pdev->dev);
+	return ret;
 }
 
 static const struct net_device_ops cpsw_netdev_ops = {
@@ -1901,10 +1932,33 @@ static int cpsw_set_pauseparam(struct net_device *ndev,
 	priv->tx_pause = pause->tx_pause ? true : false;
 
 	for_each_slave(priv, _cpsw_adjust_link, priv, &link);
-
 	return 0;
 }
 
+static int cpsw_ethtool_op_begin(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	ret = pm_runtime_get_sync(&priv->pdev->dev);
+	if (ret < 0) {
+		cpsw_err(priv, drv, "ethtool begin failed %d\n", ret);
+		pm_runtime_put_noidle(&priv->pdev->dev);
+	}
+
+	return ret;
+}
+
+static void cpsw_ethtool_op_complete(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	ret = pm_runtime_put(&priv->pdev->dev);
+	if (ret < 0)
+		cpsw_err(priv, drv, "ethtool complete failed %d\n", ret);
+}
+
 static const struct ethtool_ops cpsw_ethtool_ops = {
 	.get_drvinfo	= cpsw_get_drvinfo,
 	.get_msglevel	= cpsw_get_msglevel,
@@ -1924,6 +1978,8 @@ static const struct ethtool_ops cpsw_ethtool_ops = {
 	.set_wol	= cpsw_set_wol,
 	.get_regs_len	= cpsw_get_regs_len,
 	.get_regs	= cpsw_get_regs,
+	.begin		= cpsw_ethtool_op_begin,
+	.complete	= cpsw_ethtool_op_complete,
 };
 
 static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv,
@@ -1998,12 +2054,6 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 	}
 	data->bd_ram_size = prop;
 
-	if (of_property_read_u32(node, "rx_descs", &prop)) {
-		dev_err(&pdev->dev, "Missing rx_descs property in the DT.\n");
-		return -EINVAL;
-	}
-	data->rx_descs = prop;
-
 	if (of_property_read_u32(node, "mac_control", &prop)) {
 		dev_err(&pdev->dev, "Missing mac_control property in the DT.\n");
 		return -EINVAL;
@@ -2021,7 +2071,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 	if (ret)
 		dev_warn(&pdev->dev, "Doesn't have any child node\n");
 
-	for_each_child_of_node(node, slave_node) {
+	for_each_available_child_of_node(node, slave_node) {
 		struct cpsw_slave_data *slave_data = data->slave_data + i;
 		const void *mac_addr = NULL;
 		int lenp;
@@ -2318,7 +2368,11 @@ static int cpsw_probe(struct platform_device *pdev)
 	/* Need to enable clocks with runtime PM api to access module
 	 * registers
 	 */
-	pm_runtime_get_sync(&pdev->dev);
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(&pdev->dev);
+		goto clean_runtime_disable_ret;
+	}
 	priv->version = readl(&priv->regs->id_ver);
 	pm_runtime_put_sync(&pdev->dev);
 
@@ -2502,8 +2556,6 @@ static int cpsw_probe(struct platform_device *pdev)
 clean_ale_ret:
 	cpsw_ale_destroy(priv->ale);
 clean_dma_ret:
-	cpdma_chan_destroy(priv->txch);
-	cpdma_chan_destroy(priv->rxch);
 	cpdma_ctlr_destroy(priv->dma);
 clean_runtime_disable_ret:
 	pm_runtime_disable(&pdev->dev);
@@ -2531,8 +2583,6 @@ static int cpsw_remove(struct platform_device *pdev)
 	unregister_netdev(ndev);
 
 	cpsw_ale_destroy(priv->ale);
-	cpdma_chan_destroy(priv->txch);
-	cpdma_chan_destroy(priv->rxch);
 	cpdma_ctlr_destroy(priv->dma);
 	pm_runtime_disable(&pdev->dev);
 	device_for_each_child(&pdev->dev, NULL, cpsw_remove_child_device);
@@ -2555,16 +2605,12 @@ static int cpsw_suspend(struct device *dev)
 		for (i = 0; i < priv->data.slaves; i++) {
 			if (netif_running(priv->slaves[i].ndev))
 				cpsw_ndo_stop(priv->slaves[i].ndev);
-			soft_reset_slave(priv->slaves + i);
 		}
 	} else {
 		if (netif_running(ndev))
 			cpsw_ndo_stop(ndev);
-		for_each_slave(priv, soft_reset_slave);
 	}
 
-	pm_runtime_put_sync(&pdev->dev);
-
 	/* Select sleep pin state */
 	pinctrl_pm_select_sleep_state(&pdev->dev);
 
@@ -2577,8 +2623,6 @@ static int cpsw_resume(struct device *dev)
 	struct net_device	*ndev = platform_get_drvdata(pdev);
 	struct cpsw_priv	*priv = netdev_priv(ndev);
 
-	pm_runtime_get_sync(&pdev->dev);
-
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(&pdev->dev);
 
diff --git a/drivers/net/ethernet/ti/cpsw.h b/drivers/net/ethernet/ti/cpsw.h
index e50afd1b2eda..16b54c6f32c2 100644
--- a/drivers/net/ethernet/ti/cpsw.h
+++ b/drivers/net/ethernet/ti/cpsw.h
@@ -35,7 +35,6 @@ struct cpsw_platform_data {
 	u32	cpts_clock_shift; /* convert input clock ticks to nanoseconds */
 	u32	ale_entries;	/* ale table size */
 	u32	bd_ram_size;  /*buffer descriptor ram size */
-	u32	rx_descs;	/* Number of Rx Descriptios */
 	u32	mac_control;	/* Mac control register */
 	u16	default_vlan;	/* Def VLAN for ALE lookup in VLAN aware mode*/
 	bool	dual_emac;	/* Enable Dual EMAC mode */
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 18bf3a8fdc50..1c653ca7c316 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -21,7 +21,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
 #include <linux/delay.h>
-
+#include <linux/genalloc.h>
 #include "davinci_cpdma.h"
 
 /* DMA Registers */
@@ -87,9 +87,8 @@ struct cpdma_desc_pool {
 	void			*cpumap;	/* dma_alloc map */
 	int			desc_size, mem_size;
 	int			num_desc, used_desc;
-	unsigned long		*bitmap;
 	struct device		*dev;
-	spinlock_t		lock;
+	struct gen_pool		*gen_pool;
 };
 
 enum cpdma_state {
@@ -117,6 +116,7 @@ struct cpdma_chan {
 	int				chan_num;
 	spinlock_t			lock;
 	int				count;
+	u32				desc_num;
 	u32				mask;
 	cpdma_handler_fn		handler;
 	enum dma_data_direction		dir;
@@ -145,6 +145,19 @@ struct cpdma_chan {
 				 (directed << CPDMA_TO_PORT_SHIFT));	\
 	} while (0)
 
+static void cpdma_desc_pool_destroy(struct cpdma_desc_pool *pool)
+{
+	if (!pool)
+		return;
+
+	WARN_ON(pool->used_desc);
+	if (pool->cpumap)
+		dma_free_coherent(pool->dev, pool->mem_size, pool->cpumap,
+				  pool->phys);
+	else
+		iounmap(pool->iomap);
+}
+
 /*
  * Utility constructs for a cpdma descriptor pool.  Some devices (e.g. davinci
  * emac) have dedicated on-chip memory for these descriptors.  Some other
@@ -155,24 +168,25 @@ static struct cpdma_desc_pool *
 cpdma_desc_pool_create(struct device *dev, u32 phys, dma_addr_t hw_addr,
 				int size, int align)
 {
-	int bitmap_size;
 	struct cpdma_desc_pool *pool;
+	int ret;
 
 	pool = devm_kzalloc(dev, sizeof(*pool), GFP_KERNEL);
 	if (!pool)
-		goto fail;
-
-	spin_lock_init(&pool->lock);
+		goto gen_pool_create_fail;
 
 	pool->dev	= dev;
 	pool->mem_size	= size;
 	pool->desc_size	= ALIGN(sizeof(struct cpdma_desc), align);
 	pool->num_desc	= size / pool->desc_size;
 
-	bitmap_size  = (pool->num_desc / BITS_PER_LONG) * sizeof(long);
-	pool->bitmap = devm_kzalloc(dev, bitmap_size, GFP_KERNEL);
-	if (!pool->bitmap)
-		goto fail;
+	pool->gen_pool = devm_gen_pool_create(dev, ilog2(pool->desc_size), -1,
+					      "cpdma");
+	if (IS_ERR(pool->gen_pool)) {
+		dev_err(dev, "pool create failed %ld\n",
+			PTR_ERR(pool->gen_pool));
+		goto gen_pool_create_fail;
+	}
 
 	if (phys) {
 		pool->phys  = phys;
@@ -185,24 +199,22 @@ cpdma_desc_pool_create(struct device *dev, u32 phys, dma_addr_t hw_addr,
 		pool->phys = pool->hw_addr; /* assumes no IOMMU, don't use this value */
 	}
 
-	if (pool->iomap)
-		return pool;
-fail:
-	return NULL;
-}
-
-static void cpdma_desc_pool_destroy(struct cpdma_desc_pool *pool)
-{
-	if (!pool)
-		return;
+	if (!pool->iomap)
+		goto gen_pool_create_fail;
 
-	WARN_ON(pool->used_desc);
-	if (pool->cpumap) {
-		dma_free_coherent(pool->dev, pool->mem_size, pool->cpumap,
-				  pool->phys);
-	} else {
-		iounmap(pool->iomap);
+	ret = gen_pool_add_virt(pool->gen_pool, (unsigned long)pool->iomap,
+				pool->phys, pool->mem_size, -1);
+	if (ret < 0) {
+		dev_err(dev, "pool add failed %d\n", ret);
+		goto gen_pool_add_virt_fail;
 	}
+
+	return pool;
+
+gen_pool_add_virt_fail:
+	cpdma_desc_pool_destroy(pool);
+gen_pool_create_fail:
+	return NULL;
 }
 
 static inline dma_addr_t desc_phys(struct cpdma_desc_pool *pool,
@@ -220,47 +232,23 @@ desc_from_phys(struct cpdma_desc_pool *pool, dma_addr_t dma)
 }
 
 static struct cpdma_desc __iomem *
-cpdma_desc_alloc(struct cpdma_desc_pool *pool, int num_desc, bool is_rx)
+cpdma_desc_alloc(struct cpdma_desc_pool *pool)
 {
-	unsigned long flags;
-	int index;
-	int desc_start;
-	int desc_end;
 	struct cpdma_desc __iomem *desc = NULL;
 
-	spin_lock_irqsave(&pool->lock, flags);
-
-	if (is_rx) {
-		desc_start = 0;
-		desc_end = pool->num_desc/2;
-	 } else {
-		desc_start = pool->num_desc/2;
-		desc_end = pool->num_desc;
-	}
-
-	index = bitmap_find_next_zero_area(pool->bitmap,
-				desc_end, desc_start, num_desc, 0);
-	if (index < desc_end) {
-		bitmap_set(pool->bitmap, index, num_desc);
-		desc = pool->iomap + pool->desc_size * index;
+	desc = (struct cpdma_desc __iomem *)gen_pool_alloc(pool->gen_pool,
+							   pool->desc_size);
+	if (desc)
 		pool->used_desc++;
-	}
 
-	spin_unlock_irqrestore(&pool->lock, flags);
 	return desc;
 }
 
 static void cpdma_desc_free(struct cpdma_desc_pool *pool,
 			    struct cpdma_desc __iomem *desc, int num_desc)
 {
-	unsigned long flags, index;
-
-	index = ((unsigned long)desc - (unsigned long)pool->iomap) /
-		pool->desc_size;
-	spin_lock_irqsave(&pool->lock, flags);
-	bitmap_clear(pool->bitmap, index, num_desc);
+	gen_pool_free(pool->gen_pool, (unsigned long)desc, pool->desc_size);
 	pool->used_desc--;
-	spin_unlock_irqrestore(&pool->lock, flags);
 }
 
 struct cpdma_ctlr *cpdma_ctlr_create(struct cpdma_params *params)
@@ -516,6 +504,7 @@ struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num,
 	chan->state	= CPDMA_STATE_IDLE;
 	chan->chan_num	= chan_num;
 	chan->handler	= handler;
+	chan->desc_num = ctlr->pool->num_desc / 2;
 
 	if (is_rx_chan(chan)) {
 		chan->hdp	= ctlr->params.rxhdp + offset;
@@ -543,6 +532,12 @@ struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num,
 }
 EXPORT_SYMBOL_GPL(cpdma_chan_create);
 
+int cpdma_chan_get_rx_buf_num(struct cpdma_ctlr *ctlr)
+{
+	return ctlr->pool->num_desc / 2;
+}
+EXPORT_SYMBOL_GPL(cpdma_chan_get_rx_buf_num);
+
 int cpdma_chan_destroy(struct cpdma_chan *chan)
 {
 	struct cpdma_ctlr *ctlr;
@@ -675,7 +670,13 @@ int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 		goto unlock_ret;
 	}
 
-	desc = cpdma_desc_alloc(ctlr->pool, 1, is_rx_chan(chan));
+	if (chan->count >= chan->desc_num)	{
+		chan->stats.desc_alloc_fail++;
+		ret = -ENOMEM;
+		goto unlock_ret;
+	}
+
+	desc = cpdma_desc_alloc(ctlr->pool);
 	if (!desc) {
 		chan->stats.desc_alloc_fail++;
 		ret = -ENOMEM;
@@ -721,24 +722,16 @@ EXPORT_SYMBOL_GPL(cpdma_chan_submit);
 
 bool cpdma_check_free_tx_desc(struct cpdma_chan *chan)
 {
-	unsigned long flags;
-	int index;
-	bool ret;
 	struct cpdma_ctlr	*ctlr = chan->ctlr;
 	struct cpdma_desc_pool	*pool = ctlr->pool;
+	bool			free_tx_desc;
+	unsigned long		flags;
 
-	spin_lock_irqsave(&pool->lock, flags);
-
-	index = bitmap_find_next_zero_area(pool->bitmap,
-				pool->num_desc, pool->num_desc/2, 1, 0);
-
-	if (index < pool->num_desc)
-		ret = true;
-	else
-		ret = false;
-
-	spin_unlock_irqrestore(&pool->lock, flags);
-	return ret;
+	spin_lock_irqsave(&chan->lock, flags);
+	free_tx_desc = (chan->count < chan->desc_num) &&
+			 gen_pool_avail(pool->gen_pool);
+	spin_unlock_irqrestore(&chan->lock, flags);
+	return free_tx_desc;
 }
 EXPORT_SYMBOL_GPL(cpdma_check_free_tx_desc);
 
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.h b/drivers/net/ethernet/ti/davinci_cpdma.h
index 86dee487f2f0..80c015cbbce5 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.h
+++ b/drivers/net/ethernet/ti/davinci_cpdma.h
@@ -81,6 +81,7 @@ int cpdma_ctlr_dump(struct cpdma_ctlr *ctlr);
 
 struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num,
 				     cpdma_handler_fn handler);
+int cpdma_chan_get_rx_buf_num(struct cpdma_ctlr *ctlr);
 int cpdma_chan_destroy(struct cpdma_chan *chan);
 int cpdma_chan_start(struct cpdma_chan *chan);
 int cpdma_chan_stop(struct cpdma_chan *chan);
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index f56d66e6ec15..c6c54659f8d4 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -348,7 +348,6 @@ struct emac_priv {
 	u32 rx_addr_type;
 	const char *phy_id;
 	struct device_node *phy_node;
-	struct phy_device *phydev;
 	spinlock_t lock;
 	/*platform specific members*/
 	void (*int_enable) (void);
@@ -486,43 +485,6 @@ static void emac_get_drvinfo(struct net_device *ndev,
 }
 
 /**
- * emac_get_settings - Get EMAC settings
- * @ndev: The DaVinci EMAC network adapter
- * @ecmd: ethtool command
- *
- * Executes ethool get command
- *
- */
-static int emac_get_settings(struct net_device *ndev,
-			     struct ethtool_cmd *ecmd)
-{
-	struct emac_priv *priv = netdev_priv(ndev);
-	if (priv->phydev)
-		return phy_ethtool_gset(priv->phydev, ecmd);
-	else
-		return -EOPNOTSUPP;
-
-}
-
-/**
- * emac_set_settings - Set EMAC settings
- * @ndev: The DaVinci EMAC network adapter
- * @ecmd: ethtool command
- *
- * Executes ethool set command
- *
- */
-static int emac_set_settings(struct net_device *ndev, struct ethtool_cmd *ecmd)
-{
-	struct emac_priv *priv = netdev_priv(ndev);
-	if (priv->phydev)
-		return phy_ethtool_sset(priv->phydev, ecmd);
-	else
-		return -EOPNOTSUPP;
-
-}
-
-/**
  * emac_get_coalesce - Get interrupt coalesce settings for this device
  * @ndev : The DaVinci EMAC network adapter
  * @coal : ethtool coalesce settings structure
@@ -625,12 +587,12 @@ static int emac_set_coalesce(struct net_device *ndev,
  */
 static const struct ethtool_ops ethtool_ops = {
 	.get_drvinfo = emac_get_drvinfo,
-	.get_settings = emac_get_settings,
-	.set_settings = emac_set_settings,
 	.get_link = ethtool_op_get_link,
 	.get_coalesce = emac_get_coalesce,
 	.set_coalesce =  emac_set_coalesce,
 	.get_ts_info = ethtool_op_get_ts_info,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 /**
@@ -651,8 +613,8 @@ static void emac_update_phystatus(struct emac_priv *priv)
 	mac_control = emac_read(EMAC_MACCONTROL);
 	cur_duplex = (mac_control & EMAC_MACCONTROL_FULLDUPLEXEN) ?
 			DUPLEX_FULL : DUPLEX_HALF;
-	if (priv->phydev)
-		new_duplex = priv->phydev->duplex;
+	if (ndev->phydev)
+		new_duplex = ndev->phydev->duplex;
 	else
 		new_duplex = DUPLEX_FULL;
 
@@ -1454,7 +1416,7 @@ static void emac_poll_controller(struct net_device *ndev)
 static void emac_adjust_link(struct net_device *ndev)
 {
 	struct emac_priv *priv = netdev_priv(ndev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = ndev->phydev;
 	unsigned long flags;
 	int new_state = 0;
 
@@ -1483,7 +1445,7 @@ static void emac_adjust_link(struct net_device *ndev)
 	}
 	if (new_state) {
 		emac_update_phystatus(priv);
-		phy_print_status(priv->phydev);
+		phy_print_status(ndev->phydev);
 	}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
@@ -1505,15 +1467,13 @@ static void emac_adjust_link(struct net_device *ndev)
  */
 static int emac_devioctl(struct net_device *ndev, struct ifreq *ifrq, int cmd)
 {
-	struct emac_priv *priv = netdev_priv(ndev);
-
 	if (!(netif_running(ndev)))
 		return -EINVAL;
 
 	/* TODO: Add phy read and write and private statistics get feature */
 
-	if (priv->phydev)
-		return phy_mii_ioctl(priv->phydev, ifrq, cmd);
+	if (ndev->phydev)
+		return phy_mii_ioctl(ndev->phydev, ifrq, cmd);
 	else
 		return -EOPNOTSUPP;
 }
@@ -1542,6 +1502,7 @@ static int emac_dev_open(struct net_device *ndev)
 	int res_num = 0, irq_num = 0;
 	int i = 0;
 	struct emac_priv *priv = netdev_priv(ndev);
+	struct phy_device *phydev = NULL;
 
 	ret = pm_runtime_get_sync(&priv->pdev->dev);
 	if (ret < 0) {
@@ -1607,12 +1568,10 @@ static int emac_dev_open(struct net_device *ndev)
 
 	cpdma_ctlr_start(priv->dma);
 
-	priv->phydev = NULL;
-
 	if (priv->phy_node) {
-		priv->phydev = of_phy_connect(ndev, priv->phy_node,
-					      &emac_adjust_link, 0, 0);
-		if (!priv->phydev) {
+		phydev = of_phy_connect(ndev, priv->phy_node,
+					&emac_adjust_link, 0, 0);
+		if (!phydev) {
 			dev_err(emac_dev, "could not connect to phy %s\n",
 				priv->phy_node->full_name);
 			ret = -ENODEV;
@@ -1621,7 +1580,7 @@ static int emac_dev_open(struct net_device *ndev)
 	}
 
 	/* use the first phy on the bus if pdata did not give us a phy id */
-	if (!priv->phydev && !priv->phy_id) {
+	if (!phydev && !priv->phy_id) {
 		struct device *phy;
 
 		phy = bus_find_device(&mdio_bus_type, NULL, NULL,
@@ -1630,16 +1589,15 @@ static int emac_dev_open(struct net_device *ndev)
 			priv->phy_id = dev_name(phy);
 	}
 
-	if (!priv->phydev && priv->phy_id && *priv->phy_id) {
-		priv->phydev = phy_connect(ndev, priv->phy_id,
-					   &emac_adjust_link,
-					   PHY_INTERFACE_MODE_MII);
+	if (!phydev && priv->phy_id && *priv->phy_id) {
+		phydev = phy_connect(ndev, priv->phy_id,
+				     &emac_adjust_link,
+				     PHY_INTERFACE_MODE_MII);
 
-		if (IS_ERR(priv->phydev)) {
+		if (IS_ERR(phydev)) {
 			dev_err(emac_dev, "could not connect to phy %s\n",
 				priv->phy_id);
-			ret = PTR_ERR(priv->phydev);
-			priv->phydev = NULL;
+			ret = PTR_ERR(phydev);
 			goto err;
 		}
 
@@ -1647,10 +1605,10 @@ static int emac_dev_open(struct net_device *ndev)
 		priv->speed = 0;
 		priv->duplex = ~0;
 
-		phy_attached_info(priv->phydev);
+		phy_attached_info(phydev);
 	}
 
-	if (!priv->phydev) {
+	if (!phydev) {
 		/* No PHY , fix the link, speed and duplex settings */
 		dev_notice(emac_dev, "no phy, defaulting to 100/full\n");
 		priv->link = 1;
@@ -1665,8 +1623,8 @@ static int emac_dev_open(struct net_device *ndev)
 	if (netif_msg_drv(priv))
 		dev_notice(emac_dev, "DaVinci EMAC: Opened %s\n", ndev->name);
 
-	if (priv->phydev)
-		phy_start(priv->phydev);
+	if (phydev)
+		phy_start(phydev);
 
 	return 0;
 
@@ -1717,8 +1675,8 @@ static int emac_dev_stop(struct net_device *ndev)
 	cpdma_ctlr_stop(priv->dma);
 	emac_write(EMAC_SOFTRESET, 1);
 
-	if (priv->phydev)
-		phy_disconnect(priv->phydev);
+	if (ndev->phydev)
+		phy_disconnect(ndev->phydev);
 
 	/* Free IRQ */
 	while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, i))) {
diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c
index 4e7c9b9b042a..33df340db1f1 100644
--- a/drivers/net/ethernet/ti/davinci_mdio.c
+++ b/drivers/net/ethernet/ti/davinci_mdio.c
@@ -53,6 +53,10 @@
 
 #define DEF_OUT_FREQ		2200000		/* 2.2 MHz */
 
+struct davinci_mdio_of_param {
+	int autosuspend_delay_ms;
+};
+
 struct davinci_mdio_regs {
 	u32	version;
 	u32	control;
@@ -90,19 +94,19 @@ static const struct mdio_platform_data default_pdata = {
 struct davinci_mdio_data {
 	struct mdio_platform_data pdata;
 	struct davinci_mdio_regs __iomem *regs;
-	spinlock_t	lock;
 	struct clk	*clk;
 	struct device	*dev;
 	struct mii_bus	*bus;
-	bool		suspended;
+	bool            active_in_suspend;
 	unsigned long	access_time; /* jiffies */
 	/* Indicates that driver shouldn't modify phy_mask in case
 	 * if MDIO bus is registered from DT.
 	 */
 	bool		skip_scan;
+	u32		clk_div;
 };
 
-static void __davinci_mdio_reset(struct davinci_mdio_data *data)
+static void davinci_mdio_init_clk(struct davinci_mdio_data *data)
 {
 	u32 mdio_in, div, mdio_out_khz, access_time;
 
@@ -111,9 +115,7 @@ static void __davinci_mdio_reset(struct davinci_mdio_data *data)
 	if (div > CONTROL_MAX_DIV)
 		div = CONTROL_MAX_DIV;
 
-	/* set enable and clock divider */
-	__raw_writel(div | CONTROL_ENABLE, &data->regs->control);
-
+	data->clk_div = div;
 	/*
 	 * One mdio transaction consists of:
 	 *	32 bits of preamble
@@ -134,12 +136,23 @@ static void __davinci_mdio_reset(struct davinci_mdio_data *data)
 		data->access_time = 1;
 }
 
+static void davinci_mdio_enable(struct davinci_mdio_data *data)
+{
+	/* set enable and clock divider */
+	__raw_writel(data->clk_div | CONTROL_ENABLE, &data->regs->control);
+}
+
 static int davinci_mdio_reset(struct mii_bus *bus)
 {
 	struct davinci_mdio_data *data = bus->priv;
 	u32 phy_mask, ver;
+	int ret;
 
-	__davinci_mdio_reset(data);
+	ret = pm_runtime_get_sync(data->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(data->dev);
+		return ret;
+	}
 
 	/* wait for scan logic to settle */
 	msleep(PHY_MAX_ADDR * data->access_time);
@@ -150,7 +163,7 @@ static int davinci_mdio_reset(struct mii_bus *bus)
 		 (ver >> 8) & 0xff, ver & 0xff);
 
 	if (data->skip_scan)
-		return 0;
+		goto done;
 
 	/* get phy mask from the alive register */
 	phy_mask = __raw_readl(&data->regs->alive);
@@ -165,6 +178,10 @@ static int davinci_mdio_reset(struct mii_bus *bus)
 	}
 	data->bus->phy_mask = phy_mask;
 
+done:
+	pm_runtime_mark_last_busy(data->dev);
+	pm_runtime_put_autosuspend(data->dev);
+
 	return 0;
 }
 
@@ -190,7 +207,7 @@ static inline int wait_for_user_access(struct davinci_mdio_data *data)
 		 * operation
 		 */
 		dev_warn(data->dev, "resetting idled controller\n");
-		__davinci_mdio_reset(data);
+		davinci_mdio_enable(data);
 		return -EAGAIN;
 	}
 
@@ -225,11 +242,10 @@ static int davinci_mdio_read(struct mii_bus *bus, int phy_id, int phy_reg)
 	if (phy_reg & ~PHY_REG_MASK || phy_id & ~PHY_ID_MASK)
 		return -EINVAL;
 
-	spin_lock(&data->lock);
-
-	if (data->suspended) {
-		spin_unlock(&data->lock);
-		return -ENODEV;
+	ret = pm_runtime_get_sync(data->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(data->dev);
+		return ret;
 	}
 
 	reg = (USERACCESS_GO | USERACCESS_READ | (phy_reg << 21) |
@@ -255,8 +271,8 @@ static int davinci_mdio_read(struct mii_bus *bus, int phy_id, int phy_reg)
 		break;
 	}
 
-	spin_unlock(&data->lock);
-
+	pm_runtime_mark_last_busy(data->dev);
+	pm_runtime_put_autosuspend(data->dev);
 	return ret;
 }
 
@@ -270,11 +286,10 @@ static int davinci_mdio_write(struct mii_bus *bus, int phy_id,
 	if (phy_reg & ~PHY_REG_MASK || phy_id & ~PHY_ID_MASK)
 		return -EINVAL;
 
-	spin_lock(&data->lock);
-
-	if (data->suspended) {
-		spin_unlock(&data->lock);
-		return -ENODEV;
+	ret = pm_runtime_get_sync(data->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(data->dev);
+		return ret;
 	}
 
 	reg = (USERACCESS_GO | USERACCESS_WRITE | (phy_reg << 21) |
@@ -295,9 +310,10 @@ static int davinci_mdio_write(struct mii_bus *bus, int phy_id,
 		break;
 	}
 
-	spin_unlock(&data->lock);
+	pm_runtime_mark_last_busy(data->dev);
+	pm_runtime_put_autosuspend(data->dev);
 
-	return 0;
+	return ret;
 }
 
 #if IS_ENABLED(CONFIG_OF)
@@ -320,6 +336,19 @@ static int davinci_mdio_probe_dt(struct mdio_platform_data *data,
 }
 #endif
 
+#if IS_ENABLED(CONFIG_OF)
+static const struct davinci_mdio_of_param of_cpsw_mdio_data = {
+	.autosuspend_delay_ms = 100,
+};
+
+static const struct of_device_id davinci_mdio_of_mtable[] = {
+	{ .compatible = "ti,davinci_mdio", },
+	{ .compatible = "ti,cpsw-mdio", .data = &of_cpsw_mdio_data},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, davinci_mdio_of_mtable);
+#endif
+
 static int davinci_mdio_probe(struct platform_device *pdev)
 {
 	struct mdio_platform_data *pdata = dev_get_platdata(&pdev->dev);
@@ -328,6 +357,7 @@ static int davinci_mdio_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct phy_device *phy;
 	int ret, addr;
+	int autosuspend_delay_ms = -1;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
@@ -340,9 +370,22 @@ static int davinci_mdio_probe(struct platform_device *pdev)
 	}
 
 	if (dev->of_node) {
-		if (davinci_mdio_probe_dt(&data->pdata, pdev))
-			data->pdata = default_pdata;
+		const struct of_device_id	*of_id;
+
+		ret = davinci_mdio_probe_dt(&data->pdata, pdev);
+		if (ret)
+			return ret;
 		snprintf(data->bus->id, MII_BUS_ID_SIZE, "%s", pdev->name);
+
+		of_id = of_match_device(davinci_mdio_of_mtable, &pdev->dev);
+		if (of_id) {
+			const struct davinci_mdio_of_param *of_mdio_data;
+
+			of_mdio_data = of_id->data;
+			if (of_mdio_data)
+				autosuspend_delay_ms =
+					of_mdio_data->autosuspend_delay_ms;
+		}
 	} else {
 		data->pdata = pdata ? (*pdata) : default_pdata;
 		snprintf(data->bus->id, MII_BUS_ID_SIZE, "%s-%x",
@@ -356,26 +399,25 @@ static int davinci_mdio_probe(struct platform_device *pdev)
 	data->bus->parent	= dev;
 	data->bus->priv		= data;
 
-	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
 	data->clk = devm_clk_get(dev, "fck");
 	if (IS_ERR(data->clk)) {
 		dev_err(dev, "failed to get device clock\n");
-		ret = PTR_ERR(data->clk);
-		data->clk = NULL;
-		goto bail_out;
+		return PTR_ERR(data->clk);
 	}
 
 	dev_set_drvdata(dev, data);
 	data->dev = dev;
-	spin_lock_init(&data->lock);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	data->regs = devm_ioremap_resource(dev, res);
-	if (IS_ERR(data->regs)) {
-		ret = PTR_ERR(data->regs);
-		goto bail_out;
-	}
+	if (IS_ERR(data->regs))
+		return PTR_ERR(data->regs);
+
+	davinci_mdio_init_clk(data);
+
+	pm_runtime_set_autosuspend_delay(&pdev->dev, autosuspend_delay_ms);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
 
 	/* register the mii bus
 	 * Create PHYs from DT only in case if PHY child nodes are explicitly
@@ -404,9 +446,8 @@ static int davinci_mdio_probe(struct platform_device *pdev)
 	return 0;
 
 bail_out:
-	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-
 	return ret;
 }
 
@@ -417,29 +458,47 @@ static int davinci_mdio_remove(struct platform_device *pdev)
 	if (data->bus)
 		mdiobus_unregister(data->bus);
 
-	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int davinci_mdio_suspend(struct device *dev)
+#ifdef CONFIG_PM
+static int davinci_mdio_runtime_suspend(struct device *dev)
 {
 	struct davinci_mdio_data *data = dev_get_drvdata(dev);
 	u32 ctrl;
 
-	spin_lock(&data->lock);
-
 	/* shutdown the scan state machine */
 	ctrl = __raw_readl(&data->regs->control);
 	ctrl &= ~CONTROL_ENABLE;
 	__raw_writel(ctrl, &data->regs->control);
 	wait_for_idle(data);
 
-	data->suspended = true;
-	spin_unlock(&data->lock);
-	pm_runtime_put_sync(data->dev);
+	return 0;
+}
+
+static int davinci_mdio_runtime_resume(struct device *dev)
+{
+	struct davinci_mdio_data *data = dev_get_drvdata(dev);
+
+	davinci_mdio_enable(data);
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+static int davinci_mdio_suspend(struct device *dev)
+{
+	struct davinci_mdio_data *data = dev_get_drvdata(dev);
+	int ret = 0;
+
+	data->active_in_suspend = !pm_runtime_status_suspended(dev);
+	if (data->active_in_suspend)
+		ret = pm_runtime_force_suspend(dev);
+	if (ret < 0)
+		return ret;
 
 	/* Select sleep pin state */
 	pinctrl_pm_select_sleep_state(dev);
@@ -454,31 +513,19 @@ static int davinci_mdio_resume(struct device *dev)
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(dev);
 
-	pm_runtime_get_sync(data->dev);
-
-	spin_lock(&data->lock);
-	/* restart the scan state machine */
-	__davinci_mdio_reset(data);
-
-	data->suspended = false;
-	spin_unlock(&data->lock);
+	if (data->active_in_suspend)
+		pm_runtime_force_resume(dev);
 
 	return 0;
 }
 #endif
 
 static const struct dev_pm_ops davinci_mdio_pm_ops = {
+	SET_RUNTIME_PM_OPS(davinci_mdio_runtime_suspend,
+			   davinci_mdio_runtime_resume, NULL)
 	SET_LATE_SYSTEM_SLEEP_PM_OPS(davinci_mdio_suspend, davinci_mdio_resume)
 };
 
-#if IS_ENABLED(CONFIG_OF)
-static const struct of_device_id davinci_mdio_of_mtable[] = {
-	{ .compatible = "ti,davinci_mdio", },
-	{ /* sentinel */ },
-};
-MODULE_DEVICE_TABLE(of, davinci_mdio_of_mtable);
-#endif
-
 static struct platform_driver davinci_mdio_driver = {
 	.driver = {
 		.name	 = "davinci_mdio",
diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index 561703317312..ece0ea0f6b38 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -1651,7 +1651,6 @@ static u32 tlan_handle_tx_eoc(struct net_device *dev, u16 host_int)
 	dma_addr_t		head_list_phys;
 	u32			ack = 1;
 
-	host_int = 0;
 	if (priv->tlan_rev < 0x30) {
 		TLAN_DBG(TLAN_DEBUG_TX,
 			 "TRANSMIT:  handling TX EOC (Head=%d Tail=%d) -- IRQ\n",
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 0a15acc075b3..11213a38c795 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -462,7 +462,7 @@ static void tile_tx_timestamp(struct sk_buff *skb, int instance)
 	if (unlikely((shtx->tx_flags & SKBTX_HW_TSTAMP) != 0)) {
 		struct mpipe_data *md = &mpipe_data[instance];
 		struct skb_shared_hwtstamps shhwtstamps;
-		struct timespec ts;
+		struct timespec64 ts;
 
 		shtx->tx_flags |= SKBTX_IN_PROGRESS;
 		gxio_mpipe_get_timestamp(&md->context, &ts);
@@ -886,9 +886,9 @@ static struct ptp_clock_info ptp_mpipe_caps = {
 /* Sync mPIPE's timestamp up with Linux system time and register PTP clock. */
 static void register_ptp_clock(struct net_device *dev, struct mpipe_data *md)
 {
-	struct timespec ts;
+	struct timespec64 ts;
 
-	getnstimeofday(&ts);
+	ktime_get_ts64(&ts);
 	gxio_mpipe_set_timestamp(&md->context, &ts);
 
 	mutex_init(&md->ptp_lock);
diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index 54874783476a..74e671906ddb 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -280,7 +280,7 @@ struct tc35815_regs {
  * Descriptors
  */
 
-/* Frame descripter */
+/* Frame descriptor */
 struct FDesc {
 	volatile __u32 FDNext;
 	volatile __u32 FDSystem;
@@ -288,7 +288,7 @@ struct FDesc {
 	volatile __u32 FDCtl;
 };
 
-/* Buffer descripter */
+/* Buffer descriptor */
 struct BDesc {
 	volatile __u32 BuffData;
 	volatile __u32 BDCtl;
@@ -296,7 +296,7 @@ struct BDesc {
 
 #define FD_ALIGN	16
 
-/* Frame Descripter bit assign ---------------------------------------------- */
+/* Frame Descriptor bit assign ---------------------------------------------- */
 #define FD_FDLength_MASK       0x0000FFFF /* Length MASK		     */
 #define FD_BDCnt_MASK	       0x001F0000 /* BD count MASK in FD	     */
 #define FD_FrmOpt_MASK	       0x7C000000 /* Frame option MASK		     */
@@ -309,7 +309,7 @@ struct BDesc {
 #define FD_Next_EOL	       0x00000001 /* FD EOL indicator		     */
 #define FD_BDCnt_SHIFT	       16
 
-/* Buffer Descripter bit assign --------------------------------------------- */
+/* Buffer Descriptor bit assign --------------------------------------------- */
 #define BD_BuffLength_MASK     0x0000FFFF /* Receive Data Size		     */
 #define BD_RxBDID_MASK	       0x00FF0000 /* BD ID Number MASK		     */
 #define BD_RxBDSeqN_MASK       0x7F000000 /* Rx BD Sequence Number	     */
@@ -1387,7 +1387,7 @@ static int tc35815_do_interrupt(struct net_device *dev, u32 status, int limit)
 	if (status & Int_IntExBD) {
 		if (netif_msg_rx_err(lp))
 			dev_warn(&dev->dev,
-				 "Excessive Buffer Descriptiors (%#x).\n",
+				 "Excessive Buffer Descriptors (%#x).\n",
 				 status);
 		dev->stats.rx_length_errors++;
 		ret = 0;
diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c
index 7b44968e02e6..ddced28e8247 100644
--- a/drivers/net/ethernet/xircom/xirc2ps_cs.c
+++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c
@@ -1144,8 +1144,8 @@ xirc2ps_interrupt(int irq, void *dev_id)
 	    dev->stats.tx_packets += lp->last_ptr_value - n;
 	netif_wake_queue(dev);
     }
-    if (tx_status & 0x0002) {	/* Execessive collissions */
-	pr_debug("tx restarted due to execssive collissions\n");
+    if (tx_status & 0x0002) {	/* Excessive collisions */
+	pr_debug("tx restarted due to excessive collisions\n");
 	PutByte(XIRCREG_CR, RestartTx);  /* restart transmitter process */
     }
     if (tx_status & 0x0040)
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index 5138407941cf..7f127dc1b7ba 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -171,7 +171,6 @@ struct port {
 	struct npe *npe;
 	struct net_device *netdev;
 	struct napi_struct napi;
-	struct phy_device *phydev;
 	struct eth_plat_info *plat;
 	buffer_t *rx_buff_tab[RX_DESCS], *tx_buff_tab[TX_DESCS];
 	struct desc *desc_tab;	/* coherent */
@@ -562,7 +561,7 @@ static void ixp4xx_mdio_remove(void)
 static void ixp4xx_adjust_link(struct net_device *dev)
 {
 	struct port *port = netdev_priv(dev);
-	struct phy_device *phydev = port->phydev;
+	struct phy_device *phydev = dev->phydev;
 
 	if (!phydev->link) {
 		if (port->speed) {
@@ -976,8 +975,6 @@ static void eth_set_mcast_list(struct net_device *dev)
 
 static int eth_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 {
-	struct port *port = netdev_priv(dev);
-
 	if (!netif_running(dev))
 		return -EINVAL;
 
@@ -988,7 +985,7 @@ static int eth_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 			return hwtstamp_get(dev, req);
 	}
 
-	return phy_mii_ioctl(port->phydev, req, cmd);
+	return phy_mii_ioctl(dev->phydev, req, cmd);
 }
 
 /* ethtool support */
@@ -1005,22 +1002,9 @@ static void ixp4xx_get_drvinfo(struct net_device *dev,
 	strlcpy(info->bus_info, "internal", sizeof(info->bus_info));
 }
 
-static int ixp4xx_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct port *port = netdev_priv(dev);
-	return phy_ethtool_gset(port->phydev, cmd);
-}
-
-static int ixp4xx_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct port *port = netdev_priv(dev);
-	return phy_ethtool_sset(port->phydev, cmd);
-}
-
 static int ixp4xx_nway_reset(struct net_device *dev)
 {
-	struct port *port = netdev_priv(dev);
-	return phy_start_aneg(port->phydev);
+	return phy_start_aneg(dev->phydev);
 }
 
 int ixp46x_phc_index = -1;
@@ -1054,11 +1038,11 @@ static int ixp4xx_get_ts_info(struct net_device *dev,
 
 static const struct ethtool_ops ixp4xx_ethtool_ops = {
 	.get_drvinfo = ixp4xx_get_drvinfo,
-	.get_settings = ixp4xx_get_settings,
-	.set_settings = ixp4xx_set_settings,
 	.nway_reset = ixp4xx_nway_reset,
 	.get_link = ethtool_op_get_link,
 	.get_ts_info = ixp4xx_get_ts_info,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 
@@ -1259,7 +1243,7 @@ static int eth_open(struct net_device *dev)
 	}
 
 	port->speed = 0;	/* force "link up" message */
-	phy_start(port->phydev);
+	phy_start(dev->phydev);
 
 	for (i = 0; i < ETH_ALEN; i++)
 		__raw_writel(dev->dev_addr[i], &port->regs->hw_addr[i]);
@@ -1380,7 +1364,7 @@ static int eth_close(struct net_device *dev)
 		printk(KERN_CRIT "%s: unable to disable loopback\n",
 		       dev->name);
 
-	phy_stop(port->phydev);
+	phy_stop(dev->phydev);
 
 	if (!ports_open)
 		qmgr_disable_irq(TXDONE_QUEUE);
@@ -1405,6 +1389,7 @@ static int eth_init_one(struct platform_device *pdev)
 	struct port *port;
 	struct net_device *dev;
 	struct eth_plat_info *plat = dev_get_platdata(&pdev->dev);
+	struct phy_device *phydev = NULL;
 	u32 regs_phys;
 	char phy_id[MII_BUS_ID_SIZE + 3];
 	int err;
@@ -1466,14 +1451,14 @@ static int eth_init_one(struct platform_device *pdev)
 
 	snprintf(phy_id, MII_BUS_ID_SIZE + 3, PHY_ID_FMT,
 		mdio_bus->id, plat->phy);
-	port->phydev = phy_connect(dev, phy_id, &ixp4xx_adjust_link,
-				   PHY_INTERFACE_MODE_MII);
-	if (IS_ERR(port->phydev)) {
-		err = PTR_ERR(port->phydev);
+	phydev = phy_connect(dev, phy_id, &ixp4xx_adjust_link,
+			     PHY_INTERFACE_MODE_MII);
+	if (IS_ERR(phydev)) {
+		err = PTR_ERR(phydev);
 		goto err_free_mem;
 	}
 
-	port->phydev->irq = PHY_POLL;
+	phydev->irq = PHY_POLL;
 
 	if ((err = register_netdev(dev)))
 		goto err_phy_dis;
@@ -1484,7 +1469,7 @@ static int eth_init_one(struct platform_device *pdev)
 	return 0;
 
 err_phy_dis:
-	phy_disconnect(port->phydev);
+	phy_disconnect(phydev);
 err_free_mem:
 	npe_port_tab[NPE_ID(port->id)] = NULL;
 	release_resource(port->mem_res);
@@ -1498,10 +1483,11 @@ err_free:
 static int eth_remove_one(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
+	struct phy_device *phydev = dev->phydev;
 	struct port *port = netdev_priv(dev);
 
 	unregister_netdev(dev);
-	phy_disconnect(port->phydev);
+	phy_disconnect(phydev);
 	npe_port_tab[NPE_ID(port->id)] = NULL;
 	npe_release(port->npe);
 	release_resource(port->mem_res);
diff --git a/drivers/net/fddi/skfp/Makefile b/drivers/net/fddi/skfp/Makefile
index b0be0234abf6..a957a1c7e5ba 100644
--- a/drivers/net/fddi/skfp/Makefile
+++ b/drivers/net/fddi/skfp/Makefile
@@ -17,4 +17,4 @@ skfp-objs :=  skfddi.o    hwmtm.o    fplustm.o  smt.o      cfm.o     \
 #   projects. To keep the source common for all those drivers (and
 #   thus simplify fixes to it), please do not clean it up!
 
-ccflags-y := -Idrivers/net/skfp -DPCI -DMEM_MAPPED_IO -Wno-strict-prototypes
+ccflags-y := -DPCI -DMEM_MAPPED_IO -Wno-strict-prototypes
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index cadefe4fdaa2..310e0b9c2657 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -12,7 +12,6 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/hash.h>
 #include <net/dst_metadata.h>
@@ -397,23 +396,6 @@ static struct socket *geneve_create_sock(struct net *net, bool ipv6,
 	return sock;
 }
 
-static void geneve_notify_add_rx_port(struct geneve_sock *gs)
-{
-	struct net_device *dev;
-	struct sock *sk = gs->sock->sk;
-	struct net *net = sock_net(sk);
-	sa_family_t sa_family = geneve_get_sk_family(gs);
-	__be16 port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (dev->netdev_ops->ndo_add_geneve_port)
-			dev->netdev_ops->ndo_add_geneve_port(dev, sa_family,
-							     port);
-	}
-	rcu_read_unlock();
-}
-
 static int geneve_hlen(struct genevehdr *gh)
 {
 	return sizeof(*gh) + gh->opt_len * 4;
@@ -533,7 +515,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 		INIT_HLIST_HEAD(&gs->vni_list[h]);
 
 	/* Initialize the geneve udp offloads structure */
-	geneve_notify_add_rx_port(gs);
+	udp_tunnel_notify_add_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE);
 
 	/* Mark socket as an encapsulation socket */
 	memset(&tunnel_cfg, 0, sizeof(tunnel_cfg));
@@ -548,31 +530,13 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	return gs;
 }
 
-static void geneve_notify_del_rx_port(struct geneve_sock *gs)
-{
-	struct net_device *dev;
-	struct sock *sk = gs->sock->sk;
-	struct net *net = sock_net(sk);
-	sa_family_t sa_family = geneve_get_sk_family(gs);
-	__be16 port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (dev->netdev_ops->ndo_del_geneve_port)
-			dev->netdev_ops->ndo_del_geneve_port(dev, sa_family,
-							     port);
-	}
-
-	rcu_read_unlock();
-}
-
 static void __geneve_sock_release(struct geneve_sock *gs)
 {
 	if (!gs || --gs->refcnt)
 		return;
 
 	list_del(&gs->list);
-	geneve_notify_del_rx_port(gs);
+	udp_tunnel_notify_del_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE);
 	udp_tunnel_sock_release(gs->sock);
 	kfree_rcu(gs, rcu);
 }
@@ -958,8 +922,8 @@ tx_error:
 		dev->stats.collisions++;
 	else if (err == -ENETUNREACH)
 		dev->stats.tx_carrier_errors++;
-	else
-		dev->stats.tx_errors++;
+
+	dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
 }
 
@@ -1048,8 +1012,8 @@ tx_error:
 		dev->stats.collisions++;
 	else if (err == -ENETUNREACH)
 		dev->stats.tx_carrier_errors++;
-	else
-		dev->stats.tx_errors++;
+
+	dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
 }
 #endif
@@ -1165,29 +1129,20 @@ static struct device_type geneve_type = {
 	.name = "geneve",
 };
 
-/* Calls the ndo_add_geneve_port of the caller in order to
+/* Calls the ndo_add_udp_enc_port of the caller in order to
  * supply the listening GENEVE udp ports. Callers are expected
- * to implement the ndo_add_geneve_port.
+ * to implement the ndo_add_udp_enc_port.
  */
 static void geneve_push_rx_ports(struct net_device *dev)
 {
 	struct net *net = dev_net(dev);
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_sock *gs;
-	sa_family_t sa_family;
-	struct sock *sk;
-	__be16 port;
-
-	if (!dev->netdev_ops->ndo_add_geneve_port)
-		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(gs, &gn->sock_list, list) {
-		sk = gs->sock->sk;
-		sa_family = sk->sk_family;
-		port = inet_sk(sk)->inet_sport;
-		dev->netdev_ops->ndo_add_geneve_port(dev, sa_family, port);
-	}
+	list_for_each_entry_rcu(gs, &gn->sock_list, list)
+		udp_tunnel_push_rx_port(dev, gs->sock,
+					UDP_TUNNEL_TYPE_GENEVE);
 	rcu_read_unlock();
 }
 
@@ -1508,6 +1463,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 {
 	struct nlattr *tb[IFLA_MAX + 1];
 	struct net_device *dev;
+	LIST_HEAD(list_kill);
 	int err;
 
 	memset(tb, 0, sizeof(tb));
@@ -1519,8 +1475,10 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 	err = geneve_configure(net, dev, &geneve_remote_unspec,
 			       0, 0, 0, 0, htons(dst_port), true,
 			       GENEVE_F_UDP_ZERO_CSUM6_RX);
-	if (err)
-		goto err;
+	if (err) {
+		free_netdev(dev);
+		return ERR_PTR(err);
+	}
 
 	/* openvswitch users expect packet sizes to be unrestricted,
 	 * so set the largest MTU we can.
@@ -1529,10 +1487,15 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 	if (err)
 		goto err;
 
+	err = rtnl_configure_link(dev, NULL);
+	if (err < 0)
+		goto err;
+
 	return dev;
 
  err:
-	free_netdev(dev);
+	geneve_dellink(dev, &list_kill);
+	unregister_netdevice_many(&list_kill);
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(geneve_dev_create_fb);
@@ -1542,7 +1505,7 @@ static int geneve_netdevice_event(struct notifier_block *unused,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (event == NETDEV_OFFLOAD_PUSH_GENEVE)
+	if (event == NETDEV_UDP_TUNNEL_PUSH_INFO)
 		geneve_push_rx_ports(dev);
 
 	return NOTIFY_DONE;
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 4e976a0d5a76..97e0cbca0a08 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -16,7 +16,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/module.h>
-#include <linux/version.h>
 #include <linux/skbuff.h>
 #include <linux/udp.h>
 #include <linux/rculist.h>
diff --git a/drivers/net/hamradio/baycom_par.c b/drivers/net/hamradio/baycom_par.c
index acb636963e90..072cddce9264 100644
--- a/drivers/net/hamradio/baycom_par.c
+++ b/drivers/net/hamradio/baycom_par.c
@@ -156,7 +156,7 @@ struct baycom_state {
 
 /* --------------------------------------------------------------------- */
 
-static void __inline__ baycom_int_freq(struct baycom_state *bc)
+static inline void baycom_int_freq(struct baycom_state *bc)
 {
 #ifdef BAYCOM_DEBUG
 	unsigned long cur_jiffies = jiffies;
@@ -192,7 +192,7 @@ static void __inline__ baycom_int_freq(struct baycom_state *bc)
 
 /* --------------------------------------------------------------------- */
 
-static __inline__ void par96_tx(struct net_device *dev, struct baycom_state *bc)
+static inline void par96_tx(struct net_device *dev, struct baycom_state *bc)
 {
 	int i;
 	unsigned int data = hdlcdrv_getbits(&bc->hdrv);
@@ -216,7 +216,7 @@ static __inline__ void par96_tx(struct net_device *dev, struct baycom_state *bc)
 
 /* --------------------------------------------------------------------- */
 
-static __inline__ void par96_rx(struct net_device *dev, struct baycom_state *bc)
+static inline void par96_rx(struct net_device *dev, struct baycom_state *bc)
 {
 	int i;
 	unsigned int data, mask, mask2, descx;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 96f00c0261fa..6909c322de4e 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -244,7 +244,6 @@ static int netvsc_destroy_buf(struct hv_device *device)
 static int netvsc_init_buf(struct hv_device *device)
 {
 	int ret = 0;
-	unsigned long t;
 	struct netvsc_device *net_device;
 	struct nvsp_message *init_packet;
 	struct net_device *ndev;
@@ -305,9 +304,7 @@ static int netvsc_init_buf(struct hv_device *device)
 		goto cleanup;
 	}
 
-	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
-	BUG_ON(t == 0);
-
+	wait_for_completion(&net_device->channel_init_wait);
 
 	/* Check the response */
 	if (init_packet->msg.v1_msg.
@@ -390,8 +387,7 @@ static int netvsc_init_buf(struct hv_device *device)
 		goto cleanup;
 	}
 
-	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
-	BUG_ON(t == 0);
+	wait_for_completion(&net_device->channel_init_wait);
 
 	/* Check the response */
 	if (init_packet->msg.v1_msg.
@@ -445,7 +441,6 @@ static int negotiate_nvsp_ver(struct hv_device *device,
 {
 	struct net_device *ndev = hv_get_drvdata(device);
 	int ret;
-	unsigned long t;
 
 	memset(init_packet, 0, sizeof(struct nvsp_message));
 	init_packet->hdr.msg_type = NVSP_MSG_TYPE_INIT;
@@ -462,10 +457,7 @@ static int negotiate_nvsp_ver(struct hv_device *device,
 	if (ret != 0)
 		return ret;
 
-	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
-
-	if (t == 0)
-		return -ETIMEDOUT;
+	wait_for_completion(&net_device->channel_init_wait);
 
 	if (init_packet->msg.init_msg.init_complete.status !=
 	    NVSP_STAT_SUCCESS)
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 979fa4455f72..8e830f741d47 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -466,7 +466,6 @@ static int rndis_filter_query_device(struct rndis_device *dev, u32 oid,
 	struct rndis_query_request *query;
 	struct rndis_query_complete *query_complete;
 	int ret = 0;
-	unsigned long t;
 
 	if (!result)
 		return -EINVAL;
@@ -503,11 +502,7 @@ static int rndis_filter_query_device(struct rndis_device *dev, u32 oid,
 	if (ret != 0)
 		goto cleanup;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
-	if (t == 0) {
-		ret = -ETIMEDOUT;
-		goto cleanup;
-	}
+	wait_for_completion(&request->wait_event);
 
 	/* Copy the response back */
 	query_complete = &request->response_msg.msg.query_complete;
@@ -556,7 +551,6 @@ int rndis_filter_set_device_mac(struct net_device *ndev, char *mac)
 	u32 extlen = sizeof(struct rndis_config_parameter_info) +
 		2*NWADR_STRLEN + 4*ETH_ALEN;
 	int ret;
-	unsigned long t;
 
 	request = get_rndis_request(rdev, RNDIS_MSG_SET,
 		RNDIS_MESSAGE_SIZE(struct rndis_set_request) + extlen);
@@ -597,21 +591,13 @@ int rndis_filter_set_device_mac(struct net_device *ndev, char *mac)
 	if (ret != 0)
 		goto cleanup;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
-	if (t == 0) {
-		netdev_err(ndev, "timeout before we got a set response...\n");
-		/*
-		 * can't put_rndis_request, since we may still receive a
-		 * send-completion.
-		 */
-		return -EBUSY;
-	} else {
-		set_complete = &request->response_msg.msg.set_complete;
-		if (set_complete->status != RNDIS_STATUS_SUCCESS) {
-			netdev_err(ndev, "Fail to set MAC on host side:0x%x\n",
-				   set_complete->status);
-			ret = -EINVAL;
-		}
+	wait_for_completion(&request->wait_event);
+
+	set_complete = &request->response_msg.msg.set_complete;
+	if (set_complete->status != RNDIS_STATUS_SUCCESS) {
+		netdev_err(ndev, "Fail to set MAC on host side:0x%x\n",
+			   set_complete->status);
+		ret = -EINVAL;
 	}
 
 cleanup:
@@ -631,7 +617,6 @@ rndis_filter_set_offload_params(struct net_device *ndev,
 	struct rndis_set_complete *set_complete;
 	u32 extlen = sizeof(struct ndis_offload_params);
 	int ret;
-	unsigned long t;
 	u32 vsp_version = nvdev->nvsp_version;
 
 	if (vsp_version <= NVSP_PROTOCOL_VERSION_4) {
@@ -665,20 +650,12 @@ rndis_filter_set_offload_params(struct net_device *ndev,
 	if (ret != 0)
 		goto cleanup;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
-	if (t == 0) {
-		netdev_err(ndev, "timeout before we got aOFFLOAD set response...\n");
-		/* can't put_rndis_request, since we may still receive a
-		 * send-completion.
-		 */
-		return -EBUSY;
-	} else {
-		set_complete = &request->response_msg.msg.set_complete;
-		if (set_complete->status != RNDIS_STATUS_SUCCESS) {
-			netdev_err(ndev, "Fail to set offload on host side:0x%x\n",
-				   set_complete->status);
-			ret = -EINVAL;
-		}
+	wait_for_completion(&request->wait_event);
+	set_complete = &request->response_msg.msg.set_complete;
+	if (set_complete->status != RNDIS_STATUS_SUCCESS) {
+		netdev_err(ndev, "Fail to set offload on host side:0x%x\n",
+			   set_complete->status);
+		ret = -EINVAL;
 	}
 
 cleanup:
@@ -706,7 +683,6 @@ static int rndis_filter_set_rss_param(struct rndis_device *rdev, int num_queue)
 	u32 *itab;
 	u8 *keyp;
 	int i, ret;
-	unsigned long t;
 
 	request = get_rndis_request(
 			rdev, RNDIS_MSG_SET,
@@ -749,20 +725,12 @@ static int rndis_filter_set_rss_param(struct rndis_device *rdev, int num_queue)
 	if (ret != 0)
 		goto cleanup;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
-	if (t == 0) {
-		netdev_err(ndev, "timeout before we got a set response...\n");
-		/* can't put_rndis_request, since we may still receive a
-		 * send-completion.
-		 */
-		return -ETIMEDOUT;
-	} else {
-		set_complete = &request->response_msg.msg.set_complete;
-		if (set_complete->status != RNDIS_STATUS_SUCCESS) {
-			netdev_err(ndev, "Fail to set RSS parameters:0x%x\n",
-				   set_complete->status);
-			ret = -EINVAL;
-		}
+	wait_for_completion(&request->wait_event);
+	set_complete = &request->response_msg.msg.set_complete;
+	if (set_complete->status != RNDIS_STATUS_SUCCESS) {
+		netdev_err(ndev, "Fail to set RSS parameters:0x%x\n",
+			   set_complete->status);
+		ret = -EINVAL;
 	}
 
 cleanup:
@@ -791,8 +759,6 @@ int rndis_filter_set_packet_filter(struct rndis_device *dev, u32 new_filter)
 	struct rndis_set_complete *set_complete;
 	u32 status;
 	int ret;
-	unsigned long t;
-	struct net_device *ndev = dev->ndev;
 
 	request = get_rndis_request(dev, RNDIS_MSG_SET,
 			RNDIS_MESSAGE_SIZE(struct rndis_set_request) +
@@ -815,26 +781,14 @@ int rndis_filter_set_packet_filter(struct rndis_device *dev, u32 new_filter)
 	if (ret != 0)
 		goto cleanup;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	wait_for_completion(&request->wait_event);
 
-	if (t == 0) {
-		netdev_err(ndev,
-			"timeout before we got a set response...\n");
-		ret = -ETIMEDOUT;
-		/*
-		 * We can't deallocate the request since we may still receive a
-		 * send completion for it.
-		 */
-		goto exit;
-	} else {
-		set_complete = &request->response_msg.msg.set_complete;
-		status = set_complete->status;
-	}
+	set_complete = &request->response_msg.msg.set_complete;
+	status = set_complete->status;
 
 cleanup:
 	if (request)
 		put_rndis_request(dev, request);
-exit:
 	return ret;
 }
 
@@ -846,7 +800,6 @@ static int rndis_filter_init_device(struct rndis_device *dev)
 	struct rndis_initialize_complete *init_complete;
 	u32 status;
 	int ret;
-	unsigned long t;
 	struct netvsc_device *nvdev = net_device_to_netvsc_device(dev->ndev);
 
 	request = get_rndis_request(dev, RNDIS_MSG_INIT,
@@ -870,12 +823,7 @@ static int rndis_filter_init_device(struct rndis_device *dev)
 		goto cleanup;
 	}
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
-
-	if (t == 0) {
-		ret = -ETIMEDOUT;
-		goto cleanup;
-	}
+	wait_for_completion(&request->wait_event);
 
 	init_complete = &request->response_msg.msg.init_complete;
 	status = init_complete->status;
@@ -1008,7 +956,6 @@ int rndis_filter_device_add(struct hv_device *dev,
 	struct netvsc_device_info *device_info = additional_info;
 	struct ndis_offload_params offloads;
 	struct nvsp_message *init_packet;
-	unsigned long t;
 	struct ndis_recv_scale_cap rsscap;
 	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 	u32 mtu, size;
@@ -1151,11 +1098,8 @@ int rndis_filter_device_add(struct hv_device *dev,
 			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	if (ret)
 		goto out;
-	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
-	if (t == 0) {
-		ret = -ETIMEDOUT;
-		goto out;
-	}
+	wait_for_completion(&net_device->channel_init_wait);
+
 	if (init_packet->msg.v5_msg.subchn_comp.status !=
 	    NVSP_STAT_SUCCESS) {
 		ret = -ENODEV;
@@ -1192,17 +1136,12 @@ void rndis_filter_device_remove(struct hv_device *dev)
 {
 	struct netvsc_device *net_dev = hv_device_to_netvsc_device(dev);
 	struct rndis_device *rndis_dev = net_dev->extension;
-	unsigned long t;
 
 	/* If not all subchannel offers are complete, wait for them until
 	 * completion to avoid race.
 	 */
-	while (net_dev->num_sc_offered > 0) {
-		t = wait_for_completion_timeout(&net_dev->channel_init_wait,
-						10 * HZ);
-		if (t == 0)
-			WARN(1, "Netvsc: Waiting for sub-channel processing");
-	}
+	if (net_dev->num_sc_offered > 0)
+		wait_for_completion(&net_dev->channel_init_wait);
 
 	/* Halt and release the rndis device */
 	rndis_filter_halt_device(rndis_dev);
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 1c4d395fbd49..18b4e8c7f68a 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -80,13 +80,6 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	kfree_rcu(port, rcu);
 }
 
-/* ipvlan network devices have devices nesting below it and are a special
- * "super class" of normal network devices; split their locks off into a
- * separate class since they always nest.
- */
-static struct lock_class_key ipvlan_netdev_xmit_lock_key;
-static struct lock_class_key ipvlan_netdev_addr_lock_key;
-
 #define IPVLAN_FEATURES \
 	(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
 	 NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \
@@ -96,19 +89,6 @@ static struct lock_class_key ipvlan_netdev_addr_lock_key;
 #define IPVLAN_STATE_MASK \
 	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
 
-static void ipvlan_set_lockdep_class_one(struct net_device *dev,
-					 struct netdev_queue *txq,
-					 void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &ipvlan_netdev_xmit_lock_key);
-}
-
-static void ipvlan_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &ipvlan_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, ipvlan_set_lockdep_class_one, NULL);
-}
-
 static int ipvlan_init(struct net_device *dev)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
@@ -123,7 +103,7 @@ static int ipvlan_init(struct net_device *dev)
 	dev->gso_max_segs = phy_dev->gso_max_segs;
 	dev->hard_header_len = phy_dev->hard_header_len;
 
-	ipvlan_set_lockdep_class(dev);
+	netdev_lockdep_set_classes(dev);
 
 	ipvlan->pcpu_stats = alloc_percpu(struct ipvl_pcpu_stats);
 	if (!ipvlan->pcpu_stats)
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 47ee2c840b55..0e7eff7f1cd2 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -605,12 +605,41 @@ static void macsec_encrypt_done(struct crypto_async_request *base, int err)
 	dev_put(dev);
 }
 
+static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm,
+					     unsigned char **iv,
+					     struct scatterlist **sg)
+{
+	size_t size, iv_offset, sg_offset;
+	struct aead_request *req;
+	void *tmp;
+
+	size = sizeof(struct aead_request) + crypto_aead_reqsize(tfm);
+	iv_offset = size;
+	size += GCM_AES_IV_LEN;
+
+	size = ALIGN(size, __alignof__(struct scatterlist));
+	sg_offset = size;
+	size += sizeof(struct scatterlist) * (MAX_SKB_FRAGS + 1);
+
+	tmp = kmalloc(size, GFP_ATOMIC);
+	if (!tmp)
+		return NULL;
+
+	*iv = (unsigned char *)(tmp + iv_offset);
+	*sg = (struct scatterlist *)(tmp + sg_offset);
+	req = tmp;
+
+	aead_request_set_tfm(req, tfm);
+
+	return req;
+}
+
 static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 				      struct net_device *dev)
 {
 	int ret;
-	struct scatterlist sg[MAX_SKB_FRAGS + 1];
-	unsigned char iv[GCM_AES_IV_LEN];
+	struct scatterlist *sg;
+	unsigned char *iv;
 	struct ethhdr *eth;
 	struct macsec_eth_header *hh;
 	size_t unprotected_len;
@@ -668,8 +697,6 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 	macsec_fill_sectag(hh, secy, pn);
 	macsec_set_shortlen(hh, unprotected_len - 2 * ETH_ALEN);
 
-	macsec_fill_iv(iv, secy->sci, pn);
-
 	skb_put(skb, secy->icv_len);
 
 	if (skb->len - ETH_HLEN > macsec_priv(dev)->real_dev->mtu) {
@@ -684,13 +711,15 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 		return ERR_PTR(-EINVAL);
 	}
 
-	req = aead_request_alloc(tx_sa->key.tfm, GFP_ATOMIC);
+	req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg);
 	if (!req) {
 		macsec_txsa_put(tx_sa);
 		kfree_skb(skb);
 		return ERR_PTR(-ENOMEM);
 	}
 
+	macsec_fill_iv(iv, secy->sci, pn);
+
 	sg_init_table(sg, MAX_SKB_FRAGS + 1);
 	skb_to_sgvec(skb, sg, 0, skb->len);
 
@@ -861,7 +890,6 @@ static void macsec_decrypt_done(struct crypto_async_request *base, int err)
 out:
 	macsec_rxsa_put(rx_sa);
 	dev_put(dev);
-	return;
 }
 
 static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
@@ -871,8 +899,8 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
 				      struct macsec_secy *secy)
 {
 	int ret;
-	struct scatterlist sg[MAX_SKB_FRAGS + 1];
-	unsigned char iv[GCM_AES_IV_LEN];
+	struct scatterlist *sg;
+	unsigned char *iv;
 	struct aead_request *req;
 	struct macsec_eth_header *hdr;
 	u16 icv_len = secy->icv_len;
@@ -882,7 +910,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
-	req = aead_request_alloc(rx_sa->key.tfm, GFP_ATOMIC);
+	req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg);
 	if (!req) {
 		kfree_skb(skb);
 		return ERR_PTR(-ENOMEM);
@@ -1234,7 +1262,7 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len)
 	struct crypto_aead *tfm;
 	int ret;
 
-	tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
+	tfm = crypto_alloc_aead("gcm(aes)", 0, 0);
 	if (!tfm || IS_ERR(tfm))
 		return NULL;
 
@@ -3361,6 +3389,7 @@ static void __exit macsec_exit(void)
 	genl_unregister_family(&macsec_fam);
 	rtnl_link_unregister(&macsec_link_ops);
 	unregister_netdevice_notifier(&macsec_notifier);
+	rcu_barrier();
 }
 
 module_init(macsec_init);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 0c65bd914aed..cd9b53834bf6 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -788,7 +788,6 @@ static int macvlan_change_mtu(struct net_device *dev, int new_mtu)
  * "super class" of normal network devices; split their locks off into a
  * separate class since they always nest.
  */
-static struct lock_class_key macvlan_netdev_xmit_lock_key;
 static struct lock_class_key macvlan_netdev_addr_lock_key;
 
 #define ALWAYS_ON_FEATURES \
@@ -809,20 +808,12 @@ static int macvlan_get_nest_level(struct net_device *dev)
 	return ((struct macvlan_dev *)netdev_priv(dev))->nest_level;
 }
 
-static void macvlan_set_lockdep_class_one(struct net_device *dev,
-					  struct netdev_queue *txq,
-					  void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock,
-			  &macvlan_netdev_xmit_lock_key);
-}
-
 static void macvlan_set_lockdep_class(struct net_device *dev)
 {
+	netdev_lockdep_set_classes(dev);
 	lockdep_set_class_and_subclass(&dev->addr_list_lock,
 				       &macvlan_netdev_addr_lock_key,
 				       macvlan_get_nest_level(dev));
-	netdev_for_each_tx_queue(dev, macvlan_set_lockdep_class_one, NULL);
 }
 
 static int macvlan_init(struct net_device *dev)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index bd6720962b1f..95a13321f688 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -627,93 +627,6 @@ static inline struct sk_buff *macvtap_alloc_skb(struct sock *sk, size_t prepad,
 	return skb;
 }
 
-/*
- * macvtap_skb_from_vnet_hdr and macvtap_skb_to_vnet_hdr should
- * be shared with the tun/tap driver.
- */
-static int macvtap_skb_from_vnet_hdr(struct macvtap_queue *q,
-				     struct sk_buff *skb,
-				     struct virtio_net_hdr *vnet_hdr)
-{
-	unsigned short gso_type = 0;
-	if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-		switch (vnet_hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
-		case VIRTIO_NET_HDR_GSO_TCPV4:
-			gso_type = SKB_GSO_TCPV4;
-			break;
-		case VIRTIO_NET_HDR_GSO_TCPV6:
-			gso_type = SKB_GSO_TCPV6;
-			break;
-		case VIRTIO_NET_HDR_GSO_UDP:
-			gso_type = SKB_GSO_UDP;
-			break;
-		default:
-			return -EINVAL;
-		}
-
-		if (vnet_hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
-			gso_type |= SKB_GSO_TCP_ECN;
-
-		if (vnet_hdr->gso_size == 0)
-			return -EINVAL;
-	}
-
-	if (vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-		if (!skb_partial_csum_set(skb, macvtap16_to_cpu(q, vnet_hdr->csum_start),
-					  macvtap16_to_cpu(q, vnet_hdr->csum_offset)))
-			return -EINVAL;
-	}
-
-	if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-		skb_shinfo(skb)->gso_size = macvtap16_to_cpu(q, vnet_hdr->gso_size);
-		skb_shinfo(skb)->gso_type = gso_type;
-
-		/* Header must be checked, and gso_segs computed. */
-		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
-		skb_shinfo(skb)->gso_segs = 0;
-	}
-	return 0;
-}
-
-static void macvtap_skb_to_vnet_hdr(struct macvtap_queue *q,
-				    const struct sk_buff *skb,
-				    struct virtio_net_hdr *vnet_hdr)
-{
-	memset(vnet_hdr, 0, sizeof(*vnet_hdr));
-
-	if (skb_is_gso(skb)) {
-		struct skb_shared_info *sinfo = skb_shinfo(skb);
-
-		/* This is a hint as to how much should be linear. */
-		vnet_hdr->hdr_len = cpu_to_macvtap16(q, skb_headlen(skb));
-		vnet_hdr->gso_size = cpu_to_macvtap16(q, sinfo->gso_size);
-		if (sinfo->gso_type & SKB_GSO_TCPV4)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
-		else if (sinfo->gso_type & SKB_GSO_TCPV6)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
-		else if (sinfo->gso_type & SKB_GSO_UDP)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
-		else
-			BUG();
-		if (sinfo->gso_type & SKB_GSO_TCP_ECN)
-			vnet_hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
-	} else
-		vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
-
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		if (skb_vlan_tag_present(skb))
-			vnet_hdr->csum_start = cpu_to_macvtap16(q,
-				skb_checksum_start_offset(skb) + VLAN_HLEN);
-		else
-			vnet_hdr->csum_start = cpu_to_macvtap16(q,
-				skb_checksum_start_offset(skb));
-		vnet_hdr->csum_offset = cpu_to_macvtap16(q, skb->csum_offset);
-	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-		vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
-	} /* else everything is zero */
-}
-
 /* Neighbour code has some assumptions on HH_DATA_MOD alignment */
 #define MACVTAP_RESERVE HH_DATA_OFF(ETH_HLEN)
 
@@ -812,7 +725,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	skb->protocol = eth_hdr(skb)->h_proto;
 
 	if (vnet_hdr_len) {
-		err = macvtap_skb_from_vnet_hdr(q, skb, &vnet_hdr);
+		err = virtio_net_hdr_to_skb(skb, &vnet_hdr,
+					    macvtap_is_little_endian(q));
 		if (err)
 			goto err_kfree;
 	}
@@ -880,7 +794,10 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 		if (iov_iter_count(iter) < vnet_hdr_len)
 			return -EINVAL;
 
-		macvtap_skb_to_vnet_hdr(q, skb, &vnet_hdr);
+		ret = virtio_net_hdr_from_skb(skb, &vnet_hdr,
+					      macvtap_is_little_endian(q));
+		if (ret)
+			BUG();
 
 		if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
 		    sizeof(vnet_hdr))
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 6dad9a9c356c..f96829415ce6 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -12,6 +12,9 @@ menuconfig PHYLIB
 
 if PHYLIB
 
+config SWPHY
+	bool
+
 comment "MII PHY device drivers"
 
 config AQUANTIA_PHY
@@ -159,6 +162,7 @@ config MICROCHIP_PHY
 config FIXED_PHY
 	tristate "Driver for MDIO Bus/PHY emulation with fixed speed/link PHYs"
 	depends on PHYLIB
+	select SWPHY
 	---help---
 	  Adds the platform "fixed" MDIO Bus to cover the boards that use
 	  PHYs that are not connected to the real MDIO bus.
@@ -254,6 +258,17 @@ config MDIO_BUS_MUX_MMIOREG
 
 	  Currently, only 8-bit registers are supported.
 
+config MDIO_BUS_MUX_BCM_IPROC
+	tristate "Support for iProc based MDIO bus multiplexers"
+	depends on OF && OF_MDIO && (ARCH_BCM_IPROC || COMPILE_TEST)
+	select MDIO_BUS_MUX
+	default ARCH_BCM_IPROC
+	help
+	  This module provides a driver for MDIO bus multiplexers found in
+	  iProc based Broadcom SoCs. This multiplexer connects one of several
+	  child MDIO bus to a parent bus. Buses could be internal as well as
+	  external and selection logic lies inside the same multiplexer.
+
 config MDIO_BCM_UNIMAC
 	tristate "Broadcom UniMAC MDIO bus controller"
 	depends on HAS_IOMEM
@@ -271,6 +286,14 @@ config MDIO_BCM_IPROC
 	  This module provides a driver for the MDIO busses found in the
 	  Broadcom iProc SoC's.
 
+config INTEL_XWAY_PHY
+	tristate "Driver for Intel XWAY PHYs"
+	---help---
+	  Supports the Intel XWAY (former Lantiq) 11G and 22E PHYs.
+	  These PHYs are marked as standalone chips under the names
+	  PEF 7061, PEF 7071 and PEF 7072 or integrated into the Intel
+	  SoCs xRX200, xRX300, xRX330, xRX350 and xRX550.
+
 endif # PHYLIB
 
 config MICREL_KS8995MA
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index fcdbb9299fab..7158274327d0 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -1,6 +1,7 @@
 # Makefile for Linux PHY drivers
 
-libphy-objs			:= phy.o phy_device.o mdio_bus.o mdio_device.o
+libphy-y			:= phy.o phy_device.o mdio_bus.o mdio_device.o
+libphy-$(CONFIG_SWPHY)		+= swphy.o
 
 obj-$(CONFIG_PHYLIB)		+= libphy.o
 obj-$(CONFIG_AQUANTIA_PHY)	+= aquantia.o
@@ -39,8 +40,10 @@ obj-$(CONFIG_AMD_PHY)		+= amd.o
 obj-$(CONFIG_MDIO_BUS_MUX)	+= mdio-mux.o
 obj-$(CONFIG_MDIO_BUS_MUX_GPIO)	+= mdio-mux-gpio.o
 obj-$(CONFIG_MDIO_BUS_MUX_MMIOREG) += mdio-mux-mmioreg.o
+obj-$(CONFIG_MDIO_BUS_MUX_BCM_IPROC)	+= mdio-mux-bcm-iproc.o
 obj-$(CONFIG_MDIO_SUN4I)	+= mdio-sun4i.o
 obj-$(CONFIG_MDIO_MOXART)	+= mdio-moxart.o
 obj-$(CONFIG_MDIO_BCM_UNIMAC)	+= mdio-bcm-unimac.o
 obj-$(CONFIG_MICROCHIP_PHY)	+= microchip.o
 obj-$(CONFIG_MDIO_BCM_IPROC)	+= mdio-bcm-iproc.o
+obj-$(CONFIG_INTEL_XWAY_PHY)	+= intel-xway.o
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 2d2e4339f0df..c649c101bbab 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -23,8 +23,10 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/gpio.h>
+#include <linux/seqlock.h>
+#include <linux/idr.h>
 
-#define MII_REGS_NUM 29
+#include "swphy.h"
 
 struct fixed_mdio_bus {
 	struct mii_bus *mii_bus;
@@ -33,8 +35,8 @@ struct fixed_mdio_bus {
 
 struct fixed_phy {
 	int addr;
-	u16 regs[MII_REGS_NUM];
 	struct phy_device *phydev;
+	seqcount_t seqcount;
 	struct fixed_phy_status status;
 	int (*link_update)(struct net_device *, struct fixed_phy_status *);
 	struct list_head node;
@@ -46,103 +48,10 @@ static struct fixed_mdio_bus platform_fmb = {
 	.phys = LIST_HEAD_INIT(platform_fmb.phys),
 };
 
-static int fixed_phy_update_regs(struct fixed_phy *fp)
+static void fixed_phy_update(struct fixed_phy *fp)
 {
-	u16 bmsr = BMSR_ANEGCAPABLE;
-	u16 bmcr = 0;
-	u16 lpagb = 0;
-	u16 lpa = 0;
-
 	if (gpio_is_valid(fp->link_gpio))
 		fp->status.link = !!gpio_get_value_cansleep(fp->link_gpio);
-
-	if (fp->status.duplex) {
-		switch (fp->status.speed) {
-		case 1000:
-			bmsr |= BMSR_ESTATEN;
-			break;
-		case 100:
-			bmsr |= BMSR_100FULL;
-			break;
-		case 10:
-			bmsr |= BMSR_10FULL;
-			break;
-		default:
-			break;
-		}
-	} else {
-		switch (fp->status.speed) {
-		case 1000:
-			bmsr |= BMSR_ESTATEN;
-			break;
-		case 100:
-			bmsr |= BMSR_100HALF;
-			break;
-		case 10:
-			bmsr |= BMSR_10HALF;
-			break;
-		default:
-			break;
-		}
-	}
-
-	if (fp->status.link) {
-		bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE;
-
-		if (fp->status.duplex) {
-			bmcr |= BMCR_FULLDPLX;
-
-			switch (fp->status.speed) {
-			case 1000:
-				bmcr |= BMCR_SPEED1000;
-				lpagb |= LPA_1000FULL;
-				break;
-			case 100:
-				bmcr |= BMCR_SPEED100;
-				lpa |= LPA_100FULL;
-				break;
-			case 10:
-				lpa |= LPA_10FULL;
-				break;
-			default:
-				pr_warn("fixed phy: unknown speed\n");
-				return -EINVAL;
-			}
-		} else {
-			switch (fp->status.speed) {
-			case 1000:
-				bmcr |= BMCR_SPEED1000;
-				lpagb |= LPA_1000HALF;
-				break;
-			case 100:
-				bmcr |= BMCR_SPEED100;
-				lpa |= LPA_100HALF;
-				break;
-			case 10:
-				lpa |= LPA_10HALF;
-				break;
-			default:
-				pr_warn("fixed phy: unknown speed\n");
-			return -EINVAL;
-			}
-		}
-
-		if (fp->status.pause)
-			lpa |= LPA_PAUSE_CAP;
-
-		if (fp->status.asym_pause)
-			lpa |= LPA_PAUSE_ASYM;
-	}
-
-	fp->regs[MII_PHYSID1] = 0;
-	fp->regs[MII_PHYSID2] = 0;
-
-	fp->regs[MII_BMSR] = bmsr;
-	fp->regs[MII_BMCR] = bmcr;
-	fp->regs[MII_LPA] = lpa;
-	fp->regs[MII_STAT1000] = lpagb;
-
-	return 0;
 }
 
 static int fixed_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num)
@@ -150,29 +59,23 @@ static int fixed_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num)
 	struct fixed_mdio_bus *fmb = bus->priv;
 	struct fixed_phy *fp;
 
-	if (reg_num >= MII_REGS_NUM)
-		return -1;
-
-	/* We do not support emulating Clause 45 over Clause 22 register reads
-	 * return an error instead of bogus data.
-	 */
-	switch (reg_num) {
-	case MII_MMD_CTRL:
-	case MII_MMD_DATA:
-		return -1;
-	default:
-		break;
-	}
-
 	list_for_each_entry(fp, &fmb->phys, node) {
 		if (fp->addr == phy_addr) {
-			/* Issue callback if user registered it. */
-			if (fp->link_update) {
-				fp->link_update(fp->phydev->attached_dev,
-						&fp->status);
-				fixed_phy_update_regs(fp);
-			}
-			return fp->regs[reg_num];
+			struct fixed_phy_status state;
+			int s;
+
+			do {
+				s = read_seqcount_begin(&fp->seqcount);
+				/* Issue callback if user registered it. */
+				if (fp->link_update) {
+					fp->link_update(fp->phydev->attached_dev,
+							&fp->status);
+					fixed_phy_update(fp);
+				}
+				state = fp->status;
+			} while (read_seqcount_retry(&fp->seqcount, s));
+
+			return swphy_read_reg(reg_num, &state);
 		}
 	}
 
@@ -224,6 +127,7 @@ int fixed_phy_update_state(struct phy_device *phydev,
 
 	list_for_each_entry(fp, &fmb->phys, node) {
 		if (fp->addr == phydev->mdio.addr) {
+			write_seqcount_begin(&fp->seqcount);
 #define _UPD(x) if (changed->x) \
 	fp->status.x = status->x
 			_UPD(link);
@@ -232,7 +136,8 @@ int fixed_phy_update_state(struct phy_device *phydev,
 			_UPD(pause);
 			_UPD(asym_pause);
 #undef _UPD
-			fixed_phy_update_regs(fp);
+			fixed_phy_update(fp);
+			write_seqcount_end(&fp->seqcount);
 			return 0;
 		}
 	}
@@ -249,11 +154,15 @@ int fixed_phy_add(unsigned int irq, int phy_addr,
 	struct fixed_mdio_bus *fmb = &platform_fmb;
 	struct fixed_phy *fp;
 
+	ret = swphy_validate_state(status);
+	if (ret < 0)
+		return ret;
+
 	fp = kzalloc(sizeof(*fp), GFP_KERNEL);
 	if (!fp)
 		return -ENOMEM;
 
-	memset(fp->regs, 0xFF,  sizeof(fp->regs[0]) * MII_REGS_NUM);
+	seqcount_init(&fp->seqcount);
 
 	if (irq != PHY_POLL)
 		fmb->mii_bus->irq[phy_addr] = irq;
@@ -269,23 +178,20 @@ int fixed_phy_add(unsigned int irq, int phy_addr,
 			goto err_regs;
 	}
 
-	ret = fixed_phy_update_regs(fp);
-	if (ret)
-		goto err_gpio;
+	fixed_phy_update(fp);
 
 	list_add_tail(&fp->node, &fmb->phys);
 
 	return 0;
 
-err_gpio:
-	if (gpio_is_valid(fp->link_gpio))
-		gpio_free(fp->link_gpio);
 err_regs:
 	kfree(fp);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(fixed_phy_add);
 
+static DEFINE_IDA(phy_fixed_ida);
+
 static void fixed_phy_del(int phy_addr)
 {
 	struct fixed_mdio_bus *fmb = &platform_fmb;
@@ -297,14 +203,12 @@ static void fixed_phy_del(int phy_addr)
 			if (gpio_is_valid(fp->link_gpio))
 				gpio_free(fp->link_gpio);
 			kfree(fp);
+			ida_simple_remove(&phy_fixed_ida, phy_addr);
 			return;
 		}
 	}
 }
 
-static int phy_fixed_addr;
-static DEFINE_SPINLOCK(phy_fixed_addr_lock);
-
 struct phy_device *fixed_phy_register(unsigned int irq,
 				      struct fixed_phy_status *status,
 				      int link_gpio,
@@ -319,17 +223,15 @@ struct phy_device *fixed_phy_register(unsigned int irq,
 		return ERR_PTR(-EPROBE_DEFER);
 
 	/* Get the next available PHY address, up to PHY_MAX_ADDR */
-	spin_lock(&phy_fixed_addr_lock);
-	if (phy_fixed_addr == PHY_MAX_ADDR) {
-		spin_unlock(&phy_fixed_addr_lock);
-		return ERR_PTR(-ENOSPC);
-	}
-	phy_addr = phy_fixed_addr++;
-	spin_unlock(&phy_fixed_addr_lock);
+	phy_addr = ida_simple_get(&phy_fixed_ida, 0, PHY_MAX_ADDR, GFP_KERNEL);
+	if (phy_addr < 0)
+		return ERR_PTR(phy_addr);
 
 	ret = fixed_phy_add(irq, phy_addr, status, link_gpio);
-	if (ret < 0)
+	if (ret < 0) {
+		ida_simple_remove(&phy_fixed_ida, phy_addr);
 		return ERR_PTR(ret);
+	}
 
 	phy = get_phy_device(fmb->mii_bus, phy_addr, false);
 	if (IS_ERR(phy)) {
@@ -434,6 +336,7 @@ static void __exit fixed_mdio_bus_exit(void)
 		list_del(&fp->node);
 		kfree(fp);
 	}
+	ida_destroy(&phy_fixed_ida);
 }
 module_exit(fixed_mdio_bus_exit);
 
diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c
new file mode 100644
index 000000000000..c300ab5587b8
--- /dev/null
+++ b/drivers/net/phy/intel-xway.c
@@ -0,0 +1,376 @@
+/*
+ * Copyright (C) 2012 Daniel Schwierzeck <[email protected]>
+ * Copyright (C) 2016 Hauke Mehrtens <[email protected]>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/mdio.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/of.h>
+
+#define XWAY_MDIO_IMASK			0x19	/* interrupt mask */
+#define XWAY_MDIO_ISTAT			0x1A	/* interrupt status */
+
+#define XWAY_MDIO_INIT_WOL		BIT(15)	/* Wake-On-LAN */
+#define XWAY_MDIO_INIT_MSRE		BIT(14)
+#define XWAY_MDIO_INIT_NPRX		BIT(13)
+#define XWAY_MDIO_INIT_NPTX		BIT(12)
+#define XWAY_MDIO_INIT_ANE		BIT(11)	/* Auto-Neg error */
+#define XWAY_MDIO_INIT_ANC		BIT(10)	/* Auto-Neg complete */
+#define XWAY_MDIO_INIT_ADSC		BIT(5)	/* Link auto-downspeed detect */
+#define XWAY_MDIO_INIT_MPIPC		BIT(4)
+#define XWAY_MDIO_INIT_MDIXC		BIT(3)
+#define XWAY_MDIO_INIT_DXMC		BIT(2)	/* Duplex mode change */
+#define XWAY_MDIO_INIT_LSPC		BIT(1)	/* Link speed change */
+#define XWAY_MDIO_INIT_LSTC		BIT(0)	/* Link state change */
+#define XWAY_MDIO_INIT_MASK		(XWAY_MDIO_INIT_LSTC | \
+					 XWAY_MDIO_INIT_ADSC)
+
+#define ADVERTISED_MPD			BIT(10)	/* Multi-port device */
+
+/* LED Configuration */
+#define XWAY_MMD_LEDCH			0x01E0
+/* Inverse of SCAN Function */
+#define  XWAY_MMD_LEDCH_NACS_NONE	0x0000
+#define  XWAY_MMD_LEDCH_NACS_LINK	0x0001
+#define  XWAY_MMD_LEDCH_NACS_PDOWN	0x0002
+#define  XWAY_MMD_LEDCH_NACS_EEE	0x0003
+#define  XWAY_MMD_LEDCH_NACS_ANEG	0x0004
+#define  XWAY_MMD_LEDCH_NACS_ABIST	0x0005
+#define  XWAY_MMD_LEDCH_NACS_CDIAG	0x0006
+#define  XWAY_MMD_LEDCH_NACS_TEST	0x0007
+/* Slow Blink Frequency */
+#define  XWAY_MMD_LEDCH_SBF_F02HZ	0x0000
+#define  XWAY_MMD_LEDCH_SBF_F04HZ	0x0010
+#define  XWAY_MMD_LEDCH_SBF_F08HZ	0x0020
+#define  XWAY_MMD_LEDCH_SBF_F16HZ	0x0030
+/* Fast Blink Frequency */
+#define  XWAY_MMD_LEDCH_FBF_F02HZ	0x0000
+#define  XWAY_MMD_LEDCH_FBF_F04HZ	0x0040
+#define  XWAY_MMD_LEDCH_FBF_F08HZ	0x0080
+#define  XWAY_MMD_LEDCH_FBF_F16HZ	0x00C0
+/* LED Configuration */
+#define XWAY_MMD_LEDCL			0x01E1
+/* Complex Blinking Configuration */
+#define  XWAY_MMD_LEDCH_CBLINK_NONE	0x0000
+#define  XWAY_MMD_LEDCH_CBLINK_LINK	0x0001
+#define  XWAY_MMD_LEDCH_CBLINK_PDOWN	0x0002
+#define  XWAY_MMD_LEDCH_CBLINK_EEE	0x0003
+#define  XWAY_MMD_LEDCH_CBLINK_ANEG	0x0004
+#define  XWAY_MMD_LEDCH_CBLINK_ABIST	0x0005
+#define  XWAY_MMD_LEDCH_CBLINK_CDIAG	0x0006
+#define  XWAY_MMD_LEDCH_CBLINK_TEST	0x0007
+/* Complex SCAN Configuration */
+#define  XWAY_MMD_LEDCH_SCAN_NONE	0x0000
+#define  XWAY_MMD_LEDCH_SCAN_LINK	0x0010
+#define  XWAY_MMD_LEDCH_SCAN_PDOWN	0x0020
+#define  XWAY_MMD_LEDCH_SCAN_EEE	0x0030
+#define  XWAY_MMD_LEDCH_SCAN_ANEG	0x0040
+#define  XWAY_MMD_LEDCH_SCAN_ABIST	0x0050
+#define  XWAY_MMD_LEDCH_SCAN_CDIAG	0x0060
+#define  XWAY_MMD_LEDCH_SCAN_TEST	0x0070
+/* Configuration for LED Pin x */
+#define XWAY_MMD_LED0H			0x01E2
+/* Fast Blinking Configuration */
+#define  XWAY_MMD_LEDxH_BLINKF_MASK	0x000F
+#define  XWAY_MMD_LEDxH_BLINKF_NONE	0x0000
+#define  XWAY_MMD_LEDxH_BLINKF_LINK10	0x0001
+#define  XWAY_MMD_LEDxH_BLINKF_LINK100	0x0002
+#define  XWAY_MMD_LEDxH_BLINKF_LINK10X	0x0003
+#define  XWAY_MMD_LEDxH_BLINKF_LINK1000	0x0004
+#define  XWAY_MMD_LEDxH_BLINKF_LINK10_0	0x0005
+#define  XWAY_MMD_LEDxH_BLINKF_LINK100X	0x0006
+#define  XWAY_MMD_LEDxH_BLINKF_LINK10XX	0x0007
+#define  XWAY_MMD_LEDxH_BLINKF_PDOWN	0x0008
+#define  XWAY_MMD_LEDxH_BLINKF_EEE	0x0009
+#define  XWAY_MMD_LEDxH_BLINKF_ANEG	0x000A
+#define  XWAY_MMD_LEDxH_BLINKF_ABIST	0x000B
+#define  XWAY_MMD_LEDxH_BLINKF_CDIAG	0x000C
+/* Constant On Configuration */
+#define  XWAY_MMD_LEDxH_CON_MASK	0x00F0
+#define  XWAY_MMD_LEDxH_CON_NONE	0x0000
+#define  XWAY_MMD_LEDxH_CON_LINK10	0x0010
+#define  XWAY_MMD_LEDxH_CON_LINK100	0x0020
+#define  XWAY_MMD_LEDxH_CON_LINK10X	0x0030
+#define  XWAY_MMD_LEDxH_CON_LINK1000	0x0040
+#define  XWAY_MMD_LEDxH_CON_LINK10_0	0x0050
+#define  XWAY_MMD_LEDxH_CON_LINK100X	0x0060
+#define  XWAY_MMD_LEDxH_CON_LINK10XX	0x0070
+#define  XWAY_MMD_LEDxH_CON_PDOWN	0x0080
+#define  XWAY_MMD_LEDxH_CON_EEE		0x0090
+#define  XWAY_MMD_LEDxH_CON_ANEG	0x00A0
+#define  XWAY_MMD_LEDxH_CON_ABIST	0x00B0
+#define  XWAY_MMD_LEDxH_CON_CDIAG	0x00C0
+#define  XWAY_MMD_LEDxH_CON_COPPER	0x00D0
+#define  XWAY_MMD_LEDxH_CON_FIBER	0x00E0
+/* Configuration for LED Pin x */
+#define XWAY_MMD_LED0L			0x01E3
+/* Pulsing Configuration */
+#define  XWAY_MMD_LEDxL_PULSE_MASK	0x000F
+#define  XWAY_MMD_LEDxL_PULSE_NONE	0x0000
+#define  XWAY_MMD_LEDxL_PULSE_TXACT	0x0001
+#define  XWAY_MMD_LEDxL_PULSE_RXACT	0x0002
+#define  XWAY_MMD_LEDxL_PULSE_COL	0x0004
+/* Slow Blinking Configuration */
+#define  XWAY_MMD_LEDxL_BLINKS_MASK	0x00F0
+#define  XWAY_MMD_LEDxL_BLINKS_NONE	0x0000
+#define  XWAY_MMD_LEDxL_BLINKS_LINK10	0x0010
+#define  XWAY_MMD_LEDxL_BLINKS_LINK100	0x0020
+#define  XWAY_MMD_LEDxL_BLINKS_LINK10X	0x0030
+#define  XWAY_MMD_LEDxL_BLINKS_LINK1000	0x0040
+#define  XWAY_MMD_LEDxL_BLINKS_LINK10_0	0x0050
+#define  XWAY_MMD_LEDxL_BLINKS_LINK100X	0x0060
+#define  XWAY_MMD_LEDxL_BLINKS_LINK10XX	0x0070
+#define  XWAY_MMD_LEDxL_BLINKS_PDOWN	0x0080
+#define  XWAY_MMD_LEDxL_BLINKS_EEE	0x0090
+#define  XWAY_MMD_LEDxL_BLINKS_ANEG	0x00A0
+#define  XWAY_MMD_LEDxL_BLINKS_ABIST	0x00B0
+#define  XWAY_MMD_LEDxL_BLINKS_CDIAG	0x00C0
+#define XWAY_MMD_LED1H			0x01E4
+#define XWAY_MMD_LED1L			0x01E5
+#define XWAY_MMD_LED2H			0x01E6
+#define XWAY_MMD_LED2L			0x01E7
+#define XWAY_MMD_LED3H			0x01E8
+#define XWAY_MMD_LED3L			0x01E9
+
+#define PHY_ID_PHY11G_1_3		0x030260D1
+#define PHY_ID_PHY22F_1_3		0x030260E1
+#define PHY_ID_PHY11G_1_4		0xD565A400
+#define PHY_ID_PHY22F_1_4		0xD565A410
+#define PHY_ID_PHY11G_1_5		0xD565A401
+#define PHY_ID_PHY22F_1_5		0xD565A411
+#define PHY_ID_PHY11G_VR9		0xD565A409
+#define PHY_ID_PHY22F_VR9		0xD565A419
+
+static int xway_gphy_config_init(struct phy_device *phydev)
+{
+	int err;
+	u32 ledxh;
+	u32 ledxl;
+
+	/* Mask all interrupts */
+	err = phy_write(phydev, XWAY_MDIO_IMASK, 0);
+	if (err)
+		return err;
+
+	/* Clear all pending interrupts */
+	phy_read(phydev, XWAY_MDIO_ISTAT);
+
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LEDCH, MDIO_MMD_VEND2,
+			       XWAY_MMD_LEDCH_NACS_NONE |
+			       XWAY_MMD_LEDCH_SBF_F02HZ |
+			       XWAY_MMD_LEDCH_FBF_F16HZ);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LEDCL, MDIO_MMD_VEND2,
+			       XWAY_MMD_LEDCH_CBLINK_NONE |
+			       XWAY_MMD_LEDCH_SCAN_NONE);
+
+	/**
+	 * In most cases only one LED is connected to this phy, so
+	 * configure them all to constant on and pulse mode. LED3 is
+	 * only available in some packages, leave it in its reset
+	 * configuration.
+	 */
+	ledxh = XWAY_MMD_LEDxH_BLINKF_NONE | XWAY_MMD_LEDxH_CON_LINK10XX;
+	ledxl = XWAY_MMD_LEDxL_PULSE_TXACT | XWAY_MMD_LEDxL_PULSE_RXACT |
+		XWAY_MMD_LEDxL_BLINKS_NONE;
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED0H, MDIO_MMD_VEND2, ledxh);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED0L, MDIO_MMD_VEND2, ledxl);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED1H, MDIO_MMD_VEND2, ledxh);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED1L, MDIO_MMD_VEND2, ledxl);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED2H, MDIO_MMD_VEND2, ledxh);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED2L, MDIO_MMD_VEND2, ledxl);
+
+	return 0;
+}
+
+static int xway_gphy14_config_aneg(struct phy_device *phydev)
+{
+	int reg, err;
+
+	/* Advertise as multi-port device, see IEEE802.3-2002 40.5.1.1 */
+	/* This is a workaround for an errata in rev < 1.5 devices */
+	reg = phy_read(phydev, MII_CTRL1000);
+	reg |= ADVERTISED_MPD;
+	err = phy_write(phydev, MII_CTRL1000, reg);
+	if (err)
+		return err;
+
+	return genphy_config_aneg(phydev);
+}
+
+static int xway_gphy_ack_interrupt(struct phy_device *phydev)
+{
+	int reg;
+
+	reg = phy_read(phydev, XWAY_MDIO_ISTAT);
+	return (reg < 0) ? reg : 0;
+}
+
+static int xway_gphy_did_interrupt(struct phy_device *phydev)
+{
+	int reg;
+
+	reg = phy_read(phydev, XWAY_MDIO_ISTAT);
+	return reg & XWAY_MDIO_INIT_MASK;
+}
+
+static int xway_gphy_config_intr(struct phy_device *phydev)
+{
+	u16 mask = 0;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		mask = XWAY_MDIO_INIT_MASK;
+
+	return phy_write(phydev, XWAY_MDIO_IMASK, mask);
+}
+
+static struct phy_driver xway_gphy[] = {
+	{
+		.phy_id		= PHY_ID_PHY11G_1_3,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.3",
+		.features	= (PHY_GBIT_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= xway_gphy14_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY22F_1_3,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY22F (PEF 7061) v1.3",
+		.features	= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= xway_gphy14_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY11G_1_4,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.4",
+		.features	= (PHY_GBIT_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= xway_gphy14_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY22F_1_4,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY22F (PEF 7061) v1.4",
+		.features	= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= xway_gphy14_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY11G_1_5,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.5 / v1.6",
+		.features	= (PHY_GBIT_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= genphy_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY22F_1_5,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY22F (PEF 7061) v1.5 / v1.6",
+		.features	= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= genphy_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY11G_VR9,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY11G (xRX integrated)",
+		.features	= (PHY_GBIT_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= genphy_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY22F_VR9,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY22F (xRX integrated)",
+		.features	= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= genphy_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	},
+};
+module_phy_driver(xway_gphy);
+
+static struct mdio_device_id __maybe_unused xway_gphy_tbl[] = {
+	{ PHY_ID_PHY11G_1_3, 0xffffffff },
+	{ PHY_ID_PHY22F_1_3, 0xffffffff },
+	{ PHY_ID_PHY11G_1_4, 0xffffffff },
+	{ PHY_ID_PHY22F_1_4, 0xffffffff },
+	{ PHY_ID_PHY11G_1_5, 0xffffffff },
+	{ PHY_ID_PHY22F_1_5, 0xffffffff },
+	{ PHY_ID_PHY11G_VR9, 0xffffffff },
+	{ PHY_ID_PHY22F_VR9, 0xffffffff },
+	{ }
+};
+MODULE_DEVICE_TABLE(mdio, xway_gphy_tbl);
+
+MODULE_DESCRIPTION("Intel XWAY PHY driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 280e8795b463..ec2c1eee6405 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -285,6 +285,48 @@ static int marvell_config_aneg(struct phy_device *phydev)
 	return 0;
 }
 
+static int m88e1111_config_aneg(struct phy_device *phydev)
+{
+	int err;
+
+	/* The Marvell PHY has an errata which requires
+	 * that certain registers get written in order
+	 * to restart autonegotiation
+	 */
+	err = phy_write(phydev, MII_BMCR, BMCR_RESET);
+
+	err = marvell_set_polarity(phydev, phydev->mdix);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, MII_M1111_PHY_LED_CONTROL,
+			MII_M1111_PHY_LED_DIRECT);
+	if (err < 0)
+		return err;
+
+	err = genphy_config_aneg(phydev);
+	if (err < 0)
+		return err;
+
+	if (phydev->autoneg != AUTONEG_ENABLE) {
+		int bmcr;
+
+		/* A write to speed/duplex bits (that is performed by
+		 * genphy_config_aneg() call above) must be followed by
+		 * a software reset. Otherwise, the write has no effect.
+		 */
+		bmcr = phy_read(phydev, MII_BMCR);
+		if (bmcr < 0)
+			return bmcr;
+
+		err = phy_write(phydev, MII_BMCR, bmcr | BMCR_RESET);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_OF_MDIO
 /*
  * Set and/or override some configuration registers based on the
@@ -407,15 +449,7 @@ static int m88e1121_config_aneg(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
-	oldpage = phy_read(phydev, MII_MARVELL_PHY_PAGE);
-
-	phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_88E1121_PHY_LED_PAGE);
-	phy_write(phydev, MII_88E1121_PHY_LED_CTRL, MII_88E1121_PHY_LED_DEF);
-	phy_write(phydev, MII_MARVELL_PHY_PAGE, oldpage);
-
-	err = genphy_config_aneg(phydev);
-
-	return err;
+	return genphy_config_aneg(phydev);
 }
 
 static int m88e1318_config_aneg(struct phy_device *phydev)
@@ -636,6 +670,28 @@ static int m88e1111_config_init(struct phy_device *phydev)
 	return phy_write(phydev, MII_BMCR, BMCR_RESET);
 }
 
+static int m88e1121_config_init(struct phy_device *phydev)
+{
+	int err, oldpage;
+
+	oldpage = phy_read(phydev, MII_MARVELL_PHY_PAGE);
+
+	err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_88E1121_PHY_LED_PAGE);
+	if (err < 0)
+		return err;
+
+	/* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */
+	err = phy_write(phydev, MII_88E1121_PHY_LED_CTRL,
+			MII_88E1121_PHY_LED_DEF);
+	if (err < 0)
+		return err;
+
+	phy_write(phydev, MII_MARVELL_PHY_PAGE, oldpage);
+
+	/* Set marvell,reg-init configuration from device tree */
+	return marvell_config_init(phydev);
+}
+
 static int m88e1510_config_init(struct phy_device *phydev)
 {
 	int err;
@@ -668,7 +724,7 @@ static int m88e1510_config_init(struct phy_device *phydev)
 			return err;
 	}
 
-	return marvell_config_init(phydev);
+	return m88e1121_config_init(phydev);
 }
 
 static int m88e1118_config_aneg(struct phy_device *phydev)
@@ -1161,7 +1217,7 @@ static struct phy_driver marvell_drivers[] = {
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &m88e1111_config_init,
-		.config_aneg = &marvell_config_aneg,
+		.config_aneg = &m88e1111_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
 		.config_intr = &marvell_config_intr,
@@ -1196,7 +1252,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
-		.config_init = &marvell_config_init,
+		.config_init = &m88e1121_config_init,
 		.config_aneg = &m88e1121_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
@@ -1215,7 +1271,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
-		.config_init = &marvell_config_init,
+		.config_init = &m88e1121_config_init,
 		.config_aneg = &m88e1318_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
new file mode 100644
index 000000000000..0a0412524cec
--- /dev/null
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -0,0 +1,248 @@
+/*
+ * Copyright 2016 Broadcom
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation (the "GPL").
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License version 2 (GPLv2) for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 (GPLv2) along with this source code.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/device.h>
+#include <linux/of_mdio.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/mdio-mux.h>
+#include <linux/delay.h>
+
+#define MDIO_PARAM_OFFSET		0x00
+#define MDIO_PARAM_MIIM_CYCLE		29
+#define MDIO_PARAM_INTERNAL_SEL		25
+#define MDIO_PARAM_BUS_ID		22
+#define MDIO_PARAM_C45_SEL		21
+#define MDIO_PARAM_PHY_ID		16
+#define MDIO_PARAM_PHY_DATA		0
+
+#define MDIO_READ_OFFSET		0x04
+#define MDIO_READ_DATA_MASK		0xffff
+#define MDIO_ADDR_OFFSET		0x08
+
+#define MDIO_CTRL_OFFSET		0x0C
+#define MDIO_CTRL_WRITE_OP		0x1
+#define MDIO_CTRL_READ_OP		0x2
+
+#define MDIO_STAT_OFFSET		0x10
+#define MDIO_STAT_DONE			1
+
+#define BUS_MAX_ADDR			32
+#define EXT_BUS_START_ADDR		16
+
+struct iproc_mdiomux_desc {
+	void *mux_handle;
+	void __iomem *base;
+	struct device *dev;
+	struct mii_bus *mii_bus;
+};
+
+static int iproc_mdio_wait_for_idle(void __iomem *base, bool result)
+{
+	unsigned int timeout = 1000; /* loop for 1s */
+	u32 val;
+
+	do {
+		val = readl(base + MDIO_STAT_OFFSET);
+		if ((val & MDIO_STAT_DONE) == result)
+			return 0;
+
+		usleep_range(1000, 2000);
+	} while (timeout--);
+
+	return -ETIMEDOUT;
+}
+
+/* start_miim_ops- Program and start MDIO transaction over mdio bus.
+ * @base: Base address
+ * @phyid: phyid of the selected bus.
+ * @reg: register offset to be read/written.
+ * @val :0 if read op else value to be written in @reg;
+ * @op: Operation that need to be carried out.
+ *      MDIO_CTRL_READ_OP: Read transaction.
+ *      MDIO_CTRL_WRITE_OP: Write transaction.
+ *
+ * Return value: Successful Read operation returns read reg values and write
+ *      operation returns 0. Failure operation returns negative error code.
+ */
+static int start_miim_ops(void __iomem *base,
+			  u16 phyid, u32 reg, u16 val, u32 op)
+{
+	u32 param;
+	int ret;
+
+	writel(0, base + MDIO_CTRL_OFFSET);
+	ret = iproc_mdio_wait_for_idle(base, 0);
+	if (ret)
+		goto err;
+
+	param = readl(base + MDIO_PARAM_OFFSET);
+	param |= phyid << MDIO_PARAM_PHY_ID;
+	param |= val << MDIO_PARAM_PHY_DATA;
+	if (reg & MII_ADDR_C45)
+		param |= BIT(MDIO_PARAM_C45_SEL);
+
+	writel(param, base + MDIO_PARAM_OFFSET);
+
+	writel(reg, base + MDIO_ADDR_OFFSET);
+
+	writel(op, base + MDIO_CTRL_OFFSET);
+
+	ret = iproc_mdio_wait_for_idle(base, 1);
+	if (ret)
+		goto err;
+
+	if (op == MDIO_CTRL_READ_OP)
+		ret = readl(base + MDIO_READ_OFFSET) & MDIO_READ_DATA_MASK;
+err:
+	return ret;
+}
+
+static int iproc_mdiomux_read(struct mii_bus *bus, int phyid, int reg)
+{
+	struct iproc_mdiomux_desc *md = bus->priv;
+	int ret;
+
+	ret = start_miim_ops(md->base, phyid, reg, 0, MDIO_CTRL_READ_OP);
+	if (ret < 0)
+		dev_err(&bus->dev, "mdiomux read operation failed!!!");
+
+	return ret;
+}
+
+static int iproc_mdiomux_write(struct mii_bus *bus,
+			       int phyid, int reg, u16 val)
+{
+	struct iproc_mdiomux_desc *md = bus->priv;
+	int ret;
+
+	/* Write val at reg offset */
+	ret = start_miim_ops(md->base, phyid, reg, val, MDIO_CTRL_WRITE_OP);
+	if (ret < 0)
+		dev_err(&bus->dev, "mdiomux write operation failed!!!");
+
+	return ret;
+}
+
+static int mdio_mux_iproc_switch_fn(int current_child, int desired_child,
+				    void *data)
+{
+	struct iproc_mdiomux_desc *md = data;
+	u32 param, bus_id;
+	bool bus_dir;
+
+	/* select bus and its properties */
+	bus_dir = (desired_child < EXT_BUS_START_ADDR);
+	bus_id = bus_dir ? desired_child : (desired_child - EXT_BUS_START_ADDR);
+
+	param = (bus_dir ? 1 : 0) << MDIO_PARAM_INTERNAL_SEL;
+	param |= (bus_id << MDIO_PARAM_BUS_ID);
+
+	writel(param, md->base + MDIO_PARAM_OFFSET);
+	return 0;
+}
+
+static int mdio_mux_iproc_probe(struct platform_device *pdev)
+{
+	struct iproc_mdiomux_desc *md;
+	struct mii_bus *bus;
+	struct resource *res;
+	int rc;
+
+	md = devm_kzalloc(&pdev->dev, sizeof(*md), GFP_KERNEL);
+	if (!md)
+		return -ENOMEM;
+	md->dev = &pdev->dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	md->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(md->base)) {
+		dev_err(&pdev->dev, "failed to ioremap register\n");
+		return PTR_ERR(md->base);
+	}
+
+	md->mii_bus = mdiobus_alloc();
+	if (!md->mii_bus) {
+		dev_err(&pdev->dev, "mdiomux bus alloc failed\n");
+		return -ENOMEM;
+	}
+
+	bus = md->mii_bus;
+	bus->priv = md;
+	bus->name = "iProc MDIO mux bus";
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d", pdev->name, pdev->id);
+	bus->parent = &pdev->dev;
+	bus->read = iproc_mdiomux_read;
+	bus->write = iproc_mdiomux_write;
+
+	bus->phy_mask = ~0;
+	bus->dev.of_node = pdev->dev.of_node;
+	rc = mdiobus_register(bus);
+	if (rc) {
+		dev_err(&pdev->dev, "mdiomux registration failed\n");
+		goto out;
+	}
+
+	platform_set_drvdata(pdev, md);
+
+	rc = mdio_mux_init(md->dev, mdio_mux_iproc_switch_fn,
+			   &md->mux_handle, md, md->mii_bus);
+	if (rc) {
+		dev_info(md->dev, "mdiomux initialization failed\n");
+		goto out;
+	}
+
+	dev_info(md->dev, "iProc mdiomux registered\n");
+	return 0;
+out:
+	mdiobus_free(bus);
+	return rc;
+}
+
+static int mdio_mux_iproc_remove(struct platform_device *pdev)
+{
+	struct iproc_mdiomux_desc *md = dev_get_platdata(&pdev->dev);
+
+	mdio_mux_uninit(md->mux_handle);
+	mdiobus_unregister(md->mii_bus);
+	mdiobus_free(md->mii_bus);
+
+	return 0;
+}
+
+static const struct of_device_id mdio_mux_iproc_match[] = {
+	{
+		.compatible = "brcm,mdio-mux-iproc",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, mdio_mux_iproc_match);
+
+static struct platform_driver mdiomux_iproc_driver = {
+	.driver = {
+		.name		= "mdio-mux-iproc",
+		.of_match_table = mdio_mux_iproc_match,
+	},
+	.probe		= mdio_mux_iproc_probe,
+	.remove		= mdio_mux_iproc_remove,
+};
+
+module_platform_driver(mdiomux_iproc_driver);
+
+MODULE_DESCRIPTION("iProc MDIO Mux Bus Driver");
+MODULE_AUTHOR("Pramod Kumar <[email protected]>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c
index 7ddb1ab70891..919949960a10 100644
--- a/drivers/net/phy/mdio-mux-gpio.c
+++ b/drivers/net/phy/mdio-mux-gpio.c
@@ -55,7 +55,7 @@ static int mdio_mux_gpio_probe(struct platform_device *pdev)
 		return PTR_ERR(s->gpios);
 
 	r = mdio_mux_init(&pdev->dev,
-			  mdio_mux_gpio_switch_fn, &s->mux_handle, s);
+			  mdio_mux_gpio_switch_fn, &s->mux_handle, s, NULL);
 
 	if (r != 0) {
 		gpiod_put_array(s->gpios);
diff --git a/drivers/net/phy/mdio-mux-mmioreg.c b/drivers/net/phy/mdio-mux-mmioreg.c
index 7fde454fbc4f..d0bed52c8d16 100644
--- a/drivers/net/phy/mdio-mux-mmioreg.c
+++ b/drivers/net/phy/mdio-mux-mmioreg.c
@@ -126,7 +126,7 @@ static int mdio_mux_mmioreg_probe(struct platform_device *pdev)
 	}
 
 	ret = mdio_mux_init(&pdev->dev, mdio_mux_mmioreg_switch_fn,
-			    &s->mux_handle, s);
+			    &s->mux_handle, s, NULL);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register mdio-mux bus %s\n",
 			np->full_name);
diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c
index 5c81d6faf304..963838d4fac1 100644
--- a/drivers/net/phy/mdio-mux.c
+++ b/drivers/net/phy/mdio-mux.c
@@ -89,7 +89,8 @@ static int parent_count;
 int mdio_mux_init(struct device *dev,
 		  int (*switch_fn)(int cur, int desired, void *data),
 		  void **mux_handle,
-		  void *data)
+		  void *data,
+		  struct mii_bus *mux_bus)
 {
 	struct device_node *parent_bus_node;
 	struct device_node *child_bus_node;
@@ -101,10 +102,22 @@ int mdio_mux_init(struct device *dev,
 	if (!dev->of_node)
 		return -ENODEV;
 
-	parent_bus_node = of_parse_phandle(dev->of_node, "mdio-parent-bus", 0);
+	if (!mux_bus) {
+		parent_bus_node = of_parse_phandle(dev->of_node,
+						   "mdio-parent-bus", 0);
 
-	if (!parent_bus_node)
-		return -ENODEV;
+		if (!parent_bus_node)
+			return -ENODEV;
+
+		parent_bus = of_mdio_find_bus(parent_bus_node);
+		if (!parent_bus) {
+			ret_val = -EPROBE_DEFER;
+			goto err_parent_bus;
+		}
+	} else {
+		parent_bus_node = NULL;
+		parent_bus = mux_bus;
+	}
 
 	pb = devm_kzalloc(dev, sizeof(*pb), GFP_KERNEL);
 	if (pb == NULL) {
@@ -112,11 +125,6 @@ int mdio_mux_init(struct device *dev,
 		goto err_parent_bus;
 	}
 
-	parent_bus = of_mdio_find_bus(parent_bus_node);
-	if (parent_bus == NULL) {
-		ret_val = -EPROBE_DEFER;
-		goto err_parent_bus;
-	}
 
 	pb->switch_data = data;
 	pb->switch_fn = switch_fn;
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 2e21e9366f76..b62c4aaee40b 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -75,22 +75,13 @@ static int smsc_phy_reset(struct phy_device *phydev)
 	 * in all capable mode before using it.
 	 */
 	if ((rc & MII_LAN83C185_MODE_MASK) == MII_LAN83C185_MODE_POWERDOWN) {
-		int timeout = 50000;
-
-		/* set "all capable" mode and reset the phy */
+		/* set "all capable" mode */
 		rc |= MII_LAN83C185_MODE_ALL;
 		phy_write(phydev, MII_LAN83C185_SPECIAL_MODES, rc);
-		phy_write(phydev, MII_BMCR, BMCR_RESET);
-
-		/* wait end of reset (max 500 ms) */
-		do {
-			udelay(10);
-			if (timeout-- == 0)
-				return -1;
-			rc = phy_read(phydev, MII_BMCR);
-		} while (rc & BMCR_RESET);
 	}
-	return 0;
+
+	/* reset the phy */
+	return genphy_soft_reset(phydev);
 }
 
 static int lan911x_config_init(struct phy_device *phydev)
diff --git a/drivers/net/phy/swphy.c b/drivers/net/phy/swphy.c
new file mode 100644
index 000000000000..34f58f2349e9
--- /dev/null
+++ b/drivers/net/phy/swphy.c
@@ -0,0 +1,179 @@
+/*
+ * Software PHY emulation
+ *
+ * Code taken from fixed_phy.c by Russell King <[email protected]>
+ *
+ * Author: Vitaly Bordug <[email protected]>
+ *         Anton Vorontsov <[email protected]>
+ *
+ * Copyright (c) 2006-2007 MontaVista Software, Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#include <linux/export.h>
+#include <linux/mii.h>
+#include <linux/phy.h>
+#include <linux/phy_fixed.h>
+
+#include "swphy.h"
+
+#define MII_REGS_NUM 29
+
+struct swmii_regs {
+	u16 bmcr;
+	u16 bmsr;
+	u16 lpa;
+	u16 lpagb;
+};
+
+enum {
+	SWMII_SPEED_10 = 0,
+	SWMII_SPEED_100,
+	SWMII_SPEED_1000,
+	SWMII_DUPLEX_HALF = 0,
+	SWMII_DUPLEX_FULL,
+};
+
+/*
+ * These two tables get bitwise-anded together to produce the final result.
+ * This means the speed table must contain both duplex settings, and the
+ * duplex table must contain all speed settings.
+ */
+static const struct swmii_regs speed[] = {
+	[SWMII_SPEED_10] = {
+		.bmcr  = BMCR_FULLDPLX,
+		.lpa   = LPA_10FULL | LPA_10HALF,
+	},
+	[SWMII_SPEED_100] = {
+		.bmcr  = BMCR_FULLDPLX | BMCR_SPEED100,
+		.bmsr  = BMSR_100FULL | BMSR_100HALF,
+		.lpa   = LPA_100FULL | LPA_100HALF,
+	},
+	[SWMII_SPEED_1000] = {
+		.bmcr  = BMCR_FULLDPLX | BMCR_SPEED1000,
+		.bmsr  = BMSR_ESTATEN,
+		.lpagb = LPA_1000FULL | LPA_1000HALF,
+	},
+};
+
+static const struct swmii_regs duplex[] = {
+	[SWMII_DUPLEX_HALF] = {
+		.bmcr  = ~BMCR_FULLDPLX,
+		.bmsr  = BMSR_ESTATEN | BMSR_100HALF,
+		.lpa   = LPA_10HALF | LPA_100HALF,
+		.lpagb = LPA_1000HALF,
+	},
+	[SWMII_DUPLEX_FULL] = {
+		.bmcr  = ~0,
+		.bmsr  = BMSR_ESTATEN | BMSR_100FULL,
+		.lpa   = LPA_10FULL | LPA_100FULL,
+		.lpagb = LPA_1000FULL,
+	},
+};
+
+static int swphy_decode_speed(int speed)
+{
+	switch (speed) {
+	case 1000:
+		return SWMII_SPEED_1000;
+	case 100:
+		return SWMII_SPEED_100;
+	case 10:
+		return SWMII_SPEED_10;
+	default:
+		return -EINVAL;
+	}
+}
+
+/**
+ * swphy_validate_state - validate the software phy status
+ * @state: software phy status
+ *
+ * This checks that we can represent the state stored in @state can be
+ * represented in the emulated MII registers.  Returns 0 if it can,
+ * otherwise returns -EINVAL.
+ */
+int swphy_validate_state(const struct fixed_phy_status *state)
+{
+	int err;
+
+	if (state->link) {
+		err = swphy_decode_speed(state->speed);
+		if (err < 0) {
+			pr_warn("swphy: unknown speed\n");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(swphy_validate_state);
+
+/**
+ * swphy_read_reg - return a MII register from the fixed phy state
+ * @reg: MII register
+ * @state: fixed phy status
+ *
+ * Return the MII @reg register generated from the fixed phy state @state.
+ */
+int swphy_read_reg(int reg, const struct fixed_phy_status *state)
+{
+	int speed_index, duplex_index;
+	u16 bmsr = BMSR_ANEGCAPABLE;
+	u16 bmcr = 0;
+	u16 lpagb = 0;
+	u16 lpa = 0;
+
+	if (reg > MII_REGS_NUM)
+		return -1;
+
+	speed_index = swphy_decode_speed(state->speed);
+	if (WARN_ON(speed_index < 0))
+		return 0;
+
+	duplex_index = state->duplex ? SWMII_DUPLEX_FULL : SWMII_DUPLEX_HALF;
+
+	bmsr |= speed[speed_index].bmsr & duplex[duplex_index].bmsr;
+
+	if (state->link) {
+		bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE;
+
+		bmcr  |= speed[speed_index].bmcr  & duplex[duplex_index].bmcr;
+		lpa   |= speed[speed_index].lpa   & duplex[duplex_index].lpa;
+		lpagb |= speed[speed_index].lpagb & duplex[duplex_index].lpagb;
+
+		if (state->pause)
+			lpa |= LPA_PAUSE_CAP;
+
+		if (state->asym_pause)
+			lpa |= LPA_PAUSE_ASYM;
+	}
+
+	switch (reg) {
+	case MII_BMCR:
+		return bmcr;
+	case MII_BMSR:
+		return bmsr;
+	case MII_PHYSID1:
+	case MII_PHYSID2:
+		return 0;
+	case MII_LPA:
+		return lpa;
+	case MII_STAT1000:
+		return lpagb;
+
+	/*
+	 * We do not support emulating Clause 45 over Clause 22 register
+	 * reads.  Return an error instead of bogus data.
+	 */
+	case MII_MMD_CTRL:
+	case MII_MMD_DATA:
+		return -1;
+
+	default:
+		return 0xffff;
+	}
+}
+EXPORT_SYMBOL_GPL(swphy_read_reg);
diff --git a/drivers/net/phy/swphy.h b/drivers/net/phy/swphy.h
new file mode 100644
index 000000000000..2f09ac324e18
--- /dev/null
+++ b/drivers/net/phy/swphy.h
@@ -0,0 +1,9 @@
+#ifndef SWPHY_H
+#define SWPHY_H
+
+struct fixed_phy_status;
+
+int swphy_validate_state(const struct fixed_phy_status *state);
+int swphy_read_reg(int reg, const struct fixed_phy_status *state);
+
+#endif
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 8dedafa1a95d..17953ab15000 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1312,10 +1312,9 @@ ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64)
 	return stats64;
 }
 
-static struct lock_class_key ppp_tx_busylock;
 static int ppp_dev_init(struct net_device *dev)
 {
-	dev->qdisc_tx_busylock = &ppp_tx_busylock;
+	netdev_lockdep_set_classes(dev);
 	return 0;
 }
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 2ace126533cd..a380649bf6b5 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1203,8 +1203,10 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 		goto err_dev_open;
 	}
 
+	netif_addr_lock_bh(dev);
 	dev_uc_sync_multiple(port_dev, dev);
 	dev_mc_sync_multiple(port_dev, dev);
+	netif_addr_unlock_bh(dev);
 
 	err = vlan_vids_add_by_dev(port_dev, dev);
 	if (err) {
@@ -1574,23 +1576,6 @@ static const struct team_option team_options[] = {
 	},
 };
 
-static struct lock_class_key team_netdev_xmit_lock_key;
-static struct lock_class_key team_netdev_addr_lock_key;
-static struct lock_class_key team_tx_busylock_key;
-
-static void team_set_lockdep_class_one(struct net_device *dev,
-				       struct netdev_queue *txq,
-				       void *unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &team_netdev_xmit_lock_key);
-}
-
-static void team_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &team_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, team_set_lockdep_class_one, NULL);
-	dev->qdisc_tx_busylock = &team_tx_busylock_key;
-}
 
 static int team_init(struct net_device *dev)
 {
@@ -1626,7 +1611,7 @@ static int team_init(struct net_device *dev)
 		goto err_options_register;
 	netif_carrier_off(dev);
 
-	team_set_lockdep_class(dev);
+	netdev_lockdep_set_classes(dev);
 
 	return 0;
 
@@ -2017,6 +2002,8 @@ static const struct net_device_ops team_netdev_ops = {
 	.ndo_add_slave		= team_add_slave,
 	.ndo_del_slave		= team_del_slave,
 	.ndo_fix_features	= team_fix_features,
+	.ndo_neigh_construct	= netdev_default_l2upper_neigh_construct,
+	.ndo_neigh_destroy	= netdev_default_l2upper_neigh_destroy,
 	.ndo_change_carrier     = team_change_carrier,
 	.ndo_bridge_setlink	= switchdev_port_bridge_setlink,
 	.ndo_bridge_getlink	= switchdev_port_bridge_getlink,
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e16487cc6a9a..5eadb7a1ad7b 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -71,6 +71,7 @@
 #include <net/sock.h>
 #include <linux/seq_file.h>
 #include <linux/uio.h>
+#include <linux/skb_array.h>
 
 #include <asm/uaccess.h>
 
@@ -167,6 +168,7 @@ struct tun_file {
 	};
 	struct list_head next;
 	struct tun_struct *detached;
+	struct skb_array tx_array;
 };
 
 struct tun_flow_entry {
@@ -515,7 +517,11 @@ static struct tun_struct *tun_enable_queue(struct tun_file *tfile)
 
 static void tun_queue_purge(struct tun_file *tfile)
 {
-	skb_queue_purge(&tfile->sk.sk_receive_queue);
+	struct sk_buff *skb;
+
+	while ((skb = skb_array_consume(&tfile->tx_array)) != NULL)
+		kfree_skb(skb);
+
 	skb_queue_purge(&tfile->sk.sk_error_queue);
 }
 
@@ -560,6 +566,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 			    tun->dev->reg_state == NETREG_REGISTERED)
 				unregister_netdevice(tun->dev);
 		}
+		if (tun)
+			skb_array_cleanup(&tfile->tx_array);
 		sock_put(&tfile->sk);
 	}
 }
@@ -613,6 +621,7 @@ static void tun_detach_all(struct net_device *dev)
 static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter)
 {
 	struct tun_file *tfile = file->private_data;
+	struct net_device *dev = tun->dev;
 	int err;
 
 	err = security_tun_dev_attach(tfile->socket.sk, tun->security);
@@ -642,6 +651,13 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 		if (!err)
 			goto out;
 	}
+
+	if (!tfile->detached &&
+	    skb_array_init(&tfile->tx_array, dev->tx_queue_len, GFP_KERNEL)) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	tfile->queue_index = tun->numqueues;
 	tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN;
 	rcu_assign_pointer(tfile->tun, tun);
@@ -891,8 +907,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	nf_reset(skb);
 
-	/* Enqueue packet */
-	skb_queue_tail(&tfile->socket.sk->sk_receive_queue, skb);
+	if (skb_array_produce(&tfile->tx_array, skb))
+		goto drop;
 
 	/* Notify and wake up reader process */
 	if (tfile->flags & TUN_FASYNC)
@@ -1107,7 +1123,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, sk_sleep(sk), wait);
 
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_array_empty(&tfile->tx_array))
 		mask |= POLLIN | POLLRDNORM;
 
 	if (sock_writeable(sk) ||
@@ -1254,13 +1270,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		return -EFAULT;
 	}
 
-	if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-		if (!skb_partial_csum_set(skb, tun16_to_cpu(tun, gso.csum_start),
-					  tun16_to_cpu(tun, gso.csum_offset))) {
-			this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
-			kfree_skb(skb);
-			return -EINVAL;
-		}
+	err = virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun));
+	if (err) {
+		this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
+		kfree_skb(skb);
+		return -EINVAL;
 	}
 
 	switch (tun->flags & TUN_TYPE_MASK) {
@@ -1289,39 +1303,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		break;
 	}
 
-	if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-		pr_debug("GSO!\n");
-		switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
-		case VIRTIO_NET_HDR_GSO_TCPV4:
-			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
-			break;
-		case VIRTIO_NET_HDR_GSO_TCPV6:
-			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
-			break;
-		case VIRTIO_NET_HDR_GSO_UDP:
-			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-			break;
-		default:
-			this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
-			kfree_skb(skb);
-			return -EINVAL;
-		}
-
-		if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN)
-			skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
-
-		skb_shinfo(skb)->gso_size = tun16_to_cpu(tun, gso.gso_size);
-		if (skb_shinfo(skb)->gso_size == 0) {
-			this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
-			kfree_skb(skb);
-			return -EINVAL;
-		}
-
-		/* Header must be checked, and gso_segs computed. */
-		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
-		skb_shinfo(skb)->gso_segs = 0;
-	}
-
 	/* copy skb_ubuf_info for callback when skb has no error */
 	if (zerocopy) {
 		skb_shinfo(skb)->destructor_arg = msg_control;
@@ -1399,46 +1380,26 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 
 	if (vnet_hdr_sz) {
 		struct virtio_net_hdr gso = { 0 }; /* no info leak */
+		int ret;
+
 		if (iov_iter_count(iter) < vnet_hdr_sz)
 			return -EINVAL;
 
-		if (skb_is_gso(skb)) {
+		ret = virtio_net_hdr_from_skb(skb, &gso,
+					      tun_is_little_endian(tun));
+		if (ret) {
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
-
-			/* This is a hint as to how much should be linear. */
-			gso.hdr_len = cpu_to_tun16(tun, skb_headlen(skb));
-			gso.gso_size = cpu_to_tun16(tun, sinfo->gso_size);
-			if (sinfo->gso_type & SKB_GSO_TCPV4)
-				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
-			else if (sinfo->gso_type & SKB_GSO_TCPV6)
-				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
-			else if (sinfo->gso_type & SKB_GSO_UDP)
-				gso.gso_type = VIRTIO_NET_HDR_GSO_UDP;
-			else {
-				pr_err("unexpected GSO type: "
-				       "0x%x, gso_size %d, hdr_len %d\n",
-				       sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size),
-				       tun16_to_cpu(tun, gso.hdr_len));
-				print_hex_dump(KERN_ERR, "tun: ",
-					       DUMP_PREFIX_NONE,
-					       16, 1, skb->head,
-					       min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true);
-				WARN_ON_ONCE(1);
-				return -EINVAL;
-			}
-			if (sinfo->gso_type & SKB_GSO_TCP_ECN)
-				gso.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
-		} else
-			gso.gso_type = VIRTIO_NET_HDR_GSO_NONE;
-
-		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-			gso.csum_start = cpu_to_tun16(tun, skb_checksum_start_offset(skb) +
-						      vlan_hlen);
-			gso.csum_offset = cpu_to_tun16(tun, skb->csum_offset);
-		} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-			gso.flags = VIRTIO_NET_HDR_F_DATA_VALID;
-		} /* else everything is zero */
+			pr_err("unexpected GSO type: "
+			       "0x%x, gso_size %d, hdr_len %d\n",
+			       sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size),
+			       tun16_to_cpu(tun, gso.hdr_len));
+			print_hex_dump(KERN_ERR, "tun: ",
+				       DUMP_PREFIX_NONE,
+				       16, 1, skb->head,
+				       min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true);
+			WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
 
 		if (copy_to_iter(&gso, sizeof(gso), iter) != sizeof(gso))
 			return -EFAULT;
@@ -1481,22 +1442,63 @@ done:
 	return total;
 }
 
+static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock,
+				     int *err)
+{
+	DECLARE_WAITQUEUE(wait, current);
+	struct sk_buff *skb = NULL;
+	int error = 0;
+
+	skb = skb_array_consume(&tfile->tx_array);
+	if (skb)
+		goto out;
+	if (noblock) {
+		error = -EAGAIN;
+		goto out;
+	}
+
+	add_wait_queue(&tfile->wq.wait, &wait);
+	current->state = TASK_INTERRUPTIBLE;
+
+	while (1) {
+		skb = skb_array_consume(&tfile->tx_array);
+		if (skb)
+			break;
+		if (signal_pending(current)) {
+			error = -ERESTARTSYS;
+			break;
+		}
+		if (tfile->socket.sk->sk_shutdown & RCV_SHUTDOWN) {
+			error = -EFAULT;
+			break;
+		}
+
+		schedule();
+	}
+
+	current->state = TASK_RUNNING;
+	remove_wait_queue(&tfile->wq.wait, &wait);
+
+out:
+	*err = error;
+	return skb;
+}
+
 static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 			   struct iov_iter *to,
 			   int noblock)
 {
 	struct sk_buff *skb;
 	ssize_t ret;
-	int peeked, err, off = 0;
+	int err;
 
 	tun_debug(KERN_INFO, tun, "tun_do_read\n");
 
 	if (!iov_iter_count(to))
 		return 0;
 
-	/* Read frames from queue */
-	skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0,
-				  &peeked, &off, &err);
+	/* Read frames from ring */
+	skb = tun_ring_recv(tfile, noblock, &err);
 	if (!skb)
 		return err;
 
@@ -1629,8 +1631,25 @@ out:
 	return ret;
 }
 
+static int tun_peek_len(struct socket *sock)
+{
+	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
+	struct tun_struct *tun;
+	int ret = 0;
+
+	tun = __tun_get(tfile);
+	if (!tun)
+		return 0;
+
+	ret = skb_array_peek_len(&tfile->tx_array);
+	tun_put(tun);
+
+	return ret;
+}
+
 /* Ops structure to mimic raw sockets with tun */
 static const struct proto_ops tun_socket_ops = {
+	.peek_len = tun_peek_len,
 	.sendmsg = tun_sendmsg,
 	.recvmsg = tun_recvmsg,
 };
@@ -2452,6 +2471,53 @@ static const struct ethtool_ops tun_ethtool_ops = {
 	.get_ts_info	= ethtool_op_get_ts_info,
 };
 
+static int tun_queue_resize(struct tun_struct *tun)
+{
+	struct net_device *dev = tun->dev;
+	struct tun_file *tfile;
+	struct skb_array **arrays;
+	int n = tun->numqueues + tun->numdisabled;
+	int ret, i;
+
+	arrays = kmalloc(sizeof *arrays * n, GFP_KERNEL);
+	if (!arrays)
+		return -ENOMEM;
+
+	for (i = 0; i < tun->numqueues; i++) {
+		tfile = rtnl_dereference(tun->tfiles[i]);
+		arrays[i] = &tfile->tx_array;
+	}
+	list_for_each_entry(tfile, &tun->disabled, next)
+		arrays[i++] = &tfile->tx_array;
+
+	ret = skb_array_resize_multiple(arrays, n,
+					dev->tx_queue_len, GFP_KERNEL);
+
+	kfree(arrays);
+	return ret;
+}
+
+static int tun_device_event(struct notifier_block *unused,
+			    unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct tun_struct *tun = netdev_priv(dev);
+
+	switch (event) {
+	case NETDEV_CHANGE_TX_QUEUE_LEN:
+		if (tun_queue_resize(tun))
+			return NOTIFY_BAD;
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block tun_notifier_block __read_mostly = {
+	.notifier_call	= tun_device_event,
+};
 
 static int __init tun_init(void)
 {
@@ -2471,6 +2537,8 @@ static int __init tun_init(void)
 		pr_err("Can't register misc device %d\n", TUN_MINOR);
 		goto err_misc;
 	}
+
+	register_netdevice_notifier(&tun_notifier_block);
 	return  0;
 err_misc:
 	rtnl_link_unregister(&tun_link_ops);
@@ -2482,6 +2550,7 @@ static void tun_cleanup(void)
 {
 	misc_deregister(&tun_miscdev);
 	rtnl_link_unregister(&tun_link_ops);
+	unregister_netdevice_notifier(&tun_notifier_block);
 }
 
 /* Get an underlying socket object from tun file.  Returns error unless file is
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 3f9f6ed3eec4..24d367280ecf 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -31,7 +31,7 @@
 #define NETNEXT_VERSION		"08"
 
 /* Information for net */
-#define NET_VERSION		"3"
+#define NET_VERSION		"4"
 
 #define DRIVER_VERSION		"v1." NETNEXT_VERSION "." NET_VERSION
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <[email protected]>"
@@ -116,6 +116,7 @@
 #define USB_TX_DMA		0xd434
 #define USB_TOLERANCE		0xd490
 #define USB_LPM_CTRL		0xd41a
+#define USB_BMU_RESET		0xd4b0
 #define USB_UPS_CTRL		0xd800
 #define USB_MISC_0		0xd81a
 #define USB_POWER_CUT		0xd80a
@@ -338,6 +339,10 @@
 #define TEST_MODE_DISABLE	0x00000001
 #define TX_SIZE_ADJUST1		0x00000100
 
+/* USB_BMU_RESET */
+#define BMU_RESET_EP_IN		0x01
+#define BMU_RESET_EP_OUT	0x02
+
 /* USB_UPS_CTRL */
 #define POWER_CUT		0x0100
 
@@ -602,7 +607,7 @@ struct r8152 {
 	struct list_head rx_done, tx_free;
 	struct sk_buff_head tx_queue, rx_queue;
 	spinlock_t rx_lock, tx_lock;
-	struct delayed_work schedule;
+	struct delayed_work schedule, hw_phy_work;
 	struct mii_if_info mii;
 	struct mutex control;	/* use for hw setting */
 #ifdef CONFIG_PM_SLEEP
@@ -619,6 +624,7 @@ struct r8152 {
 		int (*eee_get)(struct r8152 *, struct ethtool_eee *);
 		int (*eee_set)(struct r8152 *, struct ethtool_eee *);
 		bool (*in_nway)(struct r8152 *);
+		void (*hw_phy_cfg)(struct r8152 *);
 	} rtl_ops;
 
 	int intr_interval;
@@ -627,8 +633,11 @@ struct r8152 {
 	u32 tx_qlen;
 	u32 coalesce;
 	u16 ocp_base;
+	u16 speed;
 	u8 *intr_buff;
 	u8 version;
+	u8 duplex;
+	u8 autoneg;
 };
 
 enum rtl_version {
@@ -1742,7 +1751,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
 			pkt_len -= CRC_SIZE;
 			rx_data += sizeof(struct rx_desc);
 
-			skb = netdev_alloc_skb_ip_align(netdev, pkt_len);
+			skb = napi_alloc_skb(&tp->napi, pkt_len);
 			if (!skb) {
 				stats->rx_dropped++;
 				goto find_next_rx;
@@ -2169,7 +2178,7 @@ static void r8153_set_rx_early_timeout(struct r8152 *tp)
 static void r8153_set_rx_early_size(struct r8152 *tp)
 {
 	u32 mtu = tp->netdev->mtu;
-	u32 ocp_data = (agg_buf_sz - mtu - VLAN_ETH_HLEN - VLAN_HLEN) / 4;
+	u32 ocp_data = (agg_buf_sz - mtu - VLAN_ETH_HLEN - VLAN_HLEN) / 8;
 
 	ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EARLY_SIZE, ocp_data);
 }
@@ -2456,6 +2465,17 @@ static void r8153_teredo_off(struct r8152 *tp)
 	ocp_write_dword(tp, MCU_TYPE_PLA, PLA_TEREDO_TIMER, 0);
 }
 
+static void rtl_reset_bmu(struct r8152 *tp)
+{
+	u32 ocp_data;
+
+	ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_BMU_RESET);
+	ocp_data &= ~(BMU_RESET_EP_IN | BMU_RESET_EP_OUT);
+	ocp_write_byte(tp, MCU_TYPE_USB, USB_BMU_RESET, ocp_data);
+	ocp_data |= BMU_RESET_EP_IN | BMU_RESET_EP_OUT;
+	ocp_write_byte(tp, MCU_TYPE_USB, USB_BMU_RESET, ocp_data);
+}
+
 static void r8152_aldps_en(struct r8152 *tp, bool enable)
 {
 	if (enable) {
@@ -2499,8 +2519,6 @@ static void r8152b_exit_oob(struct r8152 *tp)
 
 	rxdy_gated_en(tp, true);
 	r8153_teredo_off(tp);
-	r8152b_hw_phy_cfg(tp);
-
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CR, 0x00);
 
@@ -2678,9 +2696,8 @@ static void r8153_first_init(struct r8152 *tp)
 	ocp_data &= ~RCR_ACPT_ALL;
 	ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data);
 
-	r8153_hw_phy_cfg(tp);
-
 	rtl8152_nic_reset(tp);
+	rtl_reset_bmu(tp);
 
 	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
 	ocp_data &= ~NOW_IS_OOB;
@@ -2742,6 +2759,7 @@ static void r8153_enter_oob(struct r8152 *tp)
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
 
 	rtl_disable(tp);
+	rtl_reset_bmu(tp);
 
 	for (i = 0; i < 1000; i++) {
 		ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
@@ -2803,6 +2821,7 @@ static void rtl8153_disable(struct r8152 *tp)
 {
 	r8153_aldps_en(tp, false);
 	rtl_disable(tp);
+	rtl_reset_bmu(tp);
 	r8153_aldps_en(tp, true);
 	usb_enable_lpm(tp->udev);
 }
@@ -2872,7 +2891,7 @@ static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex)
 		bmcr = BMCR_ANENABLE | BMCR_ANRESTART;
 	}
 
-	if (test_bit(PHY_RESET, &tp->flags))
+	if (test_and_clear_bit(PHY_RESET, &tp->flags))
 		bmcr |= BMCR_RESET;
 
 	if (tp->mii.supports_gmii)
@@ -2881,7 +2900,7 @@ static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex)
 	r8152_mdio_write(tp, MII_ADVERTISE, anar);
 	r8152_mdio_write(tp, MII_BMCR, bmcr);
 
-	if (test_and_clear_bit(PHY_RESET, &tp->flags)) {
+	if (bmcr & BMCR_RESET) {
 		int i;
 
 		for (i = 0; i < 50; i++) {
@@ -3040,6 +3059,27 @@ out1:
 	usb_autopm_put_interface(tp->intf);
 }
 
+static void rtl_hw_phy_work_func_t(struct work_struct *work)
+{
+	struct r8152 *tp = container_of(work, struct r8152, hw_phy_work.work);
+
+	if (test_bit(RTL8152_UNPLUG, &tp->flags))
+		return;
+
+	if (usb_autopm_get_interface(tp->intf) < 0)
+		return;
+
+	mutex_lock(&tp->control);
+
+	tp->rtl_ops.hw_phy_cfg(tp);
+
+	rtl8152_set_speed(tp, tp->autoneg, tp->speed, tp->duplex);
+
+	mutex_unlock(&tp->control);
+
+	usb_autopm_put_interface(tp->intf);
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int rtl_notifier(struct notifier_block *nb, unsigned long action,
 			void *data)
@@ -3088,9 +3128,6 @@ static int rtl8152_open(struct net_device *netdev)
 
 	tp->rtl_ops.up(tp);
 
-	rtl8152_set_speed(tp, AUTONEG_ENABLE,
-			  tp->mii.supports_gmii ? SPEED_1000 : SPEED_100,
-			  DUPLEX_FULL);
 	netif_carrier_off(netdev);
 	netif_start_queue(netdev);
 	set_bit(WORK_ENABLE, &tp->flags);
@@ -3382,15 +3419,11 @@ static void r8153_init(struct r8152 *tp)
 	r8153_power_cut_en(tp, false);
 	r8153_u1u2en(tp, true);
 
-	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, ALDPS_SPDWN_RATIO);
-	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, EEE_SPDWN_RATIO);
-	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3,
-		       PKT_AVAIL_SPDWN_EN | SUSPEND_SPDWN_EN |
-		       U1U2_SPDWN_EN | L1_SPDWN_EN);
-	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4,
-		       PWRSAVE_SPDWN_EN | RXDV_SPDWN_EN | TX10MIDLE_EN |
-		       TP100_SPDWN_EN | TP500_SPDWN_EN | TP1000_SPDWN_EN |
-		       EEE_SPDWN_EN);
+	/* MAC clock speed down */
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, 0);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, 0);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, 0);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, 0);
 
 	r8153_enable_eee(tp);
 	r8153_aldps_en(tp, true);
@@ -3518,6 +3551,7 @@ static int rtl8152_resume(struct usb_interface *intf)
 
 	if (!test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 		tp->rtl_ops.init(tp);
+		queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
 		netif_device_attach(tp->netdev);
 	}
 
@@ -3532,10 +3566,6 @@ static int rtl8152_resume(struct usb_interface *intf)
 			napi_enable(&tp->napi);
 		} else {
 			tp->rtl_ops.up(tp);
-			rtl8152_set_speed(tp, AUTONEG_ENABLE,
-					  tp->mii.supports_gmii ?
-					  SPEED_1000 : SPEED_100,
-					  DUPLEX_FULL);
 			netif_carrier_off(tp->netdev);
 			set_bit(WORK_ENABLE, &tp->flags);
 		}
@@ -3665,6 +3695,11 @@ static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	mutex_lock(&tp->control);
 
 	ret = rtl8152_set_speed(tp, cmd->autoneg, cmd->speed, cmd->duplex);
+	if (!ret) {
+		tp->autoneg = cmd->autoneg;
+		tp->speed = cmd->speed;
+		tp->duplex = cmd->duplex;
+	}
 
 	mutex_unlock(&tp->control);
 
@@ -4122,6 +4157,7 @@ static int rtl_ops_init(struct r8152 *tp)
 		ops->eee_get		= r8152_get_eee;
 		ops->eee_set		= r8152_set_eee;
 		ops->in_nway		= rtl8152_in_nway;
+		ops->hw_phy_cfg		= r8152b_hw_phy_cfg;
 		break;
 
 	case RTL_VER_03:
@@ -4137,6 +4173,7 @@ static int rtl_ops_init(struct r8152 *tp)
 		ops->eee_get		= r8153_get_eee;
 		ops->eee_set		= r8153_set_eee;
 		ops->in_nway		= rtl8153_in_nway;
+		ops->hw_phy_cfg		= r8153_hw_phy_cfg;
 		break;
 
 	default:
@@ -4183,6 +4220,7 @@ static int rtl8152_probe(struct usb_interface *intf,
 
 	mutex_init(&tp->control);
 	INIT_DELAYED_WORK(&tp->schedule, rtl_work_func_t);
+	INIT_DELAYED_WORK(&tp->hw_phy_work, rtl_hw_phy_work_func_t);
 
 	netdev->netdev_ops = &rtl8152_netdev_ops;
 	netdev->watchdog_timeo = RTL8152_TX_TIMEOUT;
@@ -4222,9 +4260,14 @@ static int rtl8152_probe(struct usb_interface *intf,
 		break;
 	}
 
+	tp->autoneg = AUTONEG_ENABLE;
+	tp->speed = tp->mii.supports_gmii ? SPEED_1000 : SPEED_100;
+	tp->duplex = DUPLEX_FULL;
+
 	intf->needs_remote_wakeup = 1;
 
 	tp->rtl_ops.init(tp);
+	queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
 	set_ethernet_addr(tp);
 
 	usb_set_intfdata(intf, tp);
@@ -4270,6 +4313,7 @@ static void rtl8152_disconnect(struct usb_interface *intf)
 
 		netif_napi_del(&tp->napi);
 		unregister_netdev(tp->netdev);
+		cancel_delayed_work_sync(&tp->hw_phy_work);
 		tp->rtl_ops.unload(tp);
 		free_netdev(tp->netdev);
 	}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index e0638e556fe7..1dd08d4b9c31 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -479,53 +479,21 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 	stats->rx_packets++;
 	u64_stats_update_end(&stats->rx_syncp);
 
-	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-		pr_debug("Needs csum!\n");
-		if (!skb_partial_csum_set(skb,
-			  virtio16_to_cpu(vi->vdev, hdr->hdr.csum_start),
-			  virtio16_to_cpu(vi->vdev, hdr->hdr.csum_offset)))
-			goto frame_err;
-	} else if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) {
+	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID)
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	if (virtio_net_hdr_to_skb(skb, &hdr->hdr,
+				  virtio_is_little_endian(vi->vdev))) {
+		net_warn_ratelimited("%s: bad gso: type: %u, size: %u\n",
+				     dev->name, hdr->hdr.gso_type,
+				     hdr->hdr.gso_size);
+		goto frame_err;
 	}
 
 	skb->protocol = eth_type_trans(skb, dev);
 	pr_debug("Receiving skb proto 0x%04x len %i type %i\n",
 		 ntohs(skb->protocol), skb->len, skb->pkt_type);
 
-	if (hdr->hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-		pr_debug("GSO!\n");
-		switch (hdr->hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
-		case VIRTIO_NET_HDR_GSO_TCPV4:
-			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
-			break;
-		case VIRTIO_NET_HDR_GSO_UDP:
-			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-			break;
-		case VIRTIO_NET_HDR_GSO_TCPV6:
-			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
-			break;
-		default:
-			net_warn_ratelimited("%s: bad gso type %u.\n",
-					     dev->name, hdr->hdr.gso_type);
-			goto frame_err;
-		}
-
-		if (hdr->hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN)
-			skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
-
-		skb_shinfo(skb)->gso_size = virtio16_to_cpu(vi->vdev,
-							    hdr->hdr.gso_size);
-		if (skb_shinfo(skb)->gso_size == 0) {
-			net_warn_ratelimited("%s: zero gso size.\n", dev->name);
-			goto frame_err;
-		}
-
-		/* Header must be checked, and gso_segs computed. */
-		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
-		skb_shinfo(skb)->gso_segs = 0;
-	}
-
 	napi_gro_receive(&rq->napi, skb);
 	return;
 
@@ -868,35 +836,9 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	else
 		hdr = skb_vnet_hdr(skb);
 
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		hdr->hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		hdr->hdr.csum_start = cpu_to_virtio16(vi->vdev,
-						skb_checksum_start_offset(skb));
-		hdr->hdr.csum_offset = cpu_to_virtio16(vi->vdev,
-							 skb->csum_offset);
-	} else {
-		hdr->hdr.flags = 0;
-		hdr->hdr.csum_offset = hdr->hdr.csum_start = 0;
-	}
-
-	if (skb_is_gso(skb)) {
-		hdr->hdr.hdr_len = cpu_to_virtio16(vi->vdev, skb_headlen(skb));
-		hdr->hdr.gso_size = cpu_to_virtio16(vi->vdev,
-						    skb_shinfo(skb)->gso_size);
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
-			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
-		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
-			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
-		else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
-			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP;
-		else
-			BUG();
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN)
-			hdr->hdr.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
-	} else {
-		hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE;
-		hdr->hdr.gso_size = hdr->hdr.hdr_len = 0;
-	}
+	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
+				    virtio_is_little_endian(vi->vdev)))
+		BUG();
 
 	if (vi->mergeable_rx_bufs)
 		hdr->num_buffers = 0;
@@ -1780,6 +1722,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	struct net_device *dev;
 	struct virtnet_info *vi;
 	u16 max_queue_pairs;
+	int mtu;
 
 	if (!vdev->config->get) {
 		dev_err(&vdev->dev, "%s failure: config access disabled\n",
@@ -1896,6 +1839,14 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
 		vi->has_cvq = true;
 
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) {
+		mtu = virtio_cread16(vdev,
+				     offsetof(struct virtio_net_config,
+					      mtu));
+		if (virtnet_change_mtu(dev, mtu))
+			__virtio_clear_bit(vdev, VIRTIO_NET_F_MTU);
+	}
+
 	if (vi->any_header_sg)
 		dev->needed_headroom = vi->hdr_len;
 
@@ -2067,6 +2018,7 @@ static unsigned int features[] = {
 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ,
 	VIRTIO_NET_F_CTRL_MAC_ADDR,
 	VIRTIO_F_ANY_LAYOUT,
+	VIRTIO_NET_F_MTU,
 };
 
 static struct virtio_driver virtio_net_driver = {
diff --git a/drivers/net/vmxnet3/Makefile b/drivers/net/vmxnet3/Makefile
index 880f5098eac9..8cdbb63d1bb0 100644
--- a/drivers/net/vmxnet3/Makefile
+++ b/drivers/net/vmxnet3/Makefile
@@ -2,7 +2,7 @@
 #
 # Linux driver for VMware's vmxnet3 ethernet NIC.
 #
-# Copyright (C) 2007-2009, VMware, Inc. All Rights Reserved.
+# Copyright (C) 2007-2016, VMware, Inc. All Rights Reserved.
 #
 # This program is free software; you can redistribute it and/or modify it
 # under the terms of the GNU General Public License as published by the
@@ -21,7 +21,7 @@
 # The full GNU General Public License is included in this distribution in
 # the file called "COPYING".
 #
-# Maintained by: Shreyas Bhatewara <[email protected]>
+# Maintained by: [email protected]
 #
 #
 ################################################################################
diff --git a/drivers/net/vmxnet3/upt1_defs.h b/drivers/net/vmxnet3/upt1_defs.h
index 969c751ee404..db9f1fde3aac 100644
--- a/drivers/net/vmxnet3/upt1_defs.h
+++ b/drivers/net/vmxnet3/upt1_defs.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <[email protected]>
+ * Maintained by: [email protected]
  *
  */
 
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index 72ba8ae7f09a..c3a31646189f 100644
--- a/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2015, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <[email protected]>
+ * Maintained by: [email protected]
  *
  */
 
@@ -76,7 +76,12 @@ enum {
 	VMXNET3_CMD_UPDATE_IML,
 	VMXNET3_CMD_UPDATE_PMCFG,
 	VMXNET3_CMD_UPDATE_FEATURE,
+	VMXNET3_CMD_RESERVED1,
 	VMXNET3_CMD_LOAD_PLUGIN,
+	VMXNET3_CMD_RESERVED2,
+	VMXNET3_CMD_RESERVED3,
+	VMXNET3_CMD_SET_COALESCE,
+	VMXNET3_CMD_REGISTER_MEMREGS,
 
 	VMXNET3_CMD_FIRST_GET = 0xF00D0000,
 	VMXNET3_CMD_GET_QUEUE_STATUS = VMXNET3_CMD_FIRST_GET,
@@ -87,7 +92,10 @@ enum {
 	VMXNET3_CMD_GET_DID_LO,
 	VMXNET3_CMD_GET_DID_HI,
 	VMXNET3_CMD_GET_DEV_EXTRA_INFO,
-	VMXNET3_CMD_GET_CONF_INTR
+	VMXNET3_CMD_GET_CONF_INTR,
+	VMXNET3_CMD_GET_RESERVED1,
+	VMXNET3_CMD_GET_TXDATA_DESC_SIZE,
+	VMXNET3_CMD_GET_COALESCE,
 };
 
 /*
@@ -169,6 +177,8 @@ struct Vmxnet3_TxDataDesc {
 	u8		data[VMXNET3_HDR_COPY_SIZE];
 };
 
+typedef u8 Vmxnet3_RxDataDesc;
+
 #define VMXNET3_TCD_GEN_SHIFT	31
 #define VMXNET3_TCD_GEN_SIZE	1
 #define VMXNET3_TCD_TXIDX_SHIFT	0
@@ -373,6 +383,14 @@ union Vmxnet3_GenericDesc {
 #define VMXNET3_RING_SIZE_ALIGN 32
 #define VMXNET3_RING_SIZE_MASK  (VMXNET3_RING_SIZE_ALIGN - 1)
 
+/* Tx Data Ring buffer size must be a multiple of 64 */
+#define VMXNET3_TXDATA_DESC_SIZE_ALIGN 64
+#define VMXNET3_TXDATA_DESC_SIZE_MASK  (VMXNET3_TXDATA_DESC_SIZE_ALIGN - 1)
+
+/* Rx Data Ring buffer size must be a multiple of 64 */
+#define VMXNET3_RXDATA_DESC_SIZE_ALIGN 64
+#define VMXNET3_RXDATA_DESC_SIZE_MASK  (VMXNET3_RXDATA_DESC_SIZE_ALIGN - 1)
+
 /* Max ring size */
 #define VMXNET3_TX_RING_MAX_SIZE   4096
 #define VMXNET3_TC_RING_MAX_SIZE   4096
@@ -380,6 +398,11 @@ union Vmxnet3_GenericDesc {
 #define VMXNET3_RX_RING2_MAX_SIZE  4096
 #define VMXNET3_RC_RING_MAX_SIZE   8192
 
+#define VMXNET3_TXDATA_DESC_MIN_SIZE 128
+#define VMXNET3_TXDATA_DESC_MAX_SIZE 2048
+
+#define VMXNET3_RXDATA_DESC_MAX_SIZE 2048
+
 /* a list of reasons for queue stop */
 
 enum {
@@ -466,7 +489,9 @@ struct Vmxnet3_TxQueueConf {
 	__le32		compRingSize; /* # of comp desc */
 	__le32		ddLen;        /* size of driver data */
 	u8		intrIdx;
-	u8		_pad[7];
+	u8		_pad1[1];
+	__le16		txDataRingDescSize;
+	u8		_pad2[4];
 };
 
 
@@ -474,12 +499,14 @@ struct Vmxnet3_RxQueueConf {
 	__le64		rxRingBasePA[2];
 	__le64		compRingBasePA;
 	__le64		ddPA;            /* driver data */
-	__le64		reserved;
+	__le64		rxDataRingBasePA;
 	__le32		rxRingSize[2];   /* # of rx desc */
 	__le32		compRingSize;    /* # of rx comp desc */
 	__le32		ddLen;           /* size of driver data */
 	u8		intrIdx;
-	u8		_pad[7];
+	u8		_pad1[1];
+	__le16		rxDataRingDescSize;  /* size of rx data ring buffer */
+	u8		_pad2[4];
 };
 
 
@@ -609,6 +636,63 @@ struct Vmxnet3_RxQueueDesc {
 	u8				      __pad[88]; /* 128 aligned */
 };
 
+struct Vmxnet3_SetPolling {
+	u8					enablePolling;
+};
+
+#define VMXNET3_COAL_STATIC_MAX_DEPTH		128
+#define VMXNET3_COAL_RBC_MIN_RATE		100
+#define VMXNET3_COAL_RBC_MAX_RATE		100000
+
+enum Vmxnet3_CoalesceMode {
+	VMXNET3_COALESCE_DISABLED   = 0,
+	VMXNET3_COALESCE_ADAPT      = 1,
+	VMXNET3_COALESCE_STATIC     = 2,
+	VMXNET3_COALESCE_RBC        = 3
+};
+
+struct Vmxnet3_CoalesceRbc {
+	u32					rbc_rate;
+};
+
+struct Vmxnet3_CoalesceStatic {
+	u32					tx_depth;
+	u32					tx_comp_depth;
+	u32					rx_depth;
+};
+
+struct Vmxnet3_CoalesceScheme {
+	enum Vmxnet3_CoalesceMode		coalMode;
+	union {
+		struct Vmxnet3_CoalesceRbc	coalRbc;
+		struct Vmxnet3_CoalesceStatic	coalStatic;
+	} coalPara;
+};
+
+struct Vmxnet3_MemoryRegion {
+	__le64					startPA;
+	__le32					length;
+	__le16					txQueueBits;
+	__le16					rxQueueBits;
+};
+
+#define MAX_MEMORY_REGION_PER_QUEUE 16
+#define MAX_MEMORY_REGION_PER_DEVICE 256
+
+struct Vmxnet3_MemRegs {
+	__le16					numRegs;
+	__le16					pad[3];
+	struct Vmxnet3_MemoryRegion		memRegs[1];
+};
+
+/* If the command data <= 16 bytes, use the shared memory directly.
+ * otherwise, use variable length configuration descriptor.
+ */
+union Vmxnet3_CmdInfo {
+	struct Vmxnet3_VariableLenConfDesc	varConf;
+	struct Vmxnet3_SetPolling		setPolling;
+	__le64					data[2];
+};
 
 struct Vmxnet3_DSDevRead {
 	/* read-only region for device, read by dev in response to a SET cmd */
@@ -627,7 +711,14 @@ struct Vmxnet3_DriverShared {
 	__le32				pad;
 	struct Vmxnet3_DSDevRead	devRead;
 	__le32				ecr;
-	__le32				reserved[5];
+	__le32				reserved;
+	union {
+		__le32			reserved1[4];
+		union Vmxnet3_CmdInfo	cmdInfo; /* only valid in the context of
+						  * executing the relevant
+						  * command
+						  */
+	} cu;
 };
 
 
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index db8022ae415b..c68fe495d3f9 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <[email protected]>
+ * Maintained by: [email protected]
  *
  */
 
@@ -435,8 +435,8 @@ vmxnet3_tq_destroy(struct vmxnet3_tx_queue *tq,
 		tq->tx_ring.base = NULL;
 	}
 	if (tq->data_ring.base) {
-		dma_free_coherent(&adapter->pdev->dev, tq->data_ring.size *
-				  sizeof(struct Vmxnet3_TxDataDesc),
+		dma_free_coherent(&adapter->pdev->dev,
+				  tq->data_ring.size * tq->txdata_desc_size,
 				  tq->data_ring.base, tq->data_ring.basePA);
 		tq->data_ring.base = NULL;
 	}
@@ -478,8 +478,8 @@ vmxnet3_tq_init(struct vmxnet3_tx_queue *tq,
 	tq->tx_ring.next2fill = tq->tx_ring.next2comp = 0;
 	tq->tx_ring.gen = VMXNET3_INIT_GEN;
 
-	memset(tq->data_ring.base, 0, tq->data_ring.size *
-	       sizeof(struct Vmxnet3_TxDataDesc));
+	memset(tq->data_ring.base, 0,
+	       tq->data_ring.size * tq->txdata_desc_size);
 
 	/* reset the tx comp ring contents to 0 and reset comp ring states */
 	memset(tq->comp_ring.base, 0, tq->comp_ring.size *
@@ -514,10 +514,10 @@ vmxnet3_tq_create(struct vmxnet3_tx_queue *tq,
 	}
 
 	tq->data_ring.base = dma_alloc_coherent(&adapter->pdev->dev,
-			tq->data_ring.size * sizeof(struct Vmxnet3_TxDataDesc),
+			tq->data_ring.size * tq->txdata_desc_size,
 			&tq->data_ring.basePA, GFP_KERNEL);
 	if (!tq->data_ring.base) {
-		netdev_err(adapter->netdev, "failed to allocate data ring\n");
+		netdev_err(adapter->netdev, "failed to allocate tx data ring\n");
 		goto err;
 	}
 
@@ -689,7 +689,7 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 	if (ctx->copy_size) {
 		ctx->sop_txd->txd.addr = cpu_to_le64(tq->data_ring.basePA +
 					tq->tx_ring.next2fill *
-					sizeof(struct Vmxnet3_TxDataDesc));
+					tq->txdata_desc_size);
 		ctx->sop_txd->dword[2] = cpu_to_le32(dw2 | ctx->copy_size);
 		ctx->sop_txd->dword[3] = 0;
 
@@ -873,8 +873,9 @@ vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 			ctx->eth_ip_hdr_size = 0;
 			ctx->l4_hdr_size = 0;
 			/* copy as much as allowed */
-			ctx->copy_size = min((unsigned int)VMXNET3_HDR_COPY_SIZE
-					     , skb_headlen(skb));
+			ctx->copy_size = min_t(unsigned int,
+					       tq->txdata_desc_size,
+					       skb_headlen(skb));
 		}
 
 		if (skb->len <= VMXNET3_HDR_COPY_SIZE)
@@ -885,7 +886,7 @@ vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 			goto err;
 	}
 
-	if (unlikely(ctx->copy_size > VMXNET3_HDR_COPY_SIZE)) {
+	if (unlikely(ctx->copy_size > tq->txdata_desc_size)) {
 		tq->stats.oversized_hdr++;
 		ctx->copy_size = 0;
 		return 0;
@@ -1283,9 +1284,10 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 			 */
 			break;
 		}
-		BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2);
+		BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2 &&
+		       rcd->rqID != rq->dataRingQid);
 		idx = rcd->rxdIdx;
-		ring_idx = rcd->rqID < adapter->num_rx_queues ? 0 : 1;
+		ring_idx = VMXNET3_GET_RING_IDX(adapter, rcd->rqID);
 		ring = rq->rx_ring + ring_idx;
 		vmxnet3_getRxDesc(rxd, &rq->rx_ring[ring_idx].base[idx].rxd,
 				  &rxCmdDesc);
@@ -1300,8 +1302,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 		}
 
 		if (rcd->sop) { /* first buf of the pkt */
+			bool rxDataRingUsed;
+			u16 len;
+
 			BUG_ON(rxd->btype != VMXNET3_RXD_BTYPE_HEAD ||
-			       rcd->rqID != rq->qid);
+			       (rcd->rqID != rq->qid &&
+				rcd->rqID != rq->dataRingQid));
 
 			BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_SKB);
 			BUG_ON(ctx->skb != NULL || rbi->skb == NULL);
@@ -1317,8 +1323,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 
 			skip_page_frags = false;
 			ctx->skb = rbi->skb;
+
+			rxDataRingUsed =
+				VMXNET3_RX_DATA_RING(adapter, rcd->rqID);
+			len = rxDataRingUsed ? rcd->len : rbi->len;
 			new_skb = netdev_alloc_skb_ip_align(adapter->netdev,
-							    rbi->len);
+							    len);
 			if (new_skb == NULL) {
 				/* Skb allocation failed, do not handover this
 				 * skb to stack. Reuse it. Drop the existing pkt
@@ -1329,25 +1339,48 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 				skip_page_frags = true;
 				goto rcd_done;
 			}
-			new_dma_addr = dma_map_single(&adapter->pdev->dev,
-						      new_skb->data, rbi->len,
-						      PCI_DMA_FROMDEVICE);
-			if (dma_mapping_error(&adapter->pdev->dev,
-					      new_dma_addr)) {
-				dev_kfree_skb(new_skb);
-				/* Skb allocation failed, do not handover this
-				 * skb to stack. Reuse it. Drop the existing pkt
-				 */
-				rq->stats.rx_buf_alloc_failure++;
-				ctx->skb = NULL;
-				rq->stats.drop_total++;
-				skip_page_frags = true;
-				goto rcd_done;
-			}
 
-			dma_unmap_single(&adapter->pdev->dev, rbi->dma_addr,
-					 rbi->len,
-					 PCI_DMA_FROMDEVICE);
+			if (rxDataRingUsed) {
+				size_t sz;
+
+				BUG_ON(rcd->len > rq->data_ring.desc_size);
+
+				ctx->skb = new_skb;
+				sz = rcd->rxdIdx * rq->data_ring.desc_size;
+				memcpy(new_skb->data,
+				       &rq->data_ring.base[sz], rcd->len);
+			} else {
+				ctx->skb = rbi->skb;
+
+				new_dma_addr =
+					dma_map_single(&adapter->pdev->dev,
+						       new_skb->data, rbi->len,
+						       PCI_DMA_FROMDEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      new_dma_addr)) {
+					dev_kfree_skb(new_skb);
+					/* Skb allocation failed, do not
+					 * handover this skb to stack. Reuse
+					 * it. Drop the existing pkt.
+					 */
+					rq->stats.rx_buf_alloc_failure++;
+					ctx->skb = NULL;
+					rq->stats.drop_total++;
+					skip_page_frags = true;
+					goto rcd_done;
+				}
+
+				dma_unmap_single(&adapter->pdev->dev,
+						 rbi->dma_addr,
+						 rbi->len,
+						 PCI_DMA_FROMDEVICE);
+
+				/* Immediate refill */
+				rbi->skb = new_skb;
+				rbi->dma_addr = new_dma_addr;
+				rxd->addr = cpu_to_le64(rbi->dma_addr);
+				rxd->len = rbi->len;
+			}
 
 #ifdef VMXNET3_RSS
 			if (rcd->rssType != VMXNET3_RCD_RSS_TYPE_NONE &&
@@ -1358,18 +1391,13 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 #endif
 			skb_put(ctx->skb, rcd->len);
 
-			/* Immediate refill */
-			rbi->skb = new_skb;
-			rbi->dma_addr = new_dma_addr;
-			rxd->addr = cpu_to_le64(rbi->dma_addr);
-			rxd->len = rbi->len;
-			if (adapter->version == 2 &&
+			if (VMXNET3_VERSION_GE_2(adapter) &&
 			    rcd->type == VMXNET3_CDTYPE_RXCOMP_LRO) {
 				struct Vmxnet3_RxCompDescExt *rcdlro;
 				rcdlro = (struct Vmxnet3_RxCompDescExt *)rcd;
 
 				segCnt = rcdlro->segCnt;
-				BUG_ON(segCnt <= 1);
+				WARN_ON_ONCE(segCnt == 0);
 				mss = rcdlro->mss;
 				if (unlikely(segCnt <= 1))
 					segCnt = 0;
@@ -1589,6 +1617,13 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
 		rq->buf_info[i] = NULL;
 	}
 
+	if (rq->data_ring.base) {
+		dma_free_coherent(&adapter->pdev->dev,
+				  rq->rx_ring[0].size * rq->data_ring.desc_size,
+				  rq->data_ring.base, rq->data_ring.basePA);
+		rq->data_ring.base = NULL;
+	}
+
 	if (rq->comp_ring.base) {
 		dma_free_coherent(&adapter->pdev->dev, rq->comp_ring.size
 				  * sizeof(struct Vmxnet3_RxCompDesc),
@@ -1604,6 +1639,25 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
 	}
 }
 
+void
+vmxnet3_rq_destroy_all_rxdataring(struct vmxnet3_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
+
+		if (rq->data_ring.base) {
+			dma_free_coherent(&adapter->pdev->dev,
+					  (rq->rx_ring[0].size *
+					  rq->data_ring.desc_size),
+					  rq->data_ring.base,
+					  rq->data_ring.basePA);
+			rq->data_ring.base = NULL;
+			rq->data_ring.desc_size = 0;
+		}
+	}
+}
 
 static int
 vmxnet3_rq_init(struct vmxnet3_rx_queue *rq,
@@ -1697,6 +1751,22 @@ vmxnet3_rq_create(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter)
 		}
 	}
 
+	if ((adapter->rxdataring_enabled) && (rq->data_ring.desc_size != 0)) {
+		sz = rq->rx_ring[0].size * rq->data_ring.desc_size;
+		rq->data_ring.base =
+			dma_alloc_coherent(&adapter->pdev->dev, sz,
+					   &rq->data_ring.basePA,
+					   GFP_KERNEL);
+		if (!rq->data_ring.base) {
+			netdev_err(adapter->netdev,
+				   "rx data ring will be disabled\n");
+			adapter->rxdataring_enabled = false;
+		}
+	} else {
+		rq->data_ring.base = NULL;
+		rq->data_ring.desc_size = 0;
+	}
+
 	sz = rq->comp_ring.size * sizeof(struct Vmxnet3_RxCompDesc);
 	rq->comp_ring.base = dma_alloc_coherent(&adapter->pdev->dev, sz,
 						&rq->comp_ring.basePA,
@@ -1729,6 +1799,8 @@ vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter)
 {
 	int i, err = 0;
 
+	adapter->rxdataring_enabled = VMXNET3_VERSION_GE_3(adapter);
+
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		err = vmxnet3_rq_create(&adapter->rx_queue[i], adapter);
 		if (unlikely(err)) {
@@ -1738,6 +1810,10 @@ vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter)
 			goto err_out;
 		}
 	}
+
+	if (!adapter->rxdataring_enabled)
+		vmxnet3_rq_destroy_all_rxdataring(adapter);
+
 	return err;
 err_out:
 	vmxnet3_rq_destroy_all(adapter);
@@ -2045,10 +2121,9 @@ vmxnet3_request_irqs(struct vmxnet3_adapter *adapter)
 			struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
 			rq->qid = i;
 			rq->qid2 = i + adapter->num_rx_queues;
+			rq->dataRingQid = i + 2 * adapter->num_rx_queues;
 		}
 
-
-
 		/* init our intr settings */
 		for (i = 0; i < intr->num_intrs; i++)
 			intr->mod_levels[i] = UPT1_IML_ADAPTIVE;
@@ -2336,6 +2411,7 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 		tqc->ddPA           = cpu_to_le64(tq->buf_info_pa);
 		tqc->txRingSize     = cpu_to_le32(tq->tx_ring.size);
 		tqc->dataRingSize   = cpu_to_le32(tq->data_ring.size);
+		tqc->txDataRingDescSize = cpu_to_le32(tq->txdata_desc_size);
 		tqc->compRingSize   = cpu_to_le32(tq->comp_ring.size);
 		tqc->ddLen          = cpu_to_le32(
 					sizeof(struct vmxnet3_tx_buf_info) *
@@ -2360,6 +2436,12 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 					(rqc->rxRingSize[0] +
 					 rqc->rxRingSize[1]));
 		rqc->intrIdx         = rq->comp_ring.intr_idx;
+		if (VMXNET3_VERSION_GE_3(adapter)) {
+			rqc->rxDataRingBasePA =
+				cpu_to_le64(rq->data_ring.basePA);
+			rqc->rxDataRingDescSize =
+				cpu_to_le16(rq->data_ring.desc_size);
+		}
 	}
 
 #ifdef VMXNET3_RSS
@@ -2409,6 +2491,32 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 	/* the rest are already zeroed */
 }
 
+static void
+vmxnet3_init_coalesce(struct vmxnet3_adapter *adapter)
+{
+	struct Vmxnet3_DriverShared *shared = adapter->shared;
+	union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo;
+	unsigned long flags;
+
+	if (!VMXNET3_VERSION_GE_3(adapter))
+		return;
+
+	spin_lock_irqsave(&adapter->cmd_lock, flags);
+	cmdInfo->varConf.confVer = 1;
+	cmdInfo->varConf.confLen =
+		cpu_to_le32(sizeof(*adapter->coal_conf));
+	cmdInfo->varConf.confPA  = cpu_to_le64(adapter->coal_conf_pa);
+
+	if (adapter->default_coal_mode) {
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_COALESCE);
+	} else {
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_SET_COALESCE);
+	}
+
+	spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+}
 
 int
 vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
@@ -2458,6 +2566,8 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
 		goto activate_err;
 	}
 
+	vmxnet3_init_coalesce(adapter);
+
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		VMXNET3_WRITE_BAR0_REG(adapter,
 				VMXNET3_REG_RXPROD + i * VMXNET3_REG_ALIGN,
@@ -2689,7 +2799,8 @@ vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter)
 
 int
 vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
-		      u32 rx_ring_size, u32 rx_ring2_size)
+		      u32 rx_ring_size, u32 rx_ring2_size,
+		      u16 txdata_desc_size, u16 rxdata_desc_size)
 {
 	int err = 0, i;
 
@@ -2698,6 +2809,7 @@ vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
 		tq->tx_ring.size   = tx_ring_size;
 		tq->data_ring.size = tx_ring_size;
 		tq->comp_ring.size = tx_ring_size;
+		tq->txdata_desc_size = txdata_desc_size;
 		tq->shared = &adapter->tqd_start[i].ctrl;
 		tq->stopped = true;
 		tq->adapter = adapter;
@@ -2714,12 +2826,15 @@ vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
 	adapter->rx_queue[0].rx_ring[0].size = rx_ring_size;
 	adapter->rx_queue[0].rx_ring[1].size = rx_ring2_size;
 	vmxnet3_adjust_rx_ring_size(adapter);
+
+	adapter->rxdataring_enabled = VMXNET3_VERSION_GE_3(adapter);
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
 		/* qid and qid2 for rx queues will be assigned later when num
 		 * of rx queues is finalized after allocating intrs */
 		rq->shared = &adapter->rqd_start[i].ctrl;
 		rq->adapter = adapter;
+		rq->data_ring.desc_size = rxdata_desc_size;
 		err = vmxnet3_rq_create(rq, adapter);
 		if (err) {
 			if (i == 0) {
@@ -2737,6 +2852,10 @@ vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
 			}
 		}
 	}
+
+	if (!adapter->rxdataring_enabled)
+		vmxnet3_rq_destroy_all_rxdataring(adapter);
+
 	return err;
 queue_err:
 	vmxnet3_tq_destroy_all(adapter);
@@ -2754,9 +2873,35 @@ vmxnet3_open(struct net_device *netdev)
 	for (i = 0; i < adapter->num_tx_queues; i++)
 		spin_lock_init(&adapter->tx_queue[i].tx_lock);
 
-	err = vmxnet3_create_queues(adapter, adapter->tx_ring_size,
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		unsigned long flags;
+		u16 txdata_desc_size;
+
+		spin_lock_irqsave(&adapter->cmd_lock, flags);
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_TXDATA_DESC_SIZE);
+		txdata_desc_size = VMXNET3_READ_BAR1_REG(adapter,
+							 VMXNET3_REG_CMD);
+		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+
+		if ((txdata_desc_size < VMXNET3_TXDATA_DESC_MIN_SIZE) ||
+		    (txdata_desc_size > VMXNET3_TXDATA_DESC_MAX_SIZE) ||
+		    (txdata_desc_size & VMXNET3_TXDATA_DESC_SIZE_MASK)) {
+			adapter->txdata_desc_size =
+				sizeof(struct Vmxnet3_TxDataDesc);
+		} else {
+			adapter->txdata_desc_size = txdata_desc_size;
+		}
+	} else {
+		adapter->txdata_desc_size = sizeof(struct Vmxnet3_TxDataDesc);
+	}
+
+	err = vmxnet3_create_queues(adapter,
+				    adapter->tx_ring_size,
 				    adapter->rx_ring_size,
-				    adapter->rx_ring2_size);
+				    adapter->rx_ring2_size,
+				    adapter->txdata_desc_size,
+				    adapter->rxdata_desc_size);
 	if (err)
 		goto queue_err;
 
@@ -3200,12 +3345,21 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		goto err_alloc_pci;
 
 	ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS);
-	if (ver & 2) {
-		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 2);
-		adapter->version = 2;
-	} else if (ver & 1) {
-		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 1);
-		adapter->version = 1;
+	if (ver & (1 << VMXNET3_REV_3)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_3);
+		adapter->version = VMXNET3_REV_3 + 1;
+	} else if (ver & (1 << VMXNET3_REV_2)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_2);
+		adapter->version = VMXNET3_REV_2 + 1;
+	} else if (ver & (1 << VMXNET3_REV_1)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_1);
+		adapter->version = VMXNET3_REV_1 + 1;
 	} else {
 		dev_err(&pdev->dev,
 			"Incompatible h/w version (0x%x) for adapter\n", ver);
@@ -3224,9 +3378,28 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		goto err_ver;
 	}
 
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		adapter->coal_conf =
+			dma_alloc_coherent(&adapter->pdev->dev,
+					   sizeof(struct Vmxnet3_CoalesceScheme)
+					   ,
+					   &adapter->coal_conf_pa,
+					   GFP_KERNEL);
+		if (!adapter->coal_conf) {
+			err = -ENOMEM;
+			goto err_ver;
+		}
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_DISABLED;
+		adapter->default_coal_mode = true;
+	}
+
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 	vmxnet3_declare_features(adapter, dma64);
 
+	adapter->rxdata_desc_size = VMXNET3_VERSION_GE_3(adapter) ?
+		VMXNET3_DEF_RXDATA_DESC_SIZE : 0;
+
 	if (adapter->num_tx_queues == adapter->num_rx_queues)
 		adapter->share_intr = VMXNET3_INTR_BUDDYSHARE;
 	else
@@ -3283,6 +3456,11 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	return 0;
 
 err_register:
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		dma_free_coherent(&adapter->pdev->dev,
+				  sizeof(struct Vmxnet3_CoalesceScheme),
+				  adapter->coal_conf, adapter->coal_conf_pa);
+	}
 	vmxnet3_free_intr_resources(adapter);
 err_ver:
 	vmxnet3_free_pci_resources(adapter);
@@ -3333,6 +3511,11 @@ vmxnet3_remove_device(struct pci_dev *pdev)
 
 	vmxnet3_free_intr_resources(adapter);
 	vmxnet3_free_pci_resources(adapter);
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		dma_free_coherent(&adapter->pdev->dev,
+				  sizeof(struct Vmxnet3_CoalesceScheme),
+				  adapter->coal_conf, adapter->coal_conf_pa);
+	}
 #ifdef VMXNET3_RSS
 	dma_free_coherent(&adapter->pdev->dev, sizeof(struct UPT1_RSSConf),
 			  adapter->rss_conf, adapter->rss_conf_pa);
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 9ba11d737753..aabc6ef366b4 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <[email protected]>
+ * Maintained by: [email protected]
  *
  */
 
@@ -396,8 +396,7 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 		buf[j++] = VMXNET3_GET_ADDR_LO(tq->data_ring.basePA);
 		buf[j++] = VMXNET3_GET_ADDR_HI(tq->data_ring.basePA);
 		buf[j++] = tq->data_ring.size;
-		/* transmit data ring buffer size */
-		buf[j++] = VMXNET3_HDR_COPY_SIZE;
+		buf[j++] = tq->txdata_desc_size;
 
 		buf[j++] = VMXNET3_GET_ADDR_LO(tq->comp_ring.basePA);
 		buf[j++] = VMXNET3_GET_ADDR_HI(tq->comp_ring.basePA);
@@ -431,11 +430,10 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 		buf[j++] = rq->rx_ring[1].next2comp;
 		buf[j++] = rq->rx_ring[1].gen;
 
-		/* receive data ring */
-		buf[j++] = 0;
-		buf[j++] = 0;
-		buf[j++] = 0;
-		buf[j++] = 0;
+		buf[j++] = VMXNET3_GET_ADDR_LO(rq->data_ring.basePA);
+		buf[j++] = VMXNET3_GET_ADDR_HI(rq->data_ring.basePA);
+		buf[j++] = rq->rx_ring[0].size;
+		buf[j++] = rq->data_ring.desc_size;
 
 		buf[j++] = VMXNET3_GET_ADDR_LO(rq->comp_ring.basePA);
 		buf[j++] = VMXNET3_GET_ADDR_HI(rq->comp_ring.basePA);
@@ -504,12 +502,14 @@ vmxnet3_get_ringparam(struct net_device *netdev,
 
 	param->rx_max_pending = VMXNET3_RX_RING_MAX_SIZE;
 	param->tx_max_pending = VMXNET3_TX_RING_MAX_SIZE;
-	param->rx_mini_max_pending = 0;
+	param->rx_mini_max_pending = VMXNET3_VERSION_GE_3(adapter) ?
+		VMXNET3_RXDATA_DESC_MAX_SIZE : 0;
 	param->rx_jumbo_max_pending = VMXNET3_RX_RING2_MAX_SIZE;
 
 	param->rx_pending = adapter->rx_ring_size;
 	param->tx_pending = adapter->tx_ring_size;
-	param->rx_mini_pending = 0;
+	param->rx_mini_pending = VMXNET3_VERSION_GE_3(adapter) ?
+		adapter->rxdata_desc_size : 0;
 	param->rx_jumbo_pending = adapter->rx_ring2_size;
 }
 
@@ -520,6 +520,7 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	u32 new_tx_ring_size, new_rx_ring_size, new_rx_ring2_size;
+	u16 new_rxdata_desc_size;
 	u32 sz;
 	int err = 0;
 
@@ -542,6 +543,15 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 		return -EOPNOTSUPP;
 	}
 
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		if (param->rx_mini_pending < 0 ||
+		    param->rx_mini_pending > VMXNET3_RXDATA_DESC_MAX_SIZE) {
+			return -EINVAL;
+		}
+	} else if (param->rx_mini_pending != 0) {
+		return -EINVAL;
+	}
+
 	/* round it up to a multiple of VMXNET3_RING_SIZE_ALIGN */
 	new_tx_ring_size = (param->tx_pending + VMXNET3_RING_SIZE_MASK) &
 							~VMXNET3_RING_SIZE_MASK;
@@ -568,9 +578,19 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 	new_rx_ring2_size = min_t(u32, new_rx_ring2_size,
 				  VMXNET3_RX_RING2_MAX_SIZE);
 
+	/* rx data ring buffer size has to be a multiple of
+	 * VMXNET3_RXDATA_DESC_SIZE_ALIGN
+	 */
+	new_rxdata_desc_size =
+		(param->rx_mini_pending + VMXNET3_RXDATA_DESC_SIZE_MASK) &
+		~VMXNET3_RXDATA_DESC_SIZE_MASK;
+	new_rxdata_desc_size = min_t(u16, new_rxdata_desc_size,
+				     VMXNET3_RXDATA_DESC_MAX_SIZE);
+
 	if (new_tx_ring_size == adapter->tx_ring_size &&
 	    new_rx_ring_size == adapter->rx_ring_size &&
-	    new_rx_ring2_size == adapter->rx_ring2_size) {
+	    new_rx_ring2_size == adapter->rx_ring2_size &&
+	    new_rxdata_desc_size == adapter->rxdata_desc_size) {
 		return 0;
 	}
 
@@ -591,8 +611,9 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 		vmxnet3_rq_destroy_all(adapter);
 
 		err = vmxnet3_create_queues(adapter, new_tx_ring_size,
-			new_rx_ring_size, new_rx_ring2_size);
-
+					    new_rx_ring_size, new_rx_ring2_size,
+					    adapter->txdata_desc_size,
+					    new_rxdata_desc_size);
 		if (err) {
 			/* failed, most likely because of OOM, try default
 			 * size */
@@ -601,10 +622,15 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 			new_rx_ring_size = VMXNET3_DEF_RX_RING_SIZE;
 			new_rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE;
 			new_tx_ring_size = VMXNET3_DEF_TX_RING_SIZE;
+			new_rxdata_desc_size = VMXNET3_VERSION_GE_3(adapter) ?
+				VMXNET3_DEF_RXDATA_DESC_SIZE : 0;
+
 			err = vmxnet3_create_queues(adapter,
 						    new_tx_ring_size,
 						    new_rx_ring_size,
-						    new_rx_ring2_size);
+						    new_rx_ring2_size,
+						    adapter->txdata_desc_size,
+						    new_rxdata_desc_size);
 			if (err) {
 				netdev_err(netdev, "failed to create queues "
 					   "with default sizes. Closing it\n");
@@ -620,6 +646,7 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 	adapter->tx_ring_size = new_tx_ring_size;
 	adapter->rx_ring_size = new_rx_ring_size;
 	adapter->rx_ring2_size = new_rx_ring2_size;
+	adapter->rxdata_desc_size = new_rxdata_desc_size;
 
 out:
 	clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);
@@ -698,6 +725,162 @@ vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key,
 }
 #endif
 
+static int
+vmxnet3_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+
+	if (!VMXNET3_VERSION_GE_3(adapter))
+		return -EOPNOTSUPP;
+
+	switch (adapter->coal_conf->coalMode) {
+	case VMXNET3_COALESCE_DISABLED:
+		/* struct ethtool_coalesce is already initialized to 0 */
+		break;
+	case VMXNET3_COALESCE_ADAPT:
+		ec->use_adaptive_rx_coalesce = true;
+		break;
+	case VMXNET3_COALESCE_STATIC:
+		ec->tx_max_coalesced_frames =
+			adapter->coal_conf->coalPara.coalStatic.tx_comp_depth;
+		ec->rx_max_coalesced_frames =
+			adapter->coal_conf->coalPara.coalStatic.rx_depth;
+		break;
+	case VMXNET3_COALESCE_RBC: {
+		u32 rbc_rate;
+
+		rbc_rate = adapter->coal_conf->coalPara.coalRbc.rbc_rate;
+		ec->rx_coalesce_usecs = VMXNET3_COAL_RBC_USECS(rbc_rate);
+	}
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+vmxnet3_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+	struct Vmxnet3_DriverShared *shared = adapter->shared;
+	union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo;
+	unsigned long flags;
+
+	if (!VMXNET3_VERSION_GE_3(adapter))
+		return -EOPNOTSUPP;
+
+	if (ec->rx_coalesce_usecs_irq ||
+	    ec->rx_max_coalesced_frames_irq ||
+	    ec->tx_coalesce_usecs ||
+	    ec->tx_coalesce_usecs_irq ||
+	    ec->tx_max_coalesced_frames_irq ||
+	    ec->stats_block_coalesce_usecs ||
+	    ec->use_adaptive_tx_coalesce ||
+	    ec->pkt_rate_low ||
+	    ec->rx_coalesce_usecs_low ||
+	    ec->rx_max_coalesced_frames_low ||
+	    ec->tx_coalesce_usecs_low ||
+	    ec->tx_max_coalesced_frames_low ||
+	    ec->pkt_rate_high ||
+	    ec->rx_coalesce_usecs_high ||
+	    ec->rx_max_coalesced_frames_high ||
+	    ec->tx_coalesce_usecs_high ||
+	    ec->tx_max_coalesced_frames_high ||
+	    ec->rate_sample_interval) {
+		return -EINVAL;
+	}
+
+	if ((ec->rx_coalesce_usecs == 0) &&
+	    (ec->use_adaptive_rx_coalesce == 0) &&
+	    (ec->tx_max_coalesced_frames == 0) &&
+	    (ec->rx_max_coalesced_frames == 0)) {
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_DISABLED;
+		goto done;
+	}
+
+	if (ec->rx_coalesce_usecs != 0) {
+		u32 rbc_rate;
+
+		if ((ec->use_adaptive_rx_coalesce != 0) ||
+		    (ec->tx_max_coalesced_frames != 0) ||
+		    (ec->rx_max_coalesced_frames != 0)) {
+			return -EINVAL;
+		}
+
+		rbc_rate = VMXNET3_COAL_RBC_RATE(ec->rx_coalesce_usecs);
+		if (rbc_rate < VMXNET3_COAL_RBC_MIN_RATE ||
+		    rbc_rate > VMXNET3_COAL_RBC_MAX_RATE) {
+			return -EINVAL;
+		}
+
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_RBC;
+		adapter->coal_conf->coalPara.coalRbc.rbc_rate = rbc_rate;
+		goto done;
+	}
+
+	if (ec->use_adaptive_rx_coalesce != 0) {
+		if ((ec->rx_coalesce_usecs != 0) ||
+		    (ec->tx_max_coalesced_frames != 0) ||
+		    (ec->rx_max_coalesced_frames != 0)) {
+			return -EINVAL;
+		}
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_ADAPT;
+		goto done;
+	}
+
+	if ((ec->tx_max_coalesced_frames != 0) ||
+	    (ec->rx_max_coalesced_frames != 0)) {
+		if ((ec->rx_coalesce_usecs != 0) ||
+		    (ec->use_adaptive_rx_coalesce != 0)) {
+			return -EINVAL;
+		}
+
+		if ((ec->tx_max_coalesced_frames >
+		    VMXNET3_COAL_STATIC_MAX_DEPTH) ||
+		    (ec->rx_max_coalesced_frames >
+		     VMXNET3_COAL_STATIC_MAX_DEPTH)) {
+			return -EINVAL;
+		}
+
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_STATIC;
+
+		adapter->coal_conf->coalPara.coalStatic.tx_comp_depth =
+			(ec->tx_max_coalesced_frames ?
+			 ec->tx_max_coalesced_frames :
+			 VMXNET3_COAL_STATIC_DEFAULT_DEPTH);
+
+		adapter->coal_conf->coalPara.coalStatic.rx_depth =
+			(ec->rx_max_coalesced_frames ?
+			 ec->rx_max_coalesced_frames :
+			 VMXNET3_COAL_STATIC_DEFAULT_DEPTH);
+
+		adapter->coal_conf->coalPara.coalStatic.tx_depth =
+			 VMXNET3_COAL_STATIC_DEFAULT_DEPTH;
+		goto done;
+	}
+
+done:
+	adapter->default_coal_mode = false;
+	if (netif_running(netdev)) {
+		spin_lock_irqsave(&adapter->cmd_lock, flags);
+		cmdInfo->varConf.confVer = 1;
+		cmdInfo->varConf.confLen =
+			cpu_to_le32(sizeof(*adapter->coal_conf));
+		cmdInfo->varConf.confPA  = cpu_to_le64(adapter->coal_conf_pa);
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_SET_COALESCE);
+		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+	}
+
+	return 0;
+}
+
 static const struct ethtool_ops vmxnet3_ethtool_ops = {
 	.get_settings      = vmxnet3_get_settings,
 	.get_drvinfo       = vmxnet3_get_drvinfo,
@@ -706,6 +889,8 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = {
 	.get_wol           = vmxnet3_get_wol,
 	.set_wol           = vmxnet3_set_wol,
 	.get_link          = ethtool_op_get_link,
+	.get_coalesce      = vmxnet3_get_coalesce,
+	.set_coalesce      = vmxnet3_set_coalesce,
 	.get_strings       = vmxnet3_get_strings,
 	.get_sset_count	   = vmxnet3_get_sset_count,
 	.get_ethtool_stats = vmxnet3_get_ethtool_stats,
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index c4825392d64b..74fc03072b87 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <[email protected]>
+ * Maintained by: [email protected]
  *
  */
 
@@ -69,16 +69,20 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.4.7.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.4.9.0-k"
 
 /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01040700
+#define VMXNET3_DRIVER_VERSION_NUM      0x01040900
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
 	#define VMXNET3_RSS
 #endif
 
+#define VMXNET3_REV_3		2	/* Vmxnet3 Rev. 3 */
+#define VMXNET3_REV_2		1	/* Vmxnet3 Rev. 2 */
+#define VMXNET3_REV_1		0	/* Vmxnet3 Rev. 1 */
+
 /*
  * Capabilities
  */
@@ -237,6 +241,7 @@ struct vmxnet3_tx_queue {
 	int                             num_stop;  /* # of times the queue is
 						    * stopped */
 	int				qid;
+	u16				txdata_desc_size;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 enum vmxnet3_rx_buf_type {
@@ -267,15 +272,23 @@ struct vmxnet3_rq_driver_stats {
 	u64 rx_buf_alloc_failure;
 };
 
+struct vmxnet3_rx_data_ring {
+	Vmxnet3_RxDataDesc *base;
+	dma_addr_t basePA;
+	u16 desc_size;
+};
+
 struct vmxnet3_rx_queue {
 	char			name[IFNAMSIZ + 8]; /* To identify interrupt */
 	struct vmxnet3_adapter	  *adapter;
 	struct napi_struct        napi;
 	struct vmxnet3_cmd_ring   rx_ring[2];
+	struct vmxnet3_rx_data_ring data_ring;
 	struct vmxnet3_comp_ring  comp_ring;
 	struct vmxnet3_rx_ctx     rx_ctx;
 	u32 qid;            /* rqID in RCD for buffer from 1st ring */
 	u32 qid2;           /* rqID in RCD for buffer from 2nd ring */
+	u32 dataRingQid;    /* rqID in RCD for buffer from data ring */
 	struct vmxnet3_rx_buf_info     *buf_info[2];
 	dma_addr_t                      buf_info_pa;
 	struct Vmxnet3_RxQueueCtrl            *shared;
@@ -345,6 +358,7 @@ struct vmxnet3_adapter {
 	int		rx_buf_per_pkt;  /* only apply to the 1st ring */
 	dma_addr_t			shared_pa;
 	dma_addr_t queue_desc_pa;
+	dma_addr_t coal_conf_pa;
 
 	/* Wake-on-LAN */
 	u32     wol;
@@ -359,12 +373,21 @@ struct vmxnet3_adapter {
 	u32 rx_ring_size;
 	u32 rx_ring2_size;
 
+	/* Size of buffer in the data ring */
+	u16 txdata_desc_size;
+	u16 rxdata_desc_size;
+
+	bool rxdataring_enabled;
+
 	struct work_struct work;
 
 	unsigned long  state;    /* VMXNET3_STATE_BIT_xxx */
 
 	int share_intr;
 
+	struct Vmxnet3_CoalesceScheme *coal_conf;
+	bool   default_coal_mode;
+
 	dma_addr_t adapter_pa;
 	dma_addr_t pm_conf_pa;
 	dma_addr_t rss_conf_pa;
@@ -387,14 +410,34 @@ struct vmxnet3_adapter {
 #define VMXNET3_GET_ADDR_LO(dma)   ((u32)(dma))
 #define VMXNET3_GET_ADDR_HI(dma)   ((u32)(((u64)(dma)) >> 32))
 
+#define VMXNET3_VERSION_GE_2(adapter) \
+	(adapter->version >= VMXNET3_REV_2 + 1)
+#define VMXNET3_VERSION_GE_3(adapter) \
+	(adapter->version >= VMXNET3_REV_3 + 1)
+
 /* must be a multiple of VMXNET3_RING_SIZE_ALIGN */
 #define VMXNET3_DEF_TX_RING_SIZE    512
 #define VMXNET3_DEF_RX_RING_SIZE    256
 #define VMXNET3_DEF_RX_RING2_SIZE   128
 
+#define VMXNET3_DEF_RXDATA_DESC_SIZE 128
+
 #define VMXNET3_MAX_ETH_HDR_SIZE    22
 #define VMXNET3_MAX_SKB_BUF_SIZE    (3*1024)
 
+#define VMXNET3_GET_RING_IDX(adapter, rqID)		\
+	((rqID >= adapter->num_rx_queues &&		\
+	 rqID < 2 * adapter->num_rx_queues) ? 1 : 0)	\
+
+#define VMXNET3_RX_DATA_RING(adapter, rqID)		\
+	(rqID >= 2 * adapter->num_rx_queues &&		\
+	rqID < 3 * adapter->num_rx_queues)		\
+
+#define VMXNET3_COAL_STATIC_DEFAULT_DEPTH	64
+
+#define VMXNET3_COAL_RBC_RATE(usecs) (1000000 / usecs)
+#define VMXNET3_COAL_RBC_USECS(rbc_rate) (1000000 / rbc_rate)
+
 int
 vmxnet3_quiesce_dev(struct vmxnet3_adapter *adapter);
 
@@ -418,7 +461,8 @@ vmxnet3_set_features(struct net_device *netdev, netdev_features_t features);
 
 int
 vmxnet3_create_queues(struct vmxnet3_adapter *adapter,
-		      u32 tx_ring_size, u32 rx_ring_size, u32 rx_ring2_size);
+		      u32 tx_ring_size, u32 rx_ring_size, u32 rx_ring2_size,
+		      u16 txdata_desc_size, u16 rxdata_desc_size);
 
 void vmxnet3_set_ethtool_ops(struct net_device *netdev);
 
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 1b214ea4619a..1ce7420322ee 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -35,6 +35,7 @@
 #include <net/route.h>
 #include <net/addrconf.h>
 #include <net/l3mdev.h>
+#include <net/fib_rules.h>
 
 #define RT_FL_TOS(oldflp4) \
 	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
@@ -42,6 +43,9 @@
 #define DRV_NAME	"vrf"
 #define DRV_VERSION	"1.0"
 
+#define FIB_RULE_PREF  1000       /* default preference for FIB rules */
+static bool add_fib_rules = true;
+
 struct net_vrf {
 	struct rtable __rcu	*rth;
 	struct rtable __rcu	*rth_local;
@@ -374,23 +378,37 @@ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 
 /* holding rtnl */
-static void vrf_rt6_release(struct net_vrf *vrf)
+static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 {
 	struct rt6_info *rt6 = rtnl_dereference(vrf->rt6);
 	struct rt6_info *rt6_local = rtnl_dereference(vrf->rt6_local);
+	struct net *net = dev_net(dev);
+	struct dst_entry *dst;
 
 	RCU_INIT_POINTER(vrf->rt6, NULL);
 	RCU_INIT_POINTER(vrf->rt6_local, NULL);
 	synchronize_rcu();
 
-	if (rt6)
-		dst_release(&rt6->dst);
+	/* move dev in dst's to loopback so this VRF device can be deleted
+	 * - based on dst_ifdown
+	 */
+	if (rt6) {
+		dst = &rt6->dst;
+		dev_put(dst->dev);
+		dst->dev = net->loopback_dev;
+		dev_hold(dst->dev);
+		dst_release(dst);
+	}
 
 	if (rt6_local) {
 		if (rt6_local->rt6i_idev)
 			in6_dev_put(rt6_local->rt6i_idev);
 
-		dst_release(&rt6_local->dst);
+		dst = &rt6_local->dst;
+		dev_put(dst->dev);
+		dst->dev = net->loopback_dev;
+		dev_hold(dst->dev);
+		dst_release(dst);
 	}
 }
 
@@ -403,6 +421,10 @@ static int vrf_rt6_create(struct net_device *dev)
 	struct rt6_info *rt6, *rt6_local;
 	int rc = -ENOMEM;
 
+	/* IPv6 can be CONFIG enabled and then disabled runtime */
+	if (!ipv6_mod_enabled())
+		return 0;
+
 	rt6i_table = fib6_new_table(net, vrf->tb_id);
 	if (!rt6i_table)
 		goto out;
@@ -441,7 +463,7 @@ out:
 	return rc;
 }
 #else
-static void vrf_rt6_release(struct net_vrf *vrf)
+static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 {
 }
 
@@ -510,20 +532,35 @@ static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 
 /* holding rtnl */
-static void vrf_rtable_release(struct net_vrf *vrf)
+static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf)
 {
 	struct rtable *rth = rtnl_dereference(vrf->rth);
 	struct rtable *rth_local = rtnl_dereference(vrf->rth_local);
+	struct net *net = dev_net(dev);
+	struct dst_entry *dst;
 
 	RCU_INIT_POINTER(vrf->rth, NULL);
 	RCU_INIT_POINTER(vrf->rth_local, NULL);
 	synchronize_rcu();
 
-	if (rth)
-		dst_release(&rth->dst);
+	/* move dev in dst's to loopback so this VRF device can be deleted
+	 * - based on dst_ifdown
+	 */
+	if (rth) {
+		dst = &rth->dst;
+		dev_put(dst->dev);
+		dst->dev = net->loopback_dev;
+		dev_hold(dst->dev);
+		dst_release(dst);
+	}
 
-	if (rth_local)
-		dst_release(&rth_local->dst);
+	if (rth_local) {
+		dst = &rth_local->dst;
+		dev_put(dst->dev);
+		dst->dev = net->loopback_dev;
+		dev_hold(dst->dev);
+		dst_release(dst);
+	}
 }
 
 static int vrf_rtable_create(struct net_device *dev)
@@ -625,8 +662,8 @@ static void vrf_dev_uninit(struct net_device *dev)
 	struct net_device *port_dev;
 	struct list_head *iter;
 
-	vrf_rtable_release(vrf);
-	vrf_rt6_release(vrf);
+	vrf_rtable_release(dev, vrf);
+	vrf_rt6_release(dev, vrf);
 
 	netdev_for_each_lower_dev(dev, port_dev, iter)
 		vrf_del_slave(dev, port_dev);
@@ -657,11 +694,11 @@ static int vrf_dev_init(struct net_device *dev)
 
 	/* similarly, oper state is irrelevant; set to up to avoid confusion */
 	dev->operstate = IF_OPER_UP;
-
+	netdev_lockdep_set_classes(dev);
 	return 0;
 
 out_rth:
-	vrf_rtable_release(vrf);
+	vrf_rtable_release(dev, vrf);
 out_stats:
 	free_percpu(dev->dstats);
 	dev->dstats = NULL;
@@ -742,6 +779,25 @@ static int vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4)
 	return rc;
 }
 
+static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	return 0;
+}
+
+static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook,
+				      struct sk_buff *skb,
+				      struct net_device *dev)
+{
+	struct net *net = dev_net(dev);
+
+	nf_reset(skb);
+
+	if (NF_HOOK(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) < 0)
+		skb = NULL;    /* kfree_skb(skb) handled by nf code */
+
+	return skb;
+}
+
 #if IS_ENABLED(CONFIG_IPV6)
 /* neighbor handling is done with actual device; do not want
  * to flip skb->dev for those ndisc packets. This really fails
@@ -777,9 +833,63 @@ out:
 	return rc;
 }
 
+static struct rt6_info *vrf_ip6_route_lookup(struct net *net,
+					     const struct net_device *dev,
+					     struct flowi6 *fl6,
+					     int ifindex,
+					     int flags)
+{
+	struct net_vrf *vrf = netdev_priv(dev);
+	struct fib6_table *table = NULL;
+	struct rt6_info *rt6;
+
+	rcu_read_lock();
+
+	/* fib6_table does not have a refcnt and can not be freed */
+	rt6 = rcu_dereference(vrf->rt6);
+	if (likely(rt6))
+		table = rt6->rt6i_table;
+
+	rcu_read_unlock();
+
+	if (!table)
+		return NULL;
+
+	return ip6_pol_route(net, table, ifindex, fl6, flags);
+}
+
+static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
+			      int ifindex)
+{
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct flowi6 fl6 = {
+		.daddr          = iph->daddr,
+		.saddr          = iph->saddr,
+		.flowlabel      = ip6_flowinfo(iph),
+		.flowi6_mark    = skb->mark,
+		.flowi6_proto   = iph->nexthdr,
+		.flowi6_iif     = ifindex,
+	};
+	struct net *net = dev_net(vrf_dev);
+	struct rt6_info *rt6;
+
+	rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex,
+				   RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE);
+	if (unlikely(!rt6))
+		return;
+
+	if (unlikely(&rt6->dst == &net->ipv6.ip6_null_entry->dst))
+		return;
+
+	skb_dst_set(skb, &rt6->dst);
+}
+
 static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 				   struct sk_buff *skb)
 {
+	int orig_iif = skb->skb_iif;
+	bool need_strict;
+
 	/* loopback traffic; do not push through packet taps again.
 	 * Reset pkt_type for upper layers to process skb
 	 */
@@ -790,8 +900,11 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 		goto out;
 	}
 
-	/* if packet is NDISC keep the ingress interface */
-	if (!ipv6_ndisc_frame(skb)) {
+	/* if packet is NDISC or addressed to multicast or link-local
+	 * then keep the ingress interface
+	 */
+	need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr);
+	if (!ipv6_ndisc_frame(skb) && !need_strict) {
 		skb->dev = vrf_dev;
 		skb->skb_iif = vrf_dev->ifindex;
 
@@ -802,6 +915,10 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 		IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
 	}
 
+	if (need_strict)
+		vrf_ip6_input_dst(skb, vrf_dev, orig_iif);
+
+	skb = vrf_rcv_nfhook(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, vrf_dev);
 out:
 	return skb;
 }
@@ -832,6 +949,7 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
 	dev_queue_xmit_nit(skb, vrf_dev);
 	skb_pull(skb, skb->mac_len);
 
+	skb = vrf_rcv_nfhook(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, vrf_dev);
 out:
 	return skb;
 }
@@ -853,13 +971,37 @@ static struct sk_buff *vrf_l3_rcv(struct net_device *vrf_dev,
 
 #if IS_ENABLED(CONFIG_IPV6)
 static struct dst_entry *vrf_get_rt6_dst(const struct net_device *dev,
-					 const struct flowi6 *fl6)
+					 struct flowi6 *fl6)
 {
+	bool need_strict = rt6_need_strict(&fl6->daddr);
+	struct net_vrf *vrf = netdev_priv(dev);
+	struct net *net = dev_net(dev);
 	struct dst_entry *dst = NULL;
+	struct rt6_info *rt;
 
-	if (!(fl6->flowi6_flags & FLOWI_FLAG_L3MDEV_SRC)) {
-		struct net_vrf *vrf = netdev_priv(dev);
-		struct rt6_info *rt;
+	/* send to link-local or multicast address */
+	if (need_strict) {
+		int flags = RT6_LOOKUP_F_IFACE;
+
+		/* VRF device does not have a link-local address and
+		 * sending packets to link-local or mcast addresses over
+		 * a VRF device does not make sense
+		 */
+		if (fl6->flowi6_oif == dev->ifindex) {
+			struct dst_entry *dst = &net->ipv6.ip6_null_entry->dst;
+
+			dst_hold(dst);
+			return dst;
+		}
+
+		if (!ipv6_addr_any(&fl6->saddr))
+			flags |= RT6_LOOKUP_F_HAS_SADDR;
+
+		rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, flags);
+		if (rt)
+			dst = &rt->dst;
+
+	} else if (!(fl6->flowi6_flags & FLOWI_FLAG_L3MDEV_SRC)) {
 
 		rcu_read_lock();
 
@@ -872,8 +1014,52 @@ static struct dst_entry *vrf_get_rt6_dst(const struct net_device *dev,
 		rcu_read_unlock();
 	}
 
+	/* make sure oif is set to VRF device for lookup */
+	if (!need_strict)
+		fl6->flowi6_oif = dev->ifindex;
+
 	return dst;
 }
+
+/* called under rcu_read_lock */
+static int vrf_get_saddr6(struct net_device *dev, const struct sock *sk,
+			  struct flowi6 *fl6)
+{
+	struct net *net = dev_net(dev);
+	struct dst_entry *dst;
+	struct rt6_info *rt;
+	int err;
+
+	if (rt6_need_strict(&fl6->daddr)) {
+		rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif,
+					  RT6_LOOKUP_F_IFACE);
+		if (unlikely(!rt))
+			return 0;
+
+		dst = &rt->dst;
+	} else {
+		__u8 flags = fl6->flowi6_flags;
+
+		fl6->flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC;
+		fl6->flowi6_flags |= FLOWI_FLAG_SKIP_NH_OIF;
+
+		dst = ip6_route_output(net, sk, fl6);
+		rt = (struct rt6_info *)dst;
+
+		fl6->flowi6_flags = flags;
+	}
+
+	err = dst->error;
+	if (!err) {
+		err = ip6_route_get_saddr(net, rt, &fl6->daddr,
+					  sk ? inet6_sk(sk)->srcprefs : 0,
+					  &fl6->saddr);
+	}
+
+	dst_release(dst);
+
+	return err;
+}
 #endif
 
 static const struct l3mdev_ops vrf_l3mdev_ops = {
@@ -883,6 +1069,7 @@ static const struct l3mdev_ops vrf_l3mdev_ops = {
 	.l3mdev_l3_rcv		= vrf_l3_rcv,
 #if IS_ENABLED(CONFIG_IPV6)
 	.l3mdev_get_rt6_dst	= vrf_get_rt6_dst,
+	.l3mdev_get_saddr6	= vrf_get_saddr6,
 #endif
 };
 
@@ -897,6 +1084,94 @@ static const struct ethtool_ops vrf_ethtool_ops = {
 	.get_drvinfo	= vrf_get_drvinfo,
 };
 
+static inline size_t vrf_fib_rule_nl_size(void)
+{
+	size_t sz;
+
+	sz  = NLMSG_ALIGN(sizeof(struct fib_rule_hdr));
+	sz += nla_total_size(sizeof(u8));	/* FRA_L3MDEV */
+	sz += nla_total_size(sizeof(u32));	/* FRA_PRIORITY */
+
+	return sz;
+}
+
+static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
+{
+	struct fib_rule_hdr *frh;
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	int err;
+
+	if (family == AF_INET6 && !ipv6_mod_enabled())
+		return 0;
+
+	skb = nlmsg_new(vrf_fib_rule_nl_size(), GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(skb, 0, 0, 0, sizeof(*frh), 0);
+	if (!nlh)
+		goto nla_put_failure;
+
+	/* rule only needs to appear once */
+	nlh->nlmsg_flags &= NLM_F_EXCL;
+
+	frh = nlmsg_data(nlh);
+	memset(frh, 0, sizeof(*frh));
+	frh->family = family;
+	frh->action = FR_ACT_TO_TBL;
+
+	if (nla_put_u32(skb, FRA_L3MDEV, 1))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF))
+		goto nla_put_failure;
+
+	nlmsg_end(skb, nlh);
+
+	/* fib_nl_{new,del}rule handling looks for net from skb->sk */
+	skb->sk = dev_net(dev)->rtnl;
+	if (add_it) {
+		err = fib_nl_newrule(skb, nlh);
+		if (err == -EEXIST)
+			err = 0;
+	} else {
+		err = fib_nl_delrule(skb, nlh);
+		if (err == -ENOENT)
+			err = 0;
+	}
+	nlmsg_free(skb);
+
+	return err;
+
+nla_put_failure:
+	nlmsg_free(skb);
+
+	return -EMSGSIZE;
+}
+
+static int vrf_add_fib_rules(const struct net_device *dev)
+{
+	int err;
+
+	err = vrf_fib_rule(dev, AF_INET,  true);
+	if (err < 0)
+		goto out_err;
+
+	err = vrf_fib_rule(dev, AF_INET6, true);
+	if (err < 0)
+		goto ipv6_err;
+
+	return 0;
+
+ipv6_err:
+	vrf_fib_rule(dev, AF_INET,  false);
+
+out_err:
+	netdev_err(dev, "Failed to add FIB rules.\n");
+	return err;
+}
+
 static void vrf_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -915,6 +1190,20 @@ static void vrf_setup(struct net_device *dev)
 
 	/* don't allow vrf devices to change network namespaces. */
 	dev->features |= NETIF_F_NETNS_LOCAL;
+
+	/* does not make sense for a VLAN to be added to a vrf device */
+	dev->features   |= NETIF_F_VLAN_CHALLENGED;
+
+	/* enable offload features */
+	dev->features   |= NETIF_F_GSO_SOFTWARE;
+	dev->features   |= NETIF_F_RXCSUM | NETIF_F_HW_CSUM;
+	dev->features   |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA;
+
+	dev->hw_features = dev->features;
+	dev->hw_enc_features = dev->features;
+
+	/* default to no qdisc; user can add if desired */
+	dev->priv_flags |= IFF_NO_QUEUE;
 }
 
 static int vrf_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -937,6 +1226,7 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 		       struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net_vrf *vrf = netdev_priv(dev);
+	int err;
 
 	if (!data || !data[IFLA_VRF_TABLE])
 		return -EINVAL;
@@ -945,7 +1235,21 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 
 	dev->priv_flags |= IFF_L3MDEV_MASTER;
 
-	return register_netdevice(dev);
+	err = register_netdevice(dev);
+	if (err)
+		goto out;
+
+	if (add_fib_rules) {
+		err = vrf_add_fib_rules(dev);
+		if (err) {
+			unregister_netdevice(dev);
+			goto out;
+		}
+		add_fib_rules = false;
+	}
+
+out:
+	return err;
 }
 
 static size_t vrf_nl_getsize(const struct net_device *dev)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index f999db2f97b4..ae7455da1687 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -11,32 +11,18 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
-#include <linux/types.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
-#include <linux/skbuff.h>
-#include <linux/rculist.h>
-#include <linux/netdevice.h>
-#include <linux/in.h>
-#include <linux/ip.h>
 #include <linux/udp.h>
 #include <linux/igmp.h>
-#include <linux/etherdevice.h>
 #include <linux/if_ether.h>
-#include <linux/if_vlan.h>
-#include <linux/hash.h>
 #include <linux/ethtool.h>
 #include <net/arp.h>
 #include <net/ndisc.h>
 #include <net/ip.h>
-#include <net/ip_tunnels.h>
 #include <net/icmp.h>
-#include <net/udp.h>
-#include <net/udp_tunnel.h>
 #include <net/rtnetlink.h>
-#include <net/route.h>
-#include <net/dsfield.h>
 #include <net/inet_ecn.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
@@ -44,12 +30,9 @@
 #include <net/protocol.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
-#include <net/ipv6.h>
-#include <net/addrconf.h>
 #include <net/ip6_tunnel.h>
 #include <net/ip6_checksum.h>
 #endif
-#include <net/dst_metadata.h>
 
 #define VXLAN_VERSION	"0.1"
 
@@ -619,42 +602,6 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
 }
 
-/* Notify netdevs that UDP port started listening */
-static void vxlan_notify_add_rx_port(struct vxlan_sock *vs)
-{
-	struct net_device *dev;
-	struct sock *sk = vs->sock->sk;
-	struct net *net = sock_net(sk);
-	sa_family_t sa_family = vxlan_get_sk_family(vs);
-	__be16 port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (dev->netdev_ops->ndo_add_vxlan_port)
-			dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family,
-							    port);
-	}
-	rcu_read_unlock();
-}
-
-/* Notify netdevs that UDP port is no more listening */
-static void vxlan_notify_del_rx_port(struct vxlan_sock *vs)
-{
-	struct net_device *dev;
-	struct sock *sk = vs->sock->sk;
-	struct net *net = sock_net(sk);
-	sa_family_t sa_family = vxlan_get_sk_family(vs);
-	__be16 port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (dev->netdev_ops->ndo_del_vxlan_port)
-			dev->netdev_ops->ndo_del_vxlan_port(dev, sa_family,
-							    port);
-	}
-	rcu_read_unlock();
-}
-
 /* Add new entry to forwarding table -- assumes lock held */
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
@@ -1050,7 +997,10 @@ static bool __vxlan_sock_release_prep(struct vxlan_sock *vs)
 	vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id);
 	spin_lock(&vn->sock_lock);
 	hlist_del_rcu(&vs->hlist);
-	vxlan_notify_del_rx_port(vs);
+	udp_tunnel_notify_del_rx_port(vs->sock,
+				      (vs->flags & VXLAN_F_GPE) ?
+				      UDP_TUNNEL_TYPE_VXLAN_GPE :
+				      UDP_TUNNEL_TYPE_VXLAN);
 	spin_unlock(&vn->sock_lock);
 
 	return true;
@@ -2525,30 +2475,24 @@ static struct device_type vxlan_type = {
 	.name = "vxlan",
 };
 
-/* Calls the ndo_add_vxlan_port of the caller in order to
+/* Calls the ndo_add_udp_enc_port of the caller in order to
  * supply the listening VXLAN udp ports. Callers are expected
- * to implement the ndo_add_vxlan_port.
+ * to implement the ndo_add_udp_enc_port.
  */
 static void vxlan_push_rx_ports(struct net_device *dev)
 {
 	struct vxlan_sock *vs;
 	struct net *net = dev_net(dev);
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
-	sa_family_t sa_family;
-	__be16 port;
 	unsigned int i;
 
-	if (!dev->netdev_ops->ndo_add_vxlan_port)
-		return;
-
 	spin_lock(&vn->sock_lock);
 	for (i = 0; i < PORT_HASH_SIZE; ++i) {
-		hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) {
-			port = inet_sk(vs->sock->sk)->inet_sport;
-			sa_family = vxlan_get_sk_family(vs);
-			dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family,
-							    port);
-		}
+		hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist)
+			udp_tunnel_push_rx_port(dev, vs->sock,
+						(vs->flags & VXLAN_F_GPE) ?
+						UDP_TUNNEL_TYPE_VXLAN_GPE :
+						UDP_TUNNEL_TYPE_VXLAN);
 	}
 	spin_unlock(&vn->sock_lock);
 }
@@ -2750,7 +2694,10 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
 
 	spin_lock(&vn->sock_lock);
 	hlist_add_head_rcu(&vs->hlist, vs_head(net, port));
-	vxlan_notify_add_rx_port(vs);
+	udp_tunnel_notify_add_rx_port(sock,
+				      (vs->flags & VXLAN_F_GPE) ?
+				      UDP_TUNNEL_TYPE_VXLAN_GPE :
+				      UDP_TUNNEL_TYPE_VXLAN);
 	spin_unlock(&vn->sock_lock);
 
 	/* Mark socket as an encapsulation socket. */
@@ -2952,30 +2899,6 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	return 0;
 }
 
-struct net_device *vxlan_dev_create(struct net *net, const char *name,
-				    u8 name_assign_type, struct vxlan_config *conf)
-{
-	struct nlattr *tb[IFLA_MAX+1];
-	struct net_device *dev;
-	int err;
-
-	memset(&tb, 0, sizeof(tb));
-
-	dev = rtnl_create_link(net, name, name_assign_type,
-			       &vxlan_link_ops, tb);
-	if (IS_ERR(dev))
-		return dev;
-
-	err = vxlan_dev_configure(net, dev, conf);
-	if (err < 0) {
-		free_netdev(dev);
-		return ERR_PTR(err);
-	}
-
-	return dev;
-}
-EXPORT_SYMBOL_GPL(vxlan_dev_create);
-
 static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[])
 {
@@ -3268,6 +3191,40 @@ static struct rtnl_link_ops vxlan_link_ops __read_mostly = {
 	.get_link_net	= vxlan_get_link_net,
 };
 
+struct net_device *vxlan_dev_create(struct net *net, const char *name,
+				    u8 name_assign_type,
+				    struct vxlan_config *conf)
+{
+	struct nlattr *tb[IFLA_MAX + 1];
+	struct net_device *dev;
+	int err;
+
+	memset(&tb, 0, sizeof(tb));
+
+	dev = rtnl_create_link(net, name, name_assign_type,
+			       &vxlan_link_ops, tb);
+	if (IS_ERR(dev))
+		return dev;
+
+	err = vxlan_dev_configure(net, dev, conf);
+	if (err < 0) {
+		free_netdev(dev);
+		return ERR_PTR(err);
+	}
+
+	err = rtnl_configure_link(dev, NULL);
+	if (err < 0) {
+		LIST_HEAD(list_kill);
+
+		vxlan_dellink(dev, &list_kill);
+		unregister_netdevice_many(&list_kill);
+		return ERR_PTR(err);
+	}
+
+	return dev;
+}
+EXPORT_SYMBOL_GPL(vxlan_dev_create);
+
 static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn,
 					     struct net_device *dev)
 {
@@ -3298,7 +3255,7 @@ static int vxlan_netdevice_event(struct notifier_block *unused,
 
 	if (event == NETDEV_UNREGISTER)
 		vxlan_handle_lowerdev_unregister(vn, dev);
-	else if (event == NETDEV_OFFLOAD_PUSH_VXLAN)
+	else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO)
 		vxlan_push_rx_ports(dev);
 
 	return NOTIFY_DONE;
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index a2fdd15f285a..33ab3345d333 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -280,6 +280,28 @@ config DSCC4
 	  To compile this driver as a module, choose M here: the
 	  module will be called dscc4.
 
+config FSL_UCC_HDLC
+	tristate "Freescale QUICC Engine HDLC support"
+	depends on HDLC
+	depends on QUICC_ENGINE
+	help
+	  Driver for Freescale QUICC Engine HDLC controller. The driver
+	  supports HDLC in NMSI and TDM mode.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called fsl_ucc_hdlc.
+
+config SLIC_DS26522
+	tristate "Slic Maxim ds26522 card support"
+	depends on SPI
+	depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE
+	help
+	  This module initializes and configures the slic maxim card
+	  in T1 or E1 mode.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called slic_ds26522.
+
 config DSCC4_PCISYNC
 	bool "Etinc PCISYNC features"
 	depends on DSCC4
diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile
index c135ef47cbca..73c2326603fc 100644
--- a/drivers/net/wan/Makefile
+++ b/drivers/net/wan/Makefile
@@ -32,6 +32,8 @@ obj-$(CONFIG_WANXL)		+= wanxl.o
 obj-$(CONFIG_PCI200SYN)		+= pci200syn.o
 obj-$(CONFIG_PC300TOO)		+= pc300too.o
 obj-$(CONFIG_IXP4XX_HSS)	+= ixp4xx_hss.o
+obj-$(CONFIG_FSL_UCC_HDLC)	+= fsl_ucc_hdlc.o
+obj-$(CONFIG_SLIC_DS26522)	+= slic_ds26522.o
 
 clean-files := wanxlfw.inc
 $(obj)/wanxl.o:	$(obj)/wanxlfw.inc
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
new file mode 100644
index 000000000000..19174ac1e338
--- /dev/null
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -0,0 +1,1192 @@
+/* Freescale QUICC Engine HDLC Device Driver
+ *
+ * Copyright 2016 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/hdlc.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/sched.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <soc/fsl/qe/qe_tdm.h>
+#include <uapi/linux/if_arp.h>
+
+#include "fsl_ucc_hdlc.h"
+
+#define DRV_DESC "Freescale QE UCC HDLC Driver"
+#define DRV_NAME "ucc_hdlc"
+
+#define TDM_PPPOHT_SLIC_MAXIN
+#define BROKEN_FRAME_INFO
+
+static struct ucc_tdm_info utdm_primary_info = {
+	.uf_info = {
+		.tsa = 0,
+		.cdp = 0,
+		.cds = 1,
+		.ctsp = 1,
+		.ctss = 1,
+		.revd = 0,
+		.urfs = 256,
+		.utfs = 256,
+		.urfet = 128,
+		.urfset = 192,
+		.utfet = 128,
+		.utftt = 0x40,
+		.ufpt = 256,
+		.mode = UCC_FAST_PROTOCOL_MODE_HDLC,
+		.ttx_trx = UCC_FAST_GUMR_TRANSPARENT_TTX_TRX_NORMAL,
+		.tenc = UCC_FAST_TX_ENCODING_NRZ,
+		.renc = UCC_FAST_RX_ENCODING_NRZ,
+		.tcrc = UCC_FAST_16_BIT_CRC,
+		.synl = UCC_FAST_SYNC_LEN_NOT_USED,
+	},
+
+	.si_info = {
+#ifdef TDM_PPPOHT_SLIC_MAXIN
+		.simr_rfsd = 1,
+		.simr_tfsd = 2,
+#else
+		.simr_rfsd = 0,
+		.simr_tfsd = 0,
+#endif
+		.simr_crt = 0,
+		.simr_sl = 0,
+		.simr_ce = 1,
+		.simr_fe = 1,
+		.simr_gm = 0,
+	},
+};
+
+static struct ucc_tdm_info utdm_info[MAX_HDLC_NUM];
+
+static int uhdlc_init(struct ucc_hdlc_private *priv)
+{
+	struct ucc_tdm_info *ut_info;
+	struct ucc_fast_info *uf_info;
+	u32 cecr_subblock;
+	u16 bd_status;
+	int ret, i;
+	void *bd_buffer;
+	dma_addr_t bd_dma_addr;
+	u32 riptr;
+	u32 tiptr;
+	u32 gumr;
+
+	ut_info = priv->ut_info;
+	uf_info = &ut_info->uf_info;
+
+	if (priv->tsa) {
+		uf_info->tsa = 1;
+		uf_info->ctsp = 1;
+	}
+	uf_info->uccm_mask = ((UCC_HDLC_UCCE_RXB | UCC_HDLC_UCCE_RXF |
+				UCC_HDLC_UCCE_TXB) << 16);
+
+	ret = ucc_fast_init(uf_info, &priv->uccf);
+	if (ret) {
+		dev_err(priv->dev, "Failed to init uccf.");
+		return ret;
+	}
+
+	priv->uf_regs = priv->uccf->uf_regs;
+	ucc_fast_disable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+	/* Loopback mode */
+	if (priv->loopback) {
+		dev_info(priv->dev, "Loopback Mode\n");
+		gumr = ioread32be(&priv->uf_regs->gumr);
+		gumr |= (UCC_FAST_GUMR_LOOPBACK | UCC_FAST_GUMR_CDS |
+			 UCC_FAST_GUMR_TCI);
+		gumr &= ~(UCC_FAST_GUMR_CTSP | UCC_FAST_GUMR_RSYN);
+		iowrite32be(gumr, &priv->uf_regs->gumr);
+	}
+
+	/* Initialize SI */
+	if (priv->tsa)
+		ucc_tdm_init(priv->utdm, priv->ut_info);
+
+	/* Write to QE CECR, UCCx channel to Stop Transmission */
+	cecr_subblock = ucc_fast_get_qe_cr_subblock(uf_info->ucc_num);
+	ret = qe_issue_cmd(QE_STOP_TX, cecr_subblock,
+			   QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+	/* Set UPSMR normal mode (need fixed)*/
+	iowrite32be(0, &priv->uf_regs->upsmr);
+
+	priv->rx_ring_size = RX_BD_RING_LEN;
+	priv->tx_ring_size = TX_BD_RING_LEN;
+	/* Alloc Rx BD */
+	priv->rx_bd_base = dma_alloc_coherent(priv->dev,
+			RX_BD_RING_LEN * sizeof(struct qe_bd *),
+			&priv->dma_rx_bd, GFP_KERNEL);
+
+	if (!priv->rx_bd_base) {
+		dev_err(priv->dev, "Cannot allocate MURAM memory for RxBDs\n");
+		ret = -ENOMEM;
+		goto rxbd_alloc_error;
+	}
+
+	/* Alloc Tx BD */
+	priv->tx_bd_base = dma_alloc_coherent(priv->dev,
+			TX_BD_RING_LEN * sizeof(struct qe_bd *),
+			&priv->dma_tx_bd, GFP_KERNEL);
+
+	if (!priv->tx_bd_base) {
+		dev_err(priv->dev, "Cannot allocate MURAM memory for TxBDs\n");
+		ret = -ENOMEM;
+		goto txbd_alloc_error;
+	}
+
+	/* Alloc parameter ram for ucc hdlc */
+	priv->ucc_pram_offset = qe_muram_alloc(sizeof(priv->ucc_pram),
+				ALIGNMENT_OF_UCC_HDLC_PRAM);
+
+	if (priv->ucc_pram_offset < 0) {
+		dev_err(priv->dev, "Can not allocate MURAM for hdlc prameter.\n");
+		ret = -ENOMEM;
+		goto pram_alloc_error;
+	}
+
+	priv->rx_skbuff = kzalloc(priv->rx_ring_size * sizeof(*priv->rx_skbuff),
+				  GFP_KERNEL);
+	if (!priv->rx_skbuff)
+		goto rx_skb_alloc_error;
+
+	priv->tx_skbuff = kzalloc(priv->tx_ring_size * sizeof(*priv->tx_skbuff),
+				  GFP_KERNEL);
+	if (!priv->tx_skbuff)
+		goto tx_skb_alloc_error;
+
+	priv->skb_curtx = 0;
+	priv->skb_dirtytx = 0;
+	priv->curtx_bd = priv->tx_bd_base;
+	priv->dirty_tx = priv->tx_bd_base;
+	priv->currx_bd = priv->rx_bd_base;
+	priv->currx_bdnum = 0;
+
+	/* init parameter base */
+	cecr_subblock = ucc_fast_get_qe_cr_subblock(uf_info->ucc_num);
+	ret = qe_issue_cmd(QE_ASSIGN_PAGE_TO_DEVICE, cecr_subblock,
+			   QE_CR_PROTOCOL_UNSPECIFIED, priv->ucc_pram_offset);
+
+	priv->ucc_pram = (struct ucc_hdlc_param __iomem *)
+					qe_muram_addr(priv->ucc_pram_offset);
+
+	/* Zero out parameter ram */
+	memset_io(priv->ucc_pram, 0, sizeof(struct ucc_hdlc_param));
+
+	/* Alloc riptr, tiptr */
+	riptr = qe_muram_alloc(32, 32);
+	if (riptr < 0) {
+		dev_err(priv->dev, "Cannot allocate MURAM mem for Receive internal temp data pointer\n");
+		ret = -ENOMEM;
+		goto riptr_alloc_error;
+	}
+
+	tiptr = qe_muram_alloc(32, 32);
+	if (tiptr < 0) {
+		dev_err(priv->dev, "Cannot allocate MURAM mem for Transmit internal temp data pointer\n");
+		ret = -ENOMEM;
+		goto tiptr_alloc_error;
+	}
+
+	/* Set RIPTR, TIPTR */
+	iowrite16be(riptr, &priv->ucc_pram->riptr);
+	iowrite16be(tiptr, &priv->ucc_pram->tiptr);
+
+	/* Set MRBLR */
+	iowrite16be(MAX_RX_BUF_LENGTH, &priv->ucc_pram->mrblr);
+
+	/* Set RBASE, TBASE */
+	iowrite32be(priv->dma_rx_bd, &priv->ucc_pram->rbase);
+	iowrite32be(priv->dma_tx_bd, &priv->ucc_pram->tbase);
+
+	/* Set RSTATE, TSTATE */
+	iowrite32be(BMR_GBL | BMR_BIG_ENDIAN, &priv->ucc_pram->rstate);
+	iowrite32be(BMR_GBL | BMR_BIG_ENDIAN, &priv->ucc_pram->tstate);
+
+	/* Set C_MASK, C_PRES for 16bit CRC */
+	iowrite32be(CRC_16BIT_MASK, &priv->ucc_pram->c_mask);
+	iowrite32be(CRC_16BIT_PRES, &priv->ucc_pram->c_pres);
+
+	iowrite16be(MAX_FRAME_LENGTH, &priv->ucc_pram->mflr);
+	iowrite16be(DEFAULT_RFTHR, &priv->ucc_pram->rfthr);
+	iowrite16be(DEFAULT_RFTHR, &priv->ucc_pram->rfcnt);
+	iowrite16be(DEFAULT_ADDR_MASK, &priv->ucc_pram->hmask);
+	iowrite16be(DEFAULT_HDLC_ADDR, &priv->ucc_pram->haddr1);
+	iowrite16be(DEFAULT_HDLC_ADDR, &priv->ucc_pram->haddr2);
+	iowrite16be(DEFAULT_HDLC_ADDR, &priv->ucc_pram->haddr3);
+	iowrite16be(DEFAULT_HDLC_ADDR, &priv->ucc_pram->haddr4);
+
+	/* Get BD buffer */
+	bd_buffer = dma_alloc_coherent(priv->dev,
+				       (RX_BD_RING_LEN + TX_BD_RING_LEN) *
+				       MAX_RX_BUF_LENGTH,
+				       &bd_dma_addr, GFP_KERNEL);
+
+	if (!bd_buffer) {
+		dev_err(priv->dev, "Could not allocate buffer descriptors\n");
+		ret = -ENOMEM;
+		goto bd_alloc_error;
+	}
+
+	memset(bd_buffer, 0, (RX_BD_RING_LEN + TX_BD_RING_LEN)
+			* MAX_RX_BUF_LENGTH);
+
+	priv->rx_buffer = bd_buffer;
+	priv->tx_buffer = bd_buffer + RX_BD_RING_LEN * MAX_RX_BUF_LENGTH;
+
+	priv->dma_rx_addr = bd_dma_addr;
+	priv->dma_tx_addr = bd_dma_addr + RX_BD_RING_LEN * MAX_RX_BUF_LENGTH;
+
+	for (i = 0; i < RX_BD_RING_LEN; i++) {
+		if (i < (RX_BD_RING_LEN - 1))
+			bd_status = R_E_S | R_I_S;
+		else
+			bd_status = R_E_S | R_I_S | R_W_S;
+
+		iowrite16be(bd_status, &priv->rx_bd_base[i].status);
+		iowrite32be(priv->dma_rx_addr + i * MAX_RX_BUF_LENGTH,
+			    &priv->rx_bd_base[i].buf);
+	}
+
+	for (i = 0; i < TX_BD_RING_LEN; i++) {
+		if (i < (TX_BD_RING_LEN - 1))
+			bd_status =  T_I_S | T_TC_S;
+		else
+			bd_status =  T_I_S | T_TC_S | T_W_S;
+
+		iowrite16be(bd_status, &priv->tx_bd_base[i].status);
+		iowrite32be(priv->dma_tx_addr + i * MAX_RX_BUF_LENGTH,
+			    &priv->tx_bd_base[i].buf);
+	}
+
+	return 0;
+
+bd_alloc_error:
+	qe_muram_free(tiptr);
+tiptr_alloc_error:
+	qe_muram_free(riptr);
+riptr_alloc_error:
+	kfree(priv->tx_skbuff);
+tx_skb_alloc_error:
+	kfree(priv->rx_skbuff);
+rx_skb_alloc_error:
+	qe_muram_free(priv->ucc_pram_offset);
+pram_alloc_error:
+	dma_free_coherent(priv->dev,
+			  TX_BD_RING_LEN * sizeof(struct qe_bd),
+			  priv->tx_bd_base, priv->dma_tx_bd);
+txbd_alloc_error:
+	dma_free_coherent(priv->dev,
+			  RX_BD_RING_LEN * sizeof(struct qe_bd),
+			  priv->rx_bd_base, priv->dma_rx_bd);
+rxbd_alloc_error:
+	ucc_fast_free(priv->uccf);
+
+	return ret;
+}
+
+static netdev_tx_t ucc_hdlc_tx(struct sk_buff *skb, struct net_device *dev)
+{
+	hdlc_device *hdlc = dev_to_hdlc(dev);
+	struct ucc_hdlc_private *priv = (struct ucc_hdlc_private *)hdlc->priv;
+	struct qe_bd __iomem *bd;
+	u16 bd_status;
+	unsigned long flags;
+	u8 *send_buf;
+	int i;
+	u16 *proto_head;
+
+	switch (dev->type) {
+	case ARPHRD_RAWHDLC:
+		if (skb_headroom(skb) < HDLC_HEAD_LEN) {
+			dev->stats.tx_dropped++;
+			dev_kfree_skb(skb);
+			netdev_err(dev, "No enough space for hdlc head\n");
+			return -ENOMEM;
+		}
+
+		skb_push(skb, HDLC_HEAD_LEN);
+
+		proto_head = (u16 *)skb->data;
+		*proto_head = htons(DEFAULT_HDLC_HEAD);
+
+		dev->stats.tx_bytes += skb->len;
+		break;
+
+	case ARPHRD_PPP:
+		proto_head = (u16 *)skb->data;
+		if (*proto_head != htons(DEFAULT_PPP_HEAD)) {
+			dev->stats.tx_dropped++;
+			dev_kfree_skb(skb);
+			netdev_err(dev, "Wrong ppp header\n");
+			return -ENOMEM;
+		}
+
+		dev->stats.tx_bytes += skb->len;
+		break;
+
+	default:
+		dev->stats.tx_dropped++;
+		dev_kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	pr_info("Tx data skb->len:%d ", skb->len);
+	send_buf = (u8 *)skb->data;
+	pr_info("\nTransmitted data:\n");
+	for (i = 0; i < 16; i++) {
+		if (i == skb->len)
+			pr_info("++++");
+		else
+		pr_info("%02x\n", send_buf[i]);
+	}
+	spin_lock_irqsave(&priv->lock, flags);
+
+	/* Start from the next BD that should be filled */
+	bd = priv->curtx_bd;
+	bd_status = ioread16be(&bd->status);
+	/* Save the skb pointer so we can free it later */
+	priv->tx_skbuff[priv->skb_curtx] = skb;
+
+	/* Update the current skb pointer (wrapping if this was the last) */
+	priv->skb_curtx =
+	    (priv->skb_curtx + 1) & TX_RING_MOD_MASK(TX_BD_RING_LEN);
+
+	/* copy skb data to tx buffer for sdma processing */
+	memcpy(priv->tx_buffer + (be32_to_cpu(bd->buf) - priv->dma_tx_addr),
+	       skb->data, skb->len);
+
+	/* set bd status and length */
+	bd_status = (bd_status & T_W_S) | T_R_S | T_I_S | T_L_S | T_TC_S;
+
+	iowrite16be(bd_status, &bd->status);
+	iowrite16be(skb->len, &bd->length);
+
+	/* Move to next BD in the ring */
+	if (!(bd_status & T_W_S))
+		bd += 1;
+	else
+		bd = priv->tx_bd_base;
+
+	if (bd == priv->dirty_tx) {
+		if (!netif_queue_stopped(dev))
+			netif_stop_queue(dev);
+	}
+
+	priv->curtx_bd = bd;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return NETDEV_TX_OK;
+}
+
+static int hdlc_tx_done(struct ucc_hdlc_private *priv)
+{
+	/* Start from the next BD that should be filled */
+	struct net_device *dev = priv->ndev;
+	struct qe_bd *bd;		/* BD pointer */
+	u16 bd_status;
+
+	bd = priv->dirty_tx;
+	bd_status = ioread16be(&bd->status);
+
+	/* Normal processing. */
+	while ((bd_status & T_R_S) == 0) {
+		struct sk_buff *skb;
+
+		/* BD contains already transmitted buffer.   */
+		/* Handle the transmitted buffer and release */
+		/* the BD to be used with the current frame  */
+
+		skb = priv->tx_skbuff[priv->skb_dirtytx];
+		if (!skb)
+			break;
+		pr_info("TxBD: %x\n", bd_status);
+		dev->stats.tx_packets++;
+		memset(priv->tx_buffer +
+		       (be32_to_cpu(bd->buf) - priv->dma_tx_addr),
+		       0, skb->len);
+		dev_kfree_skb_irq(skb);
+
+		priv->tx_skbuff[priv->skb_dirtytx] = NULL;
+		priv->skb_dirtytx =
+		    (priv->skb_dirtytx +
+		     1) & TX_RING_MOD_MASK(TX_BD_RING_LEN);
+
+		/* We freed a buffer, so now we can restart transmission */
+		if (netif_queue_stopped(dev))
+			netif_wake_queue(dev);
+
+		/* Advance the confirmation BD pointer */
+		if (!(bd_status & T_W_S))
+			bd += 1;
+		else
+			bd = priv->tx_bd_base;
+		bd_status = ioread16be(&bd->status);
+	}
+	priv->dirty_tx = bd;
+
+	return 0;
+}
+
+static int hdlc_rx_done(struct ucc_hdlc_private *priv, int rx_work_limit)
+{
+	struct net_device *dev = priv->ndev;
+	struct sk_buff *skb;
+	hdlc_device *hdlc = dev_to_hdlc(dev);
+	struct qe_bd *bd;
+	u32 bd_status;
+	u16 length, howmany = 0;
+	u8 *bdbuffer;
+	int i;
+	static int entry;
+
+	bd = priv->currx_bd;
+	bd_status = ioread16be(&bd->status);
+
+	/* while there are received buffers and BD is full (~R_E) */
+	while (!((bd_status & (R_E_S)) || (--rx_work_limit < 0))) {
+		if (bd_status & R_OV_S)
+			dev->stats.rx_over_errors++;
+		if (bd_status & R_CR_S) {
+#ifdef BROKEN_FRAME_INFO
+			pr_info("Broken Frame with RxBD: %x\n", bd_status);
+#endif
+			dev->stats.rx_crc_errors++;
+			dev->stats.rx_dropped++;
+			goto recycle;
+		}
+		bdbuffer = priv->rx_buffer +
+			(priv->currx_bdnum * MAX_RX_BUF_LENGTH);
+		length = ioread16be(&bd->length);
+
+		pr_info("Received data length:%d", length);
+		pr_info("while entry times:%d", entry++);
+
+		pr_info("\nReceived data:\n");
+		for (i = 0; (i < 16); i++) {
+			if (i == length)
+				pr_info("++++");
+			else
+			pr_info("%02x\n", bdbuffer[i]);
+		}
+
+		switch (dev->type) {
+		case ARPHRD_RAWHDLC:
+			bdbuffer += HDLC_HEAD_LEN;
+			length -= (HDLC_HEAD_LEN + HDLC_CRC_SIZE);
+
+			skb = dev_alloc_skb(length);
+			if (!skb) {
+				dev->stats.rx_dropped++;
+				return -ENOMEM;
+			}
+
+			skb_put(skb, length);
+			skb->len = length;
+			skb->dev = dev;
+			memcpy(skb->data, bdbuffer, length);
+			break;
+
+		case ARPHRD_PPP:
+			length -= HDLC_CRC_SIZE;
+
+			skb = dev_alloc_skb(length);
+			if (!skb) {
+				dev->stats.rx_dropped++;
+				return -ENOMEM;
+			}
+
+			skb_put(skb, length);
+			skb->len = length;
+			skb->dev = dev;
+			memcpy(skb->data, bdbuffer, length);
+			break;
+		}
+
+		dev->stats.rx_packets++;
+		dev->stats.rx_bytes += skb->len;
+		howmany++;
+		if (hdlc->proto)
+			skb->protocol = hdlc_type_trans(skb, dev);
+		pr_info("skb->protocol:%x\n", skb->protocol);
+		netif_receive_skb(skb);
+
+recycle:
+		iowrite16be(bd_status | R_E_S | R_I_S, &bd->status);
+
+		/* update to point at the next bd */
+		if (bd_status & R_W_S) {
+			priv->currx_bdnum = 0;
+			bd = priv->rx_bd_base;
+		} else {
+			if (priv->currx_bdnum < (RX_BD_RING_LEN - 1))
+				priv->currx_bdnum += 1;
+			else
+				priv->currx_bdnum = RX_BD_RING_LEN - 1;
+
+			bd += 1;
+		}
+
+		bd_status = ioread16be(&bd->status);
+	}
+
+	priv->currx_bd = bd;
+	return howmany;
+}
+
+static int ucc_hdlc_poll(struct napi_struct *napi, int budget)
+{
+	struct ucc_hdlc_private *priv = container_of(napi,
+						     struct ucc_hdlc_private,
+						     napi);
+	int howmany;
+
+	/* Tx event processing */
+	spin_lock(&priv->lock);
+		hdlc_tx_done(priv);
+	spin_unlock(&priv->lock);
+
+	howmany = 0;
+	howmany += hdlc_rx_done(priv, budget - howmany);
+
+	if (howmany < budget) {
+		napi_complete(napi);
+		qe_setbits32(priv->uccf->p_uccm,
+			     (UCCE_HDLC_RX_EVENTS | UCCE_HDLC_TX_EVENTS) << 16);
+	}
+
+	return howmany;
+}
+
+static irqreturn_t ucc_hdlc_irq_handler(int irq, void *dev_id)
+{
+	struct ucc_hdlc_private *priv = (struct ucc_hdlc_private *)dev_id;
+	struct net_device *dev = priv->ndev;
+	struct ucc_fast_private *uccf;
+	struct ucc_tdm_info *ut_info;
+	u32 ucce;
+	u32 uccm;
+
+	ut_info = priv->ut_info;
+	uccf = priv->uccf;
+
+	ucce = ioread32be(uccf->p_ucce);
+	uccm = ioread32be(uccf->p_uccm);
+	ucce &= uccm;
+	iowrite32be(ucce, uccf->p_ucce);
+	pr_info("irq ucce:%x\n", ucce);
+	if (!ucce)
+		return IRQ_NONE;
+
+	if ((ucce >> 16) & (UCCE_HDLC_RX_EVENTS | UCCE_HDLC_TX_EVENTS)) {
+		if (napi_schedule_prep(&priv->napi)) {
+			uccm &= ~((UCCE_HDLC_RX_EVENTS | UCCE_HDLC_TX_EVENTS)
+				  << 16);
+			iowrite32be(uccm, uccf->p_uccm);
+			__napi_schedule(&priv->napi);
+		}
+	}
+
+	/* Errors and other events */
+	if (ucce >> 16 & UCC_HDLC_UCCE_BSY)
+		dev->stats.rx_errors++;
+	if (ucce >> 16 & UCC_HDLC_UCCE_TXE)
+		dev->stats.tx_errors++;
+
+	return IRQ_HANDLED;
+}
+
+static int uhdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+	const size_t size = sizeof(te1_settings);
+	te1_settings line;
+	struct ucc_hdlc_private *priv = netdev_priv(dev);
+
+	if (cmd != SIOCWANDEV)
+		return hdlc_ioctl(dev, ifr, cmd);
+
+	switch (ifr->ifr_settings.type) {
+	case IF_GET_IFACE:
+		ifr->ifr_settings.type = IF_IFACE_E1;
+		if (ifr->ifr_settings.size < size) {
+			ifr->ifr_settings.size = size; /* data size wanted */
+			return -ENOBUFS;
+		}
+		line.clock_type = priv->clocking;
+		line.clock_rate = 0;
+		line.loopback = 0;
+
+		if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &line, size))
+			return -EFAULT;
+		return 0;
+
+	default:
+		return hdlc_ioctl(dev, ifr, cmd);
+	}
+}
+
+static int uhdlc_open(struct net_device *dev)
+{
+	u32 cecr_subblock;
+	hdlc_device *hdlc = dev_to_hdlc(dev);
+	struct ucc_hdlc_private *priv = hdlc->priv;
+	struct ucc_tdm *utdm = priv->utdm;
+
+	if (priv->hdlc_busy != 1) {
+		if (request_irq(priv->ut_info->uf_info.irq,
+				ucc_hdlc_irq_handler, 0, "hdlc", priv))
+			return -ENODEV;
+
+		cecr_subblock = ucc_fast_get_qe_cr_subblock(
+					priv->ut_info->uf_info.ucc_num);
+
+		qe_issue_cmd(QE_INIT_TX_RX, cecr_subblock,
+			     QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+		ucc_fast_enable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+		/* Enable the TDM port */
+		if (priv->tsa)
+			utdm->si_regs->siglmr1_h |= (0x1 << utdm->tdm_port);
+
+		priv->hdlc_busy = 1;
+		netif_device_attach(priv->ndev);
+		napi_enable(&priv->napi);
+		netif_start_queue(dev);
+		hdlc_open(dev);
+	}
+
+	return 0;
+}
+
+static void uhdlc_memclean(struct ucc_hdlc_private *priv)
+{
+	qe_muram_free(priv->ucc_pram->riptr);
+	qe_muram_free(priv->ucc_pram->tiptr);
+
+	if (priv->rx_bd_base) {
+		dma_free_coherent(priv->dev,
+				  RX_BD_RING_LEN * sizeof(struct qe_bd),
+				  priv->rx_bd_base, priv->dma_rx_bd);
+
+		priv->rx_bd_base = NULL;
+		priv->dma_rx_bd = 0;
+	}
+
+	if (priv->tx_bd_base) {
+		dma_free_coherent(priv->dev,
+				  TX_BD_RING_LEN * sizeof(struct qe_bd),
+				  priv->tx_bd_base, priv->dma_tx_bd);
+
+		priv->tx_bd_base = NULL;
+		priv->dma_tx_bd = 0;
+	}
+
+	if (priv->ucc_pram) {
+		qe_muram_free(priv->ucc_pram_offset);
+		priv->ucc_pram = NULL;
+		priv->ucc_pram_offset = 0;
+	 }
+
+	kfree(priv->rx_skbuff);
+	priv->rx_skbuff = NULL;
+
+	kfree(priv->tx_skbuff);
+	priv->tx_skbuff = NULL;
+
+	if (priv->uf_regs) {
+		iounmap(priv->uf_regs);
+		priv->uf_regs = NULL;
+	}
+
+	if (priv->uccf) {
+		ucc_fast_free(priv->uccf);
+		priv->uccf = NULL;
+	}
+
+	if (priv->rx_buffer) {
+		dma_free_coherent(priv->dev,
+				  RX_BD_RING_LEN * MAX_RX_BUF_LENGTH,
+				  priv->rx_buffer, priv->dma_rx_addr);
+		priv->rx_buffer = NULL;
+		priv->dma_rx_addr = 0;
+	}
+
+	if (priv->tx_buffer) {
+		dma_free_coherent(priv->dev,
+				  TX_BD_RING_LEN * MAX_RX_BUF_LENGTH,
+				  priv->tx_buffer, priv->dma_tx_addr);
+		priv->tx_buffer = NULL;
+		priv->dma_tx_addr = 0;
+	}
+}
+
+static int uhdlc_close(struct net_device *dev)
+{
+	struct ucc_hdlc_private *priv = dev_to_hdlc(dev)->priv;
+	struct ucc_tdm *utdm = priv->utdm;
+	u32 cecr_subblock;
+
+	napi_disable(&priv->napi);
+	cecr_subblock = ucc_fast_get_qe_cr_subblock(
+				priv->ut_info->uf_info.ucc_num);
+
+	qe_issue_cmd(QE_GRACEFUL_STOP_TX, cecr_subblock,
+		     (u8)QE_CR_PROTOCOL_UNSPECIFIED, 0);
+	qe_issue_cmd(QE_CLOSE_RX_BD, cecr_subblock,
+		     (u8)QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+	if (priv->tsa)
+		utdm->si_regs->siglmr1_h &= ~(0x1 << utdm->tdm_port);
+
+	ucc_fast_disable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+	free_irq(priv->ut_info->uf_info.irq, priv);
+	netif_stop_queue(dev);
+	priv->hdlc_busy = 0;
+
+	return 0;
+}
+
+static int ucc_hdlc_attach(struct net_device *dev, unsigned short encoding,
+			   unsigned short parity)
+{
+	struct ucc_hdlc_private *priv = dev_to_hdlc(dev)->priv;
+
+	if (encoding != ENCODING_NRZ &&
+	    encoding != ENCODING_NRZI)
+		return -EINVAL;
+
+	if (parity != PARITY_NONE &&
+	    parity != PARITY_CRC32_PR1_CCITT &&
+	    parity != PARITY_CRC16_PR1_CCITT)
+		return -EINVAL;
+
+	priv->encoding = encoding;
+	priv->parity = parity;
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static void store_clk_config(struct ucc_hdlc_private *priv)
+{
+	struct qe_mux *qe_mux_reg = &qe_immr->qmx;
+
+	/* store si clk */
+	priv->cmxsi1cr_h = ioread32be(&qe_mux_reg->cmxsi1cr_h);
+	priv->cmxsi1cr_l = ioread32be(&qe_mux_reg->cmxsi1cr_l);
+
+	/* store si sync */
+	priv->cmxsi1syr = ioread32be(&qe_mux_reg->cmxsi1syr);
+
+	/* store ucc clk */
+	memcpy_fromio(priv->cmxucr, qe_mux_reg->cmxucr, 4 * sizeof(u32));
+}
+
+static void resume_clk_config(struct ucc_hdlc_private *priv)
+{
+	struct qe_mux *qe_mux_reg = &qe_immr->qmx;
+
+	memcpy_toio(qe_mux_reg->cmxucr, priv->cmxucr, 4 * sizeof(u32));
+
+	iowrite32be(priv->cmxsi1cr_h, &qe_mux_reg->cmxsi1cr_h);
+	iowrite32be(priv->cmxsi1cr_l, &qe_mux_reg->cmxsi1cr_l);
+
+	iowrite32be(priv->cmxsi1syr, &qe_mux_reg->cmxsi1syr);
+}
+
+static int uhdlc_suspend(struct device *dev)
+{
+	struct ucc_hdlc_private *priv = dev_get_drvdata(dev);
+	struct ucc_tdm_info *ut_info;
+	struct ucc_fast __iomem *uf_regs;
+
+	if (!priv)
+		return -EINVAL;
+
+	if (!netif_running(priv->ndev))
+		return 0;
+
+	netif_device_detach(priv->ndev);
+	napi_disable(&priv->napi);
+
+	ut_info = priv->ut_info;
+	uf_regs = priv->uf_regs;
+
+	/* backup gumr guemr*/
+	priv->gumr = ioread32be(&uf_regs->gumr);
+	priv->guemr = ioread8(&uf_regs->guemr);
+
+	priv->ucc_pram_bak = kmalloc(sizeof(*priv->ucc_pram_bak),
+					GFP_KERNEL);
+	if (!priv->ucc_pram_bak)
+		return -ENOMEM;
+
+	/* backup HDLC parameter */
+	memcpy_fromio(priv->ucc_pram_bak, priv->ucc_pram,
+		      sizeof(struct ucc_hdlc_param));
+
+	/* store the clk configuration */
+	store_clk_config(priv);
+
+	/* save power */
+	ucc_fast_disable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+	dev_dbg(dev, "ucc hdlc suspend\n");
+	return 0;
+}
+
+static int uhdlc_resume(struct device *dev)
+{
+	struct ucc_hdlc_private *priv = dev_get_drvdata(dev);
+	struct ucc_tdm *utdm = priv->utdm;
+	struct ucc_tdm_info *ut_info;
+	struct ucc_fast __iomem *uf_regs;
+	struct ucc_fast_private *uccf;
+	struct ucc_fast_info *uf_info;
+	int ret, i;
+	u32 cecr_subblock;
+	u16 bd_status;
+
+	if (!priv)
+		return -EINVAL;
+
+	if (!netif_running(priv->ndev))
+		return 0;
+
+	ut_info = priv->ut_info;
+	uf_info = &ut_info->uf_info;
+	uf_regs = priv->uf_regs;
+	uccf = priv->uccf;
+
+	/* restore gumr guemr */
+	iowrite8(priv->guemr, &uf_regs->guemr);
+	iowrite32be(priv->gumr, &uf_regs->gumr);
+
+	/* Set Virtual Fifo registers */
+	iowrite16be(uf_info->urfs, &uf_regs->urfs);
+	iowrite16be(uf_info->urfet, &uf_regs->urfet);
+	iowrite16be(uf_info->urfset, &uf_regs->urfset);
+	iowrite16be(uf_info->utfs, &uf_regs->utfs);
+	iowrite16be(uf_info->utfet, &uf_regs->utfet);
+	iowrite16be(uf_info->utftt, &uf_regs->utftt);
+	/* utfb, urfb are offsets from MURAM base */
+	iowrite32be(uccf->ucc_fast_tx_virtual_fifo_base_offset, &uf_regs->utfb);
+	iowrite32be(uccf->ucc_fast_rx_virtual_fifo_base_offset, &uf_regs->urfb);
+
+	/* Rx Tx and sync clock routing */
+	resume_clk_config(priv);
+
+	iowrite32be(uf_info->uccm_mask, &uf_regs->uccm);
+	iowrite32be(0xffffffff, &uf_regs->ucce);
+
+	ucc_fast_disable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+	/* rebuild SIRAM */
+	if (priv->tsa)
+		ucc_tdm_init(priv->utdm, priv->ut_info);
+
+	/* Write to QE CECR, UCCx channel to Stop Transmission */
+	cecr_subblock = ucc_fast_get_qe_cr_subblock(uf_info->ucc_num);
+	ret = qe_issue_cmd(QE_STOP_TX, cecr_subblock,
+			   (u8)QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+	/* Set UPSMR normal mode */
+	iowrite32be(0, &uf_regs->upsmr);
+
+	/* init parameter base */
+	cecr_subblock = ucc_fast_get_qe_cr_subblock(uf_info->ucc_num);
+	ret = qe_issue_cmd(QE_ASSIGN_PAGE_TO_DEVICE, cecr_subblock,
+			   QE_CR_PROTOCOL_UNSPECIFIED, priv->ucc_pram_offset);
+
+	priv->ucc_pram = (struct ucc_hdlc_param __iomem *)
+				qe_muram_addr(priv->ucc_pram_offset);
+
+	/* restore ucc parameter */
+	memcpy_toio(priv->ucc_pram, priv->ucc_pram_bak,
+		    sizeof(struct ucc_hdlc_param));
+	kfree(priv->ucc_pram_bak);
+
+	/* rebuild BD entry */
+	for (i = 0; i < RX_BD_RING_LEN; i++) {
+		if (i < (RX_BD_RING_LEN - 1))
+			bd_status = R_E_S | R_I_S;
+		else
+			bd_status = R_E_S | R_I_S | R_W_S;
+
+		iowrite16be(bd_status, &priv->rx_bd_base[i].status);
+		iowrite32be(priv->dma_rx_addr + i * MAX_RX_BUF_LENGTH,
+			    &priv->rx_bd_base[i].buf);
+	}
+
+	for (i = 0; i < TX_BD_RING_LEN; i++) {
+		if (i < (TX_BD_RING_LEN - 1))
+			bd_status =  T_I_S | T_TC_S;
+		else
+			bd_status =  T_I_S | T_TC_S | T_W_S;
+
+		iowrite16be(bd_status, &priv->tx_bd_base[i].status);
+		iowrite32be(priv->dma_tx_addr + i * MAX_RX_BUF_LENGTH,
+			    &priv->tx_bd_base[i].buf);
+	}
+
+	/* if hdlc is busy enable TX and RX */
+	if (priv->hdlc_busy == 1) {
+		cecr_subblock = ucc_fast_get_qe_cr_subblock(
+					priv->ut_info->uf_info.ucc_num);
+
+		qe_issue_cmd(QE_INIT_TX_RX, cecr_subblock,
+			     (u8)QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+		ucc_fast_enable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+		/* Enable the TDM port */
+		if (priv->tsa)
+			utdm->si_regs->siglmr1_h |= (0x1 << utdm->tdm_port);
+	}
+
+	napi_enable(&priv->napi);
+	netif_device_attach(priv->ndev);
+
+	return 0;
+}
+
+static const struct dev_pm_ops uhdlc_pm_ops = {
+	.suspend = uhdlc_suspend,
+	.resume = uhdlc_resume,
+	.freeze = uhdlc_suspend,
+	.thaw = uhdlc_resume,
+};
+
+#define HDLC_PM_OPS (&uhdlc_pm_ops)
+
+#else
+
+#define HDLC_PM_OPS NULL
+
+#endif
+static const struct net_device_ops uhdlc_ops = {
+	.ndo_open       = uhdlc_open,
+	.ndo_stop       = uhdlc_close,
+	.ndo_change_mtu = hdlc_change_mtu,
+	.ndo_start_xmit = hdlc_start_xmit,
+	.ndo_do_ioctl   = uhdlc_ioctl,
+};
+
+static int ucc_hdlc_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct ucc_hdlc_private *uhdlc_priv = NULL;
+	struct ucc_tdm_info *ut_info;
+	struct ucc_tdm *utdm;
+	struct resource res;
+	struct net_device *dev;
+	hdlc_device *hdlc;
+	int ucc_num;
+	const char *sprop;
+	int ret;
+	u32 val;
+
+	ret = of_property_read_u32_index(np, "cell-index", 0, &val);
+	if (ret) {
+		dev_err(&pdev->dev, "Invalid ucc property\n");
+		return -ENODEV;
+	}
+
+	ucc_num = val - 1;
+	if ((ucc_num > 3) || (ucc_num < 0)) {
+		dev_err(&pdev->dev, ": Invalid UCC num\n");
+		return -EINVAL;
+	}
+
+	memcpy(&utdm_info[ucc_num], &utdm_primary_info,
+	       sizeof(utdm_primary_info));
+
+	ut_info = &utdm_info[ucc_num];
+	ut_info->uf_info.ucc_num = ucc_num;
+
+	sprop = of_get_property(np, "rx-clock-name", NULL);
+	if (sprop) {
+		ut_info->uf_info.rx_clock = qe_clock_source(sprop);
+		if ((ut_info->uf_info.rx_clock < QE_CLK_NONE) ||
+		    (ut_info->uf_info.rx_clock > QE_CLK24)) {
+			dev_err(&pdev->dev, "Invalid rx-clock-name property\n");
+			return -EINVAL;
+		}
+	} else {
+		dev_err(&pdev->dev, "Invalid rx-clock-name property\n");
+		return -EINVAL;
+	}
+
+	sprop = of_get_property(np, "tx-clock-name", NULL);
+	if (sprop) {
+		ut_info->uf_info.tx_clock = qe_clock_source(sprop);
+		if ((ut_info->uf_info.tx_clock < QE_CLK_NONE) ||
+		    (ut_info->uf_info.tx_clock > QE_CLK24)) {
+			dev_err(&pdev->dev, "Invalid tx-clock-name property\n");
+			return -EINVAL;
+		}
+	} else {
+		dev_err(&pdev->dev, "Invalid tx-clock-name property\n");
+		return -EINVAL;
+	}
+
+	/* use the same clock when work in loopback */
+	if (ut_info->uf_info.rx_clock == ut_info->uf_info.tx_clock)
+		qe_setbrg(ut_info->uf_info.rx_clock, 20000000, 1);
+
+	ret = of_address_to_resource(np, 0, &res);
+	if (ret)
+		return -EINVAL;
+
+	ut_info->uf_info.regs = res.start;
+	ut_info->uf_info.irq = irq_of_parse_and_map(np, 0);
+
+	uhdlc_priv = kzalloc(sizeof(*uhdlc_priv), GFP_KERNEL);
+	if (!uhdlc_priv) {
+		ret = -ENOMEM;
+		dev_err(&pdev->dev, "No mem to alloc hdlc private data\n");
+		goto err_alloc_priv;
+	}
+
+	dev_set_drvdata(&pdev->dev, uhdlc_priv);
+	uhdlc_priv->dev = &pdev->dev;
+	uhdlc_priv->ut_info = ut_info;
+
+	if (of_get_property(np, "fsl,tdm-interface", NULL))
+		uhdlc_priv->tsa = 1;
+
+	if (of_get_property(np, "fsl,ucc-internal-loopback", NULL))
+		uhdlc_priv->loopback = 1;
+
+	if (uhdlc_priv->tsa == 1) {
+		utdm = kzalloc(sizeof(*utdm), GFP_KERNEL);
+		if (!utdm) {
+			ret = -ENOMEM;
+			dev_err(&pdev->dev, "No mem to alloc ucc tdm data\n");
+			goto err_alloc_utdm;
+		}
+		uhdlc_priv->utdm = utdm;
+		ret = ucc_of_parse_tdm(np, utdm, ut_info);
+		if (ret)
+			goto err_miss_tsa_property;
+	}
+
+	ret = uhdlc_init(uhdlc_priv);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to init uhdlc\n");
+		goto err_hdlc_init;
+	}
+
+	dev = alloc_hdlcdev(uhdlc_priv);
+	if (!dev) {
+		ret = -ENOMEM;
+		pr_err("ucc_hdlc: unable to allocate memory\n");
+		goto err_hdlc_init;
+	}
+
+	uhdlc_priv->ndev = dev;
+	hdlc = dev_to_hdlc(dev);
+	dev->tx_queue_len = 16;
+	dev->netdev_ops = &uhdlc_ops;
+	hdlc->attach = ucc_hdlc_attach;
+	hdlc->xmit = ucc_hdlc_tx;
+	netif_napi_add(dev, &uhdlc_priv->napi, ucc_hdlc_poll, 32);
+	if (register_hdlc_device(dev)) {
+		ret = -ENOBUFS;
+		pr_err("ucc_hdlc: unable to register hdlc device\n");
+		free_netdev(dev);
+		goto err_hdlc_init;
+	}
+
+	return 0;
+
+err_hdlc_init:
+err_miss_tsa_property:
+	kfree(uhdlc_priv);
+	if (uhdlc_priv->tsa)
+		kfree(utdm);
+err_alloc_utdm:
+	kfree(uhdlc_priv);
+err_alloc_priv:
+	return ret;
+}
+
+static int ucc_hdlc_remove(struct platform_device *pdev)
+{
+	struct ucc_hdlc_private *priv = dev_get_drvdata(&pdev->dev);
+
+	uhdlc_memclean(priv);
+
+	if (priv->utdm->si_regs) {
+		iounmap(priv->utdm->si_regs);
+		priv->utdm->si_regs = NULL;
+	}
+
+	if (priv->utdm->siram) {
+		iounmap(priv->utdm->siram);
+		priv->utdm->siram = NULL;
+	}
+	kfree(priv);
+
+	dev_info(&pdev->dev, "UCC based hdlc module removed\n");
+
+	return 0;
+}
+
+static const struct of_device_id fsl_ucc_hdlc_of_match[] = {
+	{
+	.compatible = "fsl,ucc-hdlc",
+	},
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, fsl_ucc_hdlc_of_match);
+
+static struct platform_driver ucc_hdlc_driver = {
+	.probe	= ucc_hdlc_probe,
+	.remove	= ucc_hdlc_remove,
+	.driver	= {
+		.owner		= THIS_MODULE,
+		.name		= DRV_NAME,
+		.pm		= HDLC_PM_OPS,
+		.of_match_table	= fsl_ucc_hdlc_of_match,
+	},
+};
+
+static int __init ucc_hdlc_init(void)
+{
+	return platform_driver_register(&ucc_hdlc_driver);
+}
+
+static void __exit ucc_hdlc_exit(void)
+{
+	platform_driver_unregister(&ucc_hdlc_driver);
+}
+
+module_init(ucc_hdlc_init);
+module_exit(ucc_hdlc_exit);
diff --git a/drivers/net/wan/fsl_ucc_hdlc.h b/drivers/net/wan/fsl_ucc_hdlc.h
new file mode 100644
index 000000000000..881ecdeef076
--- /dev/null
+++ b/drivers/net/wan/fsl_ucc_hdlc.h
@@ -0,0 +1,147 @@
+/* Freescale QUICC Engine HDLC Device Driver
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef _UCC_HDLC_H_
+#define _UCC_HDLC_H_
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+
+#include <soc/fsl/qe/immap_qe.h>
+#include <soc/fsl/qe/qe.h>
+
+#include <soc/fsl/qe/ucc.h>
+#include <soc/fsl/qe/ucc_fast.h>
+
+/* UCC HDLC event register */
+#define UCCE_HDLC_RX_EVENTS	\
+(UCC_HDLC_UCCE_RXF | UCC_HDLC_UCCE_RXB | UCC_HDLC_UCCE_BSY)
+#define UCCE_HDLC_TX_EVENTS	(UCC_HDLC_UCCE_TXB | UCC_HDLC_UCCE_TXE)
+
+struct ucc_hdlc_param {
+	__be16 riptr;
+	__be16 tiptr;
+	__be16 res0;
+	__be16 mrblr;
+	__be32 rstate;
+	__be32 rbase;
+	__be16 rbdstat;
+	__be16 rbdlen;
+	__be32 rdptr;
+	__be32 tstate;
+	__be32 tbase;
+	__be16 tbdstat;
+	__be16 tbdlen;
+	__be32 tdptr;
+	__be32 rbptr;
+	__be32 tbptr;
+	__be32 rcrc;
+	__be32 res1;
+	__be32 tcrc;
+	__be32 res2;
+	__be32 res3;
+	__be32 c_mask;
+	__be32 c_pres;
+	__be16 disfc;
+	__be16 crcec;
+	__be16 abtsc;
+	__be16 nmarc;
+	__be32 max_cnt;
+	__be16 mflr;
+	__be16 rfthr;
+	__be16 rfcnt;
+	__be16 hmask;
+	__be16 haddr1;
+	__be16 haddr2;
+	__be16 haddr3;
+	__be16 haddr4;
+	__be16 ts_tmp;
+	__be16 tmp_mb;
+};
+
+struct ucc_hdlc_private {
+	struct ucc_tdm	*utdm;
+	struct ucc_tdm_info *ut_info;
+	struct ucc_fast_private *uccf;
+	struct device *dev;
+	struct net_device *ndev;
+	struct napi_struct napi;
+	struct ucc_fast __iomem *uf_regs;	/* UCC Fast registers */
+	struct ucc_hdlc_param __iomem *ucc_pram;
+	u16 tsa;
+	bool hdlc_busy;
+	bool loopback;
+
+	u8 *tx_buffer;
+	u8 *rx_buffer;
+	dma_addr_t dma_tx_addr;
+	dma_addr_t dma_rx_addr;
+
+	struct qe_bd *tx_bd_base;
+	struct qe_bd *rx_bd_base;
+	dma_addr_t dma_tx_bd;
+	dma_addr_t dma_rx_bd;
+	struct qe_bd *curtx_bd;
+	struct qe_bd *currx_bd;
+	struct qe_bd *dirty_tx;
+	u16 currx_bdnum;
+
+	struct sk_buff **tx_skbuff;
+	struct sk_buff **rx_skbuff;
+	u16 skb_curtx;
+	u16 skb_currx;
+	unsigned short skb_dirtytx;
+
+	unsigned short tx_ring_size;
+	unsigned short rx_ring_size;
+	u32 ucc_pram_offset;
+
+	unsigned short encoding;
+	unsigned short parity;
+	u32 clocking;
+	spinlock_t lock;	/* lock for Tx BD and Tx buffer */
+#ifdef CONFIG_PM
+	struct ucc_hdlc_param *ucc_pram_bak;
+	u32 gumr;
+	u8 guemr;
+	u32 cmxsi1cr_l, cmxsi1cr_h;
+	u32 cmxsi1syr;
+	u32 cmxucr[4];
+#endif
+};
+
+#define TX_BD_RING_LEN	0x10
+#define RX_BD_RING_LEN	0x20
+#define RX_CLEAN_MAX	0x10
+#define NUM_OF_BUF	4
+#define MAX_RX_BUF_LENGTH	(48 * 0x20)
+#define MAX_FRAME_LENGTH	(MAX_RX_BUF_LENGTH + 8)
+#define ALIGNMENT_OF_UCC_HDLC_PRAM	64
+#define SI_BANK_SIZE	128
+#define MAX_HDLC_NUM	4
+#define HDLC_HEAD_LEN	2
+#define HDLC_CRC_SIZE	2
+#define TX_RING_MOD_MASK(size) (size - 1)
+#define RX_RING_MOD_MASK(size) (size - 1)
+
+#define HDLC_HEAD_MASK		0x0000
+#define DEFAULT_HDLC_HEAD	0xff44
+#define DEFAULT_ADDR_MASK	0x00ff
+#define DEFAULT_HDLC_ADDR	0x00ff
+
+#define BMR_GBL			0x20000000
+#define BMR_BIG_ENDIAN		0x10000000
+#define CRC_16BIT_MASK		0x0000F0B8
+#define CRC_16BIT_PRES		0x0000FFFF
+#define DEFAULT_RFTHR		1
+
+#define DEFAULT_PPP_HEAD    0xff03
+
+#endif
diff --git a/drivers/net/wan/slic_ds26522.c b/drivers/net/wan/slic_ds26522.c
new file mode 100644
index 000000000000..d06a887a2352
--- /dev/null
+++ b/drivers/net/wan/slic_ds26522.c
@@ -0,0 +1,255 @@
+/*
+ * drivers/net/wan/slic_ds26522.c
+ *
+ * Copyright (C) 2016 Freescale Semiconductor, Inc.
+ *
+ * Author:Zhao Qiang<[email protected]>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/bitrev.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/kthread.h>
+#include <linux/spi/spi.h>
+#include <linux/wait.h>
+#include <linux/param.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+#include "slic_ds26522.h"
+
+#define DRV_NAME "ds26522"
+
+#define SLIC_TRANS_LEN 1
+#define SLIC_TWO_LEN 2
+#define SLIC_THREE_LEN 3
+
+static struct spi_device *g_spi;
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Zhao Qiang<[email protected]>");
+
+/* the read/write format of address is
+ * w/r|A13|A12|A11|A10|A9|A8|A7|A6|A5|A4|A3|A2|A1|A0|x
+ */
+static void slic_write(struct spi_device *spi, u16 addr,
+		       u8 data)
+{
+	u8 temp[3];
+
+	addr = bitrev16(addr) >> 1;
+	data = bitrev8(data);
+	temp[0] = (u8)((addr >> 8) & 0x7f);
+	temp[1] = (u8)(addr & 0xfe);
+	temp[2] = data;
+
+	/* write spi addr and value */
+	spi_write(spi, &temp[0], SLIC_THREE_LEN);
+}
+
+static u8 slic_read(struct spi_device *spi, u16 addr)
+{
+	u8 temp[2];
+	u8 data;
+
+	addr = bitrev16(addr) >> 1;
+	temp[0] = (u8)(((addr >> 8) & 0x7f) | 0x80);
+	temp[1] = (u8)(addr & 0xfe);
+
+	spi_write_then_read(spi, &temp[0], SLIC_TWO_LEN, &data,
+			    SLIC_TRANS_LEN);
+
+	data = bitrev8(data);
+	return data;
+}
+
+static bool get_slic_product_code(struct spi_device *spi)
+{
+	u8 device_id;
+
+	device_id = slic_read(spi, DS26522_IDR_ADDR);
+	if ((device_id & 0xf8) == 0x68)
+		return true;
+	else
+		return false;
+}
+
+static void ds26522_e1_spec_config(struct spi_device *spi)
+{
+	/* Receive E1 Mode, Framer Disabled */
+	slic_write(spi, DS26522_RMMR_ADDR, DS26522_RMMR_E1);
+
+	/* Transmit E1 Mode, Framer Disable */
+	slic_write(spi, DS26522_TMMR_ADDR, DS26522_TMMR_E1);
+
+	/* Receive E1 Mode Framer Enable */
+	slic_write(spi, DS26522_RMMR_ADDR,
+		   slic_read(spi, DS26522_RMMR_ADDR) | DS26522_RMMR_FRM_EN);
+
+	/* Transmit E1 Mode Framer Enable */
+	slic_write(spi, DS26522_TMMR_ADDR,
+		   slic_read(spi, DS26522_TMMR_ADDR) | DS26522_TMMR_FRM_EN);
+
+	/* RCR1, receive E1 B8zs & ESF */
+	slic_write(spi, DS26522_RCR1_ADDR,
+		   DS26522_RCR1_E1_HDB3 | DS26522_RCR1_E1_CCS);
+
+	/* RSYSCLK=2.048MHz, RSYNC-Output */
+	slic_write(spi, DS26522_RIOCR_ADDR,
+		   DS26522_RIOCR_2048KHZ | DS26522_RIOCR_RSIO_OUT);
+
+	/* TCR1 Transmit E1 b8zs */
+	slic_write(spi, DS26522_TCR1_ADDR, DS26522_TCR1_TB8ZS);
+
+	/* TSYSCLK=2.048MHz, TSYNC-Output */
+	slic_write(spi, DS26522_TIOCR_ADDR,
+		   DS26522_TIOCR_2048KHZ | DS26522_TIOCR_TSIO_OUT);
+
+	/* Set E1TAF */
+	slic_write(spi, DS26522_E1TAF_ADDR, DS26522_E1TAF_DEFAULT);
+
+	/* Set E1TNAF register */
+	slic_write(spi, DS26522_E1TNAF_ADDR, DS26522_E1TNAF_DEFAULT);
+
+	/* Receive E1 Mode Framer Enable & init Done */
+	slic_write(spi, DS26522_RMMR_ADDR, slic_read(spi, DS26522_RMMR_ADDR) |
+		   DS26522_RMMR_INIT_DONE);
+
+	/* Transmit E1 Mode Framer Enable & init Done */
+	slic_write(spi, DS26522_TMMR_ADDR, slic_read(spi, DS26522_TMMR_ADDR) |
+		   DS26522_TMMR_INIT_DONE);
+
+	/* Configure LIU E1 mode */
+	slic_write(spi, DS26522_LTRCR_ADDR, DS26522_LTRCR_E1);
+
+	/* E1 Mode default 75 ohm w/Transmit Impedance Matlinking */
+	slic_write(spi, DS26522_LTITSR_ADDR,
+		   DS26522_LTITSR_TLIS_75OHM | DS26522_LTITSR_LBOS_75OHM);
+
+	/* E1 Mode default 75 ohm Long Haul w/Receive Impedance Matlinking */
+	slic_write(spi, DS26522_LRISMR_ADDR,
+		   DS26522_LRISMR_75OHM | DS26522_LRISMR_MAX);
+
+	/* Enable Transmit output */
+	slic_write(spi, DS26522_LMCR_ADDR, DS26522_LMCR_TE);
+}
+
+static int slic_ds26522_init_configure(struct spi_device *spi)
+{
+	u16 addr;
+
+	/* set clock */
+	slic_write(spi, DS26522_GTCCR_ADDR, DS26522_GTCCR_BPREFSEL_REFCLKIN |
+			DS26522_GTCCR_BFREQSEL_2048KHZ |
+			DS26522_GTCCR_FREQSEL_2048KHZ);
+	slic_write(spi, DS26522_GTCR2_ADDR, DS26522_GTCR2_TSSYNCOUT);
+	slic_write(spi, DS26522_GFCR_ADDR, DS26522_GFCR_BPCLK_2048KHZ);
+
+	/* set gtcr */
+	slic_write(spi, DS26522_GTCR1_ADDR, DS26522_GTCR1);
+
+	/* Global LIU Software Reset Register */
+	slic_write(spi, DS26522_GLSRR_ADDR, DS26522_GLSRR_RESET);
+
+	/* Global Framer and BERT Software Reset Register */
+	slic_write(spi, DS26522_GFSRR_ADDR, DS26522_GFSRR_RESET);
+
+	usleep_range(100, 120);
+
+	slic_write(spi, DS26522_GLSRR_ADDR, DS26522_GLSRR_NORMAL);
+	slic_write(spi, DS26522_GFSRR_ADDR, DS26522_GFSRR_NORMAL);
+
+	/* Perform RX/TX SRESET,Reset receiver */
+	slic_write(spi, DS26522_RMMR_ADDR, DS26522_RMMR_SFTRST);
+
+	/* Reset tranceiver */
+	slic_write(spi, DS26522_TMMR_ADDR, DS26522_TMMR_SFTRST);
+
+	usleep_range(100, 120);
+
+	/* Zero all Framer Registers */
+	for (addr = DS26522_RF_ADDR_START; addr <= DS26522_RF_ADDR_END;
+	     addr++)
+		slic_write(spi, addr, 0);
+
+	for (addr = DS26522_TF_ADDR_START; addr <= DS26522_TF_ADDR_END;
+	     addr++)
+		slic_write(spi, addr, 0);
+
+	for (addr = DS26522_LIU_ADDR_START; addr <= DS26522_LIU_ADDR_END;
+	     addr++)
+		slic_write(spi, addr, 0);
+
+	for (addr = DS26522_BERT_ADDR_START; addr <= DS26522_BERT_ADDR_END;
+	     addr++)
+		slic_write(spi, addr, 0);
+
+	/* setup ds26522 for E1 specification */
+	ds26522_e1_spec_config(spi);
+
+	slic_write(spi, DS26522_GTCR1_ADDR, 0x00);
+
+	return 0;
+}
+
+static int slic_ds26522_remove(struct spi_device *spi)
+{
+	pr_info("DS26522 module uninstalled\n");
+	return 0;
+}
+
+static int slic_ds26522_probe(struct spi_device *spi)
+{
+	int ret = 0;
+
+	g_spi = spi;
+	spi->bits_per_word = 8;
+
+	if (!get_slic_product_code(spi))
+		return ret;
+
+	ret = slic_ds26522_init_configure(spi);
+	if (ret == 0)
+		pr_info("DS26522 cs%d configurated\n", spi->chip_select);
+
+	return ret;
+}
+
+static const struct of_device_id slic_ds26522_match[] = {
+	{
+	 .compatible = "maxim,ds26522",
+	 },
+	{},
+};
+
+static struct spi_driver slic_ds26522_driver = {
+	.driver = {
+		   .name = "ds26522",
+		   .bus = &spi_bus_type,
+		   .owner = THIS_MODULE,
+		   .of_match_table = slic_ds26522_match,
+		   },
+	.probe = slic_ds26522_probe,
+	.remove = slic_ds26522_remove,
+};
+
+static int __init slic_ds26522_init(void)
+{
+	return spi_register_driver(&slic_ds26522_driver);
+}
+
+static void __exit slic_ds26522_exit(void)
+{
+	spi_unregister_driver(&slic_ds26522_driver);
+}
+
+module_init(slic_ds26522_init);
+module_exit(slic_ds26522_exit);
diff --git a/drivers/net/wan/slic_ds26522.h b/drivers/net/wan/slic_ds26522.h
new file mode 100644
index 000000000000..22aa0ecbd9fd
--- /dev/null
+++ b/drivers/net/wan/slic_ds26522.h
@@ -0,0 +1,134 @@
+/*
+ * drivers/tdm/line_ctrl/slic_ds26522.h
+ *
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ *
+ * Author: Zhao Qiang <[email protected]>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#define DS26522_RF_ADDR_START	0x00
+#define DS26522_RF_ADDR_END	0xef
+#define DS26522_GLB_ADDR_START	0xf0
+#define DS26522_GLB_ADDR_END	0xff
+#define DS26522_TF_ADDR_START	0x100
+#define DS26522_TF_ADDR_END	0x1ef
+#define DS26522_LIU_ADDR_START	0x1000
+#define DS26522_LIU_ADDR_END	0x101f
+#define DS26522_TEST_ADDR_START	0x1008
+#define DS26522_TEST_ADDR_END	0x101f
+#define DS26522_BERT_ADDR_START	0x1100
+#define DS26522_BERT_ADDR_END	0x110f
+
+#define DS26522_RMMR_ADDR	0x80
+#define DS26522_RCR1_ADDR	0x81
+#define DS26522_RCR3_ADDR	0x83
+#define DS26522_RIOCR_ADDR	0x84
+
+#define DS26522_GTCR1_ADDR	0xf0
+#define DS26522_GFCR_ADDR	0xf1
+#define DS26522_GTCR2_ADDR	0xf2
+#define DS26522_GTCCR_ADDR	0xf3
+#define DS26522_GLSRR_ADDR	0xf5
+#define DS26522_GFSRR_ADDR	0xf6
+#define DS26522_IDR_ADDR	0xf8
+
+#define DS26522_E1TAF_ADDR	0x164
+#define DS26522_E1TNAF_ADDR	0x165
+#define DS26522_TMMR_ADDR	0x180
+#define DS26522_TCR1_ADDR	0x181
+#define DS26522_TIOCR_ADDR	0x184
+
+#define DS26522_LTRCR_ADDR	0x1000
+#define DS26522_LTITSR_ADDR	0x1001
+#define DS26522_LMCR_ADDR	0x1002
+#define DS26522_LRISMR_ADDR	0x1007
+
+#define MAX_NUM_OF_CHANNELS	8
+#define PQ_MDS_8E1T1_BRD_REV	0x00
+#define PQ_MDS_8E1T1_PLD_REV	0x00
+
+#define DS26522_GTCCR_BPREFSEL_REFCLKIN	0xa0
+#define DS26522_GTCCR_BFREQSEL_1544KHZ	0x08
+#define DS26522_GTCCR_FREQSEL_1544KHZ	0x04
+#define DS26522_GTCCR_BFREQSEL_2048KHZ	0x00
+#define DS26522_GTCCR_FREQSEL_2048KHZ	0x00
+
+#define DS26522_GFCR_BPCLK_2048KHZ	0x00
+
+#define DS26522_GTCR2_TSSYNCOUT	0x02
+#define DS26522_GTCR1	0x00
+
+#define DS26522_GFSRR_RESET	0x01
+#define DS26522_GFSRR_NORMAL	0x00
+
+#define DS26522_GLSRR_RESET	0x01
+#define DS26522_GLSRR_NORMAL	0x00
+
+#define DS26522_RMMR_SFTRST	0x02
+#define DS26522_RMMR_FRM_EN	0x80
+#define DS26522_RMMR_INIT_DONE	0x40
+#define DS26522_RMMR_T1		0x00
+#define DS26522_RMMR_E1		0x01
+
+#define DS26522_E1TAF_DEFAULT	0x1b
+#define DS26522_E1TNAF_DEFAULT	0x40
+
+#define DS26522_TMMR_SFTRST	0x02
+#define DS26522_TMMR_FRM_EN	0x80
+#define DS26522_TMMR_INIT_DONE	0x40
+#define DS26522_TMMR_T1		0x00
+#define DS26522_TMMR_E1		0x01
+
+#define DS26522_RCR1_T1_SYNCT	0x80
+#define DS26522_RCR1_T1_RB8ZS	0x40
+#define DS26522_RCR1_T1_SYNCC	0x08
+
+#define DS26522_RCR1_E1_HDB3	0x40
+#define DS26522_RCR1_E1_CCS	0x20
+
+#define DS26522_RIOCR_1544KHZ	0x00
+#define DS26522_RIOCR_2048KHZ	0x10
+#define DS26522_RIOCR_RSIO_OUT	0x00
+
+#define DS26522_RCR3_FLB	0x01
+
+#define DS26522_TIOCR_1544KHZ	0x00
+#define DS26522_TIOCR_2048KHZ	0x10
+#define DS26522_TIOCR_TSIO_OUT	0x04
+
+#define DS26522_TCR1_TB8ZS	0x04
+
+#define DS26522_LTRCR_T1	0x02
+#define DS26522_LTRCR_E1	0x00
+
+#define DS26522_LTITSR_TLIS_75OHM	0x00
+#define DS26522_LTITSR_LBOS_75OHM	0x00
+#define DS26522_LTITSR_TLIS_100OHM	0x10
+#define DS26522_LTITSR_TLIS_0DB_CSU	0x00
+
+#define DS26522_LRISMR_75OHM	0x00
+#define DS26522_LRISMR_100OHM	0x10
+#define DS26522_LRISMR_MAX	0x03
+
+#define DS26522_LMCR_TE	0x01
+
+enum line_rate {
+	LINE_RATE_T1,	/* T1 line rate (1.544 Mbps)      */
+	LINE_RATE_E1	/* E1 line rate (2.048 Mbps)     */
+};
+
+enum tdm_trans_mode {
+	NORMAL = 0,
+	FRAMER_LB
+};
+
+enum card_support_type {
+	LM_CARD = 0,
+	DS26522_CARD,
+	NO_CARD
+};
diff --git a/drivers/net/wireless/ath/ath10k/ahb.c b/drivers/net/wireless/ath/ath10k/ahb.c
index bd62bc19e758..acec16b9cf49 100644
--- a/drivers/net/wireless/ath/ath10k/ahb.c
+++ b/drivers/net/wireless/ath/ath10k/ahb.c
@@ -25,10 +25,9 @@
 #include "ahb.h"
 
 static const struct of_device_id ath10k_ahb_of_match[] = {
-	/* TODO: enable this entry once everything in place.
-	 * { .compatible = "qcom,ipq4019-wifi",
-	 *   .data = (void *)ATH10K_HW_QCA4019 },
-	 */
+	{ .compatible = "qcom,ipq4019-wifi",
+	  .data = (void *)ATH10K_HW_QCA4019
+	},
 	{ }
 };
 
@@ -476,6 +475,7 @@ static irqreturn_t ath10k_ahb_interrupt_handler(int irq, void *arg)
 
 static int ath10k_ahb_request_irq_legacy(struct ath10k *ar)
 {
+	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 	struct ath10k_ahb *ar_ahb = ath10k_ahb_priv(ar);
 	int ret;
 
@@ -487,6 +487,7 @@ static int ath10k_ahb_request_irq_legacy(struct ath10k *ar)
 			    ar_ahb->irq, ret);
 		return ret;
 	}
+	ar_pci->oper_irq_mode = ATH10K_PCI_IRQ_LEGACY;
 
 	return 0;
 }
@@ -918,8 +919,6 @@ int ath10k_ahb_init(void)
 {
 	int ret;
 
-	printk(KERN_ERR "AHB support is still work in progress\n");
-
 	ret = platform_driver_register(&ath10k_ahb_driver);
 	if (ret)
 		printk(KERN_ERR "failed to register ath10k ahb driver: %d\n",
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 49af62428c88..dfb3db0ee5d1 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/of.h>
+#include <asm/byteorder.h>
 
 #include "core.h"
 #include "mac.h"
@@ -55,7 +56,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca988x hw2.0",
 		.patch_load_addr = QCA988X_HW_2_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
-		.has_shifted_cc_wraparound = true,
+		.cc_wraparound_type = ATH10K_HW_CC_WRAP_SHIFTED_ALL,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
@@ -69,6 +70,25 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		},
 	},
 	{
+		.id = QCA9887_HW_1_0_VERSION,
+		.dev_id = QCA9887_1_0_DEVICE_ID,
+		.name = "qca9887 hw1.0",
+		.patch_load_addr = QCA9887_HW_1_0_PATCH_LOAD_ADDR,
+		.uart_pin = 7,
+		.cc_wraparound_type = ATH10K_HW_CC_WRAP_SHIFTED_ALL,
+		.otp_exe_param = 0,
+		.channel_counters_freq_hz = 88000,
+		.max_probe_resp_desc_thres = 0,
+		.hw_4addr_pad = ATH10K_HW_4ADDR_PAD_AFTER,
+		.cal_data_len = 2116,
+		.fw = {
+			.dir = QCA9887_HW_1_0_FW_DIR,
+			.board = QCA9887_HW_1_0_BOARD_DATA_FILE,
+			.board_size = QCA9887_BOARD_DATA_SZ,
+			.board_ext_size = QCA9887_BOARD_EXT_DATA_SZ,
+		},
+	},
+	{
 		.id = QCA6174_HW_2_1_VERSION,
 		.dev_id = QCA6164_2_1_DEVICE_ID,
 		.name = "qca6164 hw2.1",
@@ -148,6 +168,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.uart_pin = 7,
 		.otp_exe_param = 0x00000700,
 		.continuous_frag_desc = true,
+		.cck_rate_map_rev2 = true,
 		.channel_counters_freq_hz = 150000,
 		.max_probe_resp_desc_thres = 24,
 		.hw_4addr_pad = ATH10K_HW_4ADDR_PAD_BEFORE,
@@ -163,6 +184,29 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		},
 	},
 	{
+		.id = QCA9984_HW_1_0_DEV_VERSION,
+		.dev_id = QCA9984_1_0_DEVICE_ID,
+		.name = "qca9984/qca9994 hw1.0",
+		.patch_load_addr = QCA9984_HW_1_0_PATCH_LOAD_ADDR,
+		.uart_pin = 7,
+		.otp_exe_param = 0x00000700,
+		.continuous_frag_desc = true,
+		.cck_rate_map_rev2 = true,
+		.channel_counters_freq_hz = 150000,
+		.max_probe_resp_desc_thres = 24,
+		.hw_4addr_pad = ATH10K_HW_4ADDR_PAD_BEFORE,
+		.tx_chain_mask = 0xf,
+		.rx_chain_mask = 0xf,
+		.max_spatial_stream = 4,
+		.cal_data_len = 12064,
+		.fw = {
+			.dir = QCA9984_HW_1_0_FW_DIR,
+			.board = QCA9984_HW_1_0_BOARD_DATA_FILE,
+			.board_size = QCA99X0_BOARD_DATA_SZ,
+			.board_ext_size = QCA99X0_BOARD_EXT_DATA_SZ,
+		},
+	},
+	{
 		.id = QCA9377_HW_1_0_DEV_VERSION,
 		.dev_id = QCA9377_1_0_DEVICE_ID,
 		.name = "qca9377 hw1.0",
@@ -202,9 +246,10 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.name = "qca4019 hw1.0",
 		.patch_load_addr = QCA4019_HW_1_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
-		.has_shifted_cc_wraparound = true,
+		.cc_wraparound_type = ATH10K_HW_CC_WRAP_SHIFTED_EACH,
 		.otp_exe_param = 0x0010000,
 		.continuous_frag_desc = true,
+		.cck_rate_map_rev2 = true,
 		.channel_counters_freq_hz = 125000,
 		.max_probe_resp_desc_thres = 24,
 		.hw_4addr_pad = ATH10K_HW_4ADDR_PAD_BEFORE,
@@ -236,6 +281,7 @@ static const char *const ath10k_core_fw_feature_str[] = {
 	[ATH10K_FW_FEATURE_SUPPORTS_ADAPTIVE_CCA] = "adaptive-cca",
 	[ATH10K_FW_FEATURE_MFP_SUPPORT] = "mfp",
 	[ATH10K_FW_FEATURE_PEER_FLOW_CONTROL] = "peer-flow-ctrl",
+	[ATH10K_FW_FEATURE_BTCOEX_PARAM] = "btcoex-param",
 };
 
 static unsigned int ath10k_core_get_fw_feature_str(char *buf,
@@ -531,6 +577,35 @@ out:
 	return ret;
 }
 
+static int ath10k_download_cal_eeprom(struct ath10k *ar)
+{
+	size_t data_len;
+	void *data = NULL;
+	int ret;
+
+	ret = ath10k_hif_fetch_cal_eeprom(ar, &data, &data_len);
+	if (ret) {
+		if (ret != -EOPNOTSUPP)
+			ath10k_warn(ar, "failed to read calibration data from EEPROM: %d\n",
+				    ret);
+		goto out_free;
+	}
+
+	ret = ath10k_download_board_data(ar, data, data_len);
+	if (ret) {
+		ath10k_warn(ar, "failed to download calibration data from EEPROM: %d\n",
+			    ret);
+		goto out_free;
+	}
+
+	ret = 0;
+
+out_free:
+	kfree(data);
+
+	return ret;
+}
+
 static int ath10k_core_get_board_id_from_otp(struct ath10k *ar)
 {
 	u32 result, address;
@@ -1083,7 +1158,7 @@ int ath10k_core_fetch_firmware_api_n(struct ath10k *ar, const char *name,
 			}
 
 			ath10k_dbg_dump(ar, ATH10K_DBG_BOOT, "features", "",
-					ar->running_fw->fw_file.fw_features,
+					fw_file->fw_features,
 					sizeof(fw_file->fw_features));
 			break;
 		case ATH10K_FW_IE_FW_IMAGE:
@@ -1293,7 +1368,17 @@ static int ath10k_download_cal_data(struct ath10k *ar)
 	}
 
 	ath10k_dbg(ar, ATH10K_DBG_BOOT,
-		   "boot did not find DT entry, try OTP next: %d\n",
+		   "boot did not find DT entry, try target EEPROM next: %d\n",
+		   ret);
+
+	ret = ath10k_download_cal_eeprom(ar);
+	if (ret == 0) {
+		ar->cal_mode = ATH10K_CAL_MODE_EEPROM;
+		goto done;
+	}
+
+	ath10k_dbg(ar, ATH10K_DBG_BOOT,
+		   "boot did not find target EEPROM entry, try OTP next: %d\n",
 		   ret);
 
 	ret = ath10k_download_and_run_otp(ar);
@@ -1733,6 +1818,16 @@ int ath10k_core_start(struct ath10k *ar, enum ath10k_firmware_mode mode,
 		if (test_bit(WMI_SERVICE_BSS_CHANNEL_INFO_64, ar->wmi.svc_map))
 			val |= WMI_10_4_BSS_CHANNEL_INFO_64;
 
+		/* 10.4 firmware supports BT-Coex without reloading firmware
+		 * via pdev param. To support Bluetooth coexistence pdev param,
+		 * WMI_COEX_GPIO_SUPPORT of extended resource config should be
+		 * enabled always.
+		 */
+		if (test_bit(WMI_SERVICE_COEX_GPIO, ar->wmi.svc_map) &&
+		    test_bit(ATH10K_FW_FEATURE_BTCOEX_PARAM,
+			     ar->running_fw->fw_file.fw_features))
+			val |= WMI_10_4_COEX_GPIO_SUPPORT;
+
 		status = ath10k_mac_ext_resource_config(ar, val);
 		if (status) {
 			ath10k_err(ar,
@@ -2062,6 +2157,7 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 
 	switch (hw_rev) {
 	case ATH10K_HW_QCA988X:
+	case ATH10K_HW_QCA9887:
 		ar->regs = &qca988x_regs;
 		ar->hw_values = &qca988x_values;
 		break;
@@ -2071,6 +2167,7 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 		ar->hw_values = &qca6174_values;
 		break;
 	case ATH10K_HW_QCA99X0:
+	case ATH10K_HW_QCA9984:
 		ar->regs = &qca99x0_regs;
 		ar->hw_values = &qca99x0_values;
 		break;
@@ -2159,5 +2256,5 @@ void ath10k_core_destroy(struct ath10k *ar)
 EXPORT_SYMBOL(ath10k_core_destroy);
 
 MODULE_AUTHOR("Qualcomm Atheros");
-MODULE_DESCRIPTION("Core module for QCA988X PCIe devices.");
+MODULE_DESCRIPTION("Core module for Qualcomm Atheros 802.11ac wireless LAN cards.");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 1852e0ee3fa1..3da18c9dbd7a 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -535,6 +535,13 @@ enum ath10k_fw_features {
 	 */
 	ATH10K_FW_FEATURE_PEER_FLOW_CONTROL = 13,
 
+	/* Firmware supports BT-Coex without reloading firmware via pdev param.
+	 * To support Bluetooth coexistence pdev param, WMI_COEX_GPIO_SUPPORT of
+	 * extended resource config should be enabled always. This firmware IE
+	 * is used to configure WMI_COEX_GPIO_SUPPORT.
+	 */
+	ATH10K_FW_FEATURE_BTCOEX_PARAM = 14,
+
 	/* keep last */
 	ATH10K_FW_FEATURE_COUNT,
 };
@@ -571,6 +578,7 @@ enum ath10k_cal_mode {
 	ATH10K_CAL_MODE_DT,
 	ATH10K_PRE_CAL_MODE_FILE,
 	ATH10K_PRE_CAL_MODE_DT,
+	ATH10K_CAL_MODE_EEPROM,
 };
 
 enum ath10k_crypt_mode {
@@ -593,6 +601,8 @@ static inline const char *ath10k_cal_mode_str(enum ath10k_cal_mode mode)
 		return "pre-cal-file";
 	case ATH10K_PRE_CAL_MODE_DT:
 		return "pre-cal-dt";
+	case ATH10K_CAL_MODE_EEPROM:
+		return "eeprom";
 	}
 
 	return "unknown";
@@ -703,12 +713,10 @@ struct ath10k {
 		int uart_pin;
 		u32 otp_exe_param;
 
-		/* This is true if given HW chip has a quirky Cycle Counter
-		 * wraparound which resets to 0x7fffffff instead of 0. All
-		 * other CC related counters (e.g. Rx Clear Count) are divided
-		 * by 2 so they never wraparound themselves.
+		/* Type of hw cycle counter wraparound logic, for more info
+		 * refer enum ath10k_hw_cc_wraparound_type.
 		 */
-		bool has_shifted_cc_wraparound;
+		enum ath10k_hw_cc_wraparound_type cc_wraparound_type;
 
 		/* Some of chip expects fragment descriptor to be continuous
 		 * memory for any TX operation. Set continuous_frag_desc flag
@@ -716,6 +724,12 @@ struct ath10k {
 		 */
 		bool continuous_frag_desc;
 
+		/* CCK hardware rate table mapping for the newer chipsets
+		 * like QCA99X0, QCA4019 got revised. The CCK h/w rate values
+		 * are in a proper order with respect to the rate/preamble
+		 */
+		bool cck_rate_map_rev2;
+
 		u32 channel_counters_freq_hz;
 
 		/* Mgmt tx descriptors threshold for limiting probe response
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index e2511550fbb8..8fbb8f2c7828 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -609,25 +609,23 @@ static ssize_t ath10k_write_simulate_fw_crash(struct file *file,
 	char buf[32];
 	int ret;
 
-	mutex_lock(&ar->conf_mutex);
-
 	simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, user_buf, count);
 
 	/* make sure that buf is null terminated */
 	buf[sizeof(buf) - 1] = 0;
 
+	/* drop the possible '\n' from the end */
+	if (buf[count - 1] == '\n')
+		buf[count - 1] = 0;
+
+	mutex_lock(&ar->conf_mutex);
+
 	if (ar->state != ATH10K_STATE_ON &&
 	    ar->state != ATH10K_STATE_RESTARTED) {
 		ret = -ENETDOWN;
 		goto exit;
 	}
 
-	/* drop the possible '\n' from the end */
-	if (buf[count - 1] == '\n') {
-		buf[count - 1] = 0;
-		count--;
-	}
-
 	if (!strcmp(buf, "soft")) {
 		ath10k_info(ar, "simulating soft firmware crash\n");
 		ret = ath10k_wmi_force_fw_hang(ar, WMI_FORCE_FW_HANG_ASSERT, 0);
@@ -2127,6 +2125,7 @@ static ssize_t ath10k_write_btcoex(struct file *file,
 	size_t buf_size;
 	int ret;
 	bool val;
+	u32 pdev_param;
 
 	buf_size = min(count, (sizeof(buf) - 1));
 	if (copy_from_user(buf, ubuf, buf_size))
@@ -2150,14 +2149,25 @@ static ssize_t ath10k_write_btcoex(struct file *file,
 		goto exit;
 	}
 
+	pdev_param = ar->wmi.pdev_param->enable_btcoex;
+	if (test_bit(ATH10K_FW_FEATURE_BTCOEX_PARAM,
+		     ar->running_fw->fw_file.fw_features)) {
+		ret = ath10k_wmi_pdev_set_param(ar, pdev_param, val);
+		if (ret) {
+			ath10k_warn(ar, "failed to enable btcoex: %d\n", ret);
+			ret = count;
+			goto exit;
+		}
+	} else {
+		ath10k_info(ar, "restarting firmware due to btcoex change");
+		queue_work(ar->workqueue, &ar->restart_work);
+	}
+
 	if (val)
 		set_bit(ATH10K_FLAG_BTCOEX, &ar->dev_flags);
 	else
 		clear_bit(ATH10K_FLAG_BTCOEX, &ar->dev_flags);
 
-	ath10k_info(ar, "restarting firmware due to btcoex change");
-
-	queue_work(ar->workqueue, &ar->restart_work);
 	ret = count;
 
 exit:
diff --git a/drivers/net/wireless/ath/ath10k/hif.h b/drivers/net/wireless/ath/ath10k/hif.h
index 89e7076c919f..b2566b06e1e1 100644
--- a/drivers/net/wireless/ath/ath10k/hif.h
+++ b/drivers/net/wireless/ath/ath10k/hif.h
@@ -87,6 +87,10 @@ struct ath10k_hif_ops {
 
 	int (*suspend)(struct ath10k *ar);
 	int (*resume)(struct ath10k *ar);
+
+	/* fetch calibration data from target eeprom */
+	int (*fetch_cal_eeprom)(struct ath10k *ar, void **data,
+				size_t *data_len);
 };
 
 static inline int ath10k_hif_tx_sg(struct ath10k *ar, u8 pipe_id,
@@ -202,4 +206,14 @@ static inline void ath10k_hif_write32(struct ath10k *ar,
 	ar->hif.ops->write32(ar, address, data);
 }
 
+static inline int ath10k_hif_fetch_cal_eeprom(struct ath10k *ar,
+					      void **data,
+					      size_t *data_len)
+{
+	if (!ar->hif.ops->fetch_cal_eeprom)
+		return -EOPNOTSUPP;
+
+	return ar->hif.ops->fetch_cal_eeprom(ar, data, data_len);
+}
+
 #endif /* _HIF_H_ */
diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h
index 911c535d0863..430a83e142aa 100644
--- a/drivers/net/wireless/ath/ath10k/htt.h
+++ b/drivers/net/wireless/ath/ath10k/htt.h
@@ -485,10 +485,10 @@ struct htt_mgmt_tx_completion {
 	__le32 status;
 } __packed;
 
-#define HTT_RX_INDICATION_INFO0_EXT_TID_MASK  (0x3F)
+#define HTT_RX_INDICATION_INFO0_EXT_TID_MASK  (0x1F)
 #define HTT_RX_INDICATION_INFO0_EXT_TID_LSB   (0)
-#define HTT_RX_INDICATION_INFO0_FLUSH_VALID   (1 << 6)
-#define HTT_RX_INDICATION_INFO0_RELEASE_VALID (1 << 7)
+#define HTT_RX_INDICATION_INFO0_FLUSH_VALID   (1 << 5)
+#define HTT_RX_INDICATION_INFO0_RELEASE_VALID (1 << 6)
 
 #define HTT_RX_INDICATION_INFO1_FLUSH_START_SEQNO_MASK   0x0000003F
 #define HTT_RX_INDICATION_INFO1_FLUSH_START_SEQNO_LSB    0
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index cc979a4faeb0..80e645302b54 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -748,7 +748,7 @@ ath10k_htt_rx_h_peer_channel(struct ath10k *ar, struct htt_rx_desc *rxd)
 	if (WARN_ON_ONCE(!arvif))
 		return NULL;
 
-	if (WARN_ON(ath10k_mac_vif_chan(arvif->vif, &def)))
+	if (WARN_ON_ONCE(ath10k_mac_vif_chan(arvif->vif, &def)))
 		return NULL;
 
 	return def.chan;
@@ -939,7 +939,8 @@ static void ath10k_process_rx(struct ath10k *ar,
 		   is_multicast_ether_addr(ieee80211_get_DA(hdr)) ?
 							"mcast" : "ucast",
 		   (__le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_SEQ) >> 4,
-		   status->flag == 0 ? "legacy" : "",
+		   (status->flag & (RX_FLAG_HT | RX_FLAG_VHT)) == 0 ?
+							"legacy" : "",
 		   status->flag & RX_FLAG_HT ? "ht" : "",
 		   status->flag & RX_FLAG_VHT ? "vht" : "",
 		   status->flag & RX_FLAG_40MHZ ? "40" : "",
@@ -1904,7 +1905,6 @@ static void ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb)
 			return;
 		}
 	}
-	ath10k_htt_rx_msdu_buff_replenish(htt);
 }
 
 static void ath10k_htt_rx_tx_fetch_resp_id_confirm(struct ath10k *ar,
@@ -2182,34 +2182,6 @@ static void ath10k_htt_rx_tx_mode_switch_ind(struct ath10k *ar,
 	ath10k_mac_tx_push_pending(ar);
 }
 
-static inline enum nl80211_band phy_mode_to_band(u32 phy_mode)
-{
-	enum nl80211_band band;
-
-	switch (phy_mode) {
-	case MODE_11A:
-	case MODE_11NA_HT20:
-	case MODE_11NA_HT40:
-	case MODE_11AC_VHT20:
-	case MODE_11AC_VHT40:
-	case MODE_11AC_VHT80:
-		band = NL80211_BAND_5GHZ;
-		break;
-	case MODE_11G:
-	case MODE_11B:
-	case MODE_11GONLY:
-	case MODE_11NG_HT20:
-	case MODE_11NG_HT40:
-	case MODE_11AC_VHT20_2G:
-	case MODE_11AC_VHT40_2G:
-	case MODE_11AC_VHT80_2G:
-	default:
-		band = NL80211_BAND_2GHZ;
-	}
-
-	return band;
-}
-
 void ath10k_htt_htc_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 {
 	bool release;
@@ -2291,7 +2263,6 @@ bool ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 			ath10k_htt_tx_mgmt_dec_pending(htt);
 			spin_unlock_bh(&htt->tx_lock);
 		}
-		ath10k_mac_tx_push_pending(ar);
 		break;
 	}
 	case HTT_T2H_MSG_TYPE_TX_COMPL_IND:
@@ -2442,8 +2413,6 @@ static void ath10k_htt_txrx_compl_task(unsigned long ptr)
 		dev_kfree_skb_any(skb);
 	}
 
-	ath10k_mac_tx_push_pending(ar);
-
 	num_mpdus = atomic_read(&htt->num_mpdus_ready);
 
 	while (num_mpdus) {
diff --git a/drivers/net/wireless/ath/ath10k/hw.c b/drivers/net/wireless/ath/ath10k/hw.c
index f544d48518c3..bd86e7a38db9 100644
--- a/drivers/net/wireless/ath/ath10k/hw.c
+++ b/drivers/net/wireless/ath/ath10k/hw.c
@@ -179,17 +179,35 @@ void ath10k_hw_fill_survey_time(struct ath10k *ar, struct survey_info *survey,
 				u32 cc, u32 rcc, u32 cc_prev, u32 rcc_prev)
 {
 	u32 cc_fix = 0;
+	u32 rcc_fix = 0;
+	enum ath10k_hw_cc_wraparound_type wraparound_type;
 
 	survey->filled |= SURVEY_INFO_TIME |
 			  SURVEY_INFO_TIME_BUSY;
 
-	if (ar->hw_params.has_shifted_cc_wraparound && cc < cc_prev) {
-		cc_fix = 0x7fffffff;
-		survey->filled &= ~SURVEY_INFO_TIME_BUSY;
+	wraparound_type = ar->hw_params.cc_wraparound_type;
+
+	if (cc < cc_prev || rcc < rcc_prev) {
+		switch (wraparound_type) {
+		case ATH10K_HW_CC_WRAP_SHIFTED_ALL:
+			if (cc < cc_prev) {
+				cc_fix = 0x7fffffff;
+				survey->filled &= ~SURVEY_INFO_TIME_BUSY;
+			}
+			break;
+		case ATH10K_HW_CC_WRAP_SHIFTED_EACH:
+			if (cc < cc_prev)
+				cc_fix = 0x7fffffff;
+			else
+				rcc_fix = 0x7fffffff;
+			break;
+		case ATH10K_HW_CC_WRAP_DISABLED:
+			break;
+		}
 	}
 
 	cc -= cc_prev - cc_fix;
-	rcc -= rcc_prev;
+	rcc -= rcc_prev - rcc_fix;
 
 	survey->time = CCNT_TO_MSEC(ar, cc);
 	survey->time_busy = CCNT_TO_MSEC(ar, rcc);
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index aedd8987040b..f31d3ce42470 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -26,7 +26,9 @@
 #define QCA6164_2_1_DEVICE_ID   (0x0041)
 #define QCA6174_2_1_DEVICE_ID   (0x003e)
 #define QCA99X0_2_0_DEVICE_ID   (0x0040)
+#define QCA9984_1_0_DEVICE_ID	(0x0046)
 #define QCA9377_1_0_DEVICE_ID   (0x0042)
+#define QCA9887_1_0_DEVICE_ID   (0x0050)
 
 /* QCA988X 1.0 definitions (unsupported) */
 #define QCA988X_HW_1_0_CHIP_ID_REV	0x0
@@ -38,6 +40,13 @@
 #define QCA988X_HW_2_0_BOARD_DATA_FILE	"board.bin"
 #define QCA988X_HW_2_0_PATCH_LOAD_ADDR	0x1234
 
+/* QCA9887 1.0 definitions */
+#define QCA9887_HW_1_0_VERSION		0x4100016d
+#define QCA9887_HW_1_0_CHIP_ID_REV	0
+#define QCA9887_HW_1_0_FW_DIR		ATH10K_FW_DIR "/QCA9887/hw1.0"
+#define QCA9887_HW_1_0_BOARD_DATA_FILE	"board.bin"
+#define QCA9887_HW_1_0_PATCH_LOAD_ADDR	0x1234
+
 /* QCA6174 target BMI version signatures */
 #define QCA6174_HW_1_0_VERSION		0x05000000
 #define QCA6174_HW_1_1_VERSION		0x05000001
@@ -91,6 +100,14 @@ enum qca9377_chip_id_rev {
 #define QCA99X0_HW_2_0_BOARD_DATA_FILE "board.bin"
 #define QCA99X0_HW_2_0_PATCH_LOAD_ADDR	0x1234
 
+/* QCA9984 1.0 defines */
+#define QCA9984_HW_1_0_DEV_VERSION	0x1000000
+#define QCA9984_HW_DEV_TYPE		0xa
+#define QCA9984_HW_1_0_CHIP_ID_REV	0x0
+#define QCA9984_HW_1_0_FW_DIR		ATH10K_FW_DIR "/QCA9984/hw1.0"
+#define QCA9984_HW_1_0_BOARD_DATA_FILE "board.bin"
+#define QCA9984_HW_1_0_PATCH_LOAD_ADDR	0x1234
+
 /* QCA9377 1.0 definitions */
 #define QCA9377_HW_1_0_FW_DIR          ATH10K_FW_DIR "/QCA9377/hw1.0"
 #define QCA9377_HW_1_0_BOARD_DATA_FILE "board.bin"
@@ -193,8 +210,10 @@ enum ath10k_hw_rev {
 	ATH10K_HW_QCA988X,
 	ATH10K_HW_QCA6174,
 	ATH10K_HW_QCA99X0,
+	ATH10K_HW_QCA9984,
 	ATH10K_HW_QCA9377,
 	ATH10K_HW_QCA4019,
+	ATH10K_HW_QCA9887,
 };
 
 struct ath10k_hw_regs {
@@ -247,8 +266,10 @@ void ath10k_hw_fill_survey_time(struct ath10k *ar, struct survey_info *survey,
 				u32 cc, u32 rcc, u32 cc_prev, u32 rcc_prev);
 
 #define QCA_REV_988X(ar) ((ar)->hw_rev == ATH10K_HW_QCA988X)
+#define QCA_REV_9887(ar) ((ar)->hw_rev == ATH10K_HW_QCA9887)
 #define QCA_REV_6174(ar) ((ar)->hw_rev == ATH10K_HW_QCA6174)
 #define QCA_REV_99X0(ar) ((ar)->hw_rev == ATH10K_HW_QCA99X0)
+#define QCA_REV_9984(ar) ((ar)->hw_rev == ATH10K_HW_QCA9984)
 #define QCA_REV_9377(ar) ((ar)->hw_rev == ATH10K_HW_QCA9377)
 #define QCA_REV_40XX(ar) ((ar)->hw_rev == ATH10K_HW_QCA4019)
 
@@ -315,11 +336,41 @@ enum ath10k_hw_rate_cck {
 	ATH10K_HW_RATE_CCK_SP_2M,
 };
 
+enum ath10k_hw_rate_rev2_cck {
+	ATH10K_HW_RATE_REV2_CCK_LP_1M = 1,
+	ATH10K_HW_RATE_REV2_CCK_LP_2M,
+	ATH10K_HW_RATE_REV2_CCK_LP_5_5M,
+	ATH10K_HW_RATE_REV2_CCK_LP_11M,
+	ATH10K_HW_RATE_REV2_CCK_SP_2M,
+	ATH10K_HW_RATE_REV2_CCK_SP_5_5M,
+	ATH10K_HW_RATE_REV2_CCK_SP_11M,
+};
+
 enum ath10k_hw_4addr_pad {
 	ATH10K_HW_4ADDR_PAD_AFTER,
 	ATH10K_HW_4ADDR_PAD_BEFORE,
 };
 
+enum ath10k_hw_cc_wraparound_type {
+	ATH10K_HW_CC_WRAP_DISABLED = 0,
+
+	/* This type is when the HW chip has a quirky Cycle Counter
+	 * wraparound which resets to 0x7fffffff instead of 0. All
+	 * other CC related counters (e.g. Rx Clear Count) are divided
+	 * by 2 so they never wraparound themselves.
+	 */
+	ATH10K_HW_CC_WRAP_SHIFTED_ALL = 1,
+
+	/* Each hw counter wrapsaround independently. When the
+	 * counter overflows the repestive counter is right shifted
+	 * by 1, i.e reset to 0x7fffffff, and other counters will be
+	 * running unaffected. In this type of wraparound, it should
+	 * be possible to report accurate Rx busy time unlike the
+	 * first type.
+	 */
+	ATH10K_HW_CC_WRAP_SHIFTED_EACH = 2,
+};
+
 /* Target specific defines for MAIN firmware */
 #define TARGET_NUM_VDEVS			8
 #define TARGET_NUM_PEER_AST			2
@@ -547,7 +598,10 @@ enum ath10k_hw_4addr_pad {
 #define WLAN_SYSTEM_SLEEP_DISABLE_MASK		0x00000001
 
 #define WLAN_GPIO_PIN0_ADDRESS			0x00000028
+#define WLAN_GPIO_PIN0_CONFIG_LSB		11
 #define WLAN_GPIO_PIN0_CONFIG_MASK		0x00007800
+#define WLAN_GPIO_PIN0_PAD_PULL_LSB		5
+#define WLAN_GPIO_PIN0_PAD_PULL_MASK		0x00000060
 #define WLAN_GPIO_PIN1_ADDRESS			0x0000002c
 #define WLAN_GPIO_PIN1_CONFIG_MASK		0x00007800
 #define WLAN_GPIO_PIN10_ADDRESS			0x00000050
@@ -560,6 +614,8 @@ enum ath10k_hw_4addr_pad {
 #define CLOCK_GPIO_BT_CLK_OUT_EN_MASK		0
 
 #define SI_CONFIG_OFFSET			0x00000000
+#define SI_CONFIG_ERR_INT_LSB			19
+#define SI_CONFIG_ERR_INT_MASK			0x00080000
 #define SI_CONFIG_BIDIR_OD_DATA_LSB		18
 #define SI_CONFIG_BIDIR_OD_DATA_MASK		0x00040000
 #define SI_CONFIG_I2C_LSB			16
@@ -573,7 +629,9 @@ enum ath10k_hw_4addr_pad {
 #define SI_CONFIG_DIVIDER_LSB			0
 #define SI_CONFIG_DIVIDER_MASK			0x0000000f
 #define SI_CS_OFFSET				0x00000004
+#define SI_CS_DONE_ERR_LSB			10
 #define SI_CS_DONE_ERR_MASK			0x00000400
+#define SI_CS_DONE_INT_LSB			9
 #define SI_CS_DONE_INT_MASK			0x00000200
 #define SI_CS_START_LSB				8
 #define SI_CS_START_MASK			0x00000100
@@ -624,7 +682,10 @@ enum ath10k_hw_4addr_pad {
 #define GPIO_BASE_ADDRESS			WLAN_GPIO_BASE_ADDRESS
 #define GPIO_PIN0_OFFSET			WLAN_GPIO_PIN0_ADDRESS
 #define GPIO_PIN1_OFFSET			WLAN_GPIO_PIN1_ADDRESS
+#define GPIO_PIN0_CONFIG_LSB			WLAN_GPIO_PIN0_CONFIG_LSB
 #define GPIO_PIN0_CONFIG_MASK			WLAN_GPIO_PIN0_CONFIG_MASK
+#define GPIO_PIN0_PAD_PULL_LSB			WLAN_GPIO_PIN0_PAD_PULL_LSB
+#define GPIO_PIN0_PAD_PULL_MASK			WLAN_GPIO_PIN0_PAD_PULL_MASK
 #define GPIO_PIN1_CONFIG_MASK			WLAN_GPIO_PIN1_CONFIG_MASK
 #define SI_BASE_ADDRESS				WLAN_SI_BASE_ADDRESS
 #define SCRATCH_BASE_ADDRESS			SOC_CORE_BASE_ADDRESS
@@ -679,6 +740,18 @@ enum ath10k_hw_4addr_pad {
 #define WINDOW_READ_ADDR_ADDRESS		MISSING
 #define WINDOW_WRITE_ADDR_ADDRESS		MISSING
 
+#define QCA9887_1_0_I2C_SDA_GPIO_PIN		5
+#define QCA9887_1_0_I2C_SDA_PIN_CONFIG		3
+#define QCA9887_1_0_SI_CLK_GPIO_PIN		17
+#define QCA9887_1_0_SI_CLK_PIN_CONFIG		3
+#define QCA9887_1_0_GPIO_ENABLE_W1TS_LOW_ADDRESS 0x00000010
+
+#define QCA9887_EEPROM_SELECT_READ		0xa10000a0
+#define QCA9887_EEPROM_ADDR_HI_MASK		0x0000ff00
+#define QCA9887_EEPROM_ADDR_HI_LSB		8
+#define QCA9887_EEPROM_ADDR_LO_MASK		0x00ff0000
+#define QCA9887_EEPROM_ADDR_LO_LSB		16
+
 #define RTC_STATE_V_GET(x) (((x) & RTC_STATE_V_MASK) >> RTC_STATE_V_LSB)
 
 #endif /* _HW_H_ */
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 6dd1d26b357f..d4b7a168f7c0 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -62,6 +62,32 @@ static struct ieee80211_rate ath10k_rates[] = {
 	{ .bitrate = 540, .hw_value = ATH10K_HW_RATE_OFDM_54M },
 };
 
+static struct ieee80211_rate ath10k_rates_rev2[] = {
+	{ .bitrate = 10,
+	  .hw_value = ATH10K_HW_RATE_REV2_CCK_LP_1M },
+	{ .bitrate = 20,
+	  .hw_value = ATH10K_HW_RATE_REV2_CCK_LP_2M,
+	  .hw_value_short = ATH10K_HW_RATE_REV2_CCK_SP_2M,
+	  .flags = IEEE80211_RATE_SHORT_PREAMBLE },
+	{ .bitrate = 55,
+	  .hw_value = ATH10K_HW_RATE_REV2_CCK_LP_5_5M,
+	  .hw_value_short = ATH10K_HW_RATE_REV2_CCK_SP_5_5M,
+	  .flags = IEEE80211_RATE_SHORT_PREAMBLE },
+	{ .bitrate = 110,
+	  .hw_value = ATH10K_HW_RATE_REV2_CCK_LP_11M,
+	  .hw_value_short = ATH10K_HW_RATE_REV2_CCK_SP_11M,
+	  .flags = IEEE80211_RATE_SHORT_PREAMBLE },
+
+	{ .bitrate = 60, .hw_value = ATH10K_HW_RATE_OFDM_6M },
+	{ .bitrate = 90, .hw_value = ATH10K_HW_RATE_OFDM_9M },
+	{ .bitrate = 120, .hw_value = ATH10K_HW_RATE_OFDM_12M },
+	{ .bitrate = 180, .hw_value = ATH10K_HW_RATE_OFDM_18M },
+	{ .bitrate = 240, .hw_value = ATH10K_HW_RATE_OFDM_24M },
+	{ .bitrate = 360, .hw_value = ATH10K_HW_RATE_OFDM_36M },
+	{ .bitrate = 480, .hw_value = ATH10K_HW_RATE_OFDM_48M },
+	{ .bitrate = 540, .hw_value = ATH10K_HW_RATE_OFDM_54M },
+};
+
 #define ATH10K_MAC_FIRST_OFDM_RATE_IDX 4
 
 #define ath10k_a_rates (ath10k_rates + ATH10K_MAC_FIRST_OFDM_RATE_IDX)
@@ -70,6 +96,9 @@ static struct ieee80211_rate ath10k_rates[] = {
 #define ath10k_g_rates (ath10k_rates + 0)
 #define ath10k_g_rates_size (ARRAY_SIZE(ath10k_rates))
 
+#define ath10k_g_rates_rev2 (ath10k_rates_rev2 + 0)
+#define ath10k_g_rates_rev2_size (ARRAY_SIZE(ath10k_rates_rev2))
+
 static bool ath10k_mac_bitrate_is_cck(int bitrate)
 {
 	switch (bitrate) {
@@ -679,10 +708,10 @@ static int ath10k_peer_create(struct ath10k *ar,
 
 	peer = ath10k_peer_find(ar, vdev_id, addr);
 	if (!peer) {
+		spin_unlock_bh(&ar->data_lock);
 		ath10k_warn(ar, "failed to find peer %pM on vdev %i after creation\n",
 			    addr, vdev_id);
 		ath10k_wmi_peer_delete(ar, vdev_id, addr);
-		spin_unlock_bh(&ar->data_lock);
 		return -ENOENT;
 	}
 
@@ -3781,6 +3810,9 @@ void ath10k_mac_tx_push_pending(struct ath10k *ar)
 	int ret;
 	int max;
 
+	if (ar->htt.num_pending_tx >= (ar->htt.max_num_pending_tx / 2))
+		return;
+
 	spin_lock_bh(&ar->txqs_lock);
 	rcu_read_lock();
 
@@ -4051,9 +4083,7 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 		list_add_tail(&artxq->list, &ar->txqs);
 	spin_unlock_bh(&ar->txqs_lock);
 
-	if (ath10k_mac_tx_can_push(hw, txq))
-		tasklet_schedule(&ar->htt.txrx_compl_task);
-
+	ath10k_mac_tx_push_pending(ar);
 	ath10k_htt_tx_txq_update(hw, txq);
 }
 
@@ -4467,6 +4497,19 @@ static int ath10k_start(struct ieee80211_hw *hw)
 		}
 	}
 
+	param = ar->wmi.pdev_param->enable_btcoex;
+	if (test_bit(WMI_SERVICE_COEX_GPIO, ar->wmi.svc_map) &&
+	    test_bit(ATH10K_FW_FEATURE_BTCOEX_PARAM,
+		     ar->running_fw->fw_file.fw_features)) {
+		ret = ath10k_wmi_pdev_set_param(ar, param, 0);
+		if (ret) {
+			ath10k_warn(ar,
+				    "failed to set btcoex param: %d\n", ret);
+			goto err_core_stop;
+		}
+		clear_bit(ATH10K_FLAG_BTCOEX, &ar->dev_flags);
+	}
+
 	ar->num_started_vdevs = 0;
 	ath10k_regd_update(ar);
 
@@ -7695,8 +7738,14 @@ int ath10k_mac_register(struct ath10k *ar)
 		band = &ar->mac.sbands[NL80211_BAND_2GHZ];
 		band->n_channels = ARRAY_SIZE(ath10k_2ghz_channels);
 		band->channels = channels;
-		band->n_bitrates = ath10k_g_rates_size;
-		band->bitrates = ath10k_g_rates;
+
+		if (ar->hw_params.cck_rate_map_rev2) {
+			band->n_bitrates = ath10k_g_rates_rev2_size;
+			band->bitrates = ath10k_g_rates_rev2;
+		} else {
+			band->n_bitrates = ath10k_g_rates_size;
+			band->bitrates = ath10k_g_rates;
+		}
 
 		ar->hw->wiphy->bands[NL80211_BAND_2GHZ] = band;
 	}
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 8133d7b5b956..f06dd3941bac 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -56,7 +56,9 @@ static const struct pci_device_id ath10k_pci_id_table[] = {
 	{ PCI_VDEVICE(ATHEROS, QCA6164_2_1_DEVICE_ID) }, /* PCI-E QCA6164 V2.1 */
 	{ PCI_VDEVICE(ATHEROS, QCA6174_2_1_DEVICE_ID) }, /* PCI-E QCA6174 V2.1 */
 	{ PCI_VDEVICE(ATHEROS, QCA99X0_2_0_DEVICE_ID) }, /* PCI-E QCA99X0 V2 */
+	{ PCI_VDEVICE(ATHEROS, QCA9984_1_0_DEVICE_ID) }, /* PCI-E QCA9984 V1 */
 	{ PCI_VDEVICE(ATHEROS, QCA9377_1_0_DEVICE_ID) }, /* PCI-E QCA9377 V1 */
+	{ PCI_VDEVICE(ATHEROS, QCA9887_1_0_DEVICE_ID) }, /* PCI-E QCA9887 */
 	{0}
 };
 
@@ -81,8 +83,12 @@ static const struct ath10k_pci_supp_chip ath10k_pci_supp_chips[] = {
 
 	{ QCA99X0_2_0_DEVICE_ID, QCA99X0_HW_2_0_CHIP_ID_REV },
 
+	{ QCA9984_1_0_DEVICE_ID, QCA9984_HW_1_0_CHIP_ID_REV },
+
 	{ QCA9377_1_0_DEVICE_ID, QCA9377_HW_1_0_CHIP_ID_REV },
 	{ QCA9377_1_0_DEVICE_ID, QCA9377_HW_1_1_CHIP_ID_REV },
+
+	{ QCA9887_1_0_DEVICE_ID, QCA9887_HW_1_0_CHIP_ID_REV },
 };
 
 static void ath10k_pci_buffer_cleanup(struct ath10k *ar);
@@ -837,6 +843,7 @@ static u32 ath10k_pci_targ_cpu_to_ce_addr(struct ath10k *ar, u32 addr)
 
 	switch (ar->hw_rev) {
 	case ATH10K_HW_QCA988X:
+	case ATH10K_HW_QCA9887:
 	case ATH10K_HW_QCA6174:
 	case ATH10K_HW_QCA9377:
 		val = (ath10k_pci_read32(ar, SOC_CORE_BASE_ADDRESS +
@@ -844,6 +851,7 @@ static u32 ath10k_pci_targ_cpu_to_ce_addr(struct ath10k *ar, u32 addr)
 		       0x7ff) << 21;
 		break;
 	case ATH10K_HW_QCA99X0:
+	case ATH10K_HW_QCA9984:
 	case ATH10K_HW_QCA4019:
 		val = ath10k_pci_read32(ar, PCIE_BAR_REG_ADDRESS);
 		break;
@@ -864,7 +872,7 @@ static int ath10k_pci_diag_read_mem(struct ath10k *ar, u32 address, void *data,
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 	int ret = 0;
 	u32 *buf;
-	unsigned int completed_nbytes, orig_nbytes, remaining_bytes;
+	unsigned int completed_nbytes, alloc_nbytes, remaining_bytes;
 	struct ath10k_ce_pipe *ce_diag;
 	/* Host buffer address in CE space */
 	u32 ce_data;
@@ -882,9 +890,10 @@ static int ath10k_pci_diag_read_mem(struct ath10k *ar, u32 address, void *data,
 	 *   1) 4-byte alignment
 	 *   2) Buffer in DMA-able space
 	 */
-	orig_nbytes = nbytes;
+	alloc_nbytes = min_t(unsigned int, nbytes, DIAG_TRANSFER_LIMIT);
+
 	data_buf = (unsigned char *)dma_alloc_coherent(ar->dev,
-						       orig_nbytes,
+						       alloc_nbytes,
 						       &ce_data_base,
 						       GFP_ATOMIC);
 
@@ -892,9 +901,9 @@ static int ath10k_pci_diag_read_mem(struct ath10k *ar, u32 address, void *data,
 		ret = -ENOMEM;
 		goto done;
 	}
-	memset(data_buf, 0, orig_nbytes);
+	memset(data_buf, 0, alloc_nbytes);
 
-	remaining_bytes = orig_nbytes;
+	remaining_bytes = nbytes;
 	ce_data = ce_data_base;
 	while (remaining_bytes) {
 		nbytes = min_t(unsigned int, remaining_bytes,
@@ -954,19 +963,22 @@ static int ath10k_pci_diag_read_mem(struct ath10k *ar, u32 address, void *data,
 		}
 
 		remaining_bytes -= nbytes;
+
+		if (ret) {
+			ath10k_warn(ar, "failed to read diag value at 0x%x: %d\n",
+				    address, ret);
+			break;
+		}
+		memcpy(data, data_buf, nbytes);
+
 		address += nbytes;
-		ce_data += nbytes;
+		data += nbytes;
 	}
 
 done:
-	if (ret == 0)
-		memcpy(data, data_buf, orig_nbytes);
-	else
-		ath10k_warn(ar, "failed to read diag value at 0x%x: %d\n",
-			    address, ret);
 
 	if (data_buf)
-		dma_free_coherent(ar->dev, orig_nbytes, data_buf,
+		dma_free_coherent(ar->dev, alloc_nbytes, data_buf,
 				  ce_data_base);
 
 	spin_unlock_bh(&ar_pci->ce_lock);
@@ -1560,6 +1572,7 @@ static void ath10k_pci_irq_msi_fw_mask(struct ath10k *ar)
 
 	switch (ar->hw_rev) {
 	case ATH10K_HW_QCA988X:
+	case ATH10K_HW_QCA9887:
 	case ATH10K_HW_QCA6174:
 	case ATH10K_HW_QCA9377:
 		val = ath10k_pci_read32(ar, SOC_CORE_BASE_ADDRESS +
@@ -1569,6 +1582,7 @@ static void ath10k_pci_irq_msi_fw_mask(struct ath10k *ar)
 				   CORE_CTRL_ADDRESS, val);
 		break;
 	case ATH10K_HW_QCA99X0:
+	case ATH10K_HW_QCA9984:
 	case ATH10K_HW_QCA4019:
 		/* TODO: Find appropriate register configuration for QCA99X0
 		 *  to mask irq/MSI.
@@ -1583,6 +1597,7 @@ static void ath10k_pci_irq_msi_fw_unmask(struct ath10k *ar)
 
 	switch (ar->hw_rev) {
 	case ATH10K_HW_QCA988X:
+	case ATH10K_HW_QCA9887:
 	case ATH10K_HW_QCA6174:
 	case ATH10K_HW_QCA9377:
 		val = ath10k_pci_read32(ar, SOC_CORE_BASE_ADDRESS +
@@ -1592,6 +1607,7 @@ static void ath10k_pci_irq_msi_fw_unmask(struct ath10k *ar)
 				   CORE_CTRL_ADDRESS, val);
 		break;
 	case ATH10K_HW_QCA99X0:
+	case ATH10K_HW_QCA9984:
 	case ATH10K_HW_QCA4019:
 		/* TODO: Find appropriate register configuration for QCA99X0
 		 *  to unmask irq/MSI.
@@ -1932,6 +1948,8 @@ static int ath10k_pci_get_num_banks(struct ath10k *ar)
 	switch (ar_pci->pdev->device) {
 	case QCA988X_2_0_DEVICE_ID:
 	case QCA99X0_2_0_DEVICE_ID:
+	case QCA9984_1_0_DEVICE_ID:
+	case QCA9887_1_0_DEVICE_ID:
 		return 1;
 	case QCA6164_2_1_DEVICE_ID:
 	case QCA6174_2_1_DEVICE_ID:
@@ -2293,16 +2311,20 @@ static int ath10k_pci_warm_reset(struct ath10k *ar)
 	return 0;
 }
 
+static int ath10k_pci_qca99x0_soft_chip_reset(struct ath10k *ar)
+{
+	ath10k_pci_irq_disable(ar);
+	return ath10k_pci_qca99x0_chip_reset(ar);
+}
+
 static int ath10k_pci_safe_chip_reset(struct ath10k *ar)
 {
-	if (QCA_REV_988X(ar) || QCA_REV_6174(ar)) {
-		return ath10k_pci_warm_reset(ar);
-	} else if (QCA_REV_99X0(ar)) {
-		ath10k_pci_irq_disable(ar);
-		return ath10k_pci_qca99x0_chip_reset(ar);
-	} else {
+	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+
+	if (!ar_pci->pci_soft_reset)
 		return -ENOTSUPP;
-	}
+
+	return ar_pci->pci_soft_reset(ar);
 }
 
 static int ath10k_pci_qca988x_chip_reset(struct ath10k *ar)
@@ -2437,16 +2459,12 @@ static int ath10k_pci_qca99x0_chip_reset(struct ath10k *ar)
 
 static int ath10k_pci_chip_reset(struct ath10k *ar)
 {
-	if (QCA_REV_988X(ar))
-		return ath10k_pci_qca988x_chip_reset(ar);
-	else if (QCA_REV_6174(ar))
-		return ath10k_pci_qca6174_chip_reset(ar);
-	else if (QCA_REV_9377(ar))
-		return ath10k_pci_qca6174_chip_reset(ar);
-	else if (QCA_REV_99X0(ar))
-		return ath10k_pci_qca99x0_chip_reset(ar);
-	else
+	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+
+	if (WARN_ON(!ar_pci->pci_hard_reset))
 		return -ENOTSUPP;
+
+	return ar_pci->pci_hard_reset(ar);
 }
 
 static int ath10k_pci_hif_power_up(struct ath10k *ar)
@@ -2559,6 +2577,144 @@ static int ath10k_pci_hif_resume(struct ath10k *ar)
 }
 #endif
 
+static bool ath10k_pci_validate_cal(void *data, size_t size)
+{
+	__le16 *cal_words = data;
+	u16 checksum = 0;
+	size_t i;
+
+	if (size % 2 != 0)
+		return false;
+
+	for (i = 0; i < size / 2; i++)
+		checksum ^= le16_to_cpu(cal_words[i]);
+
+	return checksum == 0xffff;
+}
+
+static void ath10k_pci_enable_eeprom(struct ath10k *ar)
+{
+	/* Enable SI clock */
+	ath10k_pci_soc_write32(ar, CLOCK_CONTROL_OFFSET, 0x0);
+
+	/* Configure GPIOs for I2C operation */
+	ath10k_pci_write32(ar,
+			   GPIO_BASE_ADDRESS + GPIO_PIN0_OFFSET +
+			   4 * QCA9887_1_0_I2C_SDA_GPIO_PIN,
+			   SM(QCA9887_1_0_I2C_SDA_PIN_CONFIG,
+			      GPIO_PIN0_CONFIG) |
+			   SM(1, GPIO_PIN0_PAD_PULL));
+
+	ath10k_pci_write32(ar,
+			   GPIO_BASE_ADDRESS + GPIO_PIN0_OFFSET +
+			   4 * QCA9887_1_0_SI_CLK_GPIO_PIN,
+			   SM(QCA9887_1_0_SI_CLK_PIN_CONFIG, GPIO_PIN0_CONFIG) |
+			   SM(1, GPIO_PIN0_PAD_PULL));
+
+	ath10k_pci_write32(ar,
+			   GPIO_BASE_ADDRESS +
+			   QCA9887_1_0_GPIO_ENABLE_W1TS_LOW_ADDRESS,
+			   1u << QCA9887_1_0_SI_CLK_GPIO_PIN);
+
+	/* In Swift ASIC - EEPROM clock will be (110MHz/512) = 214KHz */
+	ath10k_pci_write32(ar,
+			   SI_BASE_ADDRESS + SI_CONFIG_OFFSET,
+			   SM(1, SI_CONFIG_ERR_INT) |
+			   SM(1, SI_CONFIG_BIDIR_OD_DATA) |
+			   SM(1, SI_CONFIG_I2C) |
+			   SM(1, SI_CONFIG_POS_SAMPLE) |
+			   SM(1, SI_CONFIG_INACTIVE_DATA) |
+			   SM(1, SI_CONFIG_INACTIVE_CLK) |
+			   SM(8, SI_CONFIG_DIVIDER));
+}
+
+static int ath10k_pci_read_eeprom(struct ath10k *ar, u16 addr, u8 *out)
+{
+	u32 reg;
+	int wait_limit;
+
+	/* set device select byte and for the read operation */
+	reg = QCA9887_EEPROM_SELECT_READ |
+	      SM(addr, QCA9887_EEPROM_ADDR_LO) |
+	      SM(addr >> 8, QCA9887_EEPROM_ADDR_HI);
+	ath10k_pci_write32(ar, SI_BASE_ADDRESS + SI_TX_DATA0_OFFSET, reg);
+
+	/* write transmit data, transfer length, and START bit */
+	ath10k_pci_write32(ar, SI_BASE_ADDRESS + SI_CS_OFFSET,
+			   SM(1, SI_CS_START) | SM(1, SI_CS_RX_CNT) |
+			   SM(4, SI_CS_TX_CNT));
+
+	/* wait max 1 sec */
+	wait_limit = 100000;
+
+	/* wait for SI_CS_DONE_INT */
+	do {
+		reg = ath10k_pci_read32(ar, SI_BASE_ADDRESS + SI_CS_OFFSET);
+		if (MS(reg, SI_CS_DONE_INT))
+			break;
+
+		wait_limit--;
+		udelay(10);
+	} while (wait_limit > 0);
+
+	if (!MS(reg, SI_CS_DONE_INT)) {
+		ath10k_err(ar, "timeout while reading device EEPROM at %04x\n",
+			   addr);
+		return -ETIMEDOUT;
+	}
+
+	/* clear SI_CS_DONE_INT */
+	ath10k_pci_write32(ar, SI_BASE_ADDRESS + SI_CS_OFFSET, reg);
+
+	if (MS(reg, SI_CS_DONE_ERR)) {
+		ath10k_err(ar, "failed to read device EEPROM at %04x\n", addr);
+		return -EIO;
+	}
+
+	/* extract receive data */
+	reg = ath10k_pci_read32(ar, SI_BASE_ADDRESS + SI_RX_DATA0_OFFSET);
+	*out = reg;
+
+	return 0;
+}
+
+static int ath10k_pci_hif_fetch_cal_eeprom(struct ath10k *ar, void **data,
+					   size_t *data_len)
+{
+	u8 *caldata = NULL;
+	size_t calsize, i;
+	int ret;
+
+	if (!QCA_REV_9887(ar))
+		return -EOPNOTSUPP;
+
+	calsize = ar->hw_params.cal_data_len;
+	caldata = kmalloc(calsize, GFP_KERNEL);
+	if (!caldata)
+		return -ENOMEM;
+
+	ath10k_pci_enable_eeprom(ar);
+
+	for (i = 0; i < calsize; i++) {
+		ret = ath10k_pci_read_eeprom(ar, i, &caldata[i]);
+		if (ret)
+			goto err_free;
+	}
+
+	if (!ath10k_pci_validate_cal(caldata, calsize))
+		goto err_free;
+
+	*data = caldata;
+	*data_len = calsize;
+
+	return 0;
+
+err_free:
+	kfree(data);
+
+	return -EINVAL;
+}
+
 static const struct ath10k_hif_ops ath10k_pci_hif_ops = {
 	.tx_sg			= ath10k_pci_hif_tx_sg,
 	.diag_read		= ath10k_pci_hif_diag_read,
@@ -2578,6 +2734,7 @@ static const struct ath10k_hif_ops ath10k_pci_hif_ops = {
 	.suspend		= ath10k_pci_hif_suspend,
 	.resume			= ath10k_pci_hif_resume,
 #endif
+	.fetch_cal_eeprom	= ath10k_pci_hif_fetch_cal_eeprom,
 };
 
 /*
@@ -2976,24 +3133,47 @@ static int ath10k_pci_probe(struct pci_dev *pdev,
 	enum ath10k_hw_rev hw_rev;
 	u32 chip_id;
 	bool pci_ps;
+	int (*pci_soft_reset)(struct ath10k *ar);
+	int (*pci_hard_reset)(struct ath10k *ar);
 
 	switch (pci_dev->device) {
 	case QCA988X_2_0_DEVICE_ID:
 		hw_rev = ATH10K_HW_QCA988X;
 		pci_ps = false;
+		pci_soft_reset = ath10k_pci_warm_reset;
+		pci_hard_reset = ath10k_pci_qca988x_chip_reset;
+		break;
+	case QCA9887_1_0_DEVICE_ID:
+		dev_warn(&pdev->dev, "QCA9887 support is still experimental, there are likely bugs. You have been warned.\n");
+		hw_rev = ATH10K_HW_QCA9887;
+		pci_ps = false;
+		pci_soft_reset = ath10k_pci_warm_reset;
+		pci_hard_reset = ath10k_pci_qca988x_chip_reset;
 		break;
 	case QCA6164_2_1_DEVICE_ID:
 	case QCA6174_2_1_DEVICE_ID:
 		hw_rev = ATH10K_HW_QCA6174;
 		pci_ps = true;
+		pci_soft_reset = ath10k_pci_warm_reset;
+		pci_hard_reset = ath10k_pci_qca6174_chip_reset;
 		break;
 	case QCA99X0_2_0_DEVICE_ID:
 		hw_rev = ATH10K_HW_QCA99X0;
 		pci_ps = false;
+		pci_soft_reset = ath10k_pci_qca99x0_soft_chip_reset;
+		pci_hard_reset = ath10k_pci_qca99x0_chip_reset;
+		break;
+	case QCA9984_1_0_DEVICE_ID:
+		hw_rev = ATH10K_HW_QCA9984;
+		pci_ps = false;
+		pci_soft_reset = ath10k_pci_qca99x0_soft_chip_reset;
+		pci_hard_reset = ath10k_pci_qca99x0_chip_reset;
 		break;
 	case QCA9377_1_0_DEVICE_ID:
 		hw_rev = ATH10K_HW_QCA9377;
 		pci_ps = true;
+		pci_soft_reset = NULL;
+		pci_hard_reset = ath10k_pci_qca6174_chip_reset;
 		break;
 	default:
 		WARN_ON(1);
@@ -3018,6 +3198,8 @@ static int ath10k_pci_probe(struct pci_dev *pdev,
 	ar->dev_id = pci_dev->device;
 	ar_pci->pci_ps = pci_ps;
 	ar_pci->bus_ops = &ath10k_pci_bus_ops;
+	ar_pci->pci_soft_reset = pci_soft_reset;
+	ar_pci->pci_hard_reset = pci_hard_reset;
 
 	ar->id.vendor = pdev->vendor;
 	ar->id.device = pdev->device;
@@ -3169,7 +3351,7 @@ static void __exit ath10k_pci_exit(void)
 module_exit(ath10k_pci_exit);
 
 MODULE_AUTHOR("Qualcomm Atheros");
-MODULE_DESCRIPTION("Driver support for Atheros QCA988X PCIe devices");
+MODULE_DESCRIPTION("Driver support for Qualcomm Atheros 802.11ac WLAN PCIe/AHB devices");
 MODULE_LICENSE("Dual BSD/GPL");
 
 /* QCA988x 2.0 firmware files */
@@ -3180,6 +3362,11 @@ MODULE_FIRMWARE(QCA988X_HW_2_0_FW_DIR "/" ATH10K_FW_API5_FILE);
 MODULE_FIRMWARE(QCA988X_HW_2_0_FW_DIR "/" QCA988X_HW_2_0_BOARD_DATA_FILE);
 MODULE_FIRMWARE(QCA988X_HW_2_0_FW_DIR "/" ATH10K_BOARD_API2_FILE);
 
+/* QCA9887 1.0 firmware files */
+MODULE_FIRMWARE(QCA9887_HW_1_0_FW_DIR "/" ATH10K_FW_API5_FILE);
+MODULE_FIRMWARE(QCA9887_HW_1_0_FW_DIR "/" QCA9887_HW_1_0_BOARD_DATA_FILE);
+MODULE_FIRMWARE(QCA9887_HW_1_0_FW_DIR "/" ATH10K_BOARD_API2_FILE);
+
 /* QCA6174 2.1 firmware files */
 MODULE_FIRMWARE(QCA6174_HW_2_1_FW_DIR "/" ATH10K_FW_API4_FILE);
 MODULE_FIRMWARE(QCA6174_HW_2_1_FW_DIR "/" ATH10K_FW_API5_FILE);
diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h
index 959dc321b75e..6eca1df2ce60 100644
--- a/drivers/net/wireless/ath/ath10k/pci.h
+++ b/drivers/net/wireless/ath/ath10k/pci.h
@@ -234,6 +234,12 @@ struct ath10k_pci {
 
 	const struct ath10k_bus_ops *bus_ops;
 
+	/* Chip specific pci reset routine used to do a safe reset */
+	int (*pci_soft_reset)(struct ath10k *ar);
+
+	/* Chip specific pci full reset function */
+	int (*pci_hard_reset)(struct ath10k *ar);
+
 	/* Keep this entry in the last, memory for struct ath10k_ahb is
 	 * allocated (ahb support enabled case) in the continuation of
 	 * this struct.
diff --git a/drivers/net/wireless/ath/ath10k/rx_desc.h b/drivers/net/wireless/ath/ath10k/rx_desc.h
index ca8d16884af1..034e7a54c5b2 100644
--- a/drivers/net/wireless/ath/ath10k/rx_desc.h
+++ b/drivers/net/wireless/ath/ath10k/rx_desc.h
@@ -656,26 +656,6 @@ struct rx_msdu_end {
  *		Reserved: HW should fill with zero.  FW should ignore.
  */
 
-#define RX_PPDU_START_SIG_RATE_SELECT_OFDM 0
-#define RX_PPDU_START_SIG_RATE_SELECT_CCK  1
-
-#define RX_PPDU_START_SIG_RATE_OFDM_48 0
-#define RX_PPDU_START_SIG_RATE_OFDM_24 1
-#define RX_PPDU_START_SIG_RATE_OFDM_12 2
-#define RX_PPDU_START_SIG_RATE_OFDM_6  3
-#define RX_PPDU_START_SIG_RATE_OFDM_54 4
-#define RX_PPDU_START_SIG_RATE_OFDM_36 5
-#define RX_PPDU_START_SIG_RATE_OFDM_18 6
-#define RX_PPDU_START_SIG_RATE_OFDM_9  7
-
-#define RX_PPDU_START_SIG_RATE_CCK_LP_11  0
-#define RX_PPDU_START_SIG_RATE_CCK_LP_5_5 1
-#define RX_PPDU_START_SIG_RATE_CCK_LP_2   2
-#define RX_PPDU_START_SIG_RATE_CCK_LP_1   3
-#define RX_PPDU_START_SIG_RATE_CCK_SP_11  4
-#define RX_PPDU_START_SIG_RATE_CCK_SP_5_5 5
-#define RX_PPDU_START_SIG_RATE_CCK_SP_2   6
-
 #define HTT_RX_PPDU_START_PREAMBLE_LEGACY        0x04
 #define HTT_RX_PPDU_START_PREAMBLE_HT            0x08
 #define HTT_RX_PPDU_START_PREAMBLE_HT_WITH_TXBF  0x09
@@ -711,25 +691,6 @@ struct rx_msdu_end {
 /* No idea what this flag means. It seems to be always set in rate. */
 #define RX_PPDU_START_RATE_FLAG BIT(3)
 
-enum rx_ppdu_start_rate {
-	RX_PPDU_START_RATE_OFDM_48M = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_OFDM_48M,
-	RX_PPDU_START_RATE_OFDM_24M = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_OFDM_24M,
-	RX_PPDU_START_RATE_OFDM_12M = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_OFDM_12M,
-	RX_PPDU_START_RATE_OFDM_6M  = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_OFDM_6M,
-	RX_PPDU_START_RATE_OFDM_54M = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_OFDM_54M,
-	RX_PPDU_START_RATE_OFDM_36M = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_OFDM_36M,
-	RX_PPDU_START_RATE_OFDM_18M = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_OFDM_18M,
-	RX_PPDU_START_RATE_OFDM_9M  = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_OFDM_9M,
-
-	RX_PPDU_START_RATE_CCK_LP_11M  = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_CCK_LP_11M,
-	RX_PPDU_START_RATE_CCK_LP_5_5M = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_CCK_LP_5_5M,
-	RX_PPDU_START_RATE_CCK_LP_2M   = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_CCK_LP_2M,
-	RX_PPDU_START_RATE_CCK_LP_1M   = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_CCK_LP_1M,
-	RX_PPDU_START_RATE_CCK_SP_11M  = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_CCK_SP_11M,
-	RX_PPDU_START_RATE_CCK_SP_5_5M = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_CCK_SP_5_5M,
-	RX_PPDU_START_RATE_CCK_SP_2M   = RX_PPDU_START_RATE_FLAG | ATH10K_HW_RATE_CCK_SP_2M,
-};
-
 struct rx_ppdu_start {
 	struct {
 		u8 pri20_mhz;
@@ -994,7 +955,41 @@ struct rx_pkt_end {
 	__le32 info0; /* %RX_PKT_END_INFO0_ */
 	__le32 phy_timestamp_1;
 	__le32 phy_timestamp_2;
-	__le32 rx_location_info; /* %RX_LOCATION_INFO_ */
+} __packed;
+
+#define RX_LOCATION_INFO0_RTT_FAC_LEGACY_MASK		0x00003fff
+#define RX_LOCATION_INFO0_RTT_FAC_LEGACY_LSB		0
+#define RX_LOCATION_INFO0_RTT_FAC_VHT_MASK		0x1fff8000
+#define RX_LOCATION_INFO0_RTT_FAC_VHT_LSB		15
+#define RX_LOCATION_INFO0_RTT_STRONGEST_CHAIN_MASK	0xc0000000
+#define RX_LOCATION_INFO0_RTT_STRONGEST_CHAIN_LSB	30
+#define RX_LOCATION_INFO0_RTT_FAC_LEGACY_STATUS		BIT(14)
+#define RX_LOCATION_INFO0_RTT_FAC_VHT_STATUS		BIT(29)
+
+#define RX_LOCATION_INFO1_RTT_PREAMBLE_TYPE_MASK	0x0000000c
+#define RX_LOCATION_INFO1_RTT_PREAMBLE_TYPE_LSB		2
+#define RX_LOCATION_INFO1_PKT_BW_MASK			0x00000030
+#define RX_LOCATION_INFO1_PKT_BW_LSB			4
+#define RX_LOCATION_INFO1_SKIP_P_SKIP_BTCF_MASK		0x0000ff00
+#define RX_LOCATION_INFO1_SKIP_P_SKIP_BTCF_LSB		8
+#define RX_LOCATION_INFO1_RTT_MSC_RATE_MASK		0x000f0000
+#define RX_LOCATION_INFO1_RTT_MSC_RATE_LSB		16
+#define RX_LOCATION_INFO1_RTT_PBD_LEG_BW_MASK		0x00300000
+#define RX_LOCATION_INFO1_RTT_PBD_LEG_BW_LSB		20
+#define RX_LOCATION_INFO1_TIMING_BACKOFF_MASK		0x07c00000
+#define RX_LOCATION_INFO1_TIMING_BACKOFF_LSB		22
+#define RX_LOCATION_INFO1_RTT_TX_FRAME_PHASE_MASK	0x18000000
+#define RX_LOCATION_INFO1_RTT_TX_FRAME_PHASE_LSB	27
+#define RX_LOCATION_INFO1_RTT_CFR_STATUS		BIT(0)
+#define RX_LOCATION_INFO1_RTT_CIR_STATUS		BIT(1)
+#define RX_LOCATION_INFO1_RTT_GI_TYPE			BIT(7)
+#define RX_LOCATION_INFO1_RTT_MAC_PHY_PHASE		BIT(29)
+#define RX_LOCATION_INFO1_RTT_TX_DATA_START_X_PHASE	BIT(30)
+#define RX_LOCATION_INFO1_RX_LOCATION_VALID		BIT(31)
+
+struct rx_location_info {
+	__le32 rx_location_info0; /* %RX_LOCATION_INFO0_ */
+	__le32 rx_location_info1; /* %RX_LOCATION_INFO1_ */
 } __packed;
 
 enum rx_phy_ppdu_end_info0 {
@@ -1067,6 +1062,17 @@ struct rx_phy_ppdu_end {
 
 struct rx_ppdu_end_qca99x0 {
 	struct rx_pkt_end rx_pkt_end;
+	__le32 rx_location_info; /* %RX_LOCATION_INFO_ */
+	struct rx_phy_ppdu_end rx_phy_ppdu_end;
+	__le32 rx_timing_offset; /* %RX_PPDU_END_RX_TIMING_OFFSET_ */
+	__le32 rx_info; /* %RX_PPDU_END_RX_INFO_ */
+	__le16 bb_length;
+	__le16 info1; /* %RX_PPDU_END_INFO1_ */
+} __packed;
+
+struct rx_ppdu_end_qca9984 {
+	struct rx_pkt_end rx_pkt_end;
+	struct rx_location_info rx_location_info;
 	struct rx_phy_ppdu_end rx_phy_ppdu_end;
 	__le32 rx_timing_offset; /* %RX_PPDU_END_RX_TIMING_OFFSET_ */
 	__le32 rx_info; /* %RX_PPDU_END_RX_INFO_ */
@@ -1080,6 +1086,7 @@ struct rx_ppdu_end {
 		struct rx_ppdu_end_qca988x qca988x;
 		struct rx_ppdu_end_qca6174 qca6174;
 		struct rx_ppdu_end_qca99x0 qca99x0;
+		struct rx_ppdu_end_qca9984 qca9984;
 	} __packed;
 } __packed;
 
diff --git a/drivers/net/wireless/ath/ath10k/targaddrs.h b/drivers/net/wireless/ath/ath10k/targaddrs.h
index 8e24099fa936..aaf53a81e78b 100644
--- a/drivers/net/wireless/ath/ath10k/targaddrs.h
+++ b/drivers/net/wireless/ath/ath10k/targaddrs.h
@@ -447,6 +447,9 @@ Fw Mode/SubMode Mask
 #define QCA988X_BOARD_DATA_SZ     7168
 #define QCA988X_BOARD_EXT_DATA_SZ 0
 
+#define QCA9887_BOARD_DATA_SZ     7168
+#define QCA9887_BOARD_EXT_DATA_SZ 0
+
 #define QCA6174_BOARD_DATA_SZ     8192
 #define QCA6174_BOARD_EXT_DATA_SZ 0
 
diff --git a/drivers/net/wireless/ath/ath10k/txrx.c b/drivers/net/wireless/ath/ath10k/txrx.c
index 576e7c42ed65..1966c787998b 100644
--- a/drivers/net/wireless/ath/ath10k/txrx.c
+++ b/drivers/net/wireless/ath/ath10k/txrx.c
@@ -117,6 +117,9 @@ int ath10k_txrx_tx_unref(struct ath10k_htt *htt,
 
 	ieee80211_tx_status(htt->ar->hw, msdu);
 	/* we do not own the msdu anymore */
+
+	ath10k_mac_tx_push_pending(ar);
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 2c300329ebc3..6279ab4a760e 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -1104,6 +1104,7 @@ static struct wmi_pdev_param_map wmi_pdev_param_map = {
 	.wapi_mbssid_offset = WMI_PDEV_PARAM_UNSUPPORTED,
 	.arp_srcaddr = WMI_PDEV_PARAM_UNSUPPORTED,
 	.arp_dstaddr = WMI_PDEV_PARAM_UNSUPPORTED,
+	.enable_btcoex = WMI_PDEV_PARAM_UNSUPPORTED,
 };
 
 static struct wmi_pdev_param_map wmi_10x_pdev_param_map = {
@@ -1199,6 +1200,7 @@ static struct wmi_pdev_param_map wmi_10x_pdev_param_map = {
 	.wapi_mbssid_offset = WMI_PDEV_PARAM_UNSUPPORTED,
 	.arp_srcaddr = WMI_PDEV_PARAM_UNSUPPORTED,
 	.arp_dstaddr = WMI_PDEV_PARAM_UNSUPPORTED,
+	.enable_btcoex = WMI_PDEV_PARAM_UNSUPPORTED,
 };
 
 static struct wmi_pdev_param_map wmi_10_2_4_pdev_param_map = {
@@ -1294,6 +1296,7 @@ static struct wmi_pdev_param_map wmi_10_2_4_pdev_param_map = {
 	.wapi_mbssid_offset = WMI_PDEV_PARAM_UNSUPPORTED,
 	.arp_srcaddr = WMI_PDEV_PARAM_UNSUPPORTED,
 	.arp_dstaddr = WMI_PDEV_PARAM_UNSUPPORTED,
+	.enable_btcoex = WMI_PDEV_PARAM_UNSUPPORTED,
 };
 
 /* firmware 10.2 specific mappings */
@@ -1550,6 +1553,7 @@ static struct wmi_pdev_param_map wmi_10_4_pdev_param_map = {
 	.wapi_mbssid_offset = WMI_10_4_PDEV_PARAM_WAPI_MBSSID_OFFSET,
 	.arp_srcaddr = WMI_10_4_PDEV_PARAM_ARP_SRCADDR,
 	.arp_dstaddr = WMI_10_4_PDEV_PARAM_ARP_DSTADDR,
+	.enable_btcoex = WMI_10_4_PDEV_PARAM_ENABLE_BTCOEX,
 };
 
 static const struct wmi_peer_flags_map wmi_peer_flags_map = {
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index 9fdf47ea27d0..90f594e89f94 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -3447,6 +3447,7 @@ struct wmi_pdev_param_map {
 	u32 wapi_mbssid_offset;
 	u32 arp_srcaddr;
 	u32 arp_dstaddr;
+	u32 enable_btcoex;
 };
 
 #define WMI_PDEV_PARAM_UNSUPPORTED 0
@@ -3760,6 +3761,9 @@ enum wmi_10_4_pdev_param {
 	WMI_10_4_PDEV_PARAM_ATF_OBSS_NOISE_SCH,
 	WMI_10_4_PDEV_PARAM_ATF_OBSS_NOISE_SCALING_FACTOR,
 	WMI_10_4_PDEV_PARAM_CUST_TXPOWER_SCALE,
+	WMI_10_4_PDEV_PARAM_ATF_DYNAMIC_ENABLE,
+	WMI_10_4_PDEV_PARAM_ATF_SSID_GROUP_POLICY,
+	WMI_10_4_PDEV_PARAM_ENABLE_BTCOEX,
 };
 
 struct wmi_pdev_set_param_cmd {
diff --git a/drivers/net/wireless/ath/ath5k/pcu.c b/drivers/net/wireless/ath/ath5k/pcu.c
index fc47b70988b1..f23c851765df 100644
--- a/drivers/net/wireless/ath/ath5k/pcu.c
+++ b/drivers/net/wireless/ath/ath5k/pcu.c
@@ -219,8 +219,8 @@ ath5k_hw_get_default_sifs(struct ath5k_hw *ah)
 		sifs = AR5K_INIT_SIFS_QUARTER_RATE;
 		break;
 	case AR5K_BWMODE_DEFAULT:
-		sifs = AR5K_INIT_SIFS_DEFAULT_BG;
 	default:
+		sifs = AR5K_INIT_SIFS_DEFAULT_BG;
 		if (channel->band == NL80211_BAND_5GHZ)
 			sifs = AR5K_INIT_SIFS_DEFAULT_A;
 		break;
diff --git a/drivers/net/wireless/ath/ath6kl/core.h b/drivers/net/wireless/ath/ath6kl/core.h
index 7a1970e484a6..ac25f1781b42 100644
--- a/drivers/net/wireless/ath/ath6kl/core.h
+++ b/drivers/net/wireless/ath/ath6kl/core.h
@@ -148,7 +148,7 @@ enum ath6kl_fw_capability {
 	/* ratetable is the 2 stream version (max MCS15) */
 	ATH6KL_FW_CAPABILITY_RATETABLE_MCS15,
 
-	/* firmare doesn't support IP checksumming */
+	/* firmware doesn't support IP checksumming */
 	ATH6KL_FW_CAPABILITY_NO_IP_CHECKSUM,
 
 	/* this needs to be last */
diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c
index 631c3a0c572b..b8cf04d11975 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.c
+++ b/drivers/net/wireless/ath/ath6kl/wmi.c
@@ -2544,8 +2544,7 @@ int ath6kl_wmi_create_pstream_cmd(struct wmi *wmi, u8 if_idx,
 	s32 nominal_phy = 0;
 	int ret;
 
-	if (!((params->user_pri < 8) &&
-	      (params->user_pri <= 0x7) &&
+	if (!((params->user_pri <= 0x7) &&
 	      (up_to_ac[params->user_pri & 0x7] == params->traffic_class) &&
 	      (params->traffic_direc == UPLINK_TRAFFIC ||
 	       params->traffic_direc == DNLINK_TRAFFIC ||
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index dec1a317a070..d0224fc58e78 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -3202,8 +3202,7 @@ static int ar9300_compress_decision(struct ath_hw *ah,
 			it, length);
 		break;
 	case _CompressBlock:
-		if (reference == 0) {
-		} else {
+		if (reference != 0) {
 			eep = ar9003_eeprom_struct_find_by_id(reference);
 			if (eep == NULL) {
 				ath_dbg(common, EEPROM,
diff --git a/drivers/net/wireless/ath/ath9k/reg.h b/drivers/net/wireless/ath/ath9k/reg.h
index 9272ca90632b..80ff69f99229 100644
--- a/drivers/net/wireless/ath/ath9k/reg.h
+++ b/drivers/net/wireless/ath/ath9k/reg.h
@@ -1122,12 +1122,12 @@ enum {
 #define AR9300_NUM_GPIO                          16
 #define AR9330_NUM_GPIO				 16
 #define AR9340_NUM_GPIO				 23
-#define AR9462_NUM_GPIO				 10
+#define AR9462_NUM_GPIO				 14
 #define AR9485_NUM_GPIO				 12
 #define AR9531_NUM_GPIO				 18
 #define AR9550_NUM_GPIO				 24
 #define AR9561_NUM_GPIO				 23
-#define AR9565_NUM_GPIO				 12
+#define AR9565_NUM_GPIO				 14
 #define AR9580_NUM_GPIO				 16
 #define AR7010_NUM_GPIO                          16
 
@@ -1139,12 +1139,12 @@ enum {
 #define AR9300_GPIO_MASK			 0x0000F4FF
 #define AR9330_GPIO_MASK			 0x0000F4FF
 #define AR9340_GPIO_MASK			 0x0000000F
-#define AR9462_GPIO_MASK			 0x000003FF
+#define AR9462_GPIO_MASK			 0x00003FFF
 #define AR9485_GPIO_MASK			 0x00000FFF
 #define AR9531_GPIO_MASK			 0x0000000F
 #define AR9550_GPIO_MASK			 0x0000000F
 #define AR9561_GPIO_MASK			 0x0000000F
-#define AR9565_GPIO_MASK			 0x00000FFF
+#define AR9565_GPIO_MASK			 0x00003FFF
 #define AR9580_GPIO_MASK			 0x0000F4FF
 #define AR7010_GPIO_MASK			 0x0000FFFF
 
diff --git a/drivers/net/wireless/ath/ath9k/tx99.c b/drivers/net/wireless/ath/ath9k/tx99.c
index ac4781f37e78..16aca9e28b77 100644
--- a/drivers/net/wireless/ath/ath9k/tx99.c
+++ b/drivers/net/wireless/ath/ath9k/tx99.c
@@ -132,7 +132,6 @@ static int ath9k_tx99_init(struct ath_softc *sc)
 	ath9k_ps_wakeup(sc);
 
 	ath9k_hw_disable_interrupts(ah);
-	atomic_set(&ah->intr_ref_cnt, -1);
 	ath_drain_all_txq(sc);
 	ath_stoprecv(sc);
 
@@ -266,7 +265,7 @@ static const struct file_operations fops_tx99_power = {
 
 void ath9k_tx99_init_debug(struct ath_softc *sc)
 {
-	if (!AR_SREV_9300_20_OR_LATER(sc->sc_ah))
+	if (!AR_SREV_9280_20_OR_LATER(sc->sc_ah))
 		return;
 
 	debugfs_create_file("tx99", S_IRUSR | S_IWUSR,
diff --git a/drivers/net/wireless/ath/carl9170/Kconfig b/drivers/net/wireless/ath/carl9170/Kconfig
index 1a796e5f69ec..2e34baeaf764 100644
--- a/drivers/net/wireless/ath/carl9170/Kconfig
+++ b/drivers/net/wireless/ath/carl9170/Kconfig
@@ -5,12 +5,10 @@ config CARL9170
 	select FW_LOADER
 	select CRC32
 	help
-	  This is another driver for the Atheros "otus" 802.11n USB devices.
+	  This is the mainline driver for the Atheros "otus" 802.11n USB devices.
 
-	  This driver provides more features than the original,
-	  but it needs a special firmware (carl9170-1.fw) to do that.
-
-	  The firmware can be downloaded from our wiki here:
+	  It needs a special firmware (carl9170-1.fw), which can be downloaded
+	  from our wiki here:
 	  <http://wireless.kernel.org/en/users/Drivers/carl9170>
 
 	  If you choose to build a module, it'll be called carl9170.
diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index 5769811291bf..62bf9331bd7f 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -378,6 +378,10 @@ static int wil_cfg80211_scan(struct wiphy *wiphy,
 	/* social scan on P2P_DEVICE is handled as p2p search */
 	if (wdev->iftype == NL80211_IFTYPE_P2P_DEVICE &&
 	    wil_p2p_is_social_scan(request)) {
+		if (!wil->p2p.p2p_dev_started) {
+			wil_err(wil, "P2P search requested on stopped P2P device\n");
+			return -EIO;
+		}
 		wil->scan_request = request;
 		wil->radio_wdev = wdev;
 		rc = wil_p2p_search(wil, request);
@@ -1351,6 +1355,7 @@ static int wil_cfg80211_start_p2p_device(struct wiphy *wiphy,
 	struct wil6210_priv *wil = wiphy_to_wil(wiphy);
 
 	wil_dbg_misc(wil, "%s: entered\n", __func__);
+	wil->p2p.p2p_dev_started = 1;
 	return 0;
 }
 
@@ -1358,8 +1363,19 @@ static void wil_cfg80211_stop_p2p_device(struct wiphy *wiphy,
 					 struct wireless_dev *wdev)
 {
 	struct wil6210_priv *wil = wiphy_to_wil(wiphy);
+	u8 started;
 
 	wil_dbg_misc(wil, "%s: entered\n", __func__);
+	mutex_lock(&wil->mutex);
+	started = wil_p2p_stop_discovery(wil);
+	if (started && wil->scan_request) {
+		cfg80211_scan_done(wil->scan_request, 1);
+		wil->scan_request = NULL;
+		wil->radio_wdev = wil->wdev;
+	}
+	mutex_unlock(&wil->mutex);
+
+	wil->p2p.p2p_dev_started = 0;
 }
 
 static struct cfg80211_ops wil_cfg80211_ops = {
diff --git a/drivers/net/wireless/ath/wil6210/debug.c b/drivers/net/wireless/ath/wil6210/debug.c
index c312a667c12a..217a4591bde4 100644
--- a/drivers/net/wireless/ath/wil6210/debug.c
+++ b/drivers/net/wireless/ath/wil6210/debug.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2013 Qualcomm Atheros, Inc.
+ * Copyright (c) 2013,2016 Qualcomm Atheros, Inc.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -19,34 +19,31 @@
 
 void __wil_err(struct wil6210_priv *wil, const char *fmt, ...)
 {
-	struct net_device *ndev = wil_to_ndev(wil);
-	struct va_format vaf = {
-		.fmt = fmt,
-	};
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
+	vaf.fmt = fmt;
 	vaf.va = &args;
-	netdev_err(ndev, "%pV", &vaf);
+	netdev_err(wil_to_ndev(wil), "%pV", &vaf);
 	trace_wil6210_log_err(&vaf);
 	va_end(args);
 }
 
 void __wil_err_ratelimited(struct wil6210_priv *wil, const char *fmt, ...)
 {
-	if (net_ratelimit()) {
-		struct net_device *ndev = wil_to_ndev(wil);
-		struct va_format vaf = {
-			.fmt = fmt,
-		};
-		va_list args;
+	struct va_format vaf;
+	va_list args;
 
-		va_start(args, fmt);
-		vaf.va = &args;
-		netdev_err(ndev, "%pV", &vaf);
-		trace_wil6210_log_err(&vaf);
-		va_end(args);
-	}
+	if (!net_ratelimit())
+		return;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	netdev_err(wil_to_ndev(wil), "%pV", &vaf);
+	trace_wil6210_log_err(&vaf);
+	va_end(args);
 }
 
 void wil_dbg_ratelimited(const struct wil6210_priv *wil, const char *fmt, ...)
@@ -67,27 +64,24 @@ void wil_dbg_ratelimited(const struct wil6210_priv *wil, const char *fmt, ...)
 
 void __wil_info(struct wil6210_priv *wil, const char *fmt, ...)
 {
-	struct net_device *ndev = wil_to_ndev(wil);
-	struct va_format vaf = {
-		.fmt = fmt,
-	};
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
+	vaf.fmt = fmt;
 	vaf.va = &args;
-	netdev_info(ndev, "%pV", &vaf);
+	netdev_info(wil_to_ndev(wil), "%pV", &vaf);
 	trace_wil6210_log_info(&vaf);
 	va_end(args);
 }
 
 void wil_dbg_trace(struct wil6210_priv *wil, const char *fmt, ...)
 {
-	struct va_format vaf = {
-		.fmt = fmt,
-	};
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
+	vaf.fmt = fmt;
 	vaf.va = &args;
 	trace_wil6210_log_dbg(&vaf);
 	va_end(args);
diff --git a/drivers/net/wireless/ath/wil6210/p2p.c b/drivers/net/wireless/ath/wil6210/p2p.c
index 1c9153894dca..213b8259638c 100644
--- a/drivers/net/wireless/ath/wil6210/p2p.c
+++ b/drivers/net/wireless/ath/wil6210/p2p.c
@@ -114,8 +114,10 @@ int wil_p2p_listen(struct wil6210_priv *wil, unsigned int duration,
 	u8 channel = P2P_DMG_SOCIAL_CHANNEL;
 	int rc;
 
-	if (chan)
-		channel = chan->hw_value;
+	if (!chan)
+		return -EINVAL;
+
+	channel = chan->hw_value;
 
 	wil_dbg_misc(wil, "%s: duration %d\n", __func__, duration);
 
diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index aeb72c438e44..7b5c4222bc33 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2012-2015 Qualcomm Atheros, Inc.
+ * Copyright (c) 2012-2016 Qualcomm Atheros, Inc.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -18,13 +18,20 @@
 #include <linux/pci.h>
 #include <linux/moduleparam.h>
 #include <linux/interrupt.h>
-
+#include <linux/suspend.h>
 #include "wil6210.h"
 
 static bool use_msi = true;
 module_param(use_msi, bool, S_IRUGO);
 MODULE_PARM_DESC(use_msi, " Use MSI interrupt, default - true");
 
+#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
+static int wil6210_pm_notify(struct notifier_block *notify_block,
+			     unsigned long mode, void *unused);
+#endif /* CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM */
+
 static
 void wil_set_capabilities(struct wil6210_priv *wil)
 {
@@ -238,6 +245,18 @@ static int wil_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto bus_disable;
 	}
 
+#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
+	wil->pm_notify.notifier_call = wil6210_pm_notify;
+	rc = register_pm_notifier(&wil->pm_notify);
+	if (rc)
+		/* Do not fail the driver initialization, as suspend can
+		 * be prevented in a later phase if needed
+		 */
+		wil_err(wil, "register_pm_notifier failed: %d\n", rc);
+#endif /* CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM */
+
 	wil6210_debugfs_init(wil);
 
 
@@ -267,6 +286,12 @@ static void wil_pcie_remove(struct pci_dev *pdev)
 
 	wil_dbg_misc(wil, "%s()\n", __func__);
 
+#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
+	unregister_pm_notifier(&wil->pm_notify);
+#endif /* CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM */
+
 	wil6210_debugfs_remove(wil);
 	wil_if_remove(wil);
 	wil_if_pcie_disable(wil);
@@ -335,6 +360,45 @@ static int wil6210_resume(struct device *dev, bool is_runtime)
 	return rc;
 }
 
+static int wil6210_pm_notify(struct notifier_block *notify_block,
+			     unsigned long mode, void *unused)
+{
+	struct wil6210_priv *wil = container_of(
+		notify_block, struct wil6210_priv, pm_notify);
+	int rc = 0;
+	enum wil_platform_event evt;
+
+	wil_dbg_pm(wil, "%s: mode (%ld)\n", __func__, mode);
+
+	switch (mode) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+	case PM_RESTORE_PREPARE:
+		rc = wil_can_suspend(wil, false);
+		if (rc)
+			break;
+		evt = WIL_PLATFORM_EVT_PRE_SUSPEND;
+		if (wil->platform_ops.notify)
+			rc = wil->platform_ops.notify(wil->platform_handle,
+						      evt);
+		break;
+	case PM_POST_SUSPEND:
+	case PM_POST_HIBERNATION:
+	case PM_POST_RESTORE:
+		evt = WIL_PLATFORM_EVT_POST_SUSPEND;
+		if (wil->platform_ops.notify)
+			rc = wil->platform_ops.notify(wil->platform_handle,
+						      evt);
+		break;
+	default:
+		wil_dbg_pm(wil, "unhandled notify mode %ld\n", mode);
+		break;
+	}
+
+	wil_dbg_pm(wil, "notification mode %ld: rc (%d)\n", mode, rc);
+	return rc;
+}
+
 static int wil6210_pm_suspend(struct device *dev)
 {
 	return wil6210_suspend(dev, false);
diff --git a/drivers/net/wireless/ath/wil6210/pm.c b/drivers/net/wireless/ath/wil6210/pm.c
index 0b7ecbcac19c..11ee24d509e5 100644
--- a/drivers/net/wireless/ath/wil6210/pm.c
+++ b/drivers/net/wireless/ath/wil6210/pm.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2014 Qualcomm Atheros, Inc.
+ * Copyright (c) 2014,2016 Qualcomm Atheros, Inc.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -24,10 +24,32 @@ int wil_can_suspend(struct wil6210_priv *wil, bool is_runtime)
 	wil_dbg_pm(wil, "%s(%s)\n", __func__,
 		   is_runtime ? "runtime" : "system");
 
+	if (!netif_running(wil_to_ndev(wil))) {
+		/* can always sleep when down */
+		wil_dbg_pm(wil, "Interface is down\n");
+		goto out;
+	}
+	if (test_bit(wil_status_resetting, wil->status)) {
+		wil_dbg_pm(wil, "Delay suspend when resetting\n");
+		rc = -EBUSY;
+		goto out;
+	}
+	if (wil->recovery_state != fw_recovery_idle) {
+		wil_dbg_pm(wil, "Delay suspend during recovery\n");
+		rc = -EBUSY;
+		goto out;
+	}
+
+	/* interface is running */
 	switch (wdev->iftype) {
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_P2P_CLIENT:
+		if (test_bit(wil_status_fwconnecting, wil->status)) {
+			wil_dbg_pm(wil, "Delay suspend when connecting\n");
+			rc = -EBUSY;
+			goto out;
+		}
 		break;
 	/* AP-like interface - can't suspend */
 	default:
@@ -36,6 +58,7 @@ int wil_can_suspend(struct wil6210_priv *wil, bool is_runtime)
 		break;
 	}
 
+out:
 	wil_dbg_pm(wil, "%s(%s) => %s (%d)\n", __func__,
 		   is_runtime ? "runtime" : "system", rc ? "No" : "Yes", rc);
 
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index a4e43796addb..f2f6a404d3d1 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -184,6 +184,13 @@ static void wil_vring_free(struct wil6210_priv *wil, struct vring *vring,
 					&vring->va[vring->swtail].tx;
 
 			ctx = &vring->ctx[vring->swtail];
+			if (!ctx) {
+				wil_dbg_txrx(wil,
+					     "ctx(%d) was already completed\n",
+					     vring->swtail);
+				vring->swtail = wil_vring_next_tail(vring);
+				continue;
+			}
 			*d = *_d;
 			wil_txdesc_unmap(dev, d, ctx);
 			if (ctx->skb)
@@ -544,6 +551,12 @@ static int wil_rx_refill(struct wil6210_priv *wil, int count)
 			break;
 		}
 	}
+
+	/* make sure all writes to descriptors (shared memory) are done before
+	 * committing them to HW
+	 */
+	wmb();
+
 	wil_w(wil, v->hwtail, v->swtail);
 
 	return rc;
@@ -969,6 +982,13 @@ void wil_vring_fini_tx(struct wil6210_priv *wil, int id)
 	txdata->dot1x_open = false;
 	txdata->enabled = 0; /* no Tx can be in progress or start anew */
 	spin_unlock_bh(&txdata->lock);
+	/* napi_synchronize waits for completion of the current NAPI but will
+	 * not prevent the next NAPI run.
+	 * Add a memory barrier to guarantee that txdata->enabled is zeroed
+	 * before napi_synchronize so that the next scheduled NAPI will not
+	 * handle this vring
+	 */
+	wmb();
 	/* make sure NAPI won't touch this vring */
 	if (test_bit(wil_status_napi_en, wil->status))
 		napi_synchronize(&wil->napi_tx);
@@ -1551,6 +1571,13 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct vring *vring,
 			     vring_index, used, used + descs_used);
 	}
 
+	/* Make sure to advance the head only after descriptor update is done.
+	 * This will prevent a race condition where the completion thread
+	 * will see the DU bit set from previous run and will handle the
+	 * skb before it was completed.
+	 */
+	wmb();
+
 	/* advance swhead */
 	wil_vring_advance_head(vring, descs_used);
 	wil_dbg_txrx(wil, "TSO: Tx swhead %d -> %d\n", swhead, vring->swhead);
@@ -1567,7 +1594,7 @@ mem_error:
 	while (descs_used > 0) {
 		struct wil_ctx *ctx;
 
-		i = (swhead + descs_used) % vring->size;
+		i = (swhead + descs_used - 1) % vring->size;
 		d = (struct vring_tx_desc *)&vring->va[i].tx;
 		_desc = &vring->va[i].tx;
 		*d = *_desc;
@@ -1691,6 +1718,13 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct vring *vring,
 			     vring_index, used, used + nr_frags + 1);
 	}
 
+	/* Make sure to advance the head only after descriptor update is done.
+	 * This will prevent a race condition where the completion thread
+	 * will see the DU bit set from previous run and will handle the
+	 * skb before it was completed.
+	 */
+	wmb();
+
 	/* advance swhead */
 	wil_vring_advance_head(vring, nr_frags + 1);
 	wil_dbg_txrx(wil, "Tx[%2d] swhead %d -> %d\n", vring_index, swhead,
@@ -1914,6 +1948,12 @@ int wil_tx_complete(struct wil6210_priv *wil, int ringid)
 				wil_consume_skb(skb, d->dma.error == 0);
 			}
 			memset(ctx, 0, sizeof(*ctx));
+			/* Make sure the ctx is zeroed before updating the tail
+			 * to prevent a case where wil_tx_vring will see
+			 * this descriptor as used and handle it before ctx zero
+			 * is completed.
+			 */
+			wmb();
 			/* There is no need to touch HW descriptor:
 			 * - ststus bit TX_DMA_STATUS_DU is set by design,
 			 *   so hardware will not try to process this desc.,
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index aa09cbcce47c..ecab4af90602 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -458,6 +458,7 @@ struct wil_tid_crypto_rx {
 struct wil_p2p_info {
 	struct ieee80211_channel listen_chan;
 	u8 discovery_started;
+	u8 p2p_dev_started;
 	u64 cookie;
 	struct timer_list discovery_timer; /* listen/search duration */
 	struct work_struct discovery_expired_work; /* listen/search expire */
@@ -662,6 +663,11 @@ struct wil6210_priv {
 	/* High Access Latency Policy voting */
 	struct wil_halp halp;
 
+#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
+	struct notifier_block pm_notify;
+#endif /* CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM */
 };
 
 #define wil_to_wiphy(i) (i->wdev->wiphy)
diff --git a/drivers/net/wireless/ath/wil6210/wil_platform.h b/drivers/net/wireless/ath/wil6210/wil_platform.h
index 33d4a34b3b1c..f8c41172a3f4 100644
--- a/drivers/net/wireless/ath/wil6210/wil_platform.h
+++ b/drivers/net/wireless/ath/wil6210/wil_platform.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2014-2015 Qualcomm Atheros, Inc.
+ * Copyright (c) 2014-2016 Qualcomm Atheros, Inc.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -23,6 +23,8 @@ enum wil_platform_event {
 	WIL_PLATFORM_EVT_FW_CRASH = 0,
 	WIL_PLATFORM_EVT_PRE_RESET = 1,
 	WIL_PLATFORM_EVT_FW_RDY = 2,
+	WIL_PLATFORM_EVT_PRE_SUSPEND = 3,
+	WIL_PLATFORM_EVT_POST_SUSPEND = 4,
 };
 
 /**
diff --git a/drivers/net/wireless/broadcom/b43/Makefile b/drivers/net/wireless/broadcom/b43/Makefile
index ddc4df46656f..27fab958e3d5 100644
--- a/drivers/net/wireless/broadcom/b43/Makefile
+++ b/drivers/net/wireless/broadcom/b43/Makefile
@@ -1,6 +1,6 @@
 b43-y				+= main.o
 b43-y				+= bus.o
-b43-$(CONFIG_B43_PHY_G)		+= phy_a.o phy_g.o tables.o lo.o wa.o
+b43-$(CONFIG_B43_PHY_G)		+= phy_g.o tables.o lo.o wa.o
 b43-$(CONFIG_B43_PHY_N)		+= tables_nphy.o
 b43-$(CONFIG_B43_PHY_N)		+= radio_2055.o
 b43-$(CONFIG_B43_PHY_N)		+= radio_2056.o
diff --git a/drivers/net/wireless/broadcom/b43/leds.c b/drivers/net/wireless/broadcom/b43/leds.c
index d79ab2a227e1..cb987c2ecc6b 100644
--- a/drivers/net/wireless/broadcom/b43/leds.c
+++ b/drivers/net/wireless/broadcom/b43/leds.c
@@ -222,7 +222,7 @@ static void b43_led_get_sprominfo(struct b43_wldev *dev,
 	sprom[2] = dev->dev->bus_sprom->gpio2;
 	sprom[3] = dev->dev->bus_sprom->gpio3;
 
-	if (sprom[led_index] == 0xFF) {
+	if ((sprom[0] & sprom[1] & sprom[2] & sprom[3]) == 0xff) {
 		/* There is no LED information in the SPROM
 		 * for this LED. Hardcode it here. */
 		*activelow = false;
@@ -250,7 +250,11 @@ static void b43_led_get_sprominfo(struct b43_wldev *dev,
 			return;
 		}
 	} else {
-		*behaviour = sprom[led_index] & B43_LED_BEHAVIOUR;
+		/* keep LED disabled if no mapping is defined */
+		if (sprom[led_index] == 0xff)
+			*behaviour = B43_LED_OFF;
+		else
+			*behaviour = sprom[led_index] & B43_LED_BEHAVIOUR;
 		*activelow = !!(sprom[led_index] & B43_LED_ACTIVELOW);
 	}
 }
diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c
index 4ee5c5853f9f..6e5d9095b195 100644
--- a/drivers/net/wireless/broadcom/b43/main.c
+++ b/drivers/net/wireless/broadcom/b43/main.c
@@ -3180,7 +3180,6 @@ static void b43_rate_memory_write(struct b43_wldev *dev, u16 rate, int is_ofdm)
 static void b43_rate_memory_init(struct b43_wldev *dev)
 {
 	switch (dev->phy.type) {
-	case B43_PHYTYPE_A:
 	case B43_PHYTYPE_G:
 	case B43_PHYTYPE_N:
 	case B43_PHYTYPE_LP:
@@ -3194,8 +3193,6 @@ static void b43_rate_memory_init(struct b43_wldev *dev)
 		b43_rate_memory_write(dev, B43_OFDM_RATE_36MB, 1);
 		b43_rate_memory_write(dev, B43_OFDM_RATE_48MB, 1);
 		b43_rate_memory_write(dev, B43_OFDM_RATE_54MB, 1);
-		if (dev->phy.type == B43_PHYTYPE_A)
-			break;
 		/* fallthrough */
 	case B43_PHYTYPE_B:
 		b43_rate_memory_write(dev, B43_CCK_RATE_1MB, 0);
@@ -4604,14 +4601,6 @@ static int b43_phy_versioning(struct b43_wldev *dev)
 	if (radio_manuf != 0x17F /* Broadcom */)
 		unsupported = 1;
 	switch (phy_type) {
-	case B43_PHYTYPE_A:
-		if (radio_id != 0x2060)
-			unsupported = 1;
-		if (radio_rev != 1)
-			unsupported = 1;
-		if (radio_manuf != 0x17F)
-			unsupported = 1;
-		break;
 	case B43_PHYTYPE_B:
 		if ((radio_id & 0xFFF0) != 0x2050)
 			unsupported = 1;
@@ -4766,10 +4755,7 @@ static void b43_set_synth_pu_delay(struct b43_wldev *dev, bool idle)
 	u16 pu_delay;
 
 	/* The time value is in microseconds. */
-	if (dev->phy.type == B43_PHYTYPE_A)
-		pu_delay = 3700;
-	else
-		pu_delay = 1050;
+	pu_delay = 1050;
 	if (b43_is_mode(dev->wl, NL80211_IFTYPE_ADHOC) || idle)
 		pu_delay = 500;
 	if ((dev->phy.radio_ver == 0x2050) && (dev->phy.radio_rev == 8))
@@ -4784,14 +4770,10 @@ static void b43_set_pretbtt(struct b43_wldev *dev)
 	u16 pretbtt;
 
 	/* The time value is in microseconds. */
-	if (b43_is_mode(dev->wl, NL80211_IFTYPE_ADHOC)) {
+	if (b43_is_mode(dev->wl, NL80211_IFTYPE_ADHOC))
 		pretbtt = 2;
-	} else {
-		if (dev->phy.type == B43_PHYTYPE_A)
-			pretbtt = 120;
-		else
-			pretbtt = 250;
-	}
+	else
+		pretbtt = 250;
 	b43_shm_write16(dev, B43_SHM_SHARED, B43_SHM_SH_PRETBTT, pretbtt);
 	b43_write16(dev, B43_MMIO_TSF_CFP_PRETBTT, pretbtt);
 }
@@ -5380,10 +5362,6 @@ static void b43_supported_bands(struct b43_wldev *dev, bool *have_2ghz_phy,
 
 	/* As a fallback, try to guess using PHY type */
 	switch (dev->phy.type) {
-	case B43_PHYTYPE_A:
-		*have_2ghz_phy = false;
-		*have_5ghz_phy = true;
-		return;
 	case B43_PHYTYPE_G:
 	case B43_PHYTYPE_N:
 	case B43_PHYTYPE_LP:
@@ -5455,7 +5433,6 @@ static int b43_wireless_core_attach(struct b43_wldev *dev)
 	/* We don't support 5 GHz on some PHYs yet */
 	if (have_5ghz_phy) {
 		switch (dev->phy.type) {
-		case B43_PHYTYPE_A:
 		case B43_PHYTYPE_G:
 		case B43_PHYTYPE_LP:
 		case B43_PHYTYPE_HT:
diff --git a/drivers/net/wireless/broadcom/b43/phy_a.c b/drivers/net/wireless/broadcom/b43/phy_a.c
deleted file mode 100644
index 99c036f5ecb7..000000000000
--- a/drivers/net/wireless/broadcom/b43/phy_a.c
+++ /dev/null
@@ -1,595 +0,0 @@
-/*
-
-  Broadcom B43 wireless driver
-  IEEE 802.11a PHY driver
-
-  Copyright (c) 2005 Martin Langer <[email protected]>,
-  Copyright (c) 2005-2007 Stefano Brivio <[email protected]>
-  Copyright (c) 2005-2008 Michael Buesch <[email protected]>
-  Copyright (c) 2005, 2006 Danny van Dyk <[email protected]>
-  Copyright (c) 2005, 2006 Andreas Jaggi <[email protected]>
-
-  This program is free software; you can redistribute it and/or modify
-  it under the terms of the GNU General Public License as published by
-  the Free Software Foundation; either version 2 of the License, or
-  (at your option) any later version.
-
-  This program is distributed in the hope that it will be useful,
-  but WITHOUT ANY WARRANTY; without even the implied warranty of
-  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-  GNU General Public License for more details.
-
-  You should have received a copy of the GNU General Public License
-  along with this program; see the file COPYING.  If not, write to
-  the Free Software Foundation, Inc., 51 Franklin Steet, Fifth Floor,
-  Boston, MA 02110-1301, USA.
-
-*/
-
-#include <linux/slab.h>
-
-#include "b43.h"
-#include "phy_a.h"
-#include "phy_common.h"
-#include "wa.h"
-#include "tables.h"
-#include "main.h"
-
-
-/* Get the freq, as it has to be written to the device. */
-static inline u16 channel2freq_a(u8 channel)
-{
-	B43_WARN_ON(channel > 200);
-
-	return (5000 + 5 * channel);
-}
-
-static inline u16 freq_r3A_value(u16 frequency)
-{
-	u16 value;
-
-	if (frequency < 5091)
-		value = 0x0040;
-	else if (frequency < 5321)
-		value = 0x0000;
-	else if (frequency < 5806)
-		value = 0x0080;
-	else
-		value = 0x0040;
-
-	return value;
-}
-
-#if 0
-/* This function converts a TSSI value to dBm in Q5.2 */
-static s8 b43_aphy_estimate_power_out(struct b43_wldev *dev, s8 tssi)
-{
-	struct b43_phy *phy = &dev->phy;
-	struct b43_phy_a *aphy = phy->a;
-	s8 dbm = 0;
-	s32 tmp;
-
-	tmp = (aphy->tgt_idle_tssi - aphy->cur_idle_tssi + tssi);
-	tmp += 0x80;
-	tmp = clamp_val(tmp, 0x00, 0xFF);
-	dbm = aphy->tssi2dbm[tmp];
-	//TODO: There's a FIXME on the specs
-
-	return dbm;
-}
-#endif
-
-static void b43_radio_set_tx_iq(struct b43_wldev *dev)
-{
-	static const u8 data_high[5] = { 0x00, 0x40, 0x80, 0x90, 0xD0 };
-	static const u8 data_low[5] = { 0x00, 0x01, 0x05, 0x06, 0x0A };
-	u16 tmp = b43_radio_read16(dev, 0x001E);
-	int i, j;
-
-	for (i = 0; i < 5; i++) {
-		for (j = 0; j < 5; j++) {
-			if (tmp == (data_high[i] << 4 | data_low[j])) {
-				b43_phy_write(dev, 0x0069,
-					      (i - j) << 8 | 0x00C0);
-				return;
-			}
-		}
-	}
-}
-
-static void aphy_channel_switch(struct b43_wldev *dev, unsigned int channel)
-{
-	u16 freq, r8, tmp;
-
-	freq = channel2freq_a(channel);
-
-	r8 = b43_radio_read16(dev, 0x0008);
-	b43_write16(dev, 0x03F0, freq);
-	b43_radio_write16(dev, 0x0008, r8);
-
-	//TODO: write max channel TX power? to Radio 0x2D
-	tmp = b43_radio_read16(dev, 0x002E);
-	tmp &= 0x0080;
-	//TODO: OR tmp with the Power out estimation for this channel?
-	b43_radio_write16(dev, 0x002E, tmp);
-
-	if (freq >= 4920 && freq <= 5500) {
-		/*
-		 * r8 = (((freq * 15 * 0xE1FC780F) >> 32) / 29) & 0x0F;
-		 *    = (freq * 0.025862069
-		 */
-		r8 = 3 * freq / 116;	/* is equal to r8 = freq * 0.025862 */
-	}
-	b43_radio_write16(dev, 0x0007, (r8 << 4) | r8);
-	b43_radio_write16(dev, 0x0020, (r8 << 4) | r8);
-	b43_radio_write16(dev, 0x0021, (r8 << 4) | r8);
-	b43_radio_maskset(dev, 0x0022, 0x000F, (r8 << 4));
-	b43_radio_write16(dev, 0x002A, (r8 << 4));
-	b43_radio_write16(dev, 0x002B, (r8 << 4));
-	b43_radio_maskset(dev, 0x0008, 0x00F0, (r8 << 4));
-	b43_radio_maskset(dev, 0x0029, 0xFF0F, 0x00B0);
-	b43_radio_write16(dev, 0x0035, 0x00AA);
-	b43_radio_write16(dev, 0x0036, 0x0085);
-	b43_radio_maskset(dev, 0x003A, 0xFF20, freq_r3A_value(freq));
-	b43_radio_mask(dev, 0x003D, 0x00FF);
-	b43_radio_maskset(dev, 0x0081, 0xFF7F, 0x0080);
-	b43_radio_mask(dev, 0x0035, 0xFFEF);
-	b43_radio_maskset(dev, 0x0035, 0xFFEF, 0x0010);
-	b43_radio_set_tx_iq(dev);
-	//TODO: TSSI2dbm workaround
-//FIXME	b43_phy_xmitpower(dev);
-}
-
-static void b43_radio_init2060(struct b43_wldev *dev)
-{
-	b43_radio_write16(dev, 0x0004, 0x00C0);
-	b43_radio_write16(dev, 0x0005, 0x0008);
-	b43_radio_write16(dev, 0x0009, 0x0040);
-	b43_radio_write16(dev, 0x0005, 0x00AA);
-	b43_radio_write16(dev, 0x0032, 0x008F);
-	b43_radio_write16(dev, 0x0006, 0x008F);
-	b43_radio_write16(dev, 0x0034, 0x008F);
-	b43_radio_write16(dev, 0x002C, 0x0007);
-	b43_radio_write16(dev, 0x0082, 0x0080);
-	b43_radio_write16(dev, 0x0080, 0x0000);
-	b43_radio_write16(dev, 0x003F, 0x00DA);
-	b43_radio_mask(dev, 0x0005, ~0x0008);
-	b43_radio_mask(dev, 0x0081, ~0x0010);
-	b43_radio_mask(dev, 0x0081, ~0x0020);
-	b43_radio_mask(dev, 0x0081, ~0x0020);
-	msleep(1);		/* delay 400usec */
-
-	b43_radio_maskset(dev, 0x0081, ~0x0020, 0x0010);
-	msleep(1);		/* delay 400usec */
-
-	b43_radio_maskset(dev, 0x0005, ~0x0008, 0x0008);
-	b43_radio_mask(dev, 0x0085, ~0x0010);
-	b43_radio_mask(dev, 0x0005, ~0x0008);
-	b43_radio_mask(dev, 0x0081, ~0x0040);
-	b43_radio_maskset(dev, 0x0081, ~0x0040, 0x0040);
-	b43_radio_write16(dev, 0x0005,
-			  (b43_radio_read16(dev, 0x0081) & ~0x0008) | 0x0008);
-	b43_phy_write(dev, 0x0063, 0xDDC6);
-	b43_phy_write(dev, 0x0069, 0x07BE);
-	b43_phy_write(dev, 0x006A, 0x0000);
-
-	aphy_channel_switch(dev, dev->phy.ops->get_default_chan(dev));
-
-	msleep(1);
-}
-
-static void b43_phy_rssiagc(struct b43_wldev *dev, u8 enable)
-{
-	int i;
-
-	if (dev->phy.rev < 3) {
-		if (enable)
-			for (i = 0; i < B43_TAB_RSSIAGC1_SIZE; i++) {
-				b43_ofdmtab_write16(dev,
-					B43_OFDMTAB_LNAHPFGAIN1, i, 0xFFF8);
-				b43_ofdmtab_write16(dev,
-					B43_OFDMTAB_WRSSI, i, 0xFFF8);
-			}
-		else
-			for (i = 0; i < B43_TAB_RSSIAGC1_SIZE; i++) {
-				b43_ofdmtab_write16(dev,
-					B43_OFDMTAB_LNAHPFGAIN1, i, b43_tab_rssiagc1[i]);
-				b43_ofdmtab_write16(dev,
-					B43_OFDMTAB_WRSSI, i, b43_tab_rssiagc1[i]);
-			}
-	} else {
-		if (enable)
-			for (i = 0; i < B43_TAB_RSSIAGC1_SIZE; i++)
-				b43_ofdmtab_write16(dev,
-					B43_OFDMTAB_WRSSI, i, 0x0820);
-		else
-			for (i = 0; i < B43_TAB_RSSIAGC2_SIZE; i++)
-				b43_ofdmtab_write16(dev,
-					B43_OFDMTAB_WRSSI, i, b43_tab_rssiagc2[i]);
-	}
-}
-
-static void b43_phy_ww(struct b43_wldev *dev)
-{
-	u16 b, curr_s, best_s = 0xFFFF;
-	int i;
-
-	b43_phy_mask(dev, B43_PHY_CRS0, ~B43_PHY_CRS0_EN);
-	b43_phy_set(dev, B43_PHY_OFDM(0x1B), 0x1000);
-	b43_phy_maskset(dev, B43_PHY_OFDM(0x82), 0xF0FF, 0x0300);
-	b43_radio_set(dev, 0x0009, 0x0080);
-	b43_radio_maskset(dev, 0x0012, 0xFFFC, 0x0002);
-	b43_wa_initgains(dev);
-	b43_phy_write(dev, B43_PHY_OFDM(0xBA), 0x3ED5);
-	b = b43_phy_read(dev, B43_PHY_PWRDOWN);
-	b43_phy_write(dev, B43_PHY_PWRDOWN, (b & 0xFFF8) | 0x0005);
-	b43_radio_set(dev, 0x0004, 0x0004);
-	for (i = 0x10; i <= 0x20; i++) {
-		b43_radio_write16(dev, 0x0013, i);
-		curr_s = b43_phy_read(dev, B43_PHY_OTABLEQ) & 0x00FF;
-		if (!curr_s) {
-			best_s = 0x0000;
-			break;
-		} else if (curr_s >= 0x0080)
-			curr_s = 0x0100 - curr_s;
-		if (curr_s < best_s)
-			best_s = curr_s;
-	}
-	b43_phy_write(dev, B43_PHY_PWRDOWN, b);
-	b43_radio_mask(dev, 0x0004, 0xFFFB);
-	b43_radio_write16(dev, 0x0013, best_s);
-	b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC1_R1, 0, 0xFFEC);
-	b43_phy_write(dev, B43_PHY_OFDM(0xB7), 0x1E80);
-	b43_phy_write(dev, B43_PHY_OFDM(0xB6), 0x1C00);
-	b43_phy_write(dev, B43_PHY_OFDM(0xB5), 0x0EC0);
-	b43_phy_write(dev, B43_PHY_OFDM(0xB2), 0x00C0);
-	b43_phy_write(dev, B43_PHY_OFDM(0xB9), 0x1FFF);
-	b43_phy_maskset(dev, B43_PHY_OFDM(0xBB), 0xF000, 0x0053);
-	b43_phy_maskset(dev, B43_PHY_OFDM61, 0xFE1F, 0x0120);
-	b43_phy_maskset(dev, B43_PHY_OFDM(0x13), 0x0FFF, 0x3000);
-	b43_phy_maskset(dev, B43_PHY_OFDM(0x14), 0x0FFF, 0x3000);
-	b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC1, 6, 0x0017);
-	for (i = 0; i < 6; i++)
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC1, i, 0x000F);
-	b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC1, 0x0D, 0x000E);
-	b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC1, 0x0E, 0x0011);
-	b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC1, 0x0F, 0x0013);
-	b43_phy_write(dev, B43_PHY_OFDM(0x33), 0x5030);
-	b43_phy_set(dev, B43_PHY_CRS0, B43_PHY_CRS0_EN);
-}
-
-static void hardware_pctl_init_aphy(struct b43_wldev *dev)
-{
-	//TODO
-}
-
-void b43_phy_inita(struct b43_wldev *dev)
-{
-	struct b43_phy *phy = &dev->phy;
-
-	/* This lowlevel A-PHY init is also called from G-PHY init.
-	 * So we must not access phy->a, if called from G-PHY code.
-	 */
-	B43_WARN_ON((phy->type != B43_PHYTYPE_A) &&
-		    (phy->type != B43_PHYTYPE_G));
-
-	might_sleep();
-
-	if (phy->rev >= 6) {
-		if (phy->type == B43_PHYTYPE_A)
-			b43_phy_mask(dev, B43_PHY_OFDM(0x1B), ~0x1000);
-		if (b43_phy_read(dev, B43_PHY_ENCORE) & B43_PHY_ENCORE_EN)
-			b43_phy_set(dev, B43_PHY_ENCORE, 0x0010);
-		else
-			b43_phy_mask(dev, B43_PHY_ENCORE, ~0x1010);
-	}
-
-	b43_wa_all(dev);
-
-	if (phy->type == B43_PHYTYPE_A) {
-		if (phy->gmode && (phy->rev < 3))
-			b43_phy_set(dev, 0x0034, 0x0001);
-		b43_phy_rssiagc(dev, 0);
-
-		b43_phy_set(dev, B43_PHY_CRS0, B43_PHY_CRS0_EN);
-
-		b43_radio_init2060(dev);
-
-		if ((dev->dev->board_vendor == SSB_BOARDVENDOR_BCM) &&
-		    ((dev->dev->board_type == SSB_BOARD_BU4306) ||
-		     (dev->dev->board_type == SSB_BOARD_BU4309))) {
-			; //TODO: A PHY LO
-		}
-
-		if (phy->rev >= 3)
-			b43_phy_ww(dev);
-
-		hardware_pctl_init_aphy(dev);
-
-		//TODO: radar detection
-	}
-
-	if ((phy->type == B43_PHYTYPE_G) &&
-	    (dev->dev->bus_sprom->boardflags_lo & B43_BFL_PACTRL)) {
-		b43_phy_maskset(dev, B43_PHY_OFDM(0x6E), 0xE000, 0x3CF);
-	}
-}
-
-/* Initialise the TSSI->dBm lookup table */
-static int b43_aphy_init_tssi2dbm_table(struct b43_wldev *dev)
-{
-	struct b43_phy *phy = &dev->phy;
-	struct b43_phy_a *aphy = phy->a;
-	s16 pab0, pab1, pab2;
-
-	pab0 = (s16) (dev->dev->bus_sprom->pa1b0);
-	pab1 = (s16) (dev->dev->bus_sprom->pa1b1);
-	pab2 = (s16) (dev->dev->bus_sprom->pa1b2);
-
-	if (pab0 != 0 && pab1 != 0 && pab2 != 0 &&
-	    pab0 != -1 && pab1 != -1 && pab2 != -1) {
-		/* The pabX values are set in SPROM. Use them. */
-		if ((s8) dev->dev->bus_sprom->itssi_a != 0 &&
-		    (s8) dev->dev->bus_sprom->itssi_a != -1)
-			aphy->tgt_idle_tssi =
-			    (s8) (dev->dev->bus_sprom->itssi_a);
-		else
-			aphy->tgt_idle_tssi = 62;
-		aphy->tssi2dbm = b43_generate_dyn_tssi2dbm_tab(dev, pab0,
-							       pab1, pab2);
-		if (!aphy->tssi2dbm)
-			return -ENOMEM;
-	} else {
-		/* pabX values not set in SPROM,
-		 * but APHY needs a generated table. */
-		aphy->tssi2dbm = NULL;
-		b43err(dev->wl, "Could not generate tssi2dBm "
-		       "table (wrong SPROM info)!\n");
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
-static int b43_aphy_op_allocate(struct b43_wldev *dev)
-{
-	struct b43_phy_a *aphy;
-	int err;
-
-	aphy = kzalloc(sizeof(*aphy), GFP_KERNEL);
-	if (!aphy)
-		return -ENOMEM;
-	dev->phy.a = aphy;
-
-	err = b43_aphy_init_tssi2dbm_table(dev);
-	if (err)
-		goto err_free_aphy;
-
-	return 0;
-
-err_free_aphy:
-	kfree(aphy);
-	dev->phy.a = NULL;
-
-	return err;
-}
-
-static void b43_aphy_op_prepare_structs(struct b43_wldev *dev)
-{
-	struct b43_phy *phy = &dev->phy;
-	struct b43_phy_a *aphy = phy->a;
-	const void *tssi2dbm;
-	int tgt_idle_tssi;
-
-	/* tssi2dbm table is constant, so it is initialized at alloc time.
-	 * Save a copy of the pointer. */
-	tssi2dbm = aphy->tssi2dbm;
-	tgt_idle_tssi = aphy->tgt_idle_tssi;
-
-	/* Zero out the whole PHY structure. */
-	memset(aphy, 0, sizeof(*aphy));
-
-	aphy->tssi2dbm = tssi2dbm;
-	aphy->tgt_idle_tssi = tgt_idle_tssi;
-
-	//TODO init struct b43_phy_a
-
-}
-
-static void b43_aphy_op_free(struct b43_wldev *dev)
-{
-	struct b43_phy *phy = &dev->phy;
-	struct b43_phy_a *aphy = phy->a;
-
-	kfree(aphy->tssi2dbm);
-	aphy->tssi2dbm = NULL;
-
-	kfree(aphy);
-	dev->phy.a = NULL;
-}
-
-static int b43_aphy_op_init(struct b43_wldev *dev)
-{
-	b43_phy_inita(dev);
-
-	return 0;
-}
-
-static inline u16 adjust_phyreg(struct b43_wldev *dev, u16 offset)
-{
-	/* OFDM registers are base-registers for the A-PHY. */
-	if ((offset & B43_PHYROUTE) == B43_PHYROUTE_OFDM_GPHY) {
-		offset &= ~B43_PHYROUTE;
-		offset |= B43_PHYROUTE_BASE;
-	}
-
-#if B43_DEBUG
-	if ((offset & B43_PHYROUTE) == B43_PHYROUTE_EXT_GPHY) {
-		/* Ext-G registers are only available on G-PHYs */
-		b43err(dev->wl, "Invalid EXT-G PHY access at "
-		       "0x%04X on A-PHY\n", offset);
-		dump_stack();
-	}
-	if ((offset & B43_PHYROUTE) == B43_PHYROUTE_N_BMODE) {
-		/* N-BMODE registers are only available on N-PHYs */
-		b43err(dev->wl, "Invalid N-BMODE PHY access at "
-		       "0x%04X on A-PHY\n", offset);
-		dump_stack();
-	}
-#endif /* B43_DEBUG */
-
-	return offset;
-}
-
-static u16 b43_aphy_op_read(struct b43_wldev *dev, u16 reg)
-{
-	reg = adjust_phyreg(dev, reg);
-	b43_write16f(dev, B43_MMIO_PHY_CONTROL, reg);
-	return b43_read16(dev, B43_MMIO_PHY_DATA);
-}
-
-static void b43_aphy_op_write(struct b43_wldev *dev, u16 reg, u16 value)
-{
-	reg = adjust_phyreg(dev, reg);
-	b43_write16f(dev, B43_MMIO_PHY_CONTROL, reg);
-	b43_write16(dev, B43_MMIO_PHY_DATA, value);
-}
-
-static u16 b43_aphy_op_radio_read(struct b43_wldev *dev, u16 reg)
-{
-	/* Register 1 is a 32-bit register. */
-	B43_WARN_ON(reg == 1);
-	/* A-PHY needs 0x40 for read access */
-	reg |= 0x40;
-
-	b43_write16(dev, B43_MMIO_RADIO_CONTROL, reg);
-	return b43_read16(dev, B43_MMIO_RADIO_DATA_LOW);
-}
-
-static void b43_aphy_op_radio_write(struct b43_wldev *dev, u16 reg, u16 value)
-{
-	/* Register 1 is a 32-bit register. */
-	B43_WARN_ON(reg == 1);
-
-	b43_write16(dev, B43_MMIO_RADIO_CONTROL, reg);
-	b43_write16(dev, B43_MMIO_RADIO_DATA_LOW, value);
-}
-
-static bool b43_aphy_op_supports_hwpctl(struct b43_wldev *dev)
-{
-	return (dev->phy.rev >= 5);
-}
-
-static void b43_aphy_op_software_rfkill(struct b43_wldev *dev,
-					bool blocked)
-{
-	struct b43_phy *phy = &dev->phy;
-
-	if (!blocked) {
-		if (phy->radio_on)
-			return;
-		b43_radio_write16(dev, 0x0004, 0x00C0);
-		b43_radio_write16(dev, 0x0005, 0x0008);
-		b43_phy_mask(dev, 0x0010, 0xFFF7);
-		b43_phy_mask(dev, 0x0011, 0xFFF7);
-		b43_radio_init2060(dev);
-	} else {
-		b43_radio_write16(dev, 0x0004, 0x00FF);
-		b43_radio_write16(dev, 0x0005, 0x00FB);
-		b43_phy_set(dev, 0x0010, 0x0008);
-		b43_phy_set(dev, 0x0011, 0x0008);
-	}
-}
-
-static int b43_aphy_op_switch_channel(struct b43_wldev *dev,
-				      unsigned int new_channel)
-{
-	if (new_channel > 200)
-		return -EINVAL;
-	aphy_channel_switch(dev, new_channel);
-
-	return 0;
-}
-
-static unsigned int b43_aphy_op_get_default_chan(struct b43_wldev *dev)
-{
-	return 36; /* Default to channel 36 */
-}
-
-static void b43_aphy_op_set_rx_antenna(struct b43_wldev *dev, int antenna)
-{//TODO
-	struct b43_phy *phy = &dev->phy;
-	u16 tmp;
-	int autodiv = 0;
-
-	if (antenna == B43_ANTENNA_AUTO0 || antenna == B43_ANTENNA_AUTO1)
-		autodiv = 1;
-
-	b43_hf_write(dev, b43_hf_read(dev) & ~B43_HF_ANTDIVHELP);
-
-	b43_phy_maskset(dev, B43_PHY_BBANDCFG, ~B43_PHY_BBANDCFG_RXANT,
-			(autodiv ? B43_ANTENNA_AUTO1 : antenna) <<
-			B43_PHY_BBANDCFG_RXANT_SHIFT);
-
-	if (autodiv) {
-		tmp = b43_phy_read(dev, B43_PHY_ANTDWELL);
-		if (antenna == B43_ANTENNA_AUTO1)
-			tmp &= ~B43_PHY_ANTDWELL_AUTODIV1;
-		else
-			tmp |= B43_PHY_ANTDWELL_AUTODIV1;
-		b43_phy_write(dev, B43_PHY_ANTDWELL, tmp);
-	}
-	if (phy->rev < 3)
-		b43_phy_maskset(dev, B43_PHY_ANTDWELL, 0xFF00, 0x24);
-	else {
-		b43_phy_set(dev, B43_PHY_OFDM61, 0x10);
-		if (phy->rev == 3) {
-			b43_phy_write(dev, B43_PHY_CLIPPWRDOWNT, 0x1D);
-			b43_phy_write(dev, B43_PHY_ADIVRELATED, 8);
-		} else {
-			b43_phy_write(dev, B43_PHY_CLIPPWRDOWNT, 0x3A);
-			b43_phy_maskset(dev, B43_PHY_ADIVRELATED, 0xFF00, 8);
-		}
-	}
-
-	b43_hf_write(dev, b43_hf_read(dev) | B43_HF_ANTDIVHELP);
-}
-
-static void b43_aphy_op_adjust_txpower(struct b43_wldev *dev)
-{//TODO
-}
-
-static enum b43_txpwr_result b43_aphy_op_recalc_txpower(struct b43_wldev *dev,
-							bool ignore_tssi)
-{//TODO
-	return B43_TXPWR_RES_DONE;
-}
-
-static void b43_aphy_op_pwork_15sec(struct b43_wldev *dev)
-{//TODO
-}
-
-static void b43_aphy_op_pwork_60sec(struct b43_wldev *dev)
-{//TODO
-}
-
-static const struct b43_phy_operations b43_phyops_a = {
-	.allocate		= b43_aphy_op_allocate,
-	.free			= b43_aphy_op_free,
-	.prepare_structs	= b43_aphy_op_prepare_structs,
-	.init			= b43_aphy_op_init,
-	.phy_read		= b43_aphy_op_read,
-	.phy_write		= b43_aphy_op_write,
-	.radio_read		= b43_aphy_op_radio_read,
-	.radio_write		= b43_aphy_op_radio_write,
-	.supports_hwpctl	= b43_aphy_op_supports_hwpctl,
-	.software_rfkill	= b43_aphy_op_software_rfkill,
-	.switch_analog		= b43_phyop_switch_analog_generic,
-	.switch_channel		= b43_aphy_op_switch_channel,
-	.get_default_chan	= b43_aphy_op_get_default_chan,
-	.set_rx_antenna		= b43_aphy_op_set_rx_antenna,
-	.recalc_txpower		= b43_aphy_op_recalc_txpower,
-	.adjust_txpower		= b43_aphy_op_adjust_txpower,
-	.pwork_15sec		= b43_aphy_op_pwork_15sec,
-	.pwork_60sec		= b43_aphy_op_pwork_60sec,
-};
diff --git a/drivers/net/wireless/broadcom/b43/phy_a.h b/drivers/net/wireless/broadcom/b43/phy_a.h
index f7d0d929a374..0a92d01c21f9 100644
--- a/drivers/net/wireless/broadcom/b43/phy_a.h
+++ b/drivers/net/wireless/broadcom/b43/phy_a.h
@@ -101,26 +101,4 @@ u32 b43_ofdmtab_read32(struct b43_wldev *dev, u16 table, u16 offset);
 void b43_ofdmtab_write32(struct b43_wldev *dev, u16 table,
 			 u16 offset, u32 value);
 
-
-struct b43_phy_a {
-	/* Pointer to the table used to convert a
-	 * TSSI value to dBm-Q5.2 */
-	const s8 *tssi2dbm;
-	/* Target idle TSSI */
-	int tgt_idle_tssi;
-	/* Current idle TSSI */
-	int cur_idle_tssi;//FIXME value currently not set
-
-	/* A-PHY TX Power control value. */
-	u16 txpwr_offset;
-
-	//TODO lots of missing stuff
-};
-
-/**
- * b43_phy_inita - Lowlevel A-PHY init routine.
- * This is _only_ used by the G-PHY code.
- */
-void b43_phy_inita(struct b43_wldev *dev);
-
 #endif /* LINUX_B43_PHY_A_H_ */
diff --git a/drivers/net/wireless/broadcom/b43/phy_common.h b/drivers/net/wireless/broadcom/b43/phy_common.h
index 78d86526799e..ced054a9850c 100644
--- a/drivers/net/wireless/broadcom/b43/phy_common.h
+++ b/drivers/net/wireless/broadcom/b43/phy_common.h
@@ -190,7 +190,6 @@ struct b43_phy_operations {
 	void (*pwork_60sec)(struct b43_wldev *dev);
 };
 
-struct b43_phy_a;
 struct b43_phy_g;
 struct b43_phy_n;
 struct b43_phy_lp;
@@ -210,8 +209,6 @@ struct b43_phy {
 #else
 	union {
 #endif
-		/* A-PHY specific information */
-		struct b43_phy_a *a;
 		/* G-PHY specific information */
 		struct b43_phy_g *g;
 		/* N-PHY specific information */
diff --git a/drivers/net/wireless/broadcom/b43/phy_g.c b/drivers/net/wireless/broadcom/b43/phy_g.c
index 462310e6e88f..822dcaa8ace6 100644
--- a/drivers/net/wireless/broadcom/b43/phy_g.c
+++ b/drivers/net/wireless/broadcom/b43/phy_g.c
@@ -31,6 +31,7 @@
 #include "phy_common.h"
 #include "lo.h"
 #include "main.h"
+#include "wa.h"
 
 #include <linux/bitrev.h>
 #include <linux/slab.h>
@@ -1987,6 +1988,25 @@ static void b43_phy_init_pctl(struct b43_wldev *dev)
 	b43_shm_clear_tssi(dev);
 }
 
+static void b43_phy_inita(struct b43_wldev *dev)
+{
+	struct b43_phy *phy = &dev->phy;
+
+	might_sleep();
+
+	if (phy->rev >= 6) {
+		if (b43_phy_read(dev, B43_PHY_ENCORE) & B43_PHY_ENCORE_EN)
+			b43_phy_set(dev, B43_PHY_ENCORE, 0x0010);
+		else
+			b43_phy_mask(dev, B43_PHY_ENCORE, ~0x1010);
+	}
+
+	b43_wa_all(dev);
+
+	if (dev->dev->bus_sprom->boardflags_lo & B43_BFL_PACTRL)
+		b43_phy_maskset(dev, B43_PHY_OFDM(0x6E), 0xE000, 0x3CF);
+}
+
 static void b43_phy_initg(struct b43_wldev *dev)
 {
 	struct b43_phy *phy = &dev->phy;
@@ -2150,11 +2170,6 @@ static void default_radio_attenuation(struct b43_wldev *dev,
 		}
 	}
 
-	if (phy->type == B43_PHYTYPE_A) {
-		rf->att = 0x60;
-		return;
-	}
-
 	switch (phy->radio_ver) {
 	case 0x2053:
 		switch (phy->radio_rev) {
diff --git a/drivers/net/wireless/broadcom/b43/wa.c b/drivers/net/wireless/broadcom/b43/wa.c
index c218c08fb2f5..0e96c08d1e17 100644
--- a/drivers/net/wireless/broadcom/b43/wa.c
+++ b/drivers/net/wireless/broadcom/b43/wa.c
@@ -30,33 +30,6 @@
 #include "phy_common.h"
 #include "wa.h"
 
-static void b43_wa_papd(struct b43_wldev *dev)
-{
-	u16 backup;
-
-	backup = b43_ofdmtab_read16(dev, B43_OFDMTAB_PWRDYN2, 0);
-	b43_ofdmtab_write16(dev, B43_OFDMTAB_PWRDYN2, 0, 7);
-	b43_ofdmtab_write16(dev, B43_OFDMTAB_UNKNOWN_APHY, 0, 0);
-	b43_dummy_transmission(dev, true, true);
-	b43_ofdmtab_write16(dev, B43_OFDMTAB_PWRDYN2, 0, backup);
-}
-
-static void b43_wa_auxclipthr(struct b43_wldev *dev)
-{
-	b43_phy_write(dev, B43_PHY_OFDM(0x8E), 0x3800);
-}
-
-static void b43_wa_afcdac(struct b43_wldev *dev)
-{
-	b43_phy_write(dev, 0x0035, 0x03FF);
-	b43_phy_write(dev, 0x0036, 0x0400);
-}
-
-static void b43_wa_txdc_offset(struct b43_wldev *dev)
-{
-	b43_ofdmtab_write16(dev, B43_OFDMTAB_DC, 0, 0x0051);
-}
-
 void b43_wa_initgains(struct b43_wldev *dev)
 {
 	struct b43_phy *phy = &dev->phy;
@@ -81,41 +54,6 @@ void b43_wa_initgains(struct b43_wldev *dev)
 		b43_phy_write(dev, 0x00BA, 0x3ED5);
 }
 
-static void b43_wa_divider(struct b43_wldev *dev)
-{
-	b43_phy_mask(dev, 0x002B, ~0x0100);
-	b43_phy_write(dev, 0x008E, 0x58C1);
-}
-
-static void b43_wa_gt(struct b43_wldev *dev) /* Gain table. */
-{
-	if (dev->phy.rev <= 2) {
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN2, 0, 15);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN2, 1, 31);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN2, 2, 42);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN2, 3, 48);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN2, 4, 58);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 0, 19);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 1, 19);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 2, 19);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 3, 19);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 4, 21);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 5, 21);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 6, 25);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN1, 0, 3);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN1, 1, 3);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN1, 2, 7);
-	} else {
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 0, 19);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 1, 19);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 2, 19);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 3, 19);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 4, 21);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 5, 21);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_GAIN0, 6, 25);
-	}
-}
-
 static void b43_wa_rssi_lt(struct b43_wldev *dev) /* RSSI lookup table */
 {
 	int i;
@@ -133,15 +71,11 @@ static void b43_wa_rssi_lt(struct b43_wldev *dev) /* RSSI lookup table */
 
 static void b43_wa_analog(struct b43_wldev *dev)
 {
-	struct b43_phy *phy = &dev->phy;
 	u16 ofdmrev;
 
 	ofdmrev = b43_phy_read(dev, B43_PHY_VERSION_OFDM) & B43_PHYVER_VERSION;
 	if (ofdmrev > 2) {
-		if (phy->type == B43_PHYTYPE_A)
-			b43_phy_write(dev, B43_PHY_PWRDOWN, 0x1808);
-		else
-			b43_phy_write(dev, B43_PHY_PWRDOWN, 0x1000);
+		b43_phy_write(dev, B43_PHY_PWRDOWN, 0x1000);
 	} else {
 		b43_ofdmtab_write16(dev, B43_OFDMTAB_DAC, 3, 0x1044);
 		b43_ofdmtab_write16(dev, B43_OFDMTAB_DAC, 4, 0x7201);
@@ -149,26 +83,13 @@ static void b43_wa_analog(struct b43_wldev *dev)
 	}
 }
 
-static void b43_wa_dac(struct b43_wldev *dev)
-{
-	if (dev->phy.analog == 1)
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_DAC, 1,
-			(b43_ofdmtab_read16(dev, B43_OFDMTAB_DAC, 1) & ~0x0034) | 0x0008);
-	else
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_DAC, 1,
-			(b43_ofdmtab_read16(dev, B43_OFDMTAB_DAC, 1) & ~0x0078) | 0x0010);
-}
-
 static void b43_wa_fft(struct b43_wldev *dev) /* Fine frequency table */
 {
 	int i;
 
-	if (dev->phy.type == B43_PHYTYPE_A)
-		for (i = 0; i < B43_TAB_FINEFREQA_SIZE; i++)
-			b43_ofdmtab_write16(dev, B43_OFDMTAB_DACRFPABB, i, b43_tab_finefreqa[i]);
-	else
-		for (i = 0; i < B43_TAB_FINEFREQG_SIZE; i++)
-			b43_ofdmtab_write16(dev, B43_OFDMTAB_DACRFPABB, i, b43_tab_finefreqg[i]);
+	for (i = 0; i < B43_TAB_FINEFREQG_SIZE; i++)
+		b43_ofdmtab_write16(dev, B43_OFDMTAB_DACRFPABB, i,
+				    b43_tab_finefreqg[i]);
 }
 
 static void b43_wa_nft(struct b43_wldev *dev) /* Noise figure table */
@@ -176,21 +97,14 @@ static void b43_wa_nft(struct b43_wldev *dev) /* Noise figure table */
 	struct b43_phy *phy = &dev->phy;
 	int i;
 
-	if (phy->type == B43_PHYTYPE_A) {
-		if (phy->rev == 2)
-			for (i = 0; i < B43_TAB_NOISEA2_SIZE; i++)
-				b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC2, i, b43_tab_noisea2[i]);
-		else
-			for (i = 0; i < B43_TAB_NOISEA3_SIZE; i++)
-				b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC2, i, b43_tab_noisea3[i]);
-	} else {
-		if (phy->rev == 1)
-			for (i = 0; i < B43_TAB_NOISEG1_SIZE; i++)
-				b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC2, i, b43_tab_noiseg1[i]);
-		else
-			for (i = 0; i < B43_TAB_NOISEG2_SIZE; i++)
-				b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC2, i, b43_tab_noiseg2[i]);
-	}
+	if (phy->rev == 1)
+		for (i = 0; i < B43_TAB_NOISEG1_SIZE; i++)
+			b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC2, i,
+					    b43_tab_noiseg1[i]);
+	else
+		for (i = 0; i < B43_TAB_NOISEG2_SIZE; i++)
+			b43_ofdmtab_write16(dev, B43_OFDMTAB_AGC2, i,
+					    b43_tab_noiseg2[i]);
 }
 
 static void b43_wa_rt(struct b43_wldev *dev) /* Rotor table */
@@ -201,14 +115,6 @@ static void b43_wa_rt(struct b43_wldev *dev) /* Rotor table */
 		b43_ofdmtab_write32(dev, B43_OFDMTAB_ROTOR, i, b43_tab_rotor[i]);
 }
 
-static void b43_write_null_nst(struct b43_wldev *dev)
-{
-	int i;
-
-	for (i = 0; i < B43_TAB_NOISESCALE_SIZE; i++)
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_NOISESCALE, i, 0);
-}
-
 static void b43_write_nst(struct b43_wldev *dev, const u16 *nst)
 {
 	int i;
@@ -221,24 +127,13 @@ static void b43_wa_nst(struct b43_wldev *dev) /* Noise scale table */
 {
 	struct b43_phy *phy = &dev->phy;
 
-	if (phy->type == B43_PHYTYPE_A) {
-		if (phy->rev <= 1)
-			b43_write_null_nst(dev);
-		else if (phy->rev == 2)
-			b43_write_nst(dev, b43_tab_noisescalea2);
-		else if (phy->rev == 3)
-			b43_write_nst(dev, b43_tab_noisescalea3);
-		else
+	if (phy->rev >= 6) {
+		if (b43_phy_read(dev, B43_PHY_ENCORE) & B43_PHY_ENCORE_EN)
 			b43_write_nst(dev, b43_tab_noisescaleg3);
+		else
+			b43_write_nst(dev, b43_tab_noisescaleg2);
 	} else {
-		if (phy->rev >= 6) {
-			if (b43_phy_read(dev, B43_PHY_ENCORE) & B43_PHY_ENCORE_EN)
-				b43_write_nst(dev, b43_tab_noisescaleg3);
-			else
-				b43_write_nst(dev, b43_tab_noisescaleg2);
-		} else {
-			b43_write_nst(dev, b43_tab_noisescaleg1);
-		}
+		b43_write_nst(dev, b43_tab_noisescaleg1);
 	}
 }
 
@@ -251,41 +146,13 @@ static void b43_wa_art(struct b43_wldev *dev) /* ADV retard table */
 				i, b43_tab_retard[i]);
 }
 
-static void b43_wa_txlna_gain(struct b43_wldev *dev)
-{
-	b43_ofdmtab_write16(dev, B43_OFDMTAB_DC, 13, 0x0000);
-}
-
-static void b43_wa_crs_reset(struct b43_wldev *dev)
-{
-	b43_phy_write(dev, 0x002C, 0x0064);
-}
-
-static void b43_wa_2060txlna_gain(struct b43_wldev *dev)
-{
-	b43_hf_write(dev, b43_hf_read(dev) |
-			 B43_HF_2060W);
-}
-
-static void b43_wa_lms(struct b43_wldev *dev)
-{
-	b43_phy_maskset(dev, 0x0055, 0xFFC0, 0x0004);
-}
-
-static void b43_wa_mixedsignal(struct b43_wldev *dev)
-{
-	b43_ofdmtab_write16(dev, B43_OFDMTAB_DAC, 1, 3);
-}
-
 static void b43_wa_msst(struct b43_wldev *dev) /* Min sigma square table */
 {
 	struct b43_phy *phy = &dev->phy;
 	int i;
 	const u16 *tab;
 
-	if (phy->type == B43_PHYTYPE_A) {
-		tab = b43_tab_sigmasqr1;
-	} else if (phy->type == B43_PHYTYPE_G) {
+	if (phy->type == B43_PHYTYPE_G) {
 		tab = b43_tab_sigmasqr2;
 	} else {
 		B43_WARN_ON(1);
@@ -298,13 +165,6 @@ static void b43_wa_msst(struct b43_wldev *dev) /* Min sigma square table */
 	}
 }
 
-static void b43_wa_iqadc(struct b43_wldev *dev)
-{
-	if (dev->phy.analog == 4)
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_DAC, 0,
-			b43_ofdmtab_read16(dev, B43_OFDMTAB_DAC, 0) & ~0xF000);
-}
-
 static void b43_wa_crs_ed(struct b43_wldev *dev)
 {
 	struct b43_phy *phy = &dev->phy;
@@ -450,38 +310,6 @@ static void b43_wa_cpll_nonpilot(struct b43_wldev *dev)
 	b43_ofdmtab_write16(dev, B43_OFDMTAB_UNKNOWN_11, 1, 0);
 }
 
-static void b43_wa_rssi_adc(struct b43_wldev *dev)
-{
-	if (dev->phy.analog == 4)
-		b43_phy_write(dev, 0x00DC, 0x7454);
-}
-
-static void b43_wa_boards_a(struct b43_wldev *dev)
-{
-	if (dev->dev->board_vendor == SSB_BOARDVENDOR_BCM &&
-	    dev->dev->board_type == SSB_BOARD_BU4306 &&
-	    dev->dev->board_rev < 0x30) {
-		b43_phy_write(dev, 0x0010, 0xE000);
-		b43_phy_write(dev, 0x0013, 0x0140);
-		b43_phy_write(dev, 0x0014, 0x0280);
-	} else {
-		if (dev->dev->board_type == SSB_BOARD_MP4318 &&
-		    dev->dev->board_rev < 0x20) {
-			b43_phy_write(dev, 0x0013, 0x0210);
-			b43_phy_write(dev, 0x0014, 0x0840);
-		} else {
-			b43_phy_write(dev, 0x0013, 0x0140);
-			b43_phy_write(dev, 0x0014, 0x0280);
-		}
-		if (dev->phy.rev <= 4)
-			b43_phy_write(dev, 0x0010, 0xE000);
-		else
-			b43_phy_write(dev, 0x0010, 0x2000);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_DC, 1, 0x0039);
-		b43_ofdmtab_write16(dev, B43_OFDMTAB_UNKNOWN_APHY, 7, 0x0040);
-	}
-}
-
 static void b43_wa_boards_g(struct b43_wldev *dev)
 {
 	struct ssb_sprom *sprom = dev->dev->bus_sprom;
@@ -518,80 +346,7 @@ void b43_wa_all(struct b43_wldev *dev)
 {
 	struct b43_phy *phy = &dev->phy;
 
-	if (phy->type == B43_PHYTYPE_A) {
-		switch (phy->rev) {
-		case 2:
-			b43_wa_papd(dev);
-			b43_wa_auxclipthr(dev);
-			b43_wa_afcdac(dev);
-			b43_wa_txdc_offset(dev);
-			b43_wa_initgains(dev);
-			b43_wa_divider(dev);
-			b43_wa_gt(dev);
-			b43_wa_rssi_lt(dev);
-			b43_wa_analog(dev);
-			b43_wa_dac(dev);
-			b43_wa_fft(dev);
-			b43_wa_nft(dev);
-			b43_wa_rt(dev);
-			b43_wa_nst(dev);
-			b43_wa_art(dev);
-			b43_wa_txlna_gain(dev);
-			b43_wa_crs_reset(dev);
-			b43_wa_2060txlna_gain(dev);
-			b43_wa_lms(dev);
-			break;
-		case 3:
-			b43_wa_papd(dev);
-			b43_wa_mixedsignal(dev);
-			b43_wa_rssi_lt(dev);
-			b43_wa_txdc_offset(dev);
-			b43_wa_initgains(dev);
-			b43_wa_dac(dev);
-			b43_wa_nft(dev);
-			b43_wa_nst(dev);
-			b43_wa_msst(dev);
-			b43_wa_analog(dev);
-			b43_wa_gt(dev);
-			b43_wa_txpuoff_rxpuon(dev);
-			b43_wa_txlna_gain(dev);
-			break;
-		case 5:
-			b43_wa_iqadc(dev);
-		case 6:
-			b43_wa_papd(dev);
-			b43_wa_rssi_lt(dev);
-			b43_wa_txdc_offset(dev);
-			b43_wa_initgains(dev);
-			b43_wa_dac(dev);
-			b43_wa_nft(dev);
-			b43_wa_nst(dev);
-			b43_wa_msst(dev);
-			b43_wa_analog(dev);
-			b43_wa_gt(dev);
-			b43_wa_txpuoff_rxpuon(dev);
-			b43_wa_txlna_gain(dev);
-			break;
-		case 7:
-			b43_wa_iqadc(dev);
-			b43_wa_papd(dev);
-			b43_wa_rssi_lt(dev);
-			b43_wa_txdc_offset(dev);
-			b43_wa_initgains(dev);
-			b43_wa_dac(dev);
-			b43_wa_nft(dev);
-			b43_wa_nst(dev);
-			b43_wa_msst(dev);
-			b43_wa_analog(dev);
-			b43_wa_gt(dev);
-			b43_wa_txpuoff_rxpuon(dev);
-			b43_wa_txlna_gain(dev);
-			b43_wa_rssi_adc(dev);
-		default:
-			B43_WARN_ON(1);
-		}
-		b43_wa_boards_a(dev);
-	} else if (phy->type == B43_PHYTYPE_G) {
+	if (phy->type == B43_PHYTYPE_G) {
 		switch (phy->rev) {
 		case 1://XXX review rev1
 			b43_wa_crs_ed(dev);
diff --git a/drivers/net/wireless/broadcom/b43/xmit.c b/drivers/net/wireless/broadcom/b43/xmit.c
index f6201264de49..b068d5aeee24 100644
--- a/drivers/net/wireless/broadcom/b43/xmit.c
+++ b/drivers/net/wireless/broadcom/b43/xmit.c
@@ -205,7 +205,7 @@ static u16 b43_generate_tx_phy_ctl1(struct b43_wldev *dev, u8 bitrate)
 	return control;
 }
 
-static u8 b43_calc_fallback_rate(u8 bitrate)
+static u8 b43_calc_fallback_rate(u8 bitrate, int gmode)
 {
 	switch (bitrate) {
 	case B43_CCK_RATE_1MB:
@@ -216,8 +216,15 @@ static u8 b43_calc_fallback_rate(u8 bitrate)
 		return B43_CCK_RATE_2MB;
 	case B43_CCK_RATE_11MB:
 		return B43_CCK_RATE_5MB;
+	/*
+	 * Don't just fallback to CCK; it may be in 5GHz operation
+	 * and falling back to CCK won't work out very well.
+	 */
 	case B43_OFDM_RATE_6MB:
-		return B43_CCK_RATE_5MB;
+		if (gmode)
+			return B43_CCK_RATE_5MB;
+		else
+			return B43_OFDM_RATE_6MB;
 	case B43_OFDM_RATE_9MB:
 		return B43_OFDM_RATE_6MB;
 	case B43_OFDM_RATE_12MB:
@@ -438,7 +445,7 @@ int b43_generate_txhdr(struct b43_wldev *dev,
 
 		rts_rate = rts_cts_rate ? rts_cts_rate->hw_value : B43_CCK_RATE_1MB;
 		rts_rate_ofdm = b43_is_ofdm_rate(rts_rate);
-		rts_rate_fb = b43_calc_fallback_rate(rts_rate);
+		rts_rate_fb = b43_calc_fallback_rate(rts_rate, phy->gmode);
 		rts_rate_fb_ofdm = b43_is_ofdm_rate(rts_rate_fb);
 
 		if (rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT) {
@@ -642,11 +649,7 @@ static s8 b43_rssinoise_postprocess(struct b43_wldev *dev, u8 in_rssi)
 	struct b43_phy *phy = &dev->phy;
 	s8 ret;
 
-	if (phy->type == B43_PHYTYPE_A) {
-		//TODO: Incomplete specs.
-		ret = 0;
-	} else
-		ret = b43_rssi_postprocess(dev, in_rssi, 0, 1, 1);
+	ret = b43_rssi_postprocess(dev, in_rssi, 0, 1, 1);
 
 	return ret;
 }
@@ -663,7 +666,6 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 	u16 uninitialized_var(chanstat), uninitialized_var(mactime);
 	u32 uninitialized_var(macstat);
 	u16 chanid;
-	u16 phytype;
 	int padding, rate_idx;
 
 	memset(&status, 0, sizeof(status));
@@ -684,7 +686,6 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 		chanstat = le16_to_cpu(rxhdr->format_351.channel);
 		break;
 	}
-	phytype = chanstat & B43_RX_CHAN_PHYTYPE;
 
 	if (unlikely(macstat & B43_RX_MAC_FCSERR)) {
 		dev->wl->ieee_stats.dot11FCSErrorCount++;
@@ -755,7 +756,6 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 		else
 			status.signal = max(rxhdr->power0, rxhdr->power1);
 		break;
-	case B43_PHYTYPE_A:
 	case B43_PHYTYPE_B:
 	case B43_PHYTYPE_G:
 	case B43_PHYTYPE_LP:
@@ -802,14 +802,6 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 
 	chanid = (chanstat & B43_RX_CHAN_ID) >> B43_RX_CHAN_ID_SHIFT;
 	switch (chanstat & B43_RX_CHAN_PHYTYPE) {
-	case B43_PHYTYPE_A:
-		status.band = NL80211_BAND_5GHZ;
-		B43_WARN_ON(1);
-		/* FIXME: We don't really know which value the "chanid" contains.
-		 *        So the following assignment might be wrong. */
-		status.freq =
-			ieee80211_channel_to_frequency(chanid, status.band);
-		break;
 	case B43_PHYTYPE_G:
 		status.band = NL80211_BAND_2GHZ;
 		/* Somewhere between 478.104 and 508.1084 firmware for G-PHY
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index c7550dab6a23..c4b89d27e2e8 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -166,41 +166,45 @@ int brcmf_sdiod_intr_register(struct brcmf_sdio_dev *sdiodev)
 		sdio_claim_irq(sdiodev->func[1], brcmf_sdiod_ib_irqhandler);
 		sdio_claim_irq(sdiodev->func[2], brcmf_sdiod_dummy_irqhandler);
 		sdio_release_host(sdiodev->func[1]);
+		sdiodev->sd_irq_requested = true;
 	}
 
 	return 0;
 }
 
-int brcmf_sdiod_intr_unregister(struct brcmf_sdio_dev *sdiodev)
+void brcmf_sdiod_intr_unregister(struct brcmf_sdio_dev *sdiodev)
 {
-	struct brcmfmac_sdio_pd *pdata;
 
-	brcmf_dbg(SDIO, "Entering\n");
+	brcmf_dbg(SDIO, "Entering oob=%d sd=%d\n",
+		  sdiodev->oob_irq_requested,
+		  sdiodev->sd_irq_requested);
 
-	pdata = &sdiodev->settings->bus.sdio;
-	if (pdata->oob_irq_supported) {
+	if (sdiodev->oob_irq_requested) {
+		struct brcmfmac_sdio_pd *pdata;
+
+		pdata = &sdiodev->settings->bus.sdio;
 		sdio_claim_host(sdiodev->func[1]);
 		brcmf_sdiod_regwb(sdiodev, SDIO_CCCR_BRCM_SEPINT, 0, NULL);
 		brcmf_sdiod_regwb(sdiodev, SDIO_CCCR_IENx, 0, NULL);
 		sdio_release_host(sdiodev->func[1]);
 
-		if (sdiodev->oob_irq_requested) {
-			sdiodev->oob_irq_requested = false;
-			if (sdiodev->irq_wake) {
-				disable_irq_wake(pdata->oob_irq_nr);
-				sdiodev->irq_wake = false;
-			}
-			free_irq(pdata->oob_irq_nr, &sdiodev->func[1]->dev);
-			sdiodev->irq_en = false;
+		sdiodev->oob_irq_requested = false;
+		if (sdiodev->irq_wake) {
+			disable_irq_wake(pdata->oob_irq_nr);
+			sdiodev->irq_wake = false;
 		}
-	} else {
+		free_irq(pdata->oob_irq_nr, &sdiodev->func[1]->dev);
+		sdiodev->irq_en = false;
+		sdiodev->oob_irq_requested = false;
+	}
+
+	if (sdiodev->sd_irq_requested) {
 		sdio_claim_host(sdiodev->func[1]);
 		sdio_release_irq(sdiodev->func[2]);
 		sdio_release_irq(sdiodev->func[1]);
 		sdio_release_host(sdiodev->func[1]);
+		sdiodev->sd_irq_requested = false;
 	}
-
-	return 0;
 }
 
 void brcmf_sdiod_change_state(struct brcmf_sdio_dev *sdiodev,
@@ -1197,12 +1201,17 @@ static void brcmf_ops_sdio_remove(struct sdio_func *func)
 	brcmf_dbg(SDIO, "sdio device ID: 0x%04x\n", func->device);
 	brcmf_dbg(SDIO, "Function: %d\n", func->num);
 
-	if (func->num != 1)
-		return;
-
 	bus_if = dev_get_drvdata(&func->dev);
 	if (bus_if) {
 		sdiodev = bus_if->bus_priv.sdio;
+
+		/* start by unregistering irqs */
+		brcmf_sdiod_intr_unregister(sdiodev);
+
+		if (func->num != 1)
+			return;
+
+		/* only proceed with rest of cleanup if func 1 */
 		brcmf_sdiod_remove(sdiodev);
 
 		dev_set_drvdata(&sdiodev->func[1]->dev, NULL);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index d0631b6cfd53..264bd638a3d9 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -541,6 +541,21 @@ brcmf_cfg80211_update_proto_addr_mode(struct wireless_dev *wdev)
 						ADDR_INDIRECT);
 }
 
+static int brcmf_get_first_free_bsscfgidx(struct brcmf_pub *drvr)
+{
+	int bsscfgidx;
+
+	for (bsscfgidx = 0; bsscfgidx < BRCMF_MAX_IFS; bsscfgidx++) {
+		/* bsscfgidx 1 is reserved for legacy P2P */
+		if (bsscfgidx == 1)
+			continue;
+		if (!drvr->iflist[bsscfgidx])
+			return bsscfgidx;
+	}
+
+	return -ENOMEM;
+}
+
 static int brcmf_cfg80211_request_ap_if(struct brcmf_if *ifp)
 {
 	struct brcmf_mbss_ssid_le mbss_ssid_le;
@@ -548,7 +563,7 @@ static int brcmf_cfg80211_request_ap_if(struct brcmf_if *ifp)
 	int err;
 
 	memset(&mbss_ssid_le, 0, sizeof(mbss_ssid_le));
-	bsscfgidx = brcmf_get_next_free_bsscfgidx(ifp->drvr);
+	bsscfgidx = brcmf_get_first_free_bsscfgidx(ifp->drvr);
 	if (bsscfgidx < 0)
 		return bsscfgidx;
 
@@ -586,7 +601,7 @@ struct wireless_dev *brcmf_ap_add_vif(struct wiphy *wiphy, const char *name,
 
 	brcmf_dbg(INFO, "Adding vif \"%s\"\n", name);
 
-	vif = brcmf_alloc_vif(cfg, NL80211_IFTYPE_AP, false);
+	vif = brcmf_alloc_vif(cfg, NL80211_IFTYPE_AP);
 	if (IS_ERR(vif))
 		return (struct wireless_dev *)vif;
 
@@ -669,20 +684,24 @@ static struct wireless_dev *brcmf_cfg80211_add_iface(struct wiphy *wiphy,
 		return ERR_PTR(-EOPNOTSUPP);
 	case NL80211_IFTYPE_AP:
 		wdev = brcmf_ap_add_vif(wiphy, name, flags, params);
-		if (!IS_ERR(wdev))
-			brcmf_cfg80211_update_proto_addr_mode(wdev);
-		return wdev;
+		break;
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_P2P_GO:
 	case NL80211_IFTYPE_P2P_DEVICE:
 		wdev = brcmf_p2p_add_vif(wiphy, name, name_assign_type, type, flags, params);
-		if (!IS_ERR(wdev))
-			brcmf_cfg80211_update_proto_addr_mode(wdev);
-		return wdev;
+		break;
 	case NL80211_IFTYPE_UNSPECIFIED:
 	default:
 		return ERR_PTR(-EINVAL);
 	}
+
+	if (IS_ERR(wdev))
+		brcmf_err("add iface %s type %d failed: err=%d\n",
+			  name, type, (int)PTR_ERR(wdev));
+	else
+		brcmf_cfg80211_update_proto_addr_mode(wdev);
+
+	return wdev;
 }
 
 static void brcmf_scan_config_mpc(struct brcmf_if *ifp, int mpc)
@@ -2540,12 +2559,14 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 			   const u8 *mac, struct station_info *sinfo)
 {
 	struct brcmf_if *ifp = netdev_priv(ndev);
+	struct brcmf_scb_val_le scb_val;
 	s32 err = 0;
 	struct brcmf_sta_info_le sta_info_le;
 	u32 sta_flags;
 	u32 is_tdls_peer;
 	s32 total_rssi;
 	s32 count_rssi;
+	int rssi;
 	u32 i;
 
 	brcmf_dbg(TRACE, "Enter, MAC %pM\n", mac);
@@ -2629,6 +2650,20 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 			sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
 			total_rssi /= count_rssi;
 			sinfo->signal = total_rssi;
+		} else if (test_bit(BRCMF_VIF_STATUS_CONNECTED,
+			&ifp->vif->sme_state)) {
+			memset(&scb_val, 0, sizeof(scb_val));
+			err = brcmf_fil_cmd_data_get(ifp, BRCMF_C_GET_RSSI,
+						     &scb_val, sizeof(scb_val));
+			if (err) {
+				brcmf_err("Could not get rssi (%d)\n", err);
+				goto done;
+			} else {
+				rssi = le32_to_cpu(scb_val.val);
+				sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+				sinfo->signal = rssi;
+				brcmf_dbg(CONN, "RSSI %d dBm\n", rssi);
+			}
 		}
 	}
 done:
@@ -2734,7 +2769,7 @@ static s32 brcmf_inform_single_bss(struct brcmf_cfg80211_info *cfg,
 	if (!bi->ctl_ch) {
 		ch.chspec = le16_to_cpu(bi->chanspec);
 		cfg->d11inf.decchspec(&ch);
-		bi->ctl_ch = ch.chnum;
+		bi->ctl_ch = ch.control_ch_num;
 	}
 	channel = bi->ctl_ch;
 
@@ -2852,7 +2887,7 @@ static s32 brcmf_inform_ibss(struct brcmf_cfg80211_info *cfg,
 	else
 		band = wiphy->bands[NL80211_BAND_5GHZ];
 
-	freq = ieee80211_channel_to_frequency(ch.chnum, band->band);
+	freq = ieee80211_channel_to_frequency(ch.control_ch_num, band->band);
 	cfg->channel = freq;
 	notify_channel = ieee80211_get_channel(wiphy, freq);
 
@@ -2862,7 +2897,7 @@ static s32 brcmf_inform_ibss(struct brcmf_cfg80211_info *cfg,
 	notify_ielen = le32_to_cpu(bi->ie_length);
 	notify_signal = (s16)le16_to_cpu(bi->RSSI) * 100;
 
-	brcmf_dbg(CONN, "channel: %d(%d)\n", ch.chnum, freq);
+	brcmf_dbg(CONN, "channel: %d(%d)\n", ch.control_ch_num, freq);
 	brcmf_dbg(CONN, "capability: %X\n", notify_capability);
 	brcmf_dbg(CONN, "beacon interval: %d\n", notify_interval);
 	brcmf_dbg(CONN, "signal: %d\n", notify_signal);
@@ -4423,7 +4458,7 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 	struct brcmf_join_params join_params;
 	enum nl80211_iftype dev_role;
 	struct brcmf_fil_bss_enable_le bss_enable;
-	u16 chanspec;
+	u16 chanspec = chandef_to_chanspec(&cfg->d11inf, &settings->chandef);
 	bool mbss;
 	int is_11d;
 
@@ -4499,16 +4534,8 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 
 	brcmf_config_ap_mgmt_ie(ifp->vif, &settings->beacon);
 
+	/* Parameters shared by all radio interfaces */
 	if (!mbss) {
-		chanspec = chandef_to_chanspec(&cfg->d11inf,
-					       &settings->chandef);
-		err = brcmf_fil_iovar_int_set(ifp, "chanspec", chanspec);
-		if (err < 0) {
-			brcmf_err("Set Channel failed: chspec=%d, %d\n",
-				  chanspec, err);
-			goto exit;
-		}
-
 		if (is_11d != ifp->vif->is_11d) {
 			err = brcmf_fil_cmd_int_set(ifp, BRCMF_C_SET_REGULATORY,
 						    is_11d);
@@ -4556,6 +4583,8 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 		err = -EINVAL;
 		goto exit;
 	}
+
+	/* Interface specific setup */
 	if (dev_role == NL80211_IFTYPE_AP) {
 		if ((brcmf_feat_is_enabled(ifp, BRCMF_FEAT_MBSS)) && (!mbss))
 			brcmf_fil_iovar_int_set(ifp, "mbss", 1);
@@ -4565,6 +4594,17 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 			brcmf_err("setting AP mode failed %d\n", err);
 			goto exit;
 		}
+		if (!mbss) {
+			/* Firmware 10.x requires setting channel after enabling
+			 * AP and before bringing interface up.
+			 */
+			err = brcmf_fil_iovar_int_set(ifp, "chanspec", chanspec);
+			if (err < 0) {
+				brcmf_err("Set Channel failed: chspec=%d, %d\n",
+					  chanspec, err);
+				goto exit;
+			}
+		}
 		err = brcmf_fil_cmd_int_set(ifp, BRCMF_C_UP, 1);
 		if (err < 0) {
 			brcmf_err("BRCMF_C_UP error (%d)\n", err);
@@ -4586,7 +4626,13 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 			goto exit;
 		}
 		brcmf_dbg(TRACE, "AP mode configuration complete\n");
-	} else {
+	} else if (dev_role == NL80211_IFTYPE_P2P_GO) {
+		err = brcmf_fil_iovar_int_set(ifp, "chanspec", chanspec);
+		if (err < 0) {
+			brcmf_err("Set Channel failed: chspec=%d, %d\n",
+				  chanspec, err);
+			goto exit;
+		}
 		err = brcmf_fil_bsscfg_data_set(ifp, "ssid", &ssid_le,
 						sizeof(ssid_le));
 		if (err < 0) {
@@ -4603,7 +4649,10 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 		}
 
 		brcmf_dbg(TRACE, "GO mode configuration complete\n");
+	} else {
+		WARN_ON(1);
 	}
+
 	set_bit(BRCMF_VIF_STATUS_AP_CREATED, &ifp->vif->sme_state);
 	brcmf_net_setcarrier(ifp, true);
 
@@ -4892,6 +4941,68 @@ exit:
 	return err;
 }
 
+static int brcmf_cfg80211_get_channel(struct wiphy *wiphy,
+				      struct wireless_dev *wdev,
+				      struct cfg80211_chan_def *chandef)
+{
+	struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
+	struct net_device *ndev = wdev->netdev;
+	struct brcmf_if *ifp;
+	struct brcmu_chan ch;
+	enum nl80211_band band = 0;
+	enum nl80211_chan_width width = 0;
+	u32 chanspec;
+	int freq, err;
+
+	if (!ndev)
+		return -ENODEV;
+	ifp = netdev_priv(ndev);
+
+	err = brcmf_fil_iovar_int_get(ifp, "chanspec", &chanspec);
+	if (err) {
+		brcmf_err("chanspec failed (%d)\n", err);
+		return err;
+	}
+
+	ch.chspec = chanspec;
+	cfg->d11inf.decchspec(&ch);
+
+	switch (ch.band) {
+	case BRCMU_CHAN_BAND_2G:
+		band = NL80211_BAND_2GHZ;
+		break;
+	case BRCMU_CHAN_BAND_5G:
+		band = NL80211_BAND_5GHZ;
+		break;
+	}
+
+	switch (ch.bw) {
+	case BRCMU_CHAN_BW_80:
+		width = NL80211_CHAN_WIDTH_80;
+		break;
+	case BRCMU_CHAN_BW_40:
+		width = NL80211_CHAN_WIDTH_40;
+		break;
+	case BRCMU_CHAN_BW_20:
+		width = NL80211_CHAN_WIDTH_20;
+		break;
+	case BRCMU_CHAN_BW_80P80:
+		width = NL80211_CHAN_WIDTH_80P80;
+		break;
+	case BRCMU_CHAN_BW_160:
+		width = NL80211_CHAN_WIDTH_160;
+		break;
+	}
+
+	freq = ieee80211_channel_to_frequency(ch.control_ch_num, band);
+	chandef->chan = ieee80211_get_channel(wiphy, freq);
+	chandef->width = width;
+	chandef->center_freq1 = ieee80211_channel_to_frequency(ch.chnum, band);
+	chandef->center_freq2 = 0;
+
+	return 0;
+}
+
 static int brcmf_cfg80211_crit_proto_start(struct wiphy *wiphy,
 					   struct wireless_dev *wdev,
 					   enum nl80211_crit_proto_id proto,
@@ -5054,6 +5165,7 @@ static struct cfg80211_ops brcmf_cfg80211_ops = {
 	.mgmt_tx = brcmf_cfg80211_mgmt_tx,
 	.remain_on_channel = brcmf_p2p_remain_on_channel,
 	.cancel_remain_on_channel = brcmf_cfg80211_cancel_remain_on_channel,
+	.get_channel = brcmf_cfg80211_get_channel,
 	.start_p2p_device = brcmf_p2p_start_device,
 	.stop_p2p_device = brcmf_p2p_stop_device,
 	.crit_proto_start = brcmf_cfg80211_crit_proto_start,
@@ -5062,8 +5174,7 @@ static struct cfg80211_ops brcmf_cfg80211_ops = {
 };
 
 struct brcmf_cfg80211_vif *brcmf_alloc_vif(struct brcmf_cfg80211_info *cfg,
-					   enum nl80211_iftype type,
-					   bool pm_block)
+					   enum nl80211_iftype type)
 {
 	struct brcmf_cfg80211_vif *vif_walk;
 	struct brcmf_cfg80211_vif *vif;
@@ -5078,8 +5189,6 @@ struct brcmf_cfg80211_vif *brcmf_alloc_vif(struct brcmf_cfg80211_info *cfg,
 	vif->wdev.wiphy = cfg->wiphy;
 	vif->wdev.iftype = type;
 
-	vif->pm_block = pm_block;
-
 	brcmf_init_prof(&vif->profile);
 
 	if (type == NL80211_IFTYPE_AP) {
@@ -5280,7 +5389,7 @@ brcmf_bss_roaming_done(struct brcmf_cfg80211_info *cfg,
 	else
 		band = wiphy->bands[NL80211_BAND_5GHZ];
 
-	freq = ieee80211_channel_to_frequency(ch.chnum, band->band);
+	freq = ieee80211_channel_to_frequency(ch.control_ch_num, band->band);
 	notify_channel = ieee80211_get_channel(wiphy, freq);
 
 done:
@@ -5336,7 +5445,6 @@ brcmf_notify_connect_status_ap(struct brcmf_cfg80211_info *cfg,
 			       struct net_device *ndev,
 			       const struct brcmf_event_msg *e, void *data)
 {
-	struct brcmf_if *ifp = netdev_priv(ndev);
 	static int generation;
 	u32 event = e->event_code;
 	u32 reason = e->reason;
@@ -5347,8 +5455,6 @@ brcmf_notify_connect_status_ap(struct brcmf_cfg80211_info *cfg,
 	    ndev != cfg_to_ndev(cfg)) {
 		brcmf_dbg(CONN, "AP mode link down\n");
 		complete(&cfg->vif_disabled);
-		if (ifp->vif->mbss)
-			brcmf_remove_interface(ifp);
 		return 0;
 	}
 
@@ -5802,14 +5908,15 @@ static int brcmf_construct_chaninfo(struct brcmf_cfg80211_info *cfg,
 		channel = band->channels;
 		index = band->n_channels;
 		for (j = 0; j < band->n_channels; j++) {
-			if (channel[j].hw_value == ch.chnum) {
+			if (channel[j].hw_value == ch.control_ch_num) {
 				index = j;
 				break;
 			}
 		}
 		channel[index].center_freq =
-			ieee80211_channel_to_frequency(ch.chnum, band->band);
-		channel[index].hw_value = ch.chnum;
+			ieee80211_channel_to_frequency(ch.control_ch_num,
+						       band->band);
+		channel[index].hw_value = ch.control_ch_num;
 
 		/* assuming the chanspecs order is HT20,
 		 * HT40 upper, HT40 lower, and VHT80.
@@ -5911,7 +6018,7 @@ static int brcmf_enable_bw40_2g(struct brcmf_cfg80211_info *cfg)
 			if (WARN_ON(ch.bw != BRCMU_CHAN_BW_40))
 				continue;
 			for (j = 0; j < band->n_channels; j++) {
-				if (band->channels[j].hw_value == ch.chnum)
+				if (band->channels[j].hw_value == ch.control_ch_num)
 					break;
 			}
 			if (WARN_ON(j == band->n_channels))
@@ -6699,11 +6806,10 @@ struct brcmf_cfg80211_info *brcmf_cfg80211_attach(struct brcmf_pub *drvr,
 		return NULL;
 	}
 
-	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
+	ops = kmemdup(&brcmf_cfg80211_ops, sizeof(*ops), GFP_KERNEL);
 	if (!ops)
 		return NULL;
 
-	memcpy(ops, &brcmf_cfg80211_ops, sizeof(*ops));
 	ifp = netdev_priv(ndev);
 #ifdef CONFIG_PM
 	if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_WOWL_GTK))
@@ -6724,7 +6830,7 @@ struct brcmf_cfg80211_info *brcmf_cfg80211_attach(struct brcmf_pub *drvr,
 	init_vif_event(&cfg->vif_event);
 	INIT_LIST_HEAD(&cfg->vif_list);
 
-	vif = brcmf_alloc_vif(cfg, NL80211_IFTYPE_STATION, false);
+	vif = brcmf_alloc_vif(cfg, NL80211_IFTYPE_STATION);
 	if (IS_ERR(vif))
 		goto wiphy_out;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
index 95e35bcc16ce..04bfc7e3ecde 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
@@ -20,6 +20,9 @@
 /* for brcmu_d11inf */
 #include <brcmu_d11.h>
 
+#include "fwil_types.h"
+#include "p2p.h"
+
 #define WL_NUM_SCAN_MAX			10
 #define WL_TLV_INFO_MAX			1024
 #define WL_BSS_INFO_MAX			2048
@@ -167,7 +170,6 @@ struct vif_saved_ie {
  * @wdev: wireless device.
  * @profile: profile information.
  * @sme_state: SME state using enum brcmf_vif_status bits.
- * @pm_block: power-management blocked.
  * @list: linked list.
  * @mgmt_rx_reg: registered rx mgmt frame types.
  * @mbss: Multiple BSS type, set if not first AP (not relevant for P2P).
@@ -177,7 +179,6 @@ struct brcmf_cfg80211_vif {
 	struct wireless_dev wdev;
 	struct brcmf_cfg80211_profile profile;
 	unsigned long sme_state;
-	bool pm_block;
 	struct vif_saved_ie saved_ie;
 	struct list_head list;
 	u16 mgmt_rx_reg;
@@ -388,8 +389,7 @@ s32 brcmf_cfg80211_down(struct net_device *ndev);
 enum nl80211_iftype brcmf_cfg80211_get_iftype(struct brcmf_if *ifp);
 
 struct brcmf_cfg80211_vif *brcmf_alloc_vif(struct brcmf_cfg80211_info *cfg,
-					   enum nl80211_iftype type,
-					   bool pm_block);
+					   enum nl80211_iftype type);
 void brcmf_free_vif(struct brcmf_cfg80211_vif *vif);
 
 s32 brcmf_vif_set_mgmt_ie(struct brcmf_cfg80211_vif *vif, s32 pktflag,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
index d3fd6b1db1d9..05f22ff81d60 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
@@ -685,6 +685,8 @@ static u32 brcmf_chip_tcm_rambase(struct brcmf_chip_priv *ci)
 	case BRCM_CC_43602_CHIP_ID:
 	case BRCM_CC_4371_CHIP_ID:
 		return 0x180000;
+	case BRCM_CC_43465_CHIP_ID:
+	case BRCM_CC_43525_CHIP_ID:
 	case BRCM_CC_4365_CHIP_ID:
 	case BRCM_CC_4366_CHIP_ID:
 		return 0x200000;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index b590499f6883..faf4e46bd65b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -516,7 +516,7 @@ int brcmf_net_attach(struct brcmf_if *ifp, bool rtnl_locked)
 	/* set appropriate operations */
 	ndev->netdev_ops = &brcmf_netdev_ops_pri;
 
-	ndev->hard_header_len += drvr->hdrlen;
+	ndev->needed_headroom += drvr->hdrlen;
 	ndev->ethtool_ops = &brcmf_ethtool_ops;
 
 	drvr->rxsz = ndev->mtu + ndev->hard_header_len +
@@ -753,30 +753,6 @@ void brcmf_remove_interface(struct brcmf_if *ifp)
 	brcmf_del_if(ifp->drvr, ifp->bsscfgidx);
 }
 
-int brcmf_get_next_free_bsscfgidx(struct brcmf_pub *drvr)
-{
-	int ifidx;
-	int bsscfgidx;
-	bool available;
-	int highest;
-
-	available = false;
-	bsscfgidx = 2;
-	highest = 2;
-	for (ifidx = 0; ifidx < BRCMF_MAX_IFS; ifidx++) {
-		if (drvr->iflist[ifidx]) {
-			if (drvr->iflist[ifidx]->bsscfgidx == bsscfgidx)
-				bsscfgidx = highest + 1;
-			else if (drvr->iflist[ifidx]->bsscfgidx > highest)
-				highest = drvr->iflist[ifidx]->bsscfgidx;
-		} else {
-			available = true;
-		}
-	}
-
-	return available ? bsscfgidx : -ENOMEM;
-}
-
 #ifdef CONFIG_INET
 #define ARPOL_MAX_ENTRIES	8
 static int brcmf_inetaddr_changed(struct notifier_block *nb,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
index 647d3cc2a4dc..2a075c5f6f8b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
@@ -217,7 +217,6 @@ int brcmf_net_attach(struct brcmf_if *ifp, bool rtnl_locked);
 struct brcmf_if *brcmf_add_if(struct brcmf_pub *drvr, s32 bsscfgidx, s32 ifidx,
 			      bool is_p2pdev, char *name, u8 *mac_addr);
 void brcmf_remove_interface(struct brcmf_if *ifp);
-int brcmf_get_next_free_bsscfgidx(struct brcmf_pub *drvr);
 void brcmf_txflowblock_if(struct brcmf_if *ifp,
 			  enum brcmf_netif_stop_reason reason, bool state);
 void brcmf_txfinalize(struct brcmf_if *ifp, struct sk_buff *txp, bool success);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
index 5b30922b67ec..cd221ab55062 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
@@ -2101,7 +2101,7 @@ int brcmf_fws_process_skb(struct brcmf_if *ifp, struct sk_buff *skb)
 
 	brcmf_dbg(DATA, "tx proto=0x%X\n", ntohs(eh->h_proto));
 	/* determine the priority */
-	if (!skb->priority)
+	if ((skb->priority == 0) || (skb->priority > 7))
 		skb->priority = cfg80211_classify8021d(skb, NULL);
 
 	drvr->tx_multicast += !!multicast;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
index 68f1ce02f4bf..2b9a2bc429d6 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
@@ -1157,6 +1157,8 @@ brcmf_msgbuf_process_rx_complete(struct brcmf_msgbuf *msgbuf, void *buf)
 		brcmu_pkt_buf_free_skb(skb);
 		return;
 	}
+
+	skb->protocol = eth_type_trans(skb, ifp->ndev);
 	brcmf_netif_rx(ifp, skb);
 }
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
index a70cda6c0592..f38a82133540 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
@@ -1246,7 +1246,7 @@ bool brcmf_p2p_scan_finding_common_channel(struct brcmf_cfg80211_info *cfg,
 		if (!bi->ctl_ch) {
 			ch.chspec = le16_to_cpu(bi->chanspec);
 			cfg->d11inf.decchspec(&ch);
-			bi->ctl_ch = ch.chnum;
+			bi->ctl_ch = ch.control_ch_num;
 		}
 		afx_hdl->peer_chan = bi->ctl_ch;
 		brcmf_dbg(TRACE, "ACTION FRAME SCAN : Peer %pM found, channel : %d\n",
@@ -1385,7 +1385,7 @@ int brcmf_p2p_notify_action_frame_rx(struct brcmf_if *ifp,
 			if (test_bit(BRCMF_P2P_STATUS_FINDING_COMMON_CHANNEL,
 				     &p2p->status) &&
 			    (ether_addr_equal(afx_hdl->tx_dst_addr, e->addr))) {
-				afx_hdl->peer_chan = ch.chnum;
+				afx_hdl->peer_chan = ch.control_ch_num;
 				brcmf_dbg(INFO, "GON request: Peer found, channel=%d\n",
 					  afx_hdl->peer_chan);
 				complete(&afx_hdl->act_frm_scan);
@@ -1428,7 +1428,7 @@ int brcmf_p2p_notify_action_frame_rx(struct brcmf_if *ifp,
 	memcpy(&mgmt_frame->u, frame, mgmt_frame_len);
 	mgmt_frame_len += offsetof(struct ieee80211_mgmt, u);
 
-	freq = ieee80211_channel_to_frequency(ch.chnum,
+	freq = ieee80211_channel_to_frequency(ch.control_ch_num,
 					      ch.band == BRCMU_CHAN_BAND_2G ?
 					      NL80211_BAND_2GHZ :
 					      NL80211_BAND_5GHZ);
@@ -1873,7 +1873,7 @@ s32 brcmf_p2p_notify_rx_mgmt_p2p_probereq(struct brcmf_if *ifp,
 
 	if (test_bit(BRCMF_P2P_STATUS_FINDING_COMMON_CHANNEL, &p2p->status) &&
 	    (ether_addr_equal(afx_hdl->tx_dst_addr, e->addr))) {
-		afx_hdl->peer_chan = ch.chnum;
+		afx_hdl->peer_chan = ch.control_ch_num;
 		brcmf_dbg(INFO, "PROBE REQUEST: Peer found, channel=%d\n",
 			  afx_hdl->peer_chan);
 		complete(&afx_hdl->act_frm_scan);
@@ -1898,7 +1898,7 @@ s32 brcmf_p2p_notify_rx_mgmt_p2p_probereq(struct brcmf_if *ifp,
 
 	mgmt_frame = (u8 *)(rxframe + 1);
 	mgmt_frame_len = e->datalen - sizeof(*rxframe);
-	freq = ieee80211_channel_to_frequency(ch.chnum,
+	freq = ieee80211_channel_to_frequency(ch.control_ch_num,
 					      ch.band == BRCMU_CHAN_BAND_2G ?
 					      NL80211_BAND_2GHZ :
 					      NL80211_BAND_5GHZ);
@@ -2030,8 +2030,6 @@ static int brcmf_p2p_request_p2p_if(struct brcmf_p2p_info *p2p,
 
 	err = brcmf_fil_iovar_data_set(ifp, "p2p_ifadd", &if_request,
 				       sizeof(if_request));
-	if (err)
-		return err;
 
 	return err;
 }
@@ -2076,8 +2074,7 @@ static struct wireless_dev *brcmf_p2p_create_p2pdev(struct brcmf_p2p_info *p2p,
 	if (p2p->bss_idx[P2PAPI_BSSCFG_DEVICE].vif)
 		return ERR_PTR(-ENOSPC);
 
-	p2p_vif = brcmf_alloc_vif(p2p->cfg, NL80211_IFTYPE_P2P_DEVICE,
-				  false);
+	p2p_vif = brcmf_alloc_vif(p2p->cfg, NL80211_IFTYPE_P2P_DEVICE);
 	if (IS_ERR(p2p_vif)) {
 		brcmf_err("could not create discovery vif\n");
 		return (struct wireless_dev *)p2p_vif;
@@ -2177,7 +2174,7 @@ struct wireless_dev *brcmf_p2p_add_vif(struct wiphy *wiphy, const char *name,
 		return ERR_PTR(-EOPNOTSUPP);
 	}
 
-	vif = brcmf_alloc_vif(cfg, type, false);
+	vif = brcmf_alloc_vif(cfg, type);
 	if (IS_ERR(vif))
 		return (struct wireless_dev *)vif;
 	brcmf_cfg80211_arm_vif_event(cfg, vif);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index 0af8db82da0c..3deba90c7eb5 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -54,21 +54,25 @@ BRCMF_FW_NVRAM_DEF(43570, "brcmfmac43570-pcie.bin", "brcmfmac43570-pcie.txt");
 BRCMF_FW_NVRAM_DEF(4358, "brcmfmac4358-pcie.bin", "brcmfmac4358-pcie.txt");
 BRCMF_FW_NVRAM_DEF(4359, "brcmfmac4359-pcie.bin", "brcmfmac4359-pcie.txt");
 BRCMF_FW_NVRAM_DEF(4365B, "brcmfmac4365b-pcie.bin", "brcmfmac4365b-pcie.txt");
+BRCMF_FW_NVRAM_DEF(4365C, "brcmfmac4365c-pcie.bin", "brcmfmac4365c-pcie.txt");
 BRCMF_FW_NVRAM_DEF(4366B, "brcmfmac4366b-pcie.bin", "brcmfmac4366b-pcie.txt");
 BRCMF_FW_NVRAM_DEF(4366C, "brcmfmac4366c-pcie.bin", "brcmfmac4366c-pcie.txt");
 BRCMF_FW_NVRAM_DEF(4371, "brcmfmac4371-pcie.bin", "brcmfmac4371-pcie.txt");
 
 static struct brcmf_firmware_mapping brcmf_pcie_fwnames[] = {
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_43602_CHIP_ID, 0xFFFFFFFF, 43602),
+	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_43465_CHIP_ID, 0xFFFFFFF0, 4366C),
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_4350_CHIP_ID, 0x000000FF, 4350C),
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_4350_CHIP_ID, 0xFFFFFF00, 4350),
+	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_43525_CHIP_ID, 0xFFFFFFF0, 4365C),
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_4356_CHIP_ID, 0xFFFFFFFF, 4356),
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_43567_CHIP_ID, 0xFFFFFFFF, 43570),
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_43569_CHIP_ID, 0xFFFFFFFF, 43570),
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_43570_CHIP_ID, 0xFFFFFFFF, 43570),
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_4358_CHIP_ID, 0xFFFFFFFF, 4358),
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_4359_CHIP_ID, 0xFFFFFFFF, 4359),
-	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_4365_CHIP_ID, 0xFFFFFFFF, 4365B),
+	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_4365_CHIP_ID, 0x0000000F, 4365B),
+	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_4365_CHIP_ID, 0xFFFFFFF0, 4365C),
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_4366_CHIP_ID, 0x0000000F, 4366B),
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_4366_CHIP_ID, 0xFFFFFFF0, 4366C),
 	BRCMF_FW_NVRAM_ENTRY(BRCM_CC_4371_CHIP_ID, 0xFFFFFFFF, 4371),
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 67e69bff2545..5fb8b91b9326 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -1384,8 +1384,7 @@ static int brcmf_sdio_hdparse(struct brcmf_sdio *bus, u8 *header,
 		return -ENXIO;
 	}
 	if (rd->seq_num != rx_seq) {
-		brcmf_err("seq %d: sequence number error, expect %d\n",
-			  rx_seq, rd->seq_num);
+		brcmf_dbg(SDIO, "seq %d, expected %d\n", rx_seq, rd->seq_num);
 		bus->sdcnt.rx_badseq++;
 		rd->seq_num = rx_seq;
 	}
@@ -3666,7 +3665,7 @@ brcmf_sdio_drivestrengthinit(struct brcmf_sdio_dev *sdiodev,
 		str_shift = 11;
 		break;
 	default:
-		brcmf_err("No SDIO Drive strength init done for chip %s rev %d pmurev %d\n",
+		brcmf_dbg(INFO, "No SDIO driver strength init needed for chip %s rev %d pmurev %d\n",
 			  ci->name, ci->chiprev, ci->pmurev);
 		break;
 	}
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
index dcf0ce8cd2c1..f3da32fc6360 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
@@ -186,6 +186,7 @@ struct brcmf_sdio_dev {
 	struct brcmf_bus *bus_if;
 	struct brcmf_mp_device *settings;
 	bool oob_irq_requested;
+	bool sd_irq_requested;
 	bool irq_en;			/* irq enable flags */
 	spinlock_t irq_en_lock;
 	bool irq_wake;			/* irq wake enable flags */
@@ -293,7 +294,7 @@ struct sdpcmd_regs {
 
 /* Register/deregister interrupt handler. */
 int brcmf_sdiod_intr_register(struct brcmf_sdio_dev *sdiodev);
-int brcmf_sdiod_intr_unregister(struct brcmf_sdio_dev *sdiodev);
+void brcmf_sdiod_intr_unregister(struct brcmf_sdio_dev *sdiodev);
 
 /* sdio device register access interface */
 u8 brcmf_sdiod_regrb(struct brcmf_sdio_dev *sdiodev, u32 addr, int *ret);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
index 99dac9b8a082..b3aab2fe96eb 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
@@ -27017,7 +27017,7 @@ wlc_phy_rxcal_gainctrl_nphy_rev5(struct brcms_phy *pi, u8 rx_core,
 		tx_core = 1 - rx_core;
 
 	num_samps = 1024;
-	desired_log2_pwr = (cal_type == 0) ? 13 : 13;
+	desired_log2_pwr = 13;
 
 	wlc_phy_rx_iq_coeffs_nphy(pi, 0, &save_comp);
 	zero_comp.a0 = zero_comp.b0 = zero_comp.a1 = zero_comp.b1 = 0x0;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c b/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c
index 2b2522bdd8eb..d8b79cb72b58 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c
@@ -107,6 +107,7 @@ static void brcmu_d11n_decchspec(struct brcmu_chan *ch)
 	u16 val;
 
 	ch->chnum = (u8)(ch->chspec & BRCMU_CHSPEC_CH_MASK);
+	ch->control_ch_num = ch->chnum;
 
 	switch (ch->chspec & BRCMU_CHSPEC_D11N_BW_MASK) {
 	case BRCMU_CHSPEC_D11N_BW_20:
@@ -118,10 +119,10 @@ static void brcmu_d11n_decchspec(struct brcmu_chan *ch)
 		val = ch->chspec & BRCMU_CHSPEC_D11N_SB_MASK;
 		if (val == BRCMU_CHSPEC_D11N_SB_L) {
 			ch->sb = BRCMU_CHAN_SB_L;
-			ch->chnum -= CH_10MHZ_APART;
+			ch->control_ch_num -= CH_10MHZ_APART;
 		} else {
 			ch->sb = BRCMU_CHAN_SB_U;
-			ch->chnum += CH_10MHZ_APART;
+			ch->control_ch_num += CH_10MHZ_APART;
 		}
 		break;
 	default:
@@ -147,6 +148,7 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch)
 	u16 val;
 
 	ch->chnum = (u8)(ch->chspec & BRCMU_CHSPEC_CH_MASK);
+	ch->control_ch_num = ch->chnum;
 
 	switch (ch->chspec & BRCMU_CHSPEC_D11AC_BW_MASK) {
 	case BRCMU_CHSPEC_D11AC_BW_20:
@@ -158,10 +160,10 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch)
 		val = ch->chspec & BRCMU_CHSPEC_D11AC_SB_MASK;
 		if (val == BRCMU_CHSPEC_D11AC_SB_L) {
 			ch->sb = BRCMU_CHAN_SB_L;
-			ch->chnum -= CH_10MHZ_APART;
+			ch->control_ch_num -= CH_10MHZ_APART;
 		} else if (val == BRCMU_CHSPEC_D11AC_SB_U) {
 			ch->sb = BRCMU_CHAN_SB_U;
-			ch->chnum += CH_10MHZ_APART;
+			ch->control_ch_num += CH_10MHZ_APART;
 		} else {
 			WARN_ON_ONCE(1);
 		}
@@ -172,16 +174,16 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch)
 					 BRCMU_CHSPEC_D11AC_SB_SHIFT);
 		switch (ch->sb) {
 		case BRCMU_CHAN_SB_LL:
-			ch->chnum -= CH_30MHZ_APART;
+			ch->control_ch_num -= CH_30MHZ_APART;
 			break;
 		case BRCMU_CHAN_SB_LU:
-			ch->chnum -= CH_10MHZ_APART;
+			ch->control_ch_num -= CH_10MHZ_APART;
 			break;
 		case BRCMU_CHAN_SB_UL:
-			ch->chnum += CH_10MHZ_APART;
+			ch->control_ch_num += CH_10MHZ_APART;
 			break;
 		case BRCMU_CHAN_SB_UU:
-			ch->chnum += CH_30MHZ_APART;
+			ch->control_ch_num += CH_30MHZ_APART;
 			break;
 		default:
 			WARN_ON_ONCE(1);
diff --git a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
index 699f2c2782ee..3cc42bef6245 100644
--- a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
+++ b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
@@ -40,7 +40,9 @@
 #define BRCM_CC_4339_CHIP_ID		0x4339
 #define BRCM_CC_43430_CHIP_ID		43430
 #define BRCM_CC_4345_CHIP_ID		0x4345
+#define BRCM_CC_43465_CHIP_ID		43465
 #define BRCM_CC_4350_CHIP_ID		0x4350
+#define BRCM_CC_43525_CHIP_ID		43525
 #define BRCM_CC_4354_CHIP_ID		0x4354
 #define BRCM_CC_4356_CHIP_ID		0x4356
 #define BRCM_CC_43566_CHIP_ID		43566
diff --git a/drivers/net/wireless/broadcom/brcm80211/include/brcmu_d11.h b/drivers/net/wireless/broadcom/brcm80211/include/brcmu_d11.h
index f9745ea8b3e0..8b8b2ecb3199 100644
--- a/drivers/net/wireless/broadcom/brcm80211/include/brcmu_d11.h
+++ b/drivers/net/wireless/broadcom/brcm80211/include/brcmu_d11.h
@@ -125,14 +125,36 @@ enum brcmu_chan_sb {
 	BRCMU_CHAN_SB_UU = BRCMU_CHAN_SB_LUU,
 };
 
+/**
+ * struct brcmu_chan - stores channel formats
+ *
+ * This structure can be used with functions translating chanspec into generic
+ * channel info and the other way.
+ *
+ * @chspec: firmware specific format
+ * @chnum: center channel number
+ * @control_ch_num: control channel number
+ * @band: frequency band
+ * @bw: channel width
+ * @sb: control sideband (location of control channel against the center one)
+ */
 struct brcmu_chan {
 	u16 chspec;
 	u8 chnum;
+	u8 control_ch_num;
 	u8 band;
 	enum brcmu_chan_bw bw;
 	enum brcmu_chan_sb sb;
 };
 
+/**
+ * struct brcmu_d11inf - provides functions translating channel format
+ *
+ * @io_type: determines version of channel format used by firmware
+ * @encchspec: encodes channel info into a chanspec, requires center channel
+ *	number, ignores control one
+ * @decchspec: decodes chanspec into generic info
+ */
 struct brcmu_d11inf {
 	u8 io_type;
 
diff --git a/drivers/net/wireless/intel/iwlegacy/3945.c b/drivers/net/wireless/intel/iwlegacy/3945.c
index 7bcedbb53d94..209dc9988455 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945.c
@@ -1019,12 +1019,13 @@ il3945_hw_txq_ctx_free(struct il_priv *il)
 	int txq_id;
 
 	/* Tx queues */
-	if (il->txq)
+	if (il->txq) {
 		for (txq_id = 0; txq_id < il->hw_params.max_txq_num; txq_id++)
 			if (txq_id == IL39_CMD_QUEUE_NUM)
 				il_cmd_queue_free(il);
 			else
 				il_tx_queue_free(il, txq_id);
+	}
 
 	/* free tx queue structure */
 	il_free_txq_mem(il);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index e5f267b21316..18a8474b5760 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -3851,8 +3851,8 @@ static int iwl_mvm_mac_get_survey(struct ieee80211_hw *hw, int idx,
 	if (idx != 0)
 		return -ENOENT;
 
-	if (fw_has_capa(&mvm->fw->ucode_capa,
-			IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
+	if (!fw_has_capa(&mvm->fw->ucode_capa,
+			 IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
 		return -ENOENT;
 
 	mutex_lock(&mvm->mutex);
@@ -3898,8 +3898,8 @@ static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
 
-	if (fw_has_capa(&mvm->fw->ucode_capa,
-			IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
+	if (!fw_has_capa(&mvm->fw->ucode_capa,
+			 IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
 		return;
 
 	/* if beacon filtering isn't on mac80211 does it anyway */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index ac2c5718e454..2c61516d06ff 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -581,7 +581,7 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
 			    struct iwl_rx_mpdu_desc *desc)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
-	struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta);
+	struct iwl_mvm_sta *mvm_sta;
 	struct iwl_mvm_baid_data *baid_data;
 	struct iwl_mvm_reorder_buffer *buffer;
 	struct sk_buff *tail;
@@ -604,6 +604,8 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
 	if (WARN_ON(IS_ERR_OR_NULL(sta)))
 		return false;
 
+	mvm_sta = iwl_mvm_sta_from_mac80211(sta);
+
 	/* not a data packet */
 	if (!ieee80211_is_data_qos(hdr->frame_control) ||
 	    is_multicast_ether_addr(hdr->addr1))
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 6f609dd5c222..e78fc567ff7d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1222,7 +1222,7 @@ static int iwl_mvm_check_running_scans(struct iwl_mvm *mvm, int type)
 	return -EIO;
 }
 
-#define SCAN_TIMEOUT (16 * HZ)
+#define SCAN_TIMEOUT (20 * HZ)
 
 void iwl_mvm_scan_timeout(unsigned long data)
 {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index fea4d3437e2f..b23ab4a4504f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1852,12 +1852,18 @@ static struct iwl_mvm_sta *iwl_mvm_get_key_sta(struct iwl_mvm *mvm,
 	    mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT) {
 		u8 sta_id = mvmvif->ap_sta_id;
 
+		sta = rcu_dereference_check(mvm->fw_id_to_mac_id[sta_id],
+					    lockdep_is_held(&mvm->mutex));
+
 		/*
 		 * It is possible that the 'sta' parameter is NULL,
 		 * for example when a GTK is removed - the sta_id will then
 		 * be the AP ID, and no station was passed by mac80211.
 		 */
-		return iwl_mvm_sta_from_staid_protected(mvm, sta_id);
+		if (IS_ERR_OR_NULL(sta))
+			return NULL;
+
+		return iwl_mvm_sta_from_mac80211(sta);
 	}
 
 	return NULL;
@@ -1955,6 +1961,14 @@ static int iwl_mvm_send_sta_igtk(struct iwl_mvm *mvm,
 		struct ieee80211_key_seq seq;
 		const u8 *pn;
 
+		switch (keyconf->cipher) {
+		case WLAN_CIPHER_SUITE_AES_CMAC:
+			igtk_cmd.ctrl_flags |= cpu_to_le32(STA_KEY_FLG_CCM);
+			break;
+		default:
+			return -EINVAL;
+		}
+
 		memcpy(igtk_cmd.IGTK, keyconf->key, keyconf->keylen);
 		ieee80211_get_key_rx_seq(keyconf, 0, &seq);
 		pn = seq.aes_cmac.pn;
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 9ed0ed1bf514..a1e28a4fd658 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -30,6 +30,8 @@
 #include <linux/module.h>
 #include <linux/ktime.h>
 #include <net/genetlink.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 #include "mac80211_hwsim.h"
 
 #define WARN_QUEUE 100
@@ -250,6 +252,28 @@ static inline void hwsim_clear_chanctx_magic(struct ieee80211_chanctx_conf *c)
 	cp->magic = 0;
 }
 
+static unsigned int hwsim_net_id;
+
+static int hwsim_netgroup;
+
+struct hwsim_net {
+	int netgroup;
+};
+
+static inline int hwsim_net_get_netgroup(struct net *net)
+{
+	struct hwsim_net *hwsim_net = net_generic(net, hwsim_net_id);
+
+	return hwsim_net->netgroup;
+}
+
+static inline void hwsim_net_set_netgroup(struct net *net)
+{
+	struct hwsim_net *hwsim_net = net_generic(net, hwsim_net_id);
+
+	hwsim_net->netgroup = hwsim_netgroup++;
+}
+
 static struct class *hwsim_class;
 
 static struct net_device *hwsim_mon; /* global monitor netdev */
@@ -526,6 +550,9 @@ struct mac80211_hwsim_data {
 	 */
 	u64 group;
 
+	/* group shared by radios created in the same netns */
+	int netgroup;
+
 	int power_level;
 
 	/* difference between this hw's clock and the real clock, in usecs */
@@ -568,6 +595,7 @@ static struct genl_family hwsim_genl_family = {
 	.name = "MAC80211_HWSIM",
 	.version = 1,
 	.maxattr = HWSIM_ATTR_MAX,
+	.netnsok = true,
 };
 
 enum hwsim_multicast_groups {
@@ -1202,6 +1230,9 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw,
 		if (!(data->group & data2->group))
 			continue;
 
+		if (data->netgroup != data2->netgroup)
+			continue;
+
 		if (!hwsim_chans_compat(chan, data2->tmp_chan) &&
 		    !hwsim_chans_compat(chan, data2->channel)) {
 			ieee80211_iterate_active_interfaces_atomic(
@@ -2349,6 +2380,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 	struct ieee80211_hw *hw;
 	enum nl80211_band band;
 	const struct ieee80211_ops *ops = &mac80211_hwsim_ops;
+	struct net *net;
 	int idx;
 
 	if (WARN_ON(param->channels > 1 && !param->use_chanctx))
@@ -2366,6 +2398,13 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 		err = -ENOMEM;
 		goto failed;
 	}
+
+	if (info)
+		net = genl_info_net(info);
+	else
+		net = &init_net;
+	wiphy_net_set(hw->wiphy, net);
+
 	data = hw->priv;
 	data->hw = hw;
 
@@ -2541,6 +2580,8 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 	data->group = 1;
 	mutex_init(&data->mutex);
 
+	data->netgroup = hwsim_net_get_netgroup(net);
+
 	/* Enable frame retransmissions for lossy channels */
 	hw->max_rates = 4;
 	hw->max_rate_tries = 11;
@@ -2776,6 +2817,7 @@ static int hwsim_tx_info_frame_received_nl(struct sk_buff *skb_2,
 	if (!info->attrs[HWSIM_ATTR_ADDR_TRANSMITTER] ||
 	    !info->attrs[HWSIM_ATTR_FLAGS] ||
 	    !info->attrs[HWSIM_ATTR_COOKIE] ||
+	    !info->attrs[HWSIM_ATTR_SIGNAL] ||
 	    !info->attrs[HWSIM_ATTR_TX_INFO])
 		goto out;
 
@@ -3013,6 +3055,9 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info)
 				continue;
 		}
 
+		if (!net_eq(wiphy_net(data->hw->wiphy), genl_info_net(info)))
+			continue;
+
 		list_del(&data->list);
 		spin_unlock_bh(&hwsim_radio_lock);
 		mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy),
@@ -3039,6 +3084,9 @@ static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info)
 		if (data->idx != idx)
 			continue;
 
+		if (!net_eq(wiphy_net(data->hw->wiphy), genl_info_net(info)))
+			continue;
+
 		skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 		if (!skb) {
 			res = -ENOMEM;
@@ -3078,6 +3126,9 @@ static int hwsim_dump_radio_nl(struct sk_buff *skb,
 		if (data->idx < idx)
 			continue;
 
+		if (!net_eq(wiphy_net(data->hw->wiphy), sock_net(skb->sk)))
+			continue;
+
 		res = mac80211_hwsim_get_radio(skb, data,
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq, cb,
@@ -3117,13 +3168,13 @@ static const struct genl_ops hwsim_ops[] = {
 		.cmd = HWSIM_CMD_NEW_RADIO,
 		.policy = hwsim_genl_policy,
 		.doit = hwsim_new_radio_nl,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = HWSIM_CMD_DEL_RADIO,
 		.policy = hwsim_genl_policy,
 		.doit = hwsim_del_radio_nl,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = HWSIM_CMD_GET_RADIO,
@@ -3205,6 +3256,40 @@ failure:
 	return -EINVAL;
 }
 
+static __net_init int hwsim_init_net(struct net *net)
+{
+	hwsim_net_set_netgroup(net);
+
+	return 0;
+}
+
+static void __net_exit hwsim_exit_net(struct net *net)
+{
+	struct mac80211_hwsim_data *data, *tmp;
+
+	spin_lock_bh(&hwsim_radio_lock);
+	list_for_each_entry_safe(data, tmp, &hwsim_radios, list) {
+		if (!net_eq(wiphy_net(data->hw->wiphy), net))
+			continue;
+
+		/* Radios created in init_net are returned to init_net. */
+		if (data->netgroup == hwsim_net_get_netgroup(&init_net))
+			continue;
+
+		list_del(&data->list);
+		INIT_WORK(&data->destroy_work, destroy_radio);
+		schedule_work(&data->destroy_work);
+	}
+	spin_unlock_bh(&hwsim_radio_lock);
+}
+
+static struct pernet_operations hwsim_net_ops = {
+	.init = hwsim_init_net,
+	.exit = hwsim_exit_net,
+	.id   = &hwsim_net_id,
+	.size = sizeof(struct hwsim_net),
+};
+
 static void hwsim_exit_netlink(void)
 {
 	/* unregister the notifier */
@@ -3241,10 +3326,14 @@ static int __init init_mac80211_hwsim(void)
 	spin_lock_init(&hwsim_radio_lock);
 	INIT_LIST_HEAD(&hwsim_radios);
 
-	err = platform_driver_register(&mac80211_hwsim_driver);
+	err = register_pernet_device(&hwsim_net_ops);
 	if (err)
 		return err;
 
+	err = platform_driver_register(&mac80211_hwsim_driver);
+	if (err)
+		goto out_unregister_pernet;
+
 	hwsim_class = class_create(THIS_MODULE, "mac80211_hwsim");
 	if (IS_ERR(hwsim_class)) {
 		err = PTR_ERR(hwsim_class);
@@ -3362,6 +3451,8 @@ out_free_radios:
 	mac80211_hwsim_free();
 out_unregister_driver:
 	platform_driver_unregister(&mac80211_hwsim_driver);
+out_unregister_pernet:
+	unregister_pernet_device(&hwsim_net_ops);
 	return err;
 }
 module_init(init_mac80211_hwsim);
@@ -3375,5 +3466,6 @@ static void __exit exit_mac80211_hwsim(void)
 	mac80211_hwsim_free();
 	unregister_netdev(hwsim_mon);
 	platform_driver_unregister(&mac80211_hwsim_driver);
+	unregister_pernet_device(&hwsim_net_ops);
 }
 module_exit(exit_mac80211_hwsim);
diff --git a/drivers/net/wireless/marvell/libertas/if_sdio.c b/drivers/net/wireless/marvell/libertas/if_sdio.c
index 13eae9ff8c35..47f4a14c84fe 100644
--- a/drivers/net/wireless/marvell/libertas/if_sdio.c
+++ b/drivers/net/wireless/marvell/libertas/if_sdio.c
@@ -1228,7 +1228,7 @@ static int if_sdio_probe(struct sdio_func *func,
 	}
 
 	spin_lock_init(&card->lock);
-	card->workqueue = create_workqueue("libertas_sdio");
+	card->workqueue = alloc_workqueue("libertas_sdio", WQ_MEM_RECLAIM, 0);
 	INIT_WORK(&card->packet_worker, if_sdio_host_to_card_worker);
 	init_waitqueue_head(&card->pwron_waitq);
 
@@ -1326,7 +1326,6 @@ static void if_sdio_remove(struct sdio_func *func)
 	lbs_stop_card(card->priv);
 	lbs_remove_card(card->priv);
 
-	flush_workqueue(card->workqueue);
 	destroy_workqueue(card->workqueue);
 
 	while (card->packets) {
diff --git a/drivers/net/wireless/marvell/libertas/if_spi.c b/drivers/net/wireless/marvell/libertas/if_spi.c
index 82c0796377aa..c3a53cd6988e 100644
--- a/drivers/net/wireless/marvell/libertas/if_spi.c
+++ b/drivers/net/wireless/marvell/libertas/if_spi.c
@@ -1180,7 +1180,7 @@ static int if_spi_probe(struct spi_device *spi)
 	priv->fw_ready = 1;
 
 	/* Initialize interrupt handling stuff. */
-	card->workqueue = create_workqueue("libertas_spi");
+	card->workqueue = alloc_workqueue("libertas_spi", WQ_MEM_RECLAIM, 0);
 	INIT_WORK(&card->packet_work, if_spi_host_to_card_worker);
 	INIT_WORK(&card->resume_work, if_spi_resume_worker);
 
@@ -1208,7 +1208,6 @@ static int if_spi_probe(struct spi_device *spi)
 release_irq:
 	free_irq(spi->irq, card);
 terminate_workqueue:
-	flush_workqueue(card->workqueue);
 	destroy_workqueue(card->workqueue);
 	lbs_remove_card(priv); /* will call free_netdev */
 free_card:
@@ -1235,7 +1234,6 @@ static int libertas_spi_remove(struct spi_device *spi)
 	lbs_remove_card(priv); /* will call free_netdev */
 
 	free_irq(spi->irq, card);
-	flush_workqueue(card->workqueue);
 	destroy_workqueue(card->workqueue);
 	if (card->pdata->teardown)
 		card->pdata->teardown(spi);
diff --git a/drivers/net/wireless/marvell/libertas_tf/main.c b/drivers/net/wireless/marvell/libertas_tf/main.c
index 0bf8916a02cf..75bf0c8a2f6f 100644
--- a/drivers/net/wireless/marvell/libertas_tf/main.c
+++ b/drivers/net/wireless/marvell/libertas_tf/main.c
@@ -16,7 +16,6 @@
 #include <linux/module.h>
 #include "libertas_tf.h"
 
-#define DRIVER_RELEASE_VERSION "004.p0"
 /* thinfirm version: 5.132.X.pX */
 #define LBTF_FW_VER_MIN		0x05840300
 #define LBTF_FW_VER_MAX		0x0584ffff
@@ -27,12 +26,6 @@ unsigned int lbtf_debug;
 EXPORT_SYMBOL_GPL(lbtf_debug);
 module_param_named(libertas_tf_debug, lbtf_debug, int, 0644);
 
-static const char lbtf_driver_version[] = "THINFIRM-USB8388-" DRIVER_RELEASE_VERSION
-#ifdef DEBUG
-	"-dbg"
-#endif
-	"";
-
 struct workqueue_struct *lbtf_wq;
 
 static const struct ieee80211_channel lbtf_channels[] = {
diff --git a/drivers/net/wireless/marvell/mwifiex/11n_aggr.c b/drivers/net/wireless/marvell/mwifiex/11n_aggr.c
index 1efef3b8273d..dc49c3de1f25 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n_aggr.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n_aggr.c
@@ -184,7 +184,7 @@ mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv,
 
 	tx_info_src = MWIFIEX_SKB_TXCB(skb_src);
 	skb_aggr = mwifiex_alloc_dma_align_buf(adapter->tx_buf_size,
-					       GFP_ATOMIC | GFP_DMA);
+					       GFP_ATOMIC);
 	if (!skb_aggr) {
 		spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock,
 				       ra_list_flags);
diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c
index 78c532f0d286..a6d86d4ccd22 100644
--- a/drivers/net/wireless/marvell/mwifiex/init.c
+++ b/drivers/net/wireless/marvell/mwifiex/init.c
@@ -788,3 +788,4 @@ poll_fw:
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(mwifiex_dnld_fw);
diff --git a/drivers/net/wireless/marvell/mwifiex/join.c b/drivers/net/wireless/marvell/mwifiex/join.c
index 62211fca91b7..a4b773d102b3 100644
--- a/drivers/net/wireless/marvell/mwifiex/join.c
+++ b/drivers/net/wireless/marvell/mwifiex/join.c
@@ -1281,7 +1281,7 @@ int mwifiex_ret_802_11_ad_hoc(struct mwifiex_private *priv,
 	if (result) {
 		mwifiex_dbg(priv->adapter, ERROR, "ADHOC_RESP: failed\n");
 		if (priv->media_connected)
-			mwifiex_reset_connect_state(priv, result);
+			mwifiex_reset_connect_state(priv, result, true);
 
 		memset(&priv->curr_bss_params.bss_descriptor,
 		       0x00, sizeof(struct mwifiex_bssdescriptor));
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 8b67a552a690..0e280f879b58 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -526,10 +526,12 @@ static void mwifiex_fw_dpc(const struct firmware *firmware, void *context)
 	fw.fw_buf = (u8 *) adapter->firmware->data;
 	fw.fw_len = adapter->firmware->size;
 
-	if (adapter->if_ops.dnld_fw)
+	if (adapter->if_ops.dnld_fw) {
 		ret = adapter->if_ops.dnld_fw(adapter, &fw);
-	else
+	} else {
 		ret = mwifiex_dnld_fw(adapter, &fw);
+	}
+
 	if (ret == -1)
 		goto err_dnld_fw;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index 0207af00be42..f0cd055c0b2c 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -1128,7 +1128,8 @@ int mwifiex_cmd_802_11_associate(struct mwifiex_private *priv,
 				 struct mwifiex_bssdescriptor *bss_desc);
 int mwifiex_ret_802_11_associate(struct mwifiex_private *priv,
 				 struct host_cmd_ds_command *resp);
-void mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason);
+void mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason,
+				 bool from_ap);
 u8 mwifiex_band_to_radio_type(u8 band);
 int mwifiex_deauthenticate(struct mwifiex_private *priv, u8 *mac);
 void mwifiex_deauthenticate_all(struct mwifiex_adapter *adapter);
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c
index 0c7937eb6b77..1b1e266ce00f 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.c
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.c
@@ -507,7 +507,7 @@ static int mwifiex_init_rxq_ring(struct mwifiex_adapter *adapter)
 	for (i = 0; i < MWIFIEX_MAX_TXRX_BD; i++) {
 		/* Allocate skb here so that firmware can DMA data from it */
 		skb = mwifiex_alloc_dma_align_buf(MWIFIEX_RX_DATA_BUF_SIZE,
-						  GFP_KERNEL | GFP_DMA);
+						  GFP_KERNEL);
 		if (!skb) {
 			mwifiex_dbg(adapter, ERROR,
 				    "Unable to allocate skb for RX ring.\n");
@@ -1319,7 +1319,7 @@ static int mwifiex_pcie_process_recv_data(struct mwifiex_adapter *adapter)
 		}
 
 		skb_tmp = mwifiex_alloc_dma_align_buf(MWIFIEX_RX_DATA_BUF_SIZE,
-						      GFP_KERNEL | GFP_DMA);
+						      GFP_KERNEL);
 		if (!skb_tmp) {
 			mwifiex_dbg(adapter, ERROR,
 				    "Unable to allocate skb.\n");
@@ -2804,7 +2804,7 @@ static int mwifiex_pcie_request_irq(struct mwifiex_adapter *adapter)
 }
 
 /*
- * This function get firmare name for downloading by revision id
+ * This function gets the firmware name for downloading by revision id
  *
  * Read revision id register to get revision id
  */
@@ -2901,10 +2901,11 @@ static void mwifiex_unregister_dev(struct mwifiex_adapter *adapter)
 {
 	struct pcie_service_card *card = adapter->card;
 	const struct mwifiex_pcie_card_reg *reg;
-	struct pci_dev *pdev = card->dev;
+	struct pci_dev *pdev;
 	int i;
 
 	if (card) {
+		pdev = card->dev;
 		if (card->msix_enable) {
 			for (i = 0; i < MWIFIEX_NUM_MSIX_VECTORS; i++)
 				synchronize_irq(card->msix_entries[i].vector);
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c
index bdc51ffd43ec..d3e1561ca075 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.c
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.c
@@ -102,10 +102,9 @@ static int mwifiex_sdio_probe_of(struct device *dev, struct sdio_mmc_card *card)
 	struct mwifiex_plt_wake_cfg *cfg;
 	int ret;
 
-	if (!dev->of_node ||
-	    !of_match_node(mwifiex_sdio_of_match_table, dev->of_node)) {
-		dev_err(dev, "sdio platform data not available\n");
-		return -1;
+	if (!of_match_node(mwifiex_sdio_of_match_table, dev->of_node)) {
+		dev_err(dev, "required compatible string missing\n");
+		return -EINVAL;
 	}
 
 	card->plt_of_node = dev->of_node;
@@ -115,7 +114,7 @@ static int mwifiex_sdio_probe_of(struct device *dev, struct sdio_mmc_card *card)
 	if (cfg && card->plt_of_node) {
 		cfg->irq_wifi = irq_of_parse_and_map(card->plt_of_node, 0);
 		if (!cfg->irq_wifi) {
-			dev_err(dev,
+			dev_dbg(dev,
 				"fail to parse irq_wifi from device tree\n");
 		} else {
 			ret = devm_request_irq(dev, cfg->irq_wifi,
@@ -183,24 +182,35 @@ mwifiex_sdio_probe(struct sdio_func *func, const struct sdio_device_id *id)
 	sdio_release_host(func);
 
 	if (ret) {
-		pr_err("%s: failed to enable function\n", __func__);
-		kfree(card);
-		return -EIO;
+		dev_err(&func->dev, "failed to enable function\n");
+		goto err_free;
 	}
 
 	/* device tree node parsing and platform specific configuration*/
-	mwifiex_sdio_probe_of(&func->dev, card);
-
-	if (mwifiex_add_card(card, &add_remove_card_sem, &sdio_ops,
-			     MWIFIEX_SDIO)) {
-		pr_err("%s: add card failed\n", __func__);
-		kfree(card);
-		sdio_claim_host(func);
-		ret = sdio_disable_func(func);
-		sdio_release_host(func);
-		ret = -1;
+	if (func->dev.of_node) {
+		ret = mwifiex_sdio_probe_of(&func->dev, card);
+		if (ret) {
+			dev_err(&func->dev, "SDIO dt node parse failed\n");
+			goto err_disable;
+		}
+	}
+
+	ret = mwifiex_add_card(card, &add_remove_card_sem, &sdio_ops,
+			       MWIFIEX_SDIO);
+	if (ret) {
+		dev_err(&func->dev, "add card failed\n");
+		goto err_disable;
 	}
 
+	return 0;
+
+err_disable:
+	sdio_claim_host(func);
+	sdio_disable_func(func);
+	sdio_release_host(func);
+err_free:
+	kfree(card);
+
 	return ret;
 }
 
@@ -544,6 +554,19 @@ static int mwifiex_pm_wakeup_card_complete(struct mwifiex_adapter *adapter)
 	return mwifiex_write_reg(adapter, CONFIGURATION_REG, 0);
 }
 
+static int mwifiex_sdio_dnld_fw(struct mwifiex_adapter *adapter,
+			struct mwifiex_fw_image *fw)
+{
+	struct sdio_mmc_card *card = adapter->card;
+	int ret;
+
+	sdio_claim_host(card->func);
+	ret = mwifiex_dnld_fw(adapter, fw);
+	sdio_release_host(card->func);
+
+	return ret;
+}
+
 /*
  * This function is used to initialize IO ports for the
  * chipsets supporting SDIO new mode eg SD8897.
@@ -1492,7 +1515,7 @@ rx_curr_single:
 		mwifiex_dbg(adapter, INFO, "info: RX: port: %d, rx_len: %d\n",
 			    port, rx_len);
 
-		skb = mwifiex_alloc_dma_align_buf(rx_len, GFP_KERNEL | GFP_DMA);
+		skb = mwifiex_alloc_dma_align_buf(rx_len, GFP_KERNEL);
 		if (!skb) {
 			mwifiex_dbg(adapter, ERROR,
 				    "single skb allocated fail,\t"
@@ -1597,7 +1620,7 @@ static int mwifiex_process_int_status(struct mwifiex_adapter *adapter)
 		rx_len = (u16) (rx_blocks * MWIFIEX_SDIO_BLOCK_SIZE);
 		mwifiex_dbg(adapter, INFO, "info: rx_len = %d\n", rx_len);
 
-		skb = mwifiex_alloc_dma_align_buf(rx_len, GFP_KERNEL | GFP_DMA);
+		skb = mwifiex_alloc_dma_align_buf(rx_len, GFP_KERNEL);
 		if (!skb)
 			return -1;
 
@@ -2732,6 +2755,7 @@ static struct mwifiex_if_ops sdio_ops = {
 	.cleanup_mpa_buf = mwifiex_cleanup_mpa_buf,
 	.cmdrsp_complete = mwifiex_sdio_cmdrsp_complete,
 	.event_complete = mwifiex_sdio_event_complete,
+	.dnld_fw = mwifiex_sdio_dnld_fw,
 	.card_reset = mwifiex_sdio_card_reset,
 	.reg_dump = mwifiex_sdio_reg_dump,
 	.device_dump = mwifiex_sdio_device_dump,
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
index d18c7979d723..bcfd4b743145 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
@@ -553,7 +553,8 @@ static int mwifiex_ret_802_11_deauthenticate(struct mwifiex_private *priv,
 	if (!memcmp(resp->params.deauth.mac_addr,
 		    &priv->curr_bss_params.bss_descriptor.mac_address,
 		    sizeof(resp->params.deauth.mac_addr)))
-		mwifiex_reset_connect_state(priv, WLAN_REASON_DEAUTH_LEAVING);
+		mwifiex_reset_connect_state(priv, WLAN_REASON_DEAUTH_LEAVING,
+					    false);
 
 	return 0;
 }
@@ -566,7 +567,7 @@ static int mwifiex_ret_802_11_deauthenticate(struct mwifiex_private *priv,
 static int mwifiex_ret_802_11_ad_hoc_stop(struct mwifiex_private *priv,
 					  struct host_cmd_ds_command *resp)
 {
-	mwifiex_reset_connect_state(priv, WLAN_REASON_DEAUTH_LEAVING);
+	mwifiex_reset_connect_state(priv, WLAN_REASON_DEAUTH_LEAVING, false);
 	return 0;
 }
 
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_event.c b/drivers/net/wireless/marvell/mwifiex/sta_event.c
index 0104108b4ea2..0cefd40b2762 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_event.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_event.c
@@ -40,8 +40,8 @@
  *      - Erases current SSID and BSSID information
  *      - Sends a disconnect event to upper layers/applications.
  */
-void
-mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason_code)
+void mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason_code,
+				 bool from_ap)
 {
 	struct mwifiex_adapter *adapter = priv->adapter;
 
@@ -140,7 +140,7 @@ mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason_code)
 	if (priv->bss_mode == NL80211_IFTYPE_STATION ||
 	    priv->bss_mode == NL80211_IFTYPE_P2P_CLIENT) {
 		cfg80211_disconnected(priv->netdev, reason_code, NULL, 0,
-				      false, GFP_KERNEL);
+				      !from_ap, GFP_KERNEL);
 	}
 	eth_zero_addr(priv->cfg_bssid);
 
@@ -574,7 +574,7 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 		if (priv->media_connected) {
 			reason_code =
 				le16_to_cpu(*(__le16 *)adapter->event_body);
-			mwifiex_reset_connect_state(priv, reason_code);
+			mwifiex_reset_connect_state(priv, reason_code, true);
 		}
 		break;
 
@@ -589,7 +589,7 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 		if (priv->media_connected) {
 			reason_code =
 				le16_to_cpu(*(__le16 *)adapter->event_body);
-			mwifiex_reset_connect_state(priv, reason_code);
+			mwifiex_reset_connect_state(priv, reason_code, true);
 		}
 		break;
 
@@ -599,7 +599,7 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 		if (priv->media_connected) {
 			reason_code =
 				le16_to_cpu(*(__le16 *)adapter->event_body);
-			mwifiex_reset_connect_state(priv, reason_code);
+			mwifiex_reset_connect_state(priv, reason_code, true);
 		}
 		break;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
index 666e91af59d7..bf5660eb27d3 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
@@ -272,7 +272,7 @@ int mwifiex_handle_uap_rx_forward(struct mwifiex_private *priv,
 int mwifiex_uap_recv_packet(struct mwifiex_private *priv,
 			    struct sk_buff *skb)
 {
-	struct mwifiex_adapter *adapter = adapter;
+	struct mwifiex_adapter *adapter = priv->adapter;
 	struct mwifiex_sta_node *src_node;
 	struct ethhdr *p_ethhdr;
 	struct sk_buff *skb_uap;
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
index fe19ace0d6a0..b04cf30f3959 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
@@ -1149,7 +1149,7 @@ static void rtl8192eu_phy_iqcalibrate(struct rtl8xxxu_priv *priv,
 
 		for (i = 0; i < retry; i++) {
 			path_b_ok = rtl8192eu_rx_iqk_path_b(priv);
-			if (path_a_ok == 0x03) {
+			if (path_b_ok == 0x03) {
 				val32 = rtl8xxxu_read32(priv,
 							REG_RX_POWER_BEFORE_IQK_B_2);
 				result[t][6] = (val32 >> 16) & 0x3ff;
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index 0f48048b8654..3a0faa8fe9d4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -54,7 +54,7 @@ EXPORT_SYMBOL(channel5g_80m);
 void rtl_addr_delay(u32 addr)
 {
 	if (addr == 0xfe)
-		msleep(50);
+		mdelay(50);
 	else if (addr == 0xfd)
 		msleep(5);
 	else if (addr == 0xfc)
@@ -75,7 +75,7 @@ void rtl_rfreg_delay(struct ieee80211_hw *hw, enum radio_path rfpath, u32 addr,
 		rtl_addr_delay(addr);
 	} else {
 		rtl_set_rfreg(hw, rfpath, addr, mask, data);
-		usleep_range(1, 2);
+		udelay(1);
 	}
 }
 EXPORT_SYMBOL(rtl_rfreg_delay);
@@ -86,7 +86,7 @@ void rtl_bb_delay(struct ieee80211_hw *hw, u32 addr, u32 data)
 		rtl_addr_delay(addr);
 	} else {
 		rtl_set_bbreg(hw, addr, MASKDWORD, data);
-		usleep_range(1, 2);
+		udelay(1);
 	}
 }
 EXPORT_SYMBOL(rtl_bb_delay);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c
index 8ee83b093c0d..e26a233684bb 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c
@@ -1839,20 +1839,22 @@ static void _rtl88ee_read_adapter_info(struct ieee80211_hw *hw)
 	u8 hwinfo[HWSET_MAX_SIZE];
 	u16 eeprom_id;
 
-	if (rtlefuse->epromtype == EEPROM_BOOT_EFUSE) {
+	switch (rtlefuse->epromtype) {
+	case EEPROM_BOOT_EFUSE:
 		rtl_efuse_shadow_map_update(hw);
+		break;
 
-		memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
-		       HWSET_MAX_SIZE);
-	} else if (rtlefuse->epromtype == EEPROM_93C46) {
+	case EEPROM_93C46:
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "RTL819X Not boot from eeprom, check it !!");
 		return;
-	} else {
+
+	default:
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "boot from neither eeprom nor efuse, check it !!");
 		return;
 	}
+	memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0], HWSET_MAX_SIZE);
 
 	RT_PRINT_DATA(rtlpriv, COMP_INIT, DBG_DMESG, "MAP\n",
 		      hwinfo, HWSET_MAX_SIZE);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c
index 04eb5c3f8464..58b7ac6899ef 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c
@@ -1680,21 +1680,28 @@ static void _rtl92ce_read_adapter_info(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	struct device *dev = &rtl_pcipriv(hw)->dev.pdev->dev;
 	u16 i, usvalue;
 	u8 hwinfo[HWSET_MAX_SIZE];
 	u16 eeprom_id;
 
-	if (rtlefuse->epromtype == EEPROM_BOOT_EFUSE) {
+	switch (rtlefuse->epromtype) {
+	case EEPROM_BOOT_EFUSE:
 		rtl_efuse_shadow_map_update(hw);
+		break;
 
-		memcpy((void *)hwinfo,
-		       (void *)&rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
-		       HWSET_MAX_SIZE);
-	} else if (rtlefuse->epromtype == EEPROM_93C46) {
+	case EEPROM_93C46:
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "RTL819X Not boot from eeprom, check it !!");
+		return;
+
+	default:
+		dev_warn(dev, "no efuse data\n");
+		return;
 	}
 
+	memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0], HWSET_MAX_SIZE);
+
 	RT_PRINT_DATA(rtlpriv, COMP_INIT, DBG_DMESG, "MAP",
 		      hwinfo, HWSET_MAX_SIZE);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c
index 34ce06441d1b..ae1129f916d5 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c
@@ -351,15 +351,21 @@ static void _rtl92cu_read_adapter_info(struct ieee80211_hw *hw)
 	u8 hwinfo[HWSET_MAX_SIZE] = {0};
 	u16 eeprom_id;
 
-	if (rtlefuse->epromtype == EEPROM_BOOT_EFUSE) {
+	switch (rtlefuse->epromtype) {
+	case EEPROM_BOOT_EFUSE:
 		rtl_efuse_shadow_map_update(hw);
-		memcpy((void *)hwinfo,
-		       (void *)&rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
-		       HWSET_MAX_SIZE);
-	} else if (rtlefuse->epromtype == EEPROM_93C46) {
+		break;
+
+	case EEPROM_93C46:
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "RTL819X Not boot from eeprom, check it !!\n");
+		return;
+
+	default:
+		pr_warn("rtl92cu: no efuse data\n\n");
+		return;
 	}
+	memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0], HWSET_MAX_SIZE);
 	RT_PRINT_DATA(rtlpriv, COMP_INIT, DBG_LOUD, "MAP",
 		      hwinfo, HWSET_MAX_SIZE);
 	eeprom_id = le16_to_cpu(*((__le16 *)&hwinfo[0]));
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
index f49b60d31450..8618c322a3f8 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
@@ -1744,23 +1744,29 @@ static void _rtl92de_read_adapter_info(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	struct device *dev = &rtl_pcipriv(hw)->dev.pdev->dev;
 	u16 i, usvalue;
 	u8 hwinfo[HWSET_MAX_SIZE];
 	u16 eeprom_id;
 	unsigned long flags;
 
-	if (rtlefuse->epromtype == EEPROM_BOOT_EFUSE) {
+	switch (rtlefuse->epromtype) {
+	case EEPROM_BOOT_EFUSE:
 		spin_lock_irqsave(&globalmutex_for_power_and_efuse, flags);
 		rtl_efuse_shadow_map_update(hw);
 		_rtl92de_efuse_update_chip_version(hw);
 		spin_unlock_irqrestore(&globalmutex_for_power_and_efuse, flags);
-		memcpy((void *)hwinfo, (void *)&rtlefuse->efuse_map
-		       [EFUSE_INIT_MAP][0],
-		       HWSET_MAX_SIZE);
-	} else if (rtlefuse->epromtype == EEPROM_93C46) {
+		break;
+	case EEPROM_93C46:
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "RTL819X Not boot from eeprom, check it !!\n");
+		return;
+	default:
+		dev_warn(dev, "no efuse data\n");
+		return;
 	}
+
+	memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0], HWSET_MAX_SIZE);
 	RT_PRINT_DATA(rtlpriv, COMP_INIT, DBG_DMESG, "MAP",
 		      hwinfo, HWSET_MAX_SIZE);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
index 9fd3f1b6e4a8..28c260dd11ea 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
@@ -2102,20 +2102,22 @@ static void _rtl92ee_read_adapter_info(struct ieee80211_hw *hw)
 	u8 hwinfo[HWSET_MAX_SIZE];
 	u16 eeprom_id;
 
-	if (rtlefuse->epromtype == EEPROM_BOOT_EFUSE) {
+	switch (rtlefuse->epromtype) {
+	case EEPROM_BOOT_EFUSE:
 		rtl_efuse_shadow_map_update(hw);
+		break;
 
-		memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
-		       HWSET_MAX_SIZE);
-	} else if (rtlefuse->epromtype == EEPROM_93C46) {
+	case EEPROM_93C46:
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "RTL819X Not boot from eeprom, check it !!");
 		return;
-	} else {
+
+	default:
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "boot from neither eeprom nor efuse, check it !!");
 		return;
 	}
+	memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0], HWSET_MAX_SIZE);
 
 	RT_PRINT_DATA(rtlpriv, COMP_INIT, DBG_DMESG, "MAP\n",
 		      hwinfo, HWSET_MAX_SIZE);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
index 018340aedf09..c2bf8d1a7af3 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
@@ -2414,19 +2414,10 @@ static void _rtl92ee_phy_reload_mac_registers(struct ieee80211_hw *hw,
 static void _rtl92ee_phy_path_adda_on(struct ieee80211_hw *hw, u32 *addareg,
 				      bool is_patha_on, bool is2t)
 {
-	u32 pathon;
 	u32 i;
 
-	pathon = is_patha_on ? 0x0fc01616 : 0x0fc01616;
-	if (!is2t) {
-		pathon = 0x0fc01616;
-		rtl_set_bbreg(hw, addareg[0], MASKDWORD, 0x0fc01616);
-	} else {
-		rtl_set_bbreg(hw, addareg[0], MASKDWORD, pathon);
-	}
-
-	for (i = 1; i < IQK_ADDA_REG_NUM; i++)
-		rtl_set_bbreg(hw, addareg[i], MASKDWORD, pathon);
+	for (i = 0; i < IQK_ADDA_REG_NUM; i++)
+		rtl_set_bbreg(hw, addareg[i], MASKDWORD, 0x0fc01616);
 }
 
 static void _rtl92ee_phy_mac_setting_calibration(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c
index 12b0978ba4fa..442f2b68ee58 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c
@@ -1673,23 +1673,31 @@ static void _rtl92se_read_adapter_info(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
+	struct device *dev = &rtl_pcipriv(hw)->dev.pdev->dev;
 	u16 i, usvalue;
 	u16	eeprom_id;
 	u8 tempval;
 	u8 hwinfo[HWSET_MAX_SIZE_92S];
 	u8 rf_path, index;
 
-	if (rtlefuse->epromtype == EEPROM_93C46) {
+	switch (rtlefuse->epromtype) {
+	case EEPROM_BOOT_EFUSE:
+		rtl_efuse_shadow_map_update(hw);
+		break;
+
+	case EEPROM_93C46:
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "RTL819X Not boot from eeprom, check it !!\n");
-	} else if (rtlefuse->epromtype == EEPROM_BOOT_EFUSE) {
-		rtl_efuse_shadow_map_update(hw);
+		return;
 
-		memcpy((void *)hwinfo, (void *)
-			&rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
-			HWSET_MAX_SIZE_92S);
+	default:
+		dev_warn(dev, "no efuse data\n");
+		return;
 	}
 
+	memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
+	       HWSET_MAX_SIZE_92S);
+
 	RT_PRINT_DATA(rtlpriv, COMP_INIT, DBG_DMESG, "MAP",
 		      hwinfo, HWSET_MAX_SIZE_92S);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
index a4b7eac6856f..57a1ba8822b1 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
@@ -1630,6 +1630,7 @@ static void _rtl8723e_read_adapter_info(struct ieee80211_hw *hw,
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	struct device *dev = &rtl_pcipriv(hw)->dev.pdev->dev;
 	u16 i, usvalue;
 	u8 hwinfo[HWSET_MAX_SIZE];
 	u16 eeprom_id;
@@ -1638,15 +1639,19 @@ static void _rtl8723e_read_adapter_info(struct ieee80211_hw *hw,
 		/* need add */
 		return;
 	}
-	if (rtlefuse->epromtype == EEPROM_BOOT_EFUSE) {
+	switch (rtlefuse->epromtype) {
+	case EEPROM_BOOT_EFUSE:
 		rtl_efuse_shadow_map_update(hw);
 
-		memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
-		       HWSET_MAX_SIZE);
-	} else if (rtlefuse->epromtype == EEPROM_93C46) {
+	case EEPROM_93C46:
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "RTL819X Not boot from eeprom, check it !!");
+		return;
+
+	default:
+		dev_warn(dev, "no efuse data\n");
 	}
+	memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0], HWSET_MAX_SIZE);
 
 	RT_PRINT_DATA(rtlpriv, COMP_INIT, DBG_DMESG, "MAP\n",
 		      hwinfo, HWSET_MAX_SIZE);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
index 5a3df9198ddf..08288ac9020a 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
@@ -2026,6 +2026,7 @@ static void _rtl8723be_read_adapter_info(struct ieee80211_hw *hw,
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	struct device *dev = &rtl_pcipriv(hw)->dev.pdev->dev;
 	u16 i, usvalue;
 	u8 hwinfo[HWSET_MAX_SIZE];
 	u16 eeprom_id;
@@ -2055,15 +2056,22 @@ static void _rtl8723be_read_adapter_info(struct ieee80211_hw *hw,
 		/* needs to be added */
 		return;
 	}
-	if (rtlefuse->epromtype == EEPROM_BOOT_EFUSE) {
+
+	switch (rtlefuse->epromtype) {
+	case EEPROM_BOOT_EFUSE:
 		rtl_efuse_shadow_map_update(hw);
+		break;
 
-		memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
-		       HWSET_MAX_SIZE);
-	} else if (rtlefuse->epromtype == EEPROM_93C46) {
+	case EEPROM_93C46:
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "RTL819X Not boot from eeprom, check it !!");
+		return;
+
+	default:
+		dev_warn(dev, "no efuse data\n");
+		return;
 	}
+	memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0], HWSET_MAX_SIZE);
 	RT_PRINT_DATA(rtlpriv, COMP_INIT, DBG_DMESG, ("MAP\n"),
 		      hwinfo, HWSET_MAX_SIZE);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c
index 445f681d08c0..c5ca9dfb445c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c
@@ -1019,7 +1019,7 @@ static u8 _rtl8723be_get_txpower_index(struct ieee80211_hw *hw, u8 path,
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	u8 index = (channel - 1);
-	u8 txpower;
+	u8 txpower = 0;
 	u8 power_diff_byrate = 0;
 
 	if (channel > 14 || channel < 1) {
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
index 71e4dd9965bb..b9436df9e1ec 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
@@ -3101,6 +3101,7 @@ static void _rtl8821ae_read_adapter_info(struct ieee80211_hw *hw, bool b_pseudo_
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
 	struct rtl_pci_priv *pcipriv = rtl_pcipriv(hw);
+	struct device *dev = &rtl_pcipriv(hw)->dev.pdev->dev;
 	u16 i, usvalue;
 	u8 hwinfo[HWSET_MAX_SIZE];
 	u16 eeprom_id;
@@ -3109,14 +3110,20 @@ static void _rtl8821ae_read_adapter_info(struct ieee80211_hw *hw, bool b_pseudo_
 		;/* need add */
 	}
 
-	if (rtlefuse->epromtype == EEPROM_BOOT_EFUSE) {
+	switch (rtlefuse->epromtype) {
+	case EEPROM_BOOT_EFUSE:
 		rtl_efuse_shadow_map_update(hw);
-		memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0],
-		       HWSET_MAX_SIZE);
-	} else if (rtlefuse->epromtype == EEPROM_93C46) {
+		break;
+
+	case EEPROM_93C46:
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
 			 "RTL819X Not boot from eeprom, check it !!");
+		return;
+
+	default:
+		dev_warn(dev, "no efuse data\n");
 	}
+	memcpy(hwinfo, &rtlefuse->efuse_map[EFUSE_INIT_MAP][0], HWSET_MAX_SIZE);
 
 	RT_PRINT_DATA(rtlpriv, COMP_INIT, DBG_DMESG, "MAP\n",
 		      hwinfo, HWSET_MAX_SIZE);
diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
index 40658b62d077..35c14cc3f0d2 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
@@ -398,7 +398,7 @@ static int rsi_mgmt_pkt_to_core(struct rsi_common *common,
 			return -ENOLINK;
 
 		msg_len -= pad_bytes;
-		if ((msg_len <= 0) || (!msg)) {
+		if (msg_len <= 0) {
 			rsi_dbg(MGMT_RX_ZONE,
 				"%s: Invalid rx msg of len = %d\n",
 				__func__, msg_len);
diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c
index 13fd734b61ec..82d94f83b6b4 100644
--- a/drivers/net/wireless/wl3501_cs.c
+++ b/drivers/net/wireless/wl3501_cs.c
@@ -378,8 +378,7 @@ static int wl3501_esbq_exec(struct wl3501_card *this, void *sig, int sig_size)
 	return rc;
 }
 
-static int wl3501_get_mib_value(struct wl3501_card *this, u8 index,
-				void *bf, int size)
+static int wl3501_request_mib(struct wl3501_card *this, u8 index, void *bf)
 {
 	struct wl3501_get_req sig = {
 		.sig_id	    = WL3501_SIG_GET_REQ,
@@ -395,20 +394,32 @@ static int wl3501_get_mib_value(struct wl3501_card *this, u8 index,
 			wl3501_set_to_wla(this, ptr, &sig, sizeof(sig));
 			wl3501_esbq_req(this, &ptr);
 			this->sig_get_confirm.mib_status = 255;
-			spin_unlock_irqrestore(&this->lock, flags);
-			rc = wait_event_interruptible(this->wait,
-				this->sig_get_confirm.mib_status != 255);
-			if (!rc)
-				memcpy(bf, this->sig_get_confirm.mib_value,
-				       size);
-			goto out;
+			rc = 0;
 		}
 	}
 	spin_unlock_irqrestore(&this->lock, flags);
-out:
+
 	return rc;
 }
 
+static int wl3501_get_mib_value(struct wl3501_card *this, u8 index,
+				void *bf, int size)
+{
+	int rc;
+
+	rc = wl3501_request_mib(this, index, bf);
+	if (rc)
+		return rc;
+
+	rc = wait_event_interruptible(this->wait,
+		this->sig_get_confirm.mib_status != 255);
+	if (rc)
+		return rc;
+
+	memcpy(bf, this->sig_get_confirm.mib_value, size);
+	return 0;
+}
+
 static int wl3501_pwr_mgmt(struct wl3501_card *this, int suspend)
 {
 	struct wl3501_pwr_mgmt_req sig = {
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 78dca3193ca4..befac5b19490 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1679,9 +1679,14 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 
 static void nvme_dev_unmap(struct nvme_dev *dev)
 {
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+	int bars;
+
 	if (dev->bar)
 		iounmap(dev->bar);
-	pci_release_regions(to_pci_dev(dev->dev));
+
+	bars = pci_select_bars(pdev, IORESOURCE_MEM);
+	pci_release_selected_regions(pdev, bars);
 }
 
 static void nvme_pci_disable(struct nvme_dev *dev)
@@ -1924,7 +1929,7 @@ static int nvme_dev_map(struct nvme_dev *dev)
 
        return 0;
   release:
-       pci_release_regions(pdev);
+       pci_release_selected_regions(pdev, bars);
        return -ENODEV;
 }
 
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index b3bec3aaa45d..bc07ad30c9bf 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -74,6 +74,7 @@ config OF_NET
 config OF_MDIO
 	def_tristate PHYLIB
 	depends on PHYLIB
+	select FIXED_PHY
 	help
 	  OpenFirmware MDIO bus (Ethernet PHY) accessors
 
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 14f2f8c7c260..33daffc4392c 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -395,7 +395,7 @@ static int unflatten_dt_nodes(const void *blob,
 			      struct device_node **nodepp)
 {
 	struct device_node *root;
-	int offset = 0, depth = 0;
+	int offset = 0, depth = 0, initial_depth = 0;
 #define FDT_MAX_DEPTH	64
 	unsigned int fpsizes[FDT_MAX_DEPTH];
 	struct device_node *nps[FDT_MAX_DEPTH];
@@ -405,11 +405,22 @@ static int unflatten_dt_nodes(const void *blob,
 	if (nodepp)
 		*nodepp = NULL;
 
+	/*
+	 * We're unflattening device sub-tree if @dad is valid. There are
+	 * possibly multiple nodes in the first level of depth. We need
+	 * set @depth to 1 to make fdt_next_node() happy as it bails
+	 * immediately when negative @depth is found. Otherwise, the device
+	 * nodes except the first one won't be unflattened successfully.
+	 */
+	if (dad)
+		depth = initial_depth = 1;
+
 	root = dad;
 	fpsizes[depth] = dad ? strlen(of_node_full_name(dad)) : 0;
 	nps[depth] = dad;
+
 	for (offset = 0;
-	     offset >= 0 && depth >= 0;
+	     offset >= 0 && depth >= initial_depth;
 	     offset = fdt_next_node(blob, offset, &depth)) {
 		if (WARN_ON_ONCE(depth >= FDT_MAX_DEPTH))
 			continue;
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index e7bfc175b8e1..6ec743faabe8 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -386,13 +386,13 @@ int of_irq_to_resource(struct device_node *dev, int index, struct resource *r)
 EXPORT_SYMBOL_GPL(of_irq_to_resource);
 
 /**
- * of_irq_get - Decode a node's IRQ and return it as a Linux irq number
+ * of_irq_get - Decode a node's IRQ and return it as a Linux IRQ number
  * @dev: pointer to device tree node
- * @index: zero-based index of the irq
- *
- * Returns Linux irq number on success, or -EPROBE_DEFER if the irq domain
- * is not yet created.
+ * @index: zero-based index of the IRQ
  *
+ * Returns Linux IRQ number on success, or 0 on the IRQ mapping failure, or
+ * -EPROBE_DEFER if the IRQ domain is not yet created, or error code in case
+ * of any other failure.
  */
 int of_irq_get(struct device_node *dev, int index)
 {
@@ -413,12 +413,13 @@ int of_irq_get(struct device_node *dev, int index)
 EXPORT_SYMBOL_GPL(of_irq_get);
 
 /**
- * of_irq_get_byname - Decode a node's IRQ and return it as a Linux irq number
+ * of_irq_get_byname - Decode a node's IRQ and return it as a Linux IRQ number
  * @dev: pointer to device tree node
- * @name: irq name
+ * @name: IRQ name
  *
- * Returns Linux irq number on success, or -EPROBE_DEFER if the irq domain
- * is not yet created, or error code in case of any other failure.
+ * Returns Linux IRQ number on success, or 0 on the IRQ mapping failure, or
+ * -EPROBE_DEFER if the IRQ domain is not yet created, or error code in case
+ * of any other failure.
  */
 int of_irq_get_byname(struct device_node *dev, const char *name)
 {
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index e051e1b57609..e2b50bc12f23 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -361,7 +361,6 @@ struct phy_device *of_phy_attach(struct net_device *dev,
 }
 EXPORT_SYMBOL(of_phy_attach);
 
-#if defined(CONFIG_FIXED_PHY)
 /*
  * of_phy_is_fixed_link() and of_phy_register_fixed_link() must
  * support two DT bindings:
@@ -451,4 +450,3 @@ int of_phy_register_fixed_link(struct device_node *np)
 	return -ENODEV;
 }
 EXPORT_SYMBOL(of_phy_register_fixed_link);
-#endif
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index ed01c0172e4a..216648233874 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -127,8 +127,15 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
 	}
 
 	/* Need adjust the alignment to satisfy the CMA requirement */
-	if (IS_ENABLED(CONFIG_CMA) && of_flat_dt_is_compatible(node, "shared-dma-pool"))
-		align = max(align, (phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order));
+	if (IS_ENABLED(CONFIG_CMA)
+	    && of_flat_dt_is_compatible(node, "shared-dma-pool")
+	    && of_get_flat_dt_prop(node, "reusable", NULL)
+	    && !of_get_flat_dt_prop(node, "no-map", NULL)) {
+		unsigned long order =
+			max_t(unsigned long, MAX_ORDER - 1, pageblock_order);
+
+		align = max(align, (phys_addr_t)PAGE_SIZE << order);
+	}
 
 	prop = of_get_flat_dt_prop(node, "alloc-ranges", &len);
 	if (prop) {
diff --git a/drivers/pci/vc.c b/drivers/pci/vc.c
index dfbab61a1b47..1fa3a3219c45 100644
--- a/drivers/pci/vc.c
+++ b/drivers/pci/vc.c
@@ -221,9 +221,9 @@ static int pci_vc_do_save_buffer(struct pci_dev *dev, int pos,
 		else
 			pci_write_config_word(dev, pos + PCI_VC_PORT_CTRL,
 					      *(u16 *)buf);
-		buf += 2;
+		buf += 4;
 	}
-	len += 2;
+	len += 4;
 
 	/*
 	 * If we have any Low Priority VCs and a VC Arbitration Table Offset
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index f2d01d4d9364..140436a046c0 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -950,17 +950,14 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu)
 
 		/* For SPIs, we need to track the affinity per IRQ */
 		if (using_spi) {
-			if (i >= pdev->num_resources) {
-				of_node_put(dn);
+			if (i >= pdev->num_resources)
 				break;
-			}
 
 			irqs[i] = cpu;
 		}
 
 		/* Keep track of the CPUs containing this PMU type */
 		cpumask_set_cpu(cpu, &pmu->supported_cpus);
-		of_node_put(dn);
 		i++;
 	} while (1);
 
@@ -995,9 +992,6 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 
 	armpmu_init(pmu);
 
-	if (!__oprofile_cpu_pmu)
-		__oprofile_cpu_pmu = pmu;
-
 	pmu->plat_device = pdev;
 
 	if (node && (of_id = of_match_node(of_table, pdev->dev.of_node))) {
@@ -1016,8 +1010,8 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 		if (!ret)
 			ret = init_fn(pmu);
 	} else {
-		ret = probe_current_pmu(pmu, probe_table);
 		cpumask_setall(&pmu->supported_cpus);
+		ret = probe_current_pmu(pmu, probe_table);
 	}
 
 	if (ret) {
@@ -1033,6 +1027,9 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 	if (ret)
 		goto out_destroy;
 
+	if (!__oprofile_cpu_pmu)
+		__oprofile_cpu_pmu = pmu;
+
 	pr_info("enabled with %s PMU driver, %d counters available\n",
 			pmu->name, pmu->num_events);
 
@@ -1043,6 +1040,7 @@ out_destroy:
 out_free:
 	pr_info("%s: failed to register PMU devices!\n",
 		of_node_full_name(node));
+	kfree(pmu->irq_affinity);
 	kfree(pmu);
 	return ret;
 }
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index b869b98835f4..01fb93b4b1e4 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -434,4 +434,12 @@ config PHY_CYGNUS_PCIE
 
 source "drivers/phy/tegra/Kconfig"
 
+config PHY_NS2_PCIE
+	tristate "Broadcom Northstar2 PCIe PHY driver"
+	depends on OF && MDIO_BUS_MUX_BCM_IPROC
+	select GENERIC_PHY
+	default ARCH_BCM_IPROC
+	help
+	  Enable this to support the Broadcom Northstar2 PCIe PHY.
+	  If unsure, say N.
 endmenu
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index 9c3e73ccabc4..7aea094da3e2 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -53,5 +53,5 @@ obj-$(CONFIG_PHY_TUSB1210)		+= phy-tusb1210.o
 obj-$(CONFIG_PHY_BRCM_SATA)		+= phy-brcm-sata.o
 obj-$(CONFIG_PHY_PISTACHIO_USB)		+= phy-pistachio-usb.o
 obj-$(CONFIG_PHY_CYGNUS_PCIE)		+= phy-bcm-cygnus-pcie.o
-
 obj-$(CONFIG_ARCH_TEGRA) += tegra/
+obj-$(CONFIG_PHY_NS2_PCIE)		+= phy-bcm-ns2-pcie.o
diff --git a/drivers/phy/phy-bcm-ns2-pcie.c b/drivers/phy/phy-bcm-ns2-pcie.c
new file mode 100644
index 000000000000..9513f7ab1eaa
--- /dev/null
+++ b/drivers/phy/phy-bcm-ns2-pcie.c
@@ -0,0 +1,115 @@
+/*
+ * Copyright (C) 2016 Broadcom
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/of_mdio.h>
+#include <linux/mdio.h>
+#include <linux/phy.h>
+#include <linux/phy/phy.h>
+
+struct ns2_pci_phy {
+	struct mdio_device *mdiodev;
+	struct phy *phy;
+};
+
+#define BLK_ADDR_REG_OFFSET	0x1f
+#define PLL_AFE1_100MHZ_BLK	0x2100
+#define PLL_CLK_AMP_OFFSET	0x03
+#define PLL_CLK_AMP_2P05V	0x2b18
+
+static int ns2_pci_phy_init(struct phy *p)
+{
+	struct ns2_pci_phy *phy = phy_get_drvdata(p);
+	int rc;
+
+	/* select the AFE 100MHz block page */
+	rc = mdiobus_write(phy->mdiodev->bus, phy->mdiodev->addr,
+			   BLK_ADDR_REG_OFFSET, PLL_AFE1_100MHZ_BLK);
+	if (rc)
+		goto err;
+
+	/* set the 100 MHz reference clock amplitude to 2.05 v */
+	rc = mdiobus_write(phy->mdiodev->bus, phy->mdiodev->addr,
+			   PLL_CLK_AMP_OFFSET, PLL_CLK_AMP_2P05V);
+	if (rc)
+		goto err;
+
+	return 0;
+
+err:
+	dev_err(&phy->mdiodev->dev, "Error %d writing to phy\n", rc);
+	return rc;
+}
+
+static struct phy_ops ns2_pci_phy_ops = {
+	.init = ns2_pci_phy_init,
+};
+
+static int ns2_pci_phy_probe(struct mdio_device *mdiodev)
+{
+	struct device *dev = &mdiodev->dev;
+	struct phy_provider *provider;
+	struct ns2_pci_phy *p;
+	struct phy *phy;
+
+	phy = devm_phy_create(dev, dev->of_node, &ns2_pci_phy_ops);
+	if (IS_ERR(phy)) {
+		dev_err(dev, "failed to create Phy\n");
+		return PTR_ERR(phy);
+	}
+
+	p = devm_kmalloc(dev, sizeof(struct ns2_pci_phy),
+			 GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	p->mdiodev = mdiodev;
+	dev_set_drvdata(dev, p);
+
+	p->phy = phy;
+	phy_set_drvdata(phy, p);
+
+	provider = devm_of_phy_provider_register(&phy->dev,
+						 of_phy_simple_xlate);
+	if (IS_ERR(provider)) {
+		dev_err(dev, "failed to register Phy provider\n");
+		return PTR_ERR(provider);
+	}
+
+	dev_info(dev, "%s PHY registered\n", dev_name(dev));
+
+	return 0;
+}
+
+static const struct of_device_id ns2_pci_phy_of_match[] = {
+	{ .compatible = "brcm,ns2-pcie-phy", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, ns2_pci_phy_of_match);
+
+static struct mdio_driver ns2_pci_phy_driver = {
+	.mdiodrv = {
+		.driver = {
+			.name = "phy-bcm-ns2-pci",
+			.of_match_table = ns2_pci_phy_of_match,
+		},
+	},
+	.probe = ns2_pci_phy_probe,
+};
+mdio_module_driver(ns2_pci_phy_driver);
+
+MODULE_AUTHOR("Broadcom");
+MODULE_DESCRIPTION("Broadcom Northstar2 PCI Phy driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:phy-bcm-ns2-pci");
diff --git a/drivers/phy/phy-exynos-mipi-video.c b/drivers/phy/phy-exynos-mipi-video.c
index cc093ebfda94..8b851f718123 100644
--- a/drivers/phy/phy-exynos-mipi-video.c
+++ b/drivers/phy/phy-exynos-mipi-video.c
@@ -233,8 +233,12 @@ static inline int __is_running(const struct exynos_mipi_phy_desc *data,
 			struct exynos_mipi_video_phy *state)
 {
 	u32 val;
+	int ret;
+
+	ret = regmap_read(state->regmaps[data->resetn_map], data->resetn_reg, &val);
+	if (ret)
+		return 0;
 
-	regmap_read(state->regmaps[data->resetn_map], data->resetn_reg, &val);
 	return val & data->resetn_val;
 }
 
diff --git a/drivers/phy/phy-ti-pipe3.c b/drivers/phy/phy-ti-pipe3.c
index 0a477d24cf76..bf46844dc387 100644
--- a/drivers/phy/phy-ti-pipe3.c
+++ b/drivers/phy/phy-ti-pipe3.c
@@ -293,11 +293,18 @@ static int ti_pipe3_init(struct phy *x)
 		ret = ti_pipe3_dpll_wait_lock(phy);
 	}
 
-	/* Program the DPLL only if not locked */
+	/* SATA has issues if re-programmed when locked */
 	val = ti_pipe3_readl(phy->pll_ctrl_base, PLL_STATUS);
-	if (!(val & PLL_LOCK))
-		if (ti_pipe3_dpll_program(phy))
-			return -EINVAL;
+	if ((val & PLL_LOCK) && of_device_is_compatible(phy->dev->of_node,
+							"ti,phy-pipe3-sata"))
+		return ret;
+
+	/* Program the DPLL */
+	ret = ti_pipe3_dpll_program(phy);
+	if (ret) {
+		ti_pipe3_disable_clocks(phy);
+		return -EINVAL;
+	}
 
 	return ret;
 }
diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c
index 6b6af6cba454..d9b10a39a2cf 100644
--- a/drivers/phy/phy-twl4030-usb.c
+++ b/drivers/phy/phy-twl4030-usb.c
@@ -463,7 +463,8 @@ static int twl4030_phy_power_on(struct phy *phy)
 	twl4030_usb_set_mode(twl, twl->usb_mode);
 	if (twl->usb_mode == T2_USB_MODE_ULPI)
 		twl4030_i2c_access(twl, 0);
-	schedule_delayed_work(&twl->id_workaround_work, 0);
+	twl->linkstat = MUSB_UNKNOWN;
+	schedule_delayed_work(&twl->id_workaround_work, HZ);
 
 	return 0;
 }
@@ -537,6 +538,7 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl)
 	struct twl4030_usb *twl = _twl;
 	enum musb_vbus_id_status status;
 	bool status_changed = false;
+	int err;
 
 	status = twl4030_usb_linkstat(twl);
 
@@ -567,7 +569,9 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl)
 			pm_runtime_mark_last_busy(twl->dev);
 			pm_runtime_put_autosuspend(twl->dev);
 		}
-		musb_mailbox(status);
+		err = musb_mailbox(status);
+		if (err)
+			twl->linkstat = MUSB_UNKNOWN;
 	}
 
 	/* don't schedule during sleep - irq works right then */
@@ -595,7 +599,8 @@ static int twl4030_phy_init(struct phy *phy)
 	struct twl4030_usb *twl = phy_get_drvdata(phy);
 
 	pm_runtime_get_sync(twl->dev);
-	schedule_delayed_work(&twl->id_workaround_work, 0);
+	twl->linkstat = MUSB_UNKNOWN;
+	schedule_delayed_work(&twl->id_workaround_work, HZ);
 	pm_runtime_mark_last_busy(twl->dev);
 	pm_runtime_put_autosuspend(twl->dev);
 
@@ -763,7 +768,8 @@ static int twl4030_usb_remove(struct platform_device *pdev)
 	if (cable_present(twl->linkstat))
 		pm_runtime_put_noidle(twl->dev);
 	pm_runtime_mark_last_busy(twl->dev);
-	pm_runtime_put_sync_suspend(twl->dev);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_sync(twl->dev);
 	pm_runtime_disable(twl->dev);
 
 	/* autogate 60MHz ULPI clock,
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index e4bc1151e04f..42a5c1dddfef 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -23,7 +23,7 @@ obj-$(CONFIG_PINCTRL_PISTACHIO)	+= pinctrl-pistachio.o
 obj-$(CONFIG_PINCTRL_ROCKCHIP)	+= pinctrl-rockchip.o
 obj-$(CONFIG_PINCTRL_SINGLE)	+= pinctrl-single.o
 obj-$(CONFIG_PINCTRL_SIRF)	+= sirf/
-obj-$(CONFIG_PINCTRL_TEGRA)	+= tegra/
+obj-$(CONFIG_ARCH_TEGRA)	+= tegra/
 obj-$(CONFIG_PINCTRL_TZ1090)	+= pinctrl-tz1090.o
 obj-$(CONFIG_PINCTRL_TZ1090_PDC)	+= pinctrl-tz1090-pdc.o
 obj-$(CONFIG_PINCTRL_U300)	+= pinctrl-u300.o
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 47ccfcc8a647..eccb47480e1d 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -209,9 +209,9 @@ static int imx_pmx_set(struct pinctrl_dev *pctldev, unsigned selector,
 		pin_reg = &info->pin_regs[pin_id];
 
 		if (pin_reg->mux_reg == -1) {
-			dev_err(ipctl->dev, "Pin(%s) does not support mux function\n",
+			dev_dbg(ipctl->dev, "Pin(%s) does not support mux function\n",
 				info->pins[pin_id].name);
-			return -EINVAL;
+			continue;
 		}
 
 		if (info->flags & SHARE_MUX_CONF_REG) {
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 677a811b3a6f..7abfd42e8ffd 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -401,9 +401,9 @@ static const struct byt_simple_func_mux byt_score_sata_mux[] = {
 static const unsigned int byt_score_plt_clk0_pins[] = { 96 };
 static const unsigned int byt_score_plt_clk1_pins[] = { 97 };
 static const unsigned int byt_score_plt_clk2_pins[] = { 98 };
-static const unsigned int byt_score_plt_clk4_pins[] = { 99 };
-static const unsigned int byt_score_plt_clk5_pins[] = { 100 };
-static const unsigned int byt_score_plt_clk3_pins[] = { 101 };
+static const unsigned int byt_score_plt_clk3_pins[] = { 99 };
+static const unsigned int byt_score_plt_clk4_pins[] = { 100 };
+static const unsigned int byt_score_plt_clk5_pins[] = { 101 };
 static const struct byt_simple_func_mux byt_score_plt_clk_mux[] = {
 	SIMPLE_FUNC("plt_clk", 1),
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index 207b13b618cf..a607655d7830 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -1256,9 +1256,10 @@ static void mtk_eint_irq_handler(struct irq_desc *desc)
 	const struct mtk_desc_pin *pin;
 
 	chained_irq_enter(chip, desc);
-	for (eint_num = 0; eint_num < pctl->devdata->ap_num; eint_num += 32) {
+	for (eint_num = 0;
+	     eint_num < pctl->devdata->ap_num;
+	     eint_num += 32, reg += 4) {
 		status = readl(reg);
-		reg += 4;
 		while (status) {
 			offset = __ffs(status);
 			index = eint_num + offset;
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index ccbfc325c778..38faceff2f08 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -854,7 +854,7 @@ static int nmk_gpio_get_dir(struct gpio_chip *chip, unsigned offset)
 
 	clk_enable(nmk_chip->clk);
 
-	dir = !!(readl(nmk_chip->addr + NMK_GPIO_DIR) & BIT(offset));
+	dir = !(readl(nmk_chip->addr + NMK_GPIO_DIR) & BIT(offset));
 
 	clk_disable(nmk_chip->clk);
 
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index cf9bafa10acf..bfdf720db270 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1580,6 +1580,9 @@ static inline void pcs_irq_set(struct pcs_soc_data *pcs_soc,
 		else
 			mask &= ~soc_mask;
 		pcs->write(mask, pcswi->reg);
+
+		/* flush posted write */
+		mask = pcs->read(pcswi->reg);
 		raw_spin_unlock(&pcs->lock);
 	}
 
diff --git a/drivers/pinctrl/tegra/Makefile b/drivers/pinctrl/tegra/Makefile
index a927379b6794..d9ea2be69cc4 100644
--- a/drivers/pinctrl/tegra/Makefile
+++ b/drivers/pinctrl/tegra/Makefile
@@ -1,4 +1,4 @@
-obj-y					+= pinctrl-tegra.o
+obj-$(CONFIG_PINCTRL_TEGRA)		+= pinctrl-tegra.o
 obj-$(CONFIG_PINCTRL_TEGRA20)		+= pinctrl-tegra20.o
 obj-$(CONFIG_PINCTRL_TEGRA30)		+= pinctrl-tegra30.o
 obj-$(CONFIG_PINCTRL_TEGRA114)		+= pinctrl-tegra114.o
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index c06bb85c2839..3ec0025d19e7 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -103,7 +103,6 @@ config DELL_SMBIOS
 
 config DELL_LAPTOP
 	tristate "Dell Laptop Extras"
-	depends on X86
 	depends on DELL_SMBIOS
 	depends on DMI
 	depends on BACKLIGHT_CLASS_DEVICE
@@ -505,7 +504,7 @@ config THINKPAD_ACPI_HOTKEY_POLL
 
 config SENSORS_HDAPS
 	tristate "Thinkpad Hard Drive Active Protection System (hdaps)"
-	depends on INPUT && X86
+	depends on INPUT
 	select INPUT_POLLDEV
 	default n
 	help
@@ -749,7 +748,7 @@ config TOSHIBA_WMI
 
 config ACPI_CMPC
 	tristate "CMPC Laptop Extras"
-	depends on X86 && ACPI
+	depends on ACPI
 	depends on RFKILL || RFKILL=n
 	select INPUT
 	select BACKLIGHT_CLASS_DEVICE
@@ -848,7 +847,7 @@ config INTEL_IMR
 
 config INTEL_PMC_CORE
 	bool "Intel PMC Core driver"
-	depends on X86 && PCI
+	depends on PCI
 	---help---
 	  The Intel Platform Controller Hub for Intel Core SoCs provides access
 	  to Power Management Controller registers via a PCI interface. This
@@ -860,7 +859,7 @@ config INTEL_PMC_CORE
 
 config IBM_RTL
 	tristate "Device driver to enable PRTL support"
-	depends on X86 && PCI
+	depends on PCI
 	---help---
 	 Enable support for IBM Premium Real Time Mode (PRTM).
 	 This module will allow you the enter and exit PRTM in the BIOS via
@@ -894,7 +893,6 @@ config XO15_EBOOK
 
 config SAMSUNG_LAPTOP
 	tristate "Samsung Laptop driver"
-	depends on X86
 	depends on RFKILL || RFKILL = n
 	depends on ACPI_VIDEO || ACPI_VIDEO = n
 	depends on BACKLIGHT_CLASS_DEVICE
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index 4a23fbc66b71..d1a091b93192 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -567,6 +567,7 @@ static void ideapad_sysfs_exit(struct ideapad_private *priv)
 static const struct key_entry ideapad_keymap[] = {
 	{ KE_KEY, 6,  { KEY_SWITCHVIDEOMODE } },
 	{ KE_KEY, 7,  { KEY_CAMERA } },
+	{ KE_KEY, 8,  { KEY_MICMUTE } },
 	{ KE_KEY, 11, { KEY_F16 } },
 	{ KE_KEY, 13, { KEY_WLAN } },
 	{ KE_KEY, 16, { KEY_PROG1 } },
@@ -809,6 +810,7 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data)
 				break;
 			case 13:
 			case 11:
+			case 8:
 			case 7:
 			case 6:
 				ideapad_input_report(priv, vpc_bit);
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index c3bfa1fe95bf..b65ce7519411 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -2043,6 +2043,7 @@ static int hotkey_autosleep_ack;
 
 static u32 hotkey_orig_mask;		/* events the BIOS had enabled */
 static u32 hotkey_all_mask;		/* all events supported in fw */
+static u32 hotkey_adaptive_all_mask;	/* all adaptive events supported in fw */
 static u32 hotkey_reserved_mask;	/* events better left disabled */
 static u32 hotkey_driver_mask;		/* events needed by the driver */
 static u32 hotkey_user_mask;		/* events visible to userspace */
@@ -2742,6 +2743,17 @@ static ssize_t hotkey_all_mask_show(struct device *dev,
 
 static DEVICE_ATTR_RO(hotkey_all_mask);
 
+/* sysfs hotkey all_mask ----------------------------------------------- */
+static ssize_t hotkey_adaptive_all_mask_show(struct device *dev,
+			   struct device_attribute *attr,
+			   char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%08x\n",
+			hotkey_adaptive_all_mask | hotkey_source_mask);
+}
+
+static DEVICE_ATTR_RO(hotkey_adaptive_all_mask);
+
 /* sysfs hotkey recommended_mask --------------------------------------- */
 static ssize_t hotkey_recommended_mask_show(struct device *dev,
 					    struct device_attribute *attr,
@@ -2985,6 +2997,7 @@ static struct attribute *hotkey_attributes[] __initdata = {
 	&dev_attr_wakeup_hotunplug_complete.attr,
 	&dev_attr_hotkey_mask.attr,
 	&dev_attr_hotkey_all_mask.attr,
+	&dev_attr_hotkey_adaptive_all_mask.attr,
 	&dev_attr_hotkey_recommended_mask.attr,
 #ifdef CONFIG_THINKPAD_ACPI_HOTKEY_POLL
 	&dev_attr_hotkey_source_mask.attr,
@@ -3321,20 +3334,6 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
 	if (!tp_features.hotkey)
 		return 1;
 
-	/*
-	 * Check if we have an adaptive keyboard, like on the
-	 * Lenovo Carbon X1 2014 (2nd Gen).
-	 */
-	if (acpi_evalf(hkey_handle, &hkeyv, "MHKV", "qd")) {
-		if ((hkeyv >> 8) == 2) {
-			tp_features.has_adaptive_kbd = true;
-			res = sysfs_create_group(&tpacpi_pdev->dev.kobj,
-					&adaptive_kbd_attr_group);
-			if (res)
-				goto err_exit;
-		}
-	}
-
 	quirks = tpacpi_check_quirks(tpacpi_hotkey_qtable,
 				     ARRAY_SIZE(tpacpi_hotkey_qtable));
 
@@ -3357,30 +3356,70 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
 	   A30, R30, R31, T20-22, X20-21, X22-24.  Detected by checking
 	   for HKEY interface version 0x100 */
 	if (acpi_evalf(hkey_handle, &hkeyv, "MHKV", "qd")) {
-		if ((hkeyv >> 8) != 1) {
-			pr_err("unknown version of the HKEY interface: 0x%x\n",
-			       hkeyv);
-			pr_err("please report this to %s\n", TPACPI_MAIL);
-		} else {
+		vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_HKEY,
+			    "firmware HKEY interface version: 0x%x\n",
+			    hkeyv);
+
+		switch (hkeyv >> 8) {
+		case 1:
 			/*
 			 * MHKV 0x100 in A31, R40, R40e,
 			 * T4x, X31, and later
 			 */
-			vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_HKEY,
-				"firmware HKEY interface version: 0x%x\n",
-				hkeyv);
 
 			/* Paranoia check AND init hotkey_all_mask */
 			if (!acpi_evalf(hkey_handle, &hotkey_all_mask,
 					"MHKA", "qd")) {
-				pr_err("missing MHKA handler, "
-				       "please report this to %s\n",
+				pr_err("missing MHKA handler, please report this to %s\n",
 				       TPACPI_MAIL);
 				/* Fallback: pre-init for FN+F3,F4,F12 */
 				hotkey_all_mask = 0x080cU;
 			} else {
 				tp_features.hotkey_mask = 1;
 			}
+			break;
+
+		case 2:
+			/*
+			 * MHKV 0x200 in X1, T460s, X260, T560, X1 Tablet (2016)
+			 */
+
+			/* Paranoia check AND init hotkey_all_mask */
+			if (!acpi_evalf(hkey_handle, &hotkey_all_mask,
+					"MHKA", "dd", 1)) {
+				pr_err("missing MHKA handler, please report this to %s\n",
+				       TPACPI_MAIL);
+				/* Fallback: pre-init for FN+F3,F4,F12 */
+				hotkey_all_mask = 0x080cU;
+			} else {
+				tp_features.hotkey_mask = 1;
+			}
+
+			/*
+			 * Check if we have an adaptive keyboard, like on the
+			 * Lenovo Carbon X1 2014 (2nd Gen).
+			 */
+			if (acpi_evalf(hkey_handle, &hotkey_adaptive_all_mask,
+				       "MHKA", "dd", 2)) {
+				if (hotkey_adaptive_all_mask != 0) {
+					tp_features.has_adaptive_kbd = true;
+					res = sysfs_create_group(
+						&tpacpi_pdev->dev.kobj,
+						&adaptive_kbd_attr_group);
+					if (res)
+						goto err_exit;
+				}
+			} else {
+				tp_features.has_adaptive_kbd = false;
+				hotkey_adaptive_all_mask = 0x0U;
+			}
+			break;
+
+		default:
+			pr_err("unknown version of the HKEY interface: 0x%x\n",
+			       hkeyv);
+			pr_err("please report this to %s\n", TPACPI_MAIL);
+			break;
 		}
 	}
 
diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index 456987c88baa..b13cd074c52a 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -565,11 +565,12 @@ static int power_supply_read_temp(struct thermal_zone_device *tzd,
 
 	WARN_ON(tzd == NULL);
 	psy = tzd->devdata;
-	ret = psy->desc->get_property(psy, POWER_SUPPLY_PROP_TEMP, &val);
+	ret = power_supply_get_property(psy, POWER_SUPPLY_PROP_TEMP, &val);
+	if (ret)
+		return ret;
 
 	/* Convert tenths of degree Celsius to milli degree Celsius. */
-	if (!ret)
-		*temp = val.intval * 100;
+	*temp = val.intval * 100;
 
 	return ret;
 }
@@ -612,10 +613,12 @@ static int ps_get_max_charge_cntl_limit(struct thermal_cooling_device *tcd,
 	int ret;
 
 	psy = tcd->devdata;
-	ret = psy->desc->get_property(psy,
-		POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val);
-	if (!ret)
-		*state = val.intval;
+	ret = power_supply_get_property(psy,
+			POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val);
+	if (ret)
+		return ret;
+
+	*state = val.intval;
 
 	return ret;
 }
@@ -628,10 +631,12 @@ static int ps_get_cur_chrage_cntl_limit(struct thermal_cooling_device *tcd,
 	int ret;
 
 	psy = tcd->devdata;
-	ret = psy->desc->get_property(psy,
-		POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val);
-	if (!ret)
-		*state = val.intval;
+	ret = power_supply_get_property(psy,
+			POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val);
+	if (ret)
+		return ret;
+
+	*state = val.intval;
 
 	return ret;
 }
diff --git a/drivers/power/tps65217_charger.c b/drivers/power/tps65217_charger.c
index d9f56730c735..73dfae41def8 100644
--- a/drivers/power/tps65217_charger.c
+++ b/drivers/power/tps65217_charger.c
@@ -197,6 +197,7 @@ static int tps65217_charger_probe(struct platform_device *pdev)
 {
 	struct tps65217 *tps = dev_get_drvdata(pdev->dev.parent);
 	struct tps65217_charger *charger;
+	struct power_supply_config cfg = {};
 	int ret;
 
 	dev_dbg(&pdev->dev, "%s\n", __func__);
@@ -208,9 +209,12 @@ static int tps65217_charger_probe(struct platform_device *pdev)
 	charger->tps = tps;
 	charger->dev = &pdev->dev;
 
+	cfg.of_node = pdev->dev.of_node;
+	cfg.drv_data = charger;
+
 	charger->ac = devm_power_supply_register(&pdev->dev,
 						 &tps65217_charger_desc,
-						 NULL);
+						 &cfg);
 	if (IS_ERR(charger->ac)) {
 		dev_err(&pdev->dev, "failed: power supply register\n");
 		return PTR_ERR(charger->ac);
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index dba3843c53b8..ed337a8c34ab 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -457,7 +457,8 @@ int pwm_apply_state(struct pwm_device *pwm, struct pwm_state *state)
 {
 	int err;
 
-	if (!pwm)
+	if (!pwm || !state || !state->period ||
+	    state->duty_cycle > state->period)
 		return -EINVAL;
 
 	if (!memcmp(state, &pwm->state, sizeof(*state)))
diff --git a/drivers/pwm/pwm-atmel-hlcdc.c b/drivers/pwm/pwm-atmel-hlcdc.c
index f994c7eaf41c..14fc011faa32 100644
--- a/drivers/pwm/pwm-atmel-hlcdc.c
+++ b/drivers/pwm/pwm-atmel-hlcdc.c
@@ -272,7 +272,7 @@ static int atmel_hlcdc_pwm_probe(struct platform_device *pdev)
 	chip->chip.of_pwm_n_cells = 3;
 	chip->chip.can_sleep = 1;
 
-	ret = pwmchip_add(&chip->chip);
+	ret = pwmchip_add_with_polarity(&chip->chip, PWM_POLARITY_INVERSED);
 	if (ret) {
 		clk_disable_unprepare(hlcdc->periph_clk);
 		return ret;
diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c
index d98599249a05..01695d48dd54 100644
--- a/drivers/pwm/sysfs.c
+++ b/drivers/pwm/sysfs.c
@@ -152,7 +152,7 @@ static ssize_t enable_store(struct device *child,
 		goto unlock;
 	}
 
-	pwm_apply_state(pwm, &state);
+	ret = pwm_apply_state(pwm, &state);
 
 unlock:
 	mutex_unlock(&export->lock);
diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c
index 56a17ec5b5ef..526bf23dcb49 100644
--- a/drivers/regulator/qcom_smd-regulator.c
+++ b/drivers/regulator/qcom_smd-regulator.c
@@ -140,6 +140,19 @@ static const struct regulator_ops rpm_smps_ldo_ops = {
 	.enable = rpm_reg_enable,
 	.disable = rpm_reg_disable,
 	.is_enabled = rpm_reg_is_enabled,
+	.list_voltage = regulator_list_voltage_linear_range,
+
+	.get_voltage = rpm_reg_get_voltage,
+	.set_voltage = rpm_reg_set_voltage,
+
+	.set_load = rpm_reg_set_load,
+};
+
+static const struct regulator_ops rpm_smps_ldo_ops_fixed = {
+	.enable = rpm_reg_enable,
+	.disable = rpm_reg_disable,
+	.is_enabled = rpm_reg_is_enabled,
+	.list_voltage = regulator_list_voltage_linear_range,
 
 	.get_voltage = rpm_reg_get_voltage,
 	.set_voltage = rpm_reg_set_voltage,
@@ -247,7 +260,7 @@ static const struct regulator_desc pm8941_nldo = {
 static const struct regulator_desc pm8941_lnldo = {
 	.fixed_uV = 1740000,
 	.n_voltages = 1,
-	.ops = &rpm_smps_ldo_ops,
+	.ops = &rpm_smps_ldo_ops_fixed,
 };
 
 static const struct regulator_desc pm8941_switch = {
diff --git a/drivers/regulator/tps51632-regulator.c b/drivers/regulator/tps51632-regulator.c
index 572816e30095..c139890c1514 100644
--- a/drivers/regulator/tps51632-regulator.c
+++ b/drivers/regulator/tps51632-regulator.c
@@ -94,11 +94,14 @@ static int tps51632_dcdc_set_ramp_delay(struct regulator_dev *rdev,
 		int ramp_delay)
 {
 	struct tps51632_chip *tps = rdev_get_drvdata(rdev);
-	int bit = ramp_delay/6000;
+	int bit;
 	int ret;
 
-	if (bit)
-		bit--;
+	if (ramp_delay == 0)
+		bit = 0;
+	else
+		bit = DIV_ROUND_UP(ramp_delay, 6000) - 1;
+
 	ret = regmap_write(tps->regmap, TPS51632_SLEW_REGS, BIT(bit));
 	if (ret < 0)
 		dev_err(tps->dev, "SLEW reg write failed, err %d\n", ret);
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index ec2e014e885c..bf40063de202 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -19,6 +19,7 @@
 #include <linux/seq_file.h>
 #include <linux/ethtool.h>
 #include <linux/hashtable.h>
+#include <linux/ip.h>
 
 #include <net/ipv6.h>
 #include <net/if_inet6.h>
@@ -144,6 +145,7 @@ struct qeth_perf_stats {
 	unsigned int sg_alloc_page_rx;
 	unsigned int tx_csum;
 	unsigned int tx_lin;
+	unsigned int tx_linfail;
 };
 
 /* Routing stuff */
@@ -559,7 +561,6 @@ enum qeth_ip_types {
 	QETH_IP_TYPE_NORMAL,
 	QETH_IP_TYPE_VIPA,
 	QETH_IP_TYPE_RXIP,
-	QETH_IP_TYPE_DEL_ALL_MC,
 };
 
 enum qeth_cmd_buffer_state {
@@ -740,17 +741,10 @@ struct qeth_vlan_vid {
 	unsigned short vid;
 };
 
-enum qeth_mac_disposition {
-	QETH_DISP_MAC_DELETE = 0,
-	QETH_DISP_MAC_DO_NOTHING = 1,
-	QETH_DISP_MAC_ADD = 2,
-};
-
-struct qeth_mac {
-	u8 mac_addr[OSA_ADDR_LEN];
-	u8 is_uc:1;
-	u8 disp_flag:2;
-	struct hlist_node hnode;
+enum qeth_addr_disposition {
+	QETH_DISP_ADDR_DELETE = 0,
+	QETH_DISP_ADDR_DO_NOTHING = 1,
+	QETH_DISP_ADDR_ADD = 2,
 };
 
 struct qeth_rx {
@@ -798,6 +792,8 @@ struct qeth_card {
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	struct list_head vid_list;
 	DECLARE_HASHTABLE(mac_htable, 4);
+	DECLARE_HASHTABLE(ip_htable, 4);
+	DECLARE_HASHTABLE(ip_mc_htable, 4);
 	struct work_struct kernel_thread_starter;
 	spinlock_t thread_mask_lock;
 	unsigned long thread_start_mask;
@@ -805,8 +801,6 @@ struct qeth_card {
 	unsigned long thread_running_mask;
 	struct task_struct *recovery_task;
 	spinlock_t ip_lock;
-	struct list_head ip_list;
-	struct list_head *ip_tbd_list;
 	struct qeth_ipato ipato;
 	struct list_head cmd_waiter_list;
 	/* QDIO buffer handling */
@@ -844,6 +838,19 @@ struct qeth_trap_id {
 /*some helper functions*/
 #define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "")
 
+/**
+ * qeth_get_elements_for_range() -	find number of SBALEs to cover range.
+ * @start:				Start of the address range.
+ * @end:				Address after the end of the range.
+ *
+ * Returns the number of pages, and thus QDIO buffer elements, needed to cover
+ * the specified address range.
+ */
+static inline int qeth_get_elements_for_range(addr_t start, addr_t end)
+{
+	return PFN_UP(end - 1) - PFN_DOWN(start);
+}
+
 static inline int qeth_get_micros(void)
 {
 	return (int) (get_tod_clock() >> 12);
@@ -865,6 +872,11 @@ static inline int qeth_get_ip_version(struct sk_buff *skb)
 	}
 }
 
+static inline int qeth_get_ip_protocol(struct sk_buff *skb)
+{
+	return ip_hdr(skb)->protocol;
+}
+
 static inline void qeth_put_buffer_pool_entry(struct qeth_card *card,
 		struct qeth_buffer_pool_entry *entry)
 {
@@ -981,12 +993,13 @@ int qeth_send_setassparms(struct qeth_card *, struct qeth_cmd_buffer *, __u16,
 			  int (*reply_cb)(struct qeth_card *,
 					  struct qeth_reply *, unsigned long),
 			  void *);
+int qeth_setassparms_cb(struct qeth_card *, struct qeth_reply *, unsigned long);
 struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *,
 						 enum qeth_ipa_funcs,
 						 __u16, __u16,
 						 enum qeth_prot_versions);
-int qeth_start_ipa_tx_checksum(struct qeth_card *);
-int qeth_set_rx_csum(struct qeth_card *, int);
+int qeth_set_features(struct net_device *, netdev_features_t);
+netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
 
 /* exports for OSN */
 int qeth_osn_assist(struct net_device *, void *, int);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index b7b74776e2ff..7dba6c8537a1 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1464,8 +1464,6 @@ static int qeth_setup_card(struct qeth_card *card)
 	card->thread_allowed_mask = 0;
 	card->thread_running_mask = 0;
 	INIT_WORK(&card->kernel_thread_starter, qeth_start_kernel_thread);
-	INIT_LIST_HEAD(&card->ip_list);
-	INIT_LIST_HEAD(card->ip_tbd_list);
 	INIT_LIST_HEAD(&card->cmd_waiter_list);
 	init_waitqueue_head(&card->wait_q);
 	/* initial options */
@@ -1500,11 +1498,6 @@ static struct qeth_card *qeth_alloc_card(void)
 	if (!card)
 		goto out;
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
-	card->ip_tbd_list = kzalloc(sizeof(struct list_head), GFP_KERNEL);
-	if (!card->ip_tbd_list) {
-		QETH_DBF_TEXT(SETUP, 0, "iptbdnom");
-		goto out_card;
-	}
 	if (qeth_setup_channel(&card->read))
 		goto out_ip;
 	if (qeth_setup_channel(&card->write))
@@ -1517,8 +1510,6 @@ static struct qeth_card *qeth_alloc_card(void)
 out_channel:
 	qeth_clean_channel(&card->read);
 out_ip:
-	kfree(card->ip_tbd_list);
-out_card:
 	kfree(card);
 out:
 	return NULL;
@@ -3757,6 +3748,14 @@ void qeth_qdio_output_handler(struct ccw_device *ccwdev,
 }
 EXPORT_SYMBOL_GPL(qeth_qdio_output_handler);
 
+/* We cannot use outbound queue 3 for unicast packets on HiperSockets */
+static inline int qeth_cut_iqd_prio(struct qeth_card *card, int queue_num)
+{
+	if ((card->info.type == QETH_CARD_TYPE_IQD) && (queue_num == 3))
+		return 2;
+	return queue_num;
+}
+
 /**
  * Note: Function assumes that we have 4 outbound queues.
  */
@@ -3784,9 +3783,9 @@ int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
 			return card->qdio.default_out_queue;
 		}
 		if (card->qdio.do_prio_queueing == QETH_PRIO_Q_ING_PREC)
-			return ~tos >> 6 & 3;
+			return qeth_cut_iqd_prio(card, ~tos >> 6 & 3);
 		if (tos & IPTOS_MINCOST)
-			return 3;
+			return qeth_cut_iqd_prio(card, 3);
 		if (tos & IPTOS_RELIABILITY)
 			return 2;
 		if (tos & IPTOS_THROUGHPUT)
@@ -3797,11 +3796,12 @@ int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
 	case QETH_PRIO_Q_ING_SKB:
 		if (skb->priority > 5)
 			return 0;
-		return ~skb->priority >> 1 & 3;
+		return qeth_cut_iqd_prio(card, ~skb->priority >> 1 & 3);
 	case QETH_PRIO_Q_ING_VLAN:
 		tci = &((struct ethhdr *)skb->data)->h_proto;
 		if (*tci == ETH_P_8021Q)
-			return ~*(tci + 1) >> (VLAN_PRIO_SHIFT + 1) & 3;
+			return qeth_cut_iqd_prio(card, ~*(tci + 1) >>
+			(VLAN_PRIO_SHIFT + 1) & 3);
 		break;
 	default:
 		break;
@@ -3810,41 +3810,54 @@ int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(qeth_get_priority_queue);
 
+/**
+ * qeth_get_elements_for_frags() -	find number of SBALEs for skb frags.
+ * @skb:				SKB address
+ *
+ * Returns the number of pages, and thus QDIO buffer elements, needed to cover
+ * fragmented part of the SKB. Returns zero for linear SKB.
+ */
 int qeth_get_elements_for_frags(struct sk_buff *skb)
 {
-	int cnt, length, e, elements = 0;
-	struct skb_frag_struct *frag;
-	char *data;
+	int cnt, elements = 0;
 
 	for (cnt = 0; cnt < skb_shinfo(skb)->nr_frags; cnt++) {
-		frag = &skb_shinfo(skb)->frags[cnt];
-		data = (char *)page_to_phys(skb_frag_page(frag)) +
-			frag->page_offset;
-		length = frag->size;
-		e = PFN_UP((unsigned long)data + length - 1) -
-			PFN_DOWN((unsigned long)data);
-		elements += e;
+		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[cnt];
+
+		elements += qeth_get_elements_for_range(
+			(addr_t)skb_frag_address(frag),
+			(addr_t)skb_frag_address(frag) + skb_frag_size(frag));
 	}
 	return elements;
 }
 EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
 
+/**
+ * qeth_get_elements_no() -	find number of SBALEs for skb data, inc. frags.
+ * @card:			qeth card structure, to check max. elems.
+ * @skb:			SKB address
+ * @extra_elems:		extra elems needed, to check against max.
+ *
+ * Returns the number of pages, and thus QDIO buffer elements, needed to cover
+ * skb data, including linear part and fragments. Checks if the result plus
+ * extra_elems fits under the limit for the card. Returns 0 if it does not.
+ * Note: extra_elems is not included in the returned result.
+ */
 int qeth_get_elements_no(struct qeth_card *card,
-		     struct sk_buff *skb, int elems)
+		     struct sk_buff *skb, int extra_elems)
 {
-	int dlen = skb->len - skb->data_len;
-	int elements_needed = PFN_UP((unsigned long)skb->data + dlen - 1) -
-		PFN_DOWN((unsigned long)skb->data);
-
-	elements_needed += qeth_get_elements_for_frags(skb);
+	int elements = qeth_get_elements_for_range(
+				(addr_t)skb->data,
+				(addr_t)skb->data + skb_headlen(skb)) +
+			qeth_get_elements_for_frags(skb);
 
-	if ((elements_needed + elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
+	if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
 		QETH_DBF_MESSAGE(2, "Invalid size of IP packet "
 			"(Number=%d / Length=%d). Discarded.\n",
-			(elements_needed+elems), skb->len);
+			elements + extra_elems, skb->len);
 		return 0;
 	}
-	return elements_needed;
+	return elements;
 }
 EXPORT_SYMBOL_GPL(qeth_get_elements_no);
 
@@ -3859,7 +3872,7 @@ int qeth_hdr_chk_and_bounce(struct sk_buff *skb, struct qeth_hdr **hdr, int len)
 		rest = len - inpage;
 		if (rest > hroom)
 			return 1;
-		memmove(skb->data - rest, skb->data, skb->len - skb->data_len);
+		memmove(skb->data - rest, skb->data, skb_headlen(skb));
 		skb->data -= rest;
 		skb->tail -= rest;
 		*hdr = (struct qeth_hdr *)skb->data;
@@ -3873,7 +3886,7 @@ static inline void __qeth_fill_buffer(struct sk_buff *skb,
 	struct qdio_buffer *buffer, int is_tso, int *next_element_to_fill,
 	int offset)
 {
-	int length = skb->len - skb->data_len;
+	int length = skb_headlen(skb);
 	int length_here;
 	int element;
 	char *data;
@@ -4967,7 +4980,6 @@ static void qeth_core_free_card(struct qeth_card *card)
 	qeth_clean_channel(&card->write);
 	if (card->dev)
 		free_netdev(card->dev);
-	kfree(card->ip_tbd_list);
 	qeth_free_qdio_buffers(card);
 	unregister_service_level(&card->qeth_service_level);
 	kfree(card);
@@ -5265,8 +5277,8 @@ no_mem:
 }
 EXPORT_SYMBOL_GPL(qeth_core_get_next_skb);
 
-static int qeth_setassparms_cb(struct qeth_card *card,
-			       struct qeth_reply *reply, unsigned long data)
+int qeth_setassparms_cb(struct qeth_card *card,
+			struct qeth_reply *reply, unsigned long data)
 {
 	struct qeth_ipa_cmd *cmd;
 
@@ -5294,6 +5306,7 @@ static int qeth_setassparms_cb(struct qeth_card *card,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(qeth_setassparms_cb);
 
 struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card,
 						 enum qeth_ipa_funcs ipa_func,
@@ -5788,6 +5801,7 @@ static struct {
 	{"tx do_QDIO count"},
 	{"tx csum"},
 	{"tx lin"},
+	{"tx linfail"},
 	{"cq handler count"},
 	{"cq handler time"}
 };
@@ -5848,8 +5862,9 @@ void qeth_core_get_ethtool_stats(struct net_device *dev,
 	data[32] = card->perf_stats.outbound_do_qdio_cnt;
 	data[33] = card->perf_stats.tx_csum;
 	data[34] = card->perf_stats.tx_lin;
-	data[35] = card->perf_stats.cq_cnt;
-	data[36] = card->perf_stats.cq_time;
+	data[35] = card->perf_stats.tx_linfail;
+	data[36] = card->perf_stats.cq_cnt;
+	data[37] = card->perf_stats.cq_time;
 }
 EXPORT_SYMBOL_GPL(qeth_core_get_ethtool_stats);
 
@@ -6048,74 +6063,136 @@ int qeth_core_ethtool_get_settings(struct net_device *netdev,
 }
 EXPORT_SYMBOL_GPL(qeth_core_ethtool_get_settings);
 
-static int qeth_send_checksum_command(struct qeth_card *card)
+static int qeth_send_checksum_on(struct qeth_card *card, int cstype)
 {
+	long rxtx_arg;
 	int rc;
 
-	rc = qeth_send_simple_setassparms(card, IPA_INBOUND_CHECKSUM,
-					  IPA_CMD_ASS_START, 0);
+	rc = qeth_send_simple_setassparms(card, cstype, IPA_CMD_ASS_START, 0);
 	if (rc) {
-		dev_warn(&card->gdev->dev, "Starting HW checksumming for %s "
-			"failed, using SW checksumming\n",
-			QETH_CARD_IFNAME(card));
+		dev_warn(&card->gdev->dev,
+			 "Starting HW checksumming for %s failed, using SW checksumming\n",
+			 QETH_CARD_IFNAME(card));
 		return rc;
 	}
-	rc = qeth_send_simple_setassparms(card, IPA_INBOUND_CHECKSUM,
-					  IPA_CMD_ASS_ENABLE,
-					  card->info.csum_mask);
+	rxtx_arg = (cstype == IPA_OUTBOUND_CHECKSUM) ? card->info.tx_csum_mask
+						     : card->info.csum_mask;
+	rc = qeth_send_simple_setassparms(card, cstype, IPA_CMD_ASS_ENABLE,
+					  rxtx_arg);
 	if (rc) {
-		dev_warn(&card->gdev->dev, "Enabling HW checksumming for %s "
-			"failed, using SW checksumming\n",
-			QETH_CARD_IFNAME(card));
+		dev_warn(&card->gdev->dev,
+			 "Enabling HW checksumming for %s failed, using SW checksumming\n",
+			 QETH_CARD_IFNAME(card));
 		return rc;
 	}
+
+	dev_info(&card->gdev->dev, "HW Checksumming (%sbound) enabled\n",
+		 cstype == IPA_INBOUND_CHECKSUM ? "in" : "out");
 	return 0;
 }
 
-int qeth_set_rx_csum(struct qeth_card *card, int on)
+static int qeth_set_ipa_csum(struct qeth_card *card, int on, int cstype)
 {
 	int rc;
 
 	if (on) {
-		rc = qeth_send_checksum_command(card);
+		rc = qeth_send_checksum_on(card, cstype);
 		if (rc)
 			return -EIO;
-		dev_info(&card->gdev->dev,
-			"HW Checksumming (inbound) enabled\n");
 	} else {
-		rc = qeth_send_simple_setassparms(card,
-			IPA_INBOUND_CHECKSUM, IPA_CMD_ASS_STOP, 0);
+		rc = qeth_send_simple_setassparms(card, cstype,
+						  IPA_CMD_ASS_STOP, 0);
 		if (rc)
 			return -EIO;
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(qeth_set_rx_csum);
 
-int qeth_start_ipa_tx_checksum(struct qeth_card *card)
+static int qeth_set_ipa_tso(struct qeth_card *card, int on)
 {
-	int rc = 0;
+	int rc;
 
-	if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM))
-		return rc;
-	rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_CHECKSUM,
-					  IPA_CMD_ASS_START, 0);
-	if (rc)
-		goto err_out;
-	rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_CHECKSUM,
-					  IPA_CMD_ASS_ENABLE,
-					  card->info.tx_csum_mask);
-	if (rc)
-		goto err_out;
+	QETH_CARD_TEXT(card, 3, "sttso");
 
-	dev_info(&card->gdev->dev, "HW TX Checksumming enabled\n");
-	return rc;
-err_out:
-	dev_warn(&card->gdev->dev, "Enabling HW TX checksumming for %s "
-		"failed, using SW TX checksumming\n", QETH_CARD_IFNAME(card));
+	if (on) {
+		rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_TSO,
+						  IPA_CMD_ASS_START, 0);
+		if (rc) {
+			dev_warn(&card->gdev->dev,
+				 "Starting outbound TCP segmentation offload for %s failed\n",
+				 QETH_CARD_IFNAME(card));
+			return -EIO;
+		}
+		dev_info(&card->gdev->dev, "Outbound TSO enabled\n");
+	} else {
+		rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_TSO,
+						  IPA_CMD_ASS_STOP, 0);
+	}
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_start_ipa_tx_checksum);
+
+int qeth_set_features(struct net_device *dev, netdev_features_t features)
+{
+	struct qeth_card *card = dev->ml_priv;
+	netdev_features_t changed = dev->features ^ features;
+	int rc = 0;
+
+	QETH_DBF_TEXT(SETUP, 2, "setfeat");
+	QETH_DBF_HEX(SETUP, 2, &features, sizeof(features));
+
+	if ((changed & NETIF_F_IP_CSUM)) {
+		rc = qeth_set_ipa_csum(card,
+				       features & NETIF_F_IP_CSUM ? 1 : 0,
+				       IPA_OUTBOUND_CHECKSUM);
+		if (rc)
+			changed ^= NETIF_F_IP_CSUM;
+	}
+	if ((changed & NETIF_F_RXCSUM)) {
+		rc = qeth_set_ipa_csum(card,
+					features & NETIF_F_RXCSUM ? 1 : 0,
+					IPA_INBOUND_CHECKSUM);
+		if (rc)
+			changed ^= NETIF_F_RXCSUM;
+	}
+	if ((changed & NETIF_F_TSO)) {
+		rc = qeth_set_ipa_tso(card, features & NETIF_F_TSO ? 1 : 0);
+		if (rc)
+			changed ^= NETIF_F_TSO;
+	}
+
+	/* everything changed successfully? */
+	if ((dev->features ^ features) == changed)
+		return 0;
+	/* something went wrong. save changed features and return error */
+	dev->features ^= changed;
+	return -EIO;
+}
+EXPORT_SYMBOL_GPL(qeth_set_features);
+
+netdev_features_t qeth_fix_features(struct net_device *dev,
+				    netdev_features_t features)
+{
+	struct qeth_card *card = dev->ml_priv;
+
+	QETH_DBF_TEXT(SETUP, 2, "fixfeat");
+	if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM))
+		features &= ~NETIF_F_IP_CSUM;
+	if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM))
+		features &= ~NETIF_F_RXCSUM;
+	if (!qeth_is_supported(card, IPA_OUTBOUND_TSO)) {
+		features &= ~NETIF_F_TSO;
+		dev_info(&card->gdev->dev, "Outbound TSO not supported on %s\n",
+			 QETH_CARD_IFNAME(card));
+	}
+	/* if the card isn't up, remove features that require hw changes */
+	if (card->state == CARD_STATE_DOWN ||
+	    card->state == CARD_STATE_RECOVER)
+		features = features & ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
+					NETIF_F_TSO);
+	QETH_DBF_HEX(SETUP, 2, &features, sizeof(features));
+	return features;
+}
+EXPORT_SYMBOL_GPL(qeth_fix_features);
 
 static int __init qeth_core_init(void)
 {
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index e6e5b9671bf2..75b29fd2fcf4 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -243,6 +243,10 @@ static ssize_t qeth_dev_prioqing_store(struct device *dev,
 		card->qdio.do_prio_queueing = QETH_NO_PRIO_QUEUEING;
 		card->qdio.default_out_queue = 2;
 	} else if (sysfs_streq(buf, "no_prio_queueing:3")) {
+		if (card->info.type == QETH_CARD_TYPE_IQD) {
+			rc = -EPERM;
+			goto out;
+		}
 		card->qdio.do_prio_queueing = QETH_NO_PRIO_QUEUEING;
 		card->qdio.default_out_queue = 3;
 	} else if (sysfs_streq(buf, "no_prio_queueing")) {
diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h
index 0767556404bd..29d9fb3890ad 100644
--- a/drivers/s390/net/qeth_l2.h
+++ b/drivers/s390/net/qeth_l2.h
@@ -12,4 +12,11 @@ int qeth_l2_create_device_attributes(struct device *);
 void qeth_l2_remove_device_attributes(struct device *);
 void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
 
+struct qeth_mac {
+	u8 mac_addr[OSA_ADDR_LEN];
+	u8 is_uc:1;
+	u8 disp_flag:2;
+	struct hlist_node hnode;
+};
+
 #endif /* __QETH_L2_H__ */
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 80b1979e8d95..9fd48de38a4c 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -404,38 +404,6 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev,
 	return rc;
 }
 
-static netdev_features_t qeth_l2_fix_features(struct net_device *dev,
-					      netdev_features_t features)
-{
-	struct qeth_card *card = dev->ml_priv;
-
-	QETH_DBF_TEXT(SETUP, 2, "fixfeat");
-	if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM))
-		features &= ~NETIF_F_IP_CSUM;
-	if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM))
-		features &= ~NETIF_F_RXCSUM;
-	QETH_DBF_HEX(SETUP, 2, &features, sizeof(features));
-	return features;
-}
-
-static int qeth_l2_set_features(struct net_device *dev,
-				netdev_features_t features)
-{
-	struct qeth_card *card = dev->ml_priv;
-	netdev_features_t changed = dev->features ^ features;
-
-	QETH_DBF_TEXT(SETUP, 2, "setfeat");
-	QETH_DBF_HEX(SETUP, 2, &features, sizeof(features));
-
-	if (card->state == CARD_STATE_DOWN ||
-	    card->state == CARD_STATE_RECOVER)
-		return 0;
-
-	if (!(changed & NETIF_F_RXCSUM))
-		return 0;
-	return qeth_set_rx_csum(card, features & NETIF_F_RXCSUM ? 1 : 0);
-}
-
 static void qeth_l2_stop_card(struct qeth_card *card, int recovery_mode)
 {
 	QETH_DBF_TEXT(SETUP , 2, "stopcard");
@@ -780,7 +748,7 @@ qeth_l2_add_mac(struct qeth_card *card, struct netdev_hw_addr *ha, u8 is_uc)
 			qeth_l2_mac_hash(ha->addr)) {
 		if (is_uc == mac->is_uc &&
 		    !memcmp(ha->addr, mac->mac_addr, OSA_ADDR_LEN)) {
-			mac->disp_flag = QETH_DISP_MAC_DO_NOTHING;
+			mac->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 			return;
 		}
 	}
@@ -792,7 +760,7 @@ qeth_l2_add_mac(struct qeth_card *card, struct netdev_hw_addr *ha, u8 is_uc)
 
 	memcpy(mac->mac_addr, ha->addr, OSA_ADDR_LEN);
 	mac->is_uc = is_uc;
-	mac->disp_flag = QETH_DISP_MAC_ADD;
+	mac->disp_flag = QETH_DISP_ADDR_ADD;
 
 	hash_add(card->mac_htable, &mac->hnode,
 			qeth_l2_mac_hash(mac->mac_addr));
@@ -825,7 +793,7 @@ static void qeth_l2_set_rx_mode(struct net_device *dev)
 		qeth_l2_add_mac(card, ha, 1);
 
 	hash_for_each_safe(card->mac_htable, i, tmp, mac, hnode) {
-		if (mac->disp_flag == QETH_DISP_MAC_DELETE) {
+		if (mac->disp_flag == QETH_DISP_ADDR_DELETE) {
 			if (!mac->is_uc)
 				rc = qeth_l2_send_delgroupmac(card,
 						mac->mac_addr);
@@ -837,15 +805,15 @@ static void qeth_l2_set_rx_mode(struct net_device *dev)
 			hash_del(&mac->hnode);
 			kfree(mac);
 
-		} else if (mac->disp_flag == QETH_DISP_MAC_ADD) {
+		} else if (mac->disp_flag == QETH_DISP_ADDR_ADD) {
 			rc = qeth_l2_write_mac(card, mac);
 			if (rc) {
 				hash_del(&mac->hnode);
 				kfree(mac);
 			} else
-				mac->disp_flag = QETH_DISP_MAC_DELETE;
+				mac->disp_flag = QETH_DISP_ADDR_DELETE;
 		} else
-			mac->disp_flag = QETH_DISP_MAC_DELETE;
+			mac->disp_flag = QETH_DISP_ADDR_DELETE;
 	}
 
 	spin_unlock_bh(&card->mclock);
@@ -869,6 +837,7 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	int data_offset = -1;
 	int elements_needed = 0;
 	int hd_len = 0;
+	int nr_frags;
 
 	if (card->qdio.do_prio_queueing || (cast_type &&
 					card->info.is_multicast_different))
@@ -892,6 +861,23 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 	netif_stop_queue(dev);
 
+	/* fix hardware limitation: as long as we do not have sbal
+	 * chaining we can not send long frag lists
+	 */
+	if ((card->info.type != QETH_CARD_TYPE_IQD) &&
+	    !qeth_get_elements_no(card, new_skb, 0)) {
+		int lin_rc = skb_linearize(new_skb);
+
+		if (card->options.performance_stats) {
+			if (lin_rc)
+				card->perf_stats.tx_linfail++;
+			else
+				card->perf_stats.tx_lin++;
+		}
+		if (lin_rc)
+			goto tx_drop;
+	}
+
 	if (card->info.type == QETH_CARD_TYPE_OSN)
 		hdr = (struct qeth_hdr *)skb->data;
 	else {
@@ -943,6 +929,14 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (!rc) {
 		card->stats.tx_packets++;
 		card->stats.tx_bytes += tx_bytes;
+		if (card->options.performance_stats) {
+			nr_frags = skb_shinfo(new_skb)->nr_frags;
+			if (nr_frags) {
+				card->perf_stats.sg_skbs_sent++;
+				/* nr_frags + skb->data */
+				card->perf_stats.sg_frags_sent += nr_frags + 1;
+			}
+		}
 		if (new_skb != skb)
 			dev_kfree_skb_any(skb);
 		rc = NETDEV_TX_OK;
@@ -1086,8 +1080,8 @@ static const struct net_device_ops qeth_l2_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= qeth_l2_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = qeth_l2_vlan_rx_kill_vid,
 	.ndo_tx_timeout	   	= qeth_tx_timeout,
-	.ndo_fix_features	= qeth_l2_fix_features,
-	.ndo_set_features	= qeth_l2_set_features
+	.ndo_fix_features	= qeth_fix_features,
+	.ndo_set_features	= qeth_set_features
 };
 
 static int qeth_l2_setup_netdev(struct qeth_card *card)
@@ -1118,12 +1112,25 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 		&qeth_l2_ethtool_ops : &qeth_l2_osn_ops;
 	card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
-		card->dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM;
-		/* Turn on RX offloading per default */
-		card->dev->features |= NETIF_F_RXCSUM;
+		card->dev->hw_features = NETIF_F_SG;
+		card->dev->vlan_features = NETIF_F_SG;
+		/* OSA 3S and earlier has no RX/TX support */
+		if (qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) {
+			card->dev->hw_features |= NETIF_F_IP_CSUM;
+			card->dev->vlan_features |= NETIF_F_IP_CSUM;
+		}
+		if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM)) {
+			card->dev->hw_features |= NETIF_F_RXCSUM;
+			card->dev->vlan_features |= NETIF_F_RXCSUM;
+		}
+		/* Turn on SG per default */
+		card->dev->features |= NETIF_F_SG;
 	}
 	card->info.broadcast_capable = 1;
 	qeth_l2_request_initial_mac(card);
+	card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
+				  PAGE_SIZE;
+	card->dev->gso_max_segs = (QETH_MAX_BUFFER_ELEMENTS(card) - 1);
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_l2_poll, QETH_NAPI_WEIGHT);
 	netif_carrier_off(card->dev);
@@ -1135,9 +1142,6 @@ static int qeth_l2_start_ipassists(struct qeth_card *card)
 	/* configure isolation level */
 	if (qeth_set_access_ctrl_online(card, 0))
 		return -ENODEV;
-	if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM))
-		qeth_set_rx_csum(card, 1);
-	qeth_start_ipa_tx_checksum(card);
 	return 0;
 }
 
@@ -1206,7 +1210,8 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 contin:
 	if ((card->info.type == QETH_CARD_TYPE_OSD) ||
 	    (card->info.type == QETH_CARD_TYPE_OSX)) {
-		if (qeth_l2_start_ipassists(card))
+		rc = qeth_l2_start_ipassists(card);
+		if (rc)
 			goto out_remove;
 	}
 
@@ -1800,6 +1805,12 @@ static int qeth_bridgeport_makerc(struct qeth_card *card,
 			dev_err(&card->gdev->dev,
 	"The device is not configured as a Bridge Port\n");
 			break;
+		case 0x2B10:
+		case 0x0010: /* OS mismatch */
+			rc = -EPERM;
+			dev_err(&card->gdev->dev,
+	"A Bridge Port is already configured by a different operating system\n");
+			break;
 		case 0x2B14:
 		case 0x0014: /* Another device is Primary */
 			switch (setcmd) {
diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index 551a4b4c03fd..26f79533e62e 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -10,16 +10,23 @@
 #define __QETH_L3_H__
 
 #include "qeth_core.h"
+#include <linux/hashtable.h>
 
 #define QETH_SNIFF_AVAIL	0x0008
 
 struct qeth_ipaddr {
-	struct list_head entry;
+	struct hlist_node hnode;
 	enum qeth_ip_types type;
 	enum qeth_ipa_setdelip_flags set_flags;
 	enum qeth_ipa_setdelip_flags del_flags;
-	int is_multicast;
-	int users;
+	u8 is_multicast:1;
+	u8 in_progress:1;
+	u8 disp_flag:2;
+
+	/* is changed only for normal ip addresses
+	 * for non-normal addresses it always is  1
+	 */
+	int  ref_counter;
 	enum qeth_prot_versions proto;
 	unsigned char mac[OSA_ADDR_LEN];
 	union {
@@ -32,7 +39,24 @@ struct qeth_ipaddr {
 			unsigned int pfxlen;
 		} a6;
 	} u;
+
 };
+static inline  u64 qeth_l3_ipaddr_hash(struct qeth_ipaddr *addr)
+{
+	u64  ret = 0;
+	u8 *point;
+
+	if (addr->proto == QETH_PROT_IPV6) {
+		point = (u8 *) &addr->u.a6.addr;
+		ret = get_unaligned((u64 *)point) ^
+			get_unaligned((u64 *) (point + 8));
+	}
+	if (addr->proto == QETH_PROT_IPV4) {
+		point = (u8 *) &addr->u.a4.addr;
+		ret = get_unaligned((u32 *) point);
+	}
+	return ret;
+}
 
 struct qeth_ipato_entry {
 	struct list_head entry;
@@ -60,6 +84,5 @@ int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *, struct qeth_ipaddr *);
 struct qeth_ipaddr *qeth_l3_get_addr_buffer(enum qeth_prot_versions);
 int qeth_l3_add_ip(struct qeth_card *, struct qeth_ipaddr *);
 int qeth_l3_delete_ip(struct qeth_card *, struct qeth_ipaddr *);
-void qeth_l3_set_ip_addr_list(struct qeth_card *);
 
 #endif /* __QETH_L3_H__ */
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index ac544330daeb..bcd324e054a9 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -30,6 +30,7 @@
 #include <net/ip6_fib.h>
 #include <net/ip6_checksum.h>
 #include <net/iucv/af_iucv.h>
+#include <linux/hashtable.h>
 
 #include "qeth_l3.h"
 
@@ -57,7 +58,7 @@ static int qeth_l3_isxdigit(char *buf)
 
 static void qeth_l3_ipaddr4_to_string(const __u8 *addr, char *buf)
 {
-	sprintf(buf, "%i.%i.%i.%i", addr[0], addr[1], addr[2], addr[3]);
+	sprintf(buf, "%pI4", addr);
 }
 
 static int qeth_l3_string_to_ipaddr4(const char *buf, __u8 *addr)
@@ -204,104 +205,129 @@ int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
 	return rc;
 }
 
-/*
- * Add IP to be added to todo list. If there is already an "add todo"
- * in this list we just incremenent the reference count.
- * Returns 0 if we  just incremented reference count.
- */
-static int __qeth_l3_insert_ip_todo(struct qeth_card *card,
-					struct qeth_ipaddr *addr, int add)
+inline int
+qeth_l3_ipaddrs_is_equal(struct qeth_ipaddr *addr1, struct qeth_ipaddr *addr2)
 {
-	struct qeth_ipaddr *tmp, *t;
-	int found = 0;
+	return addr1->proto == addr2->proto &&
+		!memcmp(&addr1->u, &addr2->u, sizeof(addr1->u))  &&
+		!memcmp(&addr1->mac, &addr2->mac, sizeof(addr1->mac));
+}
 
-	if (card->options.sniffer)
-		return 0;
-	list_for_each_entry_safe(tmp, t, card->ip_tbd_list, entry) {
-		if ((addr->type == QETH_IP_TYPE_DEL_ALL_MC) &&
-		    (tmp->type == QETH_IP_TYPE_DEL_ALL_MC))
-			return 0;
-		if ((tmp->proto        == QETH_PROT_IPV4)     &&
-		    (addr->proto       == QETH_PROT_IPV4)     &&
-		    (tmp->type         == addr->type)         &&
-		    (tmp->is_multicast == addr->is_multicast) &&
-		    (tmp->u.a4.addr    == addr->u.a4.addr)    &&
-		    (tmp->u.a4.mask    == addr->u.a4.mask)) {
-			found = 1;
-			break;
-		}
-		if ((tmp->proto        == QETH_PROT_IPV6)      &&
-		    (addr->proto       == QETH_PROT_IPV6)      &&
-		    (tmp->type         == addr->type)          &&
-		    (tmp->is_multicast == addr->is_multicast)  &&
-		    (tmp->u.a6.pfxlen  == addr->u.a6.pfxlen)   &&
-		    (memcmp(&tmp->u.a6.addr, &addr->u.a6.addr,
-			    sizeof(struct in6_addr)) == 0)) {
-			found = 1;
-			break;
-		}
-	}
-	if (found) {
-		if (addr->users != 0)
-			tmp->users += addr->users;
-		else
-			tmp->users += add ? 1 : -1;
-		if (tmp->users == 0) {
-			list_del(&tmp->entry);
-			kfree(tmp);
-		}
-		return 0;
+static struct qeth_ipaddr *
+qeth_l3_ip_from_hash(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
+{
+	struct qeth_ipaddr *addr;
+
+	if (tmp_addr->is_multicast) {
+		hash_for_each_possible(card->ip_mc_htable,  addr,
+				hnode, qeth_l3_ipaddr_hash(tmp_addr))
+			if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr))
+				return addr;
 	} else {
-		if (addr->type == QETH_IP_TYPE_DEL_ALL_MC)
-			list_add(&addr->entry, card->ip_tbd_list);
-		else {
-			if (addr->users == 0)
-				addr->users += add ? 1 : -1;
-			if (add && (addr->type == QETH_IP_TYPE_NORMAL) &&
-			    qeth_l3_is_addr_covered_by_ipato(card, addr)) {
-				QETH_CARD_TEXT(card, 2, "tkovaddr");
-				addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
-			}
-			list_add_tail(&addr->entry, card->ip_tbd_list);
-		}
-		return 1;
+		hash_for_each_possible(card->ip_htable,  addr,
+				hnode, qeth_l3_ipaddr_hash(tmp_addr))
+			if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr))
+				return addr;
 	}
+
+	return NULL;
 }
 
-int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *addr)
+int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 {
-	unsigned long flags;
 	int rc = 0;
+	struct qeth_ipaddr *addr;
 
 	QETH_CARD_TEXT(card, 4, "delip");
 
-	if (addr->proto == QETH_PROT_IPV4)
-		QETH_CARD_HEX(card, 4, &addr->u.a4.addr, 4);
+	if (tmp_addr->proto == QETH_PROT_IPV4)
+		QETH_CARD_HEX(card, 4, &tmp_addr->u.a4.addr, 4);
 	else {
-		QETH_CARD_HEX(card, 4, &addr->u.a6.addr, 8);
-		QETH_CARD_HEX(card, 4, ((char *)&addr->u.a6.addr) + 8, 8);
+		QETH_CARD_HEX(card, 4, &tmp_addr->u.a6.addr, 8);
+		QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8);
 	}
-	spin_lock_irqsave(&card->ip_lock, flags);
-	rc = __qeth_l3_insert_ip_todo(card, addr, 0);
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+
+	addr = qeth_l3_ip_from_hash(card, tmp_addr);
+	if (!addr)
+		return -ENOENT;
+
+	addr->ref_counter--;
+	if (addr->type == QETH_IP_TYPE_NORMAL && addr->ref_counter > 0)
+		return rc;
+	if (addr->in_progress)
+		return -EINPROGRESS;
+
+	rc = qeth_l3_deregister_addr_entry(card, addr);
+
+	hash_del(&addr->hnode);
+	kfree(addr);
+
 	return rc;
 }
 
-int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *addr)
+int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 {
-	unsigned long flags;
 	int rc = 0;
+	struct qeth_ipaddr *addr;
 
 	QETH_CARD_TEXT(card, 4, "addip");
-	if (addr->proto == QETH_PROT_IPV4)
-		QETH_CARD_HEX(card, 4, &addr->u.a4.addr, 4);
+
+	if (tmp_addr->proto == QETH_PROT_IPV4)
+		QETH_CARD_HEX(card, 4, &tmp_addr->u.a4.addr, 4);
 	else {
-		QETH_CARD_HEX(card, 4, &addr->u.a6.addr, 8);
-		QETH_CARD_HEX(card, 4, ((char *)&addr->u.a6.addr) + 8, 8);
+		QETH_CARD_HEX(card, 4, &tmp_addr->u.a6.addr, 8);
+		QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8);
 	}
-	spin_lock_irqsave(&card->ip_lock, flags);
-	rc = __qeth_l3_insert_ip_todo(card, addr, 1);
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+
+	addr = qeth_l3_ip_from_hash(card, tmp_addr);
+	if (!addr) {
+		addr = qeth_l3_get_addr_buffer(tmp_addr->proto);
+		if (!addr)
+			return -ENOMEM;
+
+		memcpy(addr, tmp_addr, sizeof(struct qeth_ipaddr));
+		addr->ref_counter = 1;
+
+		if (addr->type == QETH_IP_TYPE_NORMAL  &&
+				qeth_l3_is_addr_covered_by_ipato(card, addr)) {
+			QETH_CARD_TEXT(card, 2, "tkovaddr");
+			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
+		}
+		hash_add(card->ip_htable, &addr->hnode,
+				qeth_l3_ipaddr_hash(addr));
+
+		/* qeth_l3_register_addr_entry can go to sleep
+		 * if we add a IPV4 addr. It is caused by the reason
+		 * that SETIP ipa cmd starts ARP staff for IPV4 addr.
+		 * Thus we should unlock spinlock, and make a protection
+		 * using in_progress variable to indicate that there is
+		 * an hardware operation with this IPV4 address
+		 */
+		if (addr->proto == QETH_PROT_IPV4) {
+			addr->in_progress = 1;
+			spin_unlock_bh(&card->ip_lock);
+			rc = qeth_l3_register_addr_entry(card, addr);
+			spin_lock_bh(&card->ip_lock);
+			addr->in_progress = 0;
+		} else
+			rc = qeth_l3_register_addr_entry(card, addr);
+
+		if (!rc || (rc == IPA_RC_DUPLICATE_IP_ADDRESS) ||
+				(rc == IPA_RC_LAN_OFFLINE)) {
+			addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
+			if (addr->ref_counter < 1) {
+				qeth_l3_delete_ip(card, addr);
+				kfree(addr);
+			}
+		} else {
+			hash_del(&addr->hnode);
+			kfree(addr);
+		}
+	} else {
+			if (addr->type == QETH_IP_TYPE_NORMAL)
+				addr->ref_counter++;
+	}
+
 	return rc;
 }
 
@@ -312,229 +338,88 @@ struct qeth_ipaddr *qeth_l3_get_addr_buffer(
 	struct qeth_ipaddr *addr;
 
 	addr = kzalloc(sizeof(struct qeth_ipaddr), GFP_ATOMIC);
-	if (addr == NULL) {
+	if (!addr)
 		return NULL;
-	}
+
 	addr->type = QETH_IP_TYPE_NORMAL;
+	addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 	addr->proto = prot;
+
 	return addr;
 }
 
-static void qeth_l3_delete_mc_addresses(struct qeth_card *card)
-{
-	struct qeth_ipaddr *iptodo;
-	unsigned long flags;
-
-	QETH_CARD_TEXT(card, 4, "delmc");
-	iptodo = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
-	if (!iptodo) {
-		QETH_CARD_TEXT(card, 2, "dmcnomem");
-		return;
-	}
-	iptodo->type = QETH_IP_TYPE_DEL_ALL_MC;
-	spin_lock_irqsave(&card->ip_lock, flags);
-	if (!__qeth_l3_insert_ip_todo(card, iptodo, 0))
-		kfree(iptodo);
-	spin_unlock_irqrestore(&card->ip_lock, flags);
-}
-
-/*
- * Add/remove address to/from card's ip list, i.e. try to add or remove
- * reference to/from an IP address that is already registered on the card.
- * Returns:
- *	0  address was on card and its reference count has been adjusted,
- *	   but is still > 0, so nothing has to be done
- *	   also returns 0 if card was not on card and the todo was to delete
- *	   the address -> there is also nothing to be done
- *	1  address was not on card and the todo is to add it to the card's ip
- *	   list
- *	-1 address was on card and its reference count has been decremented
- *	   to <= 0 by the todo -> address must be removed from card
- */
-static int __qeth_l3_ref_ip_on_card(struct qeth_card *card,
-		struct qeth_ipaddr *todo, struct qeth_ipaddr **__addr)
+static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover)
 {
 	struct qeth_ipaddr *addr;
-	int found = 0;
-
-	list_for_each_entry(addr, &card->ip_list, entry) {
-		if ((addr->proto == QETH_PROT_IPV4) &&
-		    (todo->proto == QETH_PROT_IPV4) &&
-		    (addr->type == todo->type) &&
-		    (addr->u.a4.addr == todo->u.a4.addr) &&
-		    (addr->u.a4.mask == todo->u.a4.mask)) {
-			found = 1;
-			break;
-		}
-		if ((addr->proto == QETH_PROT_IPV6) &&
-		    (todo->proto == QETH_PROT_IPV6) &&
-		    (addr->type == todo->type) &&
-		    (addr->u.a6.pfxlen == todo->u.a6.pfxlen) &&
-		    (memcmp(&addr->u.a6.addr, &todo->u.a6.addr,
-			    sizeof(struct in6_addr)) == 0)) {
-			found = 1;
-			break;
-		}
-	}
-	if (found) {
-		addr->users += todo->users;
-		if (addr->users <= 0) {
-			*__addr = addr;
-			return -1;
-		} else {
-			/* for VIPA and RXIP limit refcount to 1 */
-			if (addr->type != QETH_IP_TYPE_NORMAL)
-				addr->users = 1;
-			return 0;
-		}
-	}
-	if (todo->users > 0) {
-		/* for VIPA and RXIP limit refcount to 1 */
-		if (todo->type != QETH_IP_TYPE_NORMAL)
-			todo->users = 1;
-		return 1;
-	} else
-		return 0;
-}
-
-static void __qeth_l3_delete_all_mc(struct qeth_card *card,
-					unsigned long *flags)
-{
-	struct list_head fail_list;
-	struct qeth_ipaddr *addr, *tmp;
-	int rc;
-
-	INIT_LIST_HEAD(&fail_list);
-again:
-	list_for_each_entry_safe(addr, tmp, &card->ip_list, entry) {
-		if (addr->is_multicast) {
-			list_del(&addr->entry);
-			spin_unlock_irqrestore(&card->ip_lock, *flags);
-			rc = qeth_l3_deregister_addr_entry(card, addr);
-			spin_lock_irqsave(&card->ip_lock, *flags);
-			if (!rc || (rc == IPA_RC_MC_ADDR_NOT_FOUND))
-				kfree(addr);
-			else
-				list_add_tail(&addr->entry, &fail_list);
-			goto again;
-		}
-	}
-	list_splice(&fail_list, &card->ip_list);
-}
-
-void qeth_l3_set_ip_addr_list(struct qeth_card *card)
-{
-	struct list_head *tbd_list;
-	struct qeth_ipaddr *todo, *addr;
-	unsigned long flags;
-	int rc;
+	struct hlist_node *tmp;
+	int i;
 
-	QETH_CARD_TEXT(card, 2, "sdiplist");
-	QETH_CARD_HEX(card, 2, &card, sizeof(void *));
+	QETH_CARD_TEXT(card, 4, "clearip");
 
-	if (!qeth_card_hw_is_reachable(card) || card->options.sniffer)
+	if (recover && card->options.sniffer)
 		return;
 
-	spin_lock_irqsave(&card->ip_lock, flags);
-	tbd_list = card->ip_tbd_list;
-	card->ip_tbd_list = kzalloc(sizeof(struct list_head), GFP_ATOMIC);
-	if (!card->ip_tbd_list) {
-		QETH_CARD_TEXT(card, 0, "silnomem");
-		card->ip_tbd_list = tbd_list;
-		spin_unlock_irqrestore(&card->ip_lock, flags);
-		return;
-	} else
-		INIT_LIST_HEAD(card->ip_tbd_list);
-
-	while (!list_empty(tbd_list)) {
-		todo = list_entry(tbd_list->next, struct qeth_ipaddr, entry);
-		list_del(&todo->entry);
-		if (todo->type == QETH_IP_TYPE_DEL_ALL_MC) {
-			__qeth_l3_delete_all_mc(card, &flags);
-			kfree(todo);
+	spin_lock_bh(&card->ip_lock);
+
+	hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) {
+		if (!recover) {
+			hash_del(&addr->hnode);
+			kfree(addr);
 			continue;
 		}
-		rc = __qeth_l3_ref_ip_on_card(card, todo, &addr);
-		if (rc == 0) {
-			/* nothing to be done; only adjusted refcount */
-			kfree(todo);
-		} else if (rc == 1) {
-			/* new entry to be added to on-card list */
-			spin_unlock_irqrestore(&card->ip_lock, flags);
-			rc = qeth_l3_register_addr_entry(card, todo);
-			spin_lock_irqsave(&card->ip_lock, flags);
-			if (!rc || (rc == IPA_RC_LAN_OFFLINE))
-				list_add_tail(&todo->entry, &card->ip_list);
-			else
-				kfree(todo);
-		} else if (rc == -1) {
-			/* on-card entry to be removed */
-			list_del_init(&addr->entry);
-			spin_unlock_irqrestore(&card->ip_lock, flags);
-			rc = qeth_l3_deregister_addr_entry(card, addr);
-			spin_lock_irqsave(&card->ip_lock, flags);
-			if (!rc || (rc == IPA_RC_IP_ADDRESS_NOT_DEFINED))
-				kfree(addr);
-			else
-				list_add_tail(&addr->entry, &card->ip_list);
-			kfree(todo);
-		}
+		addr->disp_flag = QETH_DISP_ADDR_ADD;
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
-	kfree(tbd_list);
-}
 
-static void qeth_l3_clear_ip_list(struct qeth_card *card, int recover)
-{
-	struct qeth_ipaddr *addr, *tmp;
-	unsigned long flags;
+	spin_unlock_bh(&card->ip_lock);
 
-	QETH_CARD_TEXT(card, 4, "clearip");
-	if (recover && card->options.sniffer)
-		return;
-	spin_lock_irqsave(&card->ip_lock, flags);
-	/* clear todo list */
-	list_for_each_entry_safe(addr, tmp, card->ip_tbd_list, entry) {
-		list_del(&addr->entry);
+	spin_lock_bh(&card->mclock);
+
+	hash_for_each_safe(card->ip_mc_htable, i, tmp, addr, hnode) {
+		hash_del(&addr->hnode);
 		kfree(addr);
 	}
 
-	while (!list_empty(&card->ip_list)) {
-		addr = list_entry(card->ip_list.next,
-				  struct qeth_ipaddr, entry);
-		list_del_init(&addr->entry);
-		if (!recover || addr->is_multicast) {
-			kfree(addr);
-			continue;
-		}
-		list_add_tail(&addr->entry, card->ip_tbd_list);
-	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
-}
+	spin_unlock_bh(&card->mclock);
+
 
-static int qeth_l3_address_exists_in_list(struct list_head *list,
-		struct qeth_ipaddr *addr, int same_type)
+}
+static void qeth_l3_recover_ip(struct qeth_card *card)
 {
-	struct qeth_ipaddr *tmp;
+	struct qeth_ipaddr *addr;
+	struct hlist_node *tmp;
+	int i;
+	int rc;
 
-	list_for_each_entry(tmp, list, entry) {
-		if ((tmp->proto == QETH_PROT_IPV4) &&
-		    (addr->proto == QETH_PROT_IPV4) &&
-		    ((same_type && (tmp->type == addr->type)) ||
-		    (!same_type && (tmp->type != addr->type))) &&
-		    (tmp->u.a4.addr == addr->u.a4.addr))
-			return 1;
+	QETH_CARD_TEXT(card, 4, "recoverip");
+
+	spin_lock_bh(&card->ip_lock);
+
+	hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) {
+		if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
+			if (addr->proto == QETH_PROT_IPV4) {
+				addr->in_progress = 1;
+				spin_unlock_bh(&card->ip_lock);
+				rc = qeth_l3_register_addr_entry(card, addr);
+				spin_lock_bh(&card->ip_lock);
+				addr->in_progress = 0;
+			} else
+				rc = qeth_l3_register_addr_entry(card, addr);
+
+			if (!rc) {
+				addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
+				if (addr->ref_counter < 1) {
+					qeth_l3_delete_ip(card, addr);
+					kfree(addr);
+				}
+			} else {
+				hash_del(&addr->hnode);
+				kfree(addr);
+			}
+		}
+	}
 
-		if ((tmp->proto == QETH_PROT_IPV6) &&
-		    (addr->proto == QETH_PROT_IPV6) &&
-		    ((same_type && (tmp->type == addr->type)) ||
-		    (!same_type && (tmp->type != addr->type))) &&
-		    (memcmp(&tmp->u.a6.addr, &addr->u.a6.addr,
-			    sizeof(struct in6_addr)) == 0))
-			return 1;
+	spin_unlock_bh(&card->ip_lock);
 
-	}
-	return 0;
 }
 
 static int qeth_l3_send_setdelmc(struct qeth_card *card,
@@ -712,27 +597,28 @@ int qeth_l3_setrouting_v6(struct qeth_card *card)
  */
 static void qeth_l3_clear_ipato_list(struct qeth_card *card)
 {
-
 	struct qeth_ipato_entry *ipatoe, *tmp;
-	unsigned long flags;
 
-	spin_lock_irqsave(&card->ip_lock, flags);
+	spin_lock_bh(&card->ip_lock);
+
 	list_for_each_entry_safe(ipatoe, tmp, &card->ipato.entries, entry) {
 		list_del(&ipatoe->entry);
 		kfree(ipatoe);
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+
+	spin_unlock_bh(&card->ip_lock);
 }
 
 int qeth_l3_add_ipato_entry(struct qeth_card *card,
 				struct qeth_ipato_entry *new)
 {
 	struct qeth_ipato_entry *ipatoe;
-	unsigned long flags;
 	int rc = 0;
 
 	QETH_CARD_TEXT(card, 2, "addipato");
-	spin_lock_irqsave(&card->ip_lock, flags);
+
+	spin_lock_bh(&card->ip_lock);
+
 	list_for_each_entry(ipatoe, &card->ipato.entries, entry) {
 		if (ipatoe->proto != new->proto)
 			continue;
@@ -743,10 +629,12 @@ int qeth_l3_add_ipato_entry(struct qeth_card *card,
 			break;
 		}
 	}
+
 	if (!rc)
 		list_add_tail(&new->entry, &card->ipato.entries);
 
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+	spin_unlock_bh(&card->ip_lock);
+
 	return rc;
 }
 
@@ -754,10 +642,11 @@ void qeth_l3_del_ipato_entry(struct qeth_card *card,
 		enum qeth_prot_versions proto, u8 *addr, int mask_bits)
 {
 	struct qeth_ipato_entry *ipatoe, *tmp;
-	unsigned long flags;
 
 	QETH_CARD_TEXT(card, 2, "delipato");
-	spin_lock_irqsave(&card->ip_lock, flags);
+
+	spin_lock_bh(&card->ip_lock);
+
 	list_for_each_entry_safe(ipatoe, tmp, &card->ipato.entries, entry) {
 		if (ipatoe->proto != proto)
 			continue;
@@ -768,7 +657,8 @@ void qeth_l3_del_ipato_entry(struct qeth_card *card,
 			kfree(ipatoe);
 		}
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+
+	spin_unlock_bh(&card->ip_lock);
 }
 
 /*
@@ -778,7 +668,6 @@ int qeth_l3_add_vipa(struct qeth_card *card, enum qeth_prot_versions proto,
 	      const u8 *addr)
 {
 	struct qeth_ipaddr *ipaddr;
-	unsigned long flags;
 	int rc = 0;
 
 	ipaddr = qeth_l3_get_addr_buffer(proto);
@@ -797,18 +686,18 @@ int qeth_l3_add_vipa(struct qeth_card *card, enum qeth_prot_versions proto,
 		ipaddr->del_flags = QETH_IPA_DELIP_VIPA_FLAG;
 	} else
 		return -ENOMEM;
-	spin_lock_irqsave(&card->ip_lock, flags);
-	if (qeth_l3_address_exists_in_list(&card->ip_list, ipaddr, 0) ||
-	    qeth_l3_address_exists_in_list(card->ip_tbd_list, ipaddr, 0))
+
+	spin_lock_bh(&card->ip_lock);
+
+	if (!qeth_l3_ip_from_hash(card, ipaddr))
 		rc = -EEXIST;
-	spin_unlock_irqrestore(&card->ip_lock, flags);
-	if (rc) {
-		kfree(ipaddr);
-		return rc;
-	}
-	if (!qeth_l3_add_ip(card, ipaddr))
-		kfree(ipaddr);
-	qeth_l3_set_ip_addr_list(card);
+	else
+		qeth_l3_add_ip(card, ipaddr);
+
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(ipaddr);
+
 	return rc;
 }
 
@@ -831,9 +720,12 @@ void qeth_l3_del_vipa(struct qeth_card *card, enum qeth_prot_versions proto,
 		ipaddr->type = QETH_IP_TYPE_VIPA;
 	} else
 		return;
-	if (!qeth_l3_delete_ip(card, ipaddr))
-		kfree(ipaddr);
-	qeth_l3_set_ip_addr_list(card);
+
+	spin_lock_bh(&card->ip_lock);
+	qeth_l3_delete_ip(card, ipaddr);
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(ipaddr);
 }
 
 /*
@@ -843,7 +735,6 @@ int qeth_l3_add_rxip(struct qeth_card *card, enum qeth_prot_versions proto,
 	      const u8 *addr)
 {
 	struct qeth_ipaddr *ipaddr;
-	unsigned long flags;
 	int rc = 0;
 
 	ipaddr = qeth_l3_get_addr_buffer(proto);
@@ -857,24 +748,25 @@ int qeth_l3_add_rxip(struct qeth_card *card, enum qeth_prot_versions proto,
 			memcpy(&ipaddr->u.a6.addr, addr, 16);
 			ipaddr->u.a6.pfxlen = 0;
 		}
+
 		ipaddr->type = QETH_IP_TYPE_RXIP;
 		ipaddr->set_flags = QETH_IPA_SETIP_TAKEOVER_FLAG;
 		ipaddr->del_flags = 0;
 	} else
 		return -ENOMEM;
-	spin_lock_irqsave(&card->ip_lock, flags);
-	if (qeth_l3_address_exists_in_list(&card->ip_list, ipaddr, 0) ||
-	    qeth_l3_address_exists_in_list(card->ip_tbd_list, ipaddr, 0))
+
+	spin_lock_bh(&card->ip_lock);
+
+	if (!qeth_l3_ip_from_hash(card, ipaddr))
 		rc = -EEXIST;
-	spin_unlock_irqrestore(&card->ip_lock, flags);
-	if (rc) {
-		kfree(ipaddr);
-		return rc;
-	}
-	if (!qeth_l3_add_ip(card, ipaddr))
-		kfree(ipaddr);
-	qeth_l3_set_ip_addr_list(card);
-	return 0;
+	else
+		qeth_l3_add_ip(card, ipaddr);
+
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(ipaddr);
+
+	return rc;
 }
 
 void qeth_l3_del_rxip(struct qeth_card *card, enum qeth_prot_versions proto,
@@ -896,9 +788,12 @@ void qeth_l3_del_rxip(struct qeth_card *card, enum qeth_prot_versions proto,
 		ipaddr->type = QETH_IP_TYPE_RXIP;
 	} else
 		return;
-	if (!qeth_l3_delete_ip(card, ipaddr))
-		kfree(ipaddr);
-	qeth_l3_set_ip_addr_list(card);
+
+	spin_lock_bh(&card->ip_lock);
+	qeth_l3_delete_ip(card, ipaddr);
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(ipaddr);
 }
 
 static int qeth_l3_register_addr_entry(struct qeth_card *card,
@@ -908,6 +803,7 @@ static int qeth_l3_register_addr_entry(struct qeth_card *card,
 	int rc = 0;
 	int cnt = 3;
 
+
 	if (addr->proto == QETH_PROT_IPV4) {
 		QETH_CARD_TEXT(card, 2, "setaddr4");
 		QETH_CARD_HEX(card, 3, &addr->u.a4.addr, sizeof(int));
@@ -1013,36 +909,6 @@ static int qeth_l3_setadapter_parms(struct qeth_card *card)
 	return rc;
 }
 
-static int qeth_l3_default_setassparms_cb(struct qeth_card *card,
-			struct qeth_reply *reply, unsigned long data)
-{
-	struct qeth_ipa_cmd *cmd;
-
-	QETH_CARD_TEXT(card, 4, "defadpcb");
-
-	cmd = (struct qeth_ipa_cmd *) data;
-	if (cmd->hdr.return_code == 0) {
-		cmd->hdr.return_code = cmd->data.setassparms.hdr.return_code;
-		if (cmd->hdr.prot_version == QETH_PROT_IPV4)
-			card->options.ipa4.enabled_funcs = cmd->hdr.ipa_enabled;
-		if (cmd->hdr.prot_version == QETH_PROT_IPV6)
-			card->options.ipa6.enabled_funcs = cmd->hdr.ipa_enabled;
-	}
-	if (cmd->data.setassparms.hdr.assist_no == IPA_INBOUND_CHECKSUM &&
-	    cmd->data.setassparms.hdr.command_code == IPA_CMD_ASS_START) {
-		card->info.csum_mask = cmd->data.setassparms.data.flags_32bit;
-		QETH_CARD_TEXT_(card, 3, "csum:%d", card->info.csum_mask);
-	}
-	if (cmd->data.setassparms.hdr.assist_no == IPA_OUTBOUND_CHECKSUM &&
-	    cmd->data.setassparms.hdr.command_code == IPA_CMD_ASS_START) {
-		card->info.tx_csum_mask =
-			cmd->data.setassparms.data.flags_32bit;
-		QETH_CARD_TEXT_(card, 3, "tcsu:%d", card->info.tx_csum_mask);
-	}
-
-	return 0;
-}
-
 #ifdef CONFIG_QETH_IPV6
 static int qeth_l3_send_simple_setassparms_ipv6(struct qeth_card *card,
 		enum qeth_ipa_funcs ipa_func, __u16 cmd_code)
@@ -1056,7 +922,7 @@ static int qeth_l3_send_simple_setassparms_ipv6(struct qeth_card *card,
 	if (!iob)
 		return -ENOMEM;
 	rc = qeth_send_setassparms(card, iob, 0, 0,
-				   qeth_l3_default_setassparms_cb, NULL);
+				   qeth_setassparms_cb, NULL);
 	return rc;
 }
 #endif
@@ -1291,47 +1157,6 @@ out:
 	return rc;
 }
 
-static void qeth_l3_start_ipa_checksum(struct qeth_card *card)
-{
-	QETH_CARD_TEXT(card, 3, "strtcsum");
-	if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM)
-	    && (card->dev->features & NETIF_F_RXCSUM))
-		qeth_set_rx_csum(card, 1);
-}
-
-static void qeth_l3_start_ipa_tx_checksum(struct qeth_card *card)
-{
-	QETH_CARD_TEXT(card, 3, "strttxcs");
-	qeth_start_ipa_tx_checksum(card);
-}
-
-static int qeth_l3_start_ipa_tso(struct qeth_card *card)
-{
-	int rc;
-
-	QETH_CARD_TEXT(card, 3, "sttso");
-
-	if (!qeth_is_supported(card, IPA_OUTBOUND_TSO)) {
-		dev_info(&card->gdev->dev,
-			"Outbound TSO not supported on %s\n",
-			QETH_CARD_IFNAME(card));
-		rc = -EOPNOTSUPP;
-	} else {
-		rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_TSO,
-						  IPA_CMD_ASS_START, 0);
-		if (rc)
-			dev_warn(&card->gdev->dev, "Starting outbound TCP "
-				"segmentation offload for %s failed\n",
-				QETH_CARD_IFNAME(card));
-		else
-			dev_info(&card->gdev->dev,
-				"Outbound TSO enabled\n");
-	}
-	if (rc)
-		card->dev->features &= ~NETIF_F_TSO;
-	return rc;
-}
-
 static int qeth_l3_start_ipassists(struct qeth_card *card)
 {
 	QETH_CARD_TEXT(card, 3, "strtipas");
@@ -1345,9 +1170,6 @@ static int qeth_l3_start_ipassists(struct qeth_card *card)
 	qeth_l3_start_ipa_multicast(card);		/* go on*/
 	qeth_l3_start_ipa_ipv6(card);		/* go on*/
 	qeth_l3_start_ipa_broadcast(card);		/* go on*/
-	qeth_l3_start_ipa_checksum(card);		/* go on*/
-	qeth_l3_start_ipa_tx_checksum(card);
-	qeth_l3_start_ipa_tso(card);		/* go on*/
 	return 0;
 }
 
@@ -1507,31 +1329,99 @@ qeth_diags_trace(struct qeth_card *card, enum qeth_diags_trace_cmds diags_cmd)
 	return qeth_send_ipa_cmd(card, iob, qeth_diags_trace_cb, NULL);
 }
 
-static void qeth_l3_get_mac_for_ipm(__u32 ipm, char *mac,
-				struct net_device *dev)
+static void qeth_l3_get_mac_for_ipm(__u32 ipm, char *mac)
 {
 	ip_eth_mc_map(ipm, mac);
 }
 
-static void qeth_l3_add_mc(struct qeth_card *card, struct in_device *in4_dev)
+static void qeth_l3_mark_all_mc_to_be_deleted(struct qeth_card *card)
+{
+	struct qeth_ipaddr *addr;
+	int i;
+
+	hash_for_each(card->ip_mc_htable, i, addr, hnode)
+		addr->disp_flag = QETH_DISP_ADDR_DELETE;
+
+}
+
+static void qeth_l3_add_all_new_mc(struct qeth_card *card)
+{
+	struct qeth_ipaddr *addr;
+	struct hlist_node *tmp;
+	int i;
+	int rc;
+
+	hash_for_each_safe(card->ip_mc_htable, i, tmp, addr, hnode) {
+		if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
+			rc = qeth_l3_register_addr_entry(card, addr);
+			if (!rc || (rc == IPA_RC_LAN_OFFLINE))
+				addr->ref_counter = 1;
+			else {
+				hash_del(&addr->hnode);
+				kfree(addr);
+			}
+		}
+	}
+
+}
+
+static void qeth_l3_delete_nonused_mc(struct qeth_card *card)
+{
+	struct qeth_ipaddr *addr;
+	struct hlist_node *tmp;
+	int i;
+	int rc;
+
+	hash_for_each_safe(card->ip_mc_htable, i, tmp, addr, hnode) {
+		if (addr->disp_flag == QETH_DISP_ADDR_DELETE) {
+			rc = qeth_l3_deregister_addr_entry(card, addr);
+			if (!rc || (rc == IPA_RC_MC_ADDR_NOT_FOUND)) {
+				hash_del(&addr->hnode);
+				kfree(addr);
+			}
+		}
+	}
+
+}
+
+
+static void
+qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
 {
-	struct qeth_ipaddr *ipm;
 	struct ip_mc_list *im4;
+	struct qeth_ipaddr *tmp, *ipm;
 	char buf[MAX_ADDR_LEN];
 
 	QETH_CARD_TEXT(card, 4, "addmc");
+
+	tmp = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
+		if (!tmp)
+			return;
+
 	for (im4 = rcu_dereference(in4_dev->mc_list); im4 != NULL;
 	     im4 = rcu_dereference(im4->next_rcu)) {
-		qeth_l3_get_mac_for_ipm(im4->multiaddr, buf, in4_dev->dev);
-		ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
-		if (!ipm)
-			continue;
-		ipm->u.a4.addr = im4->multiaddr;
-		memcpy(ipm->mac, buf, OSA_ADDR_LEN);
-		ipm->is_multicast = 1;
-		if (!qeth_l3_add_ip(card, ipm))
-			kfree(ipm);
+		qeth_l3_get_mac_for_ipm(im4->multiaddr, buf);
+
+		tmp->u.a4.addr = im4->multiaddr;
+		memcpy(tmp->mac, buf, sizeof(tmp->mac));
+
+		ipm = qeth_l3_ip_from_hash(card, tmp);
+		if (ipm) {
+			ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
+		} else {
+			ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
+			if (!ipm)
+				continue;
+			memcpy(ipm->mac, buf, sizeof(tmp->mac));
+			ipm->u.a4.addr = im4->multiaddr;
+			ipm->is_multicast = 1;
+			ipm->disp_flag = QETH_DISP_ADDR_ADD;
+			hash_add(card->ip_mc_htable,
+					&ipm->hnode, qeth_l3_ipaddr_hash(ipm));
+		}
 	}
+
+	kfree(tmp);
 }
 
 /* called with rcu_read_lock */
@@ -1541,6 +1431,7 @@ static void qeth_l3_add_vlan_mc(struct qeth_card *card)
 	u16 vid;
 
 	QETH_CARD_TEXT(card, 4, "addmcvl");
+
 	if (!qeth_is_supported(card, IPA_FULL_VLAN))
 		return;
 
@@ -1555,7 +1446,7 @@ static void qeth_l3_add_vlan_mc(struct qeth_card *card)
 		in_dev = __in_dev_get_rcu(netdev);
 		if (!in_dev)
 			continue;
-		qeth_l3_add_mc(card, in_dev);
+		qeth_l3_add_mc_to_hash(card, in_dev);
 	}
 }
 
@@ -1564,36 +1455,60 @@ static void qeth_l3_add_multicast_ipv4(struct qeth_card *card)
 	struct in_device *in4_dev;
 
 	QETH_CARD_TEXT(card, 4, "chkmcv4");
+
 	rcu_read_lock();
 	in4_dev = __in_dev_get_rcu(card->dev);
 	if (in4_dev == NULL)
 		goto unlock;
-	qeth_l3_add_mc(card, in4_dev);
+	qeth_l3_add_mc_to_hash(card, in4_dev);
 	qeth_l3_add_vlan_mc(card);
 unlock:
 	rcu_read_unlock();
 }
 
 #ifdef CONFIG_QETH_IPV6
-static void qeth_l3_add_mc6(struct qeth_card *card, struct inet6_dev *in6_dev)
+static void
+qeth_l3_add_mc6_to_hash(struct qeth_card *card, struct inet6_dev *in6_dev)
 {
 	struct qeth_ipaddr *ipm;
 	struct ifmcaddr6 *im6;
+	struct qeth_ipaddr *tmp;
 	char buf[MAX_ADDR_LEN];
 
 	QETH_CARD_TEXT(card, 4, "addmc6");
+
+	tmp = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
+		if (!tmp)
+			return;
+
 	for (im6 = in6_dev->mc_list; im6 != NULL; im6 = im6->next) {
 		ndisc_mc_map(&im6->mca_addr, buf, in6_dev->dev, 0);
+
+		memcpy(tmp->mac, buf, sizeof(tmp->mac));
+		memcpy(&tmp->u.a6.addr, &im6->mca_addr.s6_addr,
+		       sizeof(struct in6_addr));
+		tmp->is_multicast = 1;
+
+		ipm = qeth_l3_ip_from_hash(card, tmp);
+		if (ipm) {
+			ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
+			continue;
+		}
+
 		ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
 		if (!ipm)
 			continue;
-		ipm->is_multicast = 1;
+
 		memcpy(ipm->mac, buf, OSA_ADDR_LEN);
 		memcpy(&ipm->u.a6.addr, &im6->mca_addr.s6_addr,
 		       sizeof(struct in6_addr));
-		if (!qeth_l3_add_ip(card, ipm))
-			kfree(ipm);
+		ipm->is_multicast = 1;
+		ipm->disp_flag = QETH_DISP_ADDR_ADD;
+		hash_add(card->ip_mc_htable,
+				&ipm->hnode, qeth_l3_ipaddr_hash(ipm));
+
 	}
+	kfree(tmp);
 }
 
 /* called with rcu_read_lock */
@@ -1603,6 +1518,7 @@ static void qeth_l3_add_vlan_mc6(struct qeth_card *card)
 	u16 vid;
 
 	QETH_CARD_TEXT(card, 4, "admc6vl");
+
 	if (!qeth_is_supported(card, IPA_FULL_VLAN))
 		return;
 
@@ -1618,7 +1534,7 @@ static void qeth_l3_add_vlan_mc6(struct qeth_card *card)
 		if (!in_dev)
 			continue;
 		read_lock_bh(&in_dev->lock);
-		qeth_l3_add_mc6(card, in_dev);
+		qeth_l3_add_mc6_to_hash(card, in_dev);
 		read_unlock_bh(&in_dev->lock);
 		in6_dev_put(in_dev);
 	}
@@ -1629,14 +1545,16 @@ static void qeth_l3_add_multicast_ipv6(struct qeth_card *card)
 	struct inet6_dev *in6_dev;
 
 	QETH_CARD_TEXT(card, 4, "chkmcv6");
+
 	if (!qeth_is_supported(card, IPA_IPV6))
 		return ;
 	in6_dev = in6_dev_get(card->dev);
-	if (in6_dev == NULL)
+	if (!in6_dev)
 		return;
+
 	rcu_read_lock();
 	read_lock_bh(&in6_dev->lock);
-	qeth_l3_add_mc6(card, in6_dev);
+	qeth_l3_add_mc6_to_hash(card, in6_dev);
 	qeth_l3_add_vlan_mc6(card);
 	read_unlock_bh(&in6_dev->lock);
 	rcu_read_unlock();
@@ -1660,16 +1578,23 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card,
 	in_dev = in_dev_get(netdev);
 	if (!in_dev)
 		return;
+
+	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
+	if (!addr)
+		return;
+
+	spin_lock_bh(&card->ip_lock);
+
 	for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
-		addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
-		if (addr) {
-			addr->u.a4.addr = ifa->ifa_address;
-			addr->u.a4.mask = ifa->ifa_mask;
-			addr->type = QETH_IP_TYPE_NORMAL;
-			if (!qeth_l3_delete_ip(card, addr))
-				kfree(addr);
-		}
+		addr->u.a4.addr = ifa->ifa_address;
+		addr->u.a4.mask = ifa->ifa_mask;
+		addr->type = QETH_IP_TYPE_NORMAL;
+		qeth_l3_delete_ip(card, addr);
 	}
+
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(addr);
 	in_dev_put(in_dev);
 }
 
@@ -1687,20 +1612,28 @@ static void qeth_l3_free_vlan_addresses6(struct qeth_card *card,
 	netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q), vid);
 	if (!netdev)
 		return;
+
 	in6_dev = in6_dev_get(netdev);
 	if (!in6_dev)
 		return;
+
+	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
+	if (!addr)
+		return;
+
+	spin_lock_bh(&card->ip_lock);
+
 	list_for_each_entry(ifa, &in6_dev->addr_list, if_list) {
-		addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
-		if (addr) {
-			memcpy(&addr->u.a6.addr, &ifa->addr,
-			       sizeof(struct in6_addr));
-			addr->u.a6.pfxlen = ifa->prefix_len;
-			addr->type = QETH_IP_TYPE_NORMAL;
-			if (!qeth_l3_delete_ip(card, addr))
-				kfree(addr);
-		}
+		memcpy(&addr->u.a6.addr, &ifa->addr,
+		       sizeof(struct in6_addr));
+		addr->u.a6.pfxlen = ifa->prefix_len;
+		addr->type = QETH_IP_TYPE_NORMAL;
+		qeth_l3_delete_ip(card, addr);
 	}
+
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(addr);
 	in6_dev_put(in6_dev);
 #endif /* CONFIG_QETH_IPV6 */
 }
@@ -1727,18 +1660,16 @@ static int qeth_l3_vlan_rx_kill_vid(struct net_device *dev,
 				    __be16 proto, u16 vid)
 {
 	struct qeth_card *card = dev->ml_priv;
-	unsigned long flags;
 
 	QETH_CARD_TEXT_(card, 4, "kid:%d", vid);
+
 	if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
 		QETH_CARD_TEXT(card, 3, "kidREC");
 		return 0;
 	}
-	spin_lock_irqsave(&card->vlanlock, flags);
 	/* unregister IP addresses of vlan device */
 	qeth_l3_free_vlan_addresses(card, vid);
 	clear_bit(vid, card->active_vlans);
-	spin_unlock_irqrestore(&card->vlanlock, flags);
 	qeth_l3_set_multicast_list(card->dev);
 	return 0;
 }
@@ -1994,8 +1925,8 @@ static int qeth_l3_verify_vlan_dev(struct net_device *dev,
 static int qeth_l3_verify_dev(struct net_device *dev)
 {
 	struct qeth_card *card;
-	unsigned long flags;
 	int rc = 0;
+	unsigned long flags;
 
 	read_lock_irqsave(&qeth_core_card_list.rwlock, flags);
 	list_for_each_entry(card, &qeth_core_card_list.list, list) {
@@ -2051,7 +1982,7 @@ static void qeth_l3_stop_card(struct qeth_card *card, int recovery_mode)
 		card->state = CARD_STATE_SOFTSETUP;
 	}
 	if (card->state == CARD_STATE_SOFTSETUP) {
-		qeth_l3_clear_ip_list(card, 1);
+		qeth_l3_clear_ip_htable(card, 1);
 		qeth_clear_ipacmd_list(card);
 		card->state = CARD_STATE_HARDSETUP;
 	}
@@ -2106,12 +2037,20 @@ static void qeth_l3_set_multicast_list(struct net_device *dev)
 	    (card->state != CARD_STATE_UP))
 		return;
 	if (!card->options.sniffer) {
-		qeth_l3_delete_mc_addresses(card);
+
+		spin_lock_bh(&card->mclock);
+
+		qeth_l3_mark_all_mc_to_be_deleted(card);
+
 		qeth_l3_add_multicast_ipv4(card);
 #ifdef CONFIG_QETH_IPV6
 		qeth_l3_add_multicast_ipv6(card);
 #endif
-		qeth_l3_set_ip_addr_list(card);
+		qeth_l3_delete_nonused_mc(card);
+		qeth_l3_add_all_new_mc(card);
+
+		spin_unlock_bh(&card->mclock);
+
 		if (!qeth_adp_supported(card, IPA_SETADP_SET_PROMISC_MODE))
 			return;
 	}
@@ -2375,22 +2314,21 @@ static int qeth_l3_arp_query(struct qeth_card *card, char __user *udata)
 	if (rc) {
 		if (copy_to_user(udata, qinfo.udata, 4))
 			rc = -EFAULT;
-			goto free_and_out;
-	} else {
+		goto free_and_out;
+	}
 #ifdef CONFIG_QETH_IPV6
-		if (qinfo.mask_bits & QETH_QARP_WITH_IPV6) {
-			/* fails in case of GuestLAN QDIO mode */
-			qeth_l3_query_arp_cache_info(card, QETH_PROT_IPV6,
-				&qinfo);
-		}
+	if (qinfo.mask_bits & QETH_QARP_WITH_IPV6) {
+		/* fails in case of GuestLAN QDIO mode */
+		qeth_l3_query_arp_cache_info(card, QETH_PROT_IPV6, &qinfo);
+	}
 #endif
-		if (copy_to_user(udata, qinfo.udata, qinfo.udata_len)) {
-			QETH_CARD_TEXT(card, 4, "qactf");
-			rc = -EFAULT;
-			goto free_and_out;
-		}
-		QETH_CARD_TEXT(card, 4, "qacts");
+	if (copy_to_user(udata, qinfo.udata, qinfo.udata_len)) {
+		QETH_CARD_TEXT(card, 4, "qactf");
+		rc = -EFAULT;
+		goto free_and_out;
 	}
+	QETH_CARD_TEXT(card, 4, "qacts");
+
 free_and_out:
 	kfree(qinfo.udata);
 out:
@@ -2427,7 +2365,7 @@ static int qeth_l3_arp_add_entry(struct qeth_card *card,
 	rc = qeth_send_setassparms(card, iob,
 				   sizeof(struct qeth_arp_cache_entry),
 				   (unsigned long) entry,
-				   qeth_l3_default_setassparms_cb, NULL);
+				   qeth_setassparms_cb, NULL);
 	if (rc) {
 		tmp = rc;
 		qeth_l3_ipaddr4_to_string((u8 *)entry->ipaddr, buf);
@@ -2467,7 +2405,7 @@ static int qeth_l3_arp_remove_entry(struct qeth_card *card,
 		return -ENOMEM;
 	rc = qeth_send_setassparms(card, iob,
 				   12, (unsigned long)buf,
-				   qeth_l3_default_setassparms_cb, NULL);
+				   qeth_setassparms_cb, NULL);
 	if (rc) {
 		tmp = rc;
 		memset(buf, 0, 16);
@@ -2793,15 +2731,34 @@ static void qeth_tso_fill_header(struct qeth_card *card,
 	}
 }
 
-static inline int qeth_l3_tso_elements(struct sk_buff *skb)
+/**
+ * qeth_l3_get_elements_no_tso() - find number of SBALEs for skb data for tso
+ * @card:			   qeth card structure, to check max. elems.
+ * @skb:			   SKB address
+ * @extra_elems:		   extra elems needed, to check against max.
+ *
+ * Returns the number of pages, and thus QDIO buffer elements, needed to cover
+ * skb data, including linear part and fragments, but excluding TCP header.
+ * (Exclusion of TCP header distinguishes it from qeth_get_elements_no().)
+ * Checks if the result plus extra_elems fits under the limit for the card.
+ * Returns 0 if it does not.
+ * Note: extra_elems is not included in the returned result.
+ */
+static int qeth_l3_get_elements_no_tso(struct qeth_card *card,
+			struct sk_buff *skb, int extra_elems)
 {
-	unsigned long tcpd = (unsigned long)tcp_hdr(skb) +
-		tcp_hdr(skb)->doff * 4;
-	int tcpd_len = skb_headlen(skb) - (tcpd - (unsigned long)skb->data);
-	int elements = PFN_UP(tcpd + tcpd_len - 1) - PFN_DOWN(tcpd);
-
-	elements += qeth_get_elements_for_frags(skb);
+	addr_t tcpdptr = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb);
+	int elements = qeth_get_elements_for_range(
+				tcpdptr,
+				(addr_t)skb->data + skb_headlen(skb)) +
+				qeth_get_elements_for_frags(skb);
 
+	if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
+		QETH_DBF_MESSAGE(2,
+	"Invalid size of TSO IP packet (Number=%d / Length=%d). Discarded.\n",
+				elements + extra_elems, skb->len);
+		return 0;
+	}
 	return elements;
 }
 
@@ -2810,8 +2767,8 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	int rc;
 	u16 *tag;
 	struct qeth_hdr *hdr = NULL;
-	int elements_needed = 0;
-	int elems;
+	int hdr_elements = 0;
+	int elements;
 	struct qeth_card *card = dev->ml_priv;
 	struct sk_buff *new_skb = NULL;
 	int ipv = qeth_get_ip_version(skb);
@@ -2822,7 +2779,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			qeth_get_priority_queue(card, skb, ipv, cast_type) :
 			card->qdio.default_out_queue];
 	int tx_bytes = skb->len;
-	bool large_send;
+	bool use_tso;
 	int data_offset = -1;
 	int nr_frags;
 
@@ -2847,10 +2804,12 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		card->perf_stats.outbound_start_time = qeth_get_micros();
 	}
 
-	large_send = skb_is_gso(skb);
+	/* Ignore segment size from skb_is_gso(), 1 page is always used. */
+	use_tso = skb_is_gso(skb) &&
+		  (qeth_get_ip_protocol(skb) == IPPROTO_TCP) && (ipv == 4);
 
-	if ((card->info.type == QETH_CARD_TYPE_IQD) && (!large_send) &&
-	    (skb_shinfo(skb)->nr_frags == 0)) {
+	if ((card->info.type == QETH_CARD_TYPE_IQD) &&
+	    !skb_is_nonlinear(skb)) {
 		new_skb = skb;
 		if (new_skb->protocol == ETH_P_AF_IUCV)
 			data_offset = 0;
@@ -2859,7 +2818,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
 		if (!hdr)
 			goto tx_drop;
-		elements_needed++;
+		hdr_elements++;
 	} else {
 		/* create a clone with writeable headroom */
 		new_skb = skb_realloc_headroom(skb, sizeof(struct qeth_hdr_tso)
@@ -2894,22 +2853,28 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* fix hardware limitation: as long as we do not have sbal
 	 * chaining we can not send long frag lists
 	 */
-	if (large_send) {
-		if (qeth_l3_tso_elements(new_skb) + 1 > 16) {
-			if (skb_linearize(new_skb))
-				goto tx_drop;
-			if (card->options.performance_stats)
+	if ((card->info.type != QETH_CARD_TYPE_IQD) &&
+	    ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
+	     (!use_tso && !qeth_get_elements_no(card, new_skb, 0)))) {
+		int lin_rc = skb_linearize(new_skb);
+
+		if (card->options.performance_stats) {
+			if (lin_rc)
+				card->perf_stats.tx_linfail++;
+			else
 				card->perf_stats.tx_lin++;
 		}
+		if (lin_rc)
+			goto tx_drop;
 	}
 
-	if (large_send && (cast_type == RTN_UNSPEC)) {
+	if (use_tso) {
 		hdr = (struct qeth_hdr *)skb_push(new_skb,
 						sizeof(struct qeth_hdr_tso));
 		memset(hdr, 0, sizeof(struct qeth_hdr_tso));
 		qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type);
 		qeth_tso_fill_header(card, hdr, new_skb);
-		elements_needed++;
+		hdr_elements++;
 	} else {
 		if (data_offset < 0) {
 			hdr = (struct qeth_hdr *)skb_push(new_skb,
@@ -2930,31 +2895,31 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			qeth_l3_hdr_csum(card, hdr, new_skb);
 	}
 
-	elems = qeth_get_elements_no(card, new_skb, elements_needed);
-	if (!elems) {
+	elements = use_tso ?
+		   qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) :
+		   qeth_get_elements_no(card, new_skb, hdr_elements);
+	if (!elements) {
 		if (data_offset >= 0)
 			kmem_cache_free(qeth_core_header_cache, hdr);
 		goto tx_drop;
 	}
-	elements_needed += elems;
-	nr_frags = skb_shinfo(new_skb)->nr_frags;
+	elements += hdr_elements;
 
 	if (card->info.type != QETH_CARD_TYPE_IQD) {
 		int len;
-		if (large_send)
+		if (use_tso)
 			len = ((unsigned long)tcp_hdr(new_skb) +
-				tcp_hdr(new_skb)->doff * 4) -
+				tcp_hdrlen(new_skb)) -
 				(unsigned long)new_skb->data;
 		else
 			len = sizeof(struct qeth_hdr_layer3);
 
 		if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len))
 			goto tx_drop;
-		rc = qeth_do_send_packet(card, queue, new_skb, hdr,
-					 elements_needed);
+		rc = qeth_do_send_packet(card, queue, new_skb, hdr, elements);
 	} else
 		rc = qeth_do_send_packet_fast(card, queue, new_skb, hdr,
-					elements_needed, data_offset, 0);
+					elements, data_offset, 0);
 
 	if (!rc) {
 		card->stats.tx_packets++;
@@ -2962,7 +2927,8 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (new_skb != skb)
 			dev_kfree_skb_any(skb);
 		if (card->options.performance_stats) {
-			if (large_send) {
+			nr_frags = skb_shinfo(new_skb)->nr_frags;
+			if (use_tso) {
 				card->perf_stats.large_send_bytes += tx_bytes;
 				card->perf_stats.large_send_cnt++;
 			}
@@ -3048,36 +3014,6 @@ static int qeth_l3_stop(struct net_device *dev)
 	return 0;
 }
 
-static netdev_features_t qeth_l3_fix_features(struct net_device *dev,
-	netdev_features_t features)
-{
-	struct qeth_card *card = dev->ml_priv;
-
-	if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM))
-		features &= ~NETIF_F_IP_CSUM;
-	if (!qeth_is_supported(card, IPA_OUTBOUND_TSO))
-		features &= ~NETIF_F_TSO;
-	if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM))
-		features &= ~NETIF_F_RXCSUM;
-	return features;
-}
-
-static int qeth_l3_set_features(struct net_device *dev,
-	netdev_features_t features)
-{
-	struct qeth_card *card = dev->ml_priv;
-	netdev_features_t changed = dev->features ^ features;
-
-	if (!(changed & NETIF_F_RXCSUM))
-		return 0;
-
-	if (card->state == CARD_STATE_DOWN ||
-	    card->state == CARD_STATE_RECOVER)
-		return 0;
-
-	return qeth_set_rx_csum(card, features & NETIF_F_RXCSUM ? 1 : 0);
-}
-
 static const struct ethtool_ops qeth_l3_ethtool_ops = {
 	.get_link = ethtool_op_get_link,
 	.get_strings = qeth_core_get_strings,
@@ -3120,8 +3056,8 @@ static const struct net_device_ops qeth_l3_netdev_ops = {
 	.ndo_set_rx_mode	= qeth_l3_set_multicast_list,
 	.ndo_do_ioctl		= qeth_l3_do_ioctl,
 	.ndo_change_mtu		= qeth_change_mtu,
-	.ndo_fix_features	= qeth_l3_fix_features,
-	.ndo_set_features	= qeth_l3_set_features,
+	.ndo_fix_features	= qeth_fix_features,
+	.ndo_set_features	= qeth_set_features,
 	.ndo_vlan_rx_add_vid	= qeth_l3_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = qeth_l3_vlan_rx_kill_vid,
 	.ndo_tx_timeout		= qeth_tx_timeout,
@@ -3136,8 +3072,8 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = {
 	.ndo_set_rx_mode	= qeth_l3_set_multicast_list,
 	.ndo_do_ioctl		= qeth_l3_do_ioctl,
 	.ndo_change_mtu		= qeth_change_mtu,
-	.ndo_fix_features	= qeth_l3_fix_features,
-	.ndo_set_features	= qeth_l3_set_features,
+	.ndo_fix_features	= qeth_fix_features,
+	.ndo_set_features	= qeth_set_features,
 	.ndo_vlan_rx_add_vid	= qeth_l3_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = qeth_l3_vlan_rx_kill_vid,
 	.ndo_tx_timeout		= qeth_tx_timeout,
@@ -3169,7 +3105,10 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 				card->dev->hw_features = NETIF_F_SG |
 					NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
 					NETIF_F_TSO;
-				card->dev->features = NETIF_F_RXCSUM;
+				card->dev->vlan_features = NETIF_F_SG |
+					NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
+					NETIF_F_TSO;
+				card->dev->features = NETIF_F_SG;
 			}
 		}
 	} else if (card->info.type == QETH_CARD_TYPE_IQD) {
@@ -3195,7 +3134,9 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 	netif_keep_dst(card->dev);
-	card->dev->gso_max_size = 15 * PAGE_SIZE;
+	card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
+				  PAGE_SIZE;
+	card->dev->gso_max_segs = (QETH_MAX_BUFFER_ELEMENTS(card) - 1);
 
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_l3_poll, QETH_NAPI_WEIGHT);
@@ -3230,7 +3171,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 		card->dev = NULL;
 	}
 
-	qeth_l3_clear_ip_list(card, 0);
+	qeth_l3_clear_ip_htable(card, 0);
 	qeth_l3_clear_ipato_list(card);
 	return;
 }
@@ -3315,7 +3256,7 @@ contin:
 	card->state = CARD_STATE_SOFTSETUP;
 
 	qeth_set_allowed_threads(card, 0xffffffff, 0);
-	qeth_l3_set_ip_addr_list(card);
+	qeth_l3_recover_ip(card);
 	if (card->lan_online)
 		netif_carrier_on(card->dev);
 	else
@@ -3516,6 +3457,7 @@ EXPORT_SYMBOL_GPL(qeth_l3_discipline);
 static int qeth_l3_ip_event(struct notifier_block *this,
 			    unsigned long event, void *ptr)
 {
+
 	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
 	struct net_device *dev = (struct net_device *)ifa->ifa_dev->dev;
 	struct qeth_ipaddr *addr;
@@ -3530,27 +3472,27 @@ static int qeth_l3_ip_event(struct notifier_block *this,
 	QETH_CARD_TEXT(card, 3, "ipevent");
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
-	if (addr != NULL) {
+	if (addr) {
 		addr->u.a4.addr = ifa->ifa_address;
 		addr->u.a4.mask = ifa->ifa_mask;
 		addr->type = QETH_IP_TYPE_NORMAL;
 	} else
-		goto out;
+		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_UP:
-		if (!qeth_l3_add_ip(card, addr))
-			kfree(addr);
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_add_ip(card, addr);
+		spin_unlock_bh(&card->ip_lock);
 		break;
 	case NETDEV_DOWN:
-		if (!qeth_l3_delete_ip(card, addr))
-			kfree(addr);
-		break;
-	default:
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_delete_ip(card, addr);
+		spin_unlock_bh(&card->ip_lock);
 		break;
 	}
-	qeth_l3_set_ip_addr_list(card);
-out:
+
+	kfree(addr);
 	return NOTIFY_DONE;
 }
 
@@ -3579,27 +3521,27 @@ static int qeth_l3_ip6_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
-	if (addr != NULL) {
+	if (addr) {
 		memcpy(&addr->u.a6.addr, &ifa->addr, sizeof(struct in6_addr));
 		addr->u.a6.pfxlen = ifa->prefix_len;
 		addr->type = QETH_IP_TYPE_NORMAL;
 	} else
-		goto out;
+		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_UP:
-		if (!qeth_l3_add_ip(card, addr))
-			kfree(addr);
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_add_ip(card, addr);
+		spin_unlock_bh(&card->ip_lock);
 		break;
 	case NETDEV_DOWN:
-		if (!qeth_l3_delete_ip(card, addr))
-			kfree(addr);
-		break;
-	default:
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_delete_ip(card, addr);
+		spin_unlock_bh(&card->ip_lock);
 		break;
 	}
-	qeth_l3_set_ip_addr_list(card);
-out:
+
+	kfree(addr);
 	return NOTIFY_DONE;
 }
 
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 386eb7b89b1e..65645b11fc19 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -8,6 +8,7 @@
 
 #include <linux/slab.h>
 #include <asm/ebcdic.h>
+#include <linux/hashtable.h>
 #include "qeth_l3.h"
 
 #define QETH_DEVICE_ATTR(_id, _name, _mode, _show, _store) \
@@ -285,19 +286,19 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
 	if (card->options.hsuid[0]) {
 		/* delete old ip address */
 		addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
-		if (addr != NULL) {
-			addr->u.a6.addr.s6_addr32[0] = 0xfe800000;
-			addr->u.a6.addr.s6_addr32[1] = 0x00000000;
-			for (i = 8; i < 16; i++)
-				addr->u.a6.addr.s6_addr[i] =
-					card->options.hsuid[i - 8];
-			addr->u.a6.pfxlen = 0;
-			addr->type = QETH_IP_TYPE_NORMAL;
-		} else
+		if (!addr)
 			return -ENOMEM;
-		if (!qeth_l3_delete_ip(card, addr))
-			kfree(addr);
-		qeth_l3_set_ip_addr_list(card);
+
+		addr->u.a6.addr.s6_addr32[0] = 0xfe800000;
+		addr->u.a6.addr.s6_addr32[1] = 0x00000000;
+		for (i = 8; i < 16; i++)
+			addr->u.a6.addr.s6_addr[i] =
+				card->options.hsuid[i - 8];
+		addr->u.a6.pfxlen = 0;
+		addr->type = QETH_IP_TYPE_NORMAL;
+
+		qeth_l3_delete_ip(card, addr);
+		kfree(addr);
 	}
 
 	if (strlen(tmp) == 0) {
@@ -328,9 +329,8 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
 		addr->type = QETH_IP_TYPE_NORMAL;
 	} else
 		return -ENOMEM;
-	if (!qeth_l3_add_ip(card, addr))
-		kfree(addr);
-	qeth_l3_set_ip_addr_list(card);
+	qeth_l3_add_ip(card, addr);
+	kfree(addr);
 
 	return count;
 }
@@ -367,8 +367,8 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
-	struct qeth_ipaddr *tmpipa, *t;
-	int rc = 0;
+	struct qeth_ipaddr *addr;
+	int i, rc = 0;
 
 	if (!card)
 		return -EINVAL;
@@ -384,21 +384,20 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 		card->ipato.enabled = (card->ipato.enabled)? 0 : 1;
 	} else if (sysfs_streq(buf, "1")) {
 		card->ipato.enabled = 1;
-		list_for_each_entry_safe(tmpipa, t, card->ip_tbd_list, entry) {
-			if ((tmpipa->type == QETH_IP_TYPE_NORMAL) &&
-				qeth_l3_is_addr_covered_by_ipato(card, tmpipa))
-				tmpipa->set_flags |=
+		hash_for_each(card->ip_htable, i, addr, hnode) {
+				if ((addr->type == QETH_IP_TYPE_NORMAL) &&
+				qeth_l3_is_addr_covered_by_ipato(card, addr))
+					addr->set_flags |=
 					QETH_IPA_SETIP_TAKEOVER_FLAG;
-		}
-
+			}
 	} else if (sysfs_streq(buf, "0")) {
 		card->ipato.enabled = 0;
-		list_for_each_entry_safe(tmpipa, t, card->ip_tbd_list, entry) {
-			if (tmpipa->set_flags &
-				QETH_IPA_SETIP_TAKEOVER_FLAG)
-				tmpipa->set_flags &=
-					~QETH_IPA_SETIP_TAKEOVER_FLAG;
-		}
+		hash_for_each(card->ip_htable, i, addr, hnode) {
+			if (addr->set_flags &
+			QETH_IPA_SETIP_TAKEOVER_FLAG)
+				addr->set_flags &=
+				~QETH_IPA_SETIP_TAKEOVER_FLAG;
+			}
 	} else
 		rc = -EINVAL;
 out:
@@ -452,7 +451,6 @@ static ssize_t qeth_l3_dev_ipato_add_show(char *buf, struct qeth_card *card,
 			enum qeth_prot_versions proto)
 {
 	struct qeth_ipato_entry *ipatoe;
-	unsigned long flags;
 	char addr_str[40];
 	int entry_len; /* length of 1 entry string, differs between v4 and v6 */
 	int i = 0;
@@ -460,7 +458,7 @@ static ssize_t qeth_l3_dev_ipato_add_show(char *buf, struct qeth_card *card,
 	entry_len = (proto == QETH_PROT_IPV4)? 12 : 40;
 	/* add strlen for "/<mask>\n" */
 	entry_len += (proto == QETH_PROT_IPV4)? 5 : 6;
-	spin_lock_irqsave(&card->ip_lock, flags);
+	spin_lock_bh(&card->ip_lock);
 	list_for_each_entry(ipatoe, &card->ipato.entries, entry) {
 		if (ipatoe->proto != proto)
 			continue;
@@ -473,7 +471,7 @@ static ssize_t qeth_l3_dev_ipato_add_show(char *buf, struct qeth_card *card,
 		i += snprintf(buf + i, PAGE_SIZE - i,
 			      "%s/%i\n", addr_str, ipatoe->mask_bits);
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+	spin_unlock_bh(&card->ip_lock);
 	i += snprintf(buf + i, PAGE_SIZE - i, "\n");
 
 	return i;
@@ -689,15 +687,15 @@ static ssize_t qeth_l3_dev_vipa_add_show(char *buf, struct qeth_card *card,
 			enum qeth_prot_versions proto)
 {
 	struct qeth_ipaddr *ipaddr;
+	struct hlist_node  *tmp;
 	char addr_str[40];
 	int entry_len; /* length of 1 entry string, differs between v4 and v6 */
-	unsigned long flags;
 	int i = 0;
 
 	entry_len = (proto == QETH_PROT_IPV4)? 12 : 40;
 	entry_len += 2; /* \n + terminator */
-	spin_lock_irqsave(&card->ip_lock, flags);
-	list_for_each_entry(ipaddr, &card->ip_list, entry) {
+	spin_lock_bh(&card->ip_lock);
+	hash_for_each_safe(card->ip_htable, i, tmp, ipaddr, hnode) {
 		if (ipaddr->proto != proto)
 			continue;
 		if (ipaddr->type != QETH_IP_TYPE_VIPA)
@@ -711,7 +709,7 @@ static ssize_t qeth_l3_dev_vipa_add_show(char *buf, struct qeth_card *card,
 			addr_str);
 		i += snprintf(buf + i, PAGE_SIZE - i, "%s\n", addr_str);
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+	spin_unlock_bh(&card->ip_lock);
 	i += snprintf(buf + i, PAGE_SIZE - i, "\n");
 
 	return i;
@@ -851,15 +849,15 @@ static ssize_t qeth_l3_dev_rxip_add_show(char *buf, struct qeth_card *card,
 		       enum qeth_prot_versions proto)
 {
 	struct qeth_ipaddr *ipaddr;
+	struct hlist_node *tmp;
 	char addr_str[40];
 	int entry_len; /* length of 1 entry string, differs between v4 and v6 */
-	unsigned long flags;
 	int i = 0;
 
 	entry_len = (proto == QETH_PROT_IPV4)? 12 : 40;
 	entry_len += 2; /* \n + terminator */
-	spin_lock_irqsave(&card->ip_lock, flags);
-	list_for_each_entry(ipaddr, &card->ip_list, entry) {
+	spin_lock_bh(&card->ip_lock);
+	hash_for_each_safe(card->ip_htable, i, tmp, ipaddr, hnode) {
 		if (ipaddr->proto != proto)
 			continue;
 		if (ipaddr->type != QETH_IP_TYPE_RXIP)
@@ -873,7 +871,7 @@ static ssize_t qeth_l3_dev_rxip_add_show(char *buf, struct qeth_card *card,
 			addr_str);
 		i += snprintf(buf + i, PAGE_SIZE - i, "%s\n", addr_str);
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+	spin_unlock_bh(&card->ip_lock);
 	i += snprintf(buf + i, PAGE_SIZE - i, "\n");
 
 	return i;
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index d4c285688ce9..3ddc85e6efd6 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -1122,7 +1122,7 @@ process_script_interrupt(__u32 dsps, __u32 dsp, struct scsi_cmnd *SCp,
 		} else {
 			struct scsi_cmnd *SCp;
 
-			SCp = scsi_host_find_tag(SDp->host, SCSI_NO_TAG);
+			SCp = SDp->current_cmnd;
 			if(unlikely(SCp == NULL)) {
 				sdev_printk(KERN_ERR, SDp,
 					"no saved request for untagged cmd\n");
@@ -1826,7 +1826,7 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *)
 		       slot->tag, slot);
 	} else {
 		slot->tag = SCSI_NO_TAG;
-		/* must populate current_cmnd for scsi_host_find_tag to work */
+		/* save current command for reselection */
 		SCp->device->current_cmnd = SCp;
 	}
 	/* sanity check: some of the commands generated by the mid-layer
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index 3408578b08d6..ff41c310c900 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -230,6 +230,7 @@ static struct {
 	{"PIONEER", "CD-ROM DRM-624X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC},
 	{"Promise", "", NULL, BLIST_SPARSELUN},
+	{"QEMU", "QEMU CD-ROM", NULL, BLIST_SKIP_VPD_PAGES},
 	{"QNAP", "iSCSI Storage", NULL, BLIST_MAX_1024},
 	{"SYNOLOGY", "iSCSI Storage", NULL, BLIST_MAX_1024},
 	{"QUANTUM", "XP34301", "1071", BLIST_NOTQ},
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index a8b610eaa0ca..106a6adbd6f1 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1128,7 +1128,6 @@ static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn)
  */
 void scsi_eh_finish_cmd(struct scsi_cmnd *scmd, struct list_head *done_q)
 {
-	scmd->device->host->host_failed--;
 	scmd->eh_eflags = 0;
 	list_move_tail(&scmd->eh_entry, done_q);
 }
@@ -2227,6 +2226,9 @@ int scsi_error_handler(void *data)
 		else
 			scsi_unjam_host(shost);
 
+		/* All scmds have been handled */
+		shost->host_failed = 0;
+
 		/*
 		 * Note - if the above fails completely, the action is to take
 		 * individual devices offline and flush the queue of any
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index f459dff30512..60bff78e9ead 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2867,10 +2867,10 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	if (sdkp->opt_xfer_blocks &&
 	    sdkp->opt_xfer_blocks <= dev_max &&
 	    sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS &&
-	    sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_SIZE)
-		rw_max = q->limits.io_opt =
-			sdkp->opt_xfer_blocks * sdp->sector_size;
-	else
+	    logical_to_bytes(sdp, sdkp->opt_xfer_blocks) >= PAGE_SIZE) {
+		q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
+		rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
+	} else
 		rw_max = BLK_DEF_MAX_SECTORS;
 
 	/* Combine with controller limits */
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 654630bb7d0e..765a6f1ac1b7 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -151,6 +151,11 @@ static inline sector_t logical_to_sectors(struct scsi_device *sdev, sector_t blo
 	return blocks << (ilog2(sdev->sector_size) - 9);
 }
 
+static inline unsigned int logical_to_bytes(struct scsi_device *sdev, sector_t blocks)
+{
+	return blocks * sdev->sector_size;
+}
+
 /*
  * A DIF-capable target device can be formatted with different
  * protection schemes.  Currently 0 through 3 are defined:
diff --git a/drivers/soc/fsl/qe/Kconfig b/drivers/soc/fsl/qe/Kconfig
index 20978f2058a6..73a2e08b47ef 100644
--- a/drivers/soc/fsl/qe/Kconfig
+++ b/drivers/soc/fsl/qe/Kconfig
@@ -22,7 +22,7 @@ config UCC_SLOW
 
 config UCC_FAST
 	bool
-	default y if UCC_GETH
+	default y if UCC_GETH || QE_TDM
 	help
 	  This option provides qe_lib support to UCC fast
 	  protocols: HDLC, Ethernet, ATM, transparent
@@ -31,6 +31,10 @@ config UCC
 	bool
 	default y if UCC_FAST || UCC_SLOW
 
+config QE_TDM
+	bool
+	default y if FSL_UCC_HDLC
+
 config QE_USB
 	bool
 	default y if USB_FSL_QE
diff --git a/drivers/soc/fsl/qe/Makefile b/drivers/soc/fsl/qe/Makefile
index ffac5410c5c7..2031d385bc7e 100644
--- a/drivers/soc/fsl/qe/Makefile
+++ b/drivers/soc/fsl/qe/Makefile
@@ -6,5 +6,6 @@ obj-$(CONFIG_CPM)	+= qe_common.o
 obj-$(CONFIG_UCC)	+= ucc.o
 obj-$(CONFIG_UCC_SLOW)	+= ucc_slow.o
 obj-$(CONFIG_UCC_FAST)	+= ucc_fast.o
+obj-$(CONFIG_QE_TDM)	+= qe_tdm.o
 obj-$(CONFIG_QE_USB)	+= usb.o
 obj-$(CONFIG_QE_GPIO)	+= gpio.o
diff --git a/drivers/soc/fsl/qe/qe.c b/drivers/soc/fsl/qe/qe.c
index 709fc63809e5..7026507e6f1d 100644
--- a/drivers/soc/fsl/qe/qe.c
+++ b/drivers/soc/fsl/qe/qe.c
@@ -239,6 +239,12 @@ enum qe_clock qe_clock_source(const char *source)
 	if (strcasecmp(source, "none") == 0)
 		return QE_CLK_NONE;
 
+	if (strcmp(source, "tsync_pin") == 0)
+		return QE_TSYNC_PIN;
+
+	if (strcmp(source, "rsync_pin") == 0)
+		return QE_RSYNC_PIN;
+
 	if (strncasecmp(source, "brg", 3) == 0) {
 		i = simple_strtoul(source + 3, NULL, 10);
 		if ((i >= 1) && (i <= 16))
diff --git a/drivers/soc/fsl/qe/qe_tdm.c b/drivers/soc/fsl/qe/qe_tdm.c
new file mode 100644
index 000000000000..5e48b1470178
--- /dev/null
+++ b/drivers/soc/fsl/qe/qe_tdm.c
@@ -0,0 +1,276 @@
+/*
+ * Copyright (C) 2015 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Authors:	Zhao Qiang <[email protected]>
+ *
+ * Description:
+ * QE TDM API Set - TDM specific routines implementations.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <soc/fsl/qe/qe_tdm.h>
+
+static int set_tdm_framer(const char *tdm_framer_type)
+{
+	if (strcmp(tdm_framer_type, "e1") == 0)
+		return TDM_FRAMER_E1;
+	else if (strcmp(tdm_framer_type, "t1") == 0)
+		return TDM_FRAMER_T1;
+	else
+		return -EINVAL;
+}
+
+static void set_si_param(struct ucc_tdm *utdm, struct ucc_tdm_info *ut_info)
+{
+	struct si_mode_info *si_info = &ut_info->si_info;
+
+	if (utdm->tdm_mode == TDM_INTERNAL_LOOPBACK) {
+		si_info->simr_crt = 1;
+		si_info->simr_rfsd = 0;
+	}
+}
+
+int ucc_of_parse_tdm(struct device_node *np, struct ucc_tdm *utdm,
+		     struct ucc_tdm_info *ut_info)
+{
+	const char *sprop;
+	int ret = 0;
+	u32 val;
+	struct resource *res;
+	struct device_node *np2;
+	static int siram_init_flag;
+	struct platform_device *pdev;
+
+	sprop = of_get_property(np, "fsl,rx-sync-clock", NULL);
+	if (sprop) {
+		ut_info->uf_info.rx_sync = qe_clock_source(sprop);
+		if ((ut_info->uf_info.rx_sync < QE_CLK_NONE) ||
+		    (ut_info->uf_info.rx_sync > QE_RSYNC_PIN)) {
+			pr_err("QE-TDM: Invalid rx-sync-clock property\n");
+			return -EINVAL;
+		}
+	} else {
+		pr_err("QE-TDM: Invalid rx-sync-clock property\n");
+		return -EINVAL;
+	}
+
+	sprop = of_get_property(np, "fsl,tx-sync-clock", NULL);
+	if (sprop) {
+		ut_info->uf_info.tx_sync = qe_clock_source(sprop);
+		if ((ut_info->uf_info.tx_sync < QE_CLK_NONE) ||
+		    (ut_info->uf_info.tx_sync > QE_TSYNC_PIN)) {
+			pr_err("QE-TDM: Invalid tx-sync-clock property\n");
+		return -EINVAL;
+		}
+	} else {
+		pr_err("QE-TDM: Invalid tx-sync-clock property\n");
+		return -EINVAL;
+	}
+
+	ret = of_property_read_u32_index(np, "fsl,tx-timeslot-mask", 0, &val);
+	if (ret) {
+		pr_err("QE-TDM: Invalid tx-timeslot-mask property\n");
+		return -EINVAL;
+	}
+	utdm->tx_ts_mask = val;
+
+	ret = of_property_read_u32_index(np, "fsl,rx-timeslot-mask", 0, &val);
+	if (ret) {
+		ret = -EINVAL;
+		pr_err("QE-TDM: Invalid rx-timeslot-mask property\n");
+		return ret;
+	}
+	utdm->rx_ts_mask = val;
+
+	ret = of_property_read_u32_index(np, "fsl,tdm-id", 0, &val);
+	if (ret) {
+		ret = -EINVAL;
+		pr_err("QE-TDM: No fsl,tdm-id property for this UCC\n");
+		return ret;
+	}
+	utdm->tdm_port = val;
+	ut_info->uf_info.tdm_num = utdm->tdm_port;
+
+	if (of_get_property(np, "fsl,tdm-internal-loopback", NULL))
+		utdm->tdm_mode = TDM_INTERNAL_LOOPBACK;
+	else
+		utdm->tdm_mode = TDM_NORMAL;
+
+	sprop = of_get_property(np, "fsl,tdm-framer-type", NULL);
+	if (!sprop) {
+		ret = -EINVAL;
+		pr_err("QE-TDM: No tdm-framer-type property for UCC\n");
+		return ret;
+	}
+	ret = set_tdm_framer(sprop);
+	if (ret < 0)
+		return -EINVAL;
+	utdm->tdm_framer_type = ret;
+
+	ret = of_property_read_u32_index(np, "fsl,siram-entry-id", 0, &val);
+	if (ret) {
+		ret = -EINVAL;
+		pr_err("QE-TDM: No siram entry id for UCC\n");
+		return ret;
+	}
+	utdm->siram_entry_id = val;
+
+	set_si_param(utdm, ut_info);
+
+	np2 = of_find_compatible_node(NULL, NULL, "fsl,t1040-qe-si");
+	if (!np2)
+		return -EINVAL;
+
+	pdev = of_find_device_by_node(np2);
+	if (!pdev) {
+		pr_err("%s: failed to lookup pdev\n", np2->name);
+		of_node_put(np2);
+		return -EINVAL;
+	}
+
+	of_node_put(np2);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	utdm->si_regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(utdm->si_regs)) {
+		ret = PTR_ERR(utdm->si_regs);
+		goto err_miss_siram_property;
+	}
+
+	np2 = of_find_compatible_node(NULL, NULL, "fsl,t1040-qe-siram");
+	if (!np2) {
+		ret = -EINVAL;
+		goto err_miss_siram_property;
+	}
+
+	pdev = of_find_device_by_node(np2);
+	if (!pdev) {
+		ret = -EINVAL;
+		pr_err("%s: failed to lookup pdev\n", np2->name);
+		of_node_put(np2);
+		goto err_miss_siram_property;
+	}
+
+	of_node_put(np2);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	utdm->siram = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(utdm->siram)) {
+		ret = PTR_ERR(utdm->siram);
+		goto err_miss_siram_property;
+	}
+
+	if (siram_init_flag == 0) {
+		memset_io(utdm->siram, 0,  res->end - res->start + 1);
+		siram_init_flag = 1;
+	}
+
+	return ret;
+
+err_miss_siram_property:
+	devm_iounmap(&pdev->dev, utdm->si_regs);
+	return ret;
+}
+
+void ucc_tdm_init(struct ucc_tdm *utdm, struct ucc_tdm_info *ut_info)
+{
+	struct si1 __iomem *si_regs;
+	u16 __iomem *siram;
+	u16 siram_entry_valid;
+	u16 siram_entry_closed;
+	u16 ucc_num;
+	u8 csel;
+	u16 sixmr;
+	u16 tdm_port;
+	u32 siram_entry_id;
+	u32 mask;
+	int i;
+
+	si_regs = utdm->si_regs;
+	siram = utdm->siram;
+	ucc_num = ut_info->uf_info.ucc_num;
+	tdm_port = utdm->tdm_port;
+	siram_entry_id = utdm->siram_entry_id;
+
+	if (utdm->tdm_framer_type == TDM_FRAMER_T1)
+		utdm->num_of_ts = 24;
+	if (utdm->tdm_framer_type == TDM_FRAMER_E1)
+		utdm->num_of_ts = 32;
+
+	/* set siram table */
+	csel = (ucc_num < 4) ? ucc_num + 9 : ucc_num - 3;
+
+	siram_entry_valid = SIR_CSEL(csel) | SIR_BYTE | SIR_CNT(0);
+	siram_entry_closed = SIR_IDLE | SIR_BYTE | SIR_CNT(0);
+
+	for (i = 0; i < utdm->num_of_ts; i++) {
+		mask = 0x01 << i;
+
+		if (utdm->tx_ts_mask & mask)
+			iowrite16be(siram_entry_valid,
+				    &siram[siram_entry_id * 32 + i]);
+		else
+			iowrite16be(siram_entry_closed,
+				    &siram[siram_entry_id * 32 + i]);
+
+		if (utdm->rx_ts_mask & mask)
+			iowrite16be(siram_entry_valid,
+				    &siram[siram_entry_id * 32 + 0x200 +  i]);
+		else
+			iowrite16be(siram_entry_closed,
+				    &siram[siram_entry_id * 32 + 0x200 +  i]);
+	}
+
+	setbits16(&siram[(siram_entry_id * 32) + (utdm->num_of_ts - 1)],
+		  SIR_LAST);
+	setbits16(&siram[(siram_entry_id * 32) + 0x200 + (utdm->num_of_ts - 1)],
+		  SIR_LAST);
+
+	/* Set SIxMR register */
+	sixmr = SIMR_SAD(siram_entry_id);
+
+	sixmr &= ~SIMR_SDM_MASK;
+
+	if (utdm->tdm_mode == TDM_INTERNAL_LOOPBACK)
+		sixmr |= SIMR_SDM_INTERNAL_LOOPBACK;
+	else
+		sixmr |= SIMR_SDM_NORMAL;
+
+	sixmr |= SIMR_RFSD(ut_info->si_info.simr_rfsd) |
+			SIMR_TFSD(ut_info->si_info.simr_tfsd);
+
+	if (ut_info->si_info.simr_crt)
+		sixmr |= SIMR_CRT;
+	if (ut_info->si_info.simr_sl)
+		sixmr |= SIMR_SL;
+	if (ut_info->si_info.simr_ce)
+		sixmr |= SIMR_CE;
+	if (ut_info->si_info.simr_fe)
+		sixmr |= SIMR_FE;
+	if (ut_info->si_info.simr_gm)
+		sixmr |= SIMR_GM;
+
+	switch (tdm_port) {
+	case 0:
+		iowrite16be(sixmr, &si_regs->sixmr1[0]);
+		break;
+	case 1:
+		iowrite16be(sixmr, &si_regs->sixmr1[1]);
+		break;
+	case 2:
+		iowrite16be(sixmr, &si_regs->sixmr1[2]);
+		break;
+	case 3:
+		iowrite16be(sixmr, &si_regs->sixmr1[3]);
+		break;
+	default:
+		pr_err("QE-TDM: can not find tdm sixmr reg\n");
+		break;
+	}
+}
diff --git a/drivers/soc/fsl/qe/ucc.c b/drivers/soc/fsl/qe/ucc.c
index b59d3358f9bd..c646d8713861 100644
--- a/drivers/soc/fsl/qe/ucc.c
+++ b/drivers/soc/fsl/qe/ucc.c
@@ -25,6 +25,12 @@
 #include <soc/fsl/qe/qe.h>
 #include <soc/fsl/qe/ucc.h>
 
+#define UCC_TDM_NUM 8
+#define RX_SYNC_SHIFT_BASE 30
+#define TX_SYNC_SHIFT_BASE 14
+#define RX_CLK_SHIFT_BASE 28
+#define TX_CLK_SHIFT_BASE 12
+
 int ucc_set_qe_mux_mii_mng(unsigned int ucc_num)
 {
 	unsigned long flags;
@@ -210,3 +216,447 @@ int ucc_set_qe_mux_rxtx(unsigned int ucc_num, enum qe_clock clock,
 
 	return 0;
 }
+
+static int ucc_get_tdm_common_clk(u32 tdm_num, enum qe_clock clock)
+{
+	int clock_bits = -EINVAL;
+
+	/*
+	 * for TDM[0, 1, 2, 3], TX and RX use  common
+	 * clock source BRG3,4 and CLK1,2
+	 * for TDM[4, 5, 6, 7], TX and RX use  common
+	 * clock source BRG12,13 and CLK23,24
+	 */
+	switch (tdm_num) {
+	case 0:
+	case 1:
+	case 2:
+	case 3:
+		switch (clock) {
+		case QE_BRG3:
+			clock_bits = 1;
+			break;
+		case QE_BRG4:
+			clock_bits = 2;
+			break;
+		case QE_CLK1:
+			clock_bits = 4;
+			break;
+		case QE_CLK2:
+			clock_bits = 5;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 4:
+	case 5:
+	case 6:
+	case 7:
+		switch (clock) {
+		case QE_BRG12:
+			clock_bits = 1;
+			break;
+		case QE_BRG13:
+			clock_bits = 2;
+			break;
+		case QE_CLK23:
+			clock_bits = 4;
+			break;
+		case QE_CLK24:
+			clock_bits = 5;
+			break;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return clock_bits;
+}
+
+static int ucc_get_tdm_rx_clk(u32 tdm_num, enum qe_clock clock)
+{
+	int clock_bits = -EINVAL;
+
+	switch (tdm_num) {
+	case 0:
+		switch (clock) {
+		case QE_CLK3:
+			clock_bits = 6;
+			break;
+		case QE_CLK8:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 1:
+		switch (clock) {
+		case QE_CLK5:
+			clock_bits = 6;
+			break;
+		case QE_CLK10:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 2:
+		switch (clock) {
+		case QE_CLK7:
+			clock_bits = 6;
+			break;
+		case QE_CLK12:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 3:
+		switch (clock) {
+		case QE_CLK9:
+			clock_bits = 6;
+			break;
+		case QE_CLK14:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 4:
+		switch (clock) {
+		case QE_CLK11:
+			clock_bits = 6;
+			break;
+		case QE_CLK16:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 5:
+		switch (clock) {
+		case QE_CLK13:
+			clock_bits = 6;
+			break;
+		case QE_CLK18:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 6:
+		switch (clock) {
+		case QE_CLK15:
+			clock_bits = 6;
+			break;
+		case QE_CLK20:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 7:
+		switch (clock) {
+		case QE_CLK17:
+			clock_bits = 6;
+			break;
+		case QE_CLK22:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	}
+
+	return clock_bits;
+}
+
+static int ucc_get_tdm_tx_clk(u32 tdm_num, enum qe_clock clock)
+{
+	int clock_bits = -EINVAL;
+
+	switch (tdm_num) {
+	case 0:
+		switch (clock) {
+		case QE_CLK4:
+			clock_bits = 6;
+			break;
+		case QE_CLK9:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 1:
+		switch (clock) {
+		case QE_CLK6:
+			clock_bits = 6;
+			break;
+		case QE_CLK11:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 2:
+		switch (clock) {
+		case QE_CLK8:
+			clock_bits = 6;
+			break;
+		case QE_CLK13:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 3:
+		switch (clock) {
+		case QE_CLK10:
+			clock_bits = 6;
+			break;
+		case QE_CLK15:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 4:
+		switch (clock) {
+		case QE_CLK12:
+			clock_bits = 6;
+			break;
+		case QE_CLK17:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 5:
+		switch (clock) {
+		case QE_CLK14:
+			clock_bits = 6;
+			break;
+		case QE_CLK19:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 6:
+		switch (clock) {
+		case QE_CLK16:
+			clock_bits = 6;
+			break;
+		case QE_CLK21:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 7:
+		switch (clock) {
+		case QE_CLK18:
+			clock_bits = 6;
+			break;
+		case QE_CLK3:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	}
+
+	return clock_bits;
+}
+
+/* tdm_num: TDM A-H port num is 0-7 */
+static int ucc_get_tdm_rxtx_clk(enum comm_dir mode, u32 tdm_num,
+				enum qe_clock clock)
+{
+	int clock_bits;
+
+	clock_bits = ucc_get_tdm_common_clk(tdm_num, clock);
+	if (clock_bits > 0)
+		return clock_bits;
+	if (mode == COMM_DIR_RX)
+		clock_bits = ucc_get_tdm_rx_clk(tdm_num, clock);
+	if (mode == COMM_DIR_TX)
+		clock_bits = ucc_get_tdm_tx_clk(tdm_num, clock);
+	return clock_bits;
+}
+
+static u32 ucc_get_tdm_clk_shift(enum comm_dir mode, u32 tdm_num)
+{
+	u32 shift;
+
+	shift = (mode == COMM_DIR_RX) ? RX_CLK_SHIFT_BASE : TX_CLK_SHIFT_BASE;
+	if (tdm_num < 4)
+		shift -= tdm_num * 4;
+	else
+		shift -= (tdm_num - 4) * 4;
+
+	return shift;
+}
+
+int ucc_set_tdm_rxtx_clk(u32 tdm_num, enum qe_clock clock,
+			 enum comm_dir mode)
+{
+	int clock_bits;
+	u32 shift;
+	struct qe_mux __iomem *qe_mux_reg;
+	 __be32 __iomem *cmxs1cr;
+
+	qe_mux_reg = &qe_immr->qmx;
+
+	if (tdm_num > 7 || tdm_num < 0)
+		return -EINVAL;
+
+	/* The communications direction must be RX or TX */
+	if (mode != COMM_DIR_RX && mode != COMM_DIR_TX)
+		return -EINVAL;
+
+	clock_bits = ucc_get_tdm_rxtx_clk(mode, tdm_num, clock);
+	if (clock_bits < 0)
+		return -EINVAL;
+
+	shift = ucc_get_tdm_clk_shift(mode, tdm_num);
+
+	cmxs1cr = (tdm_num < 4) ? &qe_mux_reg->cmxsi1cr_l :
+				  &qe_mux_reg->cmxsi1cr_h;
+
+	qe_clrsetbits32(cmxs1cr, QE_CMXUCR_TX_CLK_SRC_MASK << shift,
+			clock_bits << shift);
+
+	return 0;
+}
+
+static int ucc_get_tdm_sync_source(u32 tdm_num, enum qe_clock clock,
+				   enum comm_dir mode)
+{
+	int source = -EINVAL;
+
+	if (mode == COMM_DIR_RX && clock == QE_RSYNC_PIN) {
+		source = 0;
+		return source;
+	}
+	if (mode == COMM_DIR_TX && clock == QE_TSYNC_PIN) {
+		source = 0;
+		return source;
+	}
+
+	switch (tdm_num) {
+	case 0:
+	case 1:
+		switch (clock) {
+		case QE_BRG9:
+			source = 1;
+			break;
+		case QE_BRG10:
+			source = 2;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 2:
+	case 3:
+		switch (clock) {
+		case QE_BRG9:
+			source = 1;
+			break;
+		case QE_BRG11:
+			source = 2;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 4:
+	case 5:
+		switch (clock) {
+		case QE_BRG13:
+			source = 1;
+			break;
+		case QE_BRG14:
+			source = 2;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 6:
+	case 7:
+		switch (clock) {
+		case QE_BRG13:
+			source = 1;
+			break;
+		case QE_BRG15:
+			source = 2;
+			break;
+		default:
+			break;
+		}
+		break;
+	}
+
+	return source;
+}
+
+static u32 ucc_get_tdm_sync_shift(enum comm_dir mode, u32 tdm_num)
+{
+	u32 shift;
+
+	shift = (mode == COMM_DIR_RX) ? RX_SYNC_SHIFT_BASE : RX_SYNC_SHIFT_BASE;
+	shift -= tdm_num * 2;
+
+	return shift;
+}
+
+int ucc_set_tdm_rxtx_sync(u32 tdm_num, enum qe_clock clock,
+			  enum comm_dir mode)
+{
+	int source;
+	u32 shift;
+	struct qe_mux *qe_mux_reg;
+
+	qe_mux_reg = &qe_immr->qmx;
+
+	if (tdm_num >= UCC_TDM_NUM)
+		return -EINVAL;
+
+	/* The communications direction must be RX or TX */
+	if (mode != COMM_DIR_RX && mode != COMM_DIR_TX)
+		return -EINVAL;
+
+	source = ucc_get_tdm_sync_source(tdm_num, clock, mode);
+	if (source < 0)
+		return -EINVAL;
+
+	shift = ucc_get_tdm_sync_shift(mode, tdm_num);
+
+	qe_clrsetbits32(&qe_mux_reg->cmxsi1syr,
+			QE_CMXUCR_TX_CLK_SRC_MASK << shift,
+			source << shift);
+
+	return 0;
+}
diff --git a/drivers/soc/fsl/qe/ucc_fast.c b/drivers/soc/fsl/qe/ucc_fast.c
index a7689310fe40..83d8d16e3a69 100644
--- a/drivers/soc/fsl/qe/ucc_fast.c
+++ b/drivers/soc/fsl/qe/ucc_fast.c
@@ -327,6 +327,42 @@ int ucc_fast_init(struct ucc_fast_info * uf_info, struct ucc_fast_private ** ucc
 			ucc_fast_free(uccf);
 			return -EINVAL;
 		}
+	} else {
+		/* tdm Rx clock routing */
+		if ((uf_info->rx_clock != QE_CLK_NONE) &&
+		    ucc_set_tdm_rxtx_clk(uf_info->tdm_num, uf_info->rx_clock,
+					 COMM_DIR_RX)) {
+			pr_err("%s: illegal value for RX clock", __func__);
+			ucc_fast_free(uccf);
+			return -EINVAL;
+		}
+
+		/* tdm Tx clock routing */
+		if ((uf_info->tx_clock != QE_CLK_NONE) &&
+		    ucc_set_tdm_rxtx_clk(uf_info->tdm_num, uf_info->tx_clock,
+					 COMM_DIR_TX)) {
+			pr_err("%s: illegal value for TX clock", __func__);
+			ucc_fast_free(uccf);
+			return -EINVAL;
+		}
+
+		/* tdm Rx sync clock routing */
+		if ((uf_info->rx_sync != QE_CLK_NONE) &&
+		    ucc_set_tdm_rxtx_sync(uf_info->tdm_num, uf_info->rx_sync,
+					  COMM_DIR_RX)) {
+			pr_err("%s: illegal value for RX clock", __func__);
+			ucc_fast_free(uccf);
+			return -EINVAL;
+		}
+
+		/* tdm Tx sync clock routing */
+		if ((uf_info->tx_sync != QE_CLK_NONE) &&
+		    ucc_set_tdm_rxtx_sync(uf_info->tdm_num, uf_info->tx_sync,
+					  COMM_DIR_TX)) {
+			pr_err("%s: illegal value for TX clock", __func__);
+			ucc_fast_free(uccf);
+			return -EINVAL;
+		}
 	}
 
 	/* Set interrupt mask register at UCC level. */
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
index bbfee53cfcf5..845e49a52430 100644
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
+++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
@@ -2521,12 +2521,13 @@ kiblnd_passive_connect(struct rdma_cm_id *cmid, void *priv, int priv_nob)
 	return 0;
 
  failed:
-	if (ni)
+	if (ni) {
 		lnet_ni_decref(ni);
+		rej.ibr_cp.ibcp_queue_depth = kiblnd_msg_queue_size(version, ni);
+		rej.ibr_cp.ibcp_max_frags = kiblnd_rdma_frags(version, ni);
+	}
 
 	rej.ibr_version             = version;
-	rej.ibr_cp.ibcp_queue_depth = kiblnd_msg_queue_size(version, ni);
-	rej.ibr_cp.ibcp_max_frags = kiblnd_rdma_frags(version, ni);
 	kiblnd_reject(cmid, &rej);
 
 	return -ECONNREFUSED;
diff --git a/drivers/staging/rtl8188eu/core/rtw_efuse.c b/drivers/staging/rtl8188eu/core/rtw_efuse.c
index c17870cddb5b..fbce1f7e68ca 100644
--- a/drivers/staging/rtl8188eu/core/rtw_efuse.c
+++ b/drivers/staging/rtl8188eu/core/rtw_efuse.c
@@ -102,7 +102,7 @@ efuse_phymap_to_logical(u8 *phymap, u16 _offset, u16 _size_byte, u8  *pbuf)
 	if (!efuseTbl)
 		return;
 
-	eFuseWord = (u16 **)rtw_malloc2d(EFUSE_MAX_SECTION_88E, EFUSE_MAX_WORD_UNIT, sizeof(*eFuseWord));
+	eFuseWord = (u16 **)rtw_malloc2d(EFUSE_MAX_SECTION_88E, EFUSE_MAX_WORD_UNIT, sizeof(u16));
 	if (!eFuseWord) {
 		DBG_88E("%s: alloc eFuseWord fail!\n", __func__);
 		goto eFuseWord_failed;
diff --git a/drivers/staging/rtl8188eu/hal/usb_halinit.c b/drivers/staging/rtl8188eu/hal/usb_halinit.c
index 87ea3b844951..363f3a34ddce 100644
--- a/drivers/staging/rtl8188eu/hal/usb_halinit.c
+++ b/drivers/staging/rtl8188eu/hal/usb_halinit.c
@@ -2072,7 +2072,8 @@ void rtl8188eu_set_hal_ops(struct adapter *adapt)
 {
 	struct hal_ops	*halfunc = &adapt->HalFunc;
 
-	adapt->HalData = kzalloc(sizeof(*adapt->HalData), GFP_KERNEL);
+
+	adapt->HalData = kzalloc(sizeof(struct hal_data_8188e), GFP_KERNEL);
 	if (!adapt->HalData)
 		DBG_88E("cant not alloc memory for HAL DATA\n");
 
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 6ceac4f2d4b2..5b4b47ed948b 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -857,14 +857,6 @@ __cpufreq_cooling_register(struct device_node *np,
 		goto free_power_table;
 	}
 
-	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
-		 cpufreq_dev->id);
-
-	cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
-						      &cpufreq_cooling_ops);
-	if (IS_ERR(cool_dev))
-		goto remove_idr;
-
 	/* Fill freq-table in descending order of frequencies */
 	for (i = 0, freq = -1; i <= cpufreq_dev->max_level; i++) {
 		freq = find_next_max(table, freq);
@@ -877,6 +869,14 @@ __cpufreq_cooling_register(struct device_node *np,
 			pr_debug("%s: freq:%u KHz\n", __func__, freq);
 	}
 
+	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
+		 cpufreq_dev->id);
+
+	cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
+						      &cpufreq_cooling_ops);
+	if (IS_ERR(cool_dev))
+		goto remove_idr;
+
 	cpufreq_dev->clipped_freq = cpufreq_dev->freq_table[0];
 	cpufreq_dev->cool_dev = cool_dev;
 
diff --git a/drivers/thermal/int340x_thermal/int3406_thermal.c b/drivers/thermal/int340x_thermal/int3406_thermal.c
index 13d431cbd29e..a578cd257db4 100644
--- a/drivers/thermal/int340x_thermal/int3406_thermal.c
+++ b/drivers/thermal/int340x_thermal/int3406_thermal.c
@@ -177,7 +177,7 @@ static int int3406_thermal_probe(struct platform_device *pdev)
 		return -ENODEV;
 	d->raw_bd = bd;
 
-	ret = acpi_video_get_levels(ACPI_COMPANION(&pdev->dev), &d->br);
+	ret = acpi_video_get_levels(ACPI_COMPANION(&pdev->dev), &d->br, NULL);
 	if (ret)
 		return ret;
 
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index 82c4d2e45319..95103054c0e4 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -120,17 +120,6 @@ config UNIX98_PTYS
 	  All modern Linux systems use the Unix98 ptys.  Say Y unless
 	  you're on an embedded system and want to conserve memory.
 
-config DEVPTS_MULTIPLE_INSTANCES
-	bool "Support multiple instances of devpts"
-	depends on UNIX98_PTYS
-	default n
-	---help---
-	  Enable support for multiple instances of devpts filesystem.
-	  If you want to have isolated PTY namespaces (eg: in containers),
-	  say Y here.  Otherwise, say N. If enabled, each mount of devpts
-	  filesystem with the '-o newinstance' option will create an
-	  independent PTY namespace.
-
 config LEGACY_PTYS
 	bool "Legacy (BSD) PTY support"
 	default y
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index dd4b8417e7f4..f856c4544eea 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -668,7 +668,7 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty)
 	else
 		fsi = tty->link->driver_data;
 	devpts_kill_index(fsi, tty->index);
-	devpts_put_ref(fsi);
+	devpts_release(fsi);
 }
 
 static const struct tty_operations ptm_unix98_ops = {
@@ -733,10 +733,11 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 	if (retval)
 		return retval;
 
-	fsi = devpts_get_ref(inode, filp);
-	retval = -ENODEV;
-	if (!fsi)
+	fsi = devpts_acquire(filp);
+	if (IS_ERR(fsi)) {
+		retval = PTR_ERR(fsi);
 		goto out_free_file;
+	}
 
 	/* find a device that is not in use. */
 	mutex_lock(&devpts_mutex);
@@ -745,7 +746,7 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 
 	retval = index;
 	if (index < 0)
-		goto out_put_ref;
+		goto out_put_fsi;
 
 
 	mutex_lock(&tty_mutex);
@@ -789,8 +790,8 @@ err_release:
 	return retval;
 out:
 	devpts_kill_index(fsi, index);
-out_put_ref:
-	devpts_put_ref(fsi);
+out_put_fsi:
+	devpts_release(fsi);
 out_free_file:
 	tty_free_file(filp);
 	return retval;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 6dc810bce295..944a6dca0fcb 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -44,6 +44,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Creative SB Audigy 2 NX */
 	{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* USB3503 */
+	{ USB_DEVICE(0x0424, 0x3503), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Microsoft Wireless Laser Mouse 6000 Receiver */
 	{ USB_DEVICE(0x045e, 0x00e1), .driver_info = USB_QUIRK_RESET_RESUME },
 
@@ -173,6 +176,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* MAYA44USB sound device */
 	{ USB_DEVICE(0x0a92, 0x0091), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* ASUS Base Station(T100) */
+	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
+			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
 	/* Action Semiconductor flash disk */
 	{ USB_DEVICE(0x10d6, 0x2200), .driver_info =
 			USB_QUIRK_STRING_FETCH_255 },
@@ -188,26 +195,22 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x1908, 0x1315), .driver_info =
 			USB_QUIRK_HONOR_BNUMINTERFACES },
 
-	/* INTEL VALUE SSD */
-	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
-
-	/* USB3503 */
-	{ USB_DEVICE(0x0424, 0x3503), .driver_info = USB_QUIRK_RESET_RESUME },
-
-	/* ASUS Base Station(T100) */
-	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
-			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
-
 	/* Protocol and OTG Electrical Test Device */
 	{ USB_DEVICE(0x1a0a, 0x0200), .driver_info =
 			USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
 
+	/* Acer C120 LED Projector */
+	{ USB_DEVICE(0x1de1, 0xc102), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Blackmagic Design Intensity Shuttle */
 	{ USB_DEVICE(0x1edb, 0xbd3b), .driver_info = USB_QUIRK_NO_LPM },
 
 	/* Blackmagic Design UltraStudio SDI */
 	{ USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* INTEL VALUE SSD */
+	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	{ }  /* terminating entry must be last */
 };
 
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index 3c58d633ce80..dec0b21fc626 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -64,6 +64,17 @@
 	DWC2_TRACE_SCHEDULER_VB(pr_fmt("%s: SCH: " fmt),		\
 				dev_name(hsotg->dev), ##__VA_ARGS__)
 
+#ifdef CONFIG_MIPS
+/*
+ * There are some MIPS machines that can run in either big-endian
+ * or little-endian mode and that use the dwc2 register without
+ * a byteswap in both ways.
+ * Unlike other architectures, MIPS apparently does not require a
+ * barrier before the __raw_writel() to synchronize with DMA but does
+ * require the barrier after the __raw_writel() to serialize a set of
+ * writes. This set of operations was added specifically for MIPS and
+ * should only be used there.
+ */
 static inline u32 dwc2_readl(const void __iomem *addr)
 {
 	u32 value = __raw_readl(addr);
@@ -90,6 +101,22 @@ static inline void dwc2_writel(u32 value, void __iomem *addr)
 	pr_info("INFO:: wrote %08x to %p\n", value, addr);
 #endif
 }
+#else
+/* Normal architectures just use readl/write */
+static inline u32 dwc2_readl(const void __iomem *addr)
+{
+	return readl(addr);
+}
+
+static inline void dwc2_writel(u32 value, void __iomem *addr)
+{
+	writel(value, addr);
+
+#ifdef DWC2_LOG_WRITES
+	pr_info("info:: wrote %08x to %p\n", value, addr);
+#endif
+}
+#endif
 
 /* Maximum number of Endpoints/HostChannels */
 #define MAX_EPS_CHANNELS	16
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index 4c5e3005e1dc..26cf09d0fe3c 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -1018,7 +1018,7 @@ static int dwc2_hsotg_process_req_status(struct dwc2_hsotg *hsotg,
 	return 1;
 }
 
-static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value);
+static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value, bool now);
 
 /**
  * get_ep_head - return the first request on the endpoint
@@ -1094,7 +1094,7 @@ static int dwc2_hsotg_process_req_feature(struct dwc2_hsotg *hsotg,
 		case USB_ENDPOINT_HALT:
 			halted = ep->halted;
 
-			dwc2_hsotg_ep_sethalt(&ep->ep, set);
+			dwc2_hsotg_ep_sethalt(&ep->ep, set, true);
 
 			ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0);
 			if (ret) {
@@ -2948,8 +2948,13 @@ static int dwc2_hsotg_ep_dequeue(struct usb_ep *ep, struct usb_request *req)
  * dwc2_hsotg_ep_sethalt - set halt on a given endpoint
  * @ep: The endpoint to set halt.
  * @value: Set or unset the halt.
+ * @now: If true, stall the endpoint now. Otherwise return -EAGAIN if
+ *       the endpoint is busy processing requests.
+ *
+ * We need to stall the endpoint immediately if request comes from set_feature
+ * protocol command handler.
  */
-static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value)
+static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value, bool now)
 {
 	struct dwc2_hsotg_ep *hs_ep = our_ep(ep);
 	struct dwc2_hsotg *hs = hs_ep->parent;
@@ -2969,6 +2974,17 @@ static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value)
 		return 0;
 	}
 
+	if (hs_ep->isochronous) {
+		dev_err(hs->dev, "%s is Isochronous Endpoint\n", ep->name);
+		return -EINVAL;
+	}
+
+	if (!now && value && !list_empty(&hs_ep->queue)) {
+		dev_dbg(hs->dev, "%s request is pending, cannot halt\n",
+			ep->name);
+		return -EAGAIN;
+	}
+
 	if (hs_ep->dir_in) {
 		epreg = DIEPCTL(index);
 		epctl = dwc2_readl(hs->regs + epreg);
@@ -3020,7 +3036,7 @@ static int dwc2_hsotg_ep_sethalt_lock(struct usb_ep *ep, int value)
 	int ret = 0;
 
 	spin_lock_irqsave(&hs->lock, flags);
-	ret = dwc2_hsotg_ep_sethalt(ep, value);
+	ret = dwc2_hsotg_ep_sethalt(ep, value, false);
 	spin_unlock_irqrestore(&hs->lock, flags);
 
 	return ret;
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 7ddf9449a063..654050684f4f 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -402,6 +402,7 @@
 #define DWC3_DEPCMD_GET_RSC_IDX(x)	(((x) >> DWC3_DEPCMD_PARAM_SHIFT) & 0x7f)
 #define DWC3_DEPCMD_STATUS(x)		(((x) >> 12) & 0x0F)
 #define DWC3_DEPCMD_HIPRI_FORCERM	(1 << 11)
+#define DWC3_DEPCMD_CLEARPENDIN		(1 << 11)
 #define DWC3_DEPCMD_CMDACT		(1 << 10)
 #define DWC3_DEPCMD_CMDIOC		(1 << 8)
 
diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c
index dd5cb5577dca..2f1fb7e7aa54 100644
--- a/drivers/usb/dwc3/dwc3-exynos.c
+++ b/drivers/usb/dwc3/dwc3-exynos.c
@@ -128,12 +128,6 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, exynos);
 
-	ret = dwc3_exynos_register_phys(exynos);
-	if (ret) {
-		dev_err(dev, "couldn't register PHYs\n");
-		return ret;
-	}
-
 	exynos->dev	= dev;
 
 	exynos->clk = devm_clk_get(dev, "usbdrd30");
@@ -183,20 +177,29 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
 		goto err3;
 	}
 
+	ret = dwc3_exynos_register_phys(exynos);
+	if (ret) {
+		dev_err(dev, "couldn't register PHYs\n");
+		goto err4;
+	}
+
 	if (node) {
 		ret = of_platform_populate(node, NULL, NULL, dev);
 		if (ret) {
 			dev_err(dev, "failed to add dwc3 core\n");
-			goto err4;
+			goto err5;
 		}
 	} else {
 		dev_err(dev, "no device node, failed to add dwc3 core\n");
 		ret = -ENODEV;
-		goto err4;
+		goto err5;
 	}
 
 	return 0;
 
+err5:
+	platform_device_unregister(exynos->usb2_phy);
+	platform_device_unregister(exynos->usb3_phy);
 err4:
 	regulator_disable(exynos->vdd10);
 err3:
diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c
index 5c0adb9c6fb2..50d6ae6f88bc 100644
--- a/drivers/usb/dwc3/dwc3-st.c
+++ b/drivers/usb/dwc3/dwc3-st.c
@@ -129,12 +129,18 @@ static int st_dwc3_drd_init(struct st_dwc3 *dwc3_data)
 	switch (dwc3_data->dr_mode) {
 	case USB_DR_MODE_PERIPHERAL:
 
-		val &= ~(USB3_FORCE_VBUSVALID | USB3_DELAY_VBUSVALID
+		val &= ~(USB3_DELAY_VBUSVALID
 			| USB3_SEL_FORCE_OPMODE | USB3_FORCE_OPMODE(0x3)
 			| USB3_SEL_FORCE_DPPULLDOWN2 | USB3_FORCE_DPPULLDOWN2
 			| USB3_SEL_FORCE_DMPULLDOWN2 | USB3_FORCE_DMPULLDOWN2);
 
-		val |= USB3_DEVICE_NOT_HOST;
+		/*
+		 * USB3_PORT2_FORCE_VBUSVALID When '1' and when
+		 * USB3_PORT2_DEVICE_NOT_HOST = 1, forces VBUSVLDEXT2 input
+		 * of the pico PHY to 1.
+		 */
+
+		val |= USB3_DEVICE_NOT_HOST | USB3_FORCE_VBUSVALID;
 		break;
 
 	case USB_DR_MODE_HOST:
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 9a7d0bd15dc3..07248ff1be5c 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -347,6 +347,28 @@ int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep,
 	return ret;
 }
 
+static int dwc3_send_clear_stall_ep_cmd(struct dwc3_ep *dep)
+{
+	struct dwc3 *dwc = dep->dwc;
+	struct dwc3_gadget_ep_cmd_params params;
+	u32 cmd = DWC3_DEPCMD_CLEARSTALL;
+
+	/*
+	 * As of core revision 2.60a the recommended programming model
+	 * is to set the ClearPendIN bit when issuing a Clear Stall EP
+	 * command for IN endpoints. This is to prevent an issue where
+	 * some (non-compliant) hosts may not send ACK TPs for pending
+	 * IN transfers due to a mishandled error condition. Synopsys
+	 * STAR 9000614252.
+	 */
+	if (dep->direction && (dwc->revision >= DWC3_REVISION_260A))
+		cmd |= DWC3_DEPCMD_CLEARPENDIN;
+
+	memset(&params, 0, sizeof(params));
+
+	return dwc3_send_gadget_ep_cmd(dwc, dep->number, cmd, &params);
+}
+
 static dma_addr_t dwc3_trb_dma_offset(struct dwc3_ep *dep,
 		struct dwc3_trb *trb)
 {
@@ -1314,8 +1336,7 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol)
 		else
 			dep->flags |= DWC3_EP_STALL;
 	} else {
-		ret = dwc3_send_gadget_ep_cmd(dwc, dep->number,
-			DWC3_DEPCMD_CLEARSTALL, &params);
+		ret = dwc3_send_clear_stall_ep_cmd(dep);
 		if (ret)
 			dev_err(dwc->dev, "failed to clear STALL on %s\n",
 					dep->name);
@@ -2247,7 +2268,6 @@ static void dwc3_clear_stall_all_ep(struct dwc3 *dwc)
 
 	for (epnum = 1; epnum < DWC3_ENDPOINTS_NUM; epnum++) {
 		struct dwc3_ep *dep;
-		struct dwc3_gadget_ep_cmd_params params;
 		int ret;
 
 		dep = dwc->eps[epnum];
@@ -2259,9 +2279,7 @@ static void dwc3_clear_stall_all_ep(struct dwc3 *dwc)
 
 		dep->flags &= ~DWC3_EP_STALL;
 
-		memset(&params, 0, sizeof(params));
-		ret = dwc3_send_gadget_ep_cmd(dwc, dep->number,
-				DWC3_DEPCMD_CLEARSTALL, &params);
+		ret = dwc3_send_clear_stall_ep_cmd(dep);
 		WARN_ON_ONCE(ret);
 	}
 }
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index d67de0d22a2b..eb648485a58c 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1868,14 +1868,19 @@ unknown:
 				}
 				break;
 			}
-			req->length = value;
-			req->context = cdev;
-			req->zero = value < w_length;
-			value = composite_ep0_queue(cdev, req, GFP_ATOMIC);
-			if (value < 0) {
-				DBG(cdev, "ep_queue --> %d\n", value);
-				req->status = 0;
-				composite_setup_complete(gadget->ep0, req);
+
+			if (value >= 0) {
+				req->length = value;
+				req->context = cdev;
+				req->zero = value < w_length;
+				value = composite_ep0_queue(cdev, req,
+							    GFP_ATOMIC);
+				if (value < 0) {
+					DBG(cdev, "ep_queue --> %d\n", value);
+					req->status = 0;
+					composite_setup_complete(gadget->ep0,
+								 req);
+				}
 			}
 			return value;
 		}
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index b6f60ca8a035..70cf3477f951 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -1401,6 +1401,7 @@ static const struct usb_gadget_driver configfs_driver_template = {
 		.owner          = THIS_MODULE,
 		.name		= "configfs-gadget",
 	},
+	.match_existing_only = 1,
 };
 
 static struct config_group *gadgets_make(
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 73515d54e1cc..cc33d2667408 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -2051,7 +2051,7 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type,
 
 		if (len < sizeof(*d) ||
 		    d->bFirstInterfaceNumber >= ffs->interfaces_count ||
-		    d->Reserved1)
+		    !d->Reserved1)
 			return -EINVAL;
 		for (i = 0; i < ARRAY_SIZE(d->Reserved2); ++i)
 			if (d->Reserved2[i])
@@ -2729,6 +2729,7 @@ static int _ffs_func_bind(struct usb_configuration *c,
 		func->ffs->ss_descs_count;
 
 	int fs_len, hs_len, ss_len, ret, i;
+	struct ffs_ep *eps_ptr;
 
 	/* Make it a single chunk, less management later on */
 	vla_group(d);
@@ -2777,12 +2778,9 @@ static int _ffs_func_bind(struct usb_configuration *c,
 	       ffs->raw_descs_length);
 
 	memset(vla_ptr(vlabuf, d, inums), 0xff, d_inums__sz);
-	for (ret = ffs->eps_count; ret; --ret) {
-		struct ffs_ep *ptr;
-
-		ptr = vla_ptr(vlabuf, d, eps);
-		ptr[ret].num = -1;
-	}
+	eps_ptr = vla_ptr(vlabuf, d, eps);
+	for (i = 0; i < ffs->eps_count; i++)
+		eps_ptr[i].num = -1;
 
 	/* Save pointers
 	 * d_eps == vlabuf, func->eps used to kfree vlabuf later
@@ -2851,7 +2849,7 @@ static int _ffs_func_bind(struct usb_configuration *c,
 		goto error;
 
 	func->function.os_desc_table = vla_ptr(vlabuf, d, os_desc_table);
-	if (c->cdev->use_os_string)
+	if (c->cdev->use_os_string) {
 		for (i = 0; i < ffs->interfaces_count; ++i) {
 			struct usb_os_desc *desc;
 
@@ -2862,13 +2860,15 @@ static int _ffs_func_bind(struct usb_configuration *c,
 				vla_ptr(vlabuf, d, ext_compat) + i * 16;
 			INIT_LIST_HEAD(&desc->ext_prop);
 		}
-	ret = ffs_do_os_descs(ffs->ms_os_descs_count,
-			      vla_ptr(vlabuf, d, raw_descs) +
-			      fs_len + hs_len + ss_len,
-			      d_raw_descs__sz - fs_len - hs_len - ss_len,
-			      __ffs_func_bind_do_os_desc, func);
-	if (unlikely(ret < 0))
-		goto error;
+		ret = ffs_do_os_descs(ffs->ms_os_descs_count,
+				      vla_ptr(vlabuf, d, raw_descs) +
+				      fs_len + hs_len + ss_len,
+				      d_raw_descs__sz - fs_len - hs_len -
+				      ss_len,
+				      __ffs_func_bind_do_os_desc, func);
+		if (unlikely(ret < 0))
+			goto error;
+	}
 	func->function.os_desc_n =
 		c->cdev->use_os_string ? ffs->interfaces_count : 0;
 
diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c
index c45104e3a64b..64706a789580 100644
--- a/drivers/usb/gadget/function/f_printer.c
+++ b/drivers/usb/gadget/function/f_printer.c
@@ -161,14 +161,6 @@ static struct usb_endpoint_descriptor hs_ep_out_desc = {
 	.wMaxPacketSize =	cpu_to_le16(512)
 };
 
-static struct usb_qualifier_descriptor dev_qualifier = {
-	.bLength =		sizeof(dev_qualifier),
-	.bDescriptorType =	USB_DT_DEVICE_QUALIFIER,
-	.bcdUSB =		cpu_to_le16(0x0200),
-	.bDeviceClass =		USB_CLASS_PRINTER,
-	.bNumConfigurations =	1
-};
-
 static struct usb_descriptor_header *hs_printer_function[] = {
 	(struct usb_descriptor_header *) &intf_desc,
 	(struct usb_descriptor_header *) &hs_ep_in_desc,
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index 35fe3c80cfc0..197f73386fac 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1445,16 +1445,18 @@ static void usbg_drop_tpg(struct se_portal_group *se_tpg)
 	for (i = 0; i < TPG_INSTANCES; ++i)
 		if (tpg_instances[i].tpg == tpg)
 			break;
-	if (i < TPG_INSTANCES)
+	if (i < TPG_INSTANCES) {
 		tpg_instances[i].tpg = NULL;
-	opts = container_of(tpg_instances[i].func_inst,
-		struct f_tcm_opts, func_inst);
-	mutex_lock(&opts->dep_lock);
-	if (opts->has_dep)
-		module_put(opts->dependent);
-	else
-		configfs_undepend_item_unlocked(&opts->func_inst.group.cg_item);
-	mutex_unlock(&opts->dep_lock);
+		opts = container_of(tpg_instances[i].func_inst,
+			struct f_tcm_opts, func_inst);
+		mutex_lock(&opts->dep_lock);
+		if (opts->has_dep)
+			module_put(opts->dependent);
+		else
+			configfs_undepend_item_unlocked(
+				&opts->func_inst.group.cg_item);
+		mutex_unlock(&opts->dep_lock);
+	}
 	mutex_unlock(&tpg_instances_lock);
 
 	kfree(tpg);
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index 186d4b162524..cd214ec8a601 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -598,18 +598,6 @@ static struct usb_gadget_strings *fn_strings[] = {
 	NULL,
 };
 
-static struct usb_qualifier_descriptor devqual_desc = {
-	.bLength = sizeof devqual_desc,
-	.bDescriptorType = USB_DT_DEVICE_QUALIFIER,
-
-	.bcdUSB = cpu_to_le16(0x200),
-	.bDeviceClass = USB_CLASS_MISC,
-	.bDeviceSubClass = 0x02,
-	.bDeviceProtocol = 0x01,
-	.bNumConfigurations = 1,
-	.bRESERVED = 0,
-};
-
 static struct usb_interface_assoc_descriptor iad_desc = {
 	.bLength = sizeof iad_desc,
 	.bDescriptorType = USB_DT_INTERFACE_ASSOCIATION,
@@ -1292,6 +1280,7 @@ in_rq_cur(struct usb_function *fn, const struct usb_ctrlrequest *cr)
 
 	if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) {
 		struct cntrl_cur_lay3 c;
+		memset(&c, 0, sizeof(struct cntrl_cur_lay3));
 
 		if (entity_id == USB_IN_CLK_ID)
 			c.dCUR = p_srate;
diff --git a/drivers/usb/gadget/function/storage_common.c b/drivers/usb/gadget/function/storage_common.c
index d62683017cf3..990df221c629 100644
--- a/drivers/usb/gadget/function/storage_common.c
+++ b/drivers/usb/gadget/function/storage_common.c
@@ -83,9 +83,7 @@ EXPORT_SYMBOL_GPL(fsg_fs_function);
  * USB 2.0 devices need to expose both high speed and full speed
  * descriptors, unless they only run at full speed.
  *
- * That means alternate endpoint descriptors (bigger packets)
- * and a "device qualifier" ... plus more construction options
- * for the configuration descriptor.
+ * That means alternate endpoint descriptors (bigger packets).
  */
 struct usb_endpoint_descriptor fsg_hs_bulk_in_desc = {
 	.bLength =		USB_DT_ENDPOINT_SIZE,
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index e64479f882a5..aa3707bdebb4 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -938,8 +938,11 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr)
 			struct usb_ep		*ep = dev->gadget->ep0;
 			struct usb_request	*req = dev->req;
 
-			if ((retval = setup_req (ep, req, 0)) == 0)
-				retval = usb_ep_queue (ep, req, GFP_ATOMIC);
+			if ((retval = setup_req (ep, req, 0)) == 0) {
+				spin_unlock_irq (&dev->lock);
+				retval = usb_ep_queue (ep, req, GFP_KERNEL);
+				spin_lock_irq (&dev->lock);
+			}
 			dev->state = STATE_DEV_CONNECTED;
 
 			/* assume that was SET_CONFIGURATION */
@@ -1457,8 +1460,11 @@ delegate:
 							w_length);
 				if (value < 0)
 					break;
+
+				spin_unlock (&dev->lock);
 				value = usb_ep_queue (gadget->ep0, dev->req,
-							GFP_ATOMIC);
+							GFP_KERNEL);
+				spin_lock (&dev->lock);
 				if (value < 0) {
 					clean_req (gadget->ep0, dev->req);
 					break;
@@ -1481,11 +1487,14 @@ delegate:
 	if (value >= 0 && dev->state != STATE_DEV_SETUP) {
 		req->length = value;
 		req->zero = value < w_length;
-		value = usb_ep_queue (gadget->ep0, req, GFP_ATOMIC);
+
+		spin_unlock (&dev->lock);
+		value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL);
 		if (value < 0) {
 			DBG (dev, "ep_queue --> %d\n", value);
 			req->status = 0;
 		}
+		return value;
 	}
 
 	/* device stalls when value < 0 */
diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index 6e8300d6a737..e1b2dcebdc2e 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -603,11 +603,15 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver)
 		}
 	}
 
-	list_add_tail(&driver->pending, &gadget_driver_pending_list);
-	pr_info("udc-core: couldn't find an available UDC - added [%s] to list of pending drivers\n",
-		driver->function);
+	if (!driver->match_existing_only) {
+		list_add_tail(&driver->pending, &gadget_driver_pending_list);
+		pr_info("udc-core: couldn't find an available UDC - added [%s] to list of pending drivers\n",
+			driver->function);
+		ret = 0;
+	}
+
 	mutex_unlock(&udc_lock);
-	return 0;
+	return ret;
 found:
 	ret = udc_bind_to_driver(udc, driver);
 	mutex_unlock(&udc_lock);
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index ae1b6e69eb96..a962b89b65a6 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -368,6 +368,15 @@ static void ehci_shutdown(struct usb_hcd *hcd)
 {
 	struct ehci_hcd	*ehci = hcd_to_ehci(hcd);
 
+	/**
+	 * Protect the system from crashing at system shutdown in cases where
+	 * usb host is not added yet from OTG controller driver.
+	 * As ehci_setup() not done yet, so stop accessing registers or
+	 * variables initialized in ehci_setup()
+	 */
+	if (!ehci->sbrn)
+		return;
+
 	spin_lock_irq(&ehci->lock);
 	ehci->shutdown = true;
 	ehci->rh_state = EHCI_RH_STOPPING;
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index ffc90295a95f..74f62d68f013 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -872,15 +872,23 @@ int ehci_hub_control(
 ) {
 	struct ehci_hcd	*ehci = hcd_to_ehci (hcd);
 	int		ports = HCS_N_PORTS (ehci->hcs_params);
-	u32 __iomem	*status_reg = &ehci->regs->port_status[
-				(wIndex & 0xff) - 1];
-	u32 __iomem	*hostpc_reg = &ehci->regs->hostpc[(wIndex & 0xff) - 1];
+	u32 __iomem	*status_reg, *hostpc_reg;
 	u32		temp, temp1, status;
 	unsigned long	flags;
 	int		retval = 0;
 	unsigned	selector;
 
 	/*
+	 * Avoid underflow while calculating (wIndex & 0xff) - 1.
+	 * The compiler might deduce that wIndex can never be 0 and then
+	 * optimize away the tests for !wIndex below.
+	 */
+	temp = wIndex & 0xff;
+	temp -= (temp > 0);
+	status_reg = &ehci->regs->port_status[temp];
+	hostpc_reg = &ehci->regs->hostpc[temp];
+
+	/*
 	 * FIXME:  support SetPortFeatures USB_PORT_FEAT_INDICATOR.
 	 * HCS_INDICATOR may say we can change LEDs to off/amber/green.
 	 * (track current state ourselves) ... blink for diagnostics,
diff --git a/drivers/usb/host/ehci-msm.c b/drivers/usb/host/ehci-msm.c
index d3afc89d00f5..2f8d3af811ce 100644
--- a/drivers/usb/host/ehci-msm.c
+++ b/drivers/usb/host/ehci-msm.c
@@ -179,22 +179,32 @@ static int ehci_msm_remove(struct platform_device *pdev)
 static int ehci_msm_pm_suspend(struct device *dev)
 {
 	struct usb_hcd *hcd = dev_get_drvdata(dev);
+	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
 	bool do_wakeup = device_may_wakeup(dev);
 
 	dev_dbg(dev, "ehci-msm PM suspend\n");
 
-	return ehci_suspend(hcd, do_wakeup);
+	/* Only call ehci_suspend if ehci_setup has been done */
+	if (ehci->sbrn)
+		return ehci_suspend(hcd, do_wakeup);
+
+	return 0;
 }
 
 static int ehci_msm_pm_resume(struct device *dev)
 {
 	struct usb_hcd *hcd = dev_get_drvdata(dev);
+	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
 
 	dev_dbg(dev, "ehci-msm PM resume\n");
-	ehci_resume(hcd, false);
+
+	/* Only call ehci_resume if ehci_setup has been done */
+	if (ehci->sbrn)
+		ehci_resume(hcd, false);
 
 	return 0;
 }
+
 #else
 #define ehci_msm_pm_suspend	NULL
 #define ehci_msm_pm_resume	NULL
diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c
index 4031b372008e..9a3d7db5be57 100644
--- a/drivers/usb/host/ehci-tegra.c
+++ b/drivers/usb/host/ehci-tegra.c
@@ -81,15 +81,23 @@ static int tegra_reset_usb_controller(struct platform_device *pdev)
 	struct usb_hcd *hcd = platform_get_drvdata(pdev);
 	struct tegra_ehci_hcd *tegra =
 		(struct tegra_ehci_hcd *)hcd_to_ehci(hcd)->priv;
+	bool has_utmi_pad_registers = false;
 
 	phy_np = of_parse_phandle(pdev->dev.of_node, "nvidia,phy", 0);
 	if (!phy_np)
 		return -ENOENT;
 
+	if (of_property_read_bool(phy_np, "nvidia,has-utmi-pad-registers"))
+		has_utmi_pad_registers = true;
+
 	if (!usb1_reset_attempted) {
 		struct reset_control *usb1_reset;
 
-		usb1_reset = of_reset_control_get(phy_np, "usb");
+		if (!has_utmi_pad_registers)
+			usb1_reset = of_reset_control_get(phy_np, "utmi-pads");
+		else
+			usb1_reset = tegra->rst;
+
 		if (IS_ERR(usb1_reset)) {
 			dev_warn(&pdev->dev,
 				 "can't get utmi-pads reset from the PHY\n");
@@ -99,13 +107,15 @@ static int tegra_reset_usb_controller(struct platform_device *pdev)
 			reset_control_assert(usb1_reset);
 			udelay(1);
 			reset_control_deassert(usb1_reset);
+
+			if (!has_utmi_pad_registers)
+				reset_control_put(usb1_reset);
 		}
 
-		reset_control_put(usb1_reset);
 		usb1_reset_attempted = true;
 	}
 
-	if (!of_property_read_bool(phy_np, "nvidia,has-utmi-pad-registers")) {
+	if (!has_utmi_pad_registers) {
 		reset_control_assert(tegra->rst);
 		udelay(1);
 		reset_control_deassert(tegra->rst);
diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c
index d029bbe9eb36..641fed609911 100644
--- a/drivers/usb/host/ohci-q.c
+++ b/drivers/usb/host/ohci-q.c
@@ -183,7 +183,6 @@ static int ed_schedule (struct ohci_hcd *ohci, struct ed *ed)
 {
 	int	branch;
 
-	ed->state = ED_OPER;
 	ed->ed_prev = NULL;
 	ed->ed_next = NULL;
 	ed->hwNextED = 0;
@@ -259,6 +258,8 @@ static int ed_schedule (struct ohci_hcd *ohci, struct ed *ed)
 	/* the HC may not see the schedule updates yet, but if it does
 	 * then they'll be properly ordered.
 	 */
+
+	ed->state = ED_OPER;
 	return 0;
 }
 
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 48672fac7ff3..c10972fcc8e4 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -37,6 +37,7 @@
 /* Device for a quirk */
 #define PCI_VENDOR_ID_FRESCO_LOGIC	0x1b73
 #define PCI_DEVICE_ID_FRESCO_LOGIC_PDK	0x1000
+#define PCI_DEVICE_ID_FRESCO_LOGIC_FL1009	0x1009
 #define PCI_DEVICE_ID_FRESCO_LOGIC_FL1400	0x1400
 
 #define PCI_VENDOR_ID_ETRON		0x1b6f
@@ -114,6 +115,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
 	}
 
+	if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC &&
+			pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1009)
+		xhci->quirks |= XHCI_BROKEN_STREAMS;
+
 	if (pdev->vendor == PCI_VENDOR_ID_NEC)
 		xhci->quirks |= XHCI_NEC_HOST;
 
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 676ea458148b..1f3f981fe7f8 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -196,6 +196,9 @@ static int xhci_plat_probe(struct platform_device *pdev)
 		ret = clk_prepare_enable(clk);
 		if (ret)
 			goto put_hcd;
+	} else if (PTR_ERR(clk) == -EPROBE_DEFER) {
+		ret = -EPROBE_DEFER;
+		goto put_hcd;
 	}
 
 	xhci = hcd_to_xhci(hcd);
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 52deae4b7eac..d7d502578d79 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -290,6 +290,14 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
 
 	temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
 	xhci->cmd_ring_state = CMD_RING_STATE_ABORTED;
+
+	/*
+	 * Writing the CMD_RING_ABORT bit should cause a cmd completion event,
+	 * however on some host hw the CMD_RING_RUNNING bit is correctly cleared
+	 * but the completion event in never sent. Use the cmd timeout timer to
+	 * handle those cases. Use twice the time to cover the bit polling retry
+	 */
+	mod_timer(&xhci->cmd_timer, jiffies + (2 * XHCI_CMD_DEFAULT_TIMEOUT));
 	xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
 			&xhci->op_regs->cmd_ring);
 
@@ -314,6 +322,7 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
 
 		xhci_err(xhci, "Stopped the command ring failed, "
 				"maybe the host is dead\n");
+		del_timer(&xhci->cmd_timer);
 		xhci->xhc_state |= XHCI_STATE_DYING;
 		xhci_quiesce(xhci);
 		xhci_halt(xhci);
@@ -1246,22 +1255,21 @@ void xhci_handle_command_timeout(unsigned long data)
 	int ret;
 	unsigned long flags;
 	u64 hw_ring_state;
-	struct xhci_command *cur_cmd = NULL;
+	bool second_timeout = false;
 	xhci = (struct xhci_hcd *) data;
 
 	/* mark this command to be cancelled */
 	spin_lock_irqsave(&xhci->lock, flags);
 	if (xhci->current_cmd) {
-		cur_cmd = xhci->current_cmd;
-		cur_cmd->status = COMP_CMD_ABORT;
+		if (xhci->current_cmd->status == COMP_CMD_ABORT)
+			second_timeout = true;
+		xhci->current_cmd->status = COMP_CMD_ABORT;
 	}
 
-
 	/* Make sure command ring is running before aborting it */
 	hw_ring_state = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
 	if ((xhci->cmd_ring_state & CMD_RING_STATE_RUNNING) &&
 	    (hw_ring_state & CMD_RING_RUNNING))  {
-
 		spin_unlock_irqrestore(&xhci->lock, flags);
 		xhci_dbg(xhci, "Command timeout\n");
 		ret = xhci_abort_cmd_ring(xhci);
@@ -1273,6 +1281,15 @@ void xhci_handle_command_timeout(unsigned long data)
 		}
 		return;
 	}
+
+	/* command ring failed to restart, or host removed. Bail out */
+	if (second_timeout || xhci->xhc_state & XHCI_STATE_REMOVING) {
+		spin_unlock_irqrestore(&xhci->lock, flags);
+		xhci_dbg(xhci, "command timed out twice, ring start fail?\n");
+		xhci_cleanup_command_queue(xhci);
+		return;
+	}
+
 	/* command timeout on stopped ring, ring can't be aborted */
 	xhci_dbg(xhci, "Command timeout on stopped ring\n");
 	xhci_handle_stopped_cmd_ring(xhci, xhci->current_cmd);
@@ -2721,7 +2738,8 @@ hw_died:
 		writel(irq_pending, &xhci->ir_set->irq_pending);
 	}
 
-	if (xhci->xhc_state & XHCI_STATE_DYING) {
+	if (xhci->xhc_state & XHCI_STATE_DYING ||
+	    xhci->xhc_state & XHCI_STATE_HALTED) {
 		xhci_dbg(xhci, "xHCI dying, ignoring interrupt. "
 				"Shouldn't IRQs be disabled?\n");
 		/* Clear the event handler busy flag (RW1C);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index fa7e1ef36cd9..f2f9518c53ab 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -685,20 +685,23 @@ void xhci_stop(struct usb_hcd *hcd)
 	u32 temp;
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
 
-	if (xhci->xhc_state & XHCI_STATE_HALTED)
-		return;
-
 	mutex_lock(&xhci->mutex);
-	spin_lock_irq(&xhci->lock);
-	xhci->xhc_state |= XHCI_STATE_HALTED;
-	xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
 
-	/* Make sure the xHC is halted for a USB3 roothub
-	 * (xhci_stop() could be called as part of failed init).
-	 */
-	xhci_halt(xhci);
-	xhci_reset(xhci);
-	spin_unlock_irq(&xhci->lock);
+	if (!(xhci->xhc_state & XHCI_STATE_HALTED)) {
+		spin_lock_irq(&xhci->lock);
+
+		xhci->xhc_state |= XHCI_STATE_HALTED;
+		xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
+		xhci_halt(xhci);
+		xhci_reset(xhci);
+
+		spin_unlock_irq(&xhci->lock);
+	}
+
+	if (!usb_hcd_is_primary_hcd(hcd)) {
+		mutex_unlock(&xhci->mutex);
+		return;
+	}
 
 	xhci_cleanup_msix(xhci);
 
@@ -4886,7 +4889,7 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks)
 		xhci->hcc_params2 = readl(&xhci->cap_regs->hcc_params2);
 	xhci_print_registers(xhci);
 
-	xhci->quirks = quirks;
+	xhci->quirks |= quirks;
 
 	get_quirks(dev, xhci);
 
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 39fd95833eb8..f824336def5c 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -1090,29 +1090,6 @@ void musb_stop(struct musb *musb)
 	musb_platform_try_idle(musb, 0);
 }
 
-static void musb_shutdown(struct platform_device *pdev)
-{
-	struct musb	*musb = dev_to_musb(&pdev->dev);
-	unsigned long	flags;
-
-	pm_runtime_get_sync(musb->controller);
-
-	musb_host_cleanup(musb);
-	musb_gadget_cleanup(musb);
-
-	spin_lock_irqsave(&musb->lock, flags);
-	musb_platform_disable(musb);
-	musb_generic_disable(musb);
-	spin_unlock_irqrestore(&musb->lock, flags);
-
-	musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
-	musb_platform_exit(musb);
-
-	pm_runtime_put(musb->controller);
-	/* FIXME power down */
-}
-
-
 /*-------------------------------------------------------------------------*/
 
 /*
@@ -1702,7 +1679,7 @@ EXPORT_SYMBOL_GPL(musb_dma_completion);
 #define use_dma			0
 #endif
 
-static void (*musb_phy_callback)(enum musb_vbus_id_status status);
+static int (*musb_phy_callback)(enum musb_vbus_id_status status);
 
 /*
  * musb_mailbox - optional phy notifier function
@@ -1711,11 +1688,12 @@ static void (*musb_phy_callback)(enum musb_vbus_id_status status);
  * Optionally gets called from the USB PHY. Note that the USB PHY must be
  * disabled at the point the phy_callback is registered or unregistered.
  */
-void musb_mailbox(enum musb_vbus_id_status status)
+int musb_mailbox(enum musb_vbus_id_status status)
 {
 	if (musb_phy_callback)
-		musb_phy_callback(status);
+		return musb_phy_callback(status);
 
+	return -ENODEV;
 };
 EXPORT_SYMBOL_GPL(musb_mailbox);
 
@@ -2028,11 +2006,6 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 	musb_readl = musb_default_readl;
 	musb_writel = musb_default_writel;
 
-	/* We need musb_read/write functions initialized for PM */
-	pm_runtime_use_autosuspend(musb->controller);
-	pm_runtime_set_autosuspend_delay(musb->controller, 200);
-	pm_runtime_enable(musb->controller);
-
 	/* The musb_platform_init() call:
 	 *   - adjusts musb->mregs
 	 *   - sets the musb->isr
@@ -2134,6 +2107,16 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 	if (musb->ops->phy_callback)
 		musb_phy_callback = musb->ops->phy_callback;
 
+	/*
+	 * We need musb_read/write functions initialized for PM.
+	 * Note that at least 2430 glue needs autosuspend delay
+	 * somewhere above 300 ms for the hardware to idle properly
+	 * after disconnecting the cable in host mode. Let's use
+	 * 500 ms for some margin.
+	 */
+	pm_runtime_use_autosuspend(musb->controller);
+	pm_runtime_set_autosuspend_delay(musb->controller, 500);
+	pm_runtime_enable(musb->controller);
 	pm_runtime_get_sync(musb->controller);
 
 	status = usb_phy_init(musb->xceiv);
@@ -2237,13 +2220,8 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 	if (status)
 		goto fail5;
 
-	pm_runtime_put(musb->controller);
-
-	/*
-	 * For why this is currently needed, see commit 3e43a0725637
-	 * ("usb: musb: core: add pm_runtime_irq_safe()")
-	 */
-	pm_runtime_irq_safe(musb->controller);
+	pm_runtime_mark_last_busy(musb->controller);
+	pm_runtime_put_autosuspend(musb->controller);
 
 	return 0;
 
@@ -2265,7 +2243,9 @@ fail2_5:
 	usb_phy_shutdown(musb->xceiv);
 
 err_usb_phy_init:
+	pm_runtime_dont_use_autosuspend(musb->controller);
 	pm_runtime_put_sync(musb->controller);
+	pm_runtime_disable(musb->controller);
 
 fail2:
 	if (musb->irq_wake)
@@ -2273,7 +2253,6 @@ fail2:
 	musb_platform_exit(musb);
 
 fail1:
-	pm_runtime_disable(musb->controller);
 	dev_err(musb->controller,
 		"musb_init_controller failed with status %d\n", status);
 
@@ -2312,6 +2291,7 @@ static int musb_remove(struct platform_device *pdev)
 {
 	struct device	*dev = &pdev->dev;
 	struct musb	*musb = dev_to_musb(dev);
+	unsigned long	flags;
 
 	/* this gets called on rmmod.
 	 *  - Host mode: host may still be active
@@ -2319,17 +2299,26 @@ static int musb_remove(struct platform_device *pdev)
 	 *  - OTG mode: both roles are deactivated (or never-activated)
 	 */
 	musb_exit_debugfs(musb);
-	musb_shutdown(pdev);
-	musb_phy_callback = NULL;
-
-	if (musb->dma_controller)
-		musb_dma_controller_destroy(musb->dma_controller);
-
-	usb_phy_shutdown(musb->xceiv);
 
 	cancel_work_sync(&musb->irq_work);
 	cancel_delayed_work_sync(&musb->finish_resume_work);
 	cancel_delayed_work_sync(&musb->deassert_reset_work);
+	pm_runtime_get_sync(musb->controller);
+	musb_host_cleanup(musb);
+	musb_gadget_cleanup(musb);
+	spin_lock_irqsave(&musb->lock, flags);
+	musb_platform_disable(musb);
+	musb_generic_disable(musb);
+	spin_unlock_irqrestore(&musb->lock, flags);
+	musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
+	pm_runtime_dont_use_autosuspend(musb->controller);
+	pm_runtime_put_sync(musb->controller);
+	pm_runtime_disable(musb->controller);
+	musb_platform_exit(musb);
+	musb_phy_callback = NULL;
+	if (musb->dma_controller)
+		musb_dma_controller_destroy(musb->dma_controller);
+	usb_phy_shutdown(musb->xceiv);
 	musb_free(musb);
 	device_init_wakeup(dev, 0);
 	return 0;
@@ -2429,7 +2418,8 @@ static void musb_restore_context(struct musb *musb)
 	musb_writew(musb_base, MUSB_INTRTXE, musb->intrtxe);
 	musb_writew(musb_base, MUSB_INTRRXE, musb->intrrxe);
 	musb_writeb(musb_base, MUSB_INTRUSBE, musb->context.intrusbe);
-	musb_writeb(musb_base, MUSB_DEVCTL, musb->context.devctl);
+	if (musb->context.devctl & MUSB_DEVCTL_SESSION)
+		musb_writeb(musb_base, MUSB_DEVCTL, musb->context.devctl);
 
 	for (i = 0; i < musb->config->num_eps; ++i) {
 		struct musb_hw_ep	*hw_ep;
@@ -2612,7 +2602,6 @@ static struct platform_driver musb_driver = {
 	},
 	.probe		= musb_probe,
 	.remove		= musb_remove,
-	.shutdown	= musb_shutdown,
 };
 
 module_platform_driver(musb_driver);
diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index b6afe9e43305..b55a776b03eb 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -215,7 +215,7 @@ struct musb_platform_ops {
 				dma_addr_t *dma_addr, u32 *len);
 	void	(*pre_root_reset_end)(struct musb *musb);
 	void	(*post_root_reset_end)(struct musb *musb);
-	void	(*phy_callback)(enum musb_vbus_id_status status);
+	int	(*phy_callback)(enum musb_vbus_id_status status);
 };
 
 /*
@@ -312,6 +312,7 @@ struct musb {
 	struct work_struct	irq_work;
 	struct delayed_work	deassert_reset_work;
 	struct delayed_work	finish_resume_work;
+	struct delayed_work	gadget_work;
 	u16			hwvers;
 
 	u16			intrrxe;
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index 152865b36522..af2a3a7addf9 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -1656,6 +1656,20 @@ static int musb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA)
 	return usb_phy_set_power(musb->xceiv, mA);
 }
 
+static void musb_gadget_work(struct work_struct *work)
+{
+	struct musb *musb;
+	unsigned long flags;
+
+	musb = container_of(work, struct musb, gadget_work.work);
+	pm_runtime_get_sync(musb->controller);
+	spin_lock_irqsave(&musb->lock, flags);
+	musb_pullup(musb, musb->softconnect);
+	spin_unlock_irqrestore(&musb->lock, flags);
+	pm_runtime_mark_last_busy(musb->controller);
+	pm_runtime_put_autosuspend(musb->controller);
+}
+
 static int musb_gadget_pullup(struct usb_gadget *gadget, int is_on)
 {
 	struct musb	*musb = gadget_to_musb(gadget);
@@ -1663,20 +1677,16 @@ static int musb_gadget_pullup(struct usb_gadget *gadget, int is_on)
 
 	is_on = !!is_on;
 
-	pm_runtime_get_sync(musb->controller);
-
 	/* NOTE: this assumes we are sensing vbus; we'd rather
 	 * not pullup unless the B-session is active.
 	 */
 	spin_lock_irqsave(&musb->lock, flags);
 	if (is_on != musb->softconnect) {
 		musb->softconnect = is_on;
-		musb_pullup(musb, is_on);
+		schedule_delayed_work(&musb->gadget_work, 0);
 	}
 	spin_unlock_irqrestore(&musb->lock, flags);
 
-	pm_runtime_put(musb->controller);
-
 	return 0;
 }
 
@@ -1845,7 +1855,7 @@ int musb_gadget_setup(struct musb *musb)
 #elif IS_ENABLED(CONFIG_USB_MUSB_GADGET)
 	musb->g.is_otg = 0;
 #endif
-
+	INIT_DELAYED_WORK(&musb->gadget_work, musb_gadget_work);
 	musb_g_init_endpoints(musb);
 
 	musb->is_active = 0;
@@ -1866,6 +1876,8 @@ void musb_gadget_cleanup(struct musb *musb)
 {
 	if (musb->port_mode == MUSB_PORT_MODE_HOST)
 		return;
+
+	cancel_delayed_work_sync(&musb->gadget_work);
 	usb_del_gadget_udc(&musb->g);
 }
 
@@ -1914,8 +1926,8 @@ static int musb_gadget_start(struct usb_gadget *g,
 	if (musb->xceiv->last_event == USB_EVENT_ID)
 		musb_platform_set_vbus(musb, 1);
 
-	if (musb->xceiv->last_event == USB_EVENT_NONE)
-		pm_runtime_put(musb->controller);
+	pm_runtime_mark_last_busy(musb->controller);
+	pm_runtime_put_autosuspend(musb->controller);
 
 	return 0;
 
@@ -1934,8 +1946,7 @@ static int musb_gadget_stop(struct usb_gadget *g)
 	struct musb	*musb = gadget_to_musb(g);
 	unsigned long	flags;
 
-	if (musb->xceiv->last_event == USB_EVENT_NONE)
-		pm_runtime_get_sync(musb->controller);
+	pm_runtime_get_sync(musb->controller);
 
 	/*
 	 * REVISIT always use otg_set_peripheral() here too;
@@ -1963,7 +1974,8 @@ static int musb_gadget_stop(struct usb_gadget *g)
 	 * that currently misbehaves.
 	 */
 
-	pm_runtime_put(musb->controller);
+	pm_runtime_mark_last_busy(musb->controller);
+	pm_runtime_put_autosuspend(musb->controller);
 
 	return 0;
 }
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 2f8ad7f1f482..d227a71d85e1 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -434,7 +434,13 @@ static void musb_advance_schedule(struct musb *musb, struct urb *urb,
 		}
 	}
 
-	if (qh != NULL && qh->is_ready) {
+	/*
+	 * The pipe must be broken if current urb->status is set, so don't
+	 * start next urb.
+	 * TODO: to minimize the risk of regression, only check urb->status
+	 * for RX, until we have a test case to understand the behavior of TX.
+	 */
+	if ((!status || !is_in) && qh && qh->is_ready) {
 		dev_dbg(musb->controller, "... next ep%d %cX urb %p\n",
 		    hw_ep->epnum, is_in ? 'R' : 'T', next_urb(qh));
 		musb_start_urb(musb, is_in, qh);
@@ -594,14 +600,13 @@ musb_rx_reinit(struct musb *musb, struct musb_qh *qh, u8 epnum)
 		musb_writew(ep->regs, MUSB_TXCSR, 0);
 
 	/* scrub all previous state, clearing toggle */
-	} else {
-		csr = musb_readw(ep->regs, MUSB_RXCSR);
-		if (csr & MUSB_RXCSR_RXPKTRDY)
-			WARNING("rx%d, packet/%d ready?\n", ep->epnum,
-				musb_readw(ep->regs, MUSB_RXCOUNT));
-
-		musb_h_flush_rxfifo(ep, MUSB_RXCSR_CLRDATATOG);
 	}
+	csr = musb_readw(ep->regs, MUSB_RXCSR);
+	if (csr & MUSB_RXCSR_RXPKTRDY)
+		WARNING("rx%d, packet/%d ready?\n", ep->epnum,
+			musb_readw(ep->regs, MUSB_RXCOUNT));
+
+	musb_h_flush_rxfifo(ep, MUSB_RXCSR_CLRDATATOG);
 
 	/* target addr and (for multipoint) hub addr/port */
 	if (musb->is_multipoint) {
@@ -627,7 +632,7 @@ musb_rx_reinit(struct musb *musb, struct musb_qh *qh, u8 epnum)
 	ep->rx_reinit = 0;
 }
 
-static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma,
+static void musb_tx_dma_set_mode_mentor(struct dma_controller *dma,
 		struct musb_hw_ep *hw_ep, struct musb_qh *qh,
 		struct urb *urb, u32 offset,
 		u32 *length, u8 *mode)
@@ -664,23 +669,18 @@ static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma,
 	}
 	channel->desired_mode = *mode;
 	musb_writew(epio, MUSB_TXCSR, csr);
-
-	return 0;
 }
 
-static int musb_tx_dma_set_mode_cppi_tusb(struct dma_controller *dma,
-					  struct musb_hw_ep *hw_ep,
-					  struct musb_qh *qh,
-					  struct urb *urb,
-					  u32 offset,
-					  u32 *length,
-					  u8 *mode)
+static void musb_tx_dma_set_mode_cppi_tusb(struct dma_controller *dma,
+					   struct musb_hw_ep *hw_ep,
+					   struct musb_qh *qh,
+					   struct urb *urb,
+					   u32 offset,
+					   u32 *length,
+					   u8 *mode)
 {
 	struct dma_channel *channel = hw_ep->tx_channel;
 
-	if (!is_cppi_enabled(hw_ep->musb) && !tusb_dma_omap(hw_ep->musb))
-		return -ENODEV;
-
 	channel->actual_len = 0;
 
 	/*
@@ -688,8 +688,6 @@ static int musb_tx_dma_set_mode_cppi_tusb(struct dma_controller *dma,
 	 * to identify the zero-length-final-packet case.
 	 */
 	*mode = (urb->transfer_flags & URB_ZERO_PACKET) ? 1 : 0;
-
-	return 0;
 }
 
 static bool musb_tx_dma_program(struct dma_controller *dma,
@@ -699,15 +697,14 @@ static bool musb_tx_dma_program(struct dma_controller *dma,
 	struct dma_channel	*channel = hw_ep->tx_channel;
 	u16			pkt_size = qh->maxpacket;
 	u8			mode;
-	int			res;
 
 	if (musb_dma_inventra(hw_ep->musb) || musb_dma_ux500(hw_ep->musb))
-		res = musb_tx_dma_set_mode_mentor(dma, hw_ep, qh, urb,
-						 offset, &length, &mode);
+		musb_tx_dma_set_mode_mentor(dma, hw_ep, qh, urb, offset,
+					    &length, &mode);
+	else if (is_cppi_enabled(hw_ep->musb) || tusb_dma_omap(hw_ep->musb))
+		musb_tx_dma_set_mode_cppi_tusb(dma, hw_ep, qh, urb, offset,
+					       &length, &mode);
 	else
-		res = musb_tx_dma_set_mode_cppi_tusb(dma, hw_ep, qh, urb,
-						     offset, &length, &mode);
-	if (res)
 		return false;
 
 	qh->segsize = length;
@@ -995,9 +992,15 @@ static void musb_bulk_nak_timeout(struct musb *musb, struct musb_hw_ep *ep,
 	if (is_in) {
 		dma = is_dma_capable() ? ep->rx_channel : NULL;
 
-		/* clear nak timeout bit */
+		/*
+		 * Need to stop the transaction by clearing REQPKT first
+		 * then the NAK Timeout bit ref MUSBMHDRC USB 2.0 HIGH-SPEED
+		 * DUAL-ROLE CONTROLLER Programmer's Guide, section 9.2.2
+		 */
 		rx_csr = musb_readw(epio, MUSB_RXCSR);
 		rx_csr |= MUSB_RXCSR_H_WZC_BITS;
+		rx_csr &= ~MUSB_RXCSR_H_REQPKT;
+		musb_writew(epio, MUSB_RXCSR, rx_csr);
 		rx_csr &= ~MUSB_RXCSR_DATAERROR;
 		musb_writew(epio, MUSB_RXCSR, rx_csr);
 
@@ -1551,7 +1554,7 @@ static int musb_rx_dma_iso_cppi41(struct dma_controller *dma,
 				  struct urb *urb,
 				  size_t len)
 {
-	struct dma_channel *channel = hw_ep->tx_channel;
+	struct dma_channel *channel = hw_ep->rx_channel;
 	void __iomem *epio = hw_ep->regs;
 	dma_addr_t *buf;
 	u32 length, res;
@@ -1870,6 +1873,9 @@ void musb_host_rx(struct musb *musb, u8 epnum)
 		status = -EPROTO;
 		musb_writeb(epio, MUSB_RXINTERVAL, 0);
 
+		rx_csr &= ~MUSB_RXCSR_H_ERROR;
+		musb_writew(epio, MUSB_RXCSR, rx_csr);
+
 	} else if (rx_csr & MUSB_RXCSR_DATAERROR) {
 
 		if (USB_ENDPOINT_XFER_ISOC != qh->type) {
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index c84e0322c108..0b4cec940386 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -49,97 +49,14 @@ struct omap2430_glue {
 	enum musb_vbus_id_status status;
 	struct work_struct	omap_musb_mailbox_work;
 	struct device		*control_otghs;
+	bool			cable_connected;
+	bool			enabled;
+	bool			powered;
 };
 #define glue_to_musb(g)		platform_get_drvdata(g->musb)
 
 static struct omap2430_glue	*_glue;
 
-static struct timer_list musb_idle_timer;
-
-static void musb_do_idle(unsigned long _musb)
-{
-	struct musb	*musb = (void *)_musb;
-	unsigned long	flags;
-	u8	power;
-	u8	devctl;
-
-	spin_lock_irqsave(&musb->lock, flags);
-
-	switch (musb->xceiv->otg->state) {
-	case OTG_STATE_A_WAIT_BCON:
-
-		devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
-		if (devctl & MUSB_DEVCTL_BDEVICE) {
-			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
-			MUSB_DEV_MODE(musb);
-		} else {
-			musb->xceiv->otg->state = OTG_STATE_A_IDLE;
-			MUSB_HST_MODE(musb);
-		}
-		break;
-	case OTG_STATE_A_SUSPEND:
-		/* finish RESUME signaling? */
-		if (musb->port1_status & MUSB_PORT_STAT_RESUME) {
-			power = musb_readb(musb->mregs, MUSB_POWER);
-			power &= ~MUSB_POWER_RESUME;
-			dev_dbg(musb->controller, "root port resume stopped, power %02x\n", power);
-			musb_writeb(musb->mregs, MUSB_POWER, power);
-			musb->is_active = 1;
-			musb->port1_status &= ~(USB_PORT_STAT_SUSPEND
-						| MUSB_PORT_STAT_RESUME);
-			musb->port1_status |= USB_PORT_STAT_C_SUSPEND << 16;
-			usb_hcd_poll_rh_status(musb->hcd);
-			/* NOTE: it might really be A_WAIT_BCON ... */
-			musb->xceiv->otg->state = OTG_STATE_A_HOST;
-		}
-		break;
-	case OTG_STATE_A_HOST:
-		devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
-		if (devctl &  MUSB_DEVCTL_BDEVICE)
-			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
-		else
-			musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON;
-	default:
-		break;
-	}
-	spin_unlock_irqrestore(&musb->lock, flags);
-}
-
-
-static void omap2430_musb_try_idle(struct musb *musb, unsigned long timeout)
-{
-	unsigned long		default_timeout = jiffies + msecs_to_jiffies(3);
-	static unsigned long	last_timer;
-
-	if (timeout == 0)
-		timeout = default_timeout;
-
-	/* Never idle if active, or when VBUS timeout is not set as host */
-	if (musb->is_active || ((musb->a_wait_bcon == 0)
-			&& (musb->xceiv->otg->state == OTG_STATE_A_WAIT_BCON))) {
-		dev_dbg(musb->controller, "%s active, deleting timer\n",
-			usb_otg_state_string(musb->xceiv->otg->state));
-		del_timer(&musb_idle_timer);
-		last_timer = jiffies;
-		return;
-	}
-
-	if (time_after(last_timer, timeout)) {
-		if (!timer_pending(&musb_idle_timer))
-			last_timer = timeout;
-		else {
-			dev_dbg(musb->controller, "Longer idle timer already pending, ignoring\n");
-			return;
-		}
-	}
-	last_timer = timeout;
-
-	dev_dbg(musb->controller, "%s inactive, for idle timer for %lu ms\n",
-		usb_otg_state_string(musb->xceiv->otg->state),
-		(unsigned long)jiffies_to_msecs(timeout - jiffies));
-	mod_timer(&musb_idle_timer, timeout);
-}
-
 static void omap2430_musb_set_vbus(struct musb *musb, int is_on)
 {
 	struct usb_otg	*otg = musb->xceiv->otg;
@@ -205,16 +122,6 @@ static void omap2430_musb_set_vbus(struct musb *musb, int is_on)
 		musb_readb(musb->mregs, MUSB_DEVCTL));
 }
 
-static int omap2430_musb_set_mode(struct musb *musb, u8 musb_mode)
-{
-	u8	devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
-
-	devctl |= MUSB_DEVCTL_SESSION;
-	musb_writeb(musb->mregs, MUSB_DEVCTL, devctl);
-
-	return 0;
-}
-
 static inline void omap2430_low_level_exit(struct musb *musb)
 {
 	u32 l;
@@ -234,22 +141,63 @@ static inline void omap2430_low_level_init(struct musb *musb)
 	musb_writel(musb->mregs, OTG_FORCESTDBY, l);
 }
 
-static void omap2430_musb_mailbox(enum musb_vbus_id_status status)
+/*
+ * We can get multiple cable events so we need to keep track
+ * of the power state. Only keep power enabled if USB cable is
+ * connected and a gadget is started.
+ */
+static void omap2430_set_power(struct musb *musb, bool enabled, bool cable)
+{
+	struct device *dev = musb->controller;
+	struct omap2430_glue *glue = dev_get_drvdata(dev->parent);
+	bool power_up;
+	int res;
+
+	if (glue->enabled != enabled)
+		glue->enabled = enabled;
+
+	if (glue->cable_connected != cable)
+		glue->cable_connected = cable;
+
+	power_up = glue->enabled && glue->cable_connected;
+	if (power_up == glue->powered) {
+		dev_warn(musb->controller, "power state already %i\n",
+			 power_up);
+		return;
+	}
+
+	glue->powered = power_up;
+
+	if (power_up) {
+		res = pm_runtime_get_sync(musb->controller);
+		if (res < 0) {
+			dev_err(musb->controller, "could not enable: %i", res);
+			glue->powered = false;
+		}
+	} else {
+		pm_runtime_mark_last_busy(musb->controller);
+		pm_runtime_put_autosuspend(musb->controller);
+	}
+}
+
+static int omap2430_musb_mailbox(enum musb_vbus_id_status status)
 {
 	struct omap2430_glue	*glue = _glue;
 
 	if (!glue) {
 		pr_err("%s: musb core is not yet initialized\n", __func__);
-		return;
+		return -EPROBE_DEFER;
 	}
 	glue->status = status;
 
 	if (!glue_to_musb(glue)) {
 		pr_err("%s: musb core is not yet ready\n", __func__);
-		return;
+		return -EPROBE_DEFER;
 	}
 
 	schedule_work(&glue->omap_musb_mailbox_work);
+
+	return 0;
 }
 
 static void omap_musb_set_mailbox(struct omap2430_glue *glue)
@@ -259,6 +207,13 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
 	struct musb_hdrc_platform_data *pdata = dev_get_platdata(dev);
 	struct omap_musb_board_data *data = pdata->board_data;
 	struct usb_otg *otg = musb->xceiv->otg;
+	bool cable_connected;
+
+	cable_connected = ((glue->status == MUSB_ID_GROUND) ||
+			   (glue->status == MUSB_VBUS_VALID));
+
+	if (cable_connected)
+		omap2430_set_power(musb, glue->enabled, cable_connected);
 
 	switch (glue->status) {
 	case MUSB_ID_GROUND:
@@ -268,7 +223,6 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
 		musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 		musb->xceiv->last_event = USB_EVENT_ID;
 		if (musb->gadget_driver) {
-			pm_runtime_get_sync(dev);
 			omap_control_usb_set_mode(glue->control_otghs,
 				USB_MODE_HOST);
 			omap2430_musb_set_vbus(musb, 1);
@@ -281,8 +235,6 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
 		otg->default_a = false;
 		musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		musb->xceiv->last_event = USB_EVENT_VBUS;
-		if (musb->gadget_driver)
-			pm_runtime_get_sync(dev);
 		omap_control_usb_set_mode(glue->control_otghs, USB_MODE_DEVICE);
 		break;
 
@@ -291,11 +243,8 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
 		dev_dbg(dev, "VBUS Disconnect\n");
 
 		musb->xceiv->last_event = USB_EVENT_NONE;
-		if (musb->gadget_driver) {
+		if (musb->gadget_driver)
 			omap2430_musb_set_vbus(musb, 0);
-			pm_runtime_mark_last_busy(dev);
-			pm_runtime_put_autosuspend(dev);
-		}
 
 		if (data->interface_type == MUSB_INTERFACE_UTMI)
 			otg_set_vbus(musb->xceiv->otg, 0);
@@ -307,6 +256,9 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
 		dev_dbg(dev, "ID float\n");
 	}
 
+	if (!cable_connected)
+		omap2430_set_power(musb, glue->enabled, cable_connected);
+
 	atomic_notifier_call_chain(&musb->xceiv->notifier,
 			musb->xceiv->last_event, NULL);
 }
@@ -316,13 +268,8 @@ static void omap_musb_mailbox_work(struct work_struct *mailbox_work)
 {
 	struct omap2430_glue *glue = container_of(mailbox_work,
 				struct omap2430_glue, omap_musb_mailbox_work);
-	struct musb *musb = glue_to_musb(glue);
-	struct device *dev = musb->controller;
 
-	pm_runtime_get_sync(dev);
 	omap_musb_set_mailbox(glue);
-	pm_runtime_mark_last_busy(dev);
-	pm_runtime_put_autosuspend(dev);
 }
 
 static irqreturn_t omap2430_musb_interrupt(int irq, void *__hci)
@@ -389,23 +336,7 @@ static int omap2430_musb_init(struct musb *musb)
 		return PTR_ERR(musb->phy);
 	}
 	musb->isr = omap2430_musb_interrupt;
-
-	/*
-	 * Enable runtime PM for musb parent (this driver). We can't
-	 * do it earlier as struct musb is not yet allocated and we
-	 * need to touch the musb registers for runtime PM.
-	 */
-	pm_runtime_enable(glue->dev);
-	status = pm_runtime_get_sync(glue->dev);
-	if (status < 0)
-		goto err1;
-
-	status = pm_runtime_get_sync(dev);
-	if (status < 0) {
-		dev_err(dev, "pm_runtime_get_sync FAILED %d\n", status);
-		pm_runtime_put_sync(glue->dev);
-		goto err1;
-	}
+	phy_init(musb->phy);
 
 	l = musb_readl(musb->mregs, OTG_INTERFSEL);
 
@@ -427,20 +358,10 @@ static int omap2430_musb_init(struct musb *musb)
 			musb_readl(musb->mregs, OTG_INTERFSEL),
 			musb_readl(musb->mregs, OTG_SIMENABLE));
 
-	setup_timer(&musb_idle_timer, musb_do_idle, (unsigned long) musb);
-
 	if (glue->status != MUSB_UNKNOWN)
 		omap_musb_set_mailbox(glue);
 
-	phy_init(musb->phy);
-	phy_power_on(musb->phy);
-
-	pm_runtime_put_noidle(musb->controller);
-	pm_runtime_put_noidle(glue->dev);
 	return 0;
-
-err1:
-	return status;
 }
 
 static void omap2430_musb_enable(struct musb *musb)
@@ -452,6 +373,11 @@ static void omap2430_musb_enable(struct musb *musb)
 	struct musb_hdrc_platform_data *pdata = dev_get_platdata(dev);
 	struct omap_musb_board_data *data = pdata->board_data;
 
+	if (!WARN_ON(!musb->phy))
+		phy_power_on(musb->phy);
+
+	omap2430_set_power(musb, true, glue->cable_connected);
+
 	switch (glue->status) {
 
 	case MUSB_ID_GROUND:
@@ -487,18 +413,25 @@ static void omap2430_musb_disable(struct musb *musb)
 	struct device *dev = musb->controller;
 	struct omap2430_glue *glue = dev_get_drvdata(dev->parent);
 
+	if (!WARN_ON(!musb->phy))
+		phy_power_off(musb->phy);
+
 	if (glue->status != MUSB_UNKNOWN)
 		omap_control_usb_set_mode(glue->control_otghs,
 			USB_MODE_DISCONNECT);
+
+	omap2430_set_power(musb, false, glue->cable_connected);
 }
 
 static int omap2430_musb_exit(struct musb *musb)
 {
-	del_timer_sync(&musb_idle_timer);
+	struct device *dev = musb->controller;
+	struct omap2430_glue *glue = dev_get_drvdata(dev->parent);
 
 	omap2430_low_level_exit(musb);
-	phy_power_off(musb->phy);
 	phy_exit(musb->phy);
+	musb->phy = NULL;
+	cancel_work_sync(&glue->omap_musb_mailbox_work);
 
 	return 0;
 }
@@ -512,9 +445,6 @@ static const struct musb_platform_ops omap2430_ops = {
 	.init		= omap2430_musb_init,
 	.exit		= omap2430_musb_exit,
 
-	.set_mode	= omap2430_musb_set_mode,
-	.try_idle	= omap2430_musb_try_idle,
-
 	.set_vbus	= omap2430_musb_set_vbus,
 
 	.enable		= omap2430_musb_enable,
@@ -639,11 +569,9 @@ static int omap2430_probe(struct platform_device *pdev)
 		goto err2;
 	}
 
-	/*
-	 * Note that we cannot enable PM runtime yet for this
-	 * driver as we need struct musb initialized first.
-	 * See omap2430_musb_init above.
-	 */
+	pm_runtime_enable(glue->dev);
+	pm_runtime_use_autosuspend(glue->dev);
+	pm_runtime_set_autosuspend_delay(glue->dev, 500);
 
 	ret = platform_device_add(musb);
 	if (ret) {
@@ -662,12 +590,14 @@ err0:
 
 static int omap2430_remove(struct platform_device *pdev)
 {
-	struct omap2430_glue		*glue = platform_get_drvdata(pdev);
+	struct omap2430_glue *glue = platform_get_drvdata(pdev);
+	struct musb *musb = glue_to_musb(glue);
 
 	pm_runtime_get_sync(glue->dev);
-	cancel_work_sync(&glue->omap_musb_mailbox_work);
 	platform_device_unregister(glue->musb);
+	omap2430_set_power(musb, false, false);
 	pm_runtime_put_sync(glue->dev);
+	pm_runtime_dont_use_autosuspend(glue->dev);
 	pm_runtime_disable(glue->dev);
 
 	return 0;
@@ -680,12 +610,13 @@ static int omap2430_runtime_suspend(struct device *dev)
 	struct omap2430_glue		*glue = dev_get_drvdata(dev);
 	struct musb			*musb = glue_to_musb(glue);
 
-	if (musb) {
-		musb->context.otg_interfsel = musb_readl(musb->mregs,
-				OTG_INTERFSEL);
+	if (!musb)
+		return 0;
 
-		omap2430_low_level_exit(musb);
-	}
+	musb->context.otg_interfsel = musb_readl(musb->mregs,
+						 OTG_INTERFSEL);
+
+	omap2430_low_level_exit(musb);
 
 	return 0;
 }
@@ -696,7 +627,7 @@ static int omap2430_runtime_resume(struct device *dev)
 	struct musb			*musb = glue_to_musb(glue);
 
 	if (!musb)
-		return -EPROBE_DEFER;
+		return 0;
 
 	omap2430_low_level_init(musb);
 	musb_writel(musb->mregs, OTG_INTERFSEL,
@@ -738,18 +669,8 @@ static struct platform_driver omap2430_driver = {
 	},
 };
 
+module_platform_driver(omap2430_driver);
+
 MODULE_DESCRIPTION("OMAP2PLUS MUSB Glue Layer");
 MODULE_AUTHOR("Felipe Balbi <[email protected]>");
 MODULE_LICENSE("GPL v2");
-
-static int __init omap2430_init(void)
-{
-	return platform_driver_register(&omap2430_driver);
-}
-subsys_initcall(omap2430_init);
-
-static void __exit omap2430_exit(void)
-{
-	platform_driver_unregister(&omap2430_driver);
-}
-module_exit(omap2430_exit);
diff --git a/drivers/usb/musb/sunxi.c b/drivers/usb/musb/sunxi.c
index fdab4232cfbf..76500515dd8b 100644
--- a/drivers/usb/musb/sunxi.c
+++ b/drivers/usb/musb/sunxi.c
@@ -80,7 +80,8 @@ static struct musb *sunxi_musb;
 
 struct sunxi_glue {
 	struct device		*dev;
-	struct platform_device	*musb;
+	struct musb		*musb;
+	struct platform_device	*musb_pdev;
 	struct clk		*clk;
 	struct reset_control	*rst;
 	struct phy		*phy;
@@ -102,7 +103,7 @@ static void sunxi_musb_work(struct work_struct *work)
 		return;
 
 	if (test_and_clear_bit(SUNXI_MUSB_FL_HOSTMODE_PEND, &glue->flags)) {
-		struct musb *musb = platform_get_drvdata(glue->musb);
+		struct musb *musb = glue->musb;
 		unsigned long flags;
 		u8 devctl;
 
@@ -112,7 +113,7 @@ static void sunxi_musb_work(struct work_struct *work)
 		if (test_bit(SUNXI_MUSB_FL_HOSTMODE, &glue->flags)) {
 			set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
 			musb->xceiv->otg->default_a = 1;
-			musb->xceiv->otg->state = OTG_STATE_A_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			MUSB_HST_MODE(musb);
 			devctl |= MUSB_DEVCTL_SESSION;
 		} else {
@@ -145,10 +146,12 @@ static void sunxi_musb_set_vbus(struct musb *musb, int is_on)
 {
 	struct sunxi_glue *glue = dev_get_drvdata(musb->controller->parent);
 
-	if (is_on)
+	if (is_on) {
 		set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
-	else
+		musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
+	} else {
 		clear_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
+	}
 
 	schedule_work(&glue->work);
 }
@@ -264,15 +267,6 @@ static int sunxi_musb_init(struct musb *musb)
 	if (ret)
 		goto error_unregister_notifier;
 
-	if (musb->port_mode == MUSB_PORT_MODE_HOST) {
-		ret = phy_power_on(glue->phy);
-		if (ret)
-			goto error_phy_exit;
-		set_bit(SUNXI_MUSB_FL_PHY_ON, &glue->flags);
-		/* Stop musb work from turning vbus off again */
-		set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
-	}
-
 	musb->isr = sunxi_musb_interrupt;
 
 	/* Stop the musb-core from doing runtime pm (not supported on sunxi) */
@@ -280,8 +274,6 @@ static int sunxi_musb_init(struct musb *musb)
 
 	return 0;
 
-error_phy_exit:
-	phy_exit(glue->phy);
 error_unregister_notifier:
 	if (musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE)
 		extcon_unregister_notifier(glue->extcon, EXTCON_USB_HOST,
@@ -323,10 +315,31 @@ static int sunxi_musb_exit(struct musb *musb)
 	return 0;
 }
 
+static int sunxi_set_mode(struct musb *musb, u8 mode)
+{
+	struct sunxi_glue *glue = dev_get_drvdata(musb->controller->parent);
+	int ret;
+
+	if (mode == MUSB_HOST) {
+		ret = phy_power_on(glue->phy);
+		if (ret)
+			return ret;
+
+		set_bit(SUNXI_MUSB_FL_PHY_ON, &glue->flags);
+		/* Stop musb work from turning vbus off again */
+		set_bit(SUNXI_MUSB_FL_VBUS_ON, &glue->flags);
+		musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
+	}
+
+	return 0;
+}
+
 static void sunxi_musb_enable(struct musb *musb)
 {
 	struct sunxi_glue *glue = dev_get_drvdata(musb->controller->parent);
 
+	glue->musb = musb;
+
 	/* musb_core does not call us in a balanced manner */
 	if (test_and_set_bit(SUNXI_MUSB_FL_ENABLED, &glue->flags))
 		return;
@@ -569,6 +582,7 @@ static const struct musb_platform_ops sunxi_musb_ops = {
 	.exit		= sunxi_musb_exit,
 	.enable		= sunxi_musb_enable,
 	.disable	= sunxi_musb_disable,
+	.set_mode	= sunxi_set_mode,
 	.fifo_offset	= sunxi_musb_fifo_offset,
 	.ep_offset	= sunxi_musb_ep_offset,
 	.busctl_offset	= sunxi_musb_busctl_offset,
@@ -721,9 +735,9 @@ static int sunxi_musb_probe(struct platform_device *pdev)
 	pinfo.data	= &pdata;
 	pinfo.size_data = sizeof(pdata);
 
-	glue->musb = platform_device_register_full(&pinfo);
-	if (IS_ERR(glue->musb)) {
-		ret = PTR_ERR(glue->musb);
+	glue->musb_pdev = platform_device_register_full(&pinfo);
+	if (IS_ERR(glue->musb_pdev)) {
+		ret = PTR_ERR(glue->musb_pdev);
 		dev_err(&pdev->dev, "Error registering musb dev: %d\n", ret);
 		goto err_unregister_usb_phy;
 	}
@@ -740,7 +754,7 @@ static int sunxi_musb_remove(struct platform_device *pdev)
 	struct sunxi_glue *glue = platform_get_drvdata(pdev);
 	struct platform_device *usb_phy = glue->usb_phy;
 
-	platform_device_unregister(glue->musb); /* Frees glue ! */
+	platform_device_unregister(glue->musb_pdev);
 	usb_phy_generic_unregister(usb_phy);
 
 	return 0;
diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c
index 24e2b3cf1867..a72e8d670adc 100644
--- a/drivers/usb/phy/phy-twl6030-usb.c
+++ b/drivers/usb/phy/phy-twl6030-usb.c
@@ -97,6 +97,9 @@ struct twl6030_usb {
 
 	struct regulator		*usb3v3;
 
+	/* used to check initial cable status after probe */
+	struct delayed_work	get_status_work;
+
 	/* used to set vbus, in atomic path */
 	struct work_struct	set_vbus_work;
 
@@ -227,12 +230,16 @@ static irqreturn_t twl6030_usb_irq(int irq, void *_twl)
 			twl->asleep = 1;
 			status = MUSB_VBUS_VALID;
 			twl->linkstat = status;
-			musb_mailbox(status);
+			ret = musb_mailbox(status);
+			if (ret)
+				twl->linkstat = MUSB_UNKNOWN;
 		} else {
 			if (twl->linkstat != MUSB_UNKNOWN) {
 				status = MUSB_VBUS_OFF;
 				twl->linkstat = status;
-				musb_mailbox(status);
+				ret = musb_mailbox(status);
+				if (ret)
+					twl->linkstat = MUSB_UNKNOWN;
 				if (twl->asleep) {
 					regulator_disable(twl->usb3v3);
 					twl->asleep = 0;
@@ -264,7 +271,9 @@ static irqreturn_t twl6030_usbotg_irq(int irq, void *_twl)
 		twl6030_writeb(twl, TWL_MODULE_USB, 0x10, USB_ID_INT_EN_HI_SET);
 		status = MUSB_ID_GROUND;
 		twl->linkstat = status;
-		musb_mailbox(status);
+		ret = musb_mailbox(status);
+		if (ret)
+			twl->linkstat = MUSB_UNKNOWN;
 	} else  {
 		twl6030_writeb(twl, TWL_MODULE_USB, 0x10, USB_ID_INT_EN_HI_CLR);
 		twl6030_writeb(twl, TWL_MODULE_USB, 0x1, USB_ID_INT_EN_HI_SET);
@@ -274,6 +283,15 @@ static irqreturn_t twl6030_usbotg_irq(int irq, void *_twl)
 	return IRQ_HANDLED;
 }
 
+static void twl6030_status_work(struct work_struct *work)
+{
+	struct twl6030_usb *twl = container_of(work, struct twl6030_usb,
+					       get_status_work.work);
+
+	twl6030_usb_irq(twl->irq2, twl);
+	twl6030_usbotg_irq(twl->irq1, twl);
+}
+
 static int twl6030_enable_irq(struct twl6030_usb *twl)
 {
 	twl6030_writeb(twl, TWL_MODULE_USB, 0x1, USB_ID_INT_EN_HI_SET);
@@ -284,8 +302,6 @@ static int twl6030_enable_irq(struct twl6030_usb *twl)
 				REG_INT_MSK_LINE_C);
 	twl6030_interrupt_unmask(TWL6030_CHARGER_CTRL_INT_MASK,
 				REG_INT_MSK_STS_C);
-	twl6030_usb_irq(twl->irq2, twl);
-	twl6030_usbotg_irq(twl->irq1, twl);
 
 	return 0;
 }
@@ -371,6 +387,7 @@ static int twl6030_usb_probe(struct platform_device *pdev)
 		dev_warn(&pdev->dev, "could not create sysfs file\n");
 
 	INIT_WORK(&twl->set_vbus_work, otg_set_vbus_work);
+	INIT_DELAYED_WORK(&twl->get_status_work, twl6030_status_work);
 
 	status = request_threaded_irq(twl->irq1, NULL, twl6030_usbotg_irq,
 			IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING | IRQF_ONESHOT,
@@ -395,6 +412,7 @@ static int twl6030_usb_probe(struct platform_device *pdev)
 
 	twl->asleep = 0;
 	twl6030_enable_irq(twl);
+	schedule_delayed_work(&twl->get_status_work, HZ);
 	dev_info(&pdev->dev, "Initialized TWL6030 USB module\n");
 
 	return 0;
@@ -404,6 +422,7 @@ static int twl6030_usb_remove(struct platform_device *pdev)
 {
 	struct twl6030_usb *twl = platform_get_drvdata(pdev);
 
+	cancel_delayed_work(&twl->get_status_work);
 	twl6030_interrupt_mask(TWL6030_USBOTG_INT_MASK,
 		REG_INT_MSK_LINE_C);
 	twl6030_interrupt_mask(TWL6030_USBOTG_INT_MASK,
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index 2eddbe538cda..5608af4a369d 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -2007,6 +2007,7 @@ static void mos7720_release(struct usb_serial *serial)
 				    urblist_entry)
 			usb_unlink_urb(urbtrack->urb);
 		spin_unlock_irqrestore(&mos_parport->listlock, flags);
+		parport_del_port(mos_parport->pp);
 
 		kref_put(&mos_parport->ref_count, destroy_mos_parport);
 	}
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 4d49fce406e1..5ef014ba6ae8 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -836,6 +836,7 @@ static int uas_slave_configure(struct scsi_device *sdev)
 	if (devinfo->flags & US_FL_BROKEN_FUA)
 		sdev->broken_fua = 1;
 
+	scsi_change_queue_depth(sdev, devinfo->qdepth - 2);
 	return 0;
 }
 
@@ -848,7 +849,6 @@ static struct scsi_host_template uas_host_template = {
 	.slave_configure = uas_slave_configure,
 	.eh_abort_handler = uas_eh_abort_handler,
 	.eh_bus_reset_handler = uas_eh_bus_reset_handler,
-	.can_queue = MAX_CMNDS,
 	.this_id = -1,
 	.sg_tablesize = SG_NONE,
 	.skip_settle_delay = 1,
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index fca51105974e..2e0450bec1b1 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -941,7 +941,7 @@ static void vhci_stop(struct usb_hcd *hcd)
 
 static int vhci_get_frame_number(struct usb_hcd *hcd)
 {
-	pr_err("Not yet implemented\n");
+	dev_err_ratelimited(&hcd->self.root_hub->dev, "Not yet implemented\n");
 	return 0;
 }
 
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 93601407dab8..688691d9058d 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -749,7 +749,8 @@ static int vfio_vpd_config_write(struct vfio_pci_device *vdev, int pos,
 		if (pci_write_vpd(pdev, addr & ~PCI_VPD_ADDR_F, 4, &data) != 4)
 			return count;
 	} else {
-		if (pci_read_vpd(pdev, addr, 4, &data) != 4)
+		data = 0;
+		if (pci_read_vpd(pdev, addr, 4, &data) < 0)
 			return count;
 		*pdata = cpu_to_le32(data);
 	}
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index e9ea3fef144a..15ecfc9c5f6c 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -228,9 +228,9 @@ static int vfio_intx_set_signal(struct vfio_pci_device *vdev, int fd)
 
 static void vfio_intx_disable(struct vfio_pci_device *vdev)
 {
-	vfio_intx_set_signal(vdev, -1);
 	vfio_virqfd_disable(&vdev->ctx[0].unmask);
 	vfio_virqfd_disable(&vdev->ctx[0].mask);
+	vfio_intx_set_signal(vdev, -1);
 	vdev->irq_type = VFIO_PCI_NUM_IRQS;
 	vdev->num_ctx = 0;
 	kfree(vdev->ctx);
@@ -401,13 +401,13 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
 	struct pci_dev *pdev = vdev->pdev;
 	int i;
 
-	vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
-
 	for (i = 0; i < vdev->num_ctx; i++) {
 		vfio_virqfd_disable(&vdev->ctx[i].unmask);
 		vfio_virqfd_disable(&vdev->ctx[i].mask);
 	}
 
+	vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
+
 	if (msix) {
 		pci_disable_msix(vdev->pdev);
 		kfree(vdev->msix);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 15a65823aad9..2ba19424e4a1 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -515,7 +515,7 @@ static int map_try_harder(struct vfio_domain *domain, dma_addr_t iova,
 			  unsigned long pfn, long npage, int prot)
 {
 	long i;
-	int ret;
+	int ret = 0;
 
 	for (i = 0; i < npage; i++, pfn++, iova += PAGE_SIZE) {
 		ret = iommu_map(domain->domain, iova,
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f744eeb3e2b4..e032ca397371 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -301,6 +301,32 @@ static bool vhost_can_busy_poll(struct vhost_dev *dev,
 	       !vhost_has_work(dev);
 }
 
+static void vhost_net_disable_vq(struct vhost_net *n,
+				 struct vhost_virtqueue *vq)
+{
+	struct vhost_net_virtqueue *nvq =
+		container_of(vq, struct vhost_net_virtqueue, vq);
+	struct vhost_poll *poll = n->poll + (nvq - n->vqs);
+	if (!vq->private_data)
+		return;
+	vhost_poll_stop(poll);
+}
+
+static int vhost_net_enable_vq(struct vhost_net *n,
+				struct vhost_virtqueue *vq)
+{
+	struct vhost_net_virtqueue *nvq =
+		container_of(vq, struct vhost_net_virtqueue, vq);
+	struct vhost_poll *poll = n->poll + (nvq - n->vqs);
+	struct socket *sock;
+
+	sock = vq->private_data;
+	if (!sock)
+		return 0;
+
+	return vhost_poll_start(poll, sock->file);
+}
+
 static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 				    struct vhost_virtqueue *vq,
 				    struct iovec iov[], unsigned int iov_size,
@@ -455,10 +481,14 @@ out:
 
 static int peek_head_len(struct sock *sk)
 {
+	struct socket *sock = sk->sk_socket;
 	struct sk_buff *head;
 	int len = 0;
 	unsigned long flags;
 
+	if (sock->ops->peek_len)
+		return sock->ops->peek_len(sock);
+
 	spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
 	head = skb_peek(&sk->sk_receive_queue);
 	if (likely(head)) {
@@ -471,6 +501,16 @@ static int peek_head_len(struct sock *sk)
 	return len;
 }
 
+static int sk_has_rx_data(struct sock *sk)
+{
+	struct socket *sock = sk->sk_socket;
+
+	if (sock->ops->peek_len)
+		return sock->ops->peek_len(sock);
+
+	return skb_queue_empty(&sk->sk_receive_queue);
+}
+
 static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 {
 	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
@@ -487,7 +527,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 		endtime = busy_clock() + vq->busyloop_timeout;
 
 		while (vhost_can_busy_poll(&net->dev, endtime) &&
-		       skb_queue_empty(&sk->sk_receive_queue) &&
+		       !sk_has_rx_data(sk) &&
 		       vhost_vq_avail_empty(&net->dev, vq))
 			cpu_relax_lowlatency();
 
@@ -613,6 +653,7 @@ static void handle_rx(struct vhost_net *net)
 	if (!sock)
 		goto out;
 	vhost_disable_notify(&net->dev, vq);
+	vhost_net_disable_vq(net, vq);
 
 	vhost_hlen = nvq->vhost_hlen;
 	sock_hlen = nvq->sock_hlen;
@@ -629,7 +670,7 @@ static void handle_rx(struct vhost_net *net)
 					likely(mergeable) ? UIO_MAXIOV : 1);
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
-			break;
+			goto out;
 		/* On overrun, truncate and discard */
 		if (unlikely(headcount > UIO_MAXIOV)) {
 			iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
@@ -648,7 +689,7 @@ static void handle_rx(struct vhost_net *net)
 			}
 			/* Nothing new?  Wait for eventfd to tell us
 			 * they refilled. */
-			break;
+			goto out;
 		}
 		/* We don't need to be notified again. */
 		iov_iter_init(&msg.msg_iter, READ, vq->iov, in, vhost_len);
@@ -676,7 +717,7 @@ static void handle_rx(struct vhost_net *net)
 					 &fixup) != sizeof(hdr)) {
 				vq_err(vq, "Unable to write vnet_hdr "
 				       "at addr %p\n", vq->iov->iov_base);
-				break;
+				goto out;
 			}
 		} else {
 			/* Header came from socket; we'll need to patch
@@ -692,7 +733,7 @@ static void handle_rx(struct vhost_net *net)
 				 &fixup) != sizeof num_buffers) {
 			vq_err(vq, "Failed num_buffers write");
 			vhost_discard_vq_desc(vq, headcount);
-			break;
+			goto out;
 		}
 		vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
 					    headcount);
@@ -701,9 +742,10 @@ static void handle_rx(struct vhost_net *net)
 		total_len += vhost_len;
 		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
 			vhost_poll_queue(&vq->poll);
-			break;
+			goto out;
 		}
 	}
+	vhost_net_enable_vq(net, vq);
 out:
 	mutex_unlock(&vq->mutex);
 }
@@ -782,32 +824,6 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 	return 0;
 }
 
-static void vhost_net_disable_vq(struct vhost_net *n,
-				 struct vhost_virtqueue *vq)
-{
-	struct vhost_net_virtqueue *nvq =
-		container_of(vq, struct vhost_net_virtqueue, vq);
-	struct vhost_poll *poll = n->poll + (nvq - n->vqs);
-	if (!vq->private_data)
-		return;
-	vhost_poll_stop(poll);
-}
-
-static int vhost_net_enable_vq(struct vhost_net *n,
-				struct vhost_virtqueue *vq)
-{
-	struct vhost_net_virtqueue *nvq =
-		container_of(vq, struct vhost_net_virtqueue, vq);
-	struct vhost_poll *poll = n->poll + (nvq - n->vqs);
-	struct socket *sock;
-
-	sock = vq->private_data;
-	if (!sock)
-		return 0;
-
-	return vhost_poll_start(poll, sock->file);
-}
-
 static struct socket *vhost_net_stop_vq(struct vhost_net *n,
 					struct vhost_virtqueue *vq)
 {
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c
index 8ea531d2652c..bbfe7e2d4332 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c
@@ -51,8 +51,8 @@ static void hdmi_core_ddc_init(struct hdmi_core_data *core)
 {
 	void __iomem *base = core->base;
 	const unsigned long long iclk = 266000000;	/* DSS L3 ICLK */
-	const unsigned ss_scl_high = 4000;		/* ns */
-	const unsigned ss_scl_low = 4700;		/* ns */
+	const unsigned ss_scl_high = 4600;		/* ns */
+	const unsigned ss_scl_low = 5400;		/* ns */
 	const unsigned fs_scl_high = 600;		/* ns */
 	const unsigned fs_scl_low = 1300;		/* ns */
 	const unsigned sda_hold = 1000;			/* ns */
@@ -442,7 +442,7 @@ static void hdmi_core_write_avi_infoframe(struct hdmi_core_data *core,
 
 	c = (ptr[1] >> 6) & 0x3;
 	m = (ptr[1] >> 4) & 0x3;
-	r = (ptr[1] >> 0) & 0x3;
+	r = (ptr[1] >> 0) & 0xf;
 
 	itc = (ptr[2] >> 7) & 0x1;
 	ec = (ptr[2] >> 4) & 0x7;
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index b54f26c55dfd..b4b3e256491b 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -746,7 +746,7 @@ config ALIM7101_WDT
 
 config EBC_C384_WDT
 	tristate "WinSystems EBC-C384 Watchdog Timer"
-	depends on X86 && ISA
+	depends on X86 && ISA_BUS_API
 	select WATCHDOG_CORE
 	help
 	  Enables watchdog timer support for the watchdog timer on the
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index d46839f51e73..e4db19e88ab1 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -151,8 +151,6 @@ static DECLARE_WAIT_QUEUE_HEAD(balloon_wq);
 static void balloon_process(struct work_struct *work);
 static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
 
-static void release_memory_resource(struct resource *resource);
-
 /* When ballooning out (allocating memory to return to Xen) we don't really
    want the kernel to try too hard since that can trigger the oom killer. */
 #define GFP_BALLOON \
@@ -248,6 +246,19 @@ static enum bp_state update_schedule(enum bp_state state)
 }
 
 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+static void release_memory_resource(struct resource *resource)
+{
+	if (!resource)
+		return;
+
+	/*
+	 * No need to reset region to identity mapped since we now
+	 * know that no I/O can be in this region
+	 */
+	release_resource(resource);
+	kfree(resource);
+}
+
 static struct resource *additional_memory_resource(phys_addr_t size)
 {
 	struct resource *res;
@@ -286,19 +297,6 @@ static struct resource *additional_memory_resource(phys_addr_t size)
 	return res;
 }
 
-static void release_memory_resource(struct resource *resource)
-{
-	if (!resource)
-		return;
-
-	/*
-	 * No need to reset region to identity mapped since we now
-	 * know that no I/O can be in this region
-	 */
-	release_resource(resource);
-	kfree(resource);
-}
-
 static enum bp_state reserve_additional_memory(void)
 {
 	long credit;
diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
index 8e67336f8ddd..6a25533da237 100644
--- a/drivers/xen/xen-pciback/conf_space.c
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -183,8 +183,7 @@ int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size,
 		field_start = OFFSET(cfg_entry);
 		field_end = OFFSET(cfg_entry) + field->size;
 
-		if ((req_start >= field_start && req_start < field_end)
-		    || (req_end > field_start && req_end <= field_end)) {
+		 if (req_end > field_start && field_end > req_start) {
 			err = conf_space_read(dev, cfg_entry, field_start,
 					      &tmp_val);
 			if (err)
@@ -230,8 +229,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
 		field_start = OFFSET(cfg_entry);
 		field_end = OFFSET(cfg_entry) + field->size;
 
-		if ((req_start >= field_start && req_start < field_end)
-		    || (req_end > field_start && req_end <= field_end)) {
+		 if (req_end > field_start && field_end > req_start) {
 			tmp_val = 0;
 
 			err = xen_pcibk_config_read(dev, field_start,
diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c
index ad3d17d29c81..9ead1c2ff1dd 100644
--- a/drivers/xen/xen-pciback/conf_space_header.c
+++ b/drivers/xen/xen-pciback/conf_space_header.c
@@ -145,7 +145,7 @@ static int rom_write(struct pci_dev *dev, int offset, u32 value, void *data)
 	/* A write to obtain the length must happen as a 32-bit write.
 	 * This does not (yet) support writing individual bytes
 	 */
-	if (value == ~PCI_ROM_ADDRESS_ENABLE)
+	if ((value | ~PCI_ROM_ADDRESS_MASK) == ~0U)
 		bar->which = 1;
 	else {
 		u32 tmpval;
@@ -225,38 +225,42 @@ static inline void read_dev_bar(struct pci_dev *dev,
 			   (PCI_BASE_ADDRESS_SPACE_MEMORY |
 				PCI_BASE_ADDRESS_MEM_TYPE_64))) {
 			bar_info->val = res[pos - 1].start >> 32;
-			bar_info->len_val = res[pos - 1].end >> 32;
+			bar_info->len_val = -resource_size(&res[pos - 1]) >> 32;
 			return;
 		}
 	}
 
+	if (!res[pos].flags ||
+	    (res[pos].flags & (IORESOURCE_DISABLED | IORESOURCE_UNSET |
+			       IORESOURCE_BUSY)))
+		return;
+
 	bar_info->val = res[pos].start |
 			(res[pos].flags & PCI_REGION_FLAG_MASK);
-	bar_info->len_val = resource_size(&res[pos]);
+	bar_info->len_val = -resource_size(&res[pos]) |
+			    (res[pos].flags & PCI_REGION_FLAG_MASK);
 }
 
 static void *bar_init(struct pci_dev *dev, int offset)
 {
-	struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL);
+	struct pci_bar_info *bar = kzalloc(sizeof(*bar), GFP_KERNEL);
 
 	if (!bar)
 		return ERR_PTR(-ENOMEM);
 
 	read_dev_bar(dev, bar, offset, ~0);
-	bar->which = 0;
 
 	return bar;
 }
 
 static void *rom_init(struct pci_dev *dev, int offset)
 {
-	struct pci_bar_info *bar = kmalloc(sizeof(*bar), GFP_KERNEL);
+	struct pci_bar_info *bar = kzalloc(sizeof(*bar), GFP_KERNEL);
 
 	if (!bar)
 		return ERR_PTR(-ENOMEM);
 
 	read_dev_bar(dev, bar, offset, ~PCI_ROM_ADDRESS_ENABLE);
-	bar->which = 0;
 
 	return bar;
 }
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 63cd9f939f19..4832de84d52c 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -85,18 +85,14 @@ int afs_open_socket(void)
 
 	skb_queue_head_init(&afs_incoming_calls);
 
+	ret = -ENOMEM;
 	afs_async_calls = create_singlethread_workqueue("kafsd");
-	if (!afs_async_calls) {
-		_leave(" = -ENOMEM [wq]");
-		return -ENOMEM;
-	}
+	if (!afs_async_calls)
+		goto error_0;
 
 	ret = sock_create_kern(&init_net, AF_RXRPC, SOCK_DGRAM, PF_INET, &socket);
-	if (ret < 0) {
-		destroy_workqueue(afs_async_calls);
-		_leave(" = %d [socket]", ret);
-		return ret;
-	}
+	if (ret < 0)
+		goto error_1;
 
 	socket->sk->sk_allocation = GFP_NOFS;
 
@@ -111,18 +107,26 @@ int afs_open_socket(void)
 	       sizeof(srx.transport.sin.sin_addr));
 
 	ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx));
-	if (ret < 0) {
-		sock_release(socket);
-		destroy_workqueue(afs_async_calls);
-		_leave(" = %d [bind]", ret);
-		return ret;
-	}
+	if (ret < 0)
+		goto error_2;
+
+	ret = kernel_listen(socket, INT_MAX);
+	if (ret < 0)
+		goto error_2;
 
 	rxrpc_kernel_intercept_rx_messages(socket, afs_rx_interceptor);
 
 	afs_socket = socket;
 	_leave(" = 0");
 	return 0;
+
+error_2:
+	sock_release(socket);
+error_1:
+	destroy_workqueue(afs_async_calls);
+error_0:
+	_leave(" = %d", ret);
+	return ret;
 }
 
 /*
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index f0d268b97d19..a439548de785 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -70,9 +70,13 @@ struct autofs_info {
 };
 
 #define AUTOFS_INF_EXPIRING	(1<<0) /* dentry in the process of expiring */
-#define AUTOFS_INF_NO_RCU	(1<<1) /* the dentry is being considered
+#define AUTOFS_INF_WANT_EXPIRE	(1<<1) /* the dentry is being considered
 					* for expiry, so RCU_walk is
-					* not permitted
+					* not permitted.  If it progresses to
+					* actual expiry attempt, the flag is
+					* not cleared when EXPIRING is set -
+					* in that case it gets cleared only
+					* when it comes to clearing EXPIRING.
 					*/
 #define AUTOFS_INF_PENDING	(1<<2) /* dentry pending mount */
 
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 9510d8d2e9cd..b493909e7492 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -316,19 +316,17 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
 	if (ino->flags & AUTOFS_INF_PENDING)
 		goto out;
 	if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
-		ino->flags |= AUTOFS_INF_NO_RCU;
+		ino->flags |= AUTOFS_INF_WANT_EXPIRE;
 		spin_unlock(&sbi->fs_lock);
 		synchronize_rcu();
 		spin_lock(&sbi->fs_lock);
 		if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
 			ino->flags |= AUTOFS_INF_EXPIRING;
-			smp_mb();
-			ino->flags &= ~AUTOFS_INF_NO_RCU;
 			init_completion(&ino->expire_complete);
 			spin_unlock(&sbi->fs_lock);
 			return root;
 		}
-		ino->flags &= ~AUTOFS_INF_NO_RCU;
+		ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
 	}
 out:
 	spin_unlock(&sbi->fs_lock);
@@ -446,7 +444,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	while ((dentry = get_next_positive_subdir(dentry, root))) {
 		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(dentry);
-		if (ino->flags & AUTOFS_INF_NO_RCU)
+		if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
 			expired = NULL;
 		else
 			expired = should_expire(dentry, mnt, timeout, how);
@@ -455,7 +453,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 			continue;
 		}
 		ino = autofs4_dentry_ino(expired);
-		ino->flags |= AUTOFS_INF_NO_RCU;
+		ino->flags |= AUTOFS_INF_WANT_EXPIRE;
 		spin_unlock(&sbi->fs_lock);
 		synchronize_rcu();
 		spin_lock(&sbi->fs_lock);
@@ -465,7 +463,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 			goto found;
 		}
 
-		ino->flags &= ~AUTOFS_INF_NO_RCU;
+		ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
 		if (expired != dentry)
 			dput(expired);
 		spin_unlock(&sbi->fs_lock);
@@ -475,17 +473,8 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 found:
 	pr_debug("returning %p %pd\n", expired, expired);
 	ino->flags |= AUTOFS_INF_EXPIRING;
-	smp_mb();
-	ino->flags &= ~AUTOFS_INF_NO_RCU;
 	init_completion(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
-	spin_lock(&sbi->lookup_lock);
-	spin_lock(&expired->d_parent->d_lock);
-	spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED);
-	list_move(&expired->d_parent->d_subdirs, &expired->d_child);
-	spin_unlock(&expired->d_lock);
-	spin_unlock(&expired->d_parent->d_lock);
-	spin_unlock(&sbi->lookup_lock);
 	return expired;
 }
 
@@ -496,7 +485,7 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 	int status;
 
 	/* Block on any pending expire */
-	if (!(ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU)))
+	if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE))
 		return 0;
 	if (rcu_walk)
 		return -ECHILD;
@@ -554,7 +543,7 @@ int autofs4_expire_run(struct super_block *sb,
 	ino = autofs4_dentry_ino(dentry);
 	/* avoid rapid-fire expire attempts if expiry fails */
 	ino->last_used = now;
-	ino->flags &= ~AUTOFS_INF_EXPIRING;
+	ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE);
 	complete_all(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
 
@@ -583,7 +572,7 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 		spin_lock(&sbi->fs_lock);
 		/* avoid rapid-fire expire attempts if expiry fails */
 		ino->last_used = now;
-		ino->flags &= ~AUTOFS_INF_EXPIRING;
+		ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE);
 		complete_all(&ino->expire_complete);
 		spin_unlock(&sbi->fs_lock);
 		dput(dentry);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 78bd80298528..3767f6641af1 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -458,7 +458,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 		 */
 		struct inode *inode;
 
-		if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))
+		if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
 			return 0;
 		if (d_mountpoint(dentry))
 			return 0;
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 0146d911f468..631f1554c87b 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -66,11 +66,12 @@ static int autofs4_write(struct autofs_sb_info *sbi,
 	set_fs(KERNEL_DS);
 
 	mutex_lock(&sbi->pipe_mutex);
-	wr = __vfs_write(file, data, bytes, &file->f_pos);
-	while (bytes && wr) {
+	while (bytes) {
+		wr = __vfs_write(file, data, bytes, &file->f_pos);
+		if (wr <= 0)
+			break;
 		data += wr;
 		bytes -= wr;
-		wr = __vfs_write(file, data, bytes, &file->f_pos);
 	}
 	mutex_unlock(&sbi->pipe_mutex);
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index e158b22ef32f..a7a28110dc80 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2275,7 +2275,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 		goto end_coredump;
 
 	/* Align to page */
-	if (!dump_skip(cprm, dataoff - cprm->file->f_pos))
+	if (!dump_skip(cprm, dataoff - cprm->pos))
 		goto end_coredump;
 
 	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 71ade0e556b7..203589311bf8 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1787,7 +1787,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 				goto end_coredump;
 	}
 
-	if (!dump_skip(cprm, dataoff - cprm->file->f_pos))
+	if (!dump_skip(cprm, dataoff - cprm->pos))
 		goto end_coredump;
 
 	if (!elf_fdpic_dump_segments(cprm))
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index b677a6ea6001..7706c8dc5fa6 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -2645,7 +2645,7 @@ static void btrfsic_dump_tree_sub(const struct btrfsic_state *state,
 	 * This algorithm is recursive because the amount of used stack space
 	 * is very small and the max recursion depth is limited.
 	 */
-	indent_add = sprintf(buf, "%c-%llu(%s/%llu/%d)",
+	indent_add = sprintf(buf, "%c-%llu(%s/%llu/%u)",
 			     btrfsic_get_block_type(state, block),
 			     block->logical_bytenr, block->dev_state->name,
 			     block->dev_bytenr, block->mirror_num);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 427c36b430a6..a85cf7d23309 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1373,7 +1373,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 
 	if (tm->op == MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
 		BUG_ON(tm->slot != 0);
-		eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start);
+		eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start,
+						eb->len);
 		if (!eb_rewin) {
 			btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
@@ -1454,7 +1455,8 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 	} else if (old_root) {
 		btrfs_tree_read_unlock(eb_root);
 		free_extent_buffer(eb_root);
-		eb = alloc_dummy_extent_buffer(root->fs_info, logical);
+		eb = alloc_dummy_extent_buffer(root->fs_info, logical,
+					root->nodesize);
 	} else {
 		btrfs_set_lock_blocking_rw(eb_root, BTRFS_READ_LOCK);
 		eb = btrfs_clone_extent_buffer(eb_root);
@@ -1552,6 +1554,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		       trans->transid, root->fs_info->generation);
 
 	if (!should_cow_block(trans, root, buf)) {
+		trans->dirty = true;
 		*cow_ret = buf;
 		return 0;
 	}
@@ -1783,10 +1786,12 @@ static noinline int generic_bin_search(struct extent_buffer *eb,
 			if (!err) {
 				tmp = (struct btrfs_disk_key *)(kaddr + offset -
 							map_start);
-			} else {
+			} else if (err == 1) {
 				read_extent_buffer(eb, &unaligned,
 						   offset, sizeof(unaligned));
 				tmp = &unaligned;
+			} else {
+				return err;
 			}
 
 		} else {
@@ -2510,6 +2515,8 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 		if (!btrfs_buffer_uptodate(tmp, 0, 0))
 			ret = -EIO;
 		free_extent_buffer(tmp);
+	} else {
+		ret = PTR_ERR(tmp);
 	}
 	return ret;
 }
@@ -2773,8 +2780,10 @@ again:
 			 * then we don't want to set the path blocking,
 			 * so we test it here
 			 */
-			if (!should_cow_block(trans, root, b))
+			if (!should_cow_block(trans, root, b)) {
+				trans->dirty = true;
 				goto cow_done;
+			}
 
 			/*
 			 * must have write locks on this node and the
@@ -2823,6 +2832,8 @@ cow_done:
 		}
 
 		ret = key_search(b, key, level, &prev_cmp, &slot);
+		if (ret < 0)
+			goto done;
 
 		if (level != 0) {
 			int dec = 0;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 101c3cfd3f7c..4274a7bfdaed 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2518,7 +2518,7 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, unsigned long count);
 int btrfs_async_run_delayed_refs(struct btrfs_root *root,
-				 unsigned long count, int wait);
+				 unsigned long count, u64 transid, int wait);
 int btrfs_lookup_data_extent(struct btrfs_root *root, u64 start, u64 len);
 int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 bytenr,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 61561c2a3f96..d3aaabbfada0 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1606,15 +1606,23 @@ int btrfs_inode_delayed_dir_index_count(struct inode *inode)
 	return 0;
 }
 
-void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
-			     struct list_head *del_list)
+bool btrfs_readdir_get_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list)
 {
 	struct btrfs_delayed_node *delayed_node;
 	struct btrfs_delayed_item *item;
 
 	delayed_node = btrfs_get_delayed_node(inode);
 	if (!delayed_node)
-		return;
+		return false;
+
+	/*
+	 * We can only do one readdir with delayed items at a time because of
+	 * item->readdir_list.
+	 */
+	inode_unlock_shared(inode);
+	inode_lock(inode);
 
 	mutex_lock(&delayed_node->mutex);
 	item = __btrfs_first_delayed_insertion_item(delayed_node);
@@ -1641,10 +1649,13 @@ void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
 	 * requeue or dequeue this delayed node.
 	 */
 	atomic_dec(&delayed_node->refs);
+
+	return true;
 }
 
-void btrfs_put_delayed_items(struct list_head *ins_list,
-			     struct list_head *del_list)
+void btrfs_readdir_put_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list)
 {
 	struct btrfs_delayed_item *curr, *next;
 
@@ -1659,6 +1670,12 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
 		if (atomic_dec_and_test(&curr->refs))
 			kfree(curr);
 	}
+
+	/*
+	 * The VFS is going to do up_read(), so we need to downgrade back to a
+	 * read lock.
+	 */
+	downgrade_write(&inode->i_rwsem);
 }
 
 int btrfs_should_delete_dir_index(struct list_head *del_list,
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 0167853c84ae..2495b3d4075f 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -137,10 +137,12 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root);
 void btrfs_destroy_delayed_inodes(struct btrfs_root *root);
 
 /* Used for readdir() */
-void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
-			     struct list_head *del_list);
-void btrfs_put_delayed_items(struct list_head *ins_list,
-			     struct list_head *del_list);
+bool btrfs_readdir_get_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list);
+void btrfs_readdir_put_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list);
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index);
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6628fca9f4ed..60ce1190307b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1098,7 +1098,7 @@ void readahead_tree_block(struct btrfs_root *root, u64 bytenr)
 	struct inode *btree_inode = root->fs_info->btree_inode;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
+	if (IS_ERR(buf))
 		return;
 	read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
 				 buf, 0, WAIT_NONE, btree_get_extent, 0);
@@ -1114,7 +1114,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
 	int ret;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
+	if (IS_ERR(buf))
 		return 0;
 
 	set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
@@ -1147,7 +1147,8 @@ struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						 u64 bytenr)
 {
 	if (btrfs_test_is_dummy_root(root))
-		return alloc_test_extent_buffer(root->fs_info, bytenr);
+		return alloc_test_extent_buffer(root->fs_info, bytenr,
+				root->nodesize);
 	return alloc_extent_buffer(root->fs_info, bytenr);
 }
 
@@ -1171,8 +1172,8 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
 	int ret;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(buf))
+		return buf;
 
 	ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
 	if (ret) {
@@ -1314,14 +1315,16 @@ static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 /* Should only be used by the testing infrastructure */
-struct btrfs_root *btrfs_alloc_dummy_root(void)
+struct btrfs_root *btrfs_alloc_dummy_root(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_root *root;
 
 	root = btrfs_alloc_root(NULL, GFP_KERNEL);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
-	__setup_root(4096, 4096, 4096, root, NULL, 1);
+	/* We don't use the stripesize in selftest, set it as sectorsize */
+	__setup_root(nodesize, sectorsize, sectorsize, root, NULL,
+			BTRFS_ROOT_TREE_OBJECTID);
 	set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state);
 	root->alloc_bytenr = 0;
 
@@ -1803,6 +1806,13 @@ static int cleaner_kthread(void *arg)
 		if (btrfs_need_cleaner_sleep(root))
 			goto sleep;
 
+		/*
+		 * Do not do anything if we might cause open_ctree() to block
+		 * before we have finished mounting the filesystem.
+		 */
+		if (!root->fs_info->open)
+			goto sleep;
+
 		if (!mutex_trylock(&root->fs_info->cleaner_mutex))
 			goto sleep;
 
@@ -2517,7 +2527,6 @@ int open_ctree(struct super_block *sb,
 	int num_backups_tried = 0;
 	int backup_index = 0;
 	int max_active;
-	bool cleaner_mutex_locked = false;
 
 	tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
@@ -2797,7 +2806,7 @@ int open_ctree(struct super_block *sb,
 
 	nodesize = btrfs_super_nodesize(disk_super);
 	sectorsize = btrfs_super_sectorsize(disk_super);
-	stripesize = btrfs_super_stripesize(disk_super);
+	stripesize = sectorsize;
 	fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
 	fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
 
@@ -2996,13 +3005,6 @@ retry_root_backup:
 		goto fail_sysfs;
 	}
 
-	/*
-	 * Hold the cleaner_mutex thread here so that we don't block
-	 * for a long time on btrfs_recover_relocation.  cleaner_kthread
-	 * will wait for us to finish mounting the filesystem.
-	 */
-	mutex_lock(&fs_info->cleaner_mutex);
-	cleaner_mutex_locked = true;
 	fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
 					       "btrfs-cleaner");
 	if (IS_ERR(fs_info->cleaner_kthread))
@@ -3062,8 +3064,10 @@ retry_root_backup:
 		ret = btrfs_cleanup_fs_roots(fs_info);
 		if (ret)
 			goto fail_qgroup;
-		/* We locked cleaner_mutex before creating cleaner_kthread. */
+
+		mutex_lock(&fs_info->cleaner_mutex);
 		ret = btrfs_recover_relocation(tree_root);
+		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret < 0) {
 			btrfs_warn(fs_info, "failed to recover relocation: %d",
 					ret);
@@ -3071,8 +3075,6 @@ retry_root_backup:
 			goto fail_qgroup;
 		}
 	}
-	mutex_unlock(&fs_info->cleaner_mutex);
-	cleaner_mutex_locked = false;
 
 	location.objectid = BTRFS_FS_TREE_OBJECTID;
 	location.type = BTRFS_ROOT_ITEM_KEY;
@@ -3186,10 +3188,6 @@ fail_cleaner:
 	filemap_write_and_wait(fs_info->btree_inode->i_mapping);
 
 fail_sysfs:
-	if (cleaner_mutex_locked) {
-		mutex_unlock(&fs_info->cleaner_mutex);
-		cleaner_mutex_locked = false;
-	}
 	btrfs_sysfs_remove_mounted(fs_info);
 
 fail_fsdev_sysfs:
@@ -4130,6 +4128,16 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
 	 * done later
 	 */
+	if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
+		btrfs_err(fs_info, "bytes_used is too small %llu",
+		       btrfs_super_bytes_used(sb));
+		ret = -EINVAL;
+	}
+	if (!is_power_of_2(btrfs_super_stripesize(sb))) {
+		btrfs_err(fs_info, "invalid stripesize %u",
+		       btrfs_super_stripesize(sb));
+		ret = -EINVAL;
+	}
 	if (btrfs_super_num_devices(sb) > (1UL << 31))
 		printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
 				btrfs_super_num_devices(sb));
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 8e79d0070bcf..acba821499a9 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -90,7 +90,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 void btrfs_free_fs_root(struct btrfs_root *root);
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-struct btrfs_root *btrfs_alloc_dummy_root(void);
+struct btrfs_root *btrfs_alloc_dummy_root(u32 sectorsize, u32 nodesize);
 #endif
 
 /*
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index a400951e8678..82b912a293ab 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2042,6 +2042,11 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 	struct btrfs_bio *bbio = NULL;
 
 
+	/*
+	 * Avoid races with device replace and make sure our bbio has devices
+	 * associated to its stripes that don't go away while we are discarding.
+	 */
+	btrfs_bio_counter_inc_blocked(root->fs_info);
 	/* Tell the block device(s) that the sectors can be discarded */
 	ret = btrfs_map_block(root->fs_info, REQ_DISCARD,
 			      bytenr, &num_bytes, &bbio, 0);
@@ -2074,6 +2079,7 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 		}
 		btrfs_put_bbio(bbio);
 	}
+	btrfs_bio_counter_dec(root->fs_info);
 
 	if (actual_bytes)
 		*actual_bytes = discarded_bytes;
@@ -2829,6 +2835,7 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
 
 struct async_delayed_refs {
 	struct btrfs_root *root;
+	u64 transid;
 	int count;
 	int error;
 	int sync;
@@ -2844,6 +2851,10 @@ static void delayed_ref_async_start(struct btrfs_work *work)
 
 	async = container_of(work, struct async_delayed_refs, work);
 
+	/* if the commit is already started, we don't need to wait here */
+	if (btrfs_transaction_blocked(async->root->fs_info))
+		goto done;
+
 	trans = btrfs_join_transaction(async->root);
 	if (IS_ERR(trans)) {
 		async->error = PTR_ERR(trans);
@@ -2855,10 +2866,15 @@ static void delayed_ref_async_start(struct btrfs_work *work)
 	 * wait on delayed refs
 	 */
 	trans->sync = true;
+
+	/* Don't bother flushing if we got into a different transaction */
+	if (trans->transid > async->transid)
+		goto end;
+
 	ret = btrfs_run_delayed_refs(trans, async->root, async->count);
 	if (ret)
 		async->error = ret;
-
+end:
 	ret = btrfs_end_transaction(trans, async->root);
 	if (ret && !async->error)
 		async->error = ret;
@@ -2870,7 +2886,7 @@ done:
 }
 
 int btrfs_async_run_delayed_refs(struct btrfs_root *root,
-				 unsigned long count, int wait)
+				 unsigned long count, u64 transid, int wait)
 {
 	struct async_delayed_refs *async;
 	int ret;
@@ -2882,6 +2898,7 @@ int btrfs_async_run_delayed_refs(struct btrfs_root *root,
 	async->root = root->fs_info->tree_root;
 	async->count = count;
 	async->error = 0;
+	async->transid = transid;
 	if (wait)
 		async->sync = 1;
 	else
@@ -8010,8 +8027,9 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	struct extent_buffer *buf;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(buf))
+		return buf;
+
 	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
@@ -8038,7 +8056,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		set_extent_dirty(&trans->transaction->dirty_pages, buf->start,
 			 buf->start + buf->len - 1, GFP_NOFS);
 	}
-	trans->blocks_used++;
+	trans->dirty = true;
 	/* this returns a buffer locked for blocking */
 	return buf;
 }
@@ -8653,8 +8671,9 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	next = btrfs_find_tree_block(root->fs_info, bytenr);
 	if (!next) {
 		next = btrfs_find_create_tree_block(root, bytenr);
-		if (!next)
-			return -ENOMEM;
+		if (IS_ERR(next))
+			return PTR_ERR(next);
+
 		btrfs_set_buffer_lockdep_class(root->root_key.objectid, next,
 					       level - 1);
 		reada = 1;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3cd57825c75f..75533adef998 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2025,9 +2025,16 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 	bio->bi_iter.bi_size = 0;
 	map_length = length;
 
+	/*
+	 * Avoid races with device replace and make sure our bbio has devices
+	 * associated to its stripes that don't go away while we are doing the
+	 * read repair operation.
+	 */
+	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = btrfs_map_block(fs_info, WRITE, logical,
 			      &map_length, &bbio, mirror_num);
 	if (ret) {
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		return -EIO;
 	}
@@ -2037,6 +2044,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 	dev = bbio->stripes[mirror_num-1].dev;
 	btrfs_put_bbio(bbio);
 	if (!dev || !dev->bdev || !dev->writeable) {
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		return -EIO;
 	}
@@ -2045,6 +2053,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 
 	if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) {
 		/* try to remap that extent elsewhere? */
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
 		return -EIO;
@@ -2054,6 +2063,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 		"read error corrected: ino %llu off %llu (dev %s sector %llu)",
 				  btrfs_ino(inode), start,
 				  rcu_str_deref(dev->name), sector);
+	btrfs_bio_counter_dec(fs_info);
 	bio_put(bio);
 	return 0;
 }
@@ -4718,16 +4728,16 @@ err:
 }
 
 struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
-						u64 start)
+						u64 start, u32 nodesize)
 {
 	unsigned long len;
 
 	if (!fs_info) {
 		/*
 		 * Called only from tests that don't always have a fs_info
-		 * available, but we know that nodesize is 4096
+		 * available
 		 */
-		len = 4096;
+		len = nodesize;
 	} else {
 		len = fs_info->tree_root->nodesize;
 	}
@@ -4823,7 +4833,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
-					       u64 start)
+					u64 start, u32 nodesize)
 {
 	struct extent_buffer *eb, *exists = NULL;
 	int ret;
@@ -4831,7 +4841,7 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
 	eb = find_extent_buffer(fs_info, start);
 	if (eb)
 		return eb;
-	eb = alloc_dummy_extent_buffer(fs_info, start);
+	eb = alloc_dummy_extent_buffer(fs_info, start, nodesize);
 	if (!eb)
 		return NULL;
 	eb->fs_info = fs_info;
@@ -4882,18 +4892,25 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	int uptodate = 1;
 	int ret;
 
+	if (!IS_ALIGNED(start, fs_info->tree_root->sectorsize)) {
+		btrfs_err(fs_info, "bad tree block start %llu", start);
+		return ERR_PTR(-EINVAL);
+	}
+
 	eb = find_extent_buffer(fs_info, start);
 	if (eb)
 		return eb;
 
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	for (i = 0; i < num_pages; i++, index++) {
 		p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
-		if (!p)
+		if (!p) {
+			exists = ERR_PTR(-ENOMEM);
 			goto free_eb;
+		}
 
 		spin_lock(&mapping->private_lock);
 		if (PagePrivate(p)) {
@@ -4938,8 +4955,10 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 		set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 again:
 	ret = radix_tree_preload(GFP_NOFS);
-	if (ret)
+	if (ret) {
+		exists = ERR_PTR(ret);
 		goto free_eb;
+	}
 
 	spin_lock(&fs_info->buffer_lock);
 	ret = radix_tree_insert(&fs_info->buffer_radix,
@@ -5323,6 +5342,11 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
 	return ret;
 }
 
+/*
+ * return 0 if the item is found within a page.
+ * return 1 if the item spans two pages.
+ * return -EINVAL otherwise.
+ */
 int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 			       unsigned long min_len, char **map,
 			       unsigned long *map_start,
@@ -5337,7 +5361,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 		PAGE_SHIFT;
 
 	if (i != end_i)
-		return -EINVAL;
+		return 1;
 
 	if (i == 0) {
 		offset = start_offset;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 1baf19c9b79d..c0c1c4fef6ce 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -348,7 +348,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 						  u64 start, unsigned long len);
 struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
-						u64 start);
+						u64 start, u32 nodesize);
 struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src);
 struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 					 u64 start);
@@ -468,5 +468,5 @@ noinline u64 find_lock_delalloc_range(struct inode *inode,
 				      u64 *end, u64 max_bytes);
 #endif
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
-					       u64 start);
+					       u64 start, u32 nodesize);
 #endif
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e0c9bd3fb02d..2234e88cf674 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1534,30 +1534,30 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		reserve_bytes = round_up(write_bytes + sector_offset,
 				root->sectorsize);
 
-		if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
-					      BTRFS_INODE_PREALLOC)) &&
-		    check_can_nocow(inode, pos, &write_bytes) > 0) {
-			/*
-			 * For nodata cow case, no need to reserve
-			 * data space.
-			 */
-			only_release_metadata = true;
-			/*
-			 * our prealloc extent may be smaller than
-			 * write_bytes, so scale down.
-			 */
-			num_pages = DIV_ROUND_UP(write_bytes + offset,
-						 PAGE_SIZE);
-			reserve_bytes = round_up(write_bytes + sector_offset,
-					root->sectorsize);
-			goto reserve_metadata;
-		}
-
 		ret = btrfs_check_data_free_space(inode, pos, write_bytes);
-		if (ret < 0)
-			break;
+		if (ret < 0) {
+			if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+						      BTRFS_INODE_PREALLOC)) &&
+			    check_can_nocow(inode, pos, &write_bytes) > 0) {
+				/*
+				 * For nodata cow case, no need to reserve
+				 * data space.
+				 */
+				only_release_metadata = true;
+				/*
+				 * our prealloc extent may be smaller than
+				 * write_bytes, so scale down.
+				 */
+				num_pages = DIV_ROUND_UP(write_bytes + offset,
+							 PAGE_SIZE);
+				reserve_bytes = round_up(write_bytes +
+							 sector_offset,
+							 root->sectorsize);
+			} else {
+				break;
+			}
+		}
 
-reserve_metadata:
 		ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes);
 		if (ret) {
 			if (!only_release_metadata)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index c6dc1183f542..69d270f6602c 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -29,7 +29,7 @@
 #include "inode-map.h"
 #include "volumes.h"
 
-#define BITS_PER_BITMAP		(PAGE_SIZE * 8)
+#define BITS_PER_BITMAP		(PAGE_SIZE * 8UL)
 #define MAX_CACHE_BYTES_PER_GIG	SZ_32K
 
 struct btrfs_trim_range {
@@ -1415,11 +1415,11 @@ static inline u64 offset_to_bitmap(struct btrfs_free_space_ctl *ctl,
 				   u64 offset)
 {
 	u64 bitmap_start;
-	u32 bytes_per_bitmap;
+	u64 bytes_per_bitmap;
 
 	bytes_per_bitmap = BITS_PER_BITMAP * ctl->unit;
 	bitmap_start = offset - ctl->start;
-	bitmap_start = div_u64(bitmap_start, bytes_per_bitmap);
+	bitmap_start = div64_u64(bitmap_start, bytes_per_bitmap);
 	bitmap_start *= bytes_per_bitmap;
 	bitmap_start += ctl->start;
 
@@ -1638,10 +1638,10 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
 	u64 bitmap_bytes;
 	u64 extent_bytes;
 	u64 size = block_group->key.offset;
-	u32 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
-	u32 max_bitmaps = div_u64(size + bytes_per_bg - 1, bytes_per_bg);
+	u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
+	u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg);
 
-	max_bitmaps = max_t(u32, max_bitmaps, 1);
+	max_bitmaps = max_t(u64, max_bitmaps, 1);
 
 	ASSERT(ctl->total_bitmaps <= max_bitmaps);
 
@@ -1660,7 +1660,7 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
 	 * sure we don't go over our overall goal of MAX_CACHE_BYTES_PER_GIG as
 	 * we add more bitmaps.
 	 */
-	bitmap_bytes = (ctl->total_bitmaps + 1) * PAGE_SIZE;
+	bitmap_bytes = (ctl->total_bitmaps + 1) * ctl->unit;
 
 	if (bitmap_bytes >= max_bytes) {
 		ctl->extents_thresh = 0;
@@ -3662,7 +3662,7 @@ have_info:
 			if (tmp->offset + tmp->bytes < offset)
 				break;
 			if (offset + bytes < tmp->offset) {
-				n = rb_prev(&info->offset_index);
+				n = rb_prev(&tmp->offset_index);
 				continue;
 			}
 			info = tmp;
@@ -3676,7 +3676,7 @@ have_info:
 			if (offset + bytes < tmp->offset)
 				break;
 			if (tmp->offset + tmp->bytes < offset) {
-				n = rb_next(&info->offset_index);
+				n = rb_next(&tmp->offset_index);
 				continue;
 			}
 			info = tmp;
diff --git a/fs/btrfs/hash.c b/fs/btrfs/hash.c
index aae520b2aee5..a97fdc156a03 100644
--- a/fs/btrfs/hash.c
+++ b/fs/btrfs/hash.c
@@ -24,6 +24,11 @@ int __init btrfs_hash_init(void)
 	return PTR_ERR_OR_ZERO(tfm);
 }
 
+const char* btrfs_crc32c_impl(void)
+{
+	return crypto_tfm_alg_driver_name(crypto_shash_tfm(tfm));
+}
+
 void btrfs_hash_exit(void)
 {
 	crypto_free_shash(tfm);
diff --git a/fs/btrfs/hash.h b/fs/btrfs/hash.h
index 118a2316e5d3..c3a2ec554361 100644
--- a/fs/btrfs/hash.h
+++ b/fs/btrfs/hash.h
@@ -22,6 +22,7 @@
 int __init btrfs_hash_init(void);
 
 void btrfs_hash_exit(void);
+const char* btrfs_crc32c_impl(void);
 
 u32 btrfs_crc32c(u32 crc, const void *address, unsigned int length);
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 270499598ed4..4421954720b8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3271,7 +3271,16 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 	/* grab metadata reservation from transaction handle */
 	if (reserve) {
 		ret = btrfs_orphan_reserve_metadata(trans, inode);
-		BUG_ON(ret); /* -ENOSPC in reservation; Logic error? JDM */
+		ASSERT(!ret);
+		if (ret) {
+			atomic_dec(&root->orphan_inodes);
+			clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
+				  &BTRFS_I(inode)->runtime_flags);
+			if (insert)
+				clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
+					  &BTRFS_I(inode)->runtime_flags);
+			return ret;
+		}
 	}
 
 	/* insert an orphan item to track this unlinked/truncated file */
@@ -4549,6 +4558,7 @@ delete:
 			BUG_ON(ret);
 			if (btrfs_should_throttle_delayed_refs(trans, root))
 				btrfs_async_run_delayed_refs(root,
+							     trans->transid,
 					trans->delayed_ref_updates * 2, 0);
 			if (be_nice) {
 				if (truncate_space_check(trans, root,
@@ -5748,6 +5758,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	int name_len;
 	int is_curr = 0;	/* ctx->pos points to the current index? */
 	bool emitted;
+	bool put = false;
 
 	/* FIXME, use a real flag for deciding about the key type */
 	if (root->fs_info->tree_root == root)
@@ -5765,7 +5776,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		INIT_LIST_HEAD(&ins_list);
 		INIT_LIST_HEAD(&del_list);
-		btrfs_get_delayed_items(inode, &ins_list, &del_list);
+		put = btrfs_readdir_get_delayed_items(inode, &ins_list,
+						      &del_list);
 	}
 
 	key.type = key_type;
@@ -5912,8 +5924,8 @@ next:
 nopos:
 	ret = 0;
 err:
-	if (key_type == BTRFS_DIR_INDEX_KEY)
-		btrfs_put_delayed_items(&ins_list, &del_list);
+	if (put)
+		btrfs_readdir_put_delayed_items(inode, &ins_list, &del_list);
 	btrfs_free_path(path);
 	return ret;
 }
@@ -6979,7 +6991,18 @@ insert:
 		 * existing will always be non-NULL, since there must be
 		 * extent causing the -EEXIST.
 		 */
-		if (start >= extent_map_end(existing) ||
+		if (existing->start == em->start &&
+		    extent_map_end(existing) == extent_map_end(em) &&
+		    em->block_start == existing->block_start) {
+			/*
+			 * these two extents are the same, it happens
+			 * with inlines especially
+			 */
+			free_extent_map(em);
+			em = existing;
+			err = 0;
+
+		} else if (start >= extent_map_end(existing) ||
 		    start <= existing->start) {
 			/*
 			 * The existing extent map is the one nearest to
@@ -10514,7 +10537,7 @@ static const struct inode_operations btrfs_dir_ro_inode_operations = {
 static const struct file_operations btrfs_dir_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
-	.iterate	= btrfs_real_readdir,
+	.iterate_shared	= btrfs_real_readdir,
 	.unlocked_ioctl	= btrfs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= btrfs_compat_ioctl,
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 559170464d7c..aca8264f4a49 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -718,12 +718,13 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
 	return count;
 }
 
-void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
+int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
 			      const u64 range_start, const u64 range_len)
 {
 	struct btrfs_root *root;
 	struct list_head splice;
 	int done;
+	int total_done = 0;
 
 	INIT_LIST_HEAD(&splice);
 
@@ -742,6 +743,7 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
 		done = btrfs_wait_ordered_extents(root, nr,
 						  range_start, range_len);
 		btrfs_put_fs_root(root);
+		total_done += done;
 
 		spin_lock(&fs_info->ordered_root_lock);
 		if (nr != -1) {
@@ -752,6 +754,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
 	list_splice_tail(&splice, &fs_info->ordered_roots);
 	spin_unlock(&fs_info->ordered_root_lock);
 	mutex_unlock(&fs_info->ordered_operations_mutex);
+
+	return total_done;
 }
 
 /*
@@ -964,6 +968,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 	struct rb_node *prev = NULL;
 	struct btrfs_ordered_extent *test;
 	int ret = 1;
+	u64 orig_offset = offset;
 
 	spin_lock_irq(&tree->lock);
 	if (ordered) {
@@ -979,7 +984,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 
 	/* truncate file */
 	if (disk_i_size > i_size) {
-		BTRFS_I(inode)->disk_i_size = i_size;
+		BTRFS_I(inode)->disk_i_size = orig_offset;
 		ret = 0;
 		goto out;
 	}
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 2049c9be85ee..451507776ff5 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -199,7 +199,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
 			   u32 *sum, int len);
 int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
 			       const u64 range_start, const u64 range_len);
-void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
+int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
 			      const u64 range_start, const u64 range_len);
 void btrfs_get_logged_extents(struct inode *inode,
 			      struct list_head *logged_list,
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 298631eaee78..8428db7cd88f 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -761,12 +761,14 @@ static void __reada_start_machine(struct btrfs_fs_info *fs_info)
 
 	do {
 		enqueued = 0;
+		mutex_lock(&fs_devices->device_list_mutex);
 		list_for_each_entry(device, &fs_devices->devices, dev_list) {
 			if (atomic_read(&device->reada_in_flight) <
 			    MAX_IN_FLIGHT)
 				enqueued += reada_start_machine_dev(fs_info,
 								    device);
 		}
+		mutex_unlock(&fs_devices->device_list_mutex);
 		total += enqueued;
 	} while (enqueued && total < 10000);
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 46d847f66e4b..70427ef66b04 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3582,6 +3582,46 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 */
 		scrub_pause_on(fs_info);
 		ret = btrfs_inc_block_group_ro(root, cache);
+		if (!ret && is_dev_replace) {
+			/*
+			 * If we are doing a device replace wait for any tasks
+			 * that started dellaloc right before we set the block
+			 * group to RO mode, as they might have just allocated
+			 * an extent from it or decided they could do a nocow
+			 * write. And if any such tasks did that, wait for their
+			 * ordered extents to complete and then commit the
+			 * current transaction, so that we can later see the new
+			 * extent items in the extent tree - the ordered extents
+			 * create delayed data references (for cow writes) when
+			 * they complete, which will be run and insert the
+			 * corresponding extent items into the extent tree when
+			 * we commit the transaction they used when running
+			 * inode.c:btrfs_finish_ordered_io(). We later use
+			 * the commit root of the extent tree to find extents
+			 * to copy from the srcdev into the tgtdev, and we don't
+			 * want to miss any new extents.
+			 */
+			btrfs_wait_block_group_reservations(cache);
+			btrfs_wait_nocow_writers(cache);
+			ret = btrfs_wait_ordered_roots(fs_info, -1,
+						       cache->key.objectid,
+						       cache->key.offset);
+			if (ret > 0) {
+				struct btrfs_trans_handle *trans;
+
+				trans = btrfs_join_transaction(root);
+				if (IS_ERR(trans))
+					ret = PTR_ERR(trans);
+				else
+					ret = btrfs_commit_transaction(trans,
+								       root);
+				if (ret) {
+					scrub_pause_off(fs_info);
+					btrfs_put_block_group(cache);
+					break;
+				}
+			}
+		}
 		scrub_pause_off(fs_info);
 
 		if (ret == 0) {
@@ -3602,9 +3642,11 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			break;
 		}
 
+		btrfs_dev_replace_lock(&fs_info->dev_replace, 1);
 		dev_replace->cursor_right = found_key.offset + length;
 		dev_replace->cursor_left = found_key.offset;
 		dev_replace->item_needs_writeback = 1;
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 1);
 		ret = scrub_chunk(sctx, scrub_dev, chunk_offset, length,
 				  found_key.offset, cache, is_dev_replace);
 
@@ -3640,6 +3682,11 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 
 		scrub_pause_off(fs_info);
 
+		btrfs_dev_replace_lock(&fs_info->dev_replace, 1);
+		dev_replace->cursor_left = dev_replace->cursor_right;
+		dev_replace->item_needs_writeback = 1;
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 1);
+
 		if (ro_set)
 			btrfs_dec_block_group_ro(root, cache);
 
@@ -3677,9 +3724,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			ret = -ENOMEM;
 			break;
 		}
-
-		dev_replace->cursor_left = dev_replace->cursor_right;
-		dev_replace->item_needs_writeback = 1;
 skip:
 		key.offset = found_key.offset + length;
 		btrfs_release_path(path);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 4e59a91a11e0..60e7179ed4b7 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -235,7 +235,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 	trans->aborted = errno;
 	/* Nothing used. The other threads that have joined this
 	 * transaction may be able to continue. */
-	if (!trans->blocks_used && list_empty(&trans->new_bgs)) {
+	if (!trans->dirty && list_empty(&trans->new_bgs)) {
 		const char *errstr;
 
 		errstr = btrfs_decode_error(errno);
@@ -1807,6 +1807,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 			}
 		}
 		sb->s_flags &= ~MS_RDONLY;
+
+		fs_info->open = 1;
 	}
 out:
 	wake_up_process(fs_info->transaction_kthread);
@@ -2303,7 +2305,7 @@ static void btrfs_interface_exit(void)
 
 static void btrfs_print_mod_info(void)
 {
-	printk(KERN_INFO "Btrfs loaded"
+	printk(KERN_INFO "Btrfs loaded, crc32c=%s"
 #ifdef CONFIG_BTRFS_DEBUG
 			", debug=on"
 #endif
@@ -2313,33 +2315,48 @@ static void btrfs_print_mod_info(void)
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
 			", integrity-checker=on"
 #endif
-			"\n");
+			"\n",
+			btrfs_crc32c_impl());
 }
 
 static int btrfs_run_sanity_tests(void)
 {
-	int ret;
-
+	int ret, i;
+	u32 sectorsize, nodesize;
+	u32 test_sectorsize[] = {
+		PAGE_SIZE,
+	};
 	ret = btrfs_init_test_fs();
 	if (ret)
 		return ret;
-
-	ret = btrfs_test_free_space_cache();
-	if (ret)
-		goto out;
-	ret = btrfs_test_extent_buffer_operations();
-	if (ret)
-		goto out;
-	ret = btrfs_test_extent_io();
-	if (ret)
-		goto out;
-	ret = btrfs_test_inodes();
-	if (ret)
-		goto out;
-	ret = btrfs_test_qgroups();
-	if (ret)
-		goto out;
-	ret = btrfs_test_free_space_tree();
+	for (i = 0; i < ARRAY_SIZE(test_sectorsize); i++) {
+		sectorsize = test_sectorsize[i];
+		for (nodesize = sectorsize;
+		     nodesize <= BTRFS_MAX_METADATA_BLOCKSIZE;
+		     nodesize <<= 1) {
+			pr_info("BTRFS: selftest: sectorsize: %u  nodesize: %u\n",
+				sectorsize, nodesize);
+			ret = btrfs_test_free_space_cache(sectorsize, nodesize);
+			if (ret)
+				goto out;
+			ret = btrfs_test_extent_buffer_operations(sectorsize,
+				nodesize);
+			if (ret)
+				goto out;
+			ret = btrfs_test_extent_io(sectorsize, nodesize);
+			if (ret)
+				goto out;
+			ret = btrfs_test_inodes(sectorsize, nodesize);
+			if (ret)
+				goto out;
+			ret = btrfs_test_qgroups(sectorsize, nodesize);
+			if (ret)
+				goto out;
+			ret = btrfs_test_free_space_tree(sectorsize, nodesize);
+			if (ret)
+				goto out;
+		}
+	}
 out:
 	btrfs_destroy_test_fs();
 	return ret;
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index f54bf450bad3..02223f3f78f4 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -68,7 +68,7 @@ int btrfs_init_test_fs(void)
 	if (IS_ERR(test_mnt)) {
 		printk(KERN_ERR "btrfs: cannot mount test file system\n");
 		unregister_filesystem(&test_type);
-		return ret;
+		return PTR_ERR(test_mnt);
 	}
 	return 0;
 }
@@ -175,7 +175,7 @@ void btrfs_free_dummy_root(struct btrfs_root *root)
 }
 
 struct btrfs_block_group_cache *
-btrfs_alloc_dummy_block_group(unsigned long length)
+btrfs_alloc_dummy_block_group(unsigned long length, u32 sectorsize)
 {
 	struct btrfs_block_group_cache *cache;
 
@@ -192,8 +192,8 @@ btrfs_alloc_dummy_block_group(unsigned long length)
 	cache->key.objectid = 0;
 	cache->key.offset = length;
 	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
-	cache->sectorsize = 4096;
-	cache->full_stripe_len = 4096;
+	cache->sectorsize = sectorsize;
+	cache->full_stripe_len = sectorsize;
 
 	INIT_LIST_HEAD(&cache->list);
 	INIT_LIST_HEAD(&cache->cluster_list);
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index 054b8c73c951..66fb6b701eb7 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -26,27 +26,28 @@
 struct btrfs_root;
 struct btrfs_trans_handle;
 
-int btrfs_test_free_space_cache(void);
-int btrfs_test_extent_buffer_operations(void);
-int btrfs_test_extent_io(void);
-int btrfs_test_inodes(void);
-int btrfs_test_qgroups(void);
-int btrfs_test_free_space_tree(void);
+int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize);
+int btrfs_test_extent_buffer_operations(u32 sectorsize, u32 nodesize);
+int btrfs_test_extent_io(u32 sectorsize, u32 nodesize);
+int btrfs_test_inodes(u32 sectorsize, u32 nodesize);
+int btrfs_test_qgroups(u32 sectorsize, u32 nodesize);
+int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize);
 int btrfs_init_test_fs(void);
 void btrfs_destroy_test_fs(void);
 struct inode *btrfs_new_test_inode(void);
 struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void);
 void btrfs_free_dummy_root(struct btrfs_root *root);
 struct btrfs_block_group_cache *
-btrfs_alloc_dummy_block_group(unsigned long length);
+btrfs_alloc_dummy_block_group(unsigned long length, u32 sectorsize);
 void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache);
 void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans);
 #else
-static inline int btrfs_test_free_space_cache(void)
+static inline int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
 {
 	return 0;
 }
-static inline int btrfs_test_extent_buffer_operations(void)
+static inline int btrfs_test_extent_buffer_operations(u32 sectorsize,
+	u32 nodesize)
 {
 	return 0;
 }
@@ -57,19 +58,19 @@ static inline int btrfs_init_test_fs(void)
 static inline void btrfs_destroy_test_fs(void)
 {
 }
-static inline int btrfs_test_extent_io(void)
+static inline int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
 {
 	return 0;
 }
-static inline int btrfs_test_inodes(void)
+static inline int btrfs_test_inodes(u32 sectorsize, u32 nodesize)
 {
 	return 0;
 }
-static inline int btrfs_test_qgroups(void)
+static inline int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
 {
 	return 0;
 }
-static inline int btrfs_test_free_space_tree(void)
+static inline int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize)
 {
 	return 0;
 }
diff --git a/fs/btrfs/tests/extent-buffer-tests.c b/fs/btrfs/tests/extent-buffer-tests.c
index f51963a8f929..4f8cbd1ec5ee 100644
--- a/fs/btrfs/tests/extent-buffer-tests.c
+++ b/fs/btrfs/tests/extent-buffer-tests.c
@@ -22,7 +22,7 @@
 #include "../extent_io.h"
 #include "../disk-io.h"
 
-static int test_btrfs_split_item(void)
+static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_path *path;
 	struct btrfs_root *root;
@@ -40,7 +40,7 @@ static int test_btrfs_split_item(void)
 
 	test_msg("Running btrfs_split_item tests\n");
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Could not allocate root\n");
 		return PTR_ERR(root);
@@ -53,7 +53,8 @@ static int test_btrfs_split_item(void)
 		return -ENOMEM;
 	}
 
-	path->nodes[0] = eb = alloc_dummy_extent_buffer(NULL, 4096);
+	path->nodes[0] = eb = alloc_dummy_extent_buffer(NULL, nodesize,
+							nodesize);
 	if (!eb) {
 		test_msg("Could not allocate dummy buffer\n");
 		ret = -ENOMEM;
@@ -222,8 +223,8 @@ out:
 	return ret;
 }
 
-int btrfs_test_extent_buffer_operations(void)
+int btrfs_test_extent_buffer_operations(u32 sectorsize, u32 nodesize)
 {
-	test_msg("Running extent buffer operation tests");
-	return test_btrfs_split_item();
+	test_msg("Running extent buffer operation tests\n");
+	return test_btrfs_split_item(sectorsize, nodesize);
 }
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 55724607f79b..d19ab0317283 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <linux/sizes.h>
 #include "btrfs-tests.h"
+#include "../ctree.h"
 #include "../extent_io.h"
 
 #define PROCESS_UNLOCK		(1 << 0)
@@ -65,7 +66,7 @@ static noinline int process_page_range(struct inode *inode, u64 start, u64 end,
 	return count;
 }
 
-static int test_find_delalloc(void)
+static int test_find_delalloc(u32 sectorsize)
 {
 	struct inode *inode;
 	struct extent_io_tree tmp;
@@ -113,7 +114,7 @@ static int test_find_delalloc(void)
 	 * |--- delalloc ---|
 	 * |---  search  ---|
 	 */
-	set_extent_delalloc(&tmp, 0, 4095, NULL);
+	set_extent_delalloc(&tmp, 0, sectorsize - 1, NULL);
 	start = 0;
 	end = 0;
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -122,9 +123,9 @@ static int test_find_delalloc(void)
 		test_msg("Should have found at least one delalloc\n");
 		goto out_bits;
 	}
-	if (start != 0 || end != 4095) {
-		test_msg("Expected start 0 end 4095, got start %Lu end %Lu\n",
-			 start, end);
+	if (start != 0 || end != (sectorsize - 1)) {
+		test_msg("Expected start 0 end %u, got start %llu end %llu\n",
+			sectorsize - 1, start, end);
 		goto out_bits;
 	}
 	unlock_extent(&tmp, start, end);
@@ -144,7 +145,7 @@ static int test_find_delalloc(void)
 		test_msg("Couldn't find the locked page\n");
 		goto out_bits;
 	}
-	set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL);
+	set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, NULL);
 	start = test_start;
 	end = 0;
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -172,7 +173,7 @@ static int test_find_delalloc(void)
 	 * |--- delalloc ---|
 	 *                    |--- search ---|
 	 */
-	test_start = max_bytes + 4096;
+	test_start = max_bytes + sectorsize;
 	locked_page = find_lock_page(inode->i_mapping, test_start >>
 				     PAGE_SHIFT);
 	if (!locked_page) {
@@ -272,6 +273,16 @@ out:
 	return ret;
 }
 
+/**
+ * test_bit_in_byte - Determine whether a bit is set in a byte
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit_in_byte(int nr, const u8 *addr)
+{
+	return 1UL & (addr[nr / BITS_PER_BYTE] >> (nr & (BITS_PER_BYTE - 1)));
+}
+
 static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 			     unsigned long len)
 {
@@ -298,25 +309,29 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 		return -EINVAL;
 	}
 
-	bitmap_set(bitmap, (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
-		   sizeof(long) * BITS_PER_BYTE);
-	extent_buffer_bitmap_set(eb, PAGE_SIZE - sizeof(long) / 2, 0,
-				 sizeof(long) * BITS_PER_BYTE);
-	if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
-		test_msg("Setting straddling pages failed\n");
-		return -EINVAL;
-	}
+	/* Straddling pages test */
+	if (len > PAGE_SIZE) {
+		bitmap_set(bitmap,
+			(PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
+			sizeof(long) * BITS_PER_BYTE);
+		extent_buffer_bitmap_set(eb, PAGE_SIZE - sizeof(long) / 2, 0,
+					sizeof(long) * BITS_PER_BYTE);
+		if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+			test_msg("Setting straddling pages failed\n");
+			return -EINVAL;
+		}
 
-	bitmap_set(bitmap, 0, len * BITS_PER_BYTE);
-	bitmap_clear(bitmap,
-		     (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
-		     sizeof(long) * BITS_PER_BYTE);
-	extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
-	extent_buffer_bitmap_clear(eb, PAGE_SIZE - sizeof(long) / 2, 0,
-				   sizeof(long) * BITS_PER_BYTE);
-	if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
-		test_msg("Clearing straddling pages failed\n");
-		return -EINVAL;
+		bitmap_set(bitmap, 0, len * BITS_PER_BYTE);
+		bitmap_clear(bitmap,
+			(PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
+			sizeof(long) * BITS_PER_BYTE);
+		extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
+		extent_buffer_bitmap_clear(eb, PAGE_SIZE - sizeof(long) / 2, 0,
+					sizeof(long) * BITS_PER_BYTE);
+		if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+			test_msg("Clearing straddling pages failed\n");
+			return -EINVAL;
+		}
 	}
 
 	/*
@@ -333,7 +348,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 	for (i = 0; i < len * BITS_PER_BYTE; i++) {
 		int bit, bit1;
 
-		bit = !!test_bit(i, bitmap);
+		bit = !!test_bit_in_byte(i, (u8 *)bitmap);
 		bit1 = !!extent_buffer_test_bit(eb, 0, i);
 		if (bit1 != bit) {
 			test_msg("Testing bit pattern failed\n");
@@ -351,15 +366,22 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 	return 0;
 }
 
-static int test_eb_bitmaps(void)
+static int test_eb_bitmaps(u32 sectorsize, u32 nodesize)
 {
-	unsigned long len = PAGE_SIZE * 4;
+	unsigned long len;
 	unsigned long *bitmap;
 	struct extent_buffer *eb;
 	int ret;
 
 	test_msg("Running extent buffer bitmap tests\n");
 
+	/*
+	 * In ppc64, sectorsize can be 64K, thus 4 * 64K will be larger than
+	 * BTRFS_MAX_METADATA_BLOCKSIZE.
+	 */
+	len = (sectorsize < BTRFS_MAX_METADATA_BLOCKSIZE)
+		? sectorsize * 4 : sectorsize;
+
 	bitmap = kmalloc(len, GFP_KERNEL);
 	if (!bitmap) {
 		test_msg("Couldn't allocate test bitmap\n");
@@ -379,7 +401,7 @@ static int test_eb_bitmaps(void)
 
 	/* Do it over again with an extent buffer which isn't page-aligned. */
 	free_extent_buffer(eb);
-	eb = __alloc_dummy_extent_buffer(NULL, PAGE_SIZE / 2, len);
+	eb = __alloc_dummy_extent_buffer(NULL, nodesize / 2, len);
 	if (!eb) {
 		test_msg("Couldn't allocate test extent buffer\n");
 		kfree(bitmap);
@@ -393,17 +415,17 @@ out:
 	return ret;
 }
 
-int btrfs_test_extent_io(void)
+int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
 {
 	int ret;
 
 	test_msg("Running extent I/O tests\n");
 
-	ret = test_find_delalloc();
+	ret = test_find_delalloc(sectorsize);
 	if (ret)
 		goto out;
 
-	ret = test_eb_bitmaps();
+	ret = test_eb_bitmaps(sectorsize, nodesize);
 out:
 	test_msg("Extent I/O tests finished\n");
 	return ret;
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index 0eeb8f3d6b67..3956bb2ff84c 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -22,7 +22,7 @@
 #include "../disk-io.h"
 #include "../free-space-cache.h"
 
-#define BITS_PER_BITMAP		(PAGE_SIZE * 8)
+#define BITS_PER_BITMAP		(PAGE_SIZE * 8UL)
 
 /*
  * This test just does basic sanity checking, making sure we can add an extent
@@ -99,7 +99,8 @@ static int test_extents(struct btrfs_block_group_cache *cache)
 	return 0;
 }
 
-static int test_bitmaps(struct btrfs_block_group_cache *cache)
+static int test_bitmaps(struct btrfs_block_group_cache *cache,
+			u32 sectorsize)
 {
 	u64 next_bitmap_offset;
 	int ret;
@@ -139,7 +140,7 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache)
 	 * The first bitmap we have starts at offset 0 so the next one is just
 	 * at the end of the first bitmap.
 	 */
-	next_bitmap_offset = (u64)(BITS_PER_BITMAP * 4096);
+	next_bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize);
 
 	/* Test a bit straddling two bitmaps */
 	ret = test_add_free_space_entry(cache, next_bitmap_offset - SZ_2M,
@@ -167,9 +168,10 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache)
 }
 
 /* This is the high grade jackassery */
-static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache)
+static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
+				    u32 sectorsize)
 {
-	u64 bitmap_offset = (u64)(BITS_PER_BITMAP * 4096);
+	u64 bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize);
 	int ret;
 
 	test_msg("Running bitmap and extent tests\n");
@@ -401,7 +403,8 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache)
  * requests.
  */
 static int
-test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
+test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
+				       u32 sectorsize)
 {
 	int ret;
 	u64 offset;
@@ -539,7 +542,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * The goal is to test that the bitmap entry space stealing doesn't
 	 * steal this space region.
 	 */
-	ret = btrfs_add_free_space(cache, SZ_128M + SZ_16M, 4096);
+	ret = btrfs_add_free_space(cache, SZ_128M + SZ_16M, sectorsize);
 	if (ret) {
 		test_msg("Error adding free space: %d\n", ret);
 		return ret;
@@ -597,8 +600,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 		return -ENOENT;
 	}
 
-	if (cache->free_space_ctl->free_space != (SZ_1M + 4096)) {
-		test_msg("Cache free space is not 1Mb + 4Kb\n");
+	if (cache->free_space_ctl->free_space != (SZ_1M + sectorsize)) {
+		test_msg("Cache free space is not 1Mb + %u\n", sectorsize);
 		return -EINVAL;
 	}
 
@@ -611,22 +614,25 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 		return -EINVAL;
 	}
 
-	/* All that remains is a 4Kb free space region in a bitmap. Confirm. */
+	/*
+	 * All that remains is a sectorsize free space region in a bitmap.
+	 * Confirm.
+	 */
 	ret = check_num_extents_and_bitmaps(cache, 1, 1);
 	if (ret)
 		return ret;
 
-	if (cache->free_space_ctl->free_space != 4096) {
-		test_msg("Cache free space is not 4Kb\n");
+	if (cache->free_space_ctl->free_space != sectorsize) {
+		test_msg("Cache free space is not %u\n", sectorsize);
 		return -EINVAL;
 	}
 
 	offset = btrfs_find_space_for_alloc(cache,
-					    0, 4096, 0,
+					    0, sectorsize, 0,
 					    &max_extent_size);
 	if (offset != (SZ_128M + SZ_16M)) {
-		test_msg("Failed to allocate 4Kb from space cache, returned offset is: %llu\n",
-			 offset);
+		test_msg("Failed to allocate %u, returned offset : %llu\n",
+			 sectorsize, offset);
 		return -EINVAL;
 	}
 
@@ -733,7 +739,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * The goal is to test that the bitmap entry space stealing doesn't
 	 * steal this space region.
 	 */
-	ret = btrfs_add_free_space(cache, SZ_32M, 8192);
+	ret = btrfs_add_free_space(cache, SZ_32M, 2 * sectorsize);
 	if (ret) {
 		test_msg("Error adding free space: %d\n", ret);
 		return ret;
@@ -757,7 +763,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 
 	/*
 	 * Confirm that our extent entry didn't stole all free space from the
-	 * bitmap, because of the small 8Kb free space region.
+	 * bitmap, because of the small 2 * sectorsize free space region.
 	 */
 	ret = check_num_extents_and_bitmaps(cache, 2, 1);
 	if (ret)
@@ -783,8 +789,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 		return -ENOENT;
 	}
 
-	if (cache->free_space_ctl->free_space != (SZ_1M + 8192)) {
-		test_msg("Cache free space is not 1Mb + 8Kb\n");
+	if (cache->free_space_ctl->free_space != (SZ_1M + 2 * sectorsize)) {
+		test_msg("Cache free space is not 1Mb + %u\n", 2 * sectorsize);
 		return -EINVAL;
 	}
 
@@ -796,21 +802,25 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 		return -EINVAL;
 	}
 
-	/* All that remains is a 8Kb free space region in a bitmap. Confirm. */
+	/*
+	 * All that remains is 2 * sectorsize free space region
+	 * in a bitmap. Confirm.
+	 */
 	ret = check_num_extents_and_bitmaps(cache, 1, 1);
 	if (ret)
 		return ret;
 
-	if (cache->free_space_ctl->free_space != 8192) {
-		test_msg("Cache free space is not 8Kb\n");
+	if (cache->free_space_ctl->free_space != 2 * sectorsize) {
+		test_msg("Cache free space is not %u\n", 2 * sectorsize);
 		return -EINVAL;
 	}
 
 	offset = btrfs_find_space_for_alloc(cache,
-					    0, 8192, 0,
+					    0, 2 * sectorsize, 0,
 					    &max_extent_size);
 	if (offset != SZ_32M) {
-		test_msg("Failed to allocate 8Kb from space cache, returned offset is: %llu\n",
+		test_msg("Failed to allocate %u, offset: %llu\n",
+			 2 * sectorsize,
 			 offset);
 		return -EINVAL;
 	}
@@ -825,7 +835,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	return 0;
 }
 
-int btrfs_test_free_space_cache(void)
+int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_block_group_cache *cache;
 	struct btrfs_root *root = NULL;
@@ -833,13 +843,19 @@ int btrfs_test_free_space_cache(void)
 
 	test_msg("Running btrfs free space cache tests\n");
 
-	cache = btrfs_alloc_dummy_block_group(1024 * 1024 * 1024);
+	/*
+	 * For ppc64 (with 64k page size), bytes per bitmap might be
+	 * larger than 1G.  To make bitmap test available in ppc64,
+	 * alloc dummy block group whose size cross bitmaps.
+	 */
+	cache = btrfs_alloc_dummy_block_group(BITS_PER_BITMAP * sectorsize
+					+ PAGE_SIZE, sectorsize);
 	if (!cache) {
 		test_msg("Couldn't run the tests\n");
 		return 0;
 	}
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		ret = PTR_ERR(root);
 		goto out;
@@ -855,14 +871,14 @@ int btrfs_test_free_space_cache(void)
 	ret = test_extents(cache);
 	if (ret)
 		goto out;
-	ret = test_bitmaps(cache);
+	ret = test_bitmaps(cache, sectorsize);
 	if (ret)
 		goto out;
-	ret = test_bitmaps_and_extents(cache);
+	ret = test_bitmaps_and_extents(cache, sectorsize);
 	if (ret)
 		goto out;
 
-	ret = test_steal_space_from_bitmap_to_extent(cache);
+	ret = test_steal_space_from_bitmap_to_extent(cache, sectorsize);
 out:
 	btrfs_free_dummy_block_group(cache);
 	btrfs_free_dummy_root(root);
diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c
index 7cea4462acd5..aac507085ab0 100644
--- a/fs/btrfs/tests/free-space-tree-tests.c
+++ b/fs/btrfs/tests/free-space-tree-tests.c
@@ -16,6 +16,7 @@
  * Boston, MA 021110-1307, USA.
  */
 
+#include <linux/types.h>
 #include "btrfs-tests.h"
 #include "../ctree.h"
 #include "../disk-io.h"
@@ -30,7 +31,7 @@ struct free_space_extent {
  * The test cases align their operations to this in order to hit some of the
  * edge cases in the bitmap code.
  */
-#define BITMAP_RANGE (BTRFS_FREE_SPACE_BITMAP_BITS * 4096)
+#define BITMAP_RANGE (BTRFS_FREE_SPACE_BITMAP_BITS * PAGE_SIZE)
 
 static int __check_free_space_extents(struct btrfs_trans_handle *trans,
 				      struct btrfs_fs_info *fs_info,
@@ -439,7 +440,8 @@ typedef int (*test_func_t)(struct btrfs_trans_handle *,
 			   struct btrfs_block_group_cache *,
 			   struct btrfs_path *);
 
-static int run_test(test_func_t test_func, int bitmaps)
+static int run_test(test_func_t test_func, int bitmaps,
+		u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_root *root = NULL;
 	struct btrfs_block_group_cache *cache = NULL;
@@ -447,7 +449,7 @@ static int run_test(test_func_t test_func, int bitmaps)
 	struct btrfs_path *path = NULL;
 	int ret;
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Couldn't allocate dummy root\n");
 		ret = PTR_ERR(root);
@@ -466,7 +468,8 @@ static int run_test(test_func_t test_func, int bitmaps)
 	root->fs_info->free_space_root = root;
 	root->fs_info->tree_root = root;
 
-	root->node = alloc_test_extent_buffer(root->fs_info, 4096);
+	root->node = alloc_test_extent_buffer(root->fs_info,
+		nodesize, nodesize);
 	if (!root->node) {
 		test_msg("Couldn't allocate dummy buffer\n");
 		ret = -ENOMEM;
@@ -474,9 +477,9 @@ static int run_test(test_func_t test_func, int bitmaps)
 	}
 	btrfs_set_header_level(root->node, 0);
 	btrfs_set_header_nritems(root->node, 0);
-	root->alloc_bytenr += 8192;
+	root->alloc_bytenr += 2 * nodesize;
 
-	cache = btrfs_alloc_dummy_block_group(8 * BITMAP_RANGE);
+	cache = btrfs_alloc_dummy_block_group(8 * BITMAP_RANGE, sectorsize);
 	if (!cache) {
 		test_msg("Couldn't allocate dummy block group cache\n");
 		ret = -ENOMEM;
@@ -534,17 +537,18 @@ out:
 	return ret;
 }
 
-static int run_test_both_formats(test_func_t test_func)
+static int run_test_both_formats(test_func_t test_func,
+	u32 sectorsize, u32 nodesize)
 {
 	int ret;
 
-	ret = run_test(test_func, 0);
+	ret = run_test(test_func, 0, sectorsize, nodesize);
 	if (ret)
 		return ret;
-	return run_test(test_func, 1);
+	return run_test(test_func, 1, sectorsize, nodesize);
 }
 
-int btrfs_test_free_space_tree(void)
+int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize)
 {
 	test_func_t tests[] = {
 		test_empty_block_group,
@@ -561,9 +565,11 @@ int btrfs_test_free_space_tree(void)
 
 	test_msg("Running free space tree tests\n");
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		int ret = run_test_both_formats(tests[i]);
+		int ret = run_test_both_formats(tests[i], sectorsize,
+			nodesize);
 		if (ret) {
-			test_msg("%pf failed\n", tests[i]);
+			test_msg("%pf : sectorsize %u failed\n",
+				tests[i], sectorsize);
 			return ret;
 		}
 	}
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 8a25fe8b7c45..29648c0a39f1 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -16,6 +16,7 @@
  * Boston, MA 021110-1307, USA.
  */
 
+#include <linux/types.h>
 #include "btrfs-tests.h"
 #include "../ctree.h"
 #include "../btrfs_inode.h"
@@ -86,19 +87,19 @@ static void insert_inode_item_key(struct btrfs_root *root)
  * diagram of how the extents will look though this may not be possible we still
  * want to make sure everything acts normally (the last number is not inclusive)
  *
- * [0 - 5][5 -  6][6 - 10][10 - 4096][  4096 - 8192 ][8192 - 12288]
- * [hole ][inline][ hole ][ regular ][regular1 split][    hole    ]
+ * [0 - 5][5 -  6][     6 - 4096     ][ 4096 - 4100][4100 - 8195][8195 - 12291]
+ * [hole ][inline][hole but no extent][  hole   ][   regular ][regular1 split]
  *
- * [ 12288 - 20480][20480 - 24576][  24576 - 28672  ][28672 - 36864][36864 - 45056]
- * [regular1 split][   prealloc1 ][prealloc1 written][   prealloc1 ][ compressed  ]
+ * [12291 - 16387][16387 - 24579][24579 - 28675][ 28675 - 32771][32771 - 36867 ]
+ * [    hole    ][regular1 split][   prealloc ][   prealloc1  ][prealloc1 written]
  *
- * [45056 - 49152][49152-53248][53248-61440][61440-65536][     65536+81920   ]
- * [ compressed1 ][  regular  ][compressed1][  regular  ][ hole but no extent]
+ * [36867 - 45059][45059 - 53251][53251 - 57347][57347 - 61443][61443- 69635]
+ * [  prealloc1  ][ compressed  ][ compressed1 ][    regular  ][ compressed1]
  *
- * [81920-86016]
- * [  regular  ]
+ * [69635-73731][   73731 - 86019   ][86019-90115]
+ * [  regular  ][ hole but no extent][  regular  ]
  */
-static void setup_file_extents(struct btrfs_root *root)
+static void setup_file_extents(struct btrfs_root *root, u32 sectorsize)
 {
 	int slot = 0;
 	u64 disk_bytenr = SZ_1M;
@@ -119,7 +120,7 @@ static void setup_file_extents(struct btrfs_root *root)
 	insert_extent(root, offset, 1, 1, 0, 0, 0, BTRFS_FILE_EXTENT_INLINE, 0,
 		      slot);
 	slot++;
-	offset = 4096;
+	offset = sectorsize;
 
 	/* Now another hole */
 	insert_extent(root, offset, 4, 4, 0, 0, 0, BTRFS_FILE_EXTENT_REG, 0,
@@ -128,99 +129,106 @@ static void setup_file_extents(struct btrfs_root *root)
 	offset += 4;
 
 	/* Now for a regular extent */
-	insert_extent(root, offset, 4095, 4095, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_REG, 0, slot);
+	insert_extent(root, offset, sectorsize - 1, sectorsize - 1, 0,
+		      disk_bytenr, sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	disk_bytenr += 4096;
-	offset += 4095;
+	disk_bytenr += sectorsize;
+	offset += sectorsize - 1;
 
 	/*
 	 * Now for 3 extents that were split from a hole punch so we test
 	 * offsets properly.
 	 */
-	insert_extent(root, offset, 4096, 16384, 0, disk_bytenr, 16384,
-		      BTRFS_FILE_EXTENT_REG, 0, slot);
+	insert_extent(root, offset, sectorsize, 4 * sectorsize, 0, disk_bytenr,
+		      4 * sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 4096, 4096, 0, 0, 0, BTRFS_FILE_EXTENT_REG,
-		      0, slot);
+	offset += sectorsize;
+	insert_extent(root, offset, sectorsize, sectorsize, 0, 0, 0,
+		      BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 8192, 16384, 8192, disk_bytenr, 16384,
+	offset += sectorsize;
+	insert_extent(root, offset, 2 * sectorsize, 4 * sectorsize,
+		      2 * sectorsize, disk_bytenr, 4 * sectorsize,
 		      BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	offset += 8192;
-	disk_bytenr += 16384;
+	offset += 2 * sectorsize;
+	disk_bytenr += 4 * sectorsize;
 
 	/* Now for a unwritten prealloc extent */
-	insert_extent(root, offset, 4096, 4096, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
+	insert_extent(root, offset, sectorsize, sectorsize, 0, disk_bytenr,
+		sectorsize, BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
 	slot++;
-	offset += 4096;
+	offset += sectorsize;
 
 	/*
 	 * We want to jack up disk_bytenr a little more so the em stuff doesn't
 	 * merge our records.
 	 */
-	disk_bytenr += 8192;
+	disk_bytenr += 2 * sectorsize;
 
 	/*
 	 * Now for a partially written prealloc extent, basically the same as
 	 * the hole punch example above.  Ram_bytes never changes when you mark
 	 * extents written btw.
 	 */
-	insert_extent(root, offset, 4096, 16384, 0, disk_bytenr, 16384,
-		      BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
+	insert_extent(root, offset, sectorsize, 4 * sectorsize, 0, disk_bytenr,
+		      4 * sectorsize, BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 4096, 16384, 4096, disk_bytenr, 16384,
-		      BTRFS_FILE_EXTENT_REG, 0, slot);
+	offset += sectorsize;
+	insert_extent(root, offset, sectorsize, 4 * sectorsize, sectorsize,
+		      disk_bytenr, 4 * sectorsize, BTRFS_FILE_EXTENT_REG, 0,
+		      slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 8192, 16384, 8192, disk_bytenr, 16384,
+	offset += sectorsize;
+	insert_extent(root, offset, 2 * sectorsize, 4 * sectorsize,
+		      2 * sectorsize, disk_bytenr, 4 * sectorsize,
 		      BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
 	slot++;
-	offset += 8192;
-	disk_bytenr += 16384;
+	offset += 2 * sectorsize;
+	disk_bytenr += 4 * sectorsize;
 
 	/* Now a normal compressed extent */
-	insert_extent(root, offset, 8192, 8192, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_REG, BTRFS_COMPRESS_ZLIB, slot);
+	insert_extent(root, offset, 2 * sectorsize, 2 * sectorsize, 0,
+		      disk_bytenr, sectorsize, BTRFS_FILE_EXTENT_REG,
+		      BTRFS_COMPRESS_ZLIB, slot);
 	slot++;
-	offset += 8192;
+	offset += 2 * sectorsize;
 	/* No merges */
-	disk_bytenr += 8192;
+	disk_bytenr += 2 * sectorsize;
 
 	/* Now a split compressed extent */
-	insert_extent(root, offset, 4096, 16384, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_REG, BTRFS_COMPRESS_ZLIB, slot);
+	insert_extent(root, offset, sectorsize, 4 * sectorsize, 0, disk_bytenr,
+		      sectorsize, BTRFS_FILE_EXTENT_REG,
+		      BTRFS_COMPRESS_ZLIB, slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 4096, 4096, 0, disk_bytenr + 4096, 4096,
+	offset += sectorsize;
+	insert_extent(root, offset, sectorsize, sectorsize, 0,
+		      disk_bytenr + sectorsize, sectorsize,
 		      BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 8192, 16384, 8192, disk_bytenr, 4096,
+	offset += sectorsize;
+	insert_extent(root, offset, 2 * sectorsize, 4 * sectorsize,
+		      2 * sectorsize, disk_bytenr, sectorsize,
 		      BTRFS_FILE_EXTENT_REG, BTRFS_COMPRESS_ZLIB, slot);
 	slot++;
-	offset += 8192;
-	disk_bytenr += 8192;
+	offset += 2 * sectorsize;
+	disk_bytenr += 2 * sectorsize;
 
 	/* Now extents that have a hole but no hole extent */
-	insert_extent(root, offset, 4096, 4096, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_REG, 0, slot);
+	insert_extent(root, offset, sectorsize, sectorsize, 0, disk_bytenr,
+		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	offset += 16384;
-	disk_bytenr += 4096;
-	insert_extent(root, offset, 4096, 4096, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_REG, 0, slot);
+	offset += 4 * sectorsize;
+	disk_bytenr += sectorsize;
+	insert_extent(root, offset, sectorsize, sectorsize, 0, disk_bytenr,
+		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
 }
 
 static unsigned long prealloc_only = 0;
 static unsigned long compressed_only = 0;
 static unsigned long vacancy_only = 0;
 
-static noinline int test_btrfs_get_extent(void)
+static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 {
 	struct inode *inode = NULL;
 	struct btrfs_root *root = NULL;
@@ -240,7 +248,7 @@ static noinline int test_btrfs_get_extent(void)
 	BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	BTRFS_I(inode)->location.offset = 0;
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Couldn't allocate root\n");
 		goto out;
@@ -256,7 +264,7 @@ static noinline int test_btrfs_get_extent(void)
 		goto out;
 	}
 
-	root->node = alloc_dummy_extent_buffer(NULL, 4096);
+	root->node = alloc_dummy_extent_buffer(NULL, nodesize, nodesize);
 	if (!root->node) {
 		test_msg("Couldn't allocate dummy buffer\n");
 		goto out;
@@ -273,7 +281,7 @@ static noinline int test_btrfs_get_extent(void)
 
 	/* First with no extents */
 	BTRFS_I(inode)->root = root;
-	em = btrfs_get_extent(inode, NULL, 0, 0, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, 0, sectorsize, 0);
 	if (IS_ERR(em)) {
 		em = NULL;
 		test_msg("Got an error when we shouldn't have\n");
@@ -295,7 +303,7 @@ static noinline int test_btrfs_get_extent(void)
 	 * setup_file_extents, so if you change anything there you need to
 	 * update the comment and update the expected values below.
 	 */
-	setup_file_extents(root);
+	setup_file_extents(root, sectorsize);
 
 	em = btrfs_get_extent(inode, NULL, 0, 0, (u64)-1, 0);
 	if (IS_ERR(em)) {
@@ -318,7 +326,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -327,7 +335,8 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected an inline, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4091) {
+
+	if (em->start != offset || em->len != (sectorsize - 5)) {
 		test_msg("Unexpected extent wanted start %llu len 1, got start "
 			 "%llu len %llu\n", offset, em->start, em->len);
 		goto out;
@@ -344,7 +353,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -366,7 +375,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* Regular extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -375,7 +384,7 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4095) {
+	if (em->start != offset || em->len != sectorsize - 1) {
 		test_msg("Unexpected extent wanted start %llu len 4095, got "
 			 "start %llu len %llu\n", offset, em->start, em->len);
 		goto out;
@@ -393,7 +402,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* The next 3 are split extents */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -402,9 +411,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -421,7 +431,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -430,9 +440,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a hole, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -442,7 +453,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -451,9 +462,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 8192) {
-		test_msg("Unexpected extent wanted start %llu len 8192, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != 2 * sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -475,7 +487,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* Prealloc extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -484,9 +496,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
@@ -503,7 +516,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* The next 3 are a half written prealloc extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -512,9 +525,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
@@ -532,7 +546,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -541,9 +555,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -564,7 +579,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -573,9 +588,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 8192) {
-		test_msg("Unexpected extent wanted start %llu len 8192, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != 2 * sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
@@ -598,7 +614,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* Now for the compressed extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -607,9 +623,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 8192) {
-		test_msg("Unexpected extent wanted start %llu len 8192, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != 2 * sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u,"
+			"got start %llu len %llu\n",
+			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != compressed_only) {
@@ -631,7 +648,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* Split compressed extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -640,9 +657,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u,"
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != compressed_only) {
@@ -665,7 +683,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -674,9 +692,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -691,7 +710,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -701,9 +720,10 @@ static noinline int test_btrfs_get_extent(void)
 			 disk_bytenr, em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 8192) {
-		test_msg("Unexpected extent wanted start %llu len 8192, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != 2 * sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != compressed_only) {
@@ -725,7 +745,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* A hole between regular extents but no hole extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset + 6, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset + 6, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -734,9 +754,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -765,9 +786,10 @@ static noinline int test_btrfs_get_extent(void)
 	 * length of the actual hole, if this changes we'll have to change this
 	 * test.
 	 */
-	if (em->start != offset || em->len != 12288) {
-		test_msg("Unexpected extent wanted start %llu len 12288, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != 3 * sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, 3 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != vacancy_only) {
@@ -783,7 +805,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -792,9 +814,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u,"
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -815,7 +838,7 @@ out:
 	return ret;
 }
 
-static int test_hole_first(void)
+static int test_hole_first(u32 sectorsize, u32 nodesize)
 {
 	struct inode *inode = NULL;
 	struct btrfs_root *root = NULL;
@@ -832,7 +855,7 @@ static int test_hole_first(void)
 	BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	BTRFS_I(inode)->location.offset = 0;
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Couldn't allocate root\n");
 		goto out;
@@ -844,7 +867,7 @@ static int test_hole_first(void)
 		goto out;
 	}
 
-	root->node = alloc_dummy_extent_buffer(NULL, 4096);
+	root->node = alloc_dummy_extent_buffer(NULL, nodesize, nodesize);
 	if (!root->node) {
 		test_msg("Couldn't allocate dummy buffer\n");
 		goto out;
@@ -861,9 +884,9 @@ static int test_hole_first(void)
 	 * btrfs_get_extent.
 	 */
 	insert_inode_item_key(root);
-	insert_extent(root, 4096, 4096, 4096, 0, 4096, 4096,
-		      BTRFS_FILE_EXTENT_REG, 0, 1);
-	em = btrfs_get_extent(inode, NULL, 0, 0, 8192, 0);
+	insert_extent(root, sectorsize, sectorsize, sectorsize, 0, sectorsize,
+		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, 1);
+	em = btrfs_get_extent(inode, NULL, 0, 0, 2 * sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -872,9 +895,10 @@ static int test_hole_first(void)
 		test_msg("Expected a hole, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != 0 || em->len != 4096) {
-		test_msg("Unexpected extent wanted start 0 len 4096, got start "
-			 "%llu len %llu\n", em->start, em->len);
+	if (em->start != 0 || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start 0 len %u, "
+			"got start %llu len %llu\n",
+			sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != vacancy_only) {
@@ -884,18 +908,19 @@ static int test_hole_first(void)
 	}
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, 4096, 8192, 0);
+	em = btrfs_get_extent(inode, NULL, 0, sectorsize, 2 * sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
 	}
-	if (em->block_start != 4096) {
+	if (em->block_start != sectorsize) {
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != 4096 || em->len != 4096) {
-		test_msg("Unexpected extent wanted start 4096 len 4096, got "
-			 "start %llu len %llu\n", em->start, em->len);
+	if (em->start != sectorsize || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %u len %u, "
+			"got start %llu len %llu\n",
+			sectorsize, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -912,7 +937,7 @@ out:
 	return ret;
 }
 
-static int test_extent_accounting(void)
+static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 {
 	struct inode *inode = NULL;
 	struct btrfs_root *root = NULL;
@@ -924,7 +949,7 @@ static int test_extent_accounting(void)
 		return ret;
 	}
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Couldn't allocate root\n");
 		goto out;
@@ -954,10 +979,11 @@ static int test_extent_accounting(void)
 		goto out;
 	}
 
-	/* [BTRFS_MAX_EXTENT_SIZE][4k] */
+	/* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */
 	BTRFS_I(inode)->outstanding_extents++;
 	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE,
-					BTRFS_MAX_EXTENT_SIZE + 4095, NULL);
+					BTRFS_MAX_EXTENT_SIZE + sectorsize - 1,
+					NULL);
 	if (ret) {
 		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
 		goto out;
@@ -969,10 +995,10 @@ static int test_extent_accounting(void)
 		goto out;
 	}
 
-	/* [BTRFS_MAX_EXTENT_SIZE/2][4K HOLE][the rest] */
+	/* [BTRFS_MAX_EXTENT_SIZE/2][sectorsize HOLE][the rest] */
 	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
 			       BTRFS_MAX_EXTENT_SIZE >> 1,
-			       (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+			       (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1,
 			       EXTENT_DELALLOC | EXTENT_DIRTY |
 			       EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0,
 			       NULL, GFP_KERNEL);
@@ -987,10 +1013,11 @@ static int test_extent_accounting(void)
 		goto out;
 	}
 
-	/* [BTRFS_MAX_EXTENT_SIZE][4K] */
+	/* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */
 	BTRFS_I(inode)->outstanding_extents++;
 	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1,
-					(BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+					(BTRFS_MAX_EXTENT_SIZE >> 1)
+					+ sectorsize - 1,
 					NULL);
 	if (ret) {
 		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
@@ -1004,16 +1031,17 @@ static int test_extent_accounting(void)
 	}
 
 	/*
-	 * [BTRFS_MAX_EXTENT_SIZE+4K][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4K]
+	 * [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize HOLE][BTRFS_MAX_EXTENT_SIZE+sectorsize]
 	 *
 	 * I'm artificially adding 2 to outstanding_extents because in the
 	 * buffered IO case we'd add things up as we go, but I don't feel like
 	 * doing that here, this isn't the interesting case we want to test.
 	 */
 	BTRFS_I(inode)->outstanding_extents += 2;
-	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + 8192,
-					(BTRFS_MAX_EXTENT_SIZE << 1) + 12287,
-					NULL);
+	ret = btrfs_set_extent_delalloc(inode,
+			BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize,
+			(BTRFS_MAX_EXTENT_SIZE << 1) + 3 * sectorsize - 1,
+			NULL);
 	if (ret) {
 		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
 		goto out;
@@ -1025,10 +1053,13 @@ static int test_extent_accounting(void)
 		goto out;
 	}
 
-	/* [BTRFS_MAX_EXTENT_SIZE+4k][4k][BTRFS_MAX_EXTENT_SIZE+4k] */
+	/*
+	* [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize][BTRFS_MAX_EXTENT_SIZE+sectorsize]
+	*/
 	BTRFS_I(inode)->outstanding_extents++;
-	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
-					BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+	ret = btrfs_set_extent_delalloc(inode,
+			BTRFS_MAX_EXTENT_SIZE + sectorsize,
+			BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL);
 	if (ret) {
 		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
 		goto out;
@@ -1042,8 +1073,8 @@ static int test_extent_accounting(void)
 
 	/* [BTRFS_MAX_EXTENT_SIZE+4k][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4k] */
 	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
-			       BTRFS_MAX_EXTENT_SIZE+4096,
-			       BTRFS_MAX_EXTENT_SIZE+8191,
+			       BTRFS_MAX_EXTENT_SIZE + sectorsize,
+			       BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1,
 			       EXTENT_DIRTY | EXTENT_DELALLOC |
 			       EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
 			       NULL, GFP_KERNEL);
@@ -1063,8 +1094,9 @@ static int test_extent_accounting(void)
 	 * might fail and I'd rather satisfy my paranoia at this point.
 	 */
 	BTRFS_I(inode)->outstanding_extents++;
-	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
-					BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+	ret = btrfs_set_extent_delalloc(inode,
+			BTRFS_MAX_EXTENT_SIZE + sectorsize,
+			BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL);
 	if (ret) {
 		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
 		goto out;
@@ -1103,7 +1135,7 @@ out:
 	return ret;
 }
 
-int btrfs_test_inodes(void)
+int btrfs_test_inodes(u32 sectorsize, u32 nodesize)
 {
 	int ret;
 
@@ -1112,13 +1144,13 @@ int btrfs_test_inodes(void)
 	set_bit(EXTENT_FLAG_PREALLOC, &prealloc_only);
 
 	test_msg("Running btrfs_get_extent tests\n");
-	ret = test_btrfs_get_extent();
+	ret = test_btrfs_get_extent(sectorsize, nodesize);
 	if (ret)
 		return ret;
 	test_msg("Running hole first btrfs_get_extent test\n");
-	ret = test_hole_first();
+	ret = test_hole_first(sectorsize, nodesize);
 	if (ret)
 		return ret;
 	test_msg("Running outstanding_extents tests\n");
-	return test_extent_accounting();
+	return test_extent_accounting(sectorsize, nodesize);
 }
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index 8aa4ded31326..57a12c0d680b 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -16,6 +16,7 @@
  * Boston, MA 021110-1307, USA.
  */
 
+#include <linux/types.h>
 #include "btrfs-tests.h"
 #include "../ctree.h"
 #include "../transaction.h"
@@ -216,7 +217,8 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
 	return ret;
 }
 
-static int test_no_shared_qgroup(struct btrfs_root *root)
+static int test_no_shared_qgroup(struct btrfs_root *root,
+		u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_trans_handle trans;
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -227,7 +229,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
 	btrfs_init_dummy_trans(&trans);
 
 	test_msg("Qgroup basic add\n");
-	ret = btrfs_create_qgroup(NULL, fs_info, 5);
+	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FS_TREE_OBJECTID);
 	if (ret) {
 		test_msg("Couldn't create a qgroup %d\n", ret);
 		return ret;
@@ -238,18 +240,19 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
 	 * we can only call btrfs_qgroup_account_extent() directly to test
 	 * quota.
 	 */
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		test_msg("Couldn't find old roots: %d\n", ret);
 		return ret;
 	}
 
-	ret = insert_normal_tree_ref(root, 4096, 4096, 0, 5);
+	ret = insert_normal_tree_ref(root, nodesize, nodesize, 0,
+				BTRFS_FS_TREE_OBJECTID);
 	if (ret)
 		return ret;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
@@ -257,32 +260,33 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
-					  old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+					  nodesize, old_roots, new_roots);
 	if (ret) {
 		test_msg("Couldn't account space for a qgroup %d\n", ret);
 		return ret;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+				nodesize, nodesize)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
 	old_roots = NULL;
 	new_roots = NULL;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		test_msg("Couldn't find old roots: %d\n", ret);
 		return ret;
 	}
 
-	ret = remove_extent_item(root, 4096, 4096);
+	ret = remove_extent_item(root, nodesize, nodesize);
 	if (ret)
 		return -EINVAL;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
@@ -290,14 +294,14 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
-					  old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+					  nodesize, old_roots, new_roots);
 	if (ret) {
 		test_msg("Couldn't account space for a qgroup %d\n", ret);
 		return -EINVAL;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 5, 0, 0)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID, 0, 0)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
@@ -310,7 +314,8 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
  * right, also remove one of the roots and make sure the exclusive count is
  * adjusted properly.
  */
-static int test_multiple_refs(struct btrfs_root *root)
+static int test_multiple_refs(struct btrfs_root *root,
+		u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_trans_handle trans;
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -322,25 +327,29 @@ static int test_multiple_refs(struct btrfs_root *root)
 
 	test_msg("Qgroup multiple refs test\n");
 
-	/* We have 5 created already from the previous test */
-	ret = btrfs_create_qgroup(NULL, fs_info, 256);
+	/*
+	 * We have BTRFS_FS_TREE_OBJECTID created already from the
+	 * previous test.
+	 */
+	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FIRST_FREE_OBJECTID);
 	if (ret) {
 		test_msg("Couldn't create a qgroup %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		test_msg("Couldn't find old roots: %d\n", ret);
 		return ret;
 	}
 
-	ret = insert_normal_tree_ref(root, 4096, 4096, 0, 5);
+	ret = insert_normal_tree_ref(root, nodesize, nodesize, 0,
+				BTRFS_FS_TREE_OBJECTID);
 	if (ret)
 		return ret;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
@@ -348,30 +357,32 @@ static int test_multiple_refs(struct btrfs_root *root)
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
-					  old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+					  nodesize, old_roots, new_roots);
 	if (ret) {
 		test_msg("Couldn't account space for a qgroup %d\n", ret);
 		return ret;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+				       nodesize, nodesize)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		test_msg("Couldn't find old roots: %d\n", ret);
 		return ret;
 	}
 
-	ret = add_tree_ref(root, 4096, 4096, 0, 256);
+	ret = add_tree_ref(root, nodesize, nodesize, 0,
+			BTRFS_FIRST_FREE_OBJECTID);
 	if (ret)
 		return ret;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
@@ -379,35 +390,38 @@ static int test_multiple_refs(struct btrfs_root *root)
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
-					  old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+					  nodesize, old_roots, new_roots);
 	if (ret) {
 		test_msg("Couldn't account space for a qgroup %d\n", ret);
 		return ret;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 0)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+					nodesize, 0)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 256, 4096, 0)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FIRST_FREE_OBJECTID,
+					nodesize, 0)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		test_msg("Couldn't find old roots: %d\n", ret);
 		return ret;
 	}
 
-	ret = remove_extent_ref(root, 4096, 4096, 0, 256);
+	ret = remove_extent_ref(root, nodesize, nodesize, 0,
+				BTRFS_FIRST_FREE_OBJECTID);
 	if (ret)
 		return ret;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
@@ -415,19 +429,21 @@ static int test_multiple_refs(struct btrfs_root *root)
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
-					  old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+					  nodesize, old_roots, new_roots);
 	if (ret) {
 		test_msg("Couldn't account space for a qgroup %d\n", ret);
 		return ret;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 256, 0, 0)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FIRST_FREE_OBJECTID,
+					0, 0)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+					nodesize, nodesize)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
@@ -435,13 +451,13 @@ static int test_multiple_refs(struct btrfs_root *root)
 	return 0;
 }
 
-int btrfs_test_qgroups(void)
+int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_root *root;
 	struct btrfs_root *tmp_root;
 	int ret = 0;
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Couldn't allocate root\n");
 		return PTR_ERR(root);
@@ -468,7 +484,8 @@ int btrfs_test_qgroups(void)
 	 * Can't use bytenr 0, some things freak out
 	 * *cough*backref walking code*cough*
 	 */
-	root->node = alloc_test_extent_buffer(root->fs_info, 4096);
+	root->node = alloc_test_extent_buffer(root->fs_info, nodesize,
+					nodesize);
 	if (!root->node) {
 		test_msg("Couldn't allocate dummy buffer\n");
 		ret = -ENOMEM;
@@ -476,16 +493,16 @@ int btrfs_test_qgroups(void)
 	}
 	btrfs_set_header_level(root->node, 0);
 	btrfs_set_header_nritems(root->node, 0);
-	root->alloc_bytenr += 8192;
+	root->alloc_bytenr += 2 * nodesize;
 
-	tmp_root = btrfs_alloc_dummy_root();
+	tmp_root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(tmp_root)) {
 		test_msg("Couldn't allocate a fs root\n");
 		ret = PTR_ERR(tmp_root);
 		goto out;
 	}
 
-	tmp_root->root_key.objectid = 5;
+	tmp_root->root_key.objectid = BTRFS_FS_TREE_OBJECTID;
 	root->fs_info->fs_root = tmp_root;
 	ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
 	if (ret) {
@@ -493,14 +510,14 @@ int btrfs_test_qgroups(void)
 		goto out;
 	}
 
-	tmp_root = btrfs_alloc_dummy_root();
+	tmp_root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(tmp_root)) {
 		test_msg("Couldn't allocate a fs root\n");
 		ret = PTR_ERR(tmp_root);
 		goto out;
 	}
 
-	tmp_root->root_key.objectid = 256;
+	tmp_root->root_key.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
 	if (ret) {
 		test_msg("Couldn't insert fs root %d\n", ret);
@@ -508,10 +525,10 @@ int btrfs_test_qgroups(void)
 	}
 
 	test_msg("Running qgroup tests\n");
-	ret = test_no_shared_qgroup(root);
+	ret = test_no_shared_qgroup(root, sectorsize, nodesize);
 	if (ret)
 		goto out;
-	ret = test_multiple_refs(root);
+	ret = test_multiple_refs(root, sectorsize, nodesize);
 out:
 	btrfs_free_dummy_root(root);
 	return ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index f6e24cb423ae..948aa186b353 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -818,6 +818,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_fs_info *info = root->fs_info;
+	u64 transid = trans->transid;
 	unsigned long cur = trans->delayed_ref_updates;
 	int lock = (trans->type != TRANS_JOIN_NOLOCK);
 	int err = 0;
@@ -905,7 +906,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 	if (must_run_delayed_refs) {
-		btrfs_async_run_delayed_refs(root, cur,
+		btrfs_async_run_delayed_refs(root, cur, transid,
 					     must_run_delayed_refs == 1);
 	}
 	return err;
@@ -1311,11 +1312,6 @@ int btrfs_defrag_root(struct btrfs_root *root)
 	return ret;
 }
 
-/* Bisesctability fixup, remove in 4.8 */
-#ifndef btrfs_std_error
-#define btrfs_std_error btrfs_handle_fs_error
-#endif
-
 /*
  * Do all special snapshot related qgroup dirty hack.
  *
@@ -1385,7 +1381,7 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 	switch_commit_roots(trans->transaction, fs_info);
 	ret = btrfs_write_and_wait_transaction(trans, src);
 	if (ret)
-		btrfs_std_error(fs_info, ret,
+		btrfs_handle_fs_error(fs_info, ret,
 			"Error while writing out transaction for qgroup");
 
 out:
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 9fe0ec2bf0fe..c5abee4f01ad 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -110,7 +110,6 @@ struct btrfs_trans_handle {
 	u64 chunk_bytes_reserved;
 	unsigned long use_count;
 	unsigned long blocks_reserved;
-	unsigned long blocks_used;
 	unsigned long delayed_ref_updates;
 	struct btrfs_transaction *transaction;
 	struct btrfs_block_rsv *block_rsv;
@@ -121,6 +120,7 @@ struct btrfs_trans_handle {
 	bool can_flush_pending_bgs;
 	bool reloc_reserved;
 	bool sync;
+	bool dirty;
 	unsigned int type;
 	/*
 	 * this root is only needed to validate that the root passed to
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index b7665af471d8..c05f69a8ec42 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2422,8 +2422,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 		root_owner = btrfs_header_owner(parent);
 
 		next = btrfs_find_create_tree_block(root, bytenr);
-		if (!next)
-			return -ENOMEM;
+		if (IS_ERR(next))
+			return PTR_ERR(next);
 
 		if (*level == 1) {
 			ret = wc->process_func(root, next, wc, ptr_gen);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bdc62561ede8..589f128173b1 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2761,6 +2761,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	u64 dev_extent_len = 0;
 	u64 chunk_objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
 	int i, ret = 0;
+	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
 
 	/* Just in case */
 	root = root->fs_info->chunk_root;
@@ -2787,12 +2788,19 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	check_system_chunk(trans, extent_root, map->type);
 	unlock_chunks(root->fs_info->chunk_root);
 
+	/*
+	 * Take the device list mutex to prevent races with the final phase of
+	 * a device replace operation that replaces the device object associated
+	 * with map stripes (dev-replace.c:btrfs_dev_replace_finishing()).
+	 */
+	mutex_lock(&fs_devices->device_list_mutex);
 	for (i = 0; i < map->num_stripes; i++) {
 		struct btrfs_device *device = map->stripes[i].dev;
 		ret = btrfs_free_dev_extent(trans, device,
 					    map->stripes[i].physical,
 					    &dev_extent_len);
 		if (ret) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			btrfs_abort_transaction(trans, root, ret);
 			goto out;
 		}
@@ -2811,11 +2819,14 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 		if (map->stripes[i].dev) {
 			ret = btrfs_update_device(trans, map->stripes[i].dev);
 			if (ret) {
+				mutex_unlock(&fs_devices->device_list_mutex);
 				btrfs_abort_transaction(trans, root, ret);
 				goto out;
 			}
 		}
 	}
+	mutex_unlock(&fs_devices->device_list_mutex);
+
 	ret = btrfs_free_chunk(trans, root, chunk_objectid, chunk_offset);
 	if (ret) {
 		btrfs_abort_transaction(trans, root, ret);
@@ -4230,6 +4241,7 @@ int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info)
 	if (IS_ERR(uuid_root)) {
 		ret = PTR_ERR(uuid_root);
 		btrfs_abort_transaction(trans, tree_root, ret);
+		btrfs_end_transaction(trans, tree_root);
 		return ret;
 	}
 
@@ -4682,12 +4694,12 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	if (type & BTRFS_BLOCK_GROUP_RAID5) {
 		raid_stripe_len = find_raid56_stripe_len(ndevs - 1,
-				 btrfs_super_stripesize(info->super_copy));
+						extent_root->stripesize);
 		data_stripes = num_stripes - 1;
 	}
 	if (type & BTRFS_BLOCK_GROUP_RAID6) {
 		raid_stripe_len = find_raid56_stripe_len(ndevs - 2,
-				 btrfs_super_stripesize(info->super_copy));
+						extent_root->stripesize);
 		data_stripes = num_stripes - 2;
 	}
 
@@ -5762,20 +5774,17 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 			}
 		}
 		if (found) {
-			if (physical_of_found + map->stripe_len <=
-			    dev_replace->cursor_left) {
-				struct btrfs_bio_stripe *tgtdev_stripe =
-					bbio->stripes + num_stripes;
+			struct btrfs_bio_stripe *tgtdev_stripe =
+				bbio->stripes + num_stripes;
 
-				tgtdev_stripe->physical = physical_of_found;
-				tgtdev_stripe->length =
-					bbio->stripes[index_srcdev].length;
-				tgtdev_stripe->dev = dev_replace->tgtdev;
-				bbio->tgtdev_map[index_srcdev] = num_stripes;
+			tgtdev_stripe->physical = physical_of_found;
+			tgtdev_stripe->length =
+				bbio->stripes[index_srcdev].length;
+			tgtdev_stripe->dev = dev_replace->tgtdev;
+			bbio->tgtdev_map[index_srcdev] = num_stripes;
 
-				tgtdev_indexes++;
-				num_stripes++;
-			}
+			tgtdev_indexes++;
+			num_stripes++;
 		}
 	}
 
@@ -6250,27 +6259,23 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 	return dev;
 }
 
-static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
-			  struct extent_buffer *leaf,
-			  struct btrfs_chunk *chunk)
+/* Return -EIO if any error, otherwise return 0. */
+static int btrfs_check_chunk_valid(struct btrfs_root *root,
+				   struct extent_buffer *leaf,
+				   struct btrfs_chunk *chunk, u64 logical)
 {
-	struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
-	struct map_lookup *map;
-	struct extent_map *em;
-	u64 logical;
 	u64 length;
 	u64 stripe_len;
-	u64 devid;
-	u8 uuid[BTRFS_UUID_SIZE];
-	int num_stripes;
-	int ret;
-	int i;
+	u16 num_stripes;
+	u16 sub_stripes;
+	u64 type;
 
-	logical = key->offset;
 	length = btrfs_chunk_length(leaf, chunk);
 	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
 	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
-	/* Validation check */
+	sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
+	type = btrfs_chunk_type(leaf, chunk);
+
 	if (!num_stripes) {
 		btrfs_err(root->fs_info, "invalid chunk num_stripes: %u",
 			  num_stripes);
@@ -6281,6 +6286,11 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 			  "invalid chunk logical %llu", logical);
 		return -EIO;
 	}
+	if (btrfs_chunk_sector_size(leaf, chunk) != root->sectorsize) {
+		btrfs_err(root->fs_info, "invalid chunk sectorsize %u",
+			  btrfs_chunk_sector_size(leaf, chunk));
+		return -EIO;
+	}
 	if (!length || !IS_ALIGNED(length, root->sectorsize)) {
 		btrfs_err(root->fs_info,
 			"invalid chunk length %llu", length);
@@ -6292,13 +6302,54 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 		return -EIO;
 	}
 	if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) &
-	    btrfs_chunk_type(leaf, chunk)) {
+	    type) {
 		btrfs_err(root->fs_info, "unrecognized chunk type: %llu",
 			  ~(BTRFS_BLOCK_GROUP_TYPE_MASK |
 			    BTRFS_BLOCK_GROUP_PROFILE_MASK) &
 			  btrfs_chunk_type(leaf, chunk));
 		return -EIO;
 	}
+	if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) ||
+	    (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes < 1) ||
+	    (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) ||
+	    (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) ||
+	    (type & BTRFS_BLOCK_GROUP_DUP && num_stripes > 2) ||
+	    ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 &&
+	     num_stripes != 1)) {
+		btrfs_err(root->fs_info,
+			"invalid num_stripes:sub_stripes %u:%u for profile %llu",
+			num_stripes, sub_stripes,
+			type & BTRFS_BLOCK_GROUP_PROFILE_MASK);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
+			  struct extent_buffer *leaf,
+			  struct btrfs_chunk *chunk)
+{
+	struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
+	struct map_lookup *map;
+	struct extent_map *em;
+	u64 logical;
+	u64 length;
+	u64 stripe_len;
+	u64 devid;
+	u8 uuid[BTRFS_UUID_SIZE];
+	int num_stripes;
+	int ret;
+	int i;
+
+	logical = key->offset;
+	length = btrfs_chunk_length(leaf, chunk);
+	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
+	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+
+	ret = btrfs_check_chunk_valid(root, leaf, chunk, logical);
+	if (ret)
+		return ret;
 
 	read_lock(&map_tree->map_tree.lock);
 	em = lookup_extent_mapping(&map_tree->map_tree, logical, 1);
@@ -6546,6 +6597,7 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	u32 array_size;
 	u32 len = 0;
 	u32 cur_offset;
+	u64 type;
 	struct btrfs_key key;
 
 	ASSERT(BTRFS_SUPER_INFO_SIZE <= root->nodesize);
@@ -6555,8 +6607,8 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	 * overallocate but we can keep it as-is, only the first page is used.
 	 */
 	sb = btrfs_find_create_tree_block(root, BTRFS_SUPER_INFO_OFFSET);
-	if (!sb)
-		return -ENOMEM;
+	if (IS_ERR(sb))
+		return PTR_ERR(sb);
 	set_extent_buffer_uptodate(sb);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0);
 	/*
@@ -6612,6 +6664,15 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 				break;
 			}
 
+			type = btrfs_chunk_type(sb, chunk);
+			if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
+				btrfs_err(root->fs_info,
+			    "invalid chunk type %llu in sys_array at offset %u",
+					type, cur_offset);
+				ret = -EIO;
+				break;
+			}
+
 			len = btrfs_chunk_item_size(num_stripes);
 			if (cur_offset + len > array_size)
 				goto out_short_read;
@@ -6630,12 +6691,14 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 		sb_array_offset += len;
 		cur_offset += len;
 	}
+	clear_extent_buffer_uptodate(sb);
 	free_extent_buffer_stale(sb);
 	return ret;
 
 out_short_read:
 	printk(KERN_ERR "BTRFS: sys_array too short to read %u bytes at offset %u\n",
 			len, cur_offset);
+	clear_extent_buffer_uptodate(sb);
 	free_extent_buffer_stale(sb);
 	return -EIO;
 }
@@ -6648,6 +6711,7 @@ int btrfs_read_chunk_tree(struct btrfs_root *root)
 	struct btrfs_key found_key;
 	int ret;
 	int slot;
+	u64 total_dev = 0;
 
 	root = root->fs_info->chunk_root;
 
@@ -6689,6 +6753,7 @@ int btrfs_read_chunk_tree(struct btrfs_root *root)
 			ret = read_one_dev(root, leaf, dev_item);
 			if (ret)
 				goto error;
+			total_dev++;
 		} else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) {
 			struct btrfs_chunk *chunk;
 			chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
@@ -6698,6 +6763,28 @@ int btrfs_read_chunk_tree(struct btrfs_root *root)
 		}
 		path->slots[0]++;
 	}
+
+	/*
+	 * After loading chunk tree, we've got all device information,
+	 * do another round of validation checks.
+	 */
+	if (total_dev != root->fs_info->fs_devices->total_devices) {
+		btrfs_err(root->fs_info,
+	   "super_num_devices %llu mismatch with num_devices %llu found here",
+			  btrfs_super_num_devices(root->fs_info->super_copy),
+			  total_dev);
+		ret = -EINVAL;
+		goto error;
+	}
+	if (btrfs_super_total_bytes(root->fs_info->super_copy) <
+	    root->fs_info->fs_devices->total_rw_bytes) {
+		btrfs_err(root->fs_info,
+	"super_total_bytes %llu mismatch with fs_devices total_rw_bytes %llu",
+			  btrfs_super_total_bytes(root->fs_info->super_copy),
+			  root->fs_info->fs_devices->total_rw_bytes);
+		ret = -EINVAL;
+		goto error;
+	}
 	ret = 0;
 error:
 	unlock_chunks(root);
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 861d611b8c05..ce5f345d70f5 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -380,7 +380,7 @@ static void cachefiles_sync_cache(struct fscache_cache *_cache)
  * check if the backing cache is updated to FS-Cache
  * - called by FS-Cache when evaluates if need to invalidate the cache
  */
-static bool cachefiles_check_consistency(struct fscache_operation *op)
+static int cachefiles_check_consistency(struct fscache_operation *op)
 {
 	struct cachefiles_object *object;
 	struct cachefiles_cache *cache;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index eeb71e5de27a..26a9d10d75e9 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -276,8 +276,10 @@ static void finish_read(struct ceph_osd_request *req)
 	for (i = 0; i < num_pages; i++) {
 		struct page *page = osd_data->pages[i];
 
-		if (rc < 0 && rc != -ENOENT)
+		if (rc < 0 && rc != -ENOENT) {
+			ceph_fscache_readpage_cancel(inode, page);
 			goto unlock;
+		}
 		if (bytes < (int)PAGE_SIZE) {
 			/* zero (remainder of) page */
 			int s = bytes < 0 ? 0 : bytes;
@@ -535,8 +537,6 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
 		set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
 
-	ceph_readpage_to_fscache(inode, page);
-
 	set_page_writeback(page);
 	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
 				   &ci->i_layout, snapc,
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index c052b5bf219b..238c55b01723 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -25,6 +25,7 @@
 #include "cache.h"
 
 struct ceph_aux_inode {
+	u64 		version;
 	struct timespec	mtime;
 	loff_t          size;
 };
@@ -69,15 +70,8 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
 	fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index,
 					      &ceph_fscache_fsid_object_def,
 					      fsc, true);
-
-	if (fsc->fscache == NULL) {
+	if (!fsc->fscache)
 		pr_err("Unable to resgister fsid: %p fscache cookie", fsc);
-		return 0;
-	}
-
-	fsc->revalidate_wq = alloc_workqueue("ceph-revalidate", 0, 1);
-	if (fsc->revalidate_wq == NULL)
-		return -ENOMEM;
 
 	return 0;
 }
@@ -105,6 +99,7 @@ static uint16_t ceph_fscache_inode_get_aux(const void *cookie_netfs_data,
 	const struct inode* inode = &ci->vfs_inode;
 
 	memset(&aux, 0, sizeof(aux));
+	aux.version = ci->i_version;
 	aux.mtime = inode->i_mtime;
 	aux.size = i_size_read(inode);
 
@@ -131,6 +126,7 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux(
 		return FSCACHE_CHECKAUX_OBSOLETE;
 
 	memset(&aux, 0, sizeof(aux));
+	aux.version = ci->i_version;
 	aux.mtime = inode->i_mtime;
 	aux.size = i_size_read(inode);
 
@@ -181,32 +177,26 @@ static const struct fscache_cookie_def ceph_fscache_inode_object_def = {
 	.now_uncached	= ceph_fscache_inode_now_uncached,
 };
 
-void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
-					struct ceph_inode_info* ci)
+void ceph_fscache_register_inode_cookie(struct inode *inode)
 {
-	struct inode* inode = &ci->vfs_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 
 	/* No caching for filesystem */
 	if (fsc->fscache == NULL)
 		return;
 
 	/* Only cache for regular files that are read only */
-	if ((ci->vfs_inode.i_mode & S_IFREG) == 0)
+	if (!S_ISREG(inode->i_mode))
 		return;
 
-	/* Avoid multiple racing open requests */
-	inode_lock(inode);
-
-	if (ci->fscache)
-		goto done;
-
-	ci->fscache = fscache_acquire_cookie(fsc->fscache,
-					     &ceph_fscache_inode_object_def,
-					     ci, true);
-	fscache_check_consistency(ci->fscache);
-done:
+	inode_lock_nested(inode, I_MUTEX_CHILD);
+	if (!ci->fscache) {
+		ci->fscache = fscache_acquire_cookie(fsc->fscache,
+					&ceph_fscache_inode_object_def,
+					ci, false);
+	}
 	inode_unlock(inode);
-
 }
 
 void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
@@ -222,6 +212,34 @@ void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
 	fscache_relinquish_cookie(cookie, 0);
 }
 
+static bool ceph_fscache_can_enable(void *data)
+{
+	struct inode *inode = data;
+	return !inode_is_open_for_write(inode);
+}
+
+void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	if (!fscache_cookie_valid(ci->fscache))
+		return;
+
+	if (inode_is_open_for_write(inode)) {
+		dout("fscache_file_set_cookie %p %p disabling cache\n",
+		     inode, filp);
+		fscache_disable_cookie(ci->fscache, false);
+		fscache_uncache_all_inode_pages(ci->fscache, inode);
+	} else {
+		fscache_enable_cookie(ci->fscache, ceph_fscache_can_enable,
+				inode);
+		if (fscache_cookie_enabled(ci->fscache)) {
+			dout("fscache_file_set_cookie %p %p enabing cache\n",
+			     inode, filp);
+		}
+	}
+}
+
 static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
 {
 	if (!error)
@@ -238,8 +256,7 @@ static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int
 
 static inline bool cache_valid(struct ceph_inode_info *ci)
 {
-	return ((ceph_caps_issued(ci) & CEPH_CAP_FILE_CACHE) &&
-		(ci->i_fscache_gen == ci->i_rdcache_gen));
+	return ci->i_fscache_gen == ci->i_rdcache_gen;
 }
 
 
@@ -332,69 +349,27 @@ void ceph_invalidate_fscache_page(struct inode* inode, struct page *page)
 
 void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
 {
-	if (fsc->revalidate_wq)
-		destroy_workqueue(fsc->revalidate_wq);
-
 	fscache_relinquish_cookie(fsc->fscache, 0);
 	fsc->fscache = NULL;
 }
 
-static void ceph_revalidate_work(struct work_struct *work)
-{
-	int issued;
-	u32 orig_gen;
-	struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
-						  i_revalidate_work);
-	struct inode *inode = &ci->vfs_inode;
-
-	spin_lock(&ci->i_ceph_lock);
-	issued = __ceph_caps_issued(ci, NULL);
-	orig_gen = ci->i_rdcache_gen;
-	spin_unlock(&ci->i_ceph_lock);
-
-	if (!(issued & CEPH_CAP_FILE_CACHE)) {
-		dout("revalidate_work lost cache before validation %p\n",
-		     inode);
-		goto out;
-	}
-
-	if (!fscache_check_consistency(ci->fscache))
-		fscache_invalidate(ci->fscache);
-
-	spin_lock(&ci->i_ceph_lock);
-	/* Update the new valid generation (backwards sanity check too) */
-	if (orig_gen > ci->i_fscache_gen) {
-		ci->i_fscache_gen = orig_gen;
-	}
-	spin_unlock(&ci->i_ceph_lock);
-
-out:
-	iput(&ci->vfs_inode);
-}
-
-void ceph_queue_revalidate(struct inode *inode)
+/*
+ * caller should hold CEPH_CAP_FILE_{RD,CACHE}
+ */
+void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
-	struct ceph_inode_info *ci = ceph_inode(inode);
-
-	if (fsc->revalidate_wq == NULL || ci->fscache == NULL)
+	if (cache_valid(ci))
 		return;
 
-	ihold(inode);
-
-	if (queue_work(ceph_sb_to_client(inode->i_sb)->revalidate_wq,
-		       &ci->i_revalidate_work)) {
-		dout("ceph_queue_revalidate %p\n", inode);
-	} else {
-		dout("ceph_queue_revalidate %p failed\n)", inode);
-		iput(inode);
+	/* resue i_truncate_mutex. There should be no pending
+	 * truncate while the caller holds CEPH_CAP_FILE_RD */
+	mutex_lock(&ci->i_truncate_mutex);
+	if (!cache_valid(ci)) {
+		if (fscache_check_consistency(ci->fscache))
+			fscache_invalidate(ci->fscache);
+		spin_lock(&ci->i_ceph_lock);
+		ci->i_fscache_gen = ci->i_rdcache_gen;
+		spin_unlock(&ci->i_ceph_lock);
 	}
-}
-
-void ceph_fscache_inode_init(struct ceph_inode_info *ci)
-{
-	ci->fscache = NULL;
-	/* The first load is verifed cookie open time */
-	ci->i_fscache_gen = 1;
-	INIT_WORK(&ci->i_revalidate_work, ceph_revalidate_work);
+	mutex_unlock(&ci->i_truncate_mutex);
 }
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index 5ac591bd012b..7e72c7594f0c 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -34,10 +34,10 @@ void ceph_fscache_unregister(void);
 int ceph_fscache_register_fs(struct ceph_fs_client* fsc);
 void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc);
 
-void ceph_fscache_inode_init(struct ceph_inode_info *ci);
-void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
-					struct ceph_inode_info* ci);
+void ceph_fscache_register_inode_cookie(struct inode *inode);
 void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci);
+void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp);
+void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci);
 
 int ceph_readpage_from_fscache(struct inode *inode, struct page *page);
 int ceph_readpages_from_fscache(struct inode *inode,
@@ -46,12 +46,11 @@ int ceph_readpages_from_fscache(struct inode *inode,
 				unsigned *nr_pages);
 void ceph_readpage_to_fscache(struct inode *inode, struct page *page);
 void ceph_invalidate_fscache_page(struct inode* inode, struct page *page);
-void ceph_queue_revalidate(struct inode *inode);
 
-static inline void ceph_fscache_update_objectsize(struct inode *inode)
+static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci)
 {
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	fscache_attr_changed(ci->fscache);
+	ci->fscache = NULL;
+	ci->i_fscache_gen = 0;
 }
 
 static inline void ceph_fscache_invalidate(struct inode *inode)
@@ -88,6 +87,11 @@ static inline void ceph_fscache_readpages_cancel(struct inode *inode,
 	return fscache_readpages_cancel(ci->fscache, pages);
 }
 
+static inline void ceph_disable_fscache_readpage(struct ceph_inode_info *ci)
+{
+	ci->i_fscache_gen = ci->i_rdcache_gen - 1;
+}
+
 #else
 
 static inline int ceph_fscache_register(void)
@@ -112,8 +116,20 @@ static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci)
 {
 }
 
-static inline void ceph_fscache_register_inode_cookie(struct ceph_fs_client* parent_fsc,
-						      struct ceph_inode_info* ci)
+static inline void ceph_fscache_register_inode_cookie(struct inode *inode)
+{
+}
+
+static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
+{
+}
+
+static inline void ceph_fscache_file_set_cookie(struct inode *inode,
+						struct file *filp)
+{
+}
+
+static inline void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci)
 {
 }
 
@@ -141,10 +157,6 @@ static inline void ceph_readpage_to_fscache(struct inode *inode,
 {
 }
 
-static inline void ceph_fscache_update_objectsize(struct inode *inode)
-{
-}
-
 static inline void ceph_fscache_invalidate(struct inode *inode)
 {
 }
@@ -154,10 +166,6 @@ static inline void ceph_invalidate_fscache_page(struct inode *inode,
 {
 }
 
-static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
-{
-}
-
 static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
 {
 	return 1;
@@ -173,7 +181,7 @@ static inline void ceph_fscache_readpages_cancel(struct inode *inode,
 {
 }
 
-static inline void ceph_queue_revalidate(struct inode *inode)
+static inline void ceph_disable_fscache_readpage(struct ceph_inode_info *ci)
 {
 }
 
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index c17b5d76d75e..6f60d0a3d0f9 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2393,6 +2393,9 @@ again:
 				snap_rwsem_locked = true;
 			}
 			*got = need | (have & want);
+			if ((need & CEPH_CAP_FILE_RD) &&
+			    !(*got & CEPH_CAP_FILE_CACHE))
+				ceph_disable_fscache_readpage(ci);
 			__take_cap_refs(ci, *got, true);
 			ret = 1;
 		}
@@ -2554,6 +2557,9 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
 		break;
 	}
 
+	if ((_got & CEPH_CAP_FILE_RD) && (_got & CEPH_CAP_FILE_CACHE))
+		ceph_fscache_revalidate_cookie(ci);
+
 	*got = _got;
 	return 0;
 }
@@ -2795,7 +2801,6 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	bool writeback = false;
 	bool queue_trunc = false;
 	bool queue_invalidate = false;
-	bool queue_revalidate = false;
 	bool deleted_inode = false;
 	bool fill_inline = false;
 
@@ -2837,8 +2842,6 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 				ci->i_rdcache_revoking = ci->i_rdcache_gen;
 			}
 		}
-
-		ceph_fscache_invalidate(inode);
 	}
 
 	/* side effects now are allowed */
@@ -2880,11 +2883,6 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 		}
 	}
 
-	/* Do we need to revalidate our fscache cookie. Don't bother on the
-	 * first cache cap as we already validate at cookie creation time. */
-	if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
-		queue_revalidate = true;
-
 	if (newcaps & CEPH_CAP_ANY_RD) {
 		/* ctime/mtime/atime? */
 		ceph_decode_timespec(&mtime, &grant->mtime);
@@ -2993,11 +2991,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	if (fill_inline)
 		ceph_fill_inline_data(inode, NULL, inline_data, inline_len);
 
-	if (queue_trunc) {
+	if (queue_trunc)
 		ceph_queue_vmtruncate(inode);
-		ceph_queue_revalidate(inode);
-	} else if (queue_revalidate)
-		ceph_queue_revalidate(inode);
 
 	if (writeback)
 		/*
@@ -3199,10 +3194,8 @@ static void handle_cap_trunc(struct inode *inode,
 					  truncate_seq, truncate_size, size);
 	spin_unlock(&ci->i_ceph_lock);
 
-	if (queue_trunc) {
+	if (queue_trunc)
 		ceph_queue_vmtruncate(inode);
-		ceph_fscache_invalidate(inode);
-	}
 }
 
 /*
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index a888df6f2d71..ce2f5795e44b 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -137,23 +137,11 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 {
 	struct ceph_file_info *cf;
 	int ret = 0;
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
-	struct ceph_mds_client *mdsc = fsc->mdsc;
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
-		/* First file open request creates the cookie, we want to keep
-		 * this cookie around for the filetime of the inode as not to
-		 * have to worry about fscache register / revoke / operation
-		 * races.
-		 *
-		 * Also, if we know the operation is going to invalidate data
-		 * (non readonly) just nuke the cache right away.
-		 */
-		ceph_fscache_register_inode_cookie(mdsc->fsc, ci);
-		if ((fmode & CEPH_FILE_MODE_WR))
-			ceph_fscache_invalidate(inode);
+		ceph_fscache_register_inode_cookie(inode);
+		ceph_fscache_file_set_cookie(inode, file);
 	case S_IFDIR:
 		dout("init_file %p %p 0%o (regular)\n", inode, file,
 		     inode->i_mode);
@@ -1349,7 +1337,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 retry_snap:
-	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) {
+	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) {
 		err = -ENOSPC;
 		goto out;
 	}
@@ -1407,7 +1395,6 @@ retry_snap:
 			iov_iter_advance(from, written);
 		ceph_put_snap_context(snapc);
 	} else {
-		loff_t old_size = i_size_read(inode);
 		/*
 		 * No need to acquire the i_truncate_mutex. Because
 		 * the MDS revokes Fwb caps before sending truncate
@@ -1418,8 +1405,6 @@ retry_snap:
 		written = generic_perform_write(file, from, pos);
 		if (likely(written >= 0))
 			iocb->ki_pos = pos + written;
-		if (i_size_read(inode) > old_size)
-			ceph_fscache_update_objectsize(inode);
 		inode_unlock(inode);
 	}
 
@@ -1440,7 +1425,7 @@ retry_snap:
 	ceph_put_cap_refs(ci, got);
 
 	if (written >= 0) {
-		if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))
+		if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_NEARFULL))
 			iocb->ki_flags |= IOCB_DSYNC;
 
 		written = generic_write_sync(iocb, written);
@@ -1672,8 +1657,8 @@ static long ceph_fallocate(struct file *file, int mode,
 		goto unlock;
 	}
 
-	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) &&
-		!(mode & FALLOC_FL_PUNCH_HOLE)) {
+	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) &&
+	    !(mode & FALLOC_FL_PUNCH_HOLE)) {
 		ret = -ENOSPC;
 		goto unlock;
 	}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 0130a8592191..0168b49fb6ad 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -103,7 +103,6 @@ struct ceph_fs_client {
 
 #ifdef CONFIG_CEPH_FSCACHE
 	struct fscache_cookie *fscache;
-	struct workqueue_struct *revalidate_wq;
 #endif
 };
 
@@ -360,8 +359,7 @@ struct ceph_inode_info {
 
 #ifdef CONFIG_CEPH_FSCACHE
 	struct fscache_cookie *fscache;
-	u32 i_fscache_gen; /* sequence, for delayed fscache validate */
-	struct work_struct i_revalidate_work;
+	u32 i_fscache_gen;
 #endif
 	struct inode vfs_inode; /* at end */
 };
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 5a53ac6b1e02..02b071bf3732 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -101,6 +101,12 @@ convert_sfm_char(const __u16 src_char, char *target)
 	case SFM_SLASH:
 		*target = '\\';
 		break;
+	case SFM_SPACE:
+		*target = ' ';
+		break;
+	case SFM_PERIOD:
+		*target = '.';
+		break;
 	default:
 		return false;
 	}
@@ -404,7 +410,7 @@ static __le16 convert_to_sfu_char(char src_char)
 	return dest_char;
 }
 
-static __le16 convert_to_sfm_char(char src_char)
+static __le16 convert_to_sfm_char(char src_char, bool end_of_string)
 {
 	__le16 dest_char;
 
@@ -427,6 +433,18 @@ static __le16 convert_to_sfm_char(char src_char)
 	case '|':
 		dest_char = cpu_to_le16(SFM_PIPE);
 		break;
+	case '.':
+		if (end_of_string)
+			dest_char = cpu_to_le16(SFM_PERIOD);
+		else
+			dest_char = 0;
+		break;
+	case ' ':
+		if (end_of_string)
+			dest_char = cpu_to_le16(SFM_SPACE);
+		else
+			dest_char = 0;
+		break;
 	default:
 		dest_char = 0;
 	}
@@ -469,9 +487,16 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 		/* see if we must remap this char */
 		if (map_chars == SFU_MAP_UNI_RSVD)
 			dst_char = convert_to_sfu_char(src_char);
-		else if (map_chars == SFM_MAP_UNI_RSVD)
-			dst_char = convert_to_sfm_char(src_char);
-		else
+		else if (map_chars == SFM_MAP_UNI_RSVD) {
+			bool end_of_string;
+
+			if (i == srclen - 1)
+				end_of_string = true;
+			else
+				end_of_string = false;
+
+			dst_char = convert_to_sfm_char(src_char, end_of_string);
+		} else
 			dst_char = 0;
 		/*
 		 * FIXME: We can not handle remapping backslash (UNI_SLASH)
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index bdc52cb9a676..479bc0a941f3 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -64,6 +64,8 @@
 #define SFM_LESSTHAN    ((__u16) 0xF023)
 #define SFM_PIPE        ((__u16) 0xF027)
 #define SFM_SLASH       ((__u16) 0xF026)
+#define SFM_PERIOD	((__u16) 0xF028)
+#define SFM_SPACE	((__u16) 0xF029)
 
 /*
  * Mapping mechanism to use when one of the seven reserved characters is
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 5d8b7edf8a8f..5d841f39c4b7 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -87,6 +87,7 @@ extern mempool_t *cifs_req_poolp;
 extern mempool_t *cifs_mid_poolp;
 
 struct workqueue_struct	*cifsiod_wq;
+__u32 cifs_lock_secret;
 
 /*
  * Bumps refcount for cifs super block.
@@ -1266,6 +1267,8 @@ init_cifs(void)
 	spin_lock_init(&cifs_file_list_lock);
 	spin_lock_init(&GlobalMid_Lock);
 
+	get_random_bytes(&cifs_lock_secret, sizeof(cifs_lock_secret));
+
 	if (cifs_max_pending < 2) {
 		cifs_max_pending = 2;
 		cifs_dbg(FYI, "cifs_max_pending set to min of 2\n");
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index bba106cdc43c..8f1d8c1e72be 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1619,6 +1619,7 @@ void cifs_oplock_break(struct work_struct *work);
 
 extern const struct slow_work_ops cifs_oplock_break_ops;
 extern struct workqueue_struct *cifsiod_wq;
+extern __u32 cifs_lock_secret;
 
 extern mempool_t *cifs_mid_poolp;
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 66736f57b5ab..7d2b15c06090 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -428,7 +428,9 @@ cifs_echo_request(struct work_struct *work)
 	 * server->ops->need_neg() == true. Also, no need to ping if
 	 * we got a response recently.
 	 */
-	if (!server->ops->need_neg || server->ops->need_neg(server) ||
+
+	if (server->tcpStatus == CifsNeedReconnect ||
+	    server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew ||
 	    (server->ops->can_echo && !server->ops->can_echo(server)) ||
 	    time_before(jiffies, server->lstrp + echo_interval - HZ))
 		goto requeue_echo;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 9793ae0bcaa2..d4890b6dc22d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1112,6 +1112,12 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
 	return rc;
 }
 
+static __u32
+hash_lockowner(fl_owner_t owner)
+{
+	return cifs_lock_secret ^ hash32_ptr((const void *)owner);
+}
+
 struct lock_to_push {
 	struct list_head llist;
 	__u64 offset;
@@ -1178,7 +1184,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 		else
 			type = CIFS_WRLCK;
 		lck = list_entry(el, struct lock_to_push, llist);
-		lck->pid = flock->fl_pid;
+		lck->pid = hash_lockowner(flock->fl_owner);
 		lck->netfid = cfile->fid.netfid;
 		lck->length = length;
 		lck->type = type;
@@ -1305,7 +1311,8 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
 			posix_lock_type = CIFS_RDLCK;
 		else
 			posix_lock_type = CIFS_WRLCK;
-		rc = CIFSSMBPosixLock(xid, tcon, netfid, current->tgid,
+		rc = CIFSSMBPosixLock(xid, tcon, netfid,
+				      hash_lockowner(flock->fl_owner),
 				      flock->fl_start, length, flock,
 				      posix_lock_type, wait_flag);
 		return rc;
@@ -1505,7 +1512,8 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 			posix_lock_type = CIFS_UNLCK;
 
 		rc = CIFSSMBPosixLock(xid, tcon, cfile->fid.netfid,
-				      current->tgid, flock->fl_start, length,
+				      hash_lockowner(flock->fl_owner),
+				      flock->fl_start, length,
 				      NULL, posix_lock_type, wait_flag);
 		goto out;
 	}
diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h
index 848249fa120f..3079b38f0afb 100644
--- a/fs/cifs/ntlmssp.h
+++ b/fs/cifs/ntlmssp.h
@@ -133,6 +133,6 @@ typedef struct _AUTHENTICATE_MESSAGE {
 
 int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses);
 void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, struct cifs_ses *ses);
-int build_ntlmssp_auth_blob(unsigned char *pbuffer, u16 *buflen,
+int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen,
 			struct cifs_ses *ses,
 			const struct nls_table *nls_cp);
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index af0ec2d5ad0e..538d9b55699a 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -364,19 +364,43 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
 	sec_blob->DomainName.MaximumLength = 0;
 }
 
-/* We do not malloc the blob, it is passed in pbuffer, because its
-   maximum possible size is fixed and small, making this approach cleaner.
-   This function returns the length of the data in the blob */
-int build_ntlmssp_auth_blob(unsigned char *pbuffer,
+static int size_of_ntlmssp_blob(struct cifs_ses *ses)
+{
+	int sz = sizeof(AUTHENTICATE_MESSAGE) + ses->auth_key.len
+		- CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2;
+
+	if (ses->domainName)
+		sz += 2 * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+	else
+		sz += 2;
+
+	if (ses->user_name)
+		sz += 2 * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN);
+	else
+		sz += 2;
+
+	return sz;
+}
+
+int build_ntlmssp_auth_blob(unsigned char **pbuffer,
 					u16 *buflen,
 				   struct cifs_ses *ses,
 				   const struct nls_table *nls_cp)
 {
 	int rc;
-	AUTHENTICATE_MESSAGE *sec_blob = (AUTHENTICATE_MESSAGE *)pbuffer;
+	AUTHENTICATE_MESSAGE *sec_blob;
 	__u32 flags;
 	unsigned char *tmp;
 
+	rc = setup_ntlmv2_rsp(ses, nls_cp);
+	if (rc) {
+		cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc);
+		*buflen = 0;
+		goto setup_ntlmv2_ret;
+	}
+	*pbuffer = kmalloc(size_of_ntlmssp_blob(ses), GFP_KERNEL);
+	sec_blob = (AUTHENTICATE_MESSAGE *)*pbuffer;
+
 	memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8);
 	sec_blob->MessageType = NtLmAuthenticate;
 
@@ -391,7 +415,7 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 			flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
 	}
 
-	tmp = pbuffer + sizeof(AUTHENTICATE_MESSAGE);
+	tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE);
 	sec_blob->NegotiateFlags = cpu_to_le32(flags);
 
 	sec_blob->LmChallengeResponse.BufferOffset =
@@ -399,13 +423,9 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 	sec_blob->LmChallengeResponse.Length = 0;
 	sec_blob->LmChallengeResponse.MaximumLength = 0;
 
-	sec_blob->NtChallengeResponse.BufferOffset = cpu_to_le32(tmp - pbuffer);
+	sec_blob->NtChallengeResponse.BufferOffset =
+				cpu_to_le32(tmp - *pbuffer);
 	if (ses->user_name != NULL) {
-		rc = setup_ntlmv2_rsp(ses, nls_cp);
-		if (rc) {
-			cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc);
-			goto setup_ntlmv2_ret;
-		}
 		memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
 				ses->auth_key.len - CIFS_SESS_KEY_SIZE);
 		tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE;
@@ -423,23 +443,23 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 	}
 
 	if (ses->domainName == NULL) {
-		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->DomainName.Length = 0;
 		sec_blob->DomainName.MaximumLength = 0;
 		tmp += 2;
 	} else {
 		int len;
 		len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName,
-				      CIFS_MAX_USERNAME_LEN, nls_cp);
+				      CIFS_MAX_DOMAINNAME_LEN, nls_cp);
 		len *= 2; /* unicode is 2 bytes each */
-		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->DomainName.Length = cpu_to_le16(len);
 		sec_blob->DomainName.MaximumLength = cpu_to_le16(len);
 		tmp += len;
 	}
 
 	if (ses->user_name == NULL) {
-		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->UserName.Length = 0;
 		sec_blob->UserName.MaximumLength = 0;
 		tmp += 2;
@@ -448,13 +468,13 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 		len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name,
 				      CIFS_MAX_USERNAME_LEN, nls_cp);
 		len *= 2; /* unicode is 2 bytes each */
-		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->UserName.Length = cpu_to_le16(len);
 		sec_blob->UserName.MaximumLength = cpu_to_le16(len);
 		tmp += len;
 	}
 
-	sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+	sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 	sec_blob->WorkstationName.Length = 0;
 	sec_blob->WorkstationName.MaximumLength = 0;
 	tmp += 2;
@@ -463,19 +483,19 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 		(ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC))
 			&& !calc_seckey(ses)) {
 		memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE);
-		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE);
 		sec_blob->SessionKey.MaximumLength =
 				cpu_to_le16(CIFS_CPHTXT_SIZE);
 		tmp += CIFS_CPHTXT_SIZE;
 	} else {
-		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->SessionKey.Length = 0;
 		sec_blob->SessionKey.MaximumLength = 0;
 	}
 
+	*buflen = tmp - *pbuffer;
 setup_ntlmv2_ret:
-	*buflen = tmp - pbuffer;
 	return rc;
 }
 
@@ -690,6 +710,8 @@ sess_auth_lanman(struct sess_data *sess_data)
 		rc = calc_lanman_hash(ses->password, ses->server->cryptkey,
 				      ses->server->sec_mode & SECMODE_PW_ENCRYPT ?
 				      true : false, lnm_session_key);
+		if (rc)
+			goto out;
 
 		memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE);
 		bcc_ptr += CIFS_AUTH_RESP_SIZE;
@@ -1266,7 +1288,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data)
 	struct cifs_ses *ses = sess_data->ses;
 	__u16 bytes_remaining;
 	char *bcc_ptr;
-	char *ntlmsspblob = NULL;
+	unsigned char *ntlmsspblob = NULL;
 	u16 blob_len;
 
 	cifs_dbg(FYI, "rawntlmssp session setup authenticate phase\n");
@@ -1279,19 +1301,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data)
 	/* Build security blob before we assemble the request */
 	pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base;
 	smb_buf = (struct smb_hdr *)pSMB;
-	/*
-	 * 5 is an empirical value, large enough to hold
-	 * authenticate message plus max 10 of av paris,
-	 * domain, user, workstation names, flags, etc.
-	 */
-	ntlmsspblob = kzalloc(5*sizeof(struct _AUTHENTICATE_MESSAGE),
-				GFP_KERNEL);
-	if (!ntlmsspblob) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	rc = build_ntlmssp_auth_blob(ntlmsspblob,
+	rc = build_ntlmssp_auth_blob(&ntlmsspblob,
 					&blob_len, ses, sess_data->nls_cp);
 	if (rc)
 		goto out_free_ntlmsspblob;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 8f38e33d365b..29e06db5f187 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -588,7 +588,7 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	u16 blob_length = 0;
 	struct key *spnego_key = NULL;
 	char *security_blob = NULL;
-	char *ntlmssp_blob = NULL;
+	unsigned char *ntlmssp_blob = NULL;
 	bool use_spnego = false; /* else use raw ntlmssp */
 
 	cifs_dbg(FYI, "Session Setup\n");
@@ -713,13 +713,7 @@ ssetup_ntlmssp_authenticate:
 		iov[1].iov_len = blob_length;
 	} else if (phase == NtLmAuthenticate) {
 		req->hdr.SessionId = ses->Suid;
-		ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500,
-				       GFP_KERNEL);
-		if (ntlmssp_blob == NULL) {
-			rc = -ENOMEM;
-			goto ssetup_exit;
-		}
-		rc = build_ntlmssp_auth_blob(ntlmssp_blob, &blob_length, ses,
+		rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses,
 					     nls_cp);
 		if (rc) {
 			cifs_dbg(FYI, "build_ntlmssp_auth_blob failed %d\n",
@@ -1818,6 +1812,33 @@ SMB2_echo(struct TCP_Server_Info *server)
 
 	cifs_dbg(FYI, "In echo request\n");
 
+	if (server->tcpStatus == CifsNeedNegotiate) {
+		struct list_head *tmp, *tmp2;
+		struct cifs_ses *ses;
+		struct cifs_tcon *tcon;
+
+		cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n");
+		spin_lock(&cifs_tcp_ses_lock);
+		list_for_each(tmp, &server->smb_ses_list) {
+			ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
+			list_for_each(tmp2, &ses->tcon_list) {
+				tcon = list_entry(tmp2, struct cifs_tcon,
+						  tcon_list);
+				/* add check for persistent handle reconnect */
+				if (tcon && tcon->need_reconnect) {
+					spin_unlock(&cifs_tcp_ses_lock);
+					rc = smb2_reconnect(SMB2_ECHO, tcon);
+					spin_lock(&cifs_tcp_ses_lock);
+				}
+			}
+		}
+		spin_unlock(&cifs_tcp_ses_lock);
+	}
+
+	/* if no session, renegotiate failed above */
+	if (server->tcpStatus == CifsNeedNegotiate)
+		return -EIO;
+
 	rc = small_smb2_init(SMB2_ECHO, NULL, (void **)&req);
 	if (rc)
 		return rc;
diff --git a/fs/coredump.c b/fs/coredump.c
index 38a7ab87e10a..281b768000e6 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -794,6 +794,7 @@ int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
 			return 0;
 		file->f_pos = pos;
 		cprm->written += n;
+		cprm->pos += n;
 		nr -= n;
 	}
 	return 1;
@@ -808,6 +809,7 @@ int dump_skip(struct coredump_params *cprm, size_t nr)
 		if (dump_interrupted() ||
 		    file->f_op->llseek(file, nr, SEEK_CUR) < 0)
 			return 0;
+		cprm->pos += nr;
 		return 1;
 	} else {
 		while (nr > PAGE_SIZE) {
@@ -822,7 +824,7 @@ EXPORT_SYMBOL(dump_skip);
 
 int dump_align(struct coredump_params *cprm, int align)
 {
-	unsigned mod = cprm->file->f_pos & (align - 1);
+	unsigned mod = cprm->pos & (align - 1);
 	if (align & (align - 1))
 		return 0;
 	return mod ? dump_skip(cprm, align - mod) : 1;
diff --git a/fs/dcache.c b/fs/dcache.c
index ad4a542e9bab..d6847d7b123d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -507,6 +507,44 @@ void d_drop(struct dentry *dentry)
 }
 EXPORT_SYMBOL(d_drop);
 
+static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent)
+{
+	struct dentry *next;
+	/*
+	 * Inform d_walk() and shrink_dentry_list() that we are no longer
+	 * attached to the dentry tree
+	 */
+	dentry->d_flags |= DCACHE_DENTRY_KILLED;
+	if (unlikely(list_empty(&dentry->d_child)))
+		return;
+	__list_del_entry(&dentry->d_child);
+	/*
+	 * Cursors can move around the list of children.  While we'd been
+	 * a normal list member, it didn't matter - ->d_child.next would've
+	 * been updated.  However, from now on it won't be and for the
+	 * things like d_walk() it might end up with a nasty surprise.
+	 * Normally d_walk() doesn't care about cursors moving around -
+	 * ->d_lock on parent prevents that and since a cursor has no children
+	 * of its own, we get through it without ever unlocking the parent.
+	 * There is one exception, though - if we ascend from a child that
+	 * gets killed as soon as we unlock it, the next sibling is found
+	 * using the value left in its ->d_child.next.  And if _that_
+	 * pointed to a cursor, and cursor got moved (e.g. by lseek())
+	 * before d_walk() regains parent->d_lock, we'll end up skipping
+	 * everything the cursor had been moved past.
+	 *
+	 * Solution: make sure that the pointer left behind in ->d_child.next
+	 * points to something that won't be moving around.  I.e. skip the
+	 * cursors.
+	 */
+	while (dentry->d_child.next != &parent->d_subdirs) {
+		next = list_entry(dentry->d_child.next, struct dentry, d_child);
+		if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR)))
+			break;
+		dentry->d_child.next = next->d_child.next;
+	}
+}
+
 static void __dentry_kill(struct dentry *dentry)
 {
 	struct dentry *parent = NULL;
@@ -532,12 +570,7 @@ static void __dentry_kill(struct dentry *dentry)
 	}
 	/* if it was on the hash then remove it */
 	__d_drop(dentry);
-	__list_del_entry(&dentry->d_child);
-	/*
-	 * Inform d_walk() that we are no longer attached to the
-	 * dentry tree
-	 */
-	dentry->d_flags |= DCACHE_DENTRY_KILLED;
+	dentry_unlist(dentry, parent);
 	if (parent)
 		spin_unlock(&parent->d_lock);
 	dentry_iput(dentry);
@@ -1203,6 +1236,9 @@ resume:
 		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
 		next = tmp->next;
 
+		if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR))
+			continue;
+
 		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
 
 		ret = enter(data, dentry);
@@ -1636,7 +1672,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
 	struct dentry *dentry = __d_alloc(parent->d_sb, name);
 	if (!dentry)
 		return NULL;
-
+	dentry->d_flags |= DCACHE_RCUACCESS;
 	spin_lock(&parent->d_lock);
 	/*
 	 * don't need child lock because it is not subject
@@ -1651,6 +1687,16 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
 }
 EXPORT_SYMBOL(d_alloc);
 
+struct dentry *d_alloc_cursor(struct dentry * parent)
+{
+	struct dentry *dentry = __d_alloc(parent->d_sb, NULL);
+	if (dentry) {
+		dentry->d_flags |= DCACHE_RCUACCESS | DCACHE_DENTRY_CURSOR;
+		dentry->d_parent = dget(parent);
+	}
+	return dentry;
+}
+
 /**
  * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems)
  * @sb: the superblock
@@ -2358,7 +2404,6 @@ static void __d_rehash(struct dentry * entry, struct hlist_bl_head *b)
 {
 	BUG_ON(!d_unhashed(entry));
 	hlist_bl_lock(b);
-	entry->d_flags |= DCACHE_RCUACCESS;
 	hlist_bl_add_head_rcu(&entry->d_hash, b);
 	hlist_bl_unlock(b);
 }
@@ -2458,7 +2503,6 @@ retry:
 		rcu_read_unlock();
 		goto retry;
 	}
-	rcu_read_unlock();
 	/*
 	 * No changes for the parent since the beginning of d_lookup().
 	 * Since all removals from the chain happen with hlist_bl_lock(),
@@ -2471,8 +2515,6 @@ retry:
 			continue;
 		if (dentry->d_parent != parent)
 			continue;
-		if (d_unhashed(dentry))
-			continue;
 		if (parent->d_flags & DCACHE_OP_COMPARE) {
 			int tlen = dentry->d_name.len;
 			const char *tname = dentry->d_name.name;
@@ -2484,9 +2526,18 @@ retry:
 			if (dentry_cmp(dentry, str, len))
 				continue;
 		}
-		dget(dentry);
 		hlist_bl_unlock(b);
-		/* somebody is doing lookup for it right now; wait for it */
+		/* now we can try to grab a reference */
+		if (!lockref_get_not_dead(&dentry->d_lockref)) {
+			rcu_read_unlock();
+			goto retry;
+		}
+
+		rcu_read_unlock();
+		/*
+		 * somebody is likely to be still doing lookup for it;
+		 * wait for them to finish
+		 */
 		spin_lock(&dentry->d_lock);
 		d_wait_lookup(dentry);
 		/*
@@ -2517,6 +2568,7 @@ retry:
 		dput(new);
 		return dentry;
 	}
+	rcu_read_unlock();
 	/* we can't take ->d_lock here; it's OK, though. */
 	new->d_flags |= DCACHE_PAR_LOOKUP;
 	new->d_wait = wq;
@@ -2843,6 +2895,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	/* ... and switch them in the tree */
 	if (IS_ROOT(dentry)) {
 		/* splicing a tree */
+		dentry->d_flags |= DCACHE_RCUACCESS;
 		dentry->d_parent = target->d_parent;
 		target->d_parent = target;
 		list_del_init(&target->d_child);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 9c1c9a01b7e5..592059f88e04 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -127,7 +127,6 @@ static int open_proxy_open(struct inode *inode, struct file *filp)
 		r = real_fops->open(inode, filp);
 
 out:
-	fops_put(real_fops);
 	debugfs_use_file_finish(srcu_idx);
 	return r;
 }
@@ -262,8 +261,10 @@ static int full_proxy_open(struct inode *inode, struct file *filp)
 
 	if (real_fops->open) {
 		r = real_fops->open(inode, filp);
-
-		if (filp->f_op != proxy_fops) {
+		if (r) {
+			replace_fops(filp, d_inode(dentry)->i_fop);
+			goto free_proxy;
+		} else if (filp->f_op != proxy_fops) {
 			/* No protection against file removal anymore. */
 			WARN(1, "debugfs file owner replaced proxy fops: %pd",
 				dentry);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 0b2954d7172d..37c134a132c7 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -95,8 +95,6 @@ static struct ctl_table pty_root_table[] = {
 
 static DEFINE_MUTEX(allocated_ptys_lock);
 
-static struct vfsmount *devpts_mnt;
-
 struct pts_mount_opts {
 	int setuid;
 	int setgid;
@@ -104,7 +102,7 @@ struct pts_mount_opts {
 	kgid_t   gid;
 	umode_t mode;
 	umode_t ptmxmode;
-	int newinstance;
+	int reserve;
 	int max;
 };
 
@@ -117,11 +115,9 @@ static const match_table_t tokens = {
 	{Opt_uid, "uid=%u"},
 	{Opt_gid, "gid=%u"},
 	{Opt_mode, "mode=%o"},
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 	{Opt_ptmxmode, "ptmxmode=%o"},
 	{Opt_newinstance, "newinstance"},
 	{Opt_max, "max=%d"},
-#endif
 	{Opt_err, NULL}
 };
 
@@ -137,15 +133,48 @@ static inline struct pts_fs_info *DEVPTS_SB(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
-static inline struct super_block *pts_sb_from_inode(struct inode *inode)
+struct pts_fs_info *devpts_acquire(struct file *filp)
 {
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
-	if (inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC)
-		return inode->i_sb;
-#endif
-	if (!devpts_mnt)
-		return NULL;
-	return devpts_mnt->mnt_sb;
+	struct pts_fs_info *result;
+	struct path path;
+	struct super_block *sb;
+	int err;
+
+	path = filp->f_path;
+	path_get(&path);
+
+	/* Has the devpts filesystem already been found? */
+	sb = path.mnt->mnt_sb;
+	if (sb->s_magic != DEVPTS_SUPER_MAGIC) {
+		/* Is a devpts filesystem at "pts" in the same directory? */
+		err = path_pts(&path);
+		if (err) {
+			result = ERR_PTR(err);
+			goto out;
+		}
+
+		/* Is the path the root of a devpts filesystem? */
+		result = ERR_PTR(-ENODEV);
+		sb = path.mnt->mnt_sb;
+		if ((sb->s_magic != DEVPTS_SUPER_MAGIC) ||
+		    (path.mnt->mnt_root != sb->s_root))
+			goto out;
+	}
+
+	/*
+	 * pty code needs to hold extra references in case of last /dev/tty close
+	 */
+	atomic_inc(&sb->s_active);
+	result = DEVPTS_SB(sb);
+
+out:
+	path_put(&path);
+	return result;
+}
+
+void devpts_release(struct pts_fs_info *fsi)
+{
+	deactivate_super(fsi->sb);
 }
 
 #define PARSE_MOUNT	0
@@ -154,9 +183,7 @@ static inline struct super_block *pts_sb_from_inode(struct inode *inode)
 /*
  * parse_mount_options():
  *	Set @opts to mount options specified in @data. If an option is not
- *	specified in @data, set it to its default value. The exception is
- *	'newinstance' option which can only be set/cleared on a mount (i.e.
- *	cannot be changed during remount).
+ *	specified in @data, set it to its default value.
  *
  * Note: @data may be NULL (in which case all options are set to default).
  */
@@ -174,9 +201,12 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
 	opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
 	opts->max     = NR_UNIX98_PTY_MAX;
 
-	/* newinstance makes sense only on initial mount */
+	/* Only allow instances mounted from the initial mount
+	 * namespace to tap the reserve pool of ptys.
+	 */
 	if (op == PARSE_MOUNT)
-		opts->newinstance = 0;
+		opts->reserve =
+			(current->nsproxy->mnt_ns == init_task.nsproxy->mnt_ns);
 
 	while ((p = strsep(&data, ",")) != NULL) {
 		substring_t args[MAX_OPT_ARGS];
@@ -211,16 +241,12 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
 				return -EINVAL;
 			opts->mode = option & S_IALLUGO;
 			break;
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 		case Opt_ptmxmode:
 			if (match_octal(&args[0], &option))
 				return -EINVAL;
 			opts->ptmxmode = option & S_IALLUGO;
 			break;
 		case Opt_newinstance:
-			/* newinstance makes sense only on initial mount */
-			if (op == PARSE_MOUNT)
-				opts->newinstance = 1;
 			break;
 		case Opt_max:
 			if (match_int(&args[0], &option) ||
@@ -228,7 +254,6 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
 				return -EINVAL;
 			opts->max = option;
 			break;
-#endif
 		default:
 			pr_err("called with bogus options\n");
 			return -EINVAL;
@@ -238,7 +263,6 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
 	return 0;
 }
 
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 static int mknod_ptmx(struct super_block *sb)
 {
 	int mode;
@@ -305,12 +329,6 @@ static void update_ptmx_mode(struct pts_fs_info *fsi)
 		inode->i_mode = S_IFCHR|fsi->mount_opts.ptmxmode;
 	}
 }
-#else
-static inline void update_ptmx_mode(struct pts_fs_info *fsi)
-{
-	return;
-}
-#endif
 
 static int devpts_remount(struct super_block *sb, int *flags, char *data)
 {
@@ -344,11 +362,9 @@ static int devpts_show_options(struct seq_file *seq, struct dentry *root)
 		seq_printf(seq, ",gid=%u",
 			   from_kgid_munged(&init_user_ns, opts->gid));
 	seq_printf(seq, ",mode=%03o", opts->mode);
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 	seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode);
 	if (opts->max < NR_UNIX98_PTY_MAX)
 		seq_printf(seq, ",max=%d", opts->max);
-#endif
 
 	return 0;
 }
@@ -410,40 +426,11 @@ fail:
 	return -ENOMEM;
 }
 
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
-static int compare_init_pts_sb(struct super_block *s, void *p)
-{
-	if (devpts_mnt)
-		return devpts_mnt->mnt_sb == s;
-	return 0;
-}
-
 /*
  * devpts_mount()
  *
- *     If the '-o newinstance' mount option was specified, mount a new
- *     (private) instance of devpts.  PTYs created in this instance are
- *     independent of the PTYs in other devpts instances.
- *
- *     If the '-o newinstance' option was not specified, mount/remount the
- *     initial kernel mount of devpts.  This type of mount gives the
- *     legacy, single-instance semantics.
- *
- *     The 'newinstance' option is needed to support multiple namespace
- *     semantics in devpts while preserving backward compatibility of the
- *     current 'single-namespace' semantics. i.e all mounts of devpts
- *     without the 'newinstance' mount option should bind to the initial
- *     kernel mount, like mount_single().
- *
- *     Mounts with 'newinstance' option create a new, private namespace.
- *
- *     NOTE:
- *
- *     For single-mount semantics, devpts cannot use mount_single(),
- *     because mount_single()/sget() find and use the super-block from
- *     the most recent mount of devpts. But that recent mount may be a
- *     'newinstance' mount and mount_single() would pick the newinstance
- *     super-block instead of the initial super-block.
+ *     Mount a new (private) instance of devpts.  PTYs created in this
+ *     instance are independent of the PTYs in other devpts instances.
  */
 static struct dentry *devpts_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
@@ -456,18 +443,7 @@ static struct dentry *devpts_mount(struct file_system_type *fs_type,
 	if (error)
 		return ERR_PTR(error);
 
-	/* Require newinstance for all user namespace mounts to ensure
-	 * the mount options are not changed.
-	 */
-	if ((current_user_ns() != &init_user_ns) && !opts.newinstance)
-		return ERR_PTR(-EINVAL);
-
-	if (opts.newinstance)
-		s = sget(fs_type, NULL, set_anon_super, flags, NULL);
-	else
-		s = sget(fs_type, compare_init_pts_sb, set_anon_super, flags,
-			 NULL);
-
+	s = sget(fs_type, NULL, set_anon_super, flags, NULL);
 	if (IS_ERR(s))
 		return ERR_CAST(s);
 
@@ -491,18 +467,6 @@ out_undo_sget:
 	return ERR_PTR(error);
 }
 
-#else
-/*
- * This supports only the legacy single-instance semantics (no
- * multiple-instance semantics)
- */
-static struct dentry *devpts_mount(struct file_system_type *fs_type, int flags,
-		const char *dev_name, void *data)
-{
-	return mount_single(fs_type, flags, data, devpts_fill_super);
-}
-#endif
-
 static void devpts_kill_sb(struct super_block *sb)
 {
 	struct pts_fs_info *fsi = DEVPTS_SB(sb);
@@ -516,9 +480,7 @@ static struct file_system_type devpts_fs_type = {
 	.name		= "devpts",
 	.mount		= devpts_mount,
 	.kill_sb	= devpts_kill_sb,
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 	.fs_flags	= FS_USERNS_MOUNT | FS_USERNS_DEV_MOUNT,
-#endif
 };
 
 /*
@@ -531,16 +493,13 @@ int devpts_new_index(struct pts_fs_info *fsi)
 	int index;
 	int ida_ret;
 
-	if (!fsi)
-		return -ENODEV;
-
 retry:
 	if (!ida_pre_get(&fsi->allocated_ptys, GFP_KERNEL))
 		return -ENOMEM;
 
 	mutex_lock(&allocated_ptys_lock);
-	if (pty_count >= pty_limit -
-			(fsi->mount_opts.newinstance ? pty_reserve : 0)) {
+	if (pty_count >= (pty_limit -
+			  (fsi->mount_opts.reserve ? 0 : pty_reserve))) {
 		mutex_unlock(&allocated_ptys_lock);
 		return -ENOSPC;
 	}
@@ -571,30 +530,6 @@ void devpts_kill_index(struct pts_fs_info *fsi, int idx)
 	mutex_unlock(&allocated_ptys_lock);
 }
 
-/*
- * pty code needs to hold extra references in case of last /dev/tty close
- */
-struct pts_fs_info *devpts_get_ref(struct inode *ptmx_inode, struct file *file)
-{
-	struct super_block *sb;
-	struct pts_fs_info *fsi;
-
-	sb = pts_sb_from_inode(ptmx_inode);
-	if (!sb)
-		return NULL;
-	fsi = DEVPTS_SB(sb);
-	if (!fsi)
-		return NULL;
-
-	atomic_inc(&sb->s_active);
-	return fsi;
-}
-
-void devpts_put_ref(struct pts_fs_info *fsi)
-{
-	deactivate_super(fsi->sb);
-}
-
 /**
  * devpts_pty_new -- create a new inode in /dev/pts/
  * @ptmx_inode: inode of the master
@@ -607,16 +542,12 @@ void devpts_put_ref(struct pts_fs_info *fsi)
 struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv)
 {
 	struct dentry *dentry;
-	struct super_block *sb;
+	struct super_block *sb = fsi->sb;
 	struct inode *inode;
 	struct dentry *root;
 	struct pts_mount_opts *opts;
 	char s[12];
 
-	if (!fsi)
-		return ERR_PTR(-ENODEV);
-
-	sb = fsi->sb;
 	root = sb->s_root;
 	opts = &fsi->mount_opts;
 
@@ -676,20 +607,8 @@ void devpts_pty_kill(struct dentry *dentry)
 static int __init init_devpts_fs(void)
 {
 	int err = register_filesystem(&devpts_fs_type);
-	struct ctl_table_header *table;
-
 	if (!err) {
-		struct vfsmount *mnt;
-
-		table = register_sysctl_table(pty_root_table);
-		mnt = kern_mount(&devpts_fs_type);
-		if (IS_ERR(mnt)) {
-			err = PTR_ERR(mnt);
-			unregister_filesystem(&devpts_fs_type);
-			unregister_sysctl_table(table);
-		} else {
-			devpts_mnt = mnt;
-		}
+		register_sysctl_table(pty_root_table);
 	}
 	return err;
 }
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
index 866bb18efefe..e818f5ac7a26 100644
--- a/fs/ecryptfs/kthread.c
+++ b/fs/ecryptfs/kthread.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/wait.h>
 #include <linux/mount.h>
+#include <linux/file.h>
 #include "ecryptfs_kernel.h"
 
 struct ecryptfs_open_req {
@@ -147,7 +148,7 @@ int ecryptfs_privileged_open(struct file **lower_file,
 	flags |= IS_RDONLY(d_inode(lower_dentry)) ? O_RDONLY : O_RDWR;
 	(*lower_file) = dentry_open(&req.path, flags, cred);
 	if (!IS_ERR(*lower_file))
-		goto out;
+		goto have_file;
 	if ((flags & O_ACCMODE) == O_RDONLY) {
 		rc = PTR_ERR((*lower_file));
 		goto out;
@@ -165,8 +166,16 @@ int ecryptfs_privileged_open(struct file **lower_file,
 	mutex_unlock(&ecryptfs_kthread_ctl.mux);
 	wake_up(&ecryptfs_kthread_ctl.wait);
 	wait_for_completion(&req.done);
-	if (IS_ERR(*lower_file))
+	if (IS_ERR(*lower_file)) {
 		rc = PTR_ERR(*lower_file);
+		goto out;
+	}
+have_file:
+	if ((*lower_file)->f_op->mmap == NULL) {
+		fput(*lower_file);
+		*lower_file = NULL;
+		rc = -EMEDIUMTYPE;
+	}
 out:
 	return rc;
 }
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 3078b679fcd1..c8c4f79c7ce1 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -887,6 +887,8 @@ void fscache_invalidate_writes(struct fscache_cookie *cookie)
 			put_page(results[i]);
 	}
 
+	wake_up_bit(&cookie->flags, 0);
+
 	_leave("");
 }
 
diff --git a/fs/internal.h b/fs/internal.h
index b71deeecea17..f57ced528cde 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -130,6 +130,7 @@ extern int invalidate_inodes(struct super_block *, bool);
 extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
 extern int d_set_mounted(struct dentry *dentry);
 extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc);
+extern struct dentry *d_alloc_cursor(struct dentry *);
 
 /*
  * read_write.c
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index b31852f76f46..e3ca4b4cac84 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -2329,18 +2329,10 @@ void *jbd2_alloc(size_t size, gfp_t flags)
 
 	BUG_ON(size & (size-1)); /* Must be a power of 2 */
 
-	flags |= __GFP_REPEAT;
-	if (size == PAGE_SIZE)
-		ptr = (void *)__get_free_pages(flags, 0);
-	else if (size > PAGE_SIZE) {
-		int order = get_order(size);
-
-		if (order < 3)
-			ptr = (void *)__get_free_pages(flags, order);
-		else
-			ptr = vmalloc(size);
-	} else
+	if (size < PAGE_SIZE)
 		ptr = kmem_cache_alloc(get_slab(size), flags);
+	else
+		ptr = (void *)__get_free_pages(flags, get_order(size));
 
 	/* Check alignment; SLUB has gotten this wrong in the past,
 	 * and this can lead to user data corruption! */
@@ -2351,20 +2343,10 @@ void *jbd2_alloc(size_t size, gfp_t flags)
 
 void jbd2_free(void *ptr, size_t size)
 {
-	if (size == PAGE_SIZE) {
-		free_pages((unsigned long)ptr, 0);
-		return;
-	}
-	if (size > PAGE_SIZE) {
-		int order = get_order(size);
-
-		if (order < 3)
-			free_pages((unsigned long)ptr, order);
-		else
-			vfree(ptr);
-		return;
-	}
-	kmem_cache_free(get_slab(size), ptr);
+	if (size < PAGE_SIZE)
+		kmem_cache_free(get_slab(size), ptr);
+	else
+		free_pages((unsigned long)ptr, get_order(size));
 };
 
 /*
diff --git a/fs/libfs.c b/fs/libfs.c
index 3db2721144c2..cedeacbae303 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -71,9 +71,7 @@ EXPORT_SYMBOL(simple_lookup);
 
 int dcache_dir_open(struct inode *inode, struct file *file)
 {
-	static struct qstr cursor_name = QSTR_INIT(".", 1);
-
-	file->private_data = d_alloc(file->f_path.dentry, &cursor_name);
+	file->private_data = d_alloc_cursor(file->f_path.dentry);
 
 	return file->private_data ? 0 : -ENOMEM;
 }
diff --git a/fs/namei.c b/fs/namei.c
index 4c4f95ac8aa5..70580ab1445c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1416,21 +1416,28 @@ static void follow_mount(struct path *path)
 	}
 }
 
+static int path_parent_directory(struct path *path)
+{
+	struct dentry *old = path->dentry;
+	/* rare case of legitimate dget_parent()... */
+	path->dentry = dget_parent(path->dentry);
+	dput(old);
+	if (unlikely(!path_connected(path)))
+		return -ENOENT;
+	return 0;
+}
+
 static int follow_dotdot(struct nameidata *nd)
 {
 	while(1) {
-		struct dentry *old = nd->path.dentry;
-
 		if (nd->path.dentry == nd->root.dentry &&
 		    nd->path.mnt == nd->root.mnt) {
 			break;
 		}
 		if (nd->path.dentry != nd->path.mnt->mnt_root) {
-			/* rare case of legitimate dget_parent()... */
-			nd->path.dentry = dget_parent(nd->path.dentry);
-			dput(old);
-			if (unlikely(!path_connected(&nd->path)))
-				return -ENOENT;
+			int ret = path_parent_directory(&nd->path);
+			if (ret)
+				return ret;
 			break;
 		}
 		if (!follow_up(&nd->path))
@@ -2514,6 +2521,34 @@ struct dentry *lookup_one_len_unlocked(const char *name,
 }
 EXPORT_SYMBOL(lookup_one_len_unlocked);
 
+#ifdef CONFIG_UNIX98_PTYS
+int path_pts(struct path *path)
+{
+	/* Find something mounted on "pts" in the same directory as
+	 * the input path.
+	 */
+	struct dentry *child, *parent;
+	struct qstr this;
+	int ret;
+
+	ret = path_parent_directory(path);
+	if (ret)
+		return ret;
+
+	parent = path->dentry;
+	this.name = "pts";
+	this.len = 3;
+	child = d_hash_and_lookup(parent, &this);
+	if (!child)
+		return -ENOENT;
+
+	path->dentry = child;
+	dput(parent);
+	follow_mount(path);
+	return 0;
+}
+#endif
+
 int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
 		 struct path *path, int *empty)
 {
@@ -2995,9 +3030,13 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 			}
 			if (*opened & FILE_CREATED)
 				fsnotify_create(dir, dentry);
-			path->dentry = dentry;
-			path->mnt = nd->path.mnt;
-			return 1;
+			if (unlikely(d_is_negative(dentry))) {
+				error = -ENOENT;
+			} else {
+				path->dentry = dentry;
+				path->mnt = nd->path.mnt;
+				return 1;
+			}
 		}
 	}
 	dput(dentry);
@@ -3166,9 +3205,7 @@ static int do_last(struct nameidata *nd,
 	int acc_mode = op->acc_mode;
 	unsigned seq;
 	struct inode *inode;
-	struct path save_parent = { .dentry = NULL, .mnt = NULL };
 	struct path path;
-	bool retried = false;
 	int error;
 
 	nd->flags &= ~LOOKUP_PARENT;
@@ -3211,7 +3248,6 @@ static int do_last(struct nameidata *nd,
 			return -EISDIR;
 	}
 
-retry_lookup:
 	if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
 		error = mnt_want_write(nd->path.mnt);
 		if (!error)
@@ -3263,6 +3299,10 @@ retry_lookup:
 		got_write = false;
 	}
 
+	error = follow_managed(&path, nd);
+	if (unlikely(error < 0))
+		return error;
+
 	if (unlikely(d_is_negative(path.dentry))) {
 		path_to_nameidata(&path, nd);
 		return -ENOENT;
@@ -3278,10 +3318,6 @@ retry_lookup:
 		return -EEXIST;
 	}
 
-	error = follow_managed(&path, nd);
-	if (unlikely(error < 0))
-		return error;
-
 	seq = 0;	/* out of RCU mode, so the value doesn't matter */
 	inode = d_backing_inode(path.dentry);
 finish_lookup:
@@ -3292,23 +3328,14 @@ finish_lookup:
 	if (unlikely(error))
 		return error;
 
-	if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) {
-		path_to_nameidata(&path, nd);
-	} else {
-		save_parent.dentry = nd->path.dentry;
-		save_parent.mnt = mntget(path.mnt);
-		nd->path.dentry = path.dentry;
-
-	}
+	path_to_nameidata(&path, nd);
 	nd->inode = inode;
 	nd->seq = seq;
 	/* Why this, you ask?  _Now_ we might have grown LOOKUP_JUMPED... */
 finish_open:
 	error = complete_walk(nd);
-	if (error) {
-		path_put(&save_parent);
+	if (error)
 		return error;
-	}
 	audit_inode(nd->name, nd->path.dentry, 0);
 	error = -EISDIR;
 	if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
@@ -3331,13 +3358,9 @@ finish_open_created:
 		goto out;
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 	error = vfs_open(&nd->path, file, current_cred());
-	if (!error) {
-		*opened |= FILE_OPENED;
-	} else {
-		if (error == -EOPENSTALE)
-			goto stale_open;
+	if (error)
 		goto out;
-	}
+	*opened |= FILE_OPENED;
 opened:
 	error = open_check_o_direct(file);
 	if (!error)
@@ -3353,26 +3376,7 @@ out:
 	}
 	if (got_write)
 		mnt_drop_write(nd->path.mnt);
-	path_put(&save_parent);
 	return error;
-
-stale_open:
-	/* If no saved parent or already retried then can't retry */
-	if (!save_parent.dentry || retried)
-		goto out;
-
-	BUG_ON(save_parent.dentry != dir);
-	path_put(&nd->path);
-	nd->path = save_parent;
-	nd->inode = dir->d_inode;
-	save_parent.mnt = NULL;
-	save_parent.dentry = NULL;
-	if (got_write) {
-		mnt_drop_write(nd->path.mnt);
-		got_write = false;
-	}
-	retried = true;
-	goto retry_lookup;
 }
 
 static int do_tmpfile(struct nameidata *nd, unsigned flags,
diff --git a/fs/namespace.c b/fs/namespace.c
index 4fb1691b4355..783004af5707 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2409,8 +2409,10 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
 			mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
 		}
 		if (type->fs_flags & FS_USERNS_VISIBLE) {
-			if (!fs_fully_visible(type, &mnt_flags))
+			if (!fs_fully_visible(type, &mnt_flags)) {
+				put_filesystem(type);
 				return -EPERM;
+			}
 		}
 	}
 
@@ -3245,6 +3247,10 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
 		if (mnt->mnt.mnt_sb->s_iflags & SB_I_NOEXEC)
 			mnt_flags &= ~(MNT_LOCK_NOSUID | MNT_LOCK_NOEXEC);
 
+		/* Don't miss readonly hidden in the superblock flags */
+		if (mnt->mnt.mnt_sb->s_flags & MS_RDONLY)
+			mnt_flags |= MNT_LOCK_READONLY;
+
 		/* Verify the mount flags are equal to or more permissive
 		 * than the proposed new mount.
 		 */
@@ -3271,7 +3277,7 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
 		list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
 			struct inode *inode = child->mnt_mountpoint->d_inode;
 			/* Only worry about locked mounts */
-			if (!(mnt_flags & MNT_LOCKED))
+			if (!(child->mnt.mnt_flags & MNT_LOCKED))
 				continue;
 			/* Is the directory permanetly empty? */
 			if (!is_empty_dir_inode(inode))
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index aaf7bd0cbae2..d8015a03db4c 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -424,12 +424,17 @@ static int xdr_decode(nfs_readdir_descriptor_t *desc,
 static
 int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
 {
+	struct inode *inode;
 	struct nfs_inode *nfsi;
 
 	if (d_really_is_negative(dentry))
 		return 0;
 
-	nfsi = NFS_I(d_inode(dentry));
+	inode = d_inode(dentry);
+	if (is_bad_inode(inode) || NFS_STALE(inode))
+		return 0;
+
+	nfsi = NFS_I(inode);
 	if (entry->fattr->fileid == nfsi->fileid)
 		return 1;
 	if (nfs_compare_fh(entry->fh, &nfsi->fh) == 0)
@@ -1363,7 +1368,6 @@ EXPORT_SYMBOL_GPL(nfs_dentry_operations);
 struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
 	struct dentry *res;
-	struct dentry *parent;
 	struct inode *inode = NULL;
 	struct nfs_fh *fhandle = NULL;
 	struct nfs_fattr *fattr = NULL;
@@ -1393,7 +1397,6 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
 	if (IS_ERR(label))
 		goto out;
 
-	parent = dentry->d_parent;
 	/* Protect against concurrent sillydeletes */
 	trace_nfs_lookup_enter(dir, dentry, flags);
 	error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
@@ -1536,9 +1539,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		err = PTR_ERR(inode);
 		trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
 		put_nfs_open_context(ctx);
+		d_drop(dentry);
 		switch (err) {
 		case -ENOENT:
-			d_drop(dentry);
 			d_add(dentry, NULL);
 			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 			break;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 979b3c4dee6a..c7326c2af2c3 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -353,10 +353,12 @@ static ssize_t nfs_direct_wait(struct nfs_direct_req *dreq)
 
 	result = wait_for_completion_killable(&dreq->completion);
 
+	if (!result) {
+		result = dreq->count;
+		WARN_ON_ONCE(dreq->count < 0);
+	}
 	if (!result)
 		result = dreq->error;
-	if (!result)
-		result = dreq->count;
 
 out:
 	return (ssize_t) result;
@@ -386,8 +388,10 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
 
 	if (dreq->iocb) {
 		long res = (long) dreq->error;
-		if (!res)
+		if (dreq->count != 0) {
 			res = (long) dreq->count;
+			WARN_ON_ONCE(dreq->count < 0);
+		}
 		dreq->iocb->ki_complete(dreq->iocb, res, 0);
 	}
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 52e7d6869e3b..dda689d7a8a7 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -282,6 +282,7 @@ nfs_init_locked(struct inode *inode, void *opaque)
 	struct nfs_fattr	*fattr = desc->fattr;
 
 	set_nfs_fileid(inode, fattr->fileid);
+	inode->i_mode = fattr->mode;
 	nfs_copy_fh(NFS_FH(inode), desc->fh);
 	return 0;
 }
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index de97567795a5..ff416d0e24bc 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2882,12 +2882,11 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 			call_close |= is_wronly;
 		else if (is_wronly)
 			calldata->arg.fmode |= FMODE_WRITE;
+		if (calldata->arg.fmode != (FMODE_READ|FMODE_WRITE))
+			call_close |= is_rdwr;
 	} else if (is_rdwr)
 		calldata->arg.fmode |= FMODE_READ|FMODE_WRITE;
 
-	if (calldata->arg.fmode == 0)
-		call_close |= is_rdwr;
-
 	if (!nfs4_valid_open_stateid(state))
 		call_close = 0;
 	spin_unlock(&state->owner->so_lock);
@@ -7924,8 +7923,8 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 			break;
 		}
 		lo = NFS_I(inode)->layout;
-		if (lo && nfs4_stateid_match(&lgp->args.stateid,
-					&lo->plh_stateid)) {
+		if (lo && !test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) &&
+		    nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) {
 			LIST_HEAD(head);
 
 			/*
@@ -7936,10 +7935,10 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 			pnfs_mark_matching_lsegs_invalid(lo, &head, NULL, 0);
 			spin_unlock(&inode->i_lock);
 			pnfs_free_lseg_list(&head);
+			status = -EAGAIN;
+			goto out;
 		} else
 			spin_unlock(&inode->i_lock);
-		status = -EAGAIN;
-		goto out;
 	}
 
 	status = nfs4_handle_exception(server, status, exception);
@@ -8036,7 +8035,10 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags)
 		.flags = RPC_TASK_ASYNC,
 	};
 	struct pnfs_layout_segment *lseg = NULL;
-	struct nfs4_exception exception = { .timeout = *timeout };
+	struct nfs4_exception exception = {
+		.inode = inode,
+		.timeout = *timeout,
+	};
 	int status = 0;
 
 	dprintk("--> %s\n", __func__);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9679f4749364..834b875900d6 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1488,9 +1488,9 @@ restart:
 					}
 					spin_unlock(&state->state_lock);
 				}
-				nfs4_put_open_state(state);
 				clear_bit(NFS_STATE_RECLAIM_NOGRACE,
 					&state->flags);
+				nfs4_put_open_state(state);
 				spin_lock(&sp->so_lock);
 				goto restart;
 			}
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 0c7e0d45a4de..0fbe734cc38c 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -361,8 +361,10 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
 	list_del_init(&lseg->pls_list);
 	/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
 	atomic_dec(&lo->plh_refcount);
-	if (list_empty(&lo->plh_segs))
+	if (list_empty(&lo->plh_segs)) {
+		set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
 		clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
+	}
 	rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
 }
 
@@ -1290,6 +1292,7 @@ alloc_init_layout_hdr(struct inode *ino,
 	INIT_LIST_HEAD(&lo->plh_bulk_destroy);
 	lo->plh_inode = ino;
 	lo->plh_lc_cred = get_rpccred(ctx->cred);
+	lo->plh_flags |= 1 << NFS_LAYOUT_INVALID_STID;
 	return lo;
 }
 
@@ -1297,6 +1300,8 @@ static struct pnfs_layout_hdr *
 pnfs_find_alloc_layout(struct inode *ino,
 		       struct nfs_open_context *ctx,
 		       gfp_t gfp_flags)
+	__releases(&ino->i_lock)
+	__acquires(&ino->i_lock)
 {
 	struct nfs_inode *nfsi = NFS_I(ino);
 	struct pnfs_layout_hdr *new = NULL;
@@ -1565,8 +1570,7 @@ lookup_again:
 	 * stateid, or it has been invalidated, then we must use the open
 	 * stateid.
 	 */
-	if (lo->plh_stateid.seqid == 0 ||
-	    test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
+	if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
 
 		/*
 		 * The first layoutget for the file. Need to serialize per
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 0dfc476da3e1..b38e3c0dc790 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -247,7 +247,11 @@ void pnfs_fetch_commit_bucket_list(struct list_head *pages,
 }
 
 /* Helper function for pnfs_generic_commit_pagelist to catch an empty
- * page list. This can happen when two commits race. */
+ * page list. This can happen when two commits race.
+ *
+ * This must be called instead of nfs_init_commit - call one or the other, but
+ * not both!
+ */
 static bool
 pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages,
 					  struct nfs_commit_data *data,
@@ -256,7 +260,11 @@ pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages,
 	if (list_empty(pages)) {
 		if (atomic_dec_and_test(&cinfo->mds->rpcs_out))
 			wake_up_atomic_t(&cinfo->mds->rpcs_out);
-		nfs_commitdata_release(data);
+		/* don't call nfs_commitdata_release - it tries to put
+		 * the open_context which is not acquired until nfs_init_commit
+		 * which has not been called on @data */
+		WARN_ON_ONCE(data->context);
+		nfs_commit_free(data);
 		return true;
 	}
 
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 6776d7a7839e..572e5b3b06f1 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -367,13 +367,13 @@ readpage_async_filler(void *data, struct page *page)
 		nfs_list_remove_request(new);
 		nfs_readpage_release(new);
 		error = desc->pgio->pg_error;
-		goto out_unlock;
+		goto out;
 	}
 	return 0;
 out_error:
 	error = PTR_ERR(new);
-out_unlock:
 	unlock_page(page);
+out:
 	return error;
 }
 
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index e55b5242614d..31f3df193bdb 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -290,7 +290,7 @@ out_free_buf:
 	return error;
 }
 
-#define NFSD_MDS_PR_KEY		0x0100000000000000
+#define NFSD_MDS_PR_KEY		0x0100000000000000ULL
 
 /*
  * We use the client ID as a unique key for the reservations.
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 1580ea6fd64d..d08cd88155c7 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -104,22 +104,21 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
 		goto out;
 
 	inode = d_inode(fh->fh_dentry);
-	if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
-		error = -EOPNOTSUPP;
-		goto out_errno;
-	}
 
 	error = fh_want_write(fh);
 	if (error)
 		goto out_errno;
 
-	error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+	fh_lock(fh);
+
+	error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
 	if (error)
-		goto out_drop_write;
-	error = inode->i_op->set_acl(inode, argp->acl_default,
-				     ACL_TYPE_DEFAULT);
+		goto out_drop_lock;
+	error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
 	if (error)
-		goto out_drop_write;
+		goto out_drop_lock;
+
+	fh_unlock(fh);
 
 	fh_drop_write(fh);
 
@@ -131,7 +130,8 @@ out:
 	posix_acl_release(argp->acl_access);
 	posix_acl_release(argp->acl_default);
 	return nfserr;
-out_drop_write:
+out_drop_lock:
+	fh_unlock(fh);
 	fh_drop_write(fh);
 out_errno:
 	nfserr = nfserrno(error);
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 01df4cd7c753..0c890347cde3 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -95,22 +95,20 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp,
 		goto out;
 
 	inode = d_inode(fh->fh_dentry);
-	if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
-		error = -EOPNOTSUPP;
-		goto out_errno;
-	}
 
 	error = fh_want_write(fh);
 	if (error)
 		goto out_errno;
 
-	error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+	fh_lock(fh);
+
+	error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
 	if (error)
-		goto out_drop_write;
-	error = inode->i_op->set_acl(inode, argp->acl_default,
-				     ACL_TYPE_DEFAULT);
+		goto out_drop_lock;
+	error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
 
-out_drop_write:
+out_drop_lock:
+	fh_unlock(fh);
 	fh_drop_write(fh);
 out_errno:
 	nfserr = nfserrno(error);
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 6adabd6049b7..71292a0d6f09 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -770,9 +770,6 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	dentry = fhp->fh_dentry;
 	inode = d_inode(dentry);
 
-	if (!inode->i_op->set_acl || !IS_POSIXACL(inode))
-		return nfserr_attrnotsupp;
-
 	if (S_ISDIR(inode->i_mode))
 		flags = NFS4_ACL_DIR;
 
@@ -782,16 +779,19 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (host_error < 0)
 		goto out_nfserr;
 
-	host_error = inode->i_op->set_acl(inode, pacl, ACL_TYPE_ACCESS);
+	fh_lock(fhp);
+
+	host_error = set_posix_acl(inode, ACL_TYPE_ACCESS, pacl);
 	if (host_error < 0)
-		goto out_release;
+		goto out_drop_lock;
 
 	if (S_ISDIR(inode->i_mode)) {
-		host_error = inode->i_op->set_acl(inode, dpacl,
-						  ACL_TYPE_DEFAULT);
+		host_error = set_posix_acl(inode, ACL_TYPE_DEFAULT, dpacl);
 	}
 
-out_release:
+out_drop_lock:
+	fh_unlock(fhp);
+
 	posix_acl_release(pacl);
 	posix_acl_release(dpacl);
 out_nfserr:
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7389cb1d7409..04c68d900324 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -710,22 +710,6 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc
 	}
 }
 
-static struct rpc_clnt *create_backchannel_client(struct rpc_create_args *args)
-{
-	struct rpc_xprt *xprt;
-
-	if (args->protocol != XPRT_TRANSPORT_BC_TCP)
-		return rpc_create(args);
-
-	xprt = args->bc_xprt->xpt_bc_xprt;
-	if (xprt) {
-		xprt_get(xprt);
-		return rpc_create_xprt(args, xprt);
-	}
-
-	return rpc_create(args);
-}
-
 static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
 {
 	int maxtime = max_cb_time(clp->net);
@@ -768,7 +752,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		args.authflavor = ses->se_cb_sec.flavor;
 	}
 	/* Create RPC client */
-	client = create_backchannel_client(&args);
+	client = rpc_create(&args);
 	if (IS_ERR(client)) {
 		dprintk("NFSD: couldn't create callback client: %ld\n",
 			PTR_ERR(client));
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f5f82e145018..70d0b9b33031 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3480,12 +3480,17 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
 }
 
 static struct nfs4_ol_stateid *
-init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
-		struct nfsd4_open *open)
+init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open)
 {
 
 	struct nfs4_openowner *oo = open->op_openowner;
 	struct nfs4_ol_stateid *retstp = NULL;
+	struct nfs4_ol_stateid *stp;
+
+	stp = open->op_stp;
+	/* We are moving these outside of the spinlocks to avoid the warnings */
+	mutex_init(&stp->st_mutex);
+	mutex_lock(&stp->st_mutex);
 
 	spin_lock(&oo->oo_owner.so_client->cl_lock);
 	spin_lock(&fp->fi_lock);
@@ -3493,6 +3498,8 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
 	retstp = nfsd4_find_existing_open(fp, open);
 	if (retstp)
 		goto out_unlock;
+
+	open->op_stp = NULL;
 	atomic_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_OPEN_STID;
 	INIT_LIST_HEAD(&stp->st_locks);
@@ -3502,14 +3509,19 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = 0;
 	stp->st_openstp = NULL;
-	init_rwsem(&stp->st_rwsem);
 	list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
 	list_add(&stp->st_perfile, &fp->fi_stateids);
 
 out_unlock:
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&oo->oo_owner.so_client->cl_lock);
-	return retstp;
+	if (retstp) {
+		mutex_lock(&retstp->st_mutex);
+		/* To keep mutex tracking happy */
+		mutex_unlock(&stp->st_mutex);
+		stp = retstp;
+	}
+	return stp;
 }
 
 /*
@@ -4305,7 +4317,6 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	struct nfs4_client *cl = open->op_openowner->oo_owner.so_client;
 	struct nfs4_file *fp = NULL;
 	struct nfs4_ol_stateid *stp = NULL;
-	struct nfs4_ol_stateid *swapstp = NULL;
 	struct nfs4_delegation *dp = NULL;
 	__be32 status;
 
@@ -4335,32 +4346,28 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	 */
 	if (stp) {
 		/* Stateid was found, this is an OPEN upgrade */
-		down_read(&stp->st_rwsem);
+		mutex_lock(&stp->st_mutex);
 		status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
 		if (status) {
-			up_read(&stp->st_rwsem);
+			mutex_unlock(&stp->st_mutex);
 			goto out;
 		}
 	} else {
-		stp = open->op_stp;
-		open->op_stp = NULL;
-		swapstp = init_open_stateid(stp, fp, open);
-		if (swapstp) {
-			nfs4_put_stid(&stp->st_stid);
-			stp = swapstp;
-			down_read(&stp->st_rwsem);
+		/* stp is returned locked. */
+		stp = init_open_stateid(fp, open);
+		/* See if we lost the race to some other thread */
+		if (stp->st_access_bmap != 0) {
 			status = nfs4_upgrade_open(rqstp, fp, current_fh,
 						stp, open);
 			if (status) {
-				up_read(&stp->st_rwsem);
+				mutex_unlock(&stp->st_mutex);
 				goto out;
 			}
 			goto upgrade_out;
 		}
-		down_read(&stp->st_rwsem);
 		status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
 		if (status) {
-			up_read(&stp->st_rwsem);
+			mutex_unlock(&stp->st_mutex);
 			release_open_stateid(stp);
 			goto out;
 		}
@@ -4372,7 +4379,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	}
 upgrade_out:
 	nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
-	up_read(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 
 	if (nfsd4_has_session(&resp->cstate)) {
 		if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
@@ -4977,12 +4984,12 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
 		 * revoked delegations are kept only for free_stateid.
 		 */
 		return nfserr_bad_stateid;
-	down_write(&stp->st_rwsem);
+	mutex_lock(&stp->st_mutex);
 	status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
 	if (status == nfs_ok)
 		status = nfs4_check_fh(current_fh, &stp->st_stid);
 	if (status != nfs_ok)
-		up_write(&stp->st_rwsem);
+		mutex_unlock(&stp->st_mutex);
 	return status;
 }
 
@@ -5030,7 +5037,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs
 		return status;
 	oo = openowner(stp->st_stateowner);
 	if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
-		up_write(&stp->st_rwsem);
+		mutex_unlock(&stp->st_mutex);
 		nfs4_put_stid(&stp->st_stid);
 		return nfserr_bad_stateid;
 	}
@@ -5062,12 +5069,12 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	oo = openowner(stp->st_stateowner);
 	status = nfserr_bad_stateid;
 	if (oo->oo_flags & NFS4_OO_CONFIRMED) {
-		up_write(&stp->st_rwsem);
+		mutex_unlock(&stp->st_mutex);
 		goto put_stateid;
 	}
 	oo->oo_flags |= NFS4_OO_CONFIRMED;
 	nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid);
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 	dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
 		__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));
 
@@ -5143,7 +5150,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
 	nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid);
 	status = nfs_ok;
 put_stateid:
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 	nfs4_put_stid(&stp->st_stid);
 out:
 	nfsd4_bump_seqid(cstate, status);
@@ -5196,7 +5203,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out; 
 	nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 
 	nfsd4_close_open_stateid(stp);
 
@@ -5422,7 +5429,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = open_stp->st_deny_bmap;
 	stp->st_openstp = open_stp;
-	init_rwsem(&stp->st_rwsem);
+	mutex_init(&stp->st_mutex);
 	list_add(&stp->st_locks, &open_stp->st_locks);
 	list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
 	spin_lock(&fp->fi_lock);
@@ -5591,7 +5598,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 					&open_stp, nn);
 		if (status)
 			goto out;
-		up_write(&open_stp->st_rwsem);
+		mutex_unlock(&open_stp->st_mutex);
 		open_sop = openowner(open_stp->st_stateowner);
 		status = nfserr_bad_stateid;
 		if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid,
@@ -5600,7 +5607,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = lookup_or_create_lock_state(cstate, open_stp, lock,
 							&lock_stp, &new);
 		if (status == nfs_ok)
-			down_write(&lock_stp->st_rwsem);
+			mutex_lock(&lock_stp->st_mutex);
 	} else {
 		status = nfs4_preprocess_seqid_op(cstate,
 				       lock->lk_old_lock_seqid,
@@ -5704,7 +5711,7 @@ out:
 		    seqid_mutating_err(ntohl(status)))
 			lock_sop->lo_owner.so_seqid++;
 
-		up_write(&lock_stp->st_rwsem);
+		mutex_unlock(&lock_stp->st_mutex);
 
 		/*
 		 * If this is a new, never-before-used stateid, and we are
@@ -5874,7 +5881,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 fput:
 	fput(filp);
 put_stateid:
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 	nfs4_put_stid(&stp->st_stid);
 out:
 	nfsd4_bump_seqid(cstate, status);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 986e51e5ceac..64053eadeb81 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -535,7 +535,7 @@ struct nfs4_ol_stateid {
 	unsigned char			st_access_bmap;
 	unsigned char			st_deny_bmap;
 	struct nfs4_ol_stateid		*st_openstp;
-	struct rw_semaphore		st_rwsem;
+	struct mutex			st_mutex;
 };
 
 static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 809bd2de7ad0..e9fd241b9a0a 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -439,7 +439,7 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp)
 	if (!sbp || le16_to_cpu(sbp->s_magic) != NILFS_SUPER_MAGIC)
 		return 0;
 	bytes = le16_to_cpu(sbp->s_bytes);
-	if (bytes > BLOCK_SIZE)
+	if (bytes < sumoff + 4 || bytes > BLOCK_SIZE)
 		return 0;
 	crc = crc32_le(le32_to_cpu(sbp->s_crc_seed), (unsigned char *)sbp,
 		       sumoff);
diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index e27e6527912b..4342c7ee7d20 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -1,7 +1,5 @@
 ccflags-y := -Ifs/ocfs2
 
-ccflags-y += -DCATCH_BH_JBD_RACES
-
 obj-$(CONFIG_OCFS2_FS) += 	\
 	ocfs2.o			\
 	ocfs2_stackglue.o
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index fe50ded1b4ce..498641eed2db 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -139,11 +139,16 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 
 		lock_buffer(bh);
 		if (buffer_jbd(bh)) {
+#ifdef CATCH_BH_JBD_RACES
 			mlog(ML_ERROR,
 			     "block %llu had the JBD bit set "
 			     "while I was in lock_buffer!",
 			     (unsigned long long)bh->b_blocknr);
 			BUG();
+#else
+			unlock_buffer(bh);
+			continue;
+#endif
 		}
 
 		clear_buffer_uptodate(bh);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 22f0253a3567..c2a6b0894022 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -405,12 +405,21 @@ static int ovl_create_or_link(struct dentry *dentry, int mode, dev_t rdev,
 		err = ovl_create_upper(dentry, inode, &stat, link, hardlink);
 	} else {
 		const struct cred *old_cred;
+		struct cred *override_cred;
 
 		old_cred = ovl_override_creds(dentry->d_sb);
 
-		err = ovl_create_over_whiteout(dentry, inode, &stat, link,
-					       hardlink);
+		err = -ENOMEM;
+		override_cred = prepare_creds();
+		if (override_cred) {
+			override_cred->fsuid = old_cred->fsuid;
+			override_cred->fsgid = old_cred->fsgid;
+			put_cred(override_creds(override_cred));
+			put_cred(override_cred);
 
+			err = ovl_create_over_whiteout(dentry, inode, &stat,
+						       link, hardlink);
+		}
 		revert_creds(old_cred);
 	}
 
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 0ed7c4012437..1dbeab6cf96e 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -238,41 +238,27 @@ out:
 	return err;
 }
 
-static bool ovl_need_xattr_filter(struct dentry *dentry,
-				  enum ovl_path_type type)
-{
-	if ((type & (__OVL_PATH_PURE | __OVL_PATH_UPPER)) == __OVL_PATH_UPPER)
-		return S_ISDIR(dentry->d_inode->i_mode);
-	else
-		return false;
-}
-
 ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode,
 		     const char *name, void *value, size_t size)
 {
-	struct path realpath;
-	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+	struct dentry *realdentry = ovl_dentry_real(dentry);
 
-	if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
+	if (ovl_is_private_xattr(name))
 		return -ENODATA;
 
-	return vfs_getxattr(realpath.dentry, name, value, size);
+	return vfs_getxattr(realdentry, name, value, size);
 }
 
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 {
-	struct path realpath;
-	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+	struct dentry *realdentry = ovl_dentry_real(dentry);
 	ssize_t res;
 	int off;
 
-	res = vfs_listxattr(realpath.dentry, list, size);
+	res = vfs_listxattr(realdentry, list, size);
 	if (res <= 0 || size == 0)
 		return res;
 
-	if (!ovl_need_xattr_filter(dentry, type))
-		return res;
-
 	/* filter out private xattrs */
 	for (off = 0; off < res;) {
 		char *s = list + off;
@@ -302,7 +288,7 @@ int ovl_removexattr(struct dentry *dentry, const char *name)
 		goto out;
 
 	err = -ENODATA;
-	if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
+	if (ovl_is_private_xattr(name))
 		goto out_drop_write;
 
 	if (!OVL_TYPE_UPPER(type)) {
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 8a4a266beff3..edc452c2a563 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -820,39 +820,43 @@ posix_acl_xattr_get(const struct xattr_handler *handler,
 	return error;
 }
 
-static int
-posix_acl_xattr_set(const struct xattr_handler *handler,
-		    struct dentry *unused, struct inode *inode,
-		    const char *name, const void *value,
-		    size_t size, int flags)
+int
+set_posix_acl(struct inode *inode, int type, struct posix_acl *acl)
 {
-	struct posix_acl *acl = NULL;
-	int ret;
-
 	if (!IS_POSIXACL(inode))
 		return -EOPNOTSUPP;
 	if (!inode->i_op->set_acl)
 		return -EOPNOTSUPP;
 
-	if (handler->flags == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
-		return value ? -EACCES : 0;
+	if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
+		return acl ? -EACCES : 0;
 	if (!inode_owner_or_capable(inode))
 		return -EPERM;
 
+	if (acl) {
+		int ret = posix_acl_valid(acl);
+		if (ret)
+			return ret;
+	}
+	return inode->i_op->set_acl(inode, acl, type);
+}
+EXPORT_SYMBOL(set_posix_acl);
+
+static int
+posix_acl_xattr_set(const struct xattr_handler *handler,
+		    struct dentry *unused, struct inode *inode,
+		    const char *name, const void *value,
+		    size_t size, int flags)
+{
+	struct posix_acl *acl = NULL;
+	int ret;
+
 	if (value) {
 		acl = posix_acl_from_xattr(&init_user_ns, value, size);
 		if (IS_ERR(acl))
 			return PTR_ERR(acl);
-
-		if (acl) {
-			ret = posix_acl_valid(acl);
-			if (ret)
-				goto out;
-		}
 	}
-
-	ret = inode->i_op->set_acl(inode, acl, handler->flags);
-out:
+	ret = set_posix_acl(inode, handler->flags, acl);
 	posix_acl_release(acl);
 	return ret;
 }
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 55bc7d6c8aac..06702783bf40 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -121,6 +121,13 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 	if (IS_ERR(sb))
 		return ERR_CAST(sb);
 
+	/*
+	 * procfs isn't actually a stacking filesystem; however, there is
+	 * too much magic going on inside it to permit stacking things on
+	 * top of it
+	 */
+	sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
+
 	if (!proc_parse_options(options, ns)) {
 		deactivate_locked_super(sb);
 		return ERR_PTR(-EINVAL);
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index b8f2d1e8c645..c72c16c5a60f 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1393,7 +1393,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	unsigned long safe_mask = 0;
 	unsigned int commit_max_age = (unsigned int)-1;
 	struct reiserfs_journal *journal = SB_JOURNAL(s);
-	char *new_opts = kstrdup(arg, GFP_KERNEL);
+	char *new_opts;
 	int err;
 	char *qf_names[REISERFS_MAXQUOTAS];
 	unsigned int qfmt = 0;
@@ -1401,6 +1401,10 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	int i;
 #endif
 
+	new_opts = kstrdup(arg, GFP_KERNEL);
+	if (arg && !new_opts)
+		return -ENOMEM;
+
 	sync_filesystem(s);
 	reiserfs_write_lock(s);
 
@@ -1546,7 +1550,8 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	}
 
 out_ok_unlocked:
-	replace_mount_options(s, new_opts);
+	if (new_opts)
+		replace_mount_options(s, new_opts);
 	return 0;
 
 out_err_unlock:
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 08316972ff93..7bbf420d1289 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -52,6 +52,7 @@
 #include "ubifs.h"
 #include <linux/mount.h>
 #include <linux/slab.h>
+#include <linux/migrate.h>
 
 static int read_block(struct inode *inode, void *addr, unsigned int block,
 		      struct ubifs_data_node *dn)
@@ -1452,6 +1453,26 @@ static int ubifs_set_page_dirty(struct page *page)
 	return ret;
 }
 
+#ifdef CONFIG_MIGRATION
+static int ubifs_migrate_page(struct address_space *mapping,
+		struct page *newpage, struct page *page, enum migrate_mode mode)
+{
+	int rc;
+
+	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
+	if (rc != MIGRATEPAGE_SUCCESS)
+		return rc;
+
+	if (PagePrivate(page)) {
+		ClearPagePrivate(page);
+		SetPagePrivate(newpage);
+	}
+
+	migrate_page_copy(newpage, page);
+	return MIGRATEPAGE_SUCCESS;
+}
+#endif
+
 static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags)
 {
 	/*
@@ -1591,6 +1612,9 @@ const struct address_space_operations ubifs_file_address_operations = {
 	.write_end      = ubifs_write_end,
 	.invalidatepage = ubifs_invalidatepage,
 	.set_page_dirty = ubifs_set_page_dirty,
+#ifdef CONFIG_MIGRATION
+	.migratepage	= ubifs_migrate_page,
+#endif
 	.releasepage    = ubifs_releasepage,
 };
 
diff --git a/fs/udf/partition.c b/fs/udf/partition.c
index 5f861ed287c3..888c364b2fe9 100644
--- a/fs/udf/partition.c
+++ b/fs/udf/partition.c
@@ -295,7 +295,8 @@ static uint32_t udf_try_read_meta(struct inode *inode, uint32_t block,
 		map = &UDF_SB(sb)->s_partmaps[partition];
 		/* map to sparable/physical partition desc */
 		phyblock = udf_get_pblock(sb, eloc.logicalBlockNum,
-			map->s_partition_num, ext_offset + offset);
+			map->s_type_specific.s_metadata.s_phys_partition_ref,
+			ext_offset + offset);
 	}
 
 	brelse(epos.bh);
@@ -317,14 +318,18 @@ uint32_t udf_get_pblock_meta25(struct super_block *sb, uint32_t block,
 	mdata = &map->s_type_specific.s_metadata;
 	inode = mdata->s_metadata_fe ? : mdata->s_mirror_fe;
 
-	/* We shouldn't mount such media... */
-	BUG_ON(!inode);
+	if (!inode)
+		return 0xFFFFFFFF;
+
 	retblk = udf_try_read_meta(inode, block, partition, offset);
 	if (retblk == 0xFFFFFFFF && mdata->s_metadata_fe) {
 		udf_warn(sb, "error reading from METADATA, trying to read from MIRROR\n");
 		if (!(mdata->s_flags & MF_MIRROR_FE_LOADED)) {
 			mdata->s_mirror_fe = udf_find_metadata_inode_efe(sb,
-				mdata->s_mirror_file_loc, map->s_partition_num);
+				mdata->s_mirror_file_loc,
+				mdata->s_phys_partition_ref);
+			if (IS_ERR(mdata->s_mirror_fe))
+				mdata->s_mirror_fe = NULL;
 			mdata->s_flags |= MF_MIRROR_FE_LOADED;
 		}
 
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 5e2c8c814e1b..4942549e7dc8 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -951,13 +951,13 @@ out2:
 }
 
 struct inode *udf_find_metadata_inode_efe(struct super_block *sb,
-					u32 meta_file_loc, u32 partition_num)
+					u32 meta_file_loc, u32 partition_ref)
 {
 	struct kernel_lb_addr addr;
 	struct inode *metadata_fe;
 
 	addr.logicalBlockNum = meta_file_loc;
-	addr.partitionReferenceNum = partition_num;
+	addr.partitionReferenceNum = partition_ref;
 
 	metadata_fe = udf_iget_special(sb, &addr);
 
@@ -974,7 +974,8 @@ struct inode *udf_find_metadata_inode_efe(struct super_block *sb,
 	return metadata_fe;
 }
 
-static int udf_load_metadata_files(struct super_block *sb, int partition)
+static int udf_load_metadata_files(struct super_block *sb, int partition,
+				   int type1_index)
 {
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	struct udf_part_map *map;
@@ -984,20 +985,21 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
 
 	map = &sbi->s_partmaps[partition];
 	mdata = &map->s_type_specific.s_metadata;
+	mdata->s_phys_partition_ref = type1_index;
 
 	/* metadata address */
 	udf_debug("Metadata file location: block = %d part = %d\n",
-		  mdata->s_meta_file_loc, map->s_partition_num);
+		  mdata->s_meta_file_loc, mdata->s_phys_partition_ref);
 
 	fe = udf_find_metadata_inode_efe(sb, mdata->s_meta_file_loc,
-					 map->s_partition_num);
+					 mdata->s_phys_partition_ref);
 	if (IS_ERR(fe)) {
 		/* mirror file entry */
 		udf_debug("Mirror metadata file location: block = %d part = %d\n",
-			  mdata->s_mirror_file_loc, map->s_partition_num);
+			  mdata->s_mirror_file_loc, mdata->s_phys_partition_ref);
 
 		fe = udf_find_metadata_inode_efe(sb, mdata->s_mirror_file_loc,
-						 map->s_partition_num);
+						 mdata->s_phys_partition_ref);
 
 		if (IS_ERR(fe)) {
 			udf_err(sb, "Both metadata and mirror metadata inode efe can not found\n");
@@ -1015,7 +1017,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
 	*/
 	if (mdata->s_bitmap_file_loc != 0xFFFFFFFF) {
 		addr.logicalBlockNum = mdata->s_bitmap_file_loc;
-		addr.partitionReferenceNum = map->s_partition_num;
+		addr.partitionReferenceNum = mdata->s_phys_partition_ref;
 
 		udf_debug("Bitmap file location: block = %d part = %d\n",
 			  addr.logicalBlockNum, addr.partitionReferenceNum);
@@ -1283,7 +1285,7 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block)
 	p = (struct partitionDesc *)bh->b_data;
 	partitionNumber = le16_to_cpu(p->partitionNumber);
 
-	/* First scan for TYPE1, SPARABLE and METADATA partitions */
+	/* First scan for TYPE1 and SPARABLE partitions */
 	for (i = 0; i < sbi->s_partitions; i++) {
 		map = &sbi->s_partmaps[i];
 		udf_debug("Searching map: (%d == %d)\n",
@@ -1333,7 +1335,7 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block)
 		goto out_bh;
 
 	if (map->s_partition_type == UDF_METADATA_MAP25) {
-		ret = udf_load_metadata_files(sb, i);
+		ret = udf_load_metadata_files(sb, i, type1_idx);
 		if (ret < 0) {
 			udf_err(sb, "error loading MetaData partition map %d\n",
 				i);
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index 27b5335730c9..c13875d669c0 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -61,6 +61,11 @@ struct udf_meta_data {
 	__u32	s_bitmap_file_loc;
 	__u32	s_alloc_unit_size;
 	__u16	s_align_unit_size;
+	/*
+	 * Partition Reference Number of the associated physical / sparable
+	 * partition
+	 */
+	__u16   s_phys_partition_ref;
 	int	s_flags;
 	struct inode *s_metadata_fe;
 	struct inode *s_mirror_fe;
diff --git a/include/acpi/video.h b/include/acpi/video.h
index 70a41f742037..5731ccb42585 100644
--- a/include/acpi/video.h
+++ b/include/acpi/video.h
@@ -51,7 +51,8 @@ extern void acpi_video_set_dmi_backlight_type(enum acpi_backlight_type type);
  */
 extern bool acpi_video_handles_brightness_key_presses(void);
 extern int acpi_video_get_levels(struct acpi_device *device,
-				 struct acpi_video_device_brightness **dev_br);
+				 struct acpi_video_device_brightness **dev_br,
+				 int *pmax_level);
 #else
 static inline int acpi_video_register(void) { return 0; }
 static inline void acpi_video_unregister(void) { return; }
@@ -72,7 +73,8 @@ static inline bool acpi_video_handles_brightness_key_presses(void)
 	return false;
 }
 static inline int acpi_video_get_levels(struct acpi_device *device,
-			struct acpi_video_device_brightness **dev_br)
+			struct acpi_video_device_brightness **dev_br,
+			int *pmax_level)
 {
 	return -ENODEV;
 }
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 6bd05700d8c9..05f05f17a7c2 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -22,37 +22,33 @@
 #include <asm-generic/qspinlock_types.h>
 
 /**
+ * queued_spin_unlock_wait - wait until the _current_ lock holder releases the lock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * There is a very slight possibility of live-lock if the lockers keep coming
+ * and the waiter is just unfortunate enough to not see any unlock state.
+ */
+#ifndef queued_spin_unlock_wait
+extern void queued_spin_unlock_wait(struct qspinlock *lock);
+#endif
+
+/**
  * queued_spin_is_locked - is the spinlock locked?
  * @lock: Pointer to queued spinlock structure
  * Return: 1 if it is locked, 0 otherwise
  */
+#ifndef queued_spin_is_locked
 static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
 {
 	/*
-	 * queued_spin_lock_slowpath() can ACQUIRE the lock before
-	 * issuing the unordered store that sets _Q_LOCKED_VAL.
-	 *
-	 * See both smp_cond_acquire() sites for more detail.
-	 *
-	 * This however means that in code like:
-	 *
-	 *   spin_lock(A)		spin_lock(B)
-	 *   spin_unlock_wait(B)	spin_is_locked(A)
-	 *   do_something()		do_something()
-	 *
-	 * Both CPUs can end up running do_something() because the store
-	 * setting _Q_LOCKED_VAL will pass through the loads in
-	 * spin_unlock_wait() and/or spin_is_locked().
+	 * See queued_spin_unlock_wait().
 	 *
-	 * Avoid this by issuing a full memory barrier between the spin_lock()
-	 * and the loads in spin_unlock_wait() and spin_is_locked().
-	 *
-	 * Note that regular mutual exclusion doesn't care about this
-	 * delayed store.
+	 * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL
+	 * isn't immediately observable.
 	 */
-	smp_mb();
-	return atomic_read(&lock->val) & _Q_LOCKED_MASK;
+	return atomic_read(&lock->val);
 }
+#endif
 
 /**
  * queued_spin_value_unlocked - is the spinlock structure unlocked?
@@ -122,21 +118,6 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 }
 #endif
 
-/**
- * queued_spin_unlock_wait - wait until current lock holder releases the lock
- * @lock : Pointer to queued spinlock structure
- *
- * There is a very slight possibility of live-lock if the lockers keep coming
- * and the waiter is just unfortunate enough to not see any unlock state.
- */
-static inline void queued_spin_unlock_wait(struct qspinlock *lock)
-{
-	/* See queued_spin_is_locked() */
-	smp_mb();
-	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
-		cpu_relax();
-}
-
 #ifndef virt_spin_lock
 static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 {
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 961a417d641e..e38e3fc13ea8 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -26,7 +26,6 @@
 #include <linux/sched.h>
 #include <linux/ptrace.h>
 #include <uapi/linux/audit.h>
-#include <linux/tty.h>
 
 #define AUDIT_INO_UNSET ((unsigned long)-1)
 #define AUDIT_DEV_UNSET ((dev_t)-1)
@@ -348,23 +347,6 @@ static inline unsigned int audit_get_sessionid(struct task_struct *tsk)
 	return tsk->sessionid;
 }
 
-static inline struct tty_struct *audit_get_tty(struct task_struct *tsk)
-{
-	struct tty_struct *tty = NULL;
-	unsigned long flags;
-
-	spin_lock_irqsave(&tsk->sighand->siglock, flags);
-	if (tsk->signal)
-		tty = tty_kref_get(tsk->signal->tty);
-	spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
-	return tty;
-}
-
-static inline void audit_put_tty(struct tty_struct *tty)
-{
-	tty_kref_put(tty);
-}
-
 extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp);
 extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode);
 extern void __audit_bprm(struct linux_binprm *bprm);
@@ -522,12 +504,6 @@ static inline unsigned int audit_get_sessionid(struct task_struct *tsk)
 {
 	return -1;
 }
-static inline struct tty_struct *audit_get_tty(struct task_struct *tsk)
-{
-	return NULL;
-}
-static inline void audit_put_tty(struct tty_struct *tty)
-{ }
 static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp)
 { }
 static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid,
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 576e4639ca60..314b3caa701c 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -65,6 +65,7 @@ struct coredump_params {
 	unsigned long limit;
 	unsigned long mm_flags;
 	loff_t written;
+	loff_t pos;
 };
 
 /*
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8ee27b8afe81..b3336b4f5d04 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -11,14 +11,17 @@
 #include <linux/workqueue.h>
 #include <linux/file.h>
 #include <linux/percpu.h>
+#include <linux/err.h>
 
+struct perf_event;
 struct bpf_map;
 
 /* map is generic key/value storage optionally accesible by eBPF programs */
 struct bpf_map_ops {
 	/* funcs callable from userspace (via syscall) */
 	struct bpf_map *(*map_alloc)(union bpf_attr *attr);
-	void (*map_free)(struct bpf_map *);
+	void (*map_release)(struct bpf_map *map, struct file *map_file);
+	void (*map_free)(struct bpf_map *map);
 	int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
 
 	/* funcs callable from userspace and from eBPF programs */
@@ -27,8 +30,9 @@ struct bpf_map_ops {
 	int (*map_delete_elem)(struct bpf_map *map, void *key);
 
 	/* funcs called by prog_array and perf_event_array map */
-	void *(*map_fd_get_ptr) (struct bpf_map *map, int fd);
-	void (*map_fd_put_ptr) (void *ptr);
+	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
+				int fd);
+	void (*map_fd_put_ptr)(void *ptr);
 };
 
 struct bpf_map {
@@ -111,6 +115,31 @@ enum bpf_access_type {
 	BPF_WRITE = 2
 };
 
+/* types of values stored in eBPF registers */
+enum bpf_reg_type {
+	NOT_INIT = 0,		 /* nothing was written into register */
+	UNKNOWN_VALUE,		 /* reg doesn't contain a valid pointer */
+	PTR_TO_CTX,		 /* reg points to bpf_context */
+	CONST_PTR_TO_MAP,	 /* reg points to struct bpf_map */
+	PTR_TO_MAP_VALUE,	 /* reg points to map element value */
+	PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
+	FRAME_PTR,		 /* reg == frame_pointer */
+	PTR_TO_STACK,		 /* reg == frame_pointer + imm */
+	CONST_IMM,		 /* constant integer value */
+
+	/* PTR_TO_PACKET represents:
+	 * skb->data
+	 * skb->data + imm
+	 * skb->data + (u16) var
+	 * skb->data + (u16) var + imm
+	 * if (range > 0) then [ptr, ptr + range - off) is safe to access
+	 * if (id > 0) means that some 'var' was added
+	 * if (off > 0) menas that 'imm' was added
+	 */
+	PTR_TO_PACKET,
+	PTR_TO_PACKET_END,	 /* skb->data + headlen */
+};
+
 struct bpf_prog;
 
 struct bpf_verifier_ops {
@@ -120,7 +149,8 @@ struct bpf_verifier_ops {
 	/* return true if 'size' wide access at offset 'off' within bpf_context
 	 * with 'type' (read or write) is allowed
 	 */
-	bool (*is_valid_access)(int off, int size, enum bpf_access_type type);
+	bool (*is_valid_access)(int off, int size, enum bpf_access_type type,
+				enum bpf_reg_type *reg_type);
 
 	u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg,
 				  int src_reg, int ctx_off,
@@ -163,11 +193,19 @@ struct bpf_array {
 		void __percpu *pptrs[0] __aligned(8);
 	};
 };
+
 #define MAX_TAIL_CALL_CNT 32
 
+struct bpf_event_entry {
+	struct perf_event *event;
+	struct file *perf_file;
+	struct file *map_file;
+	struct rcu_head rcu;
+};
+
 u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
 u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
-void bpf_fd_array_map_clear(struct bpf_map *map);
+
 bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
@@ -180,9 +218,9 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl);
 void bpf_register_map_type(struct bpf_map_type_list *tl);
 
 struct bpf_prog *bpf_prog_get(u32 ufd);
+struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type);
 struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
-void bpf_prog_put_rcu(struct bpf_prog *prog);
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
@@ -205,8 +243,13 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
 			   u64 flags);
 int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
 			    u64 flags);
+
 int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
 
+int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
+				 void *key, void *value, u64 map_flags);
+void bpf_fd_array_map_clear(struct bpf_map *map);
+
 /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
  * forced to use 'long' read/writes to try to atomically copy long counters.
  * Best-effort only.  No barriers here, since it _will_ race with concurrent
@@ -235,6 +278,12 @@ static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
+static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
+						 enum bpf_prog_type type)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static inline void bpf_prog_put(struct bpf_prog *prog)
 {
 }
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 19b14862d3e0..1b3b6e155392 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -279,6 +279,11 @@ struct ceph_osd_client {
 	struct workqueue_struct	*notify_wq;
 };
 
+static inline bool ceph_osdmap_flag(struct ceph_osd_client *osdc, int flag)
+{
+	return osdc->osdmap->flags & flag;
+}
+
 extern int ceph_osdc_setup(void);
 extern void ceph_osdc_cleanup(void);
 
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index ddc426b22d81..9ccf4dbe55f8 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -189,11 +189,6 @@ static inline bool ceph_osd_is_down(struct ceph_osdmap *map, int osd)
 	return !ceph_osd_is_up(map, osd);
 }
 
-static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
-{
-	return map && (map->flags & flag);
-}
-
 extern char *ceph_osdmap_state_str(char *str, int len, int state);
 extern u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd);
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index a20320c666fd..984f73b719a9 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -87,6 +87,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 						       struct cgroup_subsys *ss);
 
 struct cgroup *cgroup_get_from_path(const char *path);
+struct cgroup *cgroup_get_from_fd(int fd);
 
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 0c72204c75fc..fb39d5add173 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -25,7 +25,7 @@
 #define CLK_SET_PARENT_GATE	BIT(1) /* must be gated across re-parent */
 #define CLK_SET_RATE_PARENT	BIT(2) /* propagate rate change up one level */
 #define CLK_IGNORE_UNUSED	BIT(3) /* do not gate even if unused */
-#define CLK_IS_ROOT		BIT(4) /* Deprecated: Don't use */
+				/* unused */
 #define CLK_IS_BASIC		BIT(5) /* Basic clk, can't do a to_clk_foo() */
 #define CLK_GET_RATE_NOCACHE	BIT(6) /* do not use the cached clk rate */
 #define CLK_SET_RATE_NO_REPARENT BIT(7) /* don't re-parent on rate change */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 786ad32631a6..07b83d32f66c 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -152,6 +152,8 @@ extern void cpuidle_disable_device(struct cpuidle_device *dev);
 extern int cpuidle_play_dead(void);
 
 extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev);
+static inline struct cpuidle_device *cpuidle_get_device(void)
+{return __this_cpu_read(cpuidle_devices); }
 #else
 static inline void disable_cpuidle(void) { }
 static inline bool cpuidle_not_available(struct cpuidle_driver *drv,
@@ -187,6 +189,7 @@ static inline void cpuidle_disable_device(struct cpuidle_device *dev) { }
 static inline int cpuidle_play_dead(void) {return -ENODEV; }
 static inline struct cpuidle_driver *cpuidle_get_cpu_driver(
 	struct cpuidle_device *dev) {return NULL; }
+static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; }
 #endif
 
 #if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SUSPEND)
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 484c8792da82..f53fa055021a 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -212,6 +212,7 @@ struct dentry_operations {
 #define DCACHE_OP_REAL			0x08000000
 
 #define DCACHE_PAR_LOOKUP		0x10000000 /* being looked up (with parent locked shared) */
+#define DCACHE_DENTRY_CURSOR		0x20000000
 
 extern seqlock_t rename_lock;
 
@@ -575,5 +576,17 @@ static inline struct inode *vfs_select_inode(struct dentry *dentry,
 	return inode;
 }
 
+/**
+ * d_real_inode - Return the real inode
+ * @dentry: The dentry to query
+ *
+ * If dentry is on an union/overlay, then return the underlying, real inode.
+ * Otherwise return d_inode().
+ */
+static inline struct inode *d_real_inode(struct dentry *dentry)
+{
+	return d_backing_inode(d_real(dentry));
+}
+
 
 #endif	/* __LINUX_DCACHE_H */
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index 5871f292b596..277ab9af9ac2 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -15,13 +15,12 @@
 
 #include <linux/errno.h>
 
-struct pts_fs_info;
-
 #ifdef CONFIG_UNIX98_PTYS
 
-/* Look up a pts fs info and get a ref to it */
-struct pts_fs_info *devpts_get_ref(struct inode *, struct file *);
-void devpts_put_ref(struct pts_fs_info *);
+struct pts_fs_info;
+
+struct pts_fs_info *devpts_acquire(struct file *);
+void devpts_release(struct pts_fs_info *);
 
 int devpts_new_index(struct pts_fs_info *);
 void devpts_kill_index(struct pts_fs_info *, int);
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 3fe90d494edb..4551c6f2a6c4 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -112,19 +112,24 @@ struct dma_buf_ops {
  * @file: file pointer used for sharing buffers across, and for refcounting.
  * @attachments: list of dma_buf_attachment that denotes all devices attached.
  * @ops: dma_buf_ops associated with this buffer object.
+ * @lock: used internally to serialize list manipulation, attach/detach and vmap/unmap
+ * @vmapping_counter: used internally to refcnt the vmaps
+ * @vmap_ptr: the current vmap ptr if vmapping_counter > 0
  * @exp_name: name of the exporter; useful for debugging.
  * @owner: pointer to exporter module; used for refcounting when exporter is a
  *         kernel module.
  * @list_node: node for dma_buf accounting and debugging.
  * @priv: exporter specific private data for this buffer object.
  * @resv: reservation object linked to this dma-buf
+ * @poll: for userspace poll support
+ * @cb_excl: for userspace poll support
+ * @cb_shared: for userspace poll support
  */
 struct dma_buf {
 	size_t size;
 	struct file *file;
 	struct list_head attachments;
 	const struct dma_buf_ops *ops;
-	/* mutex to serialize list manipulation, attach/detach and vmap/unmap */
 	struct mutex lock;
 	unsigned vmapping_counter;
 	void *vmap_ptr;
@@ -188,9 +193,11 @@ struct dma_buf_export_info {
 
 /**
  * helper macro for exporters; zeros and fills in most common values
+ *
+ * @name: export-info name
  */
-#define DEFINE_DMA_BUF_EXPORT_INFO(a)	\
-	struct dma_buf_export_info a = { .exp_name = KBUILD_MODNAME, \
+#define DEFINE_DMA_BUF_EXPORT_INFO(name)	\
+	struct dma_buf_export_info name = { .exp_name = KBUILD_MODNAME, \
 					 .owner = THIS_MODULE }
 
 /**
diff --git a/include/linux/efi.h b/include/linux/efi.h
index c2db3ca22217..f196dd0b0f2f 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1005,7 +1005,7 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm,
 /* Iterate through an efi_memory_map */
 #define for_each_efi_memory_desc_in_map(m, md)				   \
 	for ((md) = (m)->map;						   \
-	     (md) <= (efi_memory_desc_t *)((m)->map_end - (m)->desc_size); \
+	     ((void *)(md) + (m)->desc_size) <= (m)->map_end;		   \
 	     (md) = (void *)(md) + (m)->desc_size)
 
 /**
diff --git a/include/linux/fence.h b/include/linux/fence.h
index 2b17698b60b8..2056e9fd0138 100644
--- a/include/linux/fence.h
+++ b/include/linux/fence.h
@@ -49,6 +49,8 @@ struct fence_cb;
  * @timestamp: Timestamp when the fence was signaled.
  * @status: Optional, only valid if < 0, must be set before calling
  * fence_signal, indicates that the fence has completed with an error.
+ * @child_list: list of children fences
+ * @active_list: list of active fences
  *
  * the flags member must be manipulated and read using the appropriate
  * atomic ops (bit_*), so taking the spinlock will not be needed most
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 604e1526cd00..13ba552e6c09 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -241,7 +241,7 @@ struct fscache_cache_ops {
 
 	/* check the consistency between the backing cache and the FS-Cache
 	 * cookie */
-	bool (*check_consistency)(struct fscache_operation *op);
+	int (*check_consistency)(struct fscache_operation *op);
 
 	/* store the updated auxiliary data on an object */
 	void (*update_object)(struct fscache_object *object);
diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h
index 630f45335c73..57086e9fc64c 100644
--- a/include/linux/icmpv6.h
+++ b/include/linux/icmpv6.h
@@ -14,9 +14,12 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_IPV6)
 extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info);
 
-typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info);
+typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+			     const struct in6_addr *force_saddr);
 extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn);
 extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn);
+int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
+			       unsigned int data_len);
 
 #else
 
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index d029ffac0d69..99403b19092f 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -223,6 +223,8 @@ struct st_sensor_settings {
  * @get_irq_data_ready: Function to get the IRQ used for data ready signal.
  * @tf: Transfer function structure used by I/O operations.
  * @tb: Transfer buffers and mutex used by I/O operations.
+ * @hw_irq_trigger: if we're using the hardware interrupt on the sensor.
+ * @hw_timestamp: Latest timestamp from the interrupt handler, when in use.
  */
 struct st_sensor_data {
 	struct device *dev;
@@ -247,6 +249,9 @@ struct st_sensor_data {
 
 	const struct st_sensor_transfer_function *tf;
 	struct st_sensor_transfer_buffer tb;
+
+	bool hw_irq_trigger;
+	s64 hw_timestamp;
 };
 
 #ifdef CONFIG_IIO_BUFFER
@@ -260,7 +265,8 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 				const struct iio_trigger_ops *trigger_ops);
 
 void st_sensors_deallocate_trigger(struct iio_dev *indio_dev);
-
+int st_sensors_validate_device(struct iio_trigger *trig,
+			       struct iio_dev *indio_dev);
 #else
 static inline int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 				const struct iio_trigger_ops *trigger_ops)
@@ -271,6 +277,7 @@ static inline void st_sensors_deallocate_trigger(struct iio_dev *indio_dev)
 {
 	return;
 }
+#define st_sensors_validate_device NULL
 #endif
 
 int st_sensors_init_sensor(struct iio_dev *indio_dev,
diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 7c27fa1030e8..feb04ea20f11 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -52,6 +52,12 @@ struct sock *inet_diag_find_one_icsk(struct net *net,
 
 int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk);
 
+void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk);
+
+int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
+			     struct inet_diag_msg *r, int ext,
+			     struct user_namespace *user_ns);
+
 extern int  inet_diag_register(const struct inet_diag_handler *handler);
 extern void inet_diag_unregister(const struct inet_diag_handler *handler);
 #endif /* _INET_DIAG_H_ */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index f2cb8d45513d..f8834f820ec2 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -190,7 +190,7 @@ extern struct task_group root_task_group;
 #define INIT_TASK(tsk)	\
 {									\
 	.state		= 0,						\
-	.stack		= &init_thread_info,				\
+	.stack		= init_stack,					\
 	.usage		= ATOMIC_INIT(2),				\
 	.flags		= PF_KTHREAD,					\
 	.prio		= MAX_PRIO-20,					\
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 5c91b0b055d4..c6dbcd84a2c7 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -283,6 +283,8 @@ struct tcp6_timewait_sock {
 };
 
 #if IS_ENABLED(CONFIG_IPV6)
+bool ipv6_mod_enabled(void);
+
 static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk)
 {
 	return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL;
@@ -326,6 +328,11 @@ static inline int inet_v6_ipv6only(const struct sock *sk)
 #define ipv6_only_sock(sk)	0
 #define ipv6_sk_rxinfo(sk)	0
 
+static inline bool ipv6_mod_enabled(void)
+{
+	return false;
+}
+
 static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
 {
 	return NULL;
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index bfbd707de390..dc493e0f0ff7 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -305,12 +305,12 @@
 #define ICC_SGI1R_AFFINITY_1_SHIFT	16
 #define ICC_SGI1R_AFFINITY_1_MASK	(0xff << ICC_SGI1R_AFFINITY_1_SHIFT)
 #define ICC_SGI1R_SGI_ID_SHIFT		24
-#define ICC_SGI1R_SGI_ID_MASK		(0xff << ICC_SGI1R_SGI_ID_SHIFT)
+#define ICC_SGI1R_SGI_ID_MASK		(0xfULL << ICC_SGI1R_SGI_ID_SHIFT)
 #define ICC_SGI1R_AFFINITY_2_SHIFT	32
-#define ICC_SGI1R_AFFINITY_2_MASK	(0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
+#define ICC_SGI1R_AFFINITY_2_MASK	(0xffULL << ICC_SGI1R_AFFINITY_2_SHIFT)
 #define ICC_SGI1R_IRQ_ROUTING_MODE_BIT	40
 #define ICC_SGI1R_AFFINITY_3_SHIFT	48
-#define ICC_SGI1R_AFFINITY_3_MASK	(0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
+#define ICC_SGI1R_AFFINITY_3_MASK	(0xffULL << ICC_SGI1R_AFFINITY_3_SHIFT)
 
 #include <asm/arch_gicv3.h>
 
diff --git a/include/linux/isa.h b/include/linux/isa.h
index 5ab85281230b..f2d0258414cf 100644
--- a/include/linux/isa.h
+++ b/include/linux/isa.h
@@ -6,6 +6,7 @@
 #define __LINUX_ISA_H
 
 #include <linux/device.h>
+#include <linux/errno.h>
 #include <linux/kernel.h>
 
 struct isa_driver {
@@ -22,13 +23,13 @@ struct isa_driver {
 
 #define to_isa_driver(x) container_of((x), struct isa_driver, driver)
 
-#ifdef CONFIG_ISA
+#ifdef CONFIG_ISA_BUS_API
 int isa_register_driver(struct isa_driver *, unsigned int);
 void isa_unregister_driver(struct isa_driver *);
 #else
 static inline int isa_register_driver(struct isa_driver *d, unsigned int i)
 {
-	return 0;
+	return -ENODEV;
 }
 
 static inline void isa_unregister_driver(struct isa_driver *d)
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 0536524bb9eb..68904469fba1 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -117,13 +117,18 @@ struct module;
 
 #include <linux/atomic.h>
 
+#ifdef HAVE_JUMP_LABEL
+
 static inline int static_key_count(struct static_key *key)
 {
-	return atomic_read(&key->enabled);
+	/*
+	 * -1 means the first static_key_slow_inc() is in progress.
+	 *  static_key_enabled() must return true, so return 1 here.
+	 */
+	int n = atomic_read(&key->enabled);
+	return n >= 0 ? n : 1;
 }
 
-#ifdef HAVE_JUMP_LABEL
-
 #define JUMP_TYPE_FALSE	0UL
 #define JUMP_TYPE_TRUE	1UL
 #define JUMP_TYPE_MASK	1UL
@@ -162,6 +167,11 @@ extern void jump_label_apply_nops(struct module *mod);
 
 #else  /* !HAVE_JUMP_LABEL */
 
+static inline int static_key_count(struct static_key *key)
+{
+	return atomic_read(&key->enabled);
+}
+
 static __always_inline void jump_label_init(void)
 {
 	static_key_initialized = true;
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 611927f5870d..ac4b3c46a84d 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -59,14 +59,13 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object);
 
 void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags);
 void kasan_kfree_large(const void *ptr);
-void kasan_kfree(void *ptr);
+void kasan_poison_kfree(void *ptr);
 void kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size,
 		  gfp_t flags);
 void kasan_krealloc(const void *object, size_t new_size, gfp_t flags);
 
 void kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags);
 bool kasan_slab_free(struct kmem_cache *s, void *object);
-void kasan_poison_slab_free(struct kmem_cache *s, void *object);
 
 struct kasan_cache {
 	int alloc_meta_offset;
@@ -76,6 +75,9 @@ struct kasan_cache {
 int kasan_module_alloc(void *addr, size_t size);
 void kasan_free_shadow(const struct vm_struct *vm);
 
+size_t ksize(const void *);
+static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); }
+
 #else /* CONFIG_KASAN */
 
 static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
@@ -102,7 +104,7 @@ static inline void kasan_poison_object_data(struct kmem_cache *cache,
 
 static inline void kasan_kmalloc_large(void *ptr, size_t size, gfp_t flags) {}
 static inline void kasan_kfree_large(const void *ptr) {}
-static inline void kasan_kfree(void *ptr) {}
+static inline void kasan_poison_kfree(void *ptr) {}
 static inline void kasan_kmalloc(struct kmem_cache *s, const void *object,
 				size_t size, gfp_t flags) {}
 static inline void kasan_krealloc(const void *object, size_t new_size,
@@ -114,11 +116,12 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object)
 {
 	return false;
 }
-static inline void kasan_poison_slab_free(struct kmem_cache *s, void *object) {}
 
 static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
 static inline void kasan_free_shadow(const struct vm_struct *vm) {}
 
+static inline void kasan_unpoison_slab(const void *ptr) { }
+
 #endif /* CONFIG_KASAN */
 
 #endif /* LINUX_KASAN_H */
diff --git a/include/linux/leds.h b/include/linux/leds.h
index d2b13066e781..e5e7f2e80a54 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -42,15 +42,16 @@ struct led_classdev {
 #define LED_UNREGISTERING	(1 << 1)
 	/* Upper 16 bits reflect control information */
 #define LED_CORE_SUSPENDRESUME	(1 << 16)
-#define LED_BLINK_ONESHOT	(1 << 17)
-#define LED_BLINK_ONESHOT_STOP	(1 << 18)
-#define LED_BLINK_INVERT	(1 << 19)
-#define LED_BLINK_BRIGHTNESS_CHANGE (1 << 20)
-#define LED_BLINK_DISABLE	(1 << 21)
-#define LED_SYSFS_DISABLE	(1 << 22)
-#define LED_DEV_CAP_FLASH	(1 << 23)
-#define LED_HW_PLUGGABLE	(1 << 24)
-#define LED_PANIC_INDICATOR	(1 << 25)
+#define LED_BLINK_SW		(1 << 17)
+#define LED_BLINK_ONESHOT	(1 << 18)
+#define LED_BLINK_ONESHOT_STOP	(1 << 19)
+#define LED_BLINK_INVERT	(1 << 20)
+#define LED_BLINK_BRIGHTNESS_CHANGE (1 << 21)
+#define LED_BLINK_DISABLE	(1 << 22)
+#define LED_SYSFS_DISABLE	(1 << 23)
+#define LED_DEV_CAP_FLASH	(1 << 24)
+#define LED_HW_PLUGGABLE	(1 << 25)
+#define LED_PANIC_INDICATOR	(1 << 26)
 
 	/* Set LED brightness level
 	 * Must not sleep. Use brightness_set_blocking for drivers
@@ -72,8 +73,8 @@ struct led_classdev {
 	 * and if both are zero then a sensible default should be chosen.
 	 * The call should adjust the timings in that case and if it can't
 	 * match the values specified exactly.
-	 * Deactivate blinking again when the brightness is set to a fixed
-	 * value via the brightness_set() callback.
+	 * Deactivate blinking again when the brightness is set to LED_OFF
+	 * via the brightness_set() callback.
 	 */
 	int		(*blink_set)(struct led_classdev *led_cdev,
 				     unsigned long *delay_on,
diff --git a/include/linux/mdio-mux.h b/include/linux/mdio-mux.h
index a243dbba8659..61f5b21b31c7 100644
--- a/include/linux/mdio-mux.h
+++ b/include/linux/mdio-mux.h
@@ -10,11 +10,13 @@
 #ifndef __LINUX_MDIO_MUX_H
 #define __LINUX_MDIO_MUX_H
 #include <linux/device.h>
+#include <linux/phy.h>
 
 int mdio_mux_init(struct device *dev,
 		  int (*switch_fn) (int cur, int desired, void *data),
 		  void **mux_handle,
-		  void *data);
+		  void *data,
+		  struct mii_bus *mux_bus);
 
 void mdio_mux_uninit(void *mux_handle);
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 80dec87a94f8..e6f6910278f3 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -466,6 +466,7 @@ enum {
 enum {
 	MLX4_INTERFACE_STATE_UP		= 1 << 0,
 	MLX4_INTERFACE_STATE_DELETION	= 1 << 1,
+	MLX4_INTERFACE_STATE_SHUTDOWN	= 1 << 2,
 };
 
 #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \
@@ -535,6 +536,7 @@ struct mlx4_caps {
 	int			max_rq_desc_sz;
 	int			max_qp_init_rdma;
 	int			max_qp_dest_rdma;
+	int			max_tc_eth;
 	u32			*qp0_qkey;
 	u32			*qp0_proxy;
 	u32			*qp1_proxy;
@@ -1494,6 +1496,7 @@ int mlx4_mr_rereg_mem_write(struct mlx4_dev *dev, struct mlx4_mr *mr,
 
 int mlx4_get_module_info(struct mlx4_dev *dev, u8 port,
 			 u16 offset, u16 size, u8 *data);
+int mlx4_max_tc(struct mlx4_dev *dev);
 
 /* Returns true if running in low memory profile (kdump kernel) */
 static inline bool mlx4_low_memory_profile(void)
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 035abdf62cfe..e0a3ed758287 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1240,8 +1240,6 @@ struct mlx5_destroy_psv_out {
 	u8                      rsvd[8];
 };
 
-#define MLX5_CMD_OP_MAX 0x920
-
 enum {
 	VPORT_STATE_DOWN		= 0x0,
 	VPORT_STATE_UP			= 0x1,
@@ -1332,6 +1330,7 @@ enum mlx5_cap_type {
 	MLX5_CAP_ESWITCH,
 	MLX5_CAP_RESERVED,
 	MLX5_CAP_VECTOR_CALC,
+	MLX5_CAP_QOS,
 	/* NUM OF CAP Types */
 	MLX5_CAP_NUM
 };
@@ -1369,6 +1368,12 @@ enum mlx5_cap_type {
 #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \
 	MLX5_GET(flow_table_nic_cap, mdev->hca_caps_max[MLX5_CAP_FLOW_TABLE], cap)
 
+#define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \
+	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap)
+
+#define MLX5_CAP_FLOWTABLE_NIC_RX_MAX(mdev, cap) \
+	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive.cap)
+
 #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \
 	MLX5_GET(flow_table_eswitch_cap, \
 		 mdev->hca_caps_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
@@ -1410,6 +1415,9 @@ enum mlx5_cap_type {
 	MLX5_GET(vector_calc_cap, \
 		 mdev->hca_caps_cur[MLX5_CAP_VECTOR_CALC], cap)
 
+#define MLX5_CAP_QOS(mdev, cap)\
+	MLX5_GET(qos_cap, mdev->hca_caps_cur[MLX5_CAP_QOS], cap)
+
 enum {
 	MLX5_CMD_STAT_OK			= 0x0,
 	MLX5_CMD_STAT_INT_ERR			= 0x1,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 80776d0c52dc..f21c45941887 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -481,6 +481,21 @@ struct mlx5_fc_stats {
 
 struct mlx5_eswitch;
 
+struct mlx5_rl_entry {
+	u32                     rate;
+	u16                     index;
+	u16                     refcount;
+};
+
+struct mlx5_rl_table {
+	/* protect rate limit table */
+	struct mutex            rl_lock;
+	u16                     max_size;
+	u32                     max_rate;
+	u32                     min_rate;
+	struct mlx5_rl_entry   *rl_entry;
+};
+
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	eq_table;
@@ -535,15 +550,12 @@ struct mlx5_priv {
 	struct list_head        ctx_list;
 	spinlock_t              ctx_lock;
 
+	struct mlx5_flow_steering *steering;
 	struct mlx5_eswitch     *eswitch;
 	struct mlx5_core_sriov	sriov;
 	unsigned long		pci_dev_data;
-	struct mlx5_flow_root_namespace *root_ns;
-	struct mlx5_flow_root_namespace *fdb_root_ns;
-	struct mlx5_flow_root_namespace *esw_egress_root_ns;
-	struct mlx5_flow_root_namespace *esw_ingress_root_ns;
-
 	struct mlx5_fc_stats		fc_stats;
+	struct mlx5_rl_table            rl_table;
 };
 
 enum mlx5_device_state {
@@ -562,6 +574,18 @@ enum mlx5_pci_status {
 	MLX5_PCI_STATUS_ENABLED,
 };
 
+struct mlx5_td {
+	struct list_head tirs_list;
+	u32              tdn;
+};
+
+struct mlx5e_resources {
+	struct mlx5_uar            cq_uar;
+	u32                        pdn;
+	struct mlx5_td             td;
+	struct mlx5_core_mkey      mkey;
+};
+
 struct mlx5_core_dev {
 	struct pci_dev	       *pdev;
 	/* sync pci state */
@@ -586,6 +610,7 @@ struct mlx5_core_dev {
 	struct mlx5_profile	*profile;
 	atomic_t		num_qps;
 	u32			issi;
+	struct mlx5e_resources  mlx5e_res;
 #ifdef CONFIG_RFS_ACCEL
 	struct cpu_rmap         *rmap;
 #endif
@@ -861,6 +886,12 @@ int mlx5_query_odp_caps(struct mlx5_core_dev *dev,
 int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev,
 			     u8 port_num, void *out, size_t sz);
 
+int mlx5_init_rl_table(struct mlx5_core_dev *dev);
+void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev);
+int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index);
+void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate);
+bool mlx5_rl_is_in_range(struct mlx5_core_dev *dev, u32 rate);
+
 static inline int fw_initializing(struct mlx5_core_dev *dev)
 {
 	return ioread32be(&dev->iseg->initializing) >> 31;
@@ -938,6 +969,11 @@ static inline int mlx5_get_gid_table_len(u16 param)
 	return 8 * (1 << param);
 }
 
+static inline bool mlx5_rl_is_supported(struct mlx5_core_dev *dev)
+{
+	return !!(dev->priv.rl_table.max_size);
+}
+
 enum {
 	MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32,
 };
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 4b7a107d9c19..e036d6030867 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -54,6 +54,8 @@ static inline void build_leftovers_ft_param(int *priority,
 
 enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_BYPASS,
+	MLX5_FLOW_NAMESPACE_OFFLOADS,
+	MLX5_FLOW_NAMESPACE_ETHTOOL,
 	MLX5_FLOW_NAMESPACE_KERNEL,
 	MLX5_FLOW_NAMESPACE_LEFTOVERS,
 	MLX5_FLOW_NAMESPACE_ANCHOR,
@@ -67,6 +69,12 @@ struct mlx5_flow_group;
 struct mlx5_flow_rule;
 struct mlx5_flow_namespace;
 
+struct mlx5_flow_spec {
+	u8   match_criteria_enable;
+	u32  match_criteria[MLX5_ST_SZ_DW(fte_match_param)];
+	u32  match_value[MLX5_ST_SZ_DW(fte_match_param)];
+};
+
 struct mlx5_flow_destination {
 	enum mlx5_flow_destination_type	type;
 	union {
@@ -115,9 +123,7 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg);
  */
 struct mlx5_flow_rule *
 mlx5_add_flow_rule(struct mlx5_flow_table *ft,
-		   u8 match_criteria_enable,
-		   u32 *match_criteria,
-		   u32 *match_value,
+		   struct mlx5_flow_spec *spec,
 		   u32 action,
 		   u32 flow_tag,
 		   struct mlx5_flow_destination *dest);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 9a05cd7e5890..152421cc6f44 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -123,6 +123,10 @@ enum {
 	MLX5_CMD_OP_DRAIN_DCT                     = 0x712,
 	MLX5_CMD_OP_QUERY_DCT                     = 0x713,
 	MLX5_CMD_OP_ARM_DCT_FOR_KEY_VIOLATION     = 0x714,
+	MLX5_CMD_OP_CREATE_XRQ                    = 0x717,
+	MLX5_CMD_OP_DESTROY_XRQ                   = 0x718,
+	MLX5_CMD_OP_QUERY_XRQ                     = 0x719,
+	MLX5_CMD_OP_ARM_XRQ                       = 0x71a,
 	MLX5_CMD_OP_QUERY_VPORT_STATE             = 0x750,
 	MLX5_CMD_OP_MODIFY_VPORT_STATE            = 0x751,
 	MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT       = 0x752,
@@ -139,6 +143,8 @@ enum {
 	MLX5_CMD_OP_ALLOC_Q_COUNTER               = 0x771,
 	MLX5_CMD_OP_DEALLOC_Q_COUNTER             = 0x772,
 	MLX5_CMD_OP_QUERY_Q_COUNTER               = 0x773,
+	MLX5_CMD_OP_SET_RATE_LIMIT                = 0x780,
+	MLX5_CMD_OP_QUERY_RATE_LIMIT              = 0x781,
 	MLX5_CMD_OP_ALLOC_PD                      = 0x800,
 	MLX5_CMD_OP_DEALLOC_PD                    = 0x801,
 	MLX5_CMD_OP_ALLOC_UAR                     = 0x802,
@@ -205,7 +211,8 @@ enum {
 	MLX5_CMD_OP_ALLOC_FLOW_COUNTER            = 0x939,
 	MLX5_CMD_OP_DEALLOC_FLOW_COUNTER          = 0x93a,
 	MLX5_CMD_OP_QUERY_FLOW_COUNTER            = 0x93b,
-	MLX5_CMD_OP_MODIFY_FLOW_TABLE             = 0x93c
+	MLX5_CMD_OP_MODIFY_FLOW_TABLE             = 0x93c,
+	MLX5_CMD_OP_MAX
 };
 
 struct mlx5_ifc_flow_table_fields_supported_bits {
@@ -361,7 +368,8 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
 };
 
 struct mlx5_ifc_fte_match_set_misc_bits {
-	u8         reserved_at_0[0x20];
+	u8         reserved_at_0[0x8];
+	u8         source_sqn[0x18];
 
 	u8         reserved_at_20[0x10];
 	u8         source_port[0x10];
@@ -500,11 +508,24 @@ struct mlx5_ifc_e_switch_cap_bits {
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert_if_not_exist[0x1];
 	u8         vport_cvlan_insert_overwrite[0x1];
-	u8         reserved_at_5[0x1b];
+	u8         reserved_at_5[0x19];
+	u8         nic_vport_node_guid_modify[0x1];
+	u8         nic_vport_port_guid_modify[0x1];
 
 	u8         reserved_at_20[0x7e0];
 };
 
+struct mlx5_ifc_qos_cap_bits {
+	u8         packet_pacing[0x1];
+	u8         reserved_0[0x1f];
+	u8         reserved_1[0x20];
+	u8         packet_pacing_max_rate[0x20];
+	u8         packet_pacing_min_rate[0x20];
+	u8         reserved_2[0x10];
+	u8         packet_pacing_rate_table_size[0x10];
+	u8         reserved_3[0x760];
+};
+
 struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         csum_cap[0x1];
 	u8         vlan_cap[0x1];
@@ -744,7 +765,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         out_of_seq_cnt[0x1];
 	u8         vport_counters[0x1];
-	u8         reserved_at_182[0x4];
+	u8         retransmission_q_counters[0x1];
+	u8         reserved_at_183[0x3];
 	u8         max_qp_cnt[0xa];
 	u8         pkey_table_size[0x10];
 
@@ -771,7 +793,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         log_max_msg[0x5];
 	u8         reserved_at_1c8[0x4];
 	u8         max_tc[0x4];
-	u8         reserved_at_1d0[0x6];
+	u8         reserved_at_1d0[0x1];
+	u8         dcbx[0x1];
+	u8         reserved_at_1d2[0x4];
 	u8         rol_s[0x1];
 	u8         rol_g[0x1];
 	u8         reserved_at_1d8[0x1];
@@ -803,7 +827,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         tph[0x1];
 	u8         rf[0x1];
 	u8         dct[0x1];
-	u8         reserved_at_21b[0x1];
+	u8         qos[0x1];
 	u8         eth_net_offloads[0x1];
 	u8         roce[0x1];
 	u8         atomic[0x1];
@@ -929,7 +953,15 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         cqe_compression_timeout[0x10];
 	u8         cqe_compression_max_num[0x10];
 
-	u8         reserved_at_5e0[0x220];
+	u8         reserved_at_5e0[0x10];
+	u8         tag_matching[0x1];
+	u8         rndv_offload_rc[0x1];
+	u8         rndv_offload_dc[0x1];
+	u8         log_tag_matching_list_sz[0x5];
+	u8         reserved_at_5e8[0x3];
+	u8         log_max_xrq[0x5];
+
+	u8         reserved_at_5f0[0x200];
 };
 
 enum mlx5_flow_destination_type {
@@ -1967,7 +1999,7 @@ struct mlx5_ifc_qpc_bits {
 
 	u8         reserved_at_560[0x5];
 	u8         rq_type[0x3];
-	u8         srqn_rmpn[0x18];
+	u8         srqn_rmpn_xrqn[0x18];
 
 	u8         reserved_at_580[0x8];
 	u8         rmsn[0x18];
@@ -2018,6 +2050,7 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap;
 	struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
 	struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap;
+	struct mlx5_ifc_qos_cap_bits qos_cap;
 	u8         reserved_at_0[0x8000];
 };
 
@@ -2244,8 +2277,9 @@ struct mlx5_ifc_sqc_bits {
 	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_at_60[0xa0];
+	u8         reserved_at_60[0x90];
 
+	u8         packet_pacing_rate_limit_index[0x10];
 	u8         tis_lst_sz[0x10];
 	u8         reserved_at_110[0x10];
 
@@ -2593,7 +2627,7 @@ struct mlx5_ifc_dctc_bits {
 	u8         reserved_at_98[0x8];
 
 	u8         reserved_at_a0[0x8];
-	u8         srqn[0x18];
+	u8         srqn_xrqn[0x18];
 
 	u8         reserved_at_c0[0x8];
 	u8         pd[0x18];
@@ -2645,6 +2679,7 @@ enum {
 enum {
 	MLX5_CQ_PERIOD_MODE_START_FROM_EQE = 0x0,
 	MLX5_CQ_PERIOD_MODE_START_FROM_CQE = 0x1,
+	MLX5_CQ_PERIOD_NUM_MODES
 };
 
 struct mlx5_ifc_cqc_bits {
@@ -2722,6 +2757,54 @@ struct mlx5_ifc_query_adapter_param_block_bits {
 	u8         vsd_contd_psid[16][0x8];
 };
 
+enum {
+	MLX5_XRQC_STATE_GOOD   = 0x0,
+	MLX5_XRQC_STATE_ERROR  = 0x1,
+};
+
+enum {
+	MLX5_XRQC_TOPOLOGY_NO_SPECIAL_TOPOLOGY = 0x0,
+	MLX5_XRQC_TOPOLOGY_TAG_MATCHING        = 0x1,
+};
+
+enum {
+	MLX5_XRQC_OFFLOAD_RNDV = 0x1,
+};
+
+struct mlx5_ifc_tag_matching_topology_context_bits {
+	u8         log_matching_list_sz[0x4];
+	u8         reserved_at_4[0xc];
+	u8         append_next_index[0x10];
+
+	u8         sw_phase_cnt[0x10];
+	u8         hw_phase_cnt[0x10];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_xrqc_bits {
+	u8         state[0x4];
+	u8         rlkey[0x1];
+	u8         reserved_at_5[0xf];
+	u8         topology[0x4];
+	u8         reserved_at_18[0x4];
+	u8         offload[0x4];
+
+	u8         reserved_at_20[0x8];
+	u8         user_index[0x18];
+
+	u8         reserved_at_40[0x8];
+	u8         cqn[0x18];
+
+	u8         reserved_at_60[0xa0];
+
+	struct mlx5_ifc_tag_matching_topology_context_bits tag_matching_topology_context;
+
+	u8         reserved_at_180[0x180];
+
+	struct mlx5_ifc_wq_bits wq;
+};
+
 union mlx5_ifc_modify_field_select_resize_field_select_auto_bits {
 	struct mlx5_ifc_modify_field_select_bits modify_field_select;
 	struct mlx5_ifc_resize_field_select_bits resize_field_select;
@@ -3144,6 +3227,30 @@ struct mlx5_ifc_rst2init_qp_in_bits {
 	u8         reserved_at_800[0x80];
 };
 
+struct mlx5_ifc_query_xrq_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+
+	struct mlx5_ifc_xrqc_bits xrq_context;
+};
+
+struct mlx5_ifc_query_xrq_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x8];
+	u8         xrqn[0x18];
+
+	u8         reserved_at_60[0x20];
+};
+
 struct mlx5_ifc_query_xrc_srq_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -3547,7 +3654,27 @@ struct mlx5_ifc_query_q_counter_out_bits {
 
 	u8         out_of_sequence[0x20];
 
-	u8         reserved_at_1e0[0x620];
+	u8         reserved_at_1e0[0x20];
+
+	u8         duplicate_request[0x20];
+
+	u8         reserved_at_220[0x20];
+
+	u8         rnr_nak_retry_err[0x20];
+
+	u8         reserved_at_260[0x20];
+
+	u8         packet_seq_err[0x20];
+
+	u8         reserved_at_2a0[0x20];
+
+	u8         implied_nak_seq_err[0x20];
+
+	u8         reserved_at_2e0[0x20];
+
+	u8         local_ack_timeout_err[0x20];
+
+	u8         reserved_at_320[0x4e0];
 };
 
 struct mlx5_ifc_query_q_counter_in_bits {
@@ -4583,7 +4710,10 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits {
 };
 
 struct mlx5_ifc_modify_nic_vport_field_select_bits {
-	u8         reserved_at_0[0x19];
+	u8         reserved_at_0[0x16];
+	u8         node_guid[0x1];
+	u8         port_guid[0x1];
+	u8         reserved_at_18[0x1];
 	u8         mtu[0x1];
 	u8         change_event[0x1];
 	u8         promisc[0x1];
@@ -4998,6 +5128,28 @@ struct mlx5_ifc_detach_from_mcg_in_bits {
 	u8         multicast_gid[16][0x8];
 };
 
+struct mlx5_ifc_destroy_xrq_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_destroy_xrq_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x8];
+	u8         xrqn[0x18];
+
+	u8         reserved_at_60[0x20];
+};
+
 struct mlx5_ifc_destroy_xrc_srq_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -5583,6 +5735,30 @@ struct mlx5_ifc_dealloc_flow_counter_in_bits {
 	u8         reserved_at_60[0x20];
 };
 
+struct mlx5_ifc_create_xrq_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x8];
+	u8         xrqn[0x18];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_create_xrq_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x40];
+
+	struct mlx5_ifc_xrqc_bits xrq_context;
+};
+
 struct mlx5_ifc_create_xrc_srq_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -6124,6 +6300,29 @@ struct mlx5_ifc_attach_to_mcg_in_bits {
 	u8         multicast_gid[16][0x8];
 };
 
+struct mlx5_ifc_arm_xrq_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_arm_xrq_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x8];
+	u8         xrqn[0x18];
+
+	u8         reserved_at_60[0x10];
+	u8         lwm[0x10];
+};
+
 struct mlx5_ifc_arm_xrc_srq_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -6161,7 +6360,8 @@ struct mlx5_ifc_arm_rq_out_bits {
 };
 
 enum {
-	MLX5_ARM_RQ_IN_OP_MOD_SRQ_  = 0x1,
+	MLX5_ARM_RQ_IN_OP_MOD_SRQ = 0x1,
+	MLX5_ARM_RQ_IN_OP_MOD_XRQ = 0x2,
 };
 
 struct mlx5_ifc_arm_rq_in_bits {
@@ -6354,6 +6554,30 @@ struct mlx5_ifc_add_vxlan_udp_dport_in_bits {
 	u8         vxlan_udp_port[0x10];
 };
 
+struct mlx5_ifc_set_rate_limit_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_set_rate_limit_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x10];
+	u8         rate_limit_index[0x10];
+
+	u8         reserved_at_60[0x20];
+
+	u8         rate_limit[0x20];
+};
+
 struct mlx5_ifc_access_register_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -6478,12 +6702,15 @@ struct mlx5_ifc_pude_reg_bits {
 };
 
 struct mlx5_ifc_ptys_reg_bits {
-	u8         reserved_at_0[0x8];
+	u8         an_disable_cap[0x1];
+	u8         an_disable_admin[0x1];
+	u8         reserved_at_2[0x6];
 	u8         local_port[0x8];
 	u8         reserved_at_10[0xd];
 	u8         proto_mask[0x3];
 
-	u8         reserved_at_20[0x40];
+	u8         an_status[0x4];
+	u8         reserved_at_24[0x3c];
 
 	u8         eth_proto_capability[0x20];
 
@@ -7444,4 +7671,34 @@ struct mlx5_ifc_mcia_reg_bits {
 	u8         dword_11[0x20];
 };
 
+struct mlx5_ifc_dcbx_param_bits {
+	u8         dcbx_cee_cap[0x1];
+	u8         dcbx_ieee_cap[0x1];
+	u8         dcbx_standby_cap[0x1];
+	u8         reserved_at_0[0x5];
+	u8         port_number[0x8];
+	u8         reserved_at_10[0xa];
+	u8         max_application_table_size[6];
+	u8         reserved_at_20[0x15];
+	u8         version_oper[0x3];
+	u8         reserved_at_38[5];
+	u8         version_admin[0x3];
+	u8         willing_admin[0x1];
+	u8         reserved_at_41[0x3];
+	u8         pfc_cap_oper[0x4];
+	u8         reserved_at_48[0x4];
+	u8         pfc_cap_admin[0x4];
+	u8         reserved_at_50[0x4];
+	u8         num_of_tc_oper[0x4];
+	u8         reserved_at_58[0x4];
+	u8         num_of_tc_admin[0x4];
+	u8         remote_willing[0x1];
+	u8         reserved_at_61[3];
+	u8         remote_pfc_cap[4];
+	u8         reserved_at_68[0x14];
+	u8         remote_num_of_tc[0x4];
+	u8         reserved_at_80[0x18];
+	u8         error[0x8];
+	u8         reserved_at_a0[0x160];
+};
 #endif /* MLX5_IFC_H */
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 9851862c0ec5..e3012cc64b8a 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -47,6 +47,14 @@ enum mlx5_module_id {
 	MLX5_MODULE_ID_QSFP28           = 0x11,
 };
 
+enum mlx5_an_status {
+	MLX5_AN_UNAVAILABLE = 0,
+	MLX5_AN_COMPLETE    = 1,
+	MLX5_AN_FAILED      = 2,
+	MLX5_AN_LINK_UP     = 3,
+	MLX5_AN_LINK_DOWN   = 4,
+};
+
 #define MLX5_EEPROM_MAX_BYTES			32
 #define MLX5_EEPROM_IDENTIFIER_BYTE_MASK	0x000000ff
 #define MLX5_I2C_ADDR_LOW		0x50
@@ -65,13 +73,17 @@ int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
 int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev,
 			       u8 *proto_oper, int proto_mask,
 			       u8 local_port);
-int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin,
-			int proto_mask);
+int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable,
+		       u32 proto_admin, int proto_mask);
+void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
 int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 			       enum mlx5_port_status status);
 int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 				 enum mlx5_port_status *status);
 int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration);
+void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask,
+			     u8 *an_status,
+			     u8 *an_disable_cap, u8 *an_disable_admin);
 
 int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
 void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port);
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 64221027bf1f..ab310819ac36 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -172,6 +172,7 @@ enum {
 enum {
 	MLX5_FENCE_MODE_NONE			= 0 << 5,
 	MLX5_FENCE_MODE_INITIATOR_SMALL		= 1 << 5,
+	MLX5_FENCE_MODE_FENCE			= 2 << 5,
 	MLX5_FENCE_MODE_STRONG_ORDERING		= 3 << 5,
 	MLX5_FENCE_MODE_SMALL_AND_FENCE		= 4 << 5,
 };
@@ -460,10 +461,9 @@ struct mlx5_core_qp {
 };
 
 struct mlx5_qp_path {
-	u8			fl;
+	u8			fl_free_ar;
 	u8			rsvd3;
-	u8			free_ar;
-	u8			pkey_index;
+	__be16			pkey_index;
 	u8			rsvd0;
 	u8			grh_mlid;
 	__be16			rlid;
@@ -560,6 +560,7 @@ struct mlx5_modify_qp_mbox_in {
 	__be32			optparam;
 	u8			rsvd0[4];
 	struct mlx5_qp_context	ctx;
+	u8			rsvd2[16];
 };
 
 struct mlx5_modify_qp_mbox_out {
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 301da4a5e6bf..6c16c198f680 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -50,6 +50,8 @@ int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu);
 int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 					   u64 *system_image_guid);
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
+int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
+				    u32 vport, u64 node_guid);
 int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
 					u16 *qkey_viol_cntr);
 int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5df5feb49575..ece042dfe23c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -602,7 +602,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 }
 
 void do_set_pte(struct vm_area_struct *vma, unsigned long address,
-		struct page *page, pte_t *pte, bool write, bool anon, bool old);
+		struct page *page, pte_t *pte, bool write, bool anon);
 #endif
 
 /*
diff --git a/include/linux/namei.h b/include/linux/namei.h
index ec5ec2818a28..d3d0398f2a1b 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -45,6 +45,8 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_ROOT		0x2000
 #define LOOKUP_EMPTY		0x4000
 
+extern int path_pts(struct path *path);
+
 extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);
 
 static inline int user_path_at(int dfd, const char __user *name, unsigned flags,
diff --git a/include/linux/net.h b/include/linux/net.h
index 9aa49a05fe38..b9f0ff4d489c 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -185,6 +185,7 @@ struct proto_ops {
 	ssize_t 	(*splice_read)(struct socket *sock,  loff_t *ppos,
 				       struct pipe_inode_info *pipe, size_t len, unsigned int flags);
 	int		(*set_peek_off)(struct sock *sk, int val);
+	int		(*peek_len)(struct socket *sock);
 };
 
 #define DECLARE_SOCKADDR(type, dst, src)	\
@@ -251,7 +252,8 @@ do {									\
 	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
 	if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) &&	\
 	    net_ratelimit())						\
-		__dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__);	\
+		__dynamic_pr_debug(&descriptor, pr_fmt(fmt),		\
+		                   ##__VA_ARGS__);			\
 } while (0)
 #elif defined(DEBUG)
 #define net_dbg_ratelimited(fmt, ...)				\
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fa6df2699532..49736a31acaa 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -61,6 +61,8 @@ struct wireless_dev;
 /* 802.15.4 specific */
 struct wpan_dev;
 struct mpls_dev;
+/* UDP Tunnel offloads */
+struct udp_tunnel_info;
 
 void netdev_set_default_ethtool_ops(struct net_device *dev,
 				    const struct ethtool_ops *ops);
@@ -90,7 +92,6 @@ void netdev_set_default_ethtool_ops(struct net_device *dev,
 #define NET_XMIT_SUCCESS	0x00
 #define NET_XMIT_DROP		0x01	/* skb dropped			*/
 #define NET_XMIT_CN		0x02	/* congestion notification	*/
-#define NET_XMIT_POLICED	0x03	/* skb is shot by police	*/
 #define NET_XMIT_MASK		0x0f	/* qdisc flags in net/sch_generic.h */
 
 /* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It
@@ -1025,31 +1026,18 @@ struct tc_to_netdev {
  *	not implement this, it is assumed that the hw is not able to have
  *	multiple net devices on single physical port.
  *
- * void (*ndo_add_vxlan_port)(struct  net_device *dev,
- *			      sa_family_t sa_family, __be16 port);
- *	Called by vxlan to notify a driver about the UDP port and socket
- *	address family that vxlan is listening to. It is called only when
- *	a new port starts listening. The operation is protected by the
- *	vxlan_net->sock_lock.
- *
- * void (*ndo_add_geneve_port)(struct net_device *dev,
- *			       sa_family_t sa_family, __be16 port);
- *	Called by geneve to notify a driver about the UDP port and socket
- *	address family that geneve is listnening to. It is called only when
- *	a new port starts listening. The operation is protected by the
- *	geneve_net->sock_lock.
- *
- * void (*ndo_del_geneve_port)(struct net_device *dev,
- *			       sa_family_t sa_family, __be16 port);
- *	Called by geneve to notify the driver about a UDP port and socket
- *	address family that geneve is not listening to anymore. The operation
- *	is protected by the geneve_net->sock_lock.
- *
- * void (*ndo_del_vxlan_port)(struct  net_device *dev,
- *			      sa_family_t sa_family, __be16 port);
- *	Called by vxlan to notify the driver about a UDP port and socket
- *	address family that vxlan is not listening to anymore. The operation
- *	is protected by the vxlan_net->sock_lock.
+ * void (*ndo_udp_tunnel_add)(struct net_device *dev,
+ *			      struct udp_tunnel_info *ti);
+ *	Called by UDP tunnel to notify a driver about the UDP port and socket
+ *	address family that a UDP tunnel is listnening to. It is called only
+ *	when a new port starts listening. The operation is protected by the
+ *	RTNL.
+ *
+ * void (*ndo_udp_tunnel_del)(struct net_device *dev,
+ *			      struct udp_tunnel_info *ti);
+ *	Called by UDP tunnel to notify the driver about a UDP port and socket
+ *	address family that the UDP tunnel is not listening to anymore. The
+ *	operation is protected by the RTNL.
  *
  * void* (*ndo_dfwd_add_station)(struct net_device *pdev,
  *				 struct net_device *dev)
@@ -1221,8 +1209,10 @@ struct net_device_ops {
 						    netdev_features_t features);
 	int			(*ndo_set_features)(struct net_device *dev,
 						    netdev_features_t features);
-	int			(*ndo_neigh_construct)(struct neighbour *n);
-	void			(*ndo_neigh_destroy)(struct neighbour *n);
+	int			(*ndo_neigh_construct)(struct net_device *dev,
+						       struct neighbour *n);
+	void			(*ndo_neigh_destroy)(struct net_device *dev,
+						     struct neighbour *n);
 
 	int			(*ndo_fdb_add)(struct ndmsg *ndm,
 					       struct nlattr *tb[],
@@ -1258,18 +1248,10 @@ struct net_device_ops {
 							struct netdev_phys_item_id *ppid);
 	int			(*ndo_get_phys_port_name)(struct net_device *dev,
 							  char *name, size_t len);
-	void			(*ndo_add_vxlan_port)(struct  net_device *dev,
-						      sa_family_t sa_family,
-						      __be16 port);
-	void			(*ndo_del_vxlan_port)(struct  net_device *dev,
-						      sa_family_t sa_family,
-						      __be16 port);
-	void			(*ndo_add_geneve_port)(struct  net_device *dev,
-						       sa_family_t sa_family,
-						       __be16 port);
-	void			(*ndo_del_geneve_port)(struct  net_device *dev,
-						       sa_family_t sa_family,
-						       __be16 port);
+	void			(*ndo_udp_tunnel_add)(struct net_device *dev,
+						      struct udp_tunnel_info *ti);
+	void			(*ndo_udp_tunnel_del)(struct net_device *dev,
+						      struct udp_tunnel_info *ti);
 	void*			(*ndo_dfwd_add_station)(struct net_device *pdev,
 							struct net_device *dev);
 	void			(*ndo_dfwd_del_station)(struct net_device *pdev,
@@ -1457,6 +1439,8 @@ enum netdev_priv_flags {
  *	@netdev_ops:	Includes several pointers to callbacks,
  *			if one wants to override the ndo_*() functions
  *	@ethtool_ops:	Management operations
+ *	@ndisc_ops:	Includes callbacks for different IPv6 neighbour
+ *			discovery handling. Necessary for e.g. 6LoWPAN.
  *	@header_ops:	Includes callbacks for creating,parsing,caching,etc
  *			of Layer 2 headers.
  *
@@ -1484,8 +1468,7 @@ enum netdev_priv_flags {
  * 	@perm_addr:		Permanent hw address
  * 	@addr_assign_type:	Hw address assignment type
  * 	@addr_len:		Hardware address length
- * 	@neigh_priv_len;	Used in neigh_alloc(),
- * 				initialized only in atm/clip.c
+ *	@neigh_priv_len:	Used in neigh_alloc()
  * 	@dev_id:		Used to differentiate devices that share
  * 				the same link layer address
  * 	@dev_port:		Used to differentiate devices that share
@@ -1594,7 +1577,8 @@ enum netdev_priv_flags {
  *	@phydev:	Physical device may attach itself
  *			for hardware timestamping
  *
- *	@qdisc_tx_busylock:	XXX: need comments on this one
+ *	@qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock
+ *	@qdisc_running_key: lockdep class annotating Qdisc->running seqcount
  *
  *	@proto_down:	protocol port state information can be sent to the
  *			switch driver and used to set the phys state of the
@@ -1673,6 +1657,9 @@ struct net_device {
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	const struct l3mdev_ops	*l3mdev_ops;
 #endif
+#if IS_ENABLED(CONFIG_IPV6)
+	const struct ndisc_ops *ndisc_ops;
+#endif
 
 	const struct header_ops *header_ops;
 
@@ -1862,6 +1849,7 @@ struct net_device {
 #endif
 	struct phy_device	*phydev;
 	struct lock_class_key	*qdisc_tx_busylock;
+	struct lock_class_key	*qdisc_running_key;
 	bool			proto_down;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
@@ -1944,6 +1932,23 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 		f(dev, &dev->_tx[i], arg);
 }
 
+#define netdev_lockdep_set_classes(dev)				\
+{								\
+	static struct lock_class_key qdisc_tx_busylock_key;	\
+	static struct lock_class_key qdisc_running_key;		\
+	static struct lock_class_key qdisc_xmit_lock_key;	\
+	static struct lock_class_key dev_addr_list_lock_key;	\
+	unsigned int i;						\
+								\
+	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
+	(dev)->qdisc_running_key = &qdisc_running_key;		\
+	lockdep_set_class(&(dev)->addr_list_lock,		\
+			  &dev_addr_list_lock_key); 		\
+	for (i = 0; i < (dev)->num_tx_queues; i++)		\
+		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
+				  &qdisc_xmit_lock_key);	\
+}
+
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
 				    void *accel_priv);
@@ -2233,8 +2238,8 @@ struct netdev_lag_lower_state_info {
 #define NETDEV_BONDING_INFO	0x0019
 #define NETDEV_PRECHANGEUPPER	0x001A
 #define NETDEV_CHANGELOWERSTATE	0x001B
-#define NETDEV_OFFLOAD_PUSH_VXLAN	0x001C
-#define NETDEV_OFFLOAD_PUSH_GENEVE	0x001D
+#define NETDEV_UDP_TUNNEL_PUSH_INFO	0x001C
+#define NETDEV_CHANGE_TX_QUEUE_LEN	0x001E
 
 int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
@@ -2370,6 +2375,8 @@ void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
 DECLARE_PER_CPU(int, xmit_recursion);
+#define XMIT_RECURSION_LIMIT	10
+
 static inline int dev_recursion_level(void)
 {
 	return this_cpu_read(xmit_recursion);
@@ -3799,12 +3806,30 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 
 void *netdev_lower_get_next(struct net_device *dev,
 				struct list_head **iter);
+
 #define netdev_for_each_lower_dev(dev, ldev, iter) \
 	for (iter = (dev)->adj_list.lower.next, \
 	     ldev = netdev_lower_get_next(dev, &(iter)); \
 	     ldev; \
 	     ldev = netdev_lower_get_next(dev, &(iter)))
 
+struct net_device *netdev_all_lower_get_next(struct net_device *dev,
+					     struct list_head **iter);
+struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
+						 struct list_head **iter);
+
+#define netdev_for_each_all_lower_dev(dev, ldev, iter) \
+	for (iter = (dev)->all_adj_list.lower.next, \
+	     ldev = netdev_all_lower_get_next(dev, &(iter)); \
+	     ldev; \
+	     ldev = netdev_all_lower_get_next(dev, &(iter)))
+
+#define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \
+	for (iter = (dev)->all_adj_list.lower.next, \
+	     ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \
+	     ldev; \
+	     ldev = netdev_all_lower_get_next_rcu(dev, &(iter)))
+
 void *netdev_adjacent_get_private(struct list_head *adj_list);
 void *netdev_lower_get_first_private_rcu(struct net_device *dev);
 struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
@@ -3820,6 +3845,10 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev);
 void netdev_lower_state_changed(struct net_device *lower_dev,
 				void *lower_state_info);
+int netdev_default_l2upper_neigh_construct(struct net_device *dev,
+					   struct neighbour *n);
+void netdev_default_l2upper_neigh_destroy(struct net_device *dev,
+					  struct neighbour *n);
 
 /* RSS keys are 40 or 52 bytes long */
 #define NETDEV_RSS_KEY_LEN 52
diff --git a/include/linux/of.h b/include/linux/of.h
index c7292e8ea080..74eb28cadbef 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -614,7 +614,7 @@ static inline struct device_node *of_parse_phandle(const struct device_node *np,
 	return NULL;
 }
 
-static inline int of_parse_phandle_with_args(struct device_node *np,
+static inline int of_parse_phandle_with_args(const struct device_node *np,
 					     const char *list_name,
 					     const char *cells_name,
 					     int index,
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index 8f2237eb3485..4b04587d0441 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -25,6 +25,8 @@ struct phy_device *of_phy_attach(struct net_device *dev,
 
 extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np);
 extern int of_mdio_parse_addr(struct device *dev, const struct device_node *np);
+extern int of_phy_register_fixed_link(struct device_node *np);
+extern bool of_phy_is_fixed_link(struct device_node *np);
 
 #else /* CONFIG_OF */
 static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
@@ -67,12 +69,6 @@ static inline int of_mdio_parse_addr(struct device *dev,
 {
 	return -ENOSYS;
 }
-#endif /* CONFIG_OF */
-
-#if defined(CONFIG_OF) && defined(CONFIG_FIXED_PHY)
-extern int of_phy_register_fixed_link(struct device_node *np);
-extern bool of_phy_is_fixed_link(struct device_node *np);
-#else
 static inline int of_phy_register_fixed_link(struct device_node *np)
 {
 	return -ENOSYS;
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index f6e9e85164e8..b969e9443962 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -8,7 +8,7 @@ struct pci_dev;
 struct of_phandle_args;
 struct device_node;
 
-#ifdef CONFIG_OF
+#ifdef CONFIG_OF_PCI
 int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq);
 struct device_node *of_pci_find_child_device(struct device_node *parent,
 					     unsigned int devfn);
diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h
index ad2f67054372..c201060e0c6d 100644
--- a/include/linux/of_reserved_mem.h
+++ b/include/linux/of_reserved_mem.h
@@ -31,6 +31,13 @@ typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem);
 int of_reserved_mem_device_init(struct device *dev);
 void of_reserved_mem_device_release(struct device *dev);
 
+int early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
+					     phys_addr_t align,
+					     phys_addr_t start,
+					     phys_addr_t end,
+					     bool nomap,
+					     phys_addr_t *res_base);
+
 void fdt_init_reserved_mem(void);
 void fdt_reserved_mem_save_node(unsigned long node, const char *uname,
 			       phys_addr_t base, phys_addr_t size);
diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h
index bf268fa92c5b..fec40271339f 100644
--- a/include/linux/page_idle.h
+++ b/include/linux/page_idle.h
@@ -46,33 +46,62 @@ extern struct page_ext_operations page_idle_ops;
 
 static inline bool page_is_young(struct page *page)
 {
-	return test_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return false;
+
+	return test_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
 static inline void set_page_young(struct page *page)
 {
-	set_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return;
+
+	set_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
 static inline bool test_and_clear_page_young(struct page *page)
 {
-	return test_and_clear_bit(PAGE_EXT_YOUNG,
-				  &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return false;
+
+	return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
 static inline bool page_is_idle(struct page *page)
 {
-	return test_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return false;
+
+	return test_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
 
 static inline void set_page_idle(struct page *page)
 {
-	set_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return;
+
+	set_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
 
 static inline void clear_page_idle(struct page *page)
 {
-	clear_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return;
+
+	clear_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
 #endif /* CONFIG_64BIT */
 
diff --git a/include/linux/platform_data/b53.h b/include/linux/platform_data/b53.h
new file mode 100644
index 000000000000..69d279c0da96
--- /dev/null
+++ b/include/linux/platform_data/b53.h
@@ -0,0 +1,33 @@
+/*
+ * B53 platform data
+ *
+ * Copyright (C) 2013 Jonas Gorski <[email protected]>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef __B53_H
+#define __B53_H
+
+#include <linux/kernel.h>
+
+struct b53_platform_data {
+	u32 chip_id;
+	u16 enabled_ports;
+
+	/* only used by MMAP'd driver */
+	unsigned big_endian:1;
+	void __iomem *regs;
+};
+
+#endif
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
new file mode 100644
index 000000000000..2052011bf9fb
--- /dev/null
+++ b/include/linux/ptr_ring.h
@@ -0,0 +1,448 @@
+/*
+ *	Definitions for the 'struct ptr_ring' datastructure.
+ *
+ *	Author:
+ *		Michael S. Tsirkin <[email protected]>
+ *
+ *	Copyright (C) 2016 Red Hat, Inc.
+ *
+ *	This program is free software; you can redistribute it and/or modify it
+ *	under the terms of the GNU General Public License as published by the
+ *	Free Software Foundation; either version 2 of the License, or (at your
+ *	option) any later version.
+ *
+ *	This is a limited-size FIFO maintaining pointers in FIFO order, with
+ *	one CPU producing entries and another consuming entries from a FIFO.
+ *
+ *	This implementation tries to minimize cache-contention when there is a
+ *	single producer and a single consumer CPU.
+ */
+
+#ifndef _LINUX_PTR_RING_H
+#define _LINUX_PTR_RING_H 1
+
+#ifdef __KERNEL__
+#include <linux/spinlock.h>
+#include <linux/cache.h>
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/cache.h>
+#include <linux/slab.h>
+#include <asm/errno.h>
+#endif
+
+struct ptr_ring {
+	int producer ____cacheline_aligned_in_smp;
+	spinlock_t producer_lock;
+	int consumer ____cacheline_aligned_in_smp;
+	spinlock_t consumer_lock;
+	/* Shared consumer/producer data */
+	/* Read-only by both the producer and the consumer */
+	int size ____cacheline_aligned_in_smp; /* max entries in queue */
+	void **queue;
+};
+
+/* Note: callers invoking this in a loop must use a compiler barrier,
+ * for example cpu_relax().  If ring is ever resized, callers must hold
+ * producer_lock - see e.g. ptr_ring_full.  Otherwise, if callers don't hold
+ * producer_lock, the next call to __ptr_ring_produce may fail.
+ */
+static inline bool __ptr_ring_full(struct ptr_ring *r)
+{
+	return r->queue[r->producer];
+}
+
+static inline bool ptr_ring_full(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock(&r->producer_lock);
+	ret = __ptr_ring_full(r);
+	spin_unlock(&r->producer_lock);
+
+	return ret;
+}
+
+static inline bool ptr_ring_full_irq(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock_irq(&r->producer_lock);
+	ret = __ptr_ring_full(r);
+	spin_unlock_irq(&r->producer_lock);
+
+	return ret;
+}
+
+static inline bool ptr_ring_full_any(struct ptr_ring *r)
+{
+	unsigned long flags;
+	bool ret;
+
+	spin_lock_irqsave(&r->producer_lock, flags);
+	ret = __ptr_ring_full(r);
+	spin_unlock_irqrestore(&r->producer_lock, flags);
+
+	return ret;
+}
+
+static inline bool ptr_ring_full_bh(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock_bh(&r->producer_lock);
+	ret = __ptr_ring_full(r);
+	spin_unlock_bh(&r->producer_lock);
+
+	return ret;
+}
+
+/* Note: callers invoking this in a loop must use a compiler barrier,
+ * for example cpu_relax(). Callers must hold producer_lock.
+ */
+static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
+{
+	if (unlikely(!r->size) || r->queue[r->producer])
+		return -ENOSPC;
+
+	r->queue[r->producer++] = ptr;
+	if (unlikely(r->producer >= r->size))
+		r->producer = 0;
+	return 0;
+}
+
+static inline int ptr_ring_produce(struct ptr_ring *r, void *ptr)
+{
+	int ret;
+
+	spin_lock(&r->producer_lock);
+	ret = __ptr_ring_produce(r, ptr);
+	spin_unlock(&r->producer_lock);
+
+	return ret;
+}
+
+static inline int ptr_ring_produce_irq(struct ptr_ring *r, void *ptr)
+{
+	int ret;
+
+	spin_lock_irq(&r->producer_lock);
+	ret = __ptr_ring_produce(r, ptr);
+	spin_unlock_irq(&r->producer_lock);
+
+	return ret;
+}
+
+static inline int ptr_ring_produce_any(struct ptr_ring *r, void *ptr)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&r->producer_lock, flags);
+	ret = __ptr_ring_produce(r, ptr);
+	spin_unlock_irqrestore(&r->producer_lock, flags);
+
+	return ret;
+}
+
+static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr)
+{
+	int ret;
+
+	spin_lock_bh(&r->producer_lock);
+	ret = __ptr_ring_produce(r, ptr);
+	spin_unlock_bh(&r->producer_lock);
+
+	return ret;
+}
+
+/* Note: callers invoking this in a loop must use a compiler barrier,
+ * for example cpu_relax(). Callers must take consumer_lock
+ * if they dereference the pointer - see e.g. PTR_RING_PEEK_CALL.
+ * If ring is never resized, and if the pointer is merely
+ * tested, there's no need to take the lock - see e.g.  __ptr_ring_empty.
+ */
+static inline void *__ptr_ring_peek(struct ptr_ring *r)
+{
+	if (likely(r->size))
+		return r->queue[r->consumer];
+	return NULL;
+}
+
+/* Note: callers invoking this in a loop must use a compiler barrier,
+ * for example cpu_relax(). Callers must take consumer_lock
+ * if the ring is ever resized - see e.g. ptr_ring_empty.
+ */
+static inline bool __ptr_ring_empty(struct ptr_ring *r)
+{
+	return !__ptr_ring_peek(r);
+}
+
+static inline bool ptr_ring_empty(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock(&r->consumer_lock);
+	ret = __ptr_ring_empty(r);
+	spin_unlock(&r->consumer_lock);
+
+	return ret;
+}
+
+static inline bool ptr_ring_empty_irq(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock_irq(&r->consumer_lock);
+	ret = __ptr_ring_empty(r);
+	spin_unlock_irq(&r->consumer_lock);
+
+	return ret;
+}
+
+static inline bool ptr_ring_empty_any(struct ptr_ring *r)
+{
+	unsigned long flags;
+	bool ret;
+
+	spin_lock_irqsave(&r->consumer_lock, flags);
+	ret = __ptr_ring_empty(r);
+	spin_unlock_irqrestore(&r->consumer_lock, flags);
+
+	return ret;
+}
+
+static inline bool ptr_ring_empty_bh(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock_bh(&r->consumer_lock);
+	ret = __ptr_ring_empty(r);
+	spin_unlock_bh(&r->consumer_lock);
+
+	return ret;
+}
+
+/* Must only be called after __ptr_ring_peek returned !NULL */
+static inline void __ptr_ring_discard_one(struct ptr_ring *r)
+{
+	r->queue[r->consumer++] = NULL;
+	if (unlikely(r->consumer >= r->size))
+		r->consumer = 0;
+}
+
+static inline void *__ptr_ring_consume(struct ptr_ring *r)
+{
+	void *ptr;
+
+	ptr = __ptr_ring_peek(r);
+	if (ptr)
+		__ptr_ring_discard_one(r);
+
+	return ptr;
+}
+
+static inline void *ptr_ring_consume(struct ptr_ring *r)
+{
+	void *ptr;
+
+	spin_lock(&r->consumer_lock);
+	ptr = __ptr_ring_consume(r);
+	spin_unlock(&r->consumer_lock);
+
+	return ptr;
+}
+
+static inline void *ptr_ring_consume_irq(struct ptr_ring *r)
+{
+	void *ptr;
+
+	spin_lock_irq(&r->consumer_lock);
+	ptr = __ptr_ring_consume(r);
+	spin_unlock_irq(&r->consumer_lock);
+
+	return ptr;
+}
+
+static inline void *ptr_ring_consume_any(struct ptr_ring *r)
+{
+	unsigned long flags;
+	void *ptr;
+
+	spin_lock_irqsave(&r->consumer_lock, flags);
+	ptr = __ptr_ring_consume(r);
+	spin_unlock_irqrestore(&r->consumer_lock, flags);
+
+	return ptr;
+}
+
+static inline void *ptr_ring_consume_bh(struct ptr_ring *r)
+{
+	void *ptr;
+
+	spin_lock_bh(&r->consumer_lock);
+	ptr = __ptr_ring_consume(r);
+	spin_unlock_bh(&r->consumer_lock);
+
+	return ptr;
+}
+
+/* Cast to structure type and call a function without discarding from FIFO.
+ * Function must return a value.
+ * Callers must take consumer_lock.
+ */
+#define __PTR_RING_PEEK_CALL(r, f) ((f)(__ptr_ring_peek(r)))
+
+#define PTR_RING_PEEK_CALL(r, f) ({ \
+	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
+	\
+	spin_lock(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
+	spin_unlock(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v; \
+})
+
+#define PTR_RING_PEEK_CALL_IRQ(r, f) ({ \
+	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
+	\
+	spin_lock_irq(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
+	spin_unlock_irq(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v; \
+})
+
+#define PTR_RING_PEEK_CALL_BH(r, f) ({ \
+	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
+	\
+	spin_lock_bh(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
+	spin_unlock_bh(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v; \
+})
+
+#define PTR_RING_PEEK_CALL_ANY(r, f) ({ \
+	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
+	unsigned long __PTR_RING_PEEK_CALL_f;\
+	\
+	spin_lock_irqsave(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \
+	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
+	spin_unlock_irqrestore(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \
+	__PTR_RING_PEEK_CALL_v; \
+})
+
+static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp)
+{
+	return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp);
+}
+
+static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp)
+{
+	r->queue = __ptr_ring_init_queue_alloc(size, gfp);
+	if (!r->queue)
+		return -ENOMEM;
+
+	r->size = size;
+	r->producer = r->consumer = 0;
+	spin_lock_init(&r->producer_lock);
+	spin_lock_init(&r->consumer_lock);
+
+	return 0;
+}
+
+static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
+					   int size, gfp_t gfp,
+					   void (*destroy)(void *))
+{
+	int producer = 0;
+	void **old;
+	void *ptr;
+
+	while ((ptr = ptr_ring_consume(r)))
+		if (producer < size)
+			queue[producer++] = ptr;
+		else if (destroy)
+			destroy(ptr);
+
+	r->size = size;
+	r->producer = producer;
+	r->consumer = 0;
+	old = r->queue;
+	r->queue = queue;
+
+	return old;
+}
+
+static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
+				  void (*destroy)(void *))
+{
+	unsigned long flags;
+	void **queue = __ptr_ring_init_queue_alloc(size, gfp);
+	void **old;
+
+	if (!queue)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&(r)->producer_lock, flags);
+
+	old = __ptr_ring_swap_queue(r, queue, size, gfp, destroy);
+
+	spin_unlock_irqrestore(&(r)->producer_lock, flags);
+
+	kfree(old);
+
+	return 0;
+}
+
+static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
+					   int size,
+					   gfp_t gfp, void (*destroy)(void *))
+{
+	unsigned long flags;
+	void ***queues;
+	int i;
+
+	queues = kmalloc(nrings * sizeof *queues, gfp);
+	if (!queues)
+		goto noqueues;
+
+	for (i = 0; i < nrings; ++i) {
+		queues[i] = __ptr_ring_init_queue_alloc(size, gfp);
+		if (!queues[i])
+			goto nomem;
+	}
+
+	for (i = 0; i < nrings; ++i) {
+		spin_lock_irqsave(&(rings[i])->producer_lock, flags);
+		queues[i] = __ptr_ring_swap_queue(rings[i], queues[i],
+						  size, gfp, destroy);
+		spin_unlock_irqrestore(&(rings[i])->producer_lock, flags);
+	}
+
+	for (i = 0; i < nrings; ++i)
+		kfree(queues[i]);
+
+	kfree(queues);
+
+	return 0;
+
+nomem:
+	while (--i >= 0)
+		kfree(queues[i]);
+
+	kfree(queues);
+
+noqueues:
+	return -ENOMEM;
+}
+
+static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *))
+{
+	void *ptr;
+
+	if (destroy)
+		while ((ptr = ptr_ring_consume(r)))
+			destroy(ptr);
+	kfree(r->queue);
+}
+
+#endif /* _LINUX_PTR_RING_H  */
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 17018f3c066e..908b67c847cd 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -235,6 +235,9 @@ static inline int pwm_config(struct pwm_device *pwm, int duty_ns,
 	if (!pwm)
 		return -EINVAL;
 
+	if (duty_ns < 0 || period_ns < 0)
+		return -EINVAL;
+
 	pwm_get_state(pwm, &state);
 	if (state.duty_cycle == duty_ns && state.period == period_ns)
 		return 0;
diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h
index f8ff71126d9e..4475a9d8ae15 100644
--- a/include/linux/qed/qed_eth_if.h
+++ b/include/linux/qed/qed_eth_if.h
@@ -49,6 +49,7 @@ struct qed_start_vport_params {
 	bool drop_ttl0;
 	u8 vport_id;
 	u16 mtu;
+	bool clear_stats;
 };
 
 struct qed_stop_rxq_params {
@@ -128,11 +129,73 @@ struct qed_eth_cb_ops {
 	void (*force_mac) (void *dev, u8 *mac);
 };
 
+#ifdef CONFIG_DCB
+/* Prototype declaration of qed_eth_dcbnl_ops should match with the declaration
+ * of dcbnl_rtnl_ops structure.
+ */
+struct qed_eth_dcbnl_ops {
+	/* IEEE 802.1Qaz std */
+	int (*ieee_getpfc)(struct qed_dev *cdev, struct ieee_pfc *pfc);
+	int (*ieee_setpfc)(struct qed_dev *cdev, struct ieee_pfc *pfc);
+	int (*ieee_getets)(struct qed_dev *cdev, struct ieee_ets *ets);
+	int (*ieee_setets)(struct qed_dev *cdev, struct ieee_ets *ets);
+	int (*ieee_peer_getets)(struct qed_dev *cdev, struct ieee_ets *ets);
+	int (*ieee_peer_getpfc)(struct qed_dev *cdev, struct ieee_pfc *pfc);
+	int (*ieee_getapp)(struct qed_dev *cdev, struct dcb_app *app);
+	int (*ieee_setapp)(struct qed_dev *cdev, struct dcb_app *app);
+
+	/* CEE std */
+	u8 (*getstate)(struct qed_dev *cdev);
+	u8 (*setstate)(struct qed_dev *cdev, u8 state);
+	void (*getpgtccfgtx)(struct qed_dev *cdev, int prio, u8 *prio_type,
+			     u8 *pgid, u8 *bw_pct, u8 *up_map);
+	void (*getpgbwgcfgtx)(struct qed_dev *cdev, int pgid, u8 *bw_pct);
+	void (*getpgtccfgrx)(struct qed_dev *cdev, int prio, u8 *prio_type,
+			     u8 *pgid, u8 *bw_pct, u8 *up_map);
+	void (*getpgbwgcfgrx)(struct qed_dev *cdev, int pgid, u8 *bw_pct);
+	void (*getpfccfg)(struct qed_dev *cdev, int prio, u8 *setting);
+	void (*setpfccfg)(struct qed_dev *cdev, int prio, u8 setting);
+	u8 (*getcap)(struct qed_dev *cdev, int capid, u8 *cap);
+	int (*getnumtcs)(struct qed_dev *cdev, int tcid, u8 *num);
+	u8 (*getpfcstate)(struct qed_dev *cdev);
+	int (*getapp)(struct qed_dev *cdev, u8 idtype, u16 id);
+	u8 (*getfeatcfg)(struct qed_dev *cdev, int featid, u8 *flags);
+
+	/* DCBX configuration */
+	u8 (*getdcbx)(struct qed_dev *cdev);
+	void (*setpgtccfgtx)(struct qed_dev *cdev, int prio,
+			     u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map);
+	void (*setpgtccfgrx)(struct qed_dev *cdev, int prio,
+			     u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map);
+	void (*setpgbwgcfgtx)(struct qed_dev *cdev, int pgid, u8 bw_pct);
+	void (*setpgbwgcfgrx)(struct qed_dev *cdev, int pgid, u8 bw_pct);
+	u8 (*setall)(struct qed_dev *cdev);
+	int (*setnumtcs)(struct qed_dev *cdev, int tcid, u8 num);
+	void (*setpfcstate)(struct qed_dev *cdev, u8 state);
+	int (*setapp)(struct qed_dev *cdev, u8 idtype, u16 idval, u8 up);
+	u8 (*setdcbx)(struct qed_dev *cdev, u8 state);
+	u8 (*setfeatcfg)(struct qed_dev *cdev, int featid, u8 flags);
+
+	/* Peer apps */
+	int (*peer_getappinfo)(struct qed_dev *cdev,
+			       struct dcb_peer_app_info *info,
+			       u16 *app_count);
+	int (*peer_getapptable)(struct qed_dev *cdev, struct dcb_app *table);
+
+	/* CEE peer */
+	int (*cee_peer_getpfc)(struct qed_dev *cdev, struct cee_pfc *pfc);
+	int (*cee_peer_getpg)(struct qed_dev *cdev, struct cee_pg *pg);
+};
+#endif
+
 struct qed_eth_ops {
 	const struct qed_common_ops *common;
 #ifdef CONFIG_QED_SRIOV
 	const struct qed_iov_hv_ops *iov;
 #endif
+#ifdef CONFIG_DCB
+	const struct qed_eth_dcbnl_ops *dcb;
+#endif
 
 	int (*fill_dev_info)(struct qed_dev *cdev,
 			     struct qed_dev_eth_info *info);
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index e8cc49f9688a..b1e3c57c7117 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -34,6 +34,96 @@ enum dcbx_protocol_type {
 	DCBX_MAX_PROTOCOL_TYPE
 };
 
+#ifdef CONFIG_DCB
+#define QED_LLDP_CHASSIS_ID_STAT_LEN 4
+#define QED_LLDP_PORT_ID_STAT_LEN 4
+#define QED_DCBX_MAX_APP_PROTOCOL 32
+#define QED_MAX_PFC_PRIORITIES 8
+#define QED_DCBX_DSCP_SIZE 64
+
+struct qed_dcbx_lldp_remote {
+	u32 peer_chassis_id[QED_LLDP_CHASSIS_ID_STAT_LEN];
+	u32 peer_port_id[QED_LLDP_PORT_ID_STAT_LEN];
+	bool enable_rx;
+	bool enable_tx;
+	u32 tx_interval;
+	u32 max_credit;
+};
+
+struct qed_dcbx_lldp_local {
+	u32 local_chassis_id[QED_LLDP_CHASSIS_ID_STAT_LEN];
+	u32 local_port_id[QED_LLDP_PORT_ID_STAT_LEN];
+};
+
+struct qed_dcbx_app_prio {
+	u8 roce;
+	u8 roce_v2;
+	u8 fcoe;
+	u8 iscsi;
+	u8 eth;
+};
+
+struct qed_dbcx_pfc_params {
+	bool willing;
+	bool enabled;
+	u8 prio[QED_MAX_PFC_PRIORITIES];
+	u8 max_tc;
+};
+
+struct qed_app_entry {
+	bool ethtype;
+	bool enabled;
+	u8 prio;
+	u16 proto_id;
+	enum dcbx_protocol_type proto_type;
+};
+
+struct qed_dcbx_params {
+	struct qed_app_entry app_entry[QED_DCBX_MAX_APP_PROTOCOL];
+	u16 num_app_entries;
+	bool app_willing;
+	bool app_valid;
+	bool app_error;
+	bool ets_willing;
+	bool ets_enabled;
+	bool ets_cbs;
+	bool valid;
+	u8 ets_pri_tc_tbl[QED_MAX_PFC_PRIORITIES];
+	u8 ets_tc_bw_tbl[QED_MAX_PFC_PRIORITIES];
+	u8 ets_tc_tsa_tbl[QED_MAX_PFC_PRIORITIES];
+	struct qed_dbcx_pfc_params pfc;
+	u8 max_ets_tc;
+};
+
+struct qed_dcbx_admin_params {
+	struct qed_dcbx_params params;
+	bool valid;
+};
+
+struct qed_dcbx_remote_params {
+	struct qed_dcbx_params params;
+	bool valid;
+};
+
+struct qed_dcbx_operational_params {
+	struct qed_dcbx_app_prio app_prio;
+	struct qed_dcbx_params params;
+	bool valid;
+	bool enabled;
+	bool ieee;
+	bool cee;
+	u32 err;
+};
+
+struct qed_dcbx_get {
+	struct qed_dcbx_operational_params operational;
+	struct qed_dcbx_lldp_remote lldp_remote;
+	struct qed_dcbx_lldp_local lldp_local;
+	struct qed_dcbx_remote_params remote;
+	struct qed_dcbx_admin_params local;
+};
+#endif
+
 enum qed_led_mode {
 	QED_LED_MODE_OFF,
 	QED_LED_MODE_ON,
@@ -399,6 +489,30 @@ struct qed_common_ops {
 				      struct qed_chain *p_chain);
 
 /**
+ * @brief get_coalesce - Get coalesce parameters in usec
+ *
+ * @param cdev
+ * @param rx_coal - Rx coalesce value in usec
+ * @param tx_coal - Tx coalesce value in usec
+ *
+ */
+	void (*get_coalesce)(struct qed_dev *cdev, u16 *rx_coal, u16 *tx_coal);
+
+/**
+ * @brief set_coalesce - Configure Rx coalesce value in usec
+ *
+ * @param cdev
+ * @param rx_coal - Rx coalesce value in usec
+ * @param tx_coal - Tx coalesce value in usec
+ * @param qid - Queue index
+ * @param sb_id - Status Block Id
+ *
+ * @return 0 on success, error otherwise.
+ */
+	int (*set_coalesce)(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal,
+			    u8 qid, u16 sb_id);
+
+/**
  * @brief set_led - Configure LED mode
  *
  * @param cdev
diff --git a/include/linux/reservation.h b/include/linux/reservation.h
index 49d057655d62..b0f305e77b7f 100644
--- a/include/linux/reservation.h
+++ b/include/linux/reservation.h
@@ -49,12 +49,27 @@ extern struct ww_class reservation_ww_class;
 extern struct lock_class_key reservation_seqcount_class;
 extern const char reservation_seqcount_string[];
 
+/**
+ * struct reservation_object_list - a list of shared fences
+ * @rcu: for internal use
+ * @shared_count: table of shared fences
+ * @shared_max: for growing shared fence table
+ * @shared: shared fence table
+ */
 struct reservation_object_list {
 	struct rcu_head rcu;
 	u32 shared_count, shared_max;
 	struct fence __rcu *shared[];
 };
 
+/**
+ * struct reservation_object - a reservation object manages fences for a buffer
+ * @lock: update side lock
+ * @seq: sequence count for managing RCU read-side synchronization
+ * @fence_excl: the exclusive fence, if there is one currently
+ * @fence: list of current shared fences
+ * @staged: staged copy of shared fences for RCU updates
+ */
 struct reservation_object {
 	struct ww_mutex lock;
 	seqcount_t seq;
@@ -68,6 +83,10 @@ struct reservation_object {
 #define reservation_object_assert_held(obj) \
 	lockdep_assert_held(&(obj)->lock.base)
 
+/**
+ * reservation_object_init - initialize a reservation object
+ * @obj: the reservation object
+ */
 static inline void
 reservation_object_init(struct reservation_object *obj)
 {
@@ -79,6 +98,10 @@ reservation_object_init(struct reservation_object *obj)
 	obj->staged = NULL;
 }
 
+/**
+ * reservation_object_fini - destroys a reservation object
+ * @obj: the reservation object
+ */
 static inline void
 reservation_object_fini(struct reservation_object *obj)
 {
@@ -106,6 +129,14 @@ reservation_object_fini(struct reservation_object *obj)
 	ww_mutex_destroy(&obj->lock);
 }
 
+/**
+ * reservation_object_get_list - get the reservation object's
+ * shared fence list, with update-side lock held
+ * @obj: the reservation object
+ *
+ * Returns the shared fence list.  Does NOT take references to
+ * the fence.  The obj->lock must be held.
+ */
 static inline struct reservation_object_list *
 reservation_object_get_list(struct reservation_object *obj)
 {
@@ -113,6 +144,17 @@ reservation_object_get_list(struct reservation_object *obj)
 					 reservation_object_held(obj));
 }
 
+/**
+ * reservation_object_get_excl - get the reservation object's
+ * exclusive fence, with update-side lock held
+ * @obj: the reservation object
+ *
+ * Returns the exclusive fence (if any).  Does NOT take a
+ * reference.  The obj->lock must be held.
+ *
+ * RETURNS
+ * The exclusive fence or NULL
+ */
 static inline struct fence *
 reservation_object_get_excl(struct reservation_object *obj)
 {
@@ -120,6 +162,17 @@ reservation_object_get_excl(struct reservation_object *obj)
 					 reservation_object_held(obj));
 }
 
+/**
+ * reservation_object_get_excl_rcu - get the reservation object's
+ * exclusive fence, without lock held.
+ * @obj: the reservation object
+ *
+ * If there is an exclusive fence, this atomically increments it's
+ * reference count and returns it.
+ *
+ * RETURNS
+ * The exclusive fence or NULL if none
+ */
 static inline struct fence *
 reservation_object_get_excl_rcu(struct reservation_object *obj)
 {
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index c006cc900c44..2daece8979f7 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -89,8 +89,9 @@ void net_inc_egress_queue(void);
 void net_dec_egress_queue(void);
 #endif
 
-extern void rtnetlink_init(void);
-extern void __rtnl_unlock(void);
+void rtnetlink_init(void);
+void __rtnl_unlock(void);
+void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail);
 
 #define ASSERT_RTNL() do { \
 	if (unlikely(!rtnl_is_locked())) { \
diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h
index a53915cd5581..c68307bc306f 100644
--- a/include/linux/rxrpc.h
+++ b/include/linux/rxrpc.h
@@ -35,21 +35,24 @@ struct sockaddr_rxrpc {
  */
 #define RXRPC_SECURITY_KEY		1	/* [clnt] set client security key */
 #define RXRPC_SECURITY_KEYRING		2	/* [srvr] set ring of server security keys */
-#define RXRPC_EXCLUSIVE_CONNECTION	3	/* [clnt] use exclusive RxRPC connection */
+#define RXRPC_EXCLUSIVE_CONNECTION	3	/* Deprecated; use RXRPC_EXCLUSIVE_CALL instead */
 #define RXRPC_MIN_SECURITY_LEVEL	4	/* minimum security level */
 
 /*
  * RxRPC control messages
+ * - If neither abort or accept are specified, the message is a data message.
  * - terminal messages mean that a user call ID tag can be recycled
+ * - s/r/- indicate whether these are applicable to sendmsg() and/or recvmsg()
  */
-#define RXRPC_USER_CALL_ID	1	/* user call ID specifier */
-#define RXRPC_ABORT		2	/* abort request / notification [terminal] */
-#define RXRPC_ACK		3	/* [Server] RPC op final ACK received [terminal] */
-#define RXRPC_NET_ERROR		5	/* network error received [terminal] */
-#define RXRPC_BUSY		6	/* server busy received [terminal] */
-#define RXRPC_LOCAL_ERROR	7	/* local error generated [terminal] */
-#define RXRPC_NEW_CALL		8	/* [Server] new incoming call notification */
-#define RXRPC_ACCEPT		9	/* [Server] accept request */
+#define RXRPC_USER_CALL_ID	1	/* sr: user call ID specifier */
+#define RXRPC_ABORT		2	/* sr: abort request / notification [terminal] */
+#define RXRPC_ACK		3	/* -r: [Service] RPC op final ACK received [terminal] */
+#define RXRPC_NET_ERROR		5	/* -r: network error received [terminal] */
+#define RXRPC_BUSY		6	/* -r: server busy received [terminal] */
+#define RXRPC_LOCAL_ERROR	7	/* -r: local error generated [terminal] */
+#define RXRPC_NEW_CALL		8	/* -r: [Service] new incoming call notification */
+#define RXRPC_ACCEPT		9	/* s-: [Service] accept request */
+#define RXRPC_EXCLUSIVE_CALL	10	/* s-: Call should be on exclusive connection */
 
 /*
  * RxRPC security levels
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6e42ada26345..253538f29ade 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -3007,7 +3007,7 @@ static inline int object_is_on_stack(void *obj)
 	return (obj >= stack) && (obj < (stack + THREAD_SIZE));
 }
 
-extern void thread_info_cache_init(void);
+extern void thread_stack_cache_init(void);
 
 #ifdef CONFIG_DEBUG_STACK_USAGE
 static inline unsigned long stack_not_used(struct task_struct *p)
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 7973a821ac58..ead97654c4e9 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -277,7 +277,10 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s)
 
 static inline int raw_read_seqcount_latch(seqcount_t *s)
 {
-	return lockless_dereference(s)->sequence;
+	int seq = READ_ONCE(s->sequence);
+	/* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */
+	smp_read_barrier_depends();
+	return seq;
 }
 
 /**
@@ -331,7 +334,7 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
  *	unsigned seq, idx;
  *
  *	do {
- *		seq = lockless_dereference(latch)->seq;
+ *		seq = raw_read_seqcount_latch(&latch->seq);
  *
  *		idx = seq & 0x01;
  *		entry = data_query(latch->data[idx], ...);
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
new file mode 100644
index 000000000000..f4dfade428f0
--- /dev/null
+++ b/include/linux/skb_array.h
@@ -0,0 +1,178 @@
+/*
+ *	Definitions for the 'struct skb_array' datastructure.
+ *
+ *	Author:
+ *		Michael S. Tsirkin <[email protected]>
+ *
+ *	Copyright (C) 2016 Red Hat, Inc.
+ *
+ *	This program is free software; you can redistribute it and/or modify it
+ *	under the terms of the GNU General Public License as published by the
+ *	Free Software Foundation; either version 2 of the License, or (at your
+ *	option) any later version.
+ *
+ *	Limited-size FIFO of skbs. Can be used more or less whenever
+ *	sk_buff_head can be used, except you need to know the queue size in
+ *	advance.
+ *	Implemented as a type-safe wrapper around ptr_ring.
+ */
+
+#ifndef _LINUX_SKB_ARRAY_H
+#define _LINUX_SKB_ARRAY_H 1
+
+#ifdef __KERNEL__
+#include <linux/ptr_ring.h>
+#include <linux/skbuff.h>
+#include <linux/if_vlan.h>
+#endif
+
+struct skb_array {
+	struct ptr_ring ring;
+};
+
+/* Might be slightly faster than skb_array_full below, but callers invoking
+ * this in a loop must use a compiler barrier, for example cpu_relax().
+ */
+static inline bool __skb_array_full(struct skb_array *a)
+{
+	return __ptr_ring_full(&a->ring);
+}
+
+static inline bool skb_array_full(struct skb_array *a)
+{
+	return ptr_ring_full(&a->ring);
+}
+
+static inline int skb_array_produce(struct skb_array *a, struct sk_buff *skb)
+{
+	return ptr_ring_produce(&a->ring, skb);
+}
+
+static inline int skb_array_produce_irq(struct skb_array *a, struct sk_buff *skb)
+{
+	return ptr_ring_produce_irq(&a->ring, skb);
+}
+
+static inline int skb_array_produce_bh(struct skb_array *a, struct sk_buff *skb)
+{
+	return ptr_ring_produce_bh(&a->ring, skb);
+}
+
+static inline int skb_array_produce_any(struct skb_array *a, struct sk_buff *skb)
+{
+	return ptr_ring_produce_any(&a->ring, skb);
+}
+
+/* Might be slightly faster than skb_array_empty below, but only safe if the
+ * array is never resized. Also, callers invoking this in a loop must take care
+ * to use a compiler barrier, for example cpu_relax().
+ */
+static inline bool __skb_array_empty(struct skb_array *a)
+{
+	return !__ptr_ring_peek(&a->ring);
+}
+
+static inline bool skb_array_empty(struct skb_array *a)
+{
+	return ptr_ring_empty(&a->ring);
+}
+
+static inline bool skb_array_empty_bh(struct skb_array *a)
+{
+	return ptr_ring_empty_bh(&a->ring);
+}
+
+static inline bool skb_array_empty_irq(struct skb_array *a)
+{
+	return ptr_ring_empty_irq(&a->ring);
+}
+
+static inline bool skb_array_empty_any(struct skb_array *a)
+{
+	return ptr_ring_empty_any(&a->ring);
+}
+
+static inline struct sk_buff *skb_array_consume(struct skb_array *a)
+{
+	return ptr_ring_consume(&a->ring);
+}
+
+static inline struct sk_buff *skb_array_consume_irq(struct skb_array *a)
+{
+	return ptr_ring_consume_irq(&a->ring);
+}
+
+static inline struct sk_buff *skb_array_consume_any(struct skb_array *a)
+{
+	return ptr_ring_consume_any(&a->ring);
+}
+
+static inline struct sk_buff *skb_array_consume_bh(struct skb_array *a)
+{
+	return ptr_ring_consume_bh(&a->ring);
+}
+
+static inline int __skb_array_len_with_tag(struct sk_buff *skb)
+{
+	if (likely(skb)) {
+		int len = skb->len;
+
+		if (skb_vlan_tag_present(skb))
+			len += VLAN_HLEN;
+
+		return len;
+	} else {
+		return 0;
+	}
+}
+
+static inline int skb_array_peek_len(struct skb_array *a)
+{
+	return PTR_RING_PEEK_CALL(&a->ring, __skb_array_len_with_tag);
+}
+
+static inline int skb_array_peek_len_irq(struct skb_array *a)
+{
+	return PTR_RING_PEEK_CALL_IRQ(&a->ring, __skb_array_len_with_tag);
+}
+
+static inline int skb_array_peek_len_bh(struct skb_array *a)
+{
+	return PTR_RING_PEEK_CALL_BH(&a->ring, __skb_array_len_with_tag);
+}
+
+static inline int skb_array_peek_len_any(struct skb_array *a)
+{
+	return PTR_RING_PEEK_CALL_ANY(&a->ring, __skb_array_len_with_tag);
+}
+
+static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp)
+{
+	return ptr_ring_init(&a->ring, size, gfp);
+}
+
+static void __skb_array_destroy_skb(void *ptr)
+{
+	kfree_skb(ptr);
+}
+
+static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp)
+{
+	return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb);
+}
+
+static inline int skb_array_resize_multiple(struct skb_array **rings,
+					    int nrings, int size, gfp_t gfp)
+{
+	BUILD_BUG_ON(offsetof(struct skb_array, ring));
+	return ptr_ring_resize_multiple((struct ptr_ring **)rings,
+					nrings, size, gfp,
+					__skb_array_destroy_skb);
+}
+
+static inline void skb_array_cleanup(struct skb_array *a)
+{
+	ptr_ring_cleanup(&a->ring, __skb_array_destroy_skb);
+}
+
+#endif /* _LINUX_SKB_ARRAY_H  */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index dc0fca747c5e..638b0e004310 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -37,6 +37,7 @@
 #include <net/flow_dissector.h>
 #include <linux/splice.h>
 #include <linux/in6.h>
+#include <linux/if_packet.h>
 #include <net/flow.h>
 
 /* The interface for checksum offload between the stack and networking drivers
@@ -881,6 +882,15 @@ static inline struct rtable *skb_rtable(const struct sk_buff *skb)
 	return (struct rtable *)skb_dst(skb);
 }
 
+/* For mangling skb->pkt_type from user space side from applications
+ * such as nft, tc, etc, we only allow a conservative subset of
+ * possible pkt_types to be set.
+*/
+static inline bool skb_pkt_type_ok(u32 ptype)
+{
+	return ptype <= PACKET_OTHERHOST;
+}
+
 void kfree_skb(struct sk_buff *skb);
 void kfree_skb_list(struct sk_buff *segs);
 void skb_tx_error(struct sk_buff *skb);
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index 4018b48f2b3b..a0596ca0e80a 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -36,6 +36,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk)
 {
 	switch (sk->sk_family) {
 	case AF_INET:
+		if (sk->sk_type == SOCK_RAW)
+			return SKNLGRP_NONE;
+
 		switch (sk->sk_protocol) {
 		case IPPROTO_TCP:
 			return SKNLGRP_INET_TCP_DESTROY;
@@ -45,6 +48,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk)
 			return SKNLGRP_NONE;
 		}
 	case AF_INET6:
+		if (sk->sk_type == SOCK_RAW)
+			return SKNLGRP_NONE;
+
 		switch (sk->sk_protocol) {
 		case IPPROTO_TCP:
 			return SKNLGRP_INET6_TCP_DESTROY;
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index ffdaca9c01af..705840e0438f 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -135,9 +135,12 @@ struct plat_stmmacenet_data {
 	void (*bus_setup)(void __iomem *ioaddr);
 	int (*init)(struct platform_device *pdev, void *priv);
 	void (*exit)(struct platform_device *pdev, void *priv);
+	void (*suspend)(struct platform_device *pdev, void *priv);
+	void (*resume)(struct platform_device *pdev, void *priv);
 	void *bsp_priv;
 	struct stmmac_axi *axi;
 	int has_gmac4;
 	bool tso_en;
+	int mac_port_sel_speed;
 };
 #endif
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 19c659d1c0f8..b6810c92b8bb 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -137,8 +137,6 @@ struct rpc_create_args {
 #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT	(1UL << 9)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
-struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
-					struct rpc_xprt *xprt);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
 				const struct rpc_program *, u32);
 struct rpc_clnt *rpc_clone_client(struct rpc_clnt *);
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index b7dabc4baafd..79ba50856707 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -84,6 +84,7 @@ struct svc_xprt {
 
 	struct net		*xpt_net;
 	struct rpc_xprt		*xpt_bc_xprt;	/* NFSv4.1 backchannel */
+	struct rpc_xprt_switch	*xpt_bc_xps;	/* NFSv4.1 backchannel */
 };
 
 static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u)
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 5aa3834619a8..5e3e1b63dbb3 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -297,6 +297,7 @@ struct xprt_create {
 	size_t			addrlen;
 	const char		*servername;
 	struct svc_xprt		*bc_xprt;	/* NFSv4.1 backchannel */
+	struct rpc_xprt_switch	*bc_xps;
 	unsigned int		flags;
 };
 
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index e45abe7db9a6..ee517bef0db0 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -335,6 +335,8 @@ struct thermal_genl_event {
  * @get_trend: a pointer to a function that reads the sensor temperature trend.
  * @set_emul_temp: a pointer to a function that sets sensor emulated
  *		   temperature.
+ * @set_trip_temp: a pointer to a function that sets the trip temperature on
+ *		   hardware.
  */
 struct thermal_zone_of_device_ops {
 	int (*get_temp)(void *, int *);
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 37dbacf84849..816b7543f81b 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -21,6 +21,9 @@ static inline int do_sys_settimeofday(const struct timespec *tv,
 	struct timespec64 ts64;
 
 	if (!tv)
+		return do_sys_settimeofday64(NULL, tz);
+
+	if (!timespec_valid(tv))
 		return -EINVAL;
 
 	ts64 = timespec_to_timespec64(*tv);
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 457651bf45b0..fefe8b06a63d 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -1034,6 +1034,8 @@ static inline int usb_gadget_activate(struct usb_gadget *gadget)
  * @udc_name: A name of UDC this driver should be bound to. If udc_name is NULL,
  *	this driver will be bound to any available UDC.
  * @pending: UDC core private data used for deferred probe of this driver.
+ * @match_existing_only: If udc is not found, return an error and don't add this
+ *      gadget driver to list of pending driver
  *
  * Devices are disabled till a gadget driver successfully bind()s, which
  * means the driver will handle setup() requests needed to enumerate (and
@@ -1097,6 +1099,7 @@ struct usb_gadget_driver {
 
 	char			*udc_name;
 	struct list_head	pending;
+	unsigned                match_existing_only:1;
 };
 
 
diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h
index 0b3da40a525e..d315c8907869 100644
--- a/include/linux/usb/musb.h
+++ b/include/linux/usb/musb.h
@@ -142,10 +142,11 @@ enum musb_vbus_id_status {
 };
 
 #if IS_ENABLED(CONFIG_USB_MUSB_HDRC)
-void musb_mailbox(enum musb_vbus_id_status status);
+int musb_mailbox(enum musb_vbus_id_status status);
 #else
-static inline void musb_mailbox(enum musb_vbus_id_status status)
+static inline int musb_mailbox(enum musb_vbus_id_status status)
 {
+	return 0;
 }
 #endif
 
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
new file mode 100644
index 000000000000..1c912f85e041
--- /dev/null
+++ b/include/linux/virtio_net.h
@@ -0,0 +1,101 @@
+#ifndef _LINUX_VIRTIO_NET_H
+#define _LINUX_VIRTIO_NET_H
+
+#include <linux/if_vlan.h>
+#include <uapi/linux/virtio_net.h>
+
+static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
+					const struct virtio_net_hdr *hdr,
+					bool little_endian)
+{
+	unsigned short gso_type = 0;
+
+	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+		case VIRTIO_NET_HDR_GSO_TCPV4:
+			gso_type = SKB_GSO_TCPV4;
+			break;
+		case VIRTIO_NET_HDR_GSO_TCPV6:
+			gso_type = SKB_GSO_TCPV6;
+			break;
+		case VIRTIO_NET_HDR_GSO_UDP:
+			gso_type = SKB_GSO_UDP;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
+			gso_type |= SKB_GSO_TCP_ECN;
+
+		if (hdr->gso_size == 0)
+			return -EINVAL;
+	}
+
+	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+		u16 start = __virtio16_to_cpu(little_endian, hdr->csum_start);
+		u16 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
+
+		if (!skb_partial_csum_set(skb, start, off))
+			return -EINVAL;
+	}
+
+	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
+
+		skb_shinfo(skb)->gso_size = gso_size;
+		skb_shinfo(skb)->gso_type = gso_type;
+
+		/* Header must be checked, and gso_segs computed. */
+		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
+		skb_shinfo(skb)->gso_segs = 0;
+	}
+
+	return 0;
+}
+
+static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
+					  struct virtio_net_hdr *hdr,
+					  bool little_endian)
+{
+	memset(hdr, 0, sizeof(*hdr));
+
+	if (skb_is_gso(skb)) {
+		struct skb_shared_info *sinfo = skb_shinfo(skb);
+
+		/* This is a hint as to how much should be linear. */
+		hdr->hdr_len = __cpu_to_virtio16(little_endian,
+						 skb_headlen(skb));
+		hdr->gso_size = __cpu_to_virtio16(little_endian,
+						  sinfo->gso_size);
+		if (sinfo->gso_type & SKB_GSO_TCPV4)
+			hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
+		else if (sinfo->gso_type & SKB_GSO_TCPV6)
+			hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+		else if (sinfo->gso_type & SKB_GSO_UDP)
+			hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
+		else
+			return -EINVAL;
+		if (sinfo->gso_type & SKB_GSO_TCP_ECN)
+			hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
+	} else
+		hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+		if (skb_vlan_tag_present(skb))
+			hdr->csum_start = __cpu_to_virtio16(little_endian,
+				skb_checksum_start_offset(skb) + VLAN_HLEN);
+		else
+			hdr->csum_start = __cpu_to_virtio16(little_endian,
+				skb_checksum_start_offset(skb));
+		hdr->csum_offset = __cpu_to_virtio16(little_endian,
+				skb->csum_offset);
+	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+		hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
+	} /* else everything is zero */
+
+	return 0;
+}
+
+#endif /* _LINUX_VIRTIO_BYTEORDER */
diff --git a/include/media/v4l2-mc.h b/include/media/v4l2-mc.h
index 98a938aabdfb..7a8d6037a4bb 100644
--- a/include/media/v4l2-mc.h
+++ b/include/media/v4l2-mc.h
@@ -1,7 +1,7 @@
 /*
  * v4l2-mc.h - Media Controller V4L2 types and prototypes
  *
- * Copyright (C) 2016 Mauro Carvalho Chehab <[email protected]>
+ * Copyright (C) 2016 Mauro Carvalho Chehab <[email protected]>
  * Copyright (C) 2006-2010 Nokia Corporation
  * Copyright (c) 2016 Intel Corporation.
  *
diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h
index da84cf920b78..5ab4c9901ccc 100644
--- a/include/net/6lowpan.h
+++ b/include/net/6lowpan.h
@@ -141,6 +141,16 @@ struct lowpan_dev {
 	u8 priv[0] __aligned(sizeof(void *));
 };
 
+struct lowpan_802154_neigh {
+	__le16 short_addr;
+};
+
+static inline
+struct lowpan_802154_neigh *lowpan_802154_neigh(void *neigh_priv)
+{
+	return neigh_priv;
+}
+
 static inline
 struct lowpan_dev *lowpan_dev(const struct net_device *dev)
 {
@@ -244,6 +254,12 @@ static inline bool lowpan_fetch_skb(struct sk_buff *skb, void *data,
 	return false;
 }
 
+static inline bool lowpan_802154_is_valid_src_short_addr(__le16 addr)
+{
+	/* First bit of addr is multicast, reserved or 802.15.4 specific */
+	return !(addr & cpu_to_le16(0x8000));
+}
+
 static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data,
 				       const size_t len)
 {
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 9a9a8edc138f..fb82b5b5d9e7 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -2,8 +2,8 @@
 #define __NET_ACT_API_H
 
 /*
- * Public police action API for classifiers/qdiscs
- */
+ * Public action API for classifiers/qdiscs
+*/
 
 #include <net/sch_generic.h>
 #include <net/pkt_sched.h>
@@ -76,6 +76,16 @@ static inline void tcf_lastuse_update(struct tcf_t *tm)
 
 	if (tm->lastuse != now)
 		tm->lastuse = now;
+	if (unlikely(!tm->firstuse))
+		tm->firstuse = now;
+}
+
+static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm)
+{
+	dtm->install = jiffies_to_clock_t(jiffies - stm->install);
+	dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse);
+	dtm->firstuse = jiffies_to_clock_t(jiffies - stm->firstuse);
+	dtm->expires = jiffies_to_clock_t(stm->expires);
 }
 
 struct tc_action {
@@ -97,7 +107,8 @@ struct tc_action_ops {
 	char    kind[IFNAMSIZ];
 	__u32   type; /* TBD to match kind */
 	struct module		*owner;
-	int     (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *);
+	int     (*act)(struct sk_buff *, const struct tc_action *,
+		       struct tcf_result *);
 	int     (*dump)(struct sk_buff *, struct tc_action *, int, int);
 	void	(*cleanup)(struct tc_action *, int bind);
 	int     (*lookup)(struct net *, struct tc_action *, u32);
@@ -115,8 +126,8 @@ struct tc_action_net {
 };
 
 static inline
-int tc_action_net_init(struct tc_action_net *tn, const struct tc_action_ops *ops,
-		       unsigned int mask)
+int tc_action_net_init(struct tc_action_net *tn,
+		       const struct tc_action_ops *ops, unsigned int mask)
 {
 	int err = 0;
 
@@ -144,8 +155,8 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
 		       struct tc_action *a);
 int tcf_hash_search(struct tc_action_net *tn, struct tc_action *a, u32 index);
 u32 tcf_hash_new_index(struct tc_action_net *tn);
-int tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a,
-		   int bind);
+bool tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a,
+		    int bind);
 int tcf_hash_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 		    struct tc_action *a, int size, int bind, bool cpustats);
 void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
@@ -159,7 +170,8 @@ static inline int tcf_hash_release(struct tc_action *a, bool bind)
 }
 
 int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
-int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops);
+int tcf_unregister_action(struct tc_action_ops *a,
+			  struct pernet_operations *ops);
 int tcf_action_destroy(struct list_head *actions, int bind);
 int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions,
 		    struct tcf_result *res);
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 730d856683e5..9826d3a9464c 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -94,6 +94,16 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
 void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr);
 void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr);
 
+void addrconf_add_linklocal(struct inet6_dev *idev,
+			    const struct in6_addr *addr, u32 flags);
+
+int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
+				 const struct prefix_info *pinfo,
+				 struct inet6_dev *in6_dev,
+				 const struct in6_addr *addr, int addr_type,
+				 u32 addr_flags, bool sllao, bool tokenized,
+				 __u32 valid_lft, u32 prefered_lft);
+
 static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev)
 {
 	if (dev->addr_len != ETH_ALEN)
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 63921672bed0..7bbb00d8b2cd 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2367,19 +2367,23 @@ struct cfg80211_qos_map {
  *	(invoked with the wireless_dev mutex held)
  *
  * @connect: Connect to the ESS with the specified parameters. When connected,
- *	call cfg80211_connect_result() with status code %WLAN_STATUS_SUCCESS.
- *	If the connection fails for some reason, call cfg80211_connect_result()
- *	with the status from the AP. The driver is allowed to roam to other
- *	BSSes within the ESS when the other BSS matches the connect parameters.
- *	When such roaming is initiated by the driver, the driver is expected to
- *	verify that the target matches the configured security parameters and
- *	to use Reassociation Request frame instead of Association Request frame.
- *	The connect function can also be used to request the driver to perform
- *	a specific roam when connected to an ESS. In that case, the prev_bssid
+ *	call cfg80211_connect_result()/cfg80211_connect_bss() with status code
+ *	%WLAN_STATUS_SUCCESS. If the connection fails for some reason, call
+ *	cfg80211_connect_result()/cfg80211_connect_bss() with the status code
+ *	from the AP or cfg80211_connect_timeout() if no frame with status code
+ *	was received.
+ *	The driver is allowed to roam to other BSSes within the ESS when the
+ *	other BSS matches the connect parameters. When such roaming is initiated
+ *	by the driver, the driver is expected to verify that the target matches
+ *	the configured security parameters and to use Reassociation Request
+ *	frame instead of Association Request frame.
+ *	The connect function can also be used to request the driver to perform a
+ *	specific roam when connected to an ESS. In that case, the prev_bssid
  *	parameter is set to the BSSID of the currently associated BSS as an
- *	indication of requesting reassociation. In both the driver-initiated and
- *	new connect() call initiated roaming cases, the result of roaming is
- *	indicated with a call to cfg80211_roamed() or cfg80211_roamed_bss().
+ *	indication of requesting reassociation.
+ *	In both the driver-initiated and new connect() call initiated roaming
+ *	cases, the result of roaming is indicated with a call to
+ *	cfg80211_roamed() or cfg80211_roamed_bss().
  *	(invoked with the wireless_dev mutex held)
  * @disconnect: Disconnect from the BSS/ESS.
  *	(invoked with the wireless_dev mutex held)
@@ -3080,6 +3084,24 @@ struct wiphy_vendor_command {
 };
 
 /**
+ * struct wiphy_iftype_ext_capab - extended capabilities per interface type
+ * @iftype: interface type
+ * @extended_capabilities: extended capabilities supported by the driver,
+ *	additional capabilities might be supported by userspace; these are the
+ *	802.11 extended capabilities ("Extended Capabilities element") and are
+ *	in the same format as in the information element. See IEEE Std
+ *	802.11-2012 8.4.2.29 for the defined fields.
+ * @extended_capabilities_mask: mask of the valid values
+ * @extended_capabilities_len: length of the extended capabilities
+ */
+struct wiphy_iftype_ext_capab {
+	enum nl80211_iftype iftype;
+	const u8 *extended_capabilities;
+	const u8 *extended_capabilities_mask;
+	u8 extended_capabilities_len;
+};
+
+/**
  * struct wiphy - wireless hardware description
  * @reg_notifier: the driver's regulatory notification callback,
  *	note that if your driver uses wiphy_apply_custom_regulatory()
@@ -3199,9 +3221,14 @@ struct wiphy_vendor_command {
  *	additional capabilities might be supported by userspace; these are
  *	the 802.11 extended capabilities ("Extended Capabilities element")
  *	and are in the same format as in the information element. See
- *	802.11-2012 8.4.2.29 for the defined fields.
+ *	802.11-2012 8.4.2.29 for the defined fields. These are the default
+ *	extended capabilities to be used if the capabilities are not specified
+ *	for a specific interface type in iftype_ext_capab.
  * @extended_capabilities_mask: mask of the valid values
  * @extended_capabilities_len: length of the extended capabilities
+ * @iftype_ext_capab: array of extended capabilities per interface type
+ * @num_iftype_ext_capab: number of interface types for which extended
+ *	capabilities are specified separately.
  * @coalesce: packet coalescing support information
  *
  * @vendor_commands: array of vendor commands supported by the hardware
@@ -3301,6 +3328,9 @@ struct wiphy {
 	const u8 *extended_capabilities, *extended_capabilities_mask;
 	u8 extended_capabilities_len;
 
+	const struct wiphy_iftype_ext_capab *iftype_ext_capab;
+	unsigned int num_iftype_ext_capab;
+
 	/* If multiple wiphys are registered and you're handed e.g.
 	 * a regular netdev with assigned ieee80211_ptr, you won't
 	 * know whether it points to a wiphy your driver has registered
@@ -4680,7 +4710,7 @@ static inline void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
 void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid,
 			  struct cfg80211_bss *bss, const u8 *req_ie,
 			  size_t req_ie_len, const u8 *resp_ie,
-			  size_t resp_ie_len, u16 status, gfp_t gfp);
+			  size_t resp_ie_len, int status, gfp_t gfp);
 
 /**
  * cfg80211_connect_result - notify cfg80211 of connection result
@@ -4710,6 +4740,29 @@ cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 }
 
 /**
+ * cfg80211_connect_timeout - notify cfg80211 of connection timeout
+ *
+ * @dev: network device
+ * @bssid: the BSSID of the AP
+ * @req_ie: association request IEs (maybe be %NULL)
+ * @req_ie_len: association request IEs length
+ * @gfp: allocation flags
+ *
+ * It should be called by the underlying driver whenever connect() has failed
+ * in a sequence where no explicit authentication/association rejection was
+ * received from the AP. This could happen, e.g., due to not being able to send
+ * out the Authentication or Association Request frame or timing out while
+ * waiting for the response.
+ */
+static inline void
+cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid,
+			 const u8 *req_ie, size_t req_ie_len, gfp_t gfp)
+{
+	cfg80211_connect_bss(dev, bssid, NULL, req_ie, req_ie_len, NULL, 0, -1,
+			     gfp);
+}
+
+/**
  * cfg80211_roamed - notify cfg80211 of roaming
  *
  * @dev: network device
diff --git a/include/net/codel_qdisc.h b/include/net/codel_qdisc.h
index 8144d9cd2908..098630f83a55 100644
--- a/include/net/codel_qdisc.h
+++ b/include/net/codel_qdisc.h
@@ -52,6 +52,7 @@
 /* Qdiscs using codel plugin must use codel_skb_cb in their own cb[] */
 struct codel_skb_cb {
 	codel_time_t enqueue_time;
+	unsigned int mem_usage;
 };
 
 static struct codel_skb_cb *get_codel_cb(const struct sk_buff *skb)
diff --git a/include/net/compat.h b/include/net/compat.h
index 48103cf94e97..13de0ccaa059 100644
--- a/include/net/compat.h
+++ b/include/net/compat.h
@@ -42,6 +42,7 @@ int compat_sock_get_timestampns(struct sock *, struct timespec __user *);
 
 int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *,
 		      struct sockaddr __user **, struct iovec **);
+struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval);
 asmlinkage long compat_sys_sendmsg(int, struct compat_msghdr __user *,
 				   unsigned int);
 asmlinkage long compat_sys_sendmmsg(int, struct compat_mmsghdr __user *,
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 1d45b61cb320..c99ffe8cef3c 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -90,6 +90,9 @@ struct devlink_ops {
 				       u16 tc_index,
 				       enum devlink_sb_pool_type pool_type,
 				       u32 *p_cur, u32 *p_max);
+
+	int (*eswitch_mode_get)(struct devlink *devlink, u16 *p_mode);
+	int (*eswitch_mode_set)(struct devlink *devlink, u16 mode);
 };
 
 static inline void *devlink_priv(struct devlink *devlink)
diff --git a/include/net/dsa.h b/include/net/dsa.h
index cca7ef230742..20b3087ad193 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -116,6 +116,7 @@ struct dsa_switch_tree {
 	 * Original copy of the master netdev ethtool_ops
 	 */
 	struct ethtool_ops	master_ethtool_ops;
+	const struct ethtool_ops *master_orig_ethtool_ops;
 
 	/*
 	 * The switch and port to which the CPU is attached.
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 59160de702b6..456e4a6006ab 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -17,7 +17,8 @@ struct fib_rule {
 	u32			flags;
 	u32			table;
 	u8			action;
-	/* 3 bytes hole, try to use */
+	u8			l3mdev;
+	/* 2 bytes hole, try to use */
 	u32			target;
 	__be64			tun_id;
 	struct fib_rule __rcu	*ctarget;
@@ -36,6 +37,7 @@ struct fib_lookup_arg {
 	void			*lookup_ptr;
 	void			*result;
 	struct fib_rule		*rule;
+	u32			table;
 	int			flags;
 #define FIB_LOOKUP_NOREF		1
 #define FIB_LOOKUP_IGNORE_LINKSTATE	2
@@ -89,7 +91,8 @@ struct fib_rules_ops {
 	[FRA_TABLE]     = { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \
-	[FRA_GOTO]	= { .type = NLA_U32 }
+	[FRA_GOTO]	= { .type = NLA_U32 }, \
+	[FRA_L3MDEV]	= { .type = NLA_U8 }
 
 static inline void fib_rule_get(struct fib_rule *rule)
 {
@@ -102,6 +105,20 @@ static inline void fib_rule_put(struct fib_rule *rule)
 		kfree_rcu(rule, rcu);
 }
 
+#ifdef CONFIG_NET_L3_MASTER_DEV
+static inline u32 fib_rule_get_table(struct fib_rule *rule,
+				     struct fib_lookup_arg *arg)
+{
+	return rule->l3mdev ? arg->table : rule->table;
+}
+#else
+static inline u32 fib_rule_get_table(struct fib_rule *rule,
+				     struct fib_lookup_arg *arg)
+{
+	return rule->table;
+}
+#endif
+
 static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla)
 {
 	if (nla[FRA_TABLE])
@@ -117,4 +134,7 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags,
 		     struct fib_lookup_arg *);
 int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table,
 			 u32 flags);
+
+int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh);
+int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh);
 #endif
diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index 610cd397890e..231e121cc7d9 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -33,10 +33,12 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type,
 				 spinlock_t *lock, struct gnet_dump *d,
 				 int padattr);
 
-int gnet_stats_copy_basic(struct gnet_dump *d,
+int gnet_stats_copy_basic(const seqcount_t *running,
+			  struct gnet_dump *d,
 			  struct gnet_stats_basic_cpu __percpu *cpu,
 			  struct gnet_stats_basic_packed *b);
-void __gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats,
+void __gnet_stats_copy_basic(const seqcount_t *running,
+			     struct gnet_stats_basic_packed *bstats,
 			     struct gnet_stats_basic_cpu __percpu *cpu,
 			     struct gnet_stats_basic_packed *b);
 int gnet_stats_copy_rate_est(struct gnet_dump *d,
@@ -52,13 +54,15 @@ int gnet_stats_finish_copy(struct gnet_dump *d);
 int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct gnet_stats_rate_est64 *rate_est,
-		      spinlock_t *stats_lock, struct nlattr *opt);
+		      spinlock_t *stats_lock,
+		      seqcount_t *running, struct nlattr *opt);
 void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
 			struct gnet_stats_rate_est64 *rate_est);
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
 			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct gnet_stats_rate_est64 *rate_est,
-			  spinlock_t *stats_lock, struct nlattr *opt);
+			  spinlock_t *stats_lock,
+			  seqcount_t *running, struct nlattr *opt);
 bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
 			  const struct gnet_stats_rate_est64 *rate_est);
 #endif
diff --git a/include/net/geneve.h b/include/net/geneve.h
index cb544a530146..ec0327d4331b 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -1,10 +1,7 @@
 #ifndef __NET_GENEVE_H
 #define __NET_GENEVE_H  1
 
-#ifdef CONFIG_INET
 #include <net/udp_tunnel.h>
-#endif
-
 
 /* Geneve Header:
  *  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -62,12 +59,6 @@ struct genevehdr {
 	struct geneve_opt options[];
 };
 
-static inline void geneve_get_rx_port(struct net_device *netdev)
-{
-	ASSERT_RTNL();
-	call_netdevice_notifiers(NETDEV_OFFLOAD_PUSH_GENEVE, netdev);
-}
-
 #ifdef CONFIG_INET
 struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 					u8 name_assign_type, u16 dst_port);
diff --git a/include/net/gre.h b/include/net/gre.h
index 5dce30a6abe3..7a54a31d1d4c 100644
--- a/include/net/gre.h
+++ b/include/net/gre.h
@@ -26,7 +26,7 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version);
 struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 				       u8 name_assign_type);
 int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
-		     bool *csum_err, __be16 proto);
+		     bool *csum_err, __be16 proto, int nhs);
 
 static inline int gre_calc_hlen(__be16 o_flags)
 {
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 54c779416eec..d97305d0e71f 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -18,6 +18,7 @@ struct route_info {
 	__u8			prefix[0];	/* 0,8 or 16 */
 };
 
+#include <net/addrconf.h>
 #include <net/flow.h>
 #include <net/ip6_fib.h>
 #include <net/sock.h>
@@ -76,6 +77,8 @@ static inline struct dst_entry *ip6_route_output(struct net *net,
 
 struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags);
+struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
+			       int ifindex, struct flowi6 *fl6, int flags);
 
 int ip6_route_init(void);
 void ip6_route_cleanup(void);
@@ -86,9 +89,23 @@ int ip6_route_add(struct fib6_config *cfg);
 int ip6_ins_rt(struct rt6_info *);
 int ip6_del_rt(struct rt6_info *);
 
-int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
-			const struct in6_addr *daddr, unsigned int prefs,
-			struct in6_addr *saddr);
+static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
+				      const struct in6_addr *daddr,
+				      unsigned int prefs,
+				      struct in6_addr *saddr)
+{
+	struct inet6_dev *idev =
+			rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
+	int err = 0;
+
+	if (rt && rt->rt6i_prefsrc.plen)
+		*saddr = rt->rt6i_prefsrc.addr;
+	else
+		err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
+					 daddr, prefs, saddr);
+
+	return err;
+}
 
 struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
 			    const struct in6_addr *saddr, int oif, int flags);
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index dbf444428437..a5e7035fb93f 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -132,6 +132,7 @@ struct ip_tunnel {
 	int			ip_tnl_net_id;
 	struct gro_cells	gro_cells;
 	bool			collect_md;
+	bool			ignore_df;
 };
 
 #define TUNNEL_CSUM		__cpu_to_be16(0x01)
@@ -156,6 +157,7 @@ struct tnl_ptk_info {
 	__be16 proto;
 	__be32 key;
 	__be32 seq;
+	int hdr_len;
 };
 
 #define PACKET_RCVD	0
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index af4c10ebb241..cd6018a9ee24 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1232,7 +1232,7 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
 const char *ip_vs_state_name(__u16 proto, int state);
 
 void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp);
-int ip_vs_check_template(struct ip_vs_conn *ct);
+int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest);
 void ip_vs_random_dropentry(struct netns_ipvs *ipvs);
 int ip_vs_conn_init(void);
 void ip_vs_conn_cleanup(void);
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index 374388dc01c8..e90095091aa0 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -11,6 +11,8 @@
 #ifndef _NET_L3MDEV_H_
 #define _NET_L3MDEV_H_
 
+#include <net/fib_rules.h>
+
 /**
  * struct l3mdev_ops - l3mdev operations
  *
@@ -36,11 +38,17 @@ struct l3mdev_ops {
 
 	/* IPv6 ops */
 	struct dst_entry * (*l3mdev_get_rt6_dst)(const struct net_device *dev,
-						 const struct flowi6 *fl6);
+						 struct flowi6 *fl6);
+	int		   (*l3mdev_get_saddr6)(struct net_device *dev,
+						const struct sock *sk,
+						struct flowi6 *fl6);
 };
 
 #ifdef CONFIG_NET_L3_MASTER_DEV
 
+int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
+			  struct fib_lookup_arg *arg);
+
 int l3mdev_master_ifindex_rcu(const struct net_device *dev);
 static inline int l3mdev_master_ifindex(struct net_device *dev)
 {
@@ -71,6 +79,31 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex)
 	return rc;
 }
 
+static inline
+const struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev)
+{
+	/* netdev_master_upper_dev_get_rcu calls
+	 * list_first_or_null_rcu to walk the upper dev list.
+	 * list_first_or_null_rcu does not handle a const arg. We aren't
+	 * making changes, just want the master device from that list so
+	 * typecast to remove the const
+	 */
+	struct net_device *dev = (struct net_device *)_dev;
+	const struct net_device *master;
+
+	if (!dev)
+		return NULL;
+
+	if (netif_is_l3_master(dev))
+		master = dev;
+	else if (netif_is_l3_slave(dev))
+		master = netdev_master_upper_dev_get_rcu(dev);
+	else
+		master = NULL;
+
+	return master;
+}
+
 /* get index of an interface to use for FIB lookups. For devices
  * enslaved to an L3 master device FIB lookups are based on the
  * master index
@@ -134,7 +167,9 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex)
 
 int l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4);
 
-struct dst_entry *l3mdev_get_rt6_dst(struct net *net, const struct flowi6 *fl6);
+struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6);
+int l3mdev_get_saddr6(struct net *net, const struct sock *sk,
+		      struct flowi6 *fl6);
 
 static inline
 struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto)
@@ -180,6 +215,12 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex)
 	return 0;
 }
 
+static inline
+const struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev)
+{
+	return NULL;
+}
+
 static inline int l3mdev_fib_oif_rcu(struct net_device *dev)
 {
 	return dev ? dev->ifindex : 0;
@@ -220,11 +261,17 @@ static inline int l3mdev_get_saddr(struct net *net, int ifindex,
 }
 
 static inline
-struct dst_entry *l3mdev_get_rt6_dst(struct net *net, const struct flowi6 *fl6)
+struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6)
 {
 	return NULL;
 }
 
+static inline int l3mdev_get_saddr6(struct net *net, const struct sock *sk,
+				    struct flowi6 *fl6)
+{
+	return 0;
+}
+
 static inline
 struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb)
 {
@@ -236,6 +283,13 @@ struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb)
 {
 	return skb;
 }
+
+static inline
+int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
+			  struct fib_lookup_arg *arg)
+{
+	return 1;
+}
 #endif
 
 #endif /* _NET_L3MDEV_H_ */
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index be30b0549b88..a52009ffc19f 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -21,6 +21,7 @@
 #include <linux/skbuff.h>
 #include <linux/ieee80211.h>
 #include <net/cfg80211.h>
+#include <net/codel.h>
 #include <asm/unaligned.h>
 
 /**
@@ -895,7 +896,18 @@ struct ieee80211_tx_info {
 				unsigned long jiffies;
 			};
 			/* NB: vif can be NULL for injected frames */
-			struct ieee80211_vif *vif;
+			union {
+				/* NB: vif can be NULL for injected frames */
+				struct ieee80211_vif *vif;
+
+				/* When packets are enqueued on txq it's easy
+				 * to re-construct the vif pointer. There's no
+				 * more space in tx_info so it can be used to
+				 * store the necessary enqueue time for packet
+				 * sojourn time computation.
+				 */
+				codel_time_t enqueue_time;
+			};
 			struct ieee80211_key_conf *hw_key;
 			u32 flags;
 			/* 4 bytes free */
@@ -2147,9 +2159,6 @@ enum ieee80211_hw_flags {
  * @n_cipher_schemes: a size of an array of cipher schemes definitions.
  * @cipher_schemes: a pointer to an array of cipher scheme definitions
  *	supported by HW.
- *
- * @txq_ac_max_pending: maximum number of frames per AC pending in all txq
- *	entries for a vif.
  */
 struct ieee80211_hw {
 	struct ieee80211_conf conf;
@@ -2180,7 +2189,6 @@ struct ieee80211_hw {
 	u8 uapsd_max_sp_len;
 	u8 n_cipher_schemes;
 	const struct ieee80211_cipher_scheme *cipher_schemes;
-	int txq_ac_max_pending;
 };
 
 static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw,
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 2d8edaad29cb..be1fe2283254 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -35,6 +35,7 @@ enum {
 	ND_OPT_ROUTE_INFO = 24,		/* RFC4191 */
 	ND_OPT_RDNSS = 25,		/* RFC5006 */
 	ND_OPT_DNSSL = 31,		/* RFC6106 */
+	ND_OPT_6CO = 34,		/* RFC6775 */
 	__ND_OPT_MAX
 };
 
@@ -53,11 +54,21 @@ enum {
 
 #include <net/neighbour.h>
 
+/* Set to 3 to get tracing... */
+#define ND_DEBUG 1
+
+#define ND_PRINTK(val, level, fmt, ...)				\
+do {								\
+	if (val <= ND_DEBUG)					\
+		net_##level##_ratelimited(fmt, ##__VA_ARGS__);	\
+} while (0)
+
 struct ctl_table;
 struct inet6_dev;
 struct net_device;
 struct net_proto_family;
 struct sk_buff;
+struct prefix_info;
 
 extern struct neigh_table nd_tbl;
 
@@ -99,20 +110,201 @@ struct ndisc_options {
 #endif
 	struct nd_opt_hdr *nd_useropts;
 	struct nd_opt_hdr *nd_useropts_end;
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+	struct nd_opt_hdr *nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR + 1];
+#endif
 };
 
-#define nd_opts_src_lladdr	nd_opt_array[ND_OPT_SOURCE_LL_ADDR]
-#define nd_opts_tgt_lladdr	nd_opt_array[ND_OPT_TARGET_LL_ADDR]
-#define nd_opts_pi		nd_opt_array[ND_OPT_PREFIX_INFO]
-#define nd_opts_pi_end		nd_opt_array[__ND_OPT_PREFIX_INFO_END]
-#define nd_opts_rh		nd_opt_array[ND_OPT_REDIRECT_HDR]
-#define nd_opts_mtu		nd_opt_array[ND_OPT_MTU]
+#define nd_opts_src_lladdr		nd_opt_array[ND_OPT_SOURCE_LL_ADDR]
+#define nd_opts_tgt_lladdr		nd_opt_array[ND_OPT_TARGET_LL_ADDR]
+#define nd_opts_pi			nd_opt_array[ND_OPT_PREFIX_INFO]
+#define nd_opts_pi_end			nd_opt_array[__ND_OPT_PREFIX_INFO_END]
+#define nd_opts_rh			nd_opt_array[ND_OPT_REDIRECT_HDR]
+#define nd_opts_mtu			nd_opt_array[ND_OPT_MTU]
+#define nd_802154_opts_src_lladdr	nd_802154_opt_array[ND_OPT_SOURCE_LL_ADDR]
+#define nd_802154_opts_tgt_lladdr	nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR]
 
 #define NDISC_OPT_SPACE(len) (((len)+2+7)&~7)
 
-struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
+struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
+					  u8 *opt, int opt_len,
 					  struct ndisc_options *ndopts);
 
+void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data,
+			      int data_len, int pad);
+
+#define NDISC_OPS_REDIRECT_DATA_SPACE	2
+
+/*
+ * This structure defines the hooks for IPv6 neighbour discovery.
+ * The following hooks can be defined; unless noted otherwise, they are
+ * optional and can be filled with a null pointer.
+ *
+ * int (*is_useropt)(u8 nd_opt_type):
+ *     This function is called when IPv6 decide RA userspace options. if
+ *     this function returns 1 then the option given by nd_opt_type will
+ *     be handled as userspace option additional to the IPv6 options.
+ *
+ * int (*parse_options)(const struct net_device *dev,
+ *			struct nd_opt_hdr *nd_opt,
+ *			struct ndisc_options *ndopts):
+ *     This function is called while parsing ndisc ops and put each position
+ *     as pointer into ndopts. If this function return unequal 0, then this
+ *     function took care about the ndisc option, if 0 then the IPv6 ndisc
+ *     option parser will take care about that option.
+ *
+ * void (*update)(const struct net_device *dev, struct neighbour *n,
+ *		  u32 flags, u8 icmp6_type,
+ *		  const struct ndisc_options *ndopts):
+ *     This function is called when IPv6 ndisc updates the neighbour cache
+ *     entry. Additional options which can be updated may be previously
+ *     parsed by parse_opts callback and accessible over ndopts parameter.
+ *
+ * int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type,
+ *			 struct neighbour *neigh, u8 *ha_buf,
+ *			 u8 **ha):
+ *     This function is called when the necessary option space will be
+ *     calculated before allocating a skb. The parameters neigh, ha_buf
+ *     abd ha are available on NDISC_REDIRECT messages only.
+ *
+ * void (*fill_addr_option)(const struct net_device *dev,
+ *			    struct sk_buff *skb, u8 icmp6_type,
+ *			    const u8 *ha):
+ *     This function is called when the skb will finally fill the option
+ *     fields inside skb. NOTE: this callback should fill the option
+ *     fields to the skb which are previously indicated by opt_space
+ *     parameter. That means the decision to add such option should
+ *     not lost between these two callbacks, e.g. protected by interface
+ *     up state.
+ *
+ * void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev,
+ *			       const struct prefix_info *pinfo,
+ *			       struct inet6_dev *in6_dev,
+ *			       struct in6_addr *addr,
+ *			       int addr_type, u32 addr_flags,
+ *			       bool sllao, bool tokenized,
+ *			       __u32 valid_lft, u32 prefered_lft,
+ *			       bool dev_addr_generated):
+ *     This function is called when a RA messages is received with valid
+ *     PIO option fields and an IPv6 address will be added to the interface
+ *     for autoconfiguration. The parameter dev_addr_generated reports about
+ *     if the address was based on dev->dev_addr or not. This can be used
+ *     to add a second address if link-layer operates with two link layer
+ *     addresses. E.g. 802.15.4 6LoWPAN.
+ */
+struct ndisc_ops {
+	int	(*is_useropt)(u8 nd_opt_type);
+	int	(*parse_options)(const struct net_device *dev,
+				 struct nd_opt_hdr *nd_opt,
+				 struct ndisc_options *ndopts);
+	void	(*update)(const struct net_device *dev, struct neighbour *n,
+			  u32 flags, u8 icmp6_type,
+			  const struct ndisc_options *ndopts);
+	int	(*opt_addr_space)(const struct net_device *dev, u8 icmp6_type,
+				  struct neighbour *neigh, u8 *ha_buf,
+				  u8 **ha);
+	void	(*fill_addr_option)(const struct net_device *dev,
+				    struct sk_buff *skb, u8 icmp6_type,
+				    const u8 *ha);
+	void	(*prefix_rcv_add_addr)(struct net *net, struct net_device *dev,
+				       const struct prefix_info *pinfo,
+				       struct inet6_dev *in6_dev,
+				       struct in6_addr *addr,
+				       int addr_type, u32 addr_flags,
+				       bool sllao, bool tokenized,
+				       __u32 valid_lft, u32 prefered_lft,
+				       bool dev_addr_generated);
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int ndisc_ops_is_useropt(const struct net_device *dev,
+				       u8 nd_opt_type)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->is_useropt)
+		return dev->ndisc_ops->is_useropt(nd_opt_type);
+	else
+		return 0;
+}
+
+static inline int ndisc_ops_parse_options(const struct net_device *dev,
+					  struct nd_opt_hdr *nd_opt,
+					  struct ndisc_options *ndopts)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->parse_options)
+		return dev->ndisc_ops->parse_options(dev, nd_opt, ndopts);
+	else
+		return 0;
+}
+
+static inline void ndisc_ops_update(const struct net_device *dev,
+					  struct neighbour *n, u32 flags,
+					  u8 icmp6_type,
+					  const struct ndisc_options *ndopts)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->update)
+		dev->ndisc_ops->update(dev, n, flags, icmp6_type, ndopts);
+}
+
+static inline int ndisc_ops_opt_addr_space(const struct net_device *dev,
+					   u8 icmp6_type)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space &&
+	    icmp6_type != NDISC_REDIRECT)
+		return dev->ndisc_ops->opt_addr_space(dev, icmp6_type, NULL,
+						      NULL, NULL);
+	else
+		return 0;
+}
+
+static inline int ndisc_ops_redirect_opt_addr_space(const struct net_device *dev,
+						    struct neighbour *neigh,
+						    u8 *ha_buf, u8 **ha)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space)
+		return dev->ndisc_ops->opt_addr_space(dev, NDISC_REDIRECT,
+						      neigh, ha_buf, ha);
+	else
+		return 0;
+}
+
+static inline void ndisc_ops_fill_addr_option(const struct net_device *dev,
+					      struct sk_buff *skb,
+					      u8 icmp6_type)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option &&
+	    icmp6_type != NDISC_REDIRECT)
+		dev->ndisc_ops->fill_addr_option(dev, skb, icmp6_type, NULL);
+}
+
+static inline void ndisc_ops_fill_redirect_addr_option(const struct net_device *dev,
+						       struct sk_buff *skb,
+						       const u8 *ha)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option)
+		dev->ndisc_ops->fill_addr_option(dev, skb, NDISC_REDIRECT, ha);
+}
+
+static inline void ndisc_ops_prefix_rcv_add_addr(struct net *net,
+						 struct net_device *dev,
+						 const struct prefix_info *pinfo,
+						 struct inet6_dev *in6_dev,
+						 struct in6_addr *addr,
+						 int addr_type, u32 addr_flags,
+						 bool sllao, bool tokenized,
+						 __u32 valid_lft,
+						 u32 prefered_lft,
+						 bool dev_addr_generated)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->prefix_rcv_add_addr)
+		dev->ndisc_ops->prefix_rcv_add_addr(net, dev, pinfo, in6_dev,
+						    addr, addr_type,
+						    addr_flags, sllao,
+						    tokenized, valid_lft,
+						    prefered_lft,
+						    dev_addr_generated);
+}
+#endif
+
 /*
  * Return the padding between the option length and the start of the
  * link addr.  Currently only IP-over-InfiniBand needs this, although
@@ -127,23 +319,48 @@ static inline int ndisc_addr_option_pad(unsigned short type)
 	}
 }
 
-static inline int ndisc_opt_addr_space(struct net_device *dev)
+static inline int __ndisc_opt_addr_space(unsigned char addr_len, int pad)
 {
-	return NDISC_OPT_SPACE(dev->addr_len +
-			       ndisc_addr_option_pad(dev->type));
+	return NDISC_OPT_SPACE(addr_len + pad);
 }
 
-static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p,
-				      struct net_device *dev)
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int ndisc_opt_addr_space(struct net_device *dev, u8 icmp6_type)
+{
+	return __ndisc_opt_addr_space(dev->addr_len,
+				      ndisc_addr_option_pad(dev->type)) +
+		ndisc_ops_opt_addr_space(dev, icmp6_type);
+}
+
+static inline int ndisc_redirect_opt_addr_space(struct net_device *dev,
+						struct neighbour *neigh,
+						u8 *ops_data_buf,
+						u8 **ops_data)
+{
+	return __ndisc_opt_addr_space(dev->addr_len,
+				      ndisc_addr_option_pad(dev->type)) +
+		ndisc_ops_redirect_opt_addr_space(dev, neigh, ops_data_buf,
+						  ops_data);
+}
+#endif
+
+static inline u8 *__ndisc_opt_addr_data(struct nd_opt_hdr *p,
+					unsigned char addr_len, int prepad)
 {
 	u8 *lladdr = (u8 *)(p + 1);
 	int lladdrlen = p->nd_opt_len << 3;
-	int prepad = ndisc_addr_option_pad(dev->type);
-	if (lladdrlen != ndisc_opt_addr_space(dev))
+	if (lladdrlen != __ndisc_opt_addr_space(addr_len, prepad))
 		return NULL;
 	return lladdr + prepad;
 }
 
+static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p,
+				      struct net_device *dev)
+{
+	return __ndisc_opt_addr_data(p, dev->addr_len,
+				     ndisc_addr_option_pad(dev->type));
+}
+
 static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd)
 {
 	const u32 *p32 = pkey;
@@ -194,6 +411,9 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target);
 int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev,
 		 int dir);
 
+void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
+		  const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
+		  struct ndisc_options *ndopts);
 
 /*
  *	IGMP
diff --git a/include/net/netevent.h b/include/net/netevent.h
index d8bbb38584b6..f440df172b56 100644
--- a/include/net/netevent.h
+++ b/include/net/netevent.h
@@ -24,6 +24,7 @@ struct netevent_redirect {
 enum netevent_notif_type {
 	NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */
 	NETEVENT_REDIRECT,	   /* arg is struct netevent_redirect ptr */
+	NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */
 };
 
 int register_netevent_notifier(struct notifier_block *nb);
diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index 9c5638ad872e..0dbce55437f2 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -28,8 +28,8 @@ struct nf_queue_handler {
 						struct nf_hook_ops *ops);
 };
 
-void nf_register_queue_handler(const struct nf_queue_handler *qh);
-void nf_unregister_queue_handler(void);
+void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh);
+void nf_unregister_queue_handler(struct net *net);
 void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict);
 
 void nf_queue_entry_get_refs(struct nf_queue_entry *entry);
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 1ea19a6e72e6..30c1d9489ae2 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -167,6 +167,7 @@ struct nft_set_elem {
 
 struct nft_set;
 struct nft_set_iter {
+	u8		genmask;
 	unsigned int	count;
 	unsigned int	skip;
 	int		err;
diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h
index 38aa4983e2a9..36d723579af2 100644
--- a/include/net/netns/netfilter.h
+++ b/include/net/netns/netfilter.h
@@ -5,11 +5,13 @@
 
 struct proc_dir_entry;
 struct nf_logger;
+struct nf_queue_handler;
 
 struct netns_nf {
 #if defined CONFIG_PROC_FS
 	struct proc_dir_entry *proc_netfilter;
 #endif
+	const struct nf_queue_handler __rcu *queue_handler;
 	const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO];
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header *nf_log_dir_header;
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 0f7efa88f210..3722dda0199d 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -392,16 +392,20 @@ struct tc_cls_u32_offload {
 	};
 };
 
-static inline bool tc_should_offload(struct net_device *dev, u32 flags)
+static inline bool tc_should_offload(const struct net_device *dev,
+				     const struct tcf_proto *tp, u32 flags)
 {
+	const struct Qdisc *sch = tp->q;
+	const struct Qdisc_class_ops *cops = sch->ops->cl_ops;
+
 	if (!(dev->features & NETIF_F_HW_TC))
 		return false;
-
 	if (flags & TCA_CLS_FLAGS_SKIP_HW)
 		return false;
-
 	if (!dev->netdev_ops->ndo_setup_tc)
 		return false;
+	if (cops && cops->tcf_cl_offload)
+		return cops->tcf_cl_offload(tp->classid);
 
 	return true;
 }
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index fea53f4d92ca..7caa99b482c6 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -67,12 +67,12 @@ struct qdisc_watchdog {
 };
 
 void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc);
-void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool throttle);
+void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires);
 
 static inline void qdisc_watchdog_schedule(struct qdisc_watchdog *wd,
 					   psched_time_t expires)
 {
-	qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires), true);
+	qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires));
 }
 
 void qdisc_watchdog_cancel(struct qdisc_watchdog *wd);
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 006a7b81d758..4113916cc1bb 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -98,10 +98,11 @@ struct rtnl_link_ops {
 						   const struct net_device *dev,
 						   const struct net_device *slave_dev);
 	struct net		*(*get_link_net)(const struct net_device *dev);
-	size_t			(*get_linkxstats_size)(const struct net_device *dev);
+	size_t			(*get_linkxstats_size)(const struct net_device *dev,
+						       int attr);
 	int			(*fill_linkxstats)(struct sk_buff *skb,
 						   const struct net_device *dev,
-						   int *prividx);
+						   int *prividx, int attr);
 };
 
 int __rtnl_link_register(struct rtnl_link_ops *ops);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index a1fd76c22a59..909aff2db2b3 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -26,14 +26,6 @@ struct qdisc_rate_table {
 enum qdisc_state_t {
 	__QDISC_STATE_SCHED,
 	__QDISC_STATE_DEACTIVATED,
-	__QDISC_STATE_THROTTLED,
-};
-
-/*
- * following bits are only changed while qdisc lock is held
- */
-enum qdisc___state_t {
-	__QDISC___STATE_RUNNING = 1,
 };
 
 struct qdisc_size_table {
@@ -45,8 +37,10 @@ struct qdisc_size_table {
 };
 
 struct Qdisc {
-	int 			(*enqueue)(struct sk_buff *skb, struct Qdisc *dev);
-	struct sk_buff *	(*dequeue)(struct Qdisc *dev);
+	int 			(*enqueue)(struct sk_buff *skb,
+					   struct Qdisc *sch,
+					   struct sk_buff **to_free);
+	struct sk_buff *	(*dequeue)(struct Qdisc *sch);
 	unsigned int		flags;
 #define TCQ_F_BUILTIN		1
 #define TCQ_F_INGRESS		2
@@ -70,31 +64,25 @@ struct Qdisc {
 	struct list_head	list;
 	u32			handle;
 	u32			parent;
-	int			(*reshape_fail)(struct sk_buff *skb,
-					struct Qdisc *q);
-
 	void			*u32_node;
 
-	/* This field is deprecated, but it is still used by CBQ
-	 * and it will live until better solution will be invented.
-	 */
-	struct Qdisc		*__parent;
 	struct netdev_queue	*dev_queue;
 
 	struct gnet_stats_rate_est64	rate_est;
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
 	struct gnet_stats_queue	__percpu *cpu_qstats;
 
-	struct Qdisc		*next_sched;
-	struct sk_buff		*gso_skb;
 	/*
 	 * For performance sake on SMP, we put highly modified fields at the end
 	 */
-	unsigned long		state;
+	struct sk_buff		*gso_skb ____cacheline_aligned_in_smp;
 	struct sk_buff_head	q;
 	struct gnet_stats_basic_packed bstats;
-	unsigned int		__state;
+	seqcount_t		running;
 	struct gnet_stats_queue	qstats;
+	unsigned long		state;
+	struct Qdisc            *next_sched;
+	struct sk_buff		*skb_bad_txq;
 	struct rcu_head		rcu_head;
 	int			padded;
 	atomic_t		refcnt;
@@ -104,20 +92,24 @@ struct Qdisc {
 
 static inline bool qdisc_is_running(const struct Qdisc *qdisc)
 {
-	return (qdisc->__state & __QDISC___STATE_RUNNING) ? true : false;
+	return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
 }
 
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
 	if (qdisc_is_running(qdisc))
 		return false;
-	qdisc->__state |= __QDISC___STATE_RUNNING;
+	/* Variant of write_seqcount_begin() telling lockdep a trylock
+	 * was attempted.
+	 */
+	raw_write_seqcount_begin(&qdisc->running);
+	seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_);
 	return true;
 }
 
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
-	qdisc->__state &= ~__QDISC___STATE_RUNNING;
+	write_seqcount_end(&qdisc->running);
 }
 
 static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
@@ -135,21 +127,6 @@ static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq)
 #endif
 }
 
-static inline bool qdisc_is_throttled(const struct Qdisc *qdisc)
-{
-	return test_bit(__QDISC_STATE_THROTTLED, &qdisc->state) ? true : false;
-}
-
-static inline void qdisc_throttled(struct Qdisc *qdisc)
-{
-	set_bit(__QDISC_STATE_THROTTLED, &qdisc->state);
-}
-
-static inline void qdisc_unthrottled(struct Qdisc *qdisc)
-{
-	clear_bit(__QDISC_STATE_THROTTLED, &qdisc->state);
-}
-
 struct Qdisc_class_ops {
 	/* Child qdisc manipulation */
 	struct netdev_queue *	(*select_queue)(struct Qdisc *, struct tcmsg *);
@@ -168,6 +145,7 @@ struct Qdisc_class_ops {
 
 	/* Filter manipulation */
 	struct tcf_proto __rcu ** (*tcf_chain)(struct Qdisc *, unsigned long);
+	bool			(*tcf_cl_offload)(u32 classid);
 	unsigned long		(*bind_tcf)(struct Qdisc *, unsigned long,
 					u32 classid);
 	void			(*unbind_tcf)(struct Qdisc *, unsigned long);
@@ -185,10 +163,11 @@ struct Qdisc_ops {
 	char			id[IFNAMSIZ];
 	int			priv_size;
 
-	int 			(*enqueue)(struct sk_buff *, struct Qdisc *);
+	int 			(*enqueue)(struct sk_buff *skb,
+					   struct Qdisc *sch,
+					   struct sk_buff **to_free);
 	struct sk_buff *	(*dequeue)(struct Qdisc *);
 	struct sk_buff *	(*peek)(struct Qdisc *);
-	unsigned int		(*drop)(struct Qdisc *);
 
 	int			(*init)(struct Qdisc *, struct nlattr *arg);
 	void			(*reset)(struct Qdisc *);
@@ -321,6 +300,14 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc)
 	return qdisc_lock(root);
 }
 
+static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
+{
+	struct Qdisc *root = qdisc_root_sleeping(qdisc);
+
+	ASSERT_RTNL();
+	return &root->running;
+}
+
 static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc)
 {
 	return qdisc->dev_queue->dev;
@@ -516,10 +503,11 @@ static inline void qdisc_calculate_pkt_len(struct sk_buff *skb,
 #endif
 }
 
-static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+				struct sk_buff **to_free)
 {
 	qdisc_calculate_pkt_len(skb, sch);
-	return sch->enqueue(skb, sch);
+	return sch->enqueue(skb, sch, to_free);
 }
 
 static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
@@ -644,40 +632,36 @@ static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
 	return __qdisc_dequeue_head(sch, &sch->q);
 }
 
+/* Instead of calling kfree_skb() while root qdisc lock is held,
+ * queue the skb for future freeing at end of __dev_xmit_skb()
+ */
+static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free)
+{
+	skb->next = *to_free;
+	*to_free = skb;
+}
+
 static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch,
-					      struct sk_buff_head *list)
+						   struct sk_buff_head *list,
+						   struct sk_buff **to_free)
 {
 	struct sk_buff *skb = __skb_dequeue(list);
 
 	if (likely(skb != NULL)) {
 		unsigned int len = qdisc_pkt_len(skb);
+
 		qdisc_qstats_backlog_dec(sch, skb);
-		kfree_skb(skb);
+		__qdisc_drop(skb, to_free);
 		return len;
 	}
 
 	return 0;
 }
 
-static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch)
-{
-	return __qdisc_queue_drop_head(sch, &sch->q);
-}
-
-static inline struct sk_buff *__qdisc_dequeue_tail(struct Qdisc *sch,
-						   struct sk_buff_head *list)
-{
-	struct sk_buff *skb = __skb_dequeue_tail(list);
-
-	if (likely(skb != NULL))
-		qdisc_qstats_backlog_dec(sch, skb);
-
-	return skb;
-}
-
-static inline struct sk_buff *qdisc_dequeue_tail(struct Qdisc *sch)
+static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch,
+						 struct sk_buff **to_free)
 {
-	return __qdisc_dequeue_tail(sch, &sch->q);
+	return __qdisc_queue_drop_head(sch, &sch->q, to_free);
 }
 
 static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch)
@@ -691,9 +675,11 @@ static inline struct sk_buff *qdisc_peek_dequeued(struct Qdisc *sch)
 	/* we can reuse ->gso_skb because peek isn't called for root qdiscs */
 	if (!sch->gso_skb) {
 		sch->gso_skb = sch->dequeue(sch);
-		if (sch->gso_skb)
+		if (sch->gso_skb) {
 			/* it's still part of the queue */
+			qdisc_qstats_backlog_inc(sch, sch->gso_skb);
 			sch->q.qlen++;
+		}
 	}
 
 	return sch->gso_skb;
@@ -706,6 +692,7 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
 
 	if (skb) {
 		sch->gso_skb = NULL;
+		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 	} else {
 		skb = sch->dequeue(sch);
@@ -714,19 +701,21 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
 	return skb;
 }
 
-static inline void __qdisc_reset_queue(struct Qdisc *sch,
-				       struct sk_buff_head *list)
+static inline void __qdisc_reset_queue(struct sk_buff_head *list)
 {
 	/*
 	 * We do not know the backlog in bytes of this list, it
 	 * is up to the caller to correct it
 	 */
-	__skb_queue_purge(list);
+	if (!skb_queue_empty(list)) {
+		rtnl_kfree_skbs(list->next, list->prev);
+		__skb_queue_head_init(list);
+	}
 }
 
 static inline void qdisc_reset_queue(struct Qdisc *sch)
 {
-	__qdisc_reset_queue(sch, &sch->q);
+	__qdisc_reset_queue(&sch->q);
 	sch->qstats.backlog = 0;
 }
 
@@ -747,46 +736,19 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	return old;
 }
 
-static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch,
-					      struct sk_buff_head *list)
-{
-	struct sk_buff *skb = __qdisc_dequeue_tail(sch, list);
-
-	if (likely(skb != NULL)) {
-		unsigned int len = qdisc_pkt_len(skb);
-		kfree_skb(skb);
-		return len;
-	}
-
-	return 0;
-}
-
-static inline unsigned int qdisc_queue_drop(struct Qdisc *sch)
-{
-	return __qdisc_queue_drop(sch, &sch->q);
-}
-
-static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch)
+static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch)
 {
-	kfree_skb(skb);
+	rtnl_kfree_skbs(skb, skb);
 	qdisc_qstats_drop(sch);
-
-	return NET_XMIT_DROP;
 }
 
-static inline int qdisc_reshape_fail(struct sk_buff *skb, struct Qdisc *sch)
+
+static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch,
+			     struct sk_buff **to_free)
 {
+	__qdisc_drop(skb, to_free);
 	qdisc_qstats_drop(sch);
 
-#ifdef CONFIG_NET_CLS_ACT
-	if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch))
-		goto drop;
-
-	return NET_XMIT_SUCCESS;
-
-drop:
-#endif
-	kfree_skb(skb);
 	return NET_XMIT_DROP;
 }
 
diff --git a/include/net/tc_act/tc_defact.h b/include/net/tc_act/tc_defact.h
index 9763dcbb9bc3..ab9b5d6be67b 100644
--- a/include/net/tc_act/tc_defact.h
+++ b/include/net/tc_act/tc_defact.h
@@ -5,8 +5,8 @@
 
 struct tcf_defact {
 	struct tcf_common	common;
-	u32     		tcfd_datalen;
-	void    		*tcfd_defdata;
+	u32		tcfd_datalen;
+	void		*tcfd_defdata;
 };
 #define to_defact(a) \
 	container_of(a->priv, struct tcf_defact, common)
diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h
index dc9a09aefb33..c55facd17b7e 100644
--- a/include/net/tc_act/tc_ife.h
+++ b/include/net/tc_act/tc_ife.h
@@ -36,7 +36,7 @@ struct tcf_meta_ops {
 	int	(*encode)(struct sk_buff *, void *, struct tcf_meta_info *);
 	int	(*decode)(struct sk_buff *, void *, u16 len);
 	int	(*get)(struct sk_buff *skb, struct tcf_meta_info *mi);
-	int	(*alloc)(struct tcf_meta_info *, void *);
+	int	(*alloc)(struct tcf_meta_info *, void *, gfp_t);
 	void	(*release)(struct tcf_meta_info *);
 	int	(*validate)(void *val, int len);
 	struct module	*owner;
@@ -48,8 +48,8 @@ int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi);
 int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi);
 int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
 			const void *dval);
-int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval);
-int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval);
+int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp);
+int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp);
 int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi);
 int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi);
 int ife_validate_meta_u32(void *val, int len);
diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h
index b496d5ad7d42..d01a5d40cfb5 100644
--- a/include/net/tc_act/tc_skbedit.h
+++ b/include/net/tc_act/tc_skbedit.h
@@ -24,11 +24,11 @@
 
 struct tcf_skbedit {
 	struct tcf_common	common;
-	u32			flags;
-	u32     		priority;
-	u32     		mark;
-	u16			queue_mapping;
-	/* XXX: 16-bit pad here? */
+	u32		flags;
+	u32		priority;
+	u32		mark;
+	u16		queue_mapping;
+	u16		ptype;
 };
 #define to_skbedit(a) \
 	container_of(a->priv, struct tcf_skbedit, common)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0bcc70f4e1fb..c00e7d51bb18 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -589,7 +589,7 @@ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
 	 * On the other hand, for extremely large MSS devices, handling
 	 * smaller than MSS windows in this way does make sense.
 	 */
-	if (tp->max_window >= 512)
+	if (tp->max_window > TCP_MSS_DEFAULT)
 		cutoff = (tp->max_window >> 1);
 	else
 		cutoff = tp->max_window;
@@ -767,6 +767,7 @@ struct tcp_skb_cb {
 	union {
 		struct {
 			/* There is space for up to 20 bytes */
+			__u32 in_flight;/* Bytes in flight when packet sent */
 		} tx;   /* only used for outgoing skbs */
 		union {
 			struct inet_skb_parm	h4;
@@ -859,6 +860,7 @@ union tcp_cc_info;
 struct ack_sample {
 	u32 pkts_acked;
 	s32 rtt_us;
+	u32 in_flight;
 };
 
 struct tcp_congestion_ops {
@@ -1382,7 +1384,7 @@ union tcp_md5sum_block {
 /* - pool: digest algorithm, hash description and scratch buffer */
 struct tcp_md5sig_pool {
 	struct ahash_request	*md5_req;
-	union tcp_md5sum_block	md5_blk;
+	void			*scratch;
 };
 
 /* - functions */
@@ -1418,7 +1420,6 @@ static inline void tcp_put_md5sig_pool(void)
 	local_bh_enable();
 }
 
-int tcp_md5_hash_header(struct tcp_md5sig_pool *, const struct tcphdr *);
 int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *,
 			  unsigned int header_len);
 int tcp_md5_hash_key(struct tcp_md5sig_pool *hp,
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 9d14f707e534..02c5be037451 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -84,6 +84,46 @@ struct udp_tunnel_sock_cfg {
 void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 			   struct udp_tunnel_sock_cfg *sock_cfg);
 
+/* -- List of parsable UDP tunnel types --
+ *
+ * Adding to this list will result in serious debate.  The main issue is
+ * that this list is essentially a list of workarounds for either poorly
+ * designed tunnels, or poorly designed device offloads.
+ *
+ * The parsing supported via these types should really be used for Rx
+ * traffic only as the network stack will have already inserted offsets for
+ * the location of the headers in the skb.  In addition any ports that are
+ * pushed should be kept within the namespace without leaking to other
+ * devices such as VFs or other ports on the same device.
+ *
+ * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the
+ * need to use this for Rx checksum offload.  It should not be necessary to
+ * call this function to perform Tx offloads on outgoing traffic.
+ */
+enum udp_parsable_tunnel_type {
+	UDP_TUNNEL_TYPE_VXLAN,		/* RFC 7348 */
+	UDP_TUNNEL_TYPE_GENEVE,		/* draft-ietf-nvo3-geneve */
+	UDP_TUNNEL_TYPE_VXLAN_GPE,	/* draft-ietf-nvo3-vxlan-gpe */
+};
+
+struct udp_tunnel_info {
+	unsigned short type;
+	sa_family_t sa_family;
+	__be16 port;
+};
+
+/* Notify network devices of offloadable types */
+void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
+			     unsigned short type);
+void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type);
+void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type);
+
+static inline void udp_tunnel_get_rx_info(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev);
+}
+
 /* Transmit the skb using UDP encapsulation. */
 void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
 			 __be32 src, __be32 dst, __u8 tos, __u8 ttl,
@@ -105,12 +145,14 @@ struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family,
 				    __be16 flags, __be64 tunnel_id,
 				    int md_size);
 
+#ifdef CONFIG_INET
 static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum)
 {
 	int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
 
 	return iptunnel_handle_offloads(skb, type);
 }
+#endif
 
 static inline void udp_tunnel_encap_enable(struct socket *sock)
 {
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index b8803165df91..b96d0360c095 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -1,13 +1,10 @@
 #ifndef __NET_VXLAN_H
 #define __NET_VXLAN_H 1
 
-#include <linux/ip.h>
-#include <linux/ipv6.h>
 #include <linux/if_vlan.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <linux/udp.h>
+#include <net/udp_tunnel.h>
 #include <net/dst_metadata.h>
+#include <net/udp_tunnel.h>
 
 /* VXLAN protocol (RFC 7348) header:
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -392,12 +389,6 @@ static inline __be32 vxlan_compute_rco(unsigned int start, unsigned int offset)
 	return vni_field;
 }
 
-static inline void vxlan_get_rx_port(struct net_device *netdev)
-{
-	ASSERT_RTNL();
-	call_netdevice_notifiers(NETDEV_OFFLOAD_PUSH_VXLAN, netdev);
-}
-
 static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs)
 {
 	return vs->sock->sk->sk_family;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 432bed510369..7e440d41487a 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -217,10 +217,10 @@ enum ib_device_cap_flags {
 	IB_DEVICE_CROSS_CHANNEL		= (1 << 27),
 	IB_DEVICE_MANAGED_FLOW_STEERING		= (1 << 29),
 	IB_DEVICE_SIGNATURE_HANDOVER		= (1 << 30),
-	IB_DEVICE_ON_DEMAND_PAGING		= (1 << 31),
+	IB_DEVICE_ON_DEMAND_PAGING		= (1ULL << 31),
 	IB_DEVICE_SG_GAPS_REG			= (1ULL << 32),
-	IB_DEVICE_VIRTUAL_FUNCTION		= ((u64)1 << 33),
-	IB_DEVICE_RAW_SCATTER_FCS		= ((u64)1 << 34),
+	IB_DEVICE_VIRTUAL_FUNCTION		= (1ULL << 33),
+	IB_DEVICE_RAW_SCATTER_FCS		= (1ULL << 34),
 };
 
 enum ib_signature_prot_cap {
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index 16274e2133cd..9c9a27d42aaa 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -203,7 +203,9 @@ struct rvt_driver_provided {
 
 	/*
 	 * Allocate a private queue pair data structure for driver specific
-	 * information which is opaque to rdmavt.
+	 * information which is opaque to rdmavt.  Errors are returned via
+	 * ERR_PTR(err).  The driver is free to return NULL or a valid
+	 * pointer.
 	 */
 	void * (*qp_priv_alloc)(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 				gfp_t gfp);
diff --git a/include/soc/fsl/qe/immap_qe.h b/include/soc/fsl/qe/immap_qe.h
index bedbff891423..c76ef30b05ba 100644
--- a/include/soc/fsl/qe/immap_qe.h
+++ b/include/soc/fsl/qe/immap_qe.h
@@ -159,10 +159,7 @@ struct spi {
 
 /* SI */
 struct si1 {
-	__be16	siamr1;		/* SI1 TDMA mode register */
-	__be16	sibmr1;		/* SI1 TDMB mode register */
-	__be16	sicmr1;		/* SI1 TDMC mode register */
-	__be16	sidmr1;		/* SI1 TDMD mode register */
+	__be16	sixmr1[4];	/* SI1 TDMx (x = A B C D) mode register */
 	u8	siglmr1_h;	/* SI1 global mode register high */
 	u8	res0[0x1];
 	u8	sicmdr1_h;	/* SI1 command register high */
diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h
index 33b29ead3d55..70339d7958c0 100644
--- a/include/soc/fsl/qe/qe.h
+++ b/include/soc/fsl/qe/qe.h
@@ -80,6 +80,8 @@ enum qe_clock {
 	QE_CLK22,		/* Clock 22 */
 	QE_CLK23,		/* Clock 23 */
 	QE_CLK24,		/* Clock 24 */
+	QE_RSYNC_PIN,		/* RSYNC from pin */
+	QE_TSYNC_PIN,		/* TSYNC from pin */
 	QE_CLK_DUMMY
 };
 
@@ -242,6 +244,22 @@ static inline int qe_alive_during_sleep(void)
 #define qe_muram_addr cpm_muram_addr
 #define qe_muram_offset cpm_muram_offset
 
+#define qe_setbits32(_addr, _v) iowrite32be(ioread32be(_addr) |  (_v), (_addr))
+#define qe_clrbits32(_addr, _v) iowrite32be(ioread32be(_addr) & ~(_v), (_addr))
+
+#define qe_setbits16(_addr, _v) iowrite16be(ioread16be(_addr) |  (_v), (_addr))
+#define qe_clrbits16(_addr, _v) iowrite16be(ioread16be(_addr) & ~(_v), (_addr))
+
+#define qe_setbits8(_addr, _v) iowrite8(ioread8(_addr) |  (_v), (_addr))
+#define qe_clrbits8(_addr, _v) iowrite8(ioread8(_addr) & ~(_v), (_addr))
+
+#define qe_clrsetbits32(addr, clear, set) \
+	iowrite32be((ioread32be(addr) & ~(clear)) | (set), (addr))
+#define qe_clrsetbits16(addr, clear, set) \
+	iowrite16be((ioread16be(addr) & ~(clear)) | (set), (addr))
+#define qe_clrsetbits8(addr, clear, set) \
+	iowrite8((ioread8(addr) & ~(clear)) | (set), (addr))
+
 /* Structure that defines QE firmware binary files.
  *
  * See Documentation/powerpc/qe_firmware.txt for a description of these
@@ -639,6 +657,7 @@ struct ucc_slow_pram {
 #define UCC_SLOW_GUMR_L_MODE_QMC	0x00000002
 
 /* General UCC FAST Mode Register */
+#define UCC_FAST_GUMR_LOOPBACK	0x40000000
 #define UCC_FAST_GUMR_TCI	0x20000000
 #define UCC_FAST_GUMR_TRX	0x10000000
 #define UCC_FAST_GUMR_TTX	0x08000000
diff --git a/include/soc/fsl/qe/qe_tdm.h b/include/soc/fsl/qe/qe_tdm.h
new file mode 100644
index 000000000000..a1664b635f1a
--- /dev/null
+++ b/include/soc/fsl/qe/qe_tdm.h
@@ -0,0 +1,94 @@
+/*
+ * Internal header file for QE TDM mode routines.
+ *
+ * Copyright (C) 2016 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Authors:	Zhao Qiang <[email protected]>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version
+ */
+
+#ifndef _QE_TDM_H_
+#define _QE_TDM_H_
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+
+#include <soc/fsl/qe/immap_qe.h>
+#include <soc/fsl/qe/qe.h>
+
+#include <soc/fsl/qe/ucc.h>
+#include <soc/fsl/qe/ucc_fast.h>
+
+/* SI RAM entries */
+#define SIR_LAST	0x0001
+#define SIR_BYTE	0x0002
+#define SIR_CNT(x)	((x) << 2)
+#define SIR_CSEL(x)	((x) << 5)
+#define SIR_SGS		0x0200
+#define SIR_SWTR	0x4000
+#define SIR_MCC		0x8000
+#define SIR_IDLE	0
+
+/* SIxMR fields */
+#define SIMR_SAD(x) ((x) << 12)
+#define SIMR_SDM_NORMAL	0x0000
+#define SIMR_SDM_INTERNAL_LOOPBACK	0x0800
+#define SIMR_SDM_MASK	0x0c00
+#define SIMR_CRT	0x0040
+#define SIMR_SL		0x0020
+#define SIMR_CE		0x0010
+#define SIMR_FE		0x0008
+#define SIMR_GM		0x0004
+#define SIMR_TFSD(n)	(n)
+#define SIMR_RFSD(n)	((n) << 8)
+
+enum tdm_ts_t {
+	TDM_TX_TS,
+	TDM_RX_TS
+};
+
+enum tdm_framer_t {
+	TDM_FRAMER_T1,
+	TDM_FRAMER_E1
+};
+
+enum tdm_mode_t {
+	TDM_INTERNAL_LOOPBACK,
+	TDM_NORMAL
+};
+
+struct si_mode_info {
+	u8 simr_rfsd;
+	u8 simr_tfsd;
+	u8 simr_crt;
+	u8 simr_sl;
+	u8 simr_ce;
+	u8 simr_fe;
+	u8 simr_gm;
+};
+
+struct ucc_tdm_info {
+	struct ucc_fast_info uf_info;
+	struct si_mode_info si_info;
+};
+
+struct ucc_tdm {
+	u16 tdm_port;		/* port for this tdm:TDMA,TDMB */
+	u32 siram_entry_id;
+	u16 __iomem *siram;
+	struct si1 __iomem *si_regs;
+	enum tdm_framer_t tdm_framer_type;
+	enum tdm_mode_t tdm_mode;
+	u8 num_of_ts;		/* the number of timeslots in this tdm frame */
+	u32 tx_ts_mask;		/* tx time slot mask */
+	u32 rx_ts_mask;		/* rx time slot mask */
+};
+
+int ucc_of_parse_tdm(struct device_node *np, struct ucc_tdm *utdm,
+		     struct ucc_tdm_info *ut_info);
+void ucc_tdm_init(struct ucc_tdm *utdm, struct ucc_tdm_info *ut_info);
+#endif
diff --git a/include/soc/fsl/qe/ucc.h b/include/soc/fsl/qe/ucc.h
index 894f14cbb044..6bbbb597f2af 100644
--- a/include/soc/fsl/qe/ucc.h
+++ b/include/soc/fsl/qe/ucc.h
@@ -41,6 +41,10 @@ int ucc_set_qe_mux_mii_mng(unsigned int ucc_num);
 
 int ucc_set_qe_mux_rxtx(unsigned int ucc_num, enum qe_clock clock,
 	enum comm_dir mode);
+int ucc_set_tdm_rxtx_clk(unsigned int tdm_num, enum qe_clock clock,
+			 enum comm_dir mode);
+int ucc_set_tdm_rxtx_sync(unsigned int tdm_num, enum qe_clock clock,
+			  enum comm_dir mode);
 
 int ucc_mux_set_grant_tsa_bkpt(unsigned int ucc_num, int set, u32 mask);
 
diff --git a/include/soc/fsl/qe/ucc_fast.h b/include/soc/fsl/qe/ucc_fast.h
index df8ea7958c63..3ee9e7c1a7d7 100644
--- a/include/soc/fsl/qe/ucc_fast.h
+++ b/include/soc/fsl/qe/ucc_fast.h
@@ -21,19 +21,37 @@
 
 #include <soc/fsl/qe/ucc.h>
 
-/* Receive BD's status */
+/* Receive BD's status and length*/
 #define R_E	0x80000000	/* buffer empty */
 #define R_W	0x20000000	/* wrap bit */
 #define R_I	0x10000000	/* interrupt on reception */
 #define R_L	0x08000000	/* last */
 #define R_F	0x04000000	/* first */
 
-/* transmit BD's status */
+/* transmit BD's status and length*/
 #define T_R	0x80000000	/* ready bit */
 #define T_W	0x20000000	/* wrap bit */
 #define T_I	0x10000000	/* interrupt on completion */
 #define T_L	0x08000000	/* last */
 
+/* Receive BD's status */
+#define R_E_S	0x8000	/* buffer empty */
+#define R_W_S	0x2000	/* wrap bit */
+#define R_I_S	0x1000	/* interrupt on reception */
+#define R_L_S	0x0800	/* last */
+#define R_F_S	0x0400	/* first */
+#define R_CM_S	0x0200	/* continuous mode */
+#define R_CR_S	0x0004	/* crc */
+#define R_OV_S	0x0002	/* crc */
+
+/* transmit BD's status */
+#define T_R_S	0x8000	/* ready bit */
+#define T_W_S	0x2000	/* wrap bit */
+#define T_I_S	0x1000	/* interrupt on completion */
+#define T_L_S	0x0800	/* last */
+#define T_TC_S	0x0400	/* crc */
+#define T_TM_S	0x0200	/* continuous mode */
+
 /* Rx Data buffer must be 4 bytes aligned in most cases */
 #define UCC_FAST_RX_ALIGN			4
 #define UCC_FAST_MRBLR_ALIGNMENT		4
@@ -118,9 +136,12 @@ enum ucc_fast_transparent_tcrc {
 /* Fast UCC initialization structure */
 struct ucc_fast_info {
 	int ucc_num;
+	int tdm_num;
 	enum qe_clock rx_clock;
 	enum qe_clock tx_clock;
-	u32 regs;
+	enum qe_clock rx_sync;
+	enum qe_clock tx_sync;
+	resource_size_t regs;
 	int irq;
 	u32 uccm_mask;
 	int bd_mem_part;
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
new file mode 100644
index 000000000000..0fbf6fd4711b
--- /dev/null
+++ b/include/uapi/linux/batman_adv.h
@@ -0,0 +1,114 @@
+/* Copyright (C) 2016 B.A.T.M.A.N. contributors:
+ *
+ * Matthias Schiffer
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef _UAPI_LINUX_BATMAN_ADV_H_
+#define _UAPI_LINUX_BATMAN_ADV_H_
+
+#define BATADV_NL_NAME "batadv"
+
+#define BATADV_NL_MCAST_GROUP_TPMETER	"tpmeter"
+
+/**
+ * enum batadv_nl_attrs - batman-adv netlink attributes
+ *
+ * @BATADV_ATTR_UNSPEC: unspecified attribute to catch errors
+ * @BATADV_ATTR_VERSION: batman-adv version string
+ * @BATADV_ATTR_ALGO_NAME: name of routing algorithm
+ * @BATADV_ATTR_MESH_IFINDEX: index of the batman-adv interface
+ * @BATADV_ATTR_MESH_IFNAME: name of the batman-adv interface
+ * @BATADV_ATTR_MESH_ADDRESS: mac address of the batman-adv interface
+ * @BATADV_ATTR_HARD_IFINDEX: index of the non-batman-adv interface
+ * @BATADV_ATTR_HARD_IFNAME: name of the non-batman-adv interface
+ * @BATADV_ATTR_HARD_ADDRESS: mac address of the non-batman-adv interface
+ * @BATADV_ATTR_ORIG_ADDRESS: originator mac address
+ * @BATADV_ATTR_TPMETER_RESULT: result of run (see batadv_tp_meter_status)
+ * @BATADV_ATTR_TPMETER_TEST_TIME: time (msec) the run took
+ * @BATADV_ATTR_TPMETER_BYTES: amount of acked bytes during run
+ * @BATADV_ATTR_TPMETER_COOKIE: session cookie to match tp_meter session
+ * @BATADV_ATTR_PAD: attribute used for padding for 64-bit alignment
+ * @__BATADV_ATTR_AFTER_LAST: internal use
+ * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available
+ * @BATADV_ATTR_MAX: highest attribute number currently defined
+ */
+enum batadv_nl_attrs {
+	BATADV_ATTR_UNSPEC,
+	BATADV_ATTR_VERSION,
+	BATADV_ATTR_ALGO_NAME,
+	BATADV_ATTR_MESH_IFINDEX,
+	BATADV_ATTR_MESH_IFNAME,
+	BATADV_ATTR_MESH_ADDRESS,
+	BATADV_ATTR_HARD_IFINDEX,
+	BATADV_ATTR_HARD_IFNAME,
+	BATADV_ATTR_HARD_ADDRESS,
+	BATADV_ATTR_ORIG_ADDRESS,
+	BATADV_ATTR_TPMETER_RESULT,
+	BATADV_ATTR_TPMETER_TEST_TIME,
+	BATADV_ATTR_TPMETER_BYTES,
+	BATADV_ATTR_TPMETER_COOKIE,
+	BATADV_ATTR_PAD,
+	/* add attributes above here, update the policy in netlink.c */
+	__BATADV_ATTR_AFTER_LAST,
+	NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST,
+	BATADV_ATTR_MAX = __BATADV_ATTR_AFTER_LAST - 1
+};
+
+/**
+ * enum batadv_nl_commands - supported batman-adv netlink commands
+ *
+ * @BATADV_CMD_UNSPEC: unspecified command to catch errors
+ * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv device
+ * @BATADV_CMD_TP_METER: Start a tp meter session
+ * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session
+ * @__BATADV_CMD_AFTER_LAST: internal use
+ * @BATADV_CMD_MAX: highest used command number
+ */
+enum batadv_nl_commands {
+	BATADV_CMD_UNSPEC,
+	BATADV_CMD_GET_MESH_INFO,
+	BATADV_CMD_TP_METER,
+	BATADV_CMD_TP_METER_CANCEL,
+	/* add new commands above here */
+	__BATADV_CMD_AFTER_LAST,
+	BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1
+};
+
+/**
+ * enum batadv_tp_meter_reason - reason of a tp meter test run stop
+ * @BATADV_TP_REASON_COMPLETE: sender finished tp run
+ * @BATADV_TP_REASON_CANCEL: sender was stopped during run
+ * @BATADV_TP_REASON_DST_UNREACHABLE: receiver could not be reached or didn't
+ *  answer
+ * @BATADV_TP_REASON_RESEND_LIMIT: (unused) sender retry reached limit
+ * @BATADV_TP_REASON_ALREADY_ONGOING: test to or from the same node already
+ *  ongoing
+ * @BATADV_TP_REASON_MEMORY_ERROR: test was stopped due to low memory
+ * @BATADV_TP_REASON_CANT_SEND: failed to send via outgoing interface
+ * @BATADV_TP_REASON_TOO_MANY: too many ongoing sessions
+ */
+enum batadv_tp_meter_reason {
+	BATADV_TP_REASON_COMPLETE		= 3,
+	BATADV_TP_REASON_CANCEL			= 4,
+	/* error status >= 128 */
+	BATADV_TP_REASON_DST_UNREACHABLE	= 128,
+	BATADV_TP_REASON_RESEND_LIMIT		= 129,
+	BATADV_TP_REASON_ALREADY_ONGOING	= 130,
+	BATADV_TP_REASON_MEMORY_ERROR		= 131,
+	BATADV_TP_REASON_CANT_SEND		= 132,
+	BATADV_TP_REASON_TOO_MANY		= 133,
+};
+
+#endif /* _UAPI_LINUX_BATMAN_ADV_H_ */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 406459b935a2..c14ca1cd6297 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -84,6 +84,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_PERCPU_HASH,
 	BPF_MAP_TYPE_PERCPU_ARRAY,
 	BPF_MAP_TYPE_STACK_TRACE,
+	BPF_MAP_TYPE_CGROUP_ARRAY,
 };
 
 enum bpf_prog_type {
@@ -313,6 +314,49 @@ enum bpf_func_id {
 	 */
 	BPF_FUNC_skb_get_tunnel_opt,
 	BPF_FUNC_skb_set_tunnel_opt,
+
+	/**
+	 * bpf_skb_change_proto(skb, proto, flags)
+	 * Change protocol of the skb. Currently supported is
+	 * v4 -> v6, v6 -> v4 transitions. The helper will also
+	 * resize the skb. eBPF program is expected to fill the
+	 * new headers via skb_store_bytes and lX_csum_replace.
+	 * @skb: pointer to skb
+	 * @proto: new skb->protocol type
+	 * @flags: reserved
+	 * Return: 0 on success or negative error
+	 */
+	BPF_FUNC_skb_change_proto,
+
+	/**
+	 * bpf_skb_change_type(skb, type)
+	 * Change packet type of skb.
+	 * @skb: pointer to skb
+	 * @type: new skb->pkt_type type
+	 * Return: 0 on success or negative error
+	 */
+	BPF_FUNC_skb_change_type,
+
+	/**
+	 * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb
+	 * @skb: pointer to skb
+	 * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+	 * @index: index of the cgroup in the bpf_map
+	 * Return:
+	 *   == 0 skb failed the cgroup2 descendant test
+	 *   == 1 skb succeeded the cgroup2 descendant test
+	 *    < 0 error
+	 */
+	BPF_FUNC_skb_in_cgroup,
+
+	/**
+	 * bpf_get_hash_recalc(skb)
+	 * Retrieve and possibly recalculate skb->hash.
+	 * @skb: pointer to skb
+	 * Return: hash
+	 */
+	BPF_FUNC_get_hash_recalc,
+
 	__BPF_FUNC_MAX_ID,
 };
 
@@ -347,7 +391,7 @@ enum bpf_func_id {
 #define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
 #define BPF_F_DONT_FRAGMENT		(1ULL << 2)
 
-/* BPF_FUNC_perf_event_output flags. */
+/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
 #define BPF_F_INDEX_MASK		0xffffffffULL
 #define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
 
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 23c6960e94a4..2bdd1e3e7007 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -118,7 +118,7 @@ struct btrfs_ioctl_vol_args_v2 {
 	};
 	union {
 		char name[BTRFS_SUBVOL_NAME_MAX + 1];
-		u64 devid;
+		__u64 devid;
 	};
 };
 
diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h
index 7a291dc1ff15..cefb304414ba 100644
--- a/include/uapi/linux/can/bcm.h
+++ b/include/uapi/linux/can/bcm.h
@@ -99,5 +99,6 @@ enum {
 #define RX_ANNOUNCE_RESUME  0x0100
 #define TX_RESET_MULTI_IDX  0x0200
 #define RX_RTR_FRAME        0x0400
+#define CAN_FD_FRAME        0x0800
 
 #endif /* !_UAPI_CAN_BCM_H */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index ba0073b26fa6..915bfa74458c 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -57,6 +57,8 @@ enum devlink_command {
 	DEVLINK_CMD_SB_OCC_SNAPSHOT,
 	DEVLINK_CMD_SB_OCC_MAX_CLEAR,
 
+	DEVLINK_CMD_ESWITCH_MODE_GET,
+	DEVLINK_CMD_ESWITCH_MODE_SET,
 	/* add new commands above here */
 
 	__DEVLINK_CMD_MAX,
@@ -95,6 +97,11 @@ enum devlink_sb_threshold_type {
 
 #define DEVLINK_SB_THRESHOLD_TO_ALPHA_MAX 20
 
+enum devlink_eswitch_mode {
+	DEVLINK_ESWITCH_MODE_LEGACY,
+	DEVLINK_ESWITCH_MODE_SWITCHDEV,
+};
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,
@@ -125,6 +132,7 @@ enum devlink_attr {
 	DEVLINK_ATTR_SB_TC_INDEX,		/* u16 */
 	DEVLINK_ATTR_SB_OCC_CUR,		/* u32 */
 	DEVLINK_ATTR_SB_OCC_MAX,		/* u32 */
+	DEVLINK_ATTR_ESWITCH_MODE,		/* u16 */
 
 	/* add new attributes above here, update the policy in devlink.c */
 
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 5f030b46cff4..b8f38e84d93a 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1362,6 +1362,7 @@ enum ethtool_link_mode_bit_indices {
 	ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT	= 37,
 	ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT	= 38,
 	ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT	= 39,
+	ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT         = 40,
 
 	/* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit
 	 * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_*
@@ -1370,7 +1371,7 @@ enum ethtool_link_mode_bit_indices {
 	 */
 
 	__ETHTOOL_LINK_MODE_LAST
-	  = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
+	  = ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
 };
 
 #define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name)	\
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 620c8a5ddc00..14404b3ebb89 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -50,6 +50,7 @@ enum {
 	FRA_FWMASK,	/* mask for netfilter mark */
 	FRA_OIFNAME,
 	FRA_PAD,
+	FRA_L3MDEV,	/* iif or oif is l3mdev goto its table */
 	__FRA_MAX
 };
 
diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h
index ca1054dd8249..72a04a0e8cce 100644
--- a/include/uapi/linux/gtp.h
+++ b/include/uapi/linux/gtp.h
@@ -1,5 +1,5 @@
 #ifndef _UAPI_LINUX_GTP_H_
-#define _UAPI_LINUX_GTP_H__
+#define _UAPI_LINUX_GTP_H_
 
 enum gtp_genl_cmds {
 	GTP_CMD_NEWPDP,
diff --git a/include/uapi/linux/icmp.h b/include/uapi/linux/icmp.h
index 16fff055f734..fddd9d736284 100644
--- a/include/uapi/linux/icmp.h
+++ b/include/uapi/linux/icmp.h
@@ -79,6 +79,7 @@ struct icmphdr {
 		__be16	__unused;
 		__be16	mtu;
 	} frag;
+	__u8	reserved[4];
   } un;
 };
 
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 397d503fdedb..8304fe6f0561 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -247,8 +247,34 @@ enum {
 enum {
 	BRIDGE_XSTATS_UNSPEC,
 	BRIDGE_XSTATS_VLAN,
+	BRIDGE_XSTATS_MCAST,
+	BRIDGE_XSTATS_PAD,
 	__BRIDGE_XSTATS_MAX
 };
 #define BRIDGE_XSTATS_MAX (__BRIDGE_XSTATS_MAX - 1)
 
+enum {
+	BR_MCAST_DIR_RX,
+	BR_MCAST_DIR_TX,
+	BR_MCAST_DIR_SIZE
+};
+
+/* IGMP/MLD statistics */
+struct br_mcast_stats {
+	__u64 igmp_queries[BR_MCAST_DIR_SIZE];
+	__u64 igmp_leaves[BR_MCAST_DIR_SIZE];
+	__u64 igmp_v1reports[BR_MCAST_DIR_SIZE];
+	__u64 igmp_v2reports[BR_MCAST_DIR_SIZE];
+	__u64 igmp_v3reports[BR_MCAST_DIR_SIZE];
+	__u64 igmp_parse_errors;
+
+	__u64 mld_queries[BR_MCAST_DIR_SIZE];
+	__u64 mld_leaves[BR_MCAST_DIR_SIZE];
+	__u64 mld_v1reports[BR_MCAST_DIR_SIZE];
+	__u64 mld_v2reports[BR_MCAST_DIR_SIZE];
+	__u64 mld_parse_errors;
+
+	__u64 mcast_bytes[BR_MCAST_DIR_SIZE];
+	__u64 mcast_packets[BR_MCAST_DIR_SIZE];
+};
 #endif /* _UAPI_LINUX_IF_BRIDGE_H */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index bb36bd5675a7..4285ac31e865 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -273,6 +273,7 @@ enum {
 	IFLA_BR_VLAN_DEFAULT_PVID,
 	IFLA_BR_PAD,
 	IFLA_BR_VLAN_STATS_ENABLED,
+	IFLA_BR_MCAST_STATS_ENABLED,
 	__IFLA_BR_MAX,
 };
 
@@ -822,6 +823,7 @@ enum {
 	IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */
 	IFLA_STATS_LINK_64,
 	IFLA_STATS_LINK_XSTATS,
+	IFLA_STATS_LINK_XSTATS_SLAVE,
 	__IFLA_STATS_MAX,
 };
 
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index af4de90ba27d..1046f5515174 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -113,6 +113,7 @@ enum {
 	IFLA_GRE_ENCAP_SPORT,
 	IFLA_GRE_ENCAP_DPORT,
 	IFLA_GRE_COLLECT_METADATA,
+	IFLA_GRE_IGNORE_DF,
 	__IFLA_GRE_MAX,
 };
 
diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
index a16643705669..abbd1dc5d683 100644
--- a/include/uapi/linux/inet_diag.h
+++ b/include/uapi/linux/inet_diag.h
@@ -72,6 +72,7 @@ enum {
 	INET_DIAG_BC_AUTO,
 	INET_DIAG_BC_S_COND,
 	INET_DIAG_BC_D_COND,
+	INET_DIAG_BC_DEV_COND,   /* u32 ifindex */
 };
 
 struct inet_diag_hostcond {
diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index 87cf351bab03..737fa32faad4 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -611,6 +611,37 @@
 #define KEY_KBDINPUTASSIST_ACCEPT		0x264
 #define KEY_KBDINPUTASSIST_CANCEL		0x265
 
+/* Diagonal movement keys */
+#define KEY_RIGHT_UP			0x266
+#define KEY_RIGHT_DOWN			0x267
+#define KEY_LEFT_UP			0x268
+#define KEY_LEFT_DOWN			0x269
+
+#define KEY_ROOT_MENU			0x26a /* Show Device's Root Menu */
+/* Show Top Menu of the Media (e.g. DVD) */
+#define KEY_MEDIA_TOP_MENU		0x26b
+#define KEY_NUMERIC_11			0x26c
+#define KEY_NUMERIC_12			0x26d
+/*
+ * Toggle Audio Description: refers to an audio service that helps blind and
+ * visually impaired consumers understand the action in a program. Note: in
+ * some countries this is referred to as "Video Description".
+ */
+#define KEY_AUDIO_DESC			0x26e
+#define KEY_3D_MODE			0x26f
+#define KEY_NEXT_FAVORITE		0x270
+#define KEY_STOP_RECORD			0x271
+#define KEY_PAUSE_RECORD		0x272
+#define KEY_VOD				0x273 /* Video on Demand */
+#define KEY_UNMUTE			0x274
+#define KEY_FASTREVERSE			0x275
+#define KEY_SLOWREVERSE			0x276
+/*
+ * Control a data application associated with the currently viewed channel,
+ * e.g. teletext or data broadcast application (MHEG, MHP, HbbTV, etc.)
+ */
+#define KEY_DATA			0x275
+
 #define BTN_TRIGGER_HAPPY		0x2c0
 #define BTN_TRIGGER_HAPPY1		0x2c0
 #define BTN_TRIGGER_HAPPY2		0x2c1
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index 01113841190d..c51494119817 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -247,6 +247,7 @@ struct input_mask {
 #define BUS_ATARI		0x1B
 #define BUS_SPI			0x1C
 #define BUS_RMI			0x1D
+#define BUS_CEC			0x1E
 
 /*
  * MT_TOOL types
diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild
index 1d973d2ba417..cd26d7a0fd07 100644
--- a/include/uapi/linux/netfilter/Kbuild
+++ b/include/uapi/linux/netfilter/Kbuild
@@ -33,6 +33,7 @@ header-y += xt_NFLOG.h
 header-y += xt_NFQUEUE.h
 header-y += xt_RATEEST.h
 header-y += xt_SECMARK.h
+header-y += xt_SYNPROXY.h
 header-y += xt_TCPMSS.h
 header-y += xt_TCPOPTSTRIP.h
 header-y += xt_TEE.h
diff --git a/include/uapi/linux/netfilter/xt_SYNPROXY.h b/include/uapi/linux/netfilter/xt_SYNPROXY.h
index 2d59fbaa93c6..ca67e61d2a61 100644
--- a/include/uapi/linux/netfilter/xt_SYNPROXY.h
+++ b/include/uapi/linux/netfilter/xt_SYNPROXY.h
@@ -1,6 +1,8 @@
 #ifndef _XT_SYNPROXY_H
 #define _XT_SYNPROXY_H
 
+#include <linux/types.h>
+
 #define XT_SYNPROXY_OPT_MSS		0x01
 #define XT_SYNPROXY_OPT_WSCALE		0x02
 #define XT_SYNPROXY_OPT_SACK_PERM	0x04
diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
index d79399394b46..76b4d87c83a8 100644
--- a/include/uapi/linux/netlink_diag.h
+++ b/include/uapi/linux/netlink_diag.h
@@ -49,6 +49,7 @@ enum {
 #define NDIAG_SHOW_MEMINFO	0x00000001 /* show memory info of a socket */
 #define NDIAG_SHOW_GROUPS	0x00000002 /* show groups of a netlink socket */
 #ifndef __KERNEL__
+/* deprecated since 4.6 */
 #define NDIAG_SHOW_RING_CFG	0x00000004 /* show ring configuration */
 #endif
 
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index e23d78685a01..53c8278827a0 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -493,7 +493,12 @@
  *	This attribute is ignored if driver does not support roam scan.
  *	It is also sent as an event, with the BSSID and response IEs when the
  *	connection is established or failed to be established. This can be
- *	determined by the STATUS_CODE attribute.
+ *	determined by the %NL80211_ATTR_STATUS_CODE attribute (0 = success,
+ *	non-zero = failure). If %NL80211_ATTR_TIMED_OUT is included in the
+ *	event, the connection attempt failed due to not being able to initiate
+ *	authentication/association or not receiving a response from the AP.
+ *	Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as
+ *	well to remain backwards compatible.
  * @NL80211_CMD_ROAM: request that the card roam (currently not implemented),
  *	sent as an event when the card/driver roamed by itself.
  * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify
@@ -1819,6 +1824,11 @@ enum nl80211_commands {
  *
  * @NL80211_ATTR_PAD: attribute used for padding for 64-bit alignment
  *
+ * @NL80211_ATTR_IFTYPE_EXT_CAPA: Nested attribute of the following attributes:
+ *	%NL80211_ATTR_IFTYPE, %NL80211_ATTR_EXT_CAPA,
+ *	%NL80211_ATTR_EXT_CAPA_MASK, to specify the extended capabilities per
+ *	interface type.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2201,6 +2211,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_PAD,
 
+	NL80211_ATTR_IFTYPE_EXT_CAPA,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index bb0d515b7654..d95a3018f6a1 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -166,6 +166,7 @@ enum ovs_packet_cmd {
  * output port is actually a tunnel port. Contains the output tunnel key
  * extracted from the packet as nested %OVS_TUNNEL_KEY_ATTR_* attributes.
  * @OVS_PACKET_ATTR_MRU: Present for an %OVS_PACKET_CMD_ACTION and
+ * @OVS_PACKET_ATTR_LEN: Packet size before truncation.
  * %OVS_PACKET_ATTR_USERSPACE action specify the Maximum received fragment
  * size.
  *
@@ -185,6 +186,7 @@ enum ovs_packet_attr {
 	OVS_PACKET_ATTR_PROBE,      /* Packet operation is a feature probe,
 				       error logging should be suppressed. */
 	OVS_PACKET_ATTR_MRU,	    /* Maximum received IP fragment size. */
+	OVS_PACKET_ATTR_LEN,		/* Packet size before truncation. */
 	__OVS_PACKET_ATTR_MAX
 };
 
@@ -580,6 +582,10 @@ enum ovs_userspace_attr {
 
 #define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1)
 
+struct ovs_action_trunc {
+	uint32_t max_len; /* Max packet size in bytes. */
+};
+
 /**
  * struct ovs_action_push_mpls - %OVS_ACTION_ATTR_PUSH_MPLS action argument.
  * @mpls_lse: MPLS label stack entry to push.
@@ -703,6 +709,7 @@ enum ovs_nat_attr {
  * enum ovs_action_attr - Action types.
  *
  * @OVS_ACTION_ATTR_OUTPUT: Output packet to port.
+ * @OVS_ACTION_ATTR_TRUNC: Output packet to port with truncated packet size.
  * @OVS_ACTION_ATTR_USERSPACE: Send packet to userspace according to nested
  * %OVS_USERSPACE_ATTR_* attributes.
  * @OVS_ACTION_ATTR_SET: Replaces the contents of an existing header.  The
@@ -756,6 +763,7 @@ enum ovs_action_attr {
 				       * The data must be zero for the unmasked
 				       * bits. */
 	OVS_ACTION_ATTR_CT,           /* Nested OVS_CT_ATTR_* . */
+	OVS_ACTION_ATTR_TRUNC,        /* u32 struct ovs_action_trunc. */
 
 	__OVS_ACTION_ATTR_MAX,	      /* Nothing past this will be accepted
 				       * from userspace. */
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index f4297c8a42fe..5702e933dc07 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -115,8 +115,8 @@ struct tc_police {
 	__u32			mtu;
 	struct tc_ratespec	rate;
 	struct tc_ratespec	peakrate;
-	int 			refcnt;
-	int 			bindcnt;
+	int			refcnt;
+	int			bindcnt;
 	__u32			capab;
 };
 
@@ -124,10 +124,11 @@ struct tcf_t {
 	__u64   install;
 	__u64   lastuse;
 	__u64   expires;
+	__u64   firstuse;
 };
 
 struct tc_cnt {
-	int                   refcnt; 
+	int                   refcnt;
 	int                   bindcnt;
 };
 
diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h
index fecb5cc48c40..a4d00c608d8f 100644
--- a/include/uapi/linux/tc_act/tc_skbedit.h
+++ b/include/uapi/linux/tc_act/tc_skbedit.h
@@ -27,6 +27,7 @@
 #define SKBEDIT_F_PRIORITY		0x1
 #define SKBEDIT_F_QUEUE_MAPPING		0x2
 #define SKBEDIT_F_MARK			0x4
+#define SKBEDIT_F_PTYPE			0x8
 
 struct tc_skbedit {
 	tc_gen;
@@ -40,6 +41,7 @@ enum {
 	TCA_SKBEDIT_QUEUE_MAPPING,
 	TCA_SKBEDIT_MARK,
 	TCA_SKBEDIT_PAD,
+	TCA_SKBEDIT_PTYPE,
 	__TCA_SKBEDIT_MAX
 };
 #define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1)
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 53e8e3fe6b1b..482898fc433a 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -115,12 +115,22 @@ enum {
 #define TCP_CC_INFO		26	/* Get Congestion Control (optional) info */
 #define TCP_SAVE_SYN		27	/* Record SYN headers for new connections */
 #define TCP_SAVED_SYN		28	/* Get SYN headers recorded for connection */
+#define TCP_REPAIR_WINDOW	29	/* Get/set window parameters */
 
 struct tcp_repair_opt {
 	__u32	opt_code;
 	__u32	opt_val;
 };
 
+struct tcp_repair_window {
+	__u32	snd_wl1;
+	__u32	snd_wnd;
+	__u32	max_window;
+
+	__u32	rcv_wnd;
+	__u32	rcv_wup;
+};
+
 enum {
 	TCP_NO_QUEUE,
 	TCP_RECV_QUEUE,
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index ec32293a00db..fc353b518288 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -1,5 +1,5 @@
-#ifndef _LINUX_VIRTIO_NET_H
-#define _LINUX_VIRTIO_NET_H
+#ifndef _UAPI_LINUX_VIRTIO_NET_H
+#define _UAPI_LINUX_VIRTIO_NET_H
 /* This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
  *
@@ -35,6 +35,7 @@
 #define VIRTIO_NET_F_CSUM	0	/* Host handles pkts w/ partial csum */
 #define VIRTIO_NET_F_GUEST_CSUM	1	/* Guest handles pkts w/ partial csum */
 #define VIRTIO_NET_F_CTRL_GUEST_OFFLOADS 2 /* Dynamic offload configuration. */
+#define VIRTIO_NET_F_MTU	3	/* Initial MTU advice */
 #define VIRTIO_NET_F_MAC	5	/* Host has given MAC address. */
 #define VIRTIO_NET_F_GUEST_TSO4	7	/* Guest can handle TSOv4 in. */
 #define VIRTIO_NET_F_GUEST_TSO6	8	/* Guest can handle TSOv6 in. */
@@ -73,6 +74,8 @@ struct virtio_net_config {
 	 * Legal values are between 1 and 0x8000
 	 */
 	__u16 max_virtqueue_pairs;
+	/* Default maximum transmit unit advice */
+	__u16 mtu;
 } __attribute__((packed));
 
 /*
@@ -242,4 +245,4 @@ struct virtio_net_ctrl_mq {
 #define VIRTIO_NET_CTRL_GUEST_OFFLOADS   5
 #define VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET        0
 
-#endif /* _LINUX_VIRTIO_NET_H */
+#endif /* _UAPI_LINUX_VIRTIO_NET_H */
diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h
index c1592e3e4036..d9ecd7c6d691 100644
--- a/include/uapi/linux/wireless.h
+++ b/include/uapi/linux/wireless.h
@@ -670,8 +670,7 @@
 /*
  *	Generic format for most parameters that fit in an int
  */
-struct	iw_param
-{
+struct iw_param {
   __s32		value;		/* The value of the parameter itself */
   __u8		fixed;		/* Hardware should not use auto select */
   __u8		disabled;	/* Disable the feature */
@@ -682,8 +681,7 @@ struct	iw_param
  *	For all data larger than 16 octets, we need to use a
  *	pointer to memory allocated in user space.
  */
-struct	iw_point
-{
+struct iw_point {
   void __user	*pointer;	/* Pointer to the data  (in user space) */
   __u16		length;		/* number of fields or size in bytes */
   __u16		flags;		/* Optional params */
@@ -698,8 +696,7 @@ struct	iw_point
  *	of 10 to get 'm' lower than 10^9, with 'm'= f / (10^'e')...
  *	The power of 10 is in 'e', the result of the division is in 'm'.
  */
-struct	iw_freq
-{
+struct iw_freq {
 	__s32		m;		/* Mantissa */
 	__s16		e;		/* Exponent */
 	__u8		i;		/* List index (when in range struct) */
@@ -709,8 +706,7 @@ struct	iw_freq
 /*
  *	Quality of the link
  */
-struct	iw_quality
-{
+struct iw_quality {
 	__u8		qual;		/* link quality (%retries, SNR,
 					   %missed beacons or better...) */
 	__u8		level;		/* signal level (dBm) */
@@ -725,8 +721,7 @@ struct	iw_quality
  *	is already pretty exhaustive, and you should use that first.
  *	This is only additional stats...
  */
-struct	iw_discarded
-{
+struct iw_discarded {
 	__u32		nwid;		/* Rx : Wrong nwid/essid */
 	__u32		code;		/* Rx : Unable to code/decode (WEP) */
 	__u32		fragment;	/* Rx : Can't perform MAC reassembly */
@@ -738,16 +733,14 @@ struct	iw_discarded
  *	Packet/Time period missed in the wireless adapter due to
  *	"wireless" specific problems...
  */
-struct	iw_missed
-{
+struct iw_missed {
 	__u32		beacon;		/* Missed beacons/superframe */
 };
 
 /*
  *	Quality range (for spy threshold)
  */
-struct	iw_thrspy
-{
+struct iw_thrspy {
 	struct sockaddr		addr;		/* Source address (hw/mac) */
 	struct iw_quality	qual;		/* Quality of the link */
 	struct iw_quality	low;		/* Low threshold */
@@ -765,8 +758,7 @@ struct	iw_thrspy
  *	Especially, scan results are required to include an entry for the
  *	current BSS if the driver is in Managed mode and associated with an AP.
  */
-struct	iw_scan_req
-{
+struct iw_scan_req {
 	__u8		scan_type; /* IW_SCAN_TYPE_{ACTIVE,PASSIVE} */
 	__u8		essid_len;
 	__u8		num_channels; /* num entries in channel_list;
@@ -827,8 +819,7 @@ struct	iw_scan_req
  *	RX_SEQ_VALID for SIOCGIWENCODEEXT are optional, but can be useful for
  *	debugging/testing.
  */
-struct	iw_encode_ext
-{
+struct iw_encode_ext {
 	__u32		ext_flags; /* IW_ENCODE_EXT_* */
 	__u8		tx_seq[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */
 	__u8		rx_seq[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */
@@ -841,8 +832,7 @@ struct	iw_encode_ext
 };
 
 /* SIOCSIWMLME data */
-struct	iw_mlme
-{
+struct iw_mlme {
 	__u16		cmd; /* IW_MLME_* */
 	__u16		reason_code;
 	struct sockaddr	addr;
@@ -855,16 +845,14 @@ struct	iw_mlme
 
 #define IW_PMKID_LEN	16
 
-struct	iw_pmksa
-{
+struct iw_pmksa {
 	__u32		cmd; /* IW_PMKSA_* */
 	struct sockaddr	bssid;
 	__u8		pmkid[IW_PMKID_LEN];
 };
 
 /* IWEVMICHAELMICFAILURE data */
-struct	iw_michaelmicfailure
-{
+struct iw_michaelmicfailure {
 	__u32		flags;
 	struct sockaddr	src_addr;
 	__u8		tsc[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */
@@ -872,8 +860,7 @@ struct	iw_michaelmicfailure
 
 /* IWEVPMKIDCAND data */
 #define IW_PMKID_CAND_PREAUTH	0x00000001 /* RNS pre-authentication enabled */
-struct	iw_pmkid_cand
-{
+struct iw_pmkid_cand {
 	__u32		flags; /* IW_PMKID_CAND_* */
 	__u32		index; /* the smaller the index, the higher the
 				* priority */
@@ -884,8 +871,7 @@ struct	iw_pmkid_cand
 /*
  * Wireless statistics (used for /proc/net/wireless)
  */
-struct	iw_statistics
-{
+struct iw_statistics {
 	__u16		status;		/* Status
 					 * - device dependent for now */
 
@@ -897,7 +883,7 @@ struct	iw_statistics
 
 /* ------------------------ IOCTL REQUEST ------------------------ */
 /*
- * This structure defines the payload of an ioctl, and is used 
+ * This structure defines the payload of an ioctl, and is used
  * below.
  *
  * Note that this structure should fit on the memory footprint
@@ -906,8 +892,7 @@ struct	iw_statistics
  * You should check this when increasing the structures defined
  * above in this file...
  */
-union	iwreq_data
-{
+union iwreq_data {
 	/* Config - generic */
 	char		name[IFNAMSIZ];
 	/* Name : used to verify the presence of  wireless extensions.
@@ -944,15 +929,14 @@ union	iwreq_data
  * convenience...
  * Do I need to remind you about structure size (32 octets) ?
  */
-struct	iwreq 
-{
+struct iwreq {
 	union
 	{
 		char	ifrn_name[IFNAMSIZ];	/* if name, e.g. "eth0" */
 	} ifr_ifrn;
 
 	/* Data part (defined just above) */
-	union	iwreq_data	u;
+	union iwreq_data	u;
 };
 
 /* -------------------------- IOCTL DATA -------------------------- */
@@ -965,8 +949,7 @@ struct	iwreq
  *	Range of parameters
  */
 
-struct	iw_range
-{
+struct iw_range {
 	/* Informative stuff (to choose between different interface) */
 	__u32		throughput;	/* To give an idea... */
 	/* In theory this value should be the maximum benchmarked
@@ -1069,9 +1052,8 @@ struct	iw_range
 /*
  * Private ioctl interface information
  */
- 
-struct	iw_priv_args
-{
+
+struct iw_priv_args {
 	__u32		cmd;		/* Number of the ioctl to issue */
 	__u16		set_args;	/* Type and number of args */
 	__u16		get_args;	/* Type and number of args */
@@ -1088,8 +1070,7 @@ struct	iw_priv_args
 /*
  * A Wireless Event. Contains basically the same data as the ioctl...
  */
-struct iw_event
-{
+struct iw_event {
 	__u16		len;			/* Real length of this stuff */
 	__u16		cmd;			/* Wireless IOCTL */
 	union iwreq_data	u;		/* IOCTL fixed payload */
diff --git a/include/uapi/sound/Kbuild b/include/uapi/sound/Kbuild
index a7f27704f980..691984cb0b91 100644
--- a/include/uapi/sound/Kbuild
+++ b/include/uapi/sound/Kbuild
@@ -1,5 +1,6 @@
 # UAPI Header export list
 header-y += asequencer.h
+header-y += asoc.h
 header-y += asound.h
 header-y += asound_fm.h
 header-y += compress_offload.h
@@ -10,3 +11,5 @@ header-y += hdsp.h
 header-y += hdspm.h
 header-y += sb16_csp.h
 header-y += sfnt_info.h
+header-y += tlv.h
+header-y += usb_stream.h
diff --git a/init/main.c b/init/main.c
index 4c17fda5c2ff..eae02aa03c9e 100644
--- a/init/main.c
+++ b/init/main.c
@@ -453,7 +453,7 @@ void __init __weak smp_setup_processor_id(void)
 }
 
 # if THREAD_SIZE >= PAGE_SIZE
-void __init __weak thread_info_cache_init(void)
+void __init __weak thread_stack_cache_init(void)
 {
 }
 #endif
@@ -627,7 +627,7 @@ asmlinkage __visible void __init start_kernel(void)
 	/* Should be run before the first non-init thread is created */
 	init_espfix_bsp();
 #endif
-	thread_info_cache_init();
+	thread_stack_cache_init();
 	cred_init();
 	fork_init();
 	proc_caches_init();
@@ -708,11 +708,13 @@ static bool __init_or_module initcall_blacklisted(initcall_t fn)
 {
 	struct blacklist_entry *entry;
 	char fn_name[KSYM_SYMBOL_LEN];
+	unsigned long addr;
 
 	if (list_empty(&blacklisted_initcalls))
 		return false;
 
-	sprint_symbol_no_offset(fn_name, (unsigned long)fn);
+	addr = (unsigned long) dereference_function_descriptor(fn);
+	sprint_symbol_no_offset(fn_name, addr);
 
 	list_for_each_entry(entry, &blacklisted_initcalls, next) {
 		if (!strcmp(fn_name, entry->buf)) {
diff --git a/kernel/audit.c b/kernel/audit.c
index 22bb4f24f071..8d528f9930da 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1883,6 +1883,23 @@ out_null:
 	audit_log_format(ab, " exe=(null)");
 }
 
+struct tty_struct *audit_get_tty(struct task_struct *tsk)
+{
+	struct tty_struct *tty = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tsk->sighand->siglock, flags);
+	if (tsk->signal)
+		tty = tty_kref_get(tsk->signal->tty);
+	spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
+	return tty;
+}
+
+void audit_put_tty(struct tty_struct *tty)
+{
+	tty_kref_put(tty);
+}
+
 void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
 {
 	const struct cred *cred;
diff --git a/kernel/audit.h b/kernel/audit.h
index cbbe6bb6496e..a492f4c4e710 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -23,6 +23,7 @@
 #include <linux/audit.h>
 #include <linux/skbuff.h>
 #include <uapi/linux/mqueue.h>
+#include <linux/tty.h>
 
 /* AUDIT_NAMES is the number of slots we reserve in the audit_context
  * for saving names from getname().  If we get more names we will allocate
@@ -262,6 +263,9 @@ extern struct audit_entry *audit_dupe_rule(struct audit_krule *old);
 extern void audit_log_d_path_exe(struct audit_buffer *ab,
 				 struct mm_struct *mm);
 
+extern struct tty_struct *audit_get_tty(struct task_struct *tsk);
+extern void audit_put_tty(struct tty_struct *tty);
+
 /* audit watch functions */
 #ifdef CONFIG_AUDIT_WATCH
 extern void audit_put_watch(struct audit_watch *watch);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 62ab53d7619c..2672d105cffc 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -63,7 +63,6 @@
 #include <asm/unistd.h>
 #include <linux/security.h>
 #include <linux/list.h>
-#include <linux/tty.h>
 #include <linux/binfmts.h>
 #include <linux/highmem.h>
 #include <linux/syscalls.h>
@@ -1985,14 +1984,15 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
 	if (!audit_enabled)
 		return;
 
+	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
+	if (!ab)
+		return;
+
 	uid = from_kuid(&init_user_ns, task_uid(current));
 	oldloginuid = from_kuid(&init_user_ns, koldloginuid);
 	loginuid = from_kuid(&init_user_ns, kloginuid),
 	tty = audit_get_tty(current);
 
-	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
-	if (!ab)
-		return;
 	audit_log_format(ab, "pid=%d uid=%u", task_pid_nr(current), uid);
 	audit_log_task_context(ab);
 	audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d",
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 76d5a794e426..db1a743e3db2 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -328,8 +328,8 @@ static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
 }
 
 /* only called from syscall */
-static int fd_array_map_update_elem(struct bpf_map *map, void *key,
-				    void *value, u64 map_flags)
+int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
+				 void *key, void *value, u64 map_flags)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	void *new_ptr, *old_ptr;
@@ -342,7 +342,7 @@ static int fd_array_map_update_elem(struct bpf_map *map, void *key,
 		return -E2BIG;
 
 	ufd = *(u32 *)value;
-	new_ptr = map->ops->map_fd_get_ptr(map, ufd);
+	new_ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
 	if (IS_ERR(new_ptr))
 		return PTR_ERR(new_ptr);
 
@@ -371,10 +371,12 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
 	}
 }
 
-static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
+static void *prog_fd_array_get_ptr(struct bpf_map *map,
+				   struct file *map_file, int fd)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	struct bpf_prog *prog = bpf_prog_get(fd);
+
 	if (IS_ERR(prog))
 		return prog;
 
@@ -382,14 +384,13 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
 		bpf_prog_put(prog);
 		return ERR_PTR(-EINVAL);
 	}
+
 	return prog;
 }
 
 static void prog_fd_array_put_ptr(void *ptr)
 {
-	struct bpf_prog *prog = ptr;
-
-	bpf_prog_put_rcu(prog);
+	bpf_prog_put(ptr);
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
@@ -407,7 +408,6 @@ static const struct bpf_map_ops prog_array_ops = {
 	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = fd_array_map_lookup_elem,
-	.map_update_elem = fd_array_map_update_elem,
 	.map_delete_elem = fd_array_map_delete_elem,
 	.map_fd_get_ptr = prog_fd_array_get_ptr,
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
@@ -425,59 +425,105 @@ static int __init register_prog_array_map(void)
 }
 late_initcall(register_prog_array_map);
 
-static void perf_event_array_map_free(struct bpf_map *map)
+static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
+						   struct file *map_file)
 {
-	bpf_fd_array_map_clear(map);
-	fd_array_map_free(map);
+	struct bpf_event_entry *ee;
+
+	ee = kzalloc(sizeof(*ee), GFP_KERNEL);
+	if (ee) {
+		ee->event = perf_file->private_data;
+		ee->perf_file = perf_file;
+		ee->map_file = map_file;
+	}
+
+	return ee;
 }
 
-static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
+static void __bpf_event_entry_free(struct rcu_head *rcu)
 {
-	struct perf_event *event;
-	const struct perf_event_attr *attr;
-	struct file *file;
+	struct bpf_event_entry *ee;
 
-	file = perf_event_get(fd);
-	if (IS_ERR(file))
-		return file;
+	ee = container_of(rcu, struct bpf_event_entry, rcu);
+	fput(ee->perf_file);
+	kfree(ee);
+}
 
-	event = file->private_data;
+static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee)
+{
+	call_rcu(&ee->rcu, __bpf_event_entry_free);
+}
 
-	attr = perf_event_attrs(event);
-	if (IS_ERR(attr))
-		goto err;
+static void *perf_event_fd_array_get_ptr(struct bpf_map *map,
+					 struct file *map_file, int fd)
+{
+	const struct perf_event_attr *attr;
+	struct bpf_event_entry *ee;
+	struct perf_event *event;
+	struct file *perf_file;
 
-	if (attr->inherit)
-		goto err;
+	perf_file = perf_event_get(fd);
+	if (IS_ERR(perf_file))
+		return perf_file;
 
-	if (attr->type == PERF_TYPE_RAW)
-		return file;
+	event = perf_file->private_data;
+	ee = ERR_PTR(-EINVAL);
 
-	if (attr->type == PERF_TYPE_HARDWARE)
-		return file;
+	attr = perf_event_attrs(event);
+	if (IS_ERR(attr) || attr->inherit)
+		goto err_out;
+
+	switch (attr->type) {
+	case PERF_TYPE_SOFTWARE:
+		if (attr->config != PERF_COUNT_SW_BPF_OUTPUT)
+			goto err_out;
+		/* fall-through */
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+		ee = bpf_event_entry_gen(perf_file, map_file);
+		if (ee)
+			return ee;
+		ee = ERR_PTR(-ENOMEM);
+		/* fall-through */
+	default:
+		break;
+	}
 
-	if (attr->type == PERF_TYPE_SOFTWARE &&
-	    attr->config == PERF_COUNT_SW_BPF_OUTPUT)
-		return file;
-err:
-	fput(file);
-	return ERR_PTR(-EINVAL);
+err_out:
+	fput(perf_file);
+	return ee;
 }
 
 static void perf_event_fd_array_put_ptr(void *ptr)
 {
-	fput((struct file *)ptr);
+	bpf_event_entry_free_rcu(ptr);
+}
+
+static void perf_event_fd_array_release(struct bpf_map *map,
+					struct file *map_file)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_event_entry *ee;
+	int i;
+
+	rcu_read_lock();
+	for (i = 0; i < array->map.max_entries; i++) {
+		ee = READ_ONCE(array->ptrs[i]);
+		if (ee && ee->map_file == map_file)
+			fd_array_map_delete_elem(map, &i);
+	}
+	rcu_read_unlock();
 }
 
 static const struct bpf_map_ops perf_event_array_ops = {
 	.map_alloc = fd_array_map_alloc,
-	.map_free = perf_event_array_map_free,
+	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = fd_array_map_lookup_elem,
-	.map_update_elem = fd_array_map_update_elem,
 	.map_delete_elem = fd_array_map_delete_elem,
 	.map_fd_get_ptr = perf_event_fd_array_get_ptr,
 	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
+	.map_release = perf_event_fd_array_release,
 };
 
 static struct bpf_map_type_list perf_event_array_type __read_mostly = {
@@ -491,3 +537,46 @@ static int __init register_perf_event_array_map(void)
 	return 0;
 }
 late_initcall(register_perf_event_array_map);
+
+#ifdef CONFIG_SOCK_CGROUP_DATA
+static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
+				     struct file *map_file /* not used */,
+				     int fd)
+{
+	return cgroup_get_from_fd(fd);
+}
+
+static void cgroup_fd_array_put_ptr(void *ptr)
+{
+	/* cgroup_put free cgrp after a rcu grace period */
+	cgroup_put(ptr);
+}
+
+static void cgroup_fd_array_free(struct bpf_map *map)
+{
+	bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
+}
+
+static const struct bpf_map_ops cgroup_array_ops = {
+	.map_alloc = fd_array_map_alloc,
+	.map_free = cgroup_fd_array_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
+	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
+};
+
+static struct bpf_map_type_list cgroup_array_type __read_mostly = {
+	.ops = &cgroup_array_ops,
+	.type = BPF_MAP_TYPE_CGROUP_ARRAY,
+};
+
+static int __init register_cgroup_array_map(void)
+{
+	bpf_register_map_type(&cgroup_array_type);
+	return 0;
+}
+late_initcall(register_cgroup_array_map);
+#endif
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index b94a36550591..d638062f66d6 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -719,14 +719,13 @@ select_insn:
 
 		if (unlikely(index >= array->map.max_entries))
 			goto out;
-
 		if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT))
 			goto out;
 
 		tail_call_cnt++;
 
 		prog = READ_ONCE(array->ptrs[index]);
-		if (unlikely(!prog))
+		if (!prog)
 			goto out;
 
 		/* ARG1 at this point is guaranteed to point to CTX from
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index ad7a0573f71b..1ea3afba1a4f 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -101,7 +101,7 @@ const struct bpf_func_proto bpf_get_prandom_u32_proto = {
 
 static u64 bpf_get_smp_processor_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 {
-	return raw_smp_processor_id();
+	return smp_processor_id();
 }
 
 const struct bpf_func_proto bpf_get_smp_processor_id_proto = {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 46ecce4b79ed..96d938a22050 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -124,7 +124,12 @@ void bpf_map_put_with_uref(struct bpf_map *map)
 
 static int bpf_map_release(struct inode *inode, struct file *filp)
 {
-	bpf_map_put_with_uref(filp->private_data);
+	struct bpf_map *map = filp->private_data;
+
+	if (map->ops->map_release)
+		map->ops->map_release(map, filp);
+
+	bpf_map_put_with_uref(map);
 	return 0;
 }
 
@@ -387,6 +392,13 @@ static int map_update_elem(union bpf_attr *attr)
 		err = bpf_percpu_hash_update(map, key, value, attr->flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_update(map, key, value, attr->flags);
+	} else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY ||
+		   map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
+		   map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY) {
+		rcu_read_lock();
+		err = bpf_fd_array_map_update_elem(map, f.file, key, value,
+						   attr->flags);
+		rcu_read_unlock();
 	} else {
 		rcu_read_lock();
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
@@ -612,7 +624,7 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
 	free_uid(user);
 }
 
-static void __prog_put_common(struct rcu_head *rcu)
+static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 {
 	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
 
@@ -621,17 +633,10 @@ static void __prog_put_common(struct rcu_head *rcu)
 	bpf_prog_free(aux->prog);
 }
 
-/* version of bpf_prog_put() that is called after a grace period */
-void bpf_prog_put_rcu(struct bpf_prog *prog)
-{
-	if (atomic_dec_and_test(&prog->aux->refcnt))
-		call_rcu(&prog->aux->rcu, __prog_put_common);
-}
-
 void bpf_prog_put(struct bpf_prog *prog)
 {
 	if (atomic_dec_and_test(&prog->aux->refcnt))
-		__prog_put_common(&prog->aux->rcu);
+		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_put);
 
@@ -639,7 +644,7 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
 {
 	struct bpf_prog *prog = filp->private_data;
 
-	bpf_prog_put_rcu(prog);
+	bpf_prog_put(prog);
 	return 0;
 }
 
@@ -653,7 +658,7 @@ int bpf_prog_new_fd(struct bpf_prog *prog)
 				O_RDWR | O_CLOEXEC);
 }
 
-static struct bpf_prog *__bpf_prog_get(struct fd f)
+static struct bpf_prog *____bpf_prog_get(struct fd f)
 {
 	if (!f.file)
 		return ERR_PTR(-EBADF);
@@ -674,24 +679,35 @@ struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
 	return prog;
 }
 
-/* called by sockets/tracing/seccomp before attaching program to an event
- * pairs with bpf_prog_put()
- */
-struct bpf_prog *bpf_prog_get(u32 ufd)
+static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type)
 {
 	struct fd f = fdget(ufd);
 	struct bpf_prog *prog;
 
-	prog = __bpf_prog_get(f);
+	prog = ____bpf_prog_get(f);
 	if (IS_ERR(prog))
 		return prog;
+	if (type && prog->type != *type) {
+		prog = ERR_PTR(-EINVAL);
+		goto out;
+	}
 
 	prog = bpf_prog_inc(prog);
+out:
 	fdput(f);
-
 	return prog;
 }
-EXPORT_SYMBOL_GPL(bpf_prog_get);
+
+struct bpf_prog *bpf_prog_get(u32 ufd)
+{
+	return __bpf_prog_get(ufd, NULL);
+}
+
+struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
+{
+	return __bpf_prog_get(ufd, &type);
+}
+EXPORT_SYMBOL_GPL(bpf_prog_get_type);
 
 /* last field in 'union bpf_attr' used by this command */
 #define	BPF_PROG_LOAD_LAST_FIELD kern_version
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 668e07903c8f..e206c2181412 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -126,31 +126,6 @@
  * are set to NOT_INIT to indicate that they are no longer readable.
  */
 
-/* types of values stored in eBPF registers */
-enum bpf_reg_type {
-	NOT_INIT = 0,		 /* nothing was written into register */
-	UNKNOWN_VALUE,		 /* reg doesn't contain a valid pointer */
-	PTR_TO_CTX,		 /* reg points to bpf_context */
-	CONST_PTR_TO_MAP,	 /* reg points to struct bpf_map */
-	PTR_TO_MAP_VALUE,	 /* reg points to map element value */
-	PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
-	FRAME_PTR,		 /* reg == frame_pointer */
-	PTR_TO_STACK,		 /* reg == frame_pointer + imm */
-	CONST_IMM,		 /* constant integer value */
-
-	/* PTR_TO_PACKET represents:
-	 * skb->data
-	 * skb->data + imm
-	 * skb->data + (u16) var
-	 * skb->data + (u16) var + imm
-	 * if (range > 0) then [ptr, ptr + range - off) is safe to access
-	 * if (id > 0) means that some 'var' was added
-	 * if (off > 0) menas that 'imm' was added
-	 */
-	PTR_TO_PACKET,
-	PTR_TO_PACKET_END,	 /* skb->data + headlen */
-};
-
 struct reg_state {
 	enum bpf_reg_type type;
 	union {
@@ -695,10 +670,10 @@ static int check_packet_access(struct verifier_env *env, u32 regno, int off,
 
 /* check access to 'struct bpf_context' fields */
 static int check_ctx_access(struct verifier_env *env, int off, int size,
-			    enum bpf_access_type t)
+			    enum bpf_access_type t, enum bpf_reg_type *reg_type)
 {
 	if (env->prog->aux->ops->is_valid_access &&
-	    env->prog->aux->ops->is_valid_access(off, size, t)) {
+	    env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) {
 		/* remember the offset of last byte accessed in ctx */
 		if (env->prog->aux->max_ctx_offset < off + size)
 			env->prog->aux->max_ctx_offset = off + size;
@@ -798,21 +773,19 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
 			mark_reg_unknown_value(state->regs, value_regno);
 
 	} else if (reg->type == PTR_TO_CTX) {
+		enum bpf_reg_type reg_type = UNKNOWN_VALUE;
+
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
 			verbose("R%d leaks addr into ctx\n", value_regno);
 			return -EACCES;
 		}
-		err = check_ctx_access(env, off, size, t);
+		err = check_ctx_access(env, off, size, t, &reg_type);
 		if (!err && t == BPF_READ && value_regno >= 0) {
 			mark_reg_unknown_value(state->regs, value_regno);
-			if (off == offsetof(struct __sk_buff, data) &&
-			    env->allow_ptr_leaks)
+			if (env->allow_ptr_leaks)
 				/* note that reg.[id|off|range] == 0 */
-				state->regs[value_regno].type = PTR_TO_PACKET;
-			else if (off == offsetof(struct __sk_buff, data_end) &&
-				 env->allow_ptr_leaks)
-				state->regs[value_regno].type = PTR_TO_PACKET_END;
+				state->regs[value_regno].type = reg_type;
 		}
 
 	} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
@@ -1062,6 +1035,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		if (func_id != BPF_FUNC_get_stackid)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_CGROUP_ARRAY:
+		if (func_id != BPF_FUNC_skb_in_cgroup)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -1081,6 +1058,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
 			goto error;
 		break;
+	case BPF_FUNC_skb_in_cgroup:
+		if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
+			goto error;
+		break;
 	default:
 		break;
 	}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 86cb5c6e8932..50787cd61da2 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -62,6 +62,7 @@
 #include <linux/proc_ns.h>
 #include <linux/nsproxy.h>
 #include <linux/proc_ns.h>
+#include <linux/file.h>
 #include <net/sock.h>
 
 /*
@@ -837,6 +838,8 @@ static void put_css_set_locked(struct css_set *cset)
 
 static void put_css_set(struct css_set *cset)
 {
+	unsigned long flags;
+
 	/*
 	 * Ensure that the refcount doesn't hit zero while any readers
 	 * can see it. Similar to atomic_dec_and_lock(), but for an
@@ -845,9 +848,9 @@ static void put_css_set(struct css_set *cset)
 	if (atomic_add_unless(&cset->refcount, -1, 1))
 		return;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irqsave(&css_set_lock, flags);
 	put_css_set_locked(cset);
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irqrestore(&css_set_lock, flags);
 }
 
 /*
@@ -1070,11 +1073,11 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 
 	/* First see if we already have a cgroup group that matches
 	 * the desired set */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	cset = find_existing_css_set(old_cset, cgrp, template);
 	if (cset)
 		get_css_set(cset);
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	if (cset)
 		return cset;
@@ -1102,7 +1105,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	 * find_existing_css_set() */
 	memcpy(cset->subsys, template, sizeof(cset->subsys));
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	/* Add reference counts and links from the new css_set. */
 	list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) {
 		struct cgroup *c = link->cgrp;
@@ -1128,7 +1131,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 		css_get(css);
 	}
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	return cset;
 }
@@ -1192,7 +1195,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 	 * Release all the links from cset_links to this hierarchy's
 	 * root cgroup
 	 */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
 		list_del(&link->cset_link);
@@ -1200,7 +1203,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 		kfree(link);
 	}
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	if (!list_empty(&root->root_list)) {
 		list_del(&root->root_list);
@@ -1600,11 +1603,11 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		ss->root = dst_root;
 		css->cgroup = dcgrp;
 
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		hash_for_each(css_set_table, i, cset, hlist)
 			list_move_tail(&cset->e_cset_node[ss->id],
 				       &dcgrp->e_csets[ss->id]);
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 
 		/* default hierarchy doesn't enable controllers by default */
 		dst_root->subsys_mask |= 1 << ssid;
@@ -1640,10 +1643,10 @@ static int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 	if (!buf)
 		return -ENOMEM;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot);
 	len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX);
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	if (len >= PATH_MAX)
 		len = -ERANGE;
@@ -1897,7 +1900,7 @@ static void cgroup_enable_task_cg_lists(void)
 {
 	struct task_struct *p, *g;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	if (use_task_css_set_links)
 		goto out_unlock;
@@ -1922,8 +1925,12 @@ static void cgroup_enable_task_cg_lists(void)
 		 * entry won't be deleted though the process has exited.
 		 * Do it while holding siglock so that we don't end up
 		 * racing against cgroup_exit().
+		 *
+		 * Interrupts were already disabled while acquiring
+		 * the css_set_lock, so we do not need to disable it
+		 * again when acquiring the sighand->siglock here.
 		 */
-		spin_lock_irq(&p->sighand->siglock);
+		spin_lock(&p->sighand->siglock);
 		if (!(p->flags & PF_EXITING)) {
 			struct css_set *cset = task_css_set(p);
 
@@ -1932,11 +1939,11 @@ static void cgroup_enable_task_cg_lists(void)
 			list_add_tail(&p->cg_list, &cset->tasks);
 			get_css_set(cset);
 		}
-		spin_unlock_irq(&p->sighand->siglock);
+		spin_unlock(&p->sighand->siglock);
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
 out_unlock:
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 }
 
 static void init_cgroup_housekeeping(struct cgroup *cgrp)
@@ -2043,13 +2050,13 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	 * Link the root cgroup in this hierarchy into all the css_set
 	 * objects.
 	 */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	hash_for_each(css_set_table, i, cset, hlist) {
 		link_css_set(&tmp_links, cset, root_cgrp);
 		if (css_set_populated(cset))
 			cgroup_update_populated(root_cgrp, true);
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	BUG_ON(!list_empty(&root_cgrp->self.children));
 	BUG_ON(atomic_read(&root->nr_cgrps) != 1);
@@ -2256,11 +2263,11 @@ out_mount:
 		struct cgroup *cgrp;
 
 		mutex_lock(&cgroup_mutex);
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 
 		cgrp = cset_cgroup_from_root(ns->root_cset, root);
 
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 		mutex_unlock(&cgroup_mutex);
 
 		nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
@@ -2337,11 +2344,11 @@ char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
 	char *ret;
 
 	mutex_lock(&cgroup_mutex);
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns);
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	mutex_unlock(&cgroup_mutex);
 
 	return ret;
@@ -2369,7 +2376,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 	char *path = NULL;
 
 	mutex_lock(&cgroup_mutex);
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
 
@@ -2382,7 +2389,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 			path = buf;
 	}
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	mutex_unlock(&cgroup_mutex);
 	return path;
 }
@@ -2557,7 +2564,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
 	 * the new cgroup.  There are no failure cases after here, so this
 	 * is the commit point.
 	 */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(cset, &tset->src_csets, mg_node) {
 		list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) {
 			struct css_set *from_cset = task_css_set(task);
@@ -2568,7 +2575,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
 			put_css_set_locked(from_cset);
 		}
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	/*
 	 * Migration is committed, all target tasks are now on dst_csets.
@@ -2597,13 +2604,13 @@ out_cancel_attach:
 		}
 	} while_each_subsys_mask();
 out_release_tset:
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_splice_init(&tset->dst_csets, &tset->src_csets);
 	list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) {
 		list_splice_tail_init(&cset->mg_tasks, &cset->tasks);
 		list_del_init(&cset->mg_node);
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	return ret;
 }
 
@@ -2634,7 +2641,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) {
 		cset->mg_src_cgrp = NULL;
 		cset->mg_dst_cgrp = NULL;
@@ -2642,7 +2649,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
 		list_del_init(&cset->mg_preload_node);
 		put_css_set_locked(cset);
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 }
 
 /**
@@ -2783,7 +2790,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
 	 * already PF_EXITING could be freed from underneath us unless we
 	 * take an rcu_read_lock.
 	 */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	rcu_read_lock();
 	task = leader;
 	do {
@@ -2792,7 +2799,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
 			break;
 	} while_each_thread(leader, task);
 	rcu_read_unlock();
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	return cgroup_taskset_migrate(&tset, root);
 }
@@ -2816,7 +2823,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
 		return -EBUSY;
 
 	/* look up all src csets */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	rcu_read_lock();
 	task = leader;
 	do {
@@ -2826,7 +2833,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
 			break;
 	} while_each_thread(leader, task);
 	rcu_read_unlock();
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	/* prepare dst csets and commit */
 	ret = cgroup_migrate_prepare_dst(&preloaded_csets);
@@ -2859,9 +2866,9 @@ static int cgroup_procs_write_permission(struct task_struct *task,
 		struct cgroup *cgrp;
 		struct inode *inode;
 
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 
 		while (!cgroup_is_descendant(dst_cgrp, cgrp))
 			cgrp = cgroup_parent(cgrp);
@@ -2962,9 +2969,9 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 		if (root == &cgrp_dfl_root)
 			continue;
 
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		from_cgrp = task_cgroup_from_root(from, root);
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 
 		retval = cgroup_attach_task(from_cgrp, tsk, false);
 		if (retval)
@@ -3080,7 +3087,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	percpu_down_write(&cgroup_threadgroup_rwsem);
 
 	/* look up all csses currently attached to @cgrp's subtree */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
 		struct cgrp_cset_link *link;
 
@@ -3088,14 +3095,14 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 			cgroup_migrate_add_src(link->cset, dsct,
 					       &preloaded_csets);
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	/* NULL dst indicates self on default hierarchy */
 	ret = cgroup_migrate_prepare_dst(&preloaded_csets);
 	if (ret)
 		goto out_finish;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) {
 		struct task_struct *task, *ntask;
 
@@ -3107,7 +3114,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 		list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list)
 			cgroup_taskset_add(task, &tset);
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	ret = cgroup_taskset_migrate(&tset, cgrp->root);
 out_finish:
@@ -3908,10 +3915,10 @@ static int cgroup_task_count(const struct cgroup *cgrp)
 	int count = 0;
 	struct cgrp_cset_link *link;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &cgrp->cset_links, cset_link)
 		count += atomic_read(&link->cset->refcount);
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	return count;
 }
 
@@ -4249,7 +4256,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
 
 	memset(it, 0, sizeof(*it));
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	it->ss = css->ss;
 
@@ -4262,7 +4269,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
 
 	css_task_iter_advance_css_set(it);
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 }
 
 /**
@@ -4280,7 +4287,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 		it->cur_task = NULL;
 	}
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	if (it->task_pos) {
 		it->cur_task = list_entry(it->task_pos, struct task_struct,
@@ -4289,7 +4296,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 		css_task_iter_advance(it);
 	}
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	return it->cur_task;
 }
@@ -4303,10 +4310,10 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 void css_task_iter_end(struct css_task_iter *it)
 {
 	if (it->cur_cset) {
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		list_del(&it->iters_node);
 		put_css_set_locked(it->cur_cset);
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 	}
 
 	if (it->cur_task)
@@ -4338,10 +4345,10 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 	mutex_lock(&cgroup_mutex);
 
 	/* all tasks in @from are being moved, all csets are source */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &from->cset_links, cset_link)
 		cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	ret = cgroup_migrate_prepare_dst(&preloaded_csets);
 	if (ret)
@@ -5063,6 +5070,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	memset(css, 0, sizeof(*css));
 	css->cgroup = cgrp;
 	css->ss = ss;
+	css->id = -1;
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
 	css->serial_nr = css_serial_nr_next++;
@@ -5150,7 +5158,7 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 
 	err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL);
 	if (err < 0)
-		goto err_free_percpu_ref;
+		goto err_free_css;
 	css->id = err;
 
 	/* @css is ready to be brought online now, make it visible */
@@ -5174,9 +5182,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 
 err_list_del:
 	list_del_rcu(&css->sibling);
-	cgroup_idr_remove(&ss->css_idr, css->id);
-err_free_percpu_ref:
-	percpu_ref_exit(&css->refcnt);
 err_free_css:
 	call_rcu(&css->rcu_head, css_free_rcu_fn);
 	return ERR_PTR(err);
@@ -5451,10 +5456,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	 */
 	cgrp->self.flags &= ~CSS_ONLINE;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &cgrp->cset_links, cset_link)
 		link->cset->dead = true;
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	/* initiate massacre of all css's */
 	for_each_css(css, ssid, cgrp)
@@ -5725,7 +5730,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		goto out;
 
 	mutex_lock(&cgroup_mutex);
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	for_each_root(root) {
 		struct cgroup_subsys *ss;
@@ -5778,7 +5783,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 
 	retval = 0;
 out_unlock:
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	mutex_unlock(&cgroup_mutex);
 	kfree(buf);
 out:
@@ -5923,13 +5928,13 @@ void cgroup_post_fork(struct task_struct *child)
 	if (use_task_css_set_links) {
 		struct css_set *cset;
 
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		cset = task_css_set(current);
 		if (list_empty(&child->cg_list)) {
 			get_css_set(cset);
 			css_set_move_task(child, NULL, cset, false);
 		}
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 	}
 
 	/*
@@ -5974,9 +5979,9 @@ void cgroup_exit(struct task_struct *tsk)
 	cset = task_css_set(tsk);
 
 	if (!list_empty(&tsk->cg_list)) {
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		css_set_move_task(tsk, cset, NULL, false);
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 	} else {
 		get_css_set(cset);
 	}
@@ -6044,9 +6049,9 @@ static void cgroup_release_agent(struct work_struct *work)
 	if (!pathbuf || !agentbuf)
 		goto out;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	path = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	if (!path)
 		goto out;
 
@@ -6205,6 +6210,40 @@ struct cgroup *cgroup_get_from_path(const char *path)
 }
 EXPORT_SYMBOL_GPL(cgroup_get_from_path);
 
+/**
+ * cgroup_get_from_fd - get a cgroup pointer from a fd
+ * @fd: fd obtained by open(cgroup2_dir)
+ *
+ * Find the cgroup from a fd which should be obtained
+ * by opening a cgroup directory.  Returns a pointer to the
+ * cgroup on success. ERR_PTR is returned if the cgroup
+ * cannot be found.
+ */
+struct cgroup *cgroup_get_from_fd(int fd)
+{
+	struct cgroup_subsys_state *css;
+	struct cgroup *cgrp;
+	struct file *f;
+
+	f = fget_raw(fd);
+	if (!f)
+		return ERR_PTR(-EBADF);
+
+	css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
+	fput(f);
+	if (IS_ERR(css))
+		return ERR_CAST(css);
+
+	cgrp = css->cgroup;
+	if (!cgroup_on_dfl(cgrp)) {
+		cgroup_put(cgrp);
+		return ERR_PTR(-EBADF);
+	}
+
+	return cgrp;
+}
+EXPORT_SYMBOL_GPL(cgroup_get_from_fd);
+
 /*
  * sock->sk_cgrp_data handling.  For more info, see sock_cgroup_data
  * definition in cgroup-defs.h.
@@ -6306,12 +6345,12 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
 		return ERR_PTR(-EPERM);
 
 	mutex_lock(&cgroup_mutex);
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	cset = task_css_set(current);
 	get_css_set(cset);
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	mutex_unlock(&cgroup_mutex);
 
 	new_ns = alloc_cgroup_ns();
@@ -6435,7 +6474,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
 	if (!name_buf)
 		return -ENOMEM;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	rcu_read_lock();
 	cset = rcu_dereference(current->cgroups);
 	list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
@@ -6446,7 +6485,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
 			   c->root->hierarchy_id, name_buf);
 	}
 	rcu_read_unlock();
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	kfree(name_buf);
 	return 0;
 }
@@ -6457,7 +6496,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
 	struct cgroup_subsys_state *css = seq_css(seq);
 	struct cgrp_cset_link *link;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
 		struct css_set *cset = link->cset;
 		struct task_struct *task;
@@ -6480,7 +6519,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
 	overflow:
 		seq_puts(seq, "  ...\n");
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	return 0;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 274450efea90..9c51ec3f0f44 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3862,10 +3862,8 @@ static void _free_event(struct perf_event *event)
 	if (event->ctx)
 		put_ctx(event->ctx);
 
-	if (event->pmu) {
-		exclusive_event_destroy(event);
-		module_put(event->pmu->module);
-	}
+	exclusive_event_destroy(event);
+	module_put(event->pmu->module);
 
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 5c2c355aa97f..4a7ec0c6c88c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -148,18 +148,18 @@ static inline void free_task_struct(struct task_struct *tsk)
 }
 #endif
 
-void __weak arch_release_thread_info(struct thread_info *ti)
+void __weak arch_release_thread_stack(unsigned long *stack)
 {
 }
 
-#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
 
 /*
  * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
  * kmemcache based allocator.
  */
 # if THREAD_SIZE >= PAGE_SIZE
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 						  int node)
 {
 	struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
@@ -172,33 +172,33 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
 	return page ? page_address(page) : NULL;
 }
 
-static inline void free_thread_info(struct thread_info *ti)
+static inline void free_thread_stack(unsigned long *stack)
 {
-	struct page *page = virt_to_page(ti);
+	struct page *page = virt_to_page(stack);
 
 	memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
 				    -(1 << THREAD_SIZE_ORDER));
 	__free_kmem_pages(page, THREAD_SIZE_ORDER);
 }
 # else
-static struct kmem_cache *thread_info_cache;
+static struct kmem_cache *thread_stack_cache;
 
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 						  int node)
 {
-	return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+	return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
 }
 
-static void free_thread_info(struct thread_info *ti)
+static void free_thread_stack(unsigned long *stack)
 {
-	kmem_cache_free(thread_info_cache, ti);
+	kmem_cache_free(thread_stack_cache, stack);
 }
 
-void thread_info_cache_init(void)
+void thread_stack_cache_init(void)
 {
-	thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+	thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
 					      THREAD_SIZE, 0, NULL);
-	BUG_ON(thread_info_cache == NULL);
+	BUG_ON(thread_stack_cache == NULL);
 }
 # endif
 #endif
@@ -221,9 +221,9 @@ struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
-static void account_kernel_stack(struct thread_info *ti, int account)
+static void account_kernel_stack(unsigned long *stack, int account)
 {
-	struct zone *zone = page_zone(virt_to_page(ti));
+	struct zone *zone = page_zone(virt_to_page(stack));
 
 	mod_zone_page_state(zone, NR_KERNEL_STACK, account);
 }
@@ -231,8 +231,8 @@ static void account_kernel_stack(struct thread_info *ti, int account)
 void free_task(struct task_struct *tsk)
 {
 	account_kernel_stack(tsk->stack, -1);
-	arch_release_thread_info(tsk->stack);
-	free_thread_info(tsk->stack);
+	arch_release_thread_stack(tsk->stack);
+	free_thread_stack(tsk->stack);
 	rt_mutex_debug_task_free(tsk);
 	ftrace_graph_exit_task(tsk);
 	put_seccomp_filter(tsk);
@@ -343,7 +343,7 @@ void set_task_stack_end_magic(struct task_struct *tsk)
 static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 {
 	struct task_struct *tsk;
-	struct thread_info *ti;
+	unsigned long *stack;
 	int err;
 
 	if (node == NUMA_NO_NODE)
@@ -352,15 +352,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	if (!tsk)
 		return NULL;
 
-	ti = alloc_thread_info_node(tsk, node);
-	if (!ti)
+	stack = alloc_thread_stack_node(tsk, node);
+	if (!stack)
 		goto free_tsk;
 
 	err = arch_dup_task_struct(tsk, orig);
 	if (err)
-		goto free_ti;
+		goto free_stack;
 
-	tsk->stack = ti;
+	tsk->stack = stack;
 #ifdef CONFIG_SECCOMP
 	/*
 	 * We must handle setting up seccomp filters once we're under
@@ -392,14 +392,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->task_frag.page = NULL;
 	tsk->wake_q.next = NULL;
 
-	account_kernel_stack(ti, 1);
+	account_kernel_stack(stack, 1);
 
 	kcov_task_init(tsk);
 
 	return tsk;
 
-free_ti:
-	free_thread_info(ti);
+free_stack:
+	free_thread_stack(stack);
 free_tsk:
 	free_task_struct(tsk);
 	return NULL;
diff --git a/kernel/futex.c b/kernel/futex.c
index ee25f5ba4aca..33664f70e2d2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -469,7 +469,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
-	struct page *page;
+	struct page *page, *tail;
 	struct address_space *mapping;
 	int err, ro = 0;
 
@@ -530,7 +530,15 @@ again:
 	 * considered here and page lock forces unnecessarily serialization
 	 * From this point on, mapping will be re-verified if necessary and
 	 * page lock will be acquired only if it is unavoidable
-	 */
+	 *
+	 * Mapping checks require the head page for any compound page so the
+	 * head page and mapping is looked up now. For anonymous pages, it
+	 * does not matter if the page splits in the future as the key is
+	 * based on the address. For filesystem-backed pages, the tail is
+	 * required as the index of the page determines the key. For
+	 * base pages, there is no tail page and tail == page.
+	 */
+	tail = page;
 	page = compound_head(page);
 	mapping = READ_ONCE(page->mapping);
 
@@ -654,7 +662,7 @@ again:
 
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
 		key->shared.inode = inode;
-		key->shared.pgoff = basepage_index(page);
+		key->shared.pgoff = basepage_index(tail);
 		rcu_read_unlock();
 	}
 
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index c42742208e5e..89b49f6773f0 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -125,7 +125,7 @@ int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest)
 
 	domain = data->domain;
 	if (WARN_ON(domain == NULL))
-		return;
+		return -EINVAL;
 
 	if (!irq_domain_is_ipi(domain)) {
 		pr_warn("Trying to destroy a non IPI domain!\n");
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 05254eeb4b4e..4b353e0be121 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -58,13 +58,36 @@ static void jump_label_update(struct static_key *key);
 
 void static_key_slow_inc(struct static_key *key)
 {
+	int v, v1;
+
 	STATIC_KEY_CHECK_USE();
-	if (atomic_inc_not_zero(&key->enabled))
-		return;
+
+	/*
+	 * Careful if we get concurrent static_key_slow_inc() calls;
+	 * later calls must wait for the first one to _finish_ the
+	 * jump_label_update() process.  At the same time, however,
+	 * the jump_label_update() call below wants to see
+	 * static_key_enabled(&key) for jumps to be updated properly.
+	 *
+	 * So give a special meaning to negative key->enabled: it sends
+	 * static_key_slow_inc() down the slow path, and it is non-zero
+	 * so it counts as "enabled" in jump_label_update().  Note that
+	 * atomic_inc_unless_negative() checks >= 0, so roll our own.
+	 */
+	for (v = atomic_read(&key->enabled); v > 0; v = v1) {
+		v1 = atomic_cmpxchg(&key->enabled, v, v + 1);
+		if (likely(v1 == v))
+			return;
+	}
 
 	jump_label_lock();
-	if (atomic_inc_return(&key->enabled) == 1)
+	if (atomic_read(&key->enabled) == 0) {
+		atomic_set(&key->enabled, -1);
 		jump_label_update(key);
+		atomic_set(&key->enabled, 1);
+	} else {
+		atomic_inc(&key->enabled);
+	}
 	jump_label_unlock();
 }
 EXPORT_SYMBOL_GPL(static_key_slow_inc);
@@ -72,6 +95,13 @@ EXPORT_SYMBOL_GPL(static_key_slow_inc);
 static void __static_key_slow_dec(struct static_key *key,
 		unsigned long rate_limit, struct delayed_work *work)
 {
+	/*
+	 * The negative count check is valid even when a negative
+	 * key->enabled is in use by static_key_slow_inc(); a
+	 * __static_key_slow_dec() before the first static_key_slow_inc()
+	 * returns is unbalanced, because all other static_key_slow_inc()
+	 * instances block while the update is in progress.
+	 */
 	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
 		WARN(atomic_read(&key->enabled) < 0,
 		     "jump label: negative count!\n");
diff --git a/kernel/kcov.c b/kernel/kcov.c
index a02f2dddd1d7..8d44b3fea9d0 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -264,7 +264,12 @@ static const struct file_operations kcov_fops = {
 
 static int __init kcov_init(void)
 {
-	if (!debugfs_create_file("kcov", 0600, NULL, NULL, &kcov_fops)) {
+	/*
+	 * The kcov debugfs file won't ever get removed and thus,
+	 * there is no need to protect it against removal races. The
+	 * use of debugfs_create_file_unsafe() is actually safe here.
+	 */
+	if (!debugfs_create_file_unsafe("kcov", 0600, NULL, NULL, &kcov_fops)) {
 		pr_err("failed to create kcov in debugfs\n");
 		return -ENOMEM;
 	}
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 3ef3736002d8..9c951fade415 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -49,21 +49,21 @@ void debug_mutex_free_waiter(struct mutex_waiter *waiter)
 }
 
 void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
-			    struct thread_info *ti)
+			    struct task_struct *task)
 {
 	SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
 
 	/* Mark the current thread as blocked on the lock: */
-	ti->task->blocked_on = waiter;
+	task->blocked_on = waiter;
 }
 
 void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
-			 struct thread_info *ti)
+			 struct task_struct *task)
 {
 	DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
-	DEBUG_LOCKS_WARN_ON(waiter->task != ti->task);
-	DEBUG_LOCKS_WARN_ON(ti->task->blocked_on != waiter);
-	ti->task->blocked_on = NULL;
+	DEBUG_LOCKS_WARN_ON(waiter->task != task);
+	DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter);
+	task->blocked_on = NULL;
 
 	list_del_init(&waiter->list);
 	waiter->task = NULL;
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index 0799fd3e4cfa..d06ae3bb46c5 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -20,9 +20,9 @@ extern void debug_mutex_wake_waiter(struct mutex *lock,
 extern void debug_mutex_free_waiter(struct mutex_waiter *waiter);
 extern void debug_mutex_add_waiter(struct mutex *lock,
 				   struct mutex_waiter *waiter,
-				   struct thread_info *ti);
+				   struct task_struct *task);
 extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
-				struct thread_info *ti);
+				struct task_struct *task);
 extern void debug_mutex_unlock(struct mutex *lock);
 extern void debug_mutex_init(struct mutex *lock, const char *name,
 			     struct lock_class_key *key);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index e364b424b019..a70b90db3909 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -486,9 +486,6 @@ __ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx)
 	if (!hold_ctx)
 		return 0;
 
-	if (unlikely(ctx == hold_ctx))
-		return -EALREADY;
-
 	if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
 	    (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
 #ifdef CONFIG_DEBUG_MUTEXES
@@ -514,6 +511,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	unsigned long flags;
 	int ret;
 
+	if (use_ww_ctx) {
+		struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
+			return -EALREADY;
+	}
+
 	preempt_disable();
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
@@ -534,7 +537,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		goto skip_wait;
 
 	debug_mutex_lock_common(lock, &waiter);
-	debug_mutex_add_waiter(lock, &waiter, task_thread_info(task));
+	debug_mutex_add_waiter(lock, &waiter, task);
 
 	/* add waiting tasks to the end of the waitqueue (FIFO): */
 	list_add_tail(&waiter.list, &lock->wait_list);
@@ -581,7 +584,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	}
 	__set_task_state(task, TASK_RUNNING);
 
-	mutex_remove_waiter(lock, &waiter, current_thread_info());
+	mutex_remove_waiter(lock, &waiter, task);
 	/* set it to 0 if there are no waiters left: */
 	if (likely(list_empty(&lock->wait_list)))
 		atomic_set(&lock->count, 0);
@@ -602,7 +605,7 @@ skip_wait:
 	return 0;
 
 err:
-	mutex_remove_waiter(lock, &waiter, task_thread_info(task));
+	mutex_remove_waiter(lock, &waiter, task);
 	spin_unlock_mutex(&lock->wait_lock, flags);
 	debug_mutex_free_waiter(&waiter);
 	mutex_release(&lock->dep_map, 1, ip);
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 5cda397607f2..a68bae5e852a 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -13,7 +13,7 @@
 		do { spin_lock(lock); (void)(flags); } while (0)
 #define spin_unlock_mutex(lock, flags) \
 		do { spin_unlock(lock); (void)(flags); } while (0)
-#define mutex_remove_waiter(lock, waiter, ti) \
+#define mutex_remove_waiter(lock, waiter, task) \
 		__list_del((waiter)->list.prev, (waiter)->list.next)
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index ce2f75e32ae1..5fc8c311b8fe 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -267,6 +267,66 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
 #define queued_spin_lock_slowpath	native_queued_spin_lock_slowpath
 #endif
 
+/*
+ * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
+ * issuing an _unordered_ store to set _Q_LOCKED_VAL.
+ *
+ * This means that the store can be delayed, but no later than the
+ * store-release from the unlock. This means that simply observing
+ * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired.
+ *
+ * There are two paths that can issue the unordered store:
+ *
+ *  (1) clear_pending_set_locked():	*,1,0 -> *,0,1
+ *
+ *  (2) set_locked():			t,0,0 -> t,0,1 ; t != 0
+ *      atomic_cmpxchg_relaxed():	t,0,0 -> 0,0,1
+ *
+ * However, in both cases we have other !0 state we've set before to queue
+ * ourseves:
+ *
+ * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our
+ * load is constrained by that ACQUIRE to not pass before that, and thus must
+ * observe the store.
+ *
+ * For (2) we have a more intersting scenario. We enqueue ourselves using
+ * xchg_tail(), which ends up being a RELEASE. This in itself is not
+ * sufficient, however that is followed by an smp_cond_acquire() on the same
+ * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and
+ * guarantees we must observe that store.
+ *
+ * Therefore both cases have other !0 state that is observable before the
+ * unordered locked byte store comes through. This means we can use that to
+ * wait for the lock store, and then wait for an unlock.
+ */
+#ifndef queued_spin_unlock_wait
+void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+	u32 val;
+
+	for (;;) {
+		val = atomic_read(&lock->val);
+
+		if (!val) /* not locked, we're done */
+			goto done;
+
+		if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */
+			break;
+
+		/* not locked, but pending, wait until we observe the lock */
+		cpu_relax();
+	}
+
+	/* any unlock is good */
+	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+		cpu_relax();
+
+done:
+	smp_rmb(); /* CTRL + RMB -> ACQUIRE */
+}
+EXPORT_SYMBOL(queued_spin_unlock_wait);
+#endif
+
 #endif /* _GEN_PV_LOCK_SLOWPATH */
 
 /**
diff --git a/kernel/power/process.c b/kernel/power/process.c
index df058bed53ce..0c2ee9761d57 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -146,6 +146,18 @@ int freeze_processes(void)
 	if (!error && !oom_killer_disable())
 		error = -EBUSY;
 
+	/*
+	 * There is a hard to fix race between oom_reaper kernel thread
+	 * and oom_killer_disable. oom_reaper calls exit_oom_victim
+	 * before the victim reaches exit_mm so try to freeze all the tasks
+	 * again and catch such a left over task.
+	 */
+	if (!error) {
+		pr_info("Double checking all user space processes after OOM killer disable... ");
+		error = try_to_freeze_tasks(true);
+		pr_cont("\n");
+	}
+
 	if (error)
 		thaw_processes();
 	return error;
diff --git a/kernel/relay.c b/kernel/relay.c
index 074994bcfa9b..04d7cf3ef8cf 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -614,6 +614,7 @@ free_bufs:
 
 	kref_put(&chan->kref, relay_destroy_channel);
 	mutex_unlock(&relay_channels_mutex);
+	kfree(chan);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(relay_open);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f2cae4620c7..51d7105f529a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1536,7 +1536,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 	for (;;) {
 		/* Any allowed, online CPU? */
 		for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) {
-			if (!cpu_active(dest_cpu))
+			if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
+				continue;
+			if (!cpu_online(dest_cpu))
 				continue;
 			goto out;
 		}
@@ -2253,9 +2255,11 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
 #endif
 #endif
 
+#ifdef CONFIG_SCHEDSTATS
+
 DEFINE_STATIC_KEY_FALSE(sched_schedstats);
+static bool __initdata __sched_schedstats = false;
 
-#ifdef CONFIG_SCHEDSTATS
 static void set_schedstats(bool enabled)
 {
 	if (enabled)
@@ -2278,11 +2282,16 @@ static int __init setup_schedstats(char *str)
 	if (!str)
 		goto out;
 
+	/*
+	 * This code is called before jump labels have been set up, so we can't
+	 * change the static branch directly just yet.  Instead set a temporary
+	 * variable so init_schedstats() can do it later.
+	 */
 	if (!strcmp(str, "enable")) {
-		set_schedstats(true);
+		__sched_schedstats = true;
 		ret = 1;
 	} else if (!strcmp(str, "disable")) {
-		set_schedstats(false);
+		__sched_schedstats = false;
 		ret = 1;
 	}
 out:
@@ -2293,6 +2302,11 @@ out:
 }
 __setup("schedstats=", setup_schedstats);
 
+static void __init init_schedstats(void)
+{
+	set_schedstats(__sched_schedstats);
+}
+
 #ifdef CONFIG_PROC_SYSCTL
 int sysctl_schedstats(struct ctl_table *table, int write,
 			 void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -2313,8 +2327,10 @@ int sysctl_schedstats(struct ctl_table *table, int write,
 		set_schedstats(state);
 	return err;
 }
-#endif
-#endif
+#endif /* CONFIG_PROC_SYSCTL */
+#else  /* !CONFIG_SCHEDSTATS */
+static inline void init_schedstats(void) {}
+#endif /* CONFIG_SCHEDSTATS */
 
 /*
  * fork()/clone()-time setup:
@@ -2521,10 +2537,9 @@ void wake_up_new_task(struct task_struct *p)
 	 */
 	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
-	/* Post initialize new task's util average when its cfs_rq is set */
+	rq = __task_rq_lock(p, &rf);
 	post_init_entity_util_avg(&p->se);
 
-	rq = __task_rq_lock(p, &rf);
 	activate_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p);
@@ -3156,7 +3171,8 @@ static noinline void __schedule_bug(struct task_struct *prev)
 static inline void schedule_debug(struct task_struct *prev)
 {
 #ifdef CONFIG_SCHED_STACK_END_CHECK
-	BUG_ON(task_stack_end_corrupted(prev));
+	if (task_stack_end_corrupted(prev))
+		panic("corrupted stack end detected inside scheduler\n");
 #endif
 
 	if (unlikely(in_atomic_preempt_off())) {
@@ -5133,14 +5149,16 @@ void show_state_filter(unsigned long state_filter)
 		/*
 		 * reset the NMI-timeout, listing all files on a slow
 		 * console might take a lot of time:
+		 * Also, reset softlockup watchdogs on all CPUs, because
+		 * another CPU might be blocked waiting for us to process
+		 * an IPI.
 		 */
 		touch_nmi_watchdog();
+		touch_all_softlockup_watchdogs();
 		if (!state_filter || (p->state & state_filter))
 			sched_show_task(p);
 	}
 
-	touch_all_softlockup_watchdogs();
-
 #ifdef CONFIG_SCHED_DEBUG
 	if (!state_filter)
 		sysrq_sched_debug_show();
@@ -7487,6 +7505,8 @@ void __init sched_init(void)
 #endif
 	init_sched_fair_class();
 
+	init_schedstats();
+
 	scheduler_running = 1;
 }
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index cf905f655ba1..0368c393a336 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -427,19 +427,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		SPLIT_NS(p->se.vruntime),
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
-#ifdef CONFIG_SCHEDSTATS
-	if (schedstat_enabled()) {
-		SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
-			SPLIT_NS(p->se.statistics.wait_sum),
-			SPLIT_NS(p->se.sum_exec_runtime),
-			SPLIT_NS(p->se.statistics.sum_sleep_runtime));
-	}
-#else
+
 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
-		0LL, 0L,
+		SPLIT_NS(schedstat_val(p, se.statistics.wait_sum)),
 		SPLIT_NS(p->se.sum_exec_runtime),
-		0LL, 0L);
-#endif
+		SPLIT_NS(schedstat_val(p, se.statistics.sum_sleep_runtime)));
+
 #ifdef CONFIG_NUMA_BALANCING
 	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 218f8e83db73..bdcbeea90c95 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2904,6 +2904,23 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 	}
 }
 
+/*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define sub_positive(_ptr, _val) do {				\
+	typeof(_ptr) ptr = (_ptr);				\
+	typeof(*ptr) val = (_val);				\
+	typeof(*ptr) res, var = READ_ONCE(*ptr);		\
+	res = var - val;					\
+	if (res > var)						\
+		res = 0;					\
+	WRITE_ONCE(*ptr, res);					\
+} while (0)
+
 /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
 static inline int
 update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
@@ -2913,15 +2930,15 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 
 	if (atomic_long_read(&cfs_rq->removed_load_avg)) {
 		s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
-		sa->load_avg = max_t(long, sa->load_avg - r, 0);
-		sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+		sub_positive(&sa->load_avg, r);
+		sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
 		removed_load = 1;
 	}
 
 	if (atomic_long_read(&cfs_rq->removed_util_avg)) {
 		long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
-		sa->util_avg = max_t(long, sa->util_avg - r, 0);
-		sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
+		sub_positive(&sa->util_avg, r);
+		sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
 		removed_util = 1;
 	}
 
@@ -2994,10 +3011,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 			  &se->avg, se->on_rq * scale_load_down(se->load.weight),
 			  cfs_rq->curr == se, NULL);
 
-	cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
-	cfs_rq->avg.load_sum = max_t(s64,  cfs_rq->avg.load_sum - se->avg.load_sum, 0);
-	cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
-	cfs_rq->avg.util_sum = max_t(s32,  cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+	sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
+	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
+	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
 
 	cfs_rq_util_change(cfs_rq);
 }
@@ -3246,7 +3263,7 @@ static inline void check_schedstat_required(void)
 			trace_sched_stat_iowait_enabled()  ||
 			trace_sched_stat_blocked_enabled() ||
 			trace_sched_stat_runtime_enabled())  {
-		pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, "
+		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
 			     "stat_blocked and stat_runtime require the "
 			     "kernel parameter schedstats=enabled or "
 			     "kernel.sched_schedstats=1\n");
@@ -4185,6 +4202,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 	if (!cfs_bandwidth_used())
 		return;
 
+	/* Synchronize hierarchical throttle counter: */
+	if (unlikely(!cfs_rq->throttle_uptodate)) {
+		struct rq *rq = rq_of(cfs_rq);
+		struct cfs_rq *pcfs_rq;
+		struct task_group *tg;
+
+		cfs_rq->throttle_uptodate = 1;
+
+		/* Get closest up-to-date node, because leaves go first: */
+		for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+			pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+			if (pcfs_rq->throttle_uptodate)
+				break;
+		}
+		if (tg) {
+			cfs_rq->throttle_count = pcfs_rq->throttle_count;
+			cfs_rq->throttled_clock_task = rq_clock_task(rq);
+		}
+	}
+
 	/* an active group must be handled by the update_curr()->put() path */
 	if (!cfs_rq->runtime_enabled || cfs_rq->curr)
 		return;
@@ -4500,15 +4537,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
+			/* Avoid re-evaluating load for this entity: */
+			se = parent_entity(se);
 			/*
 			 * Bias pick_next to pick a task from this cfs_rq, as
 			 * p is sleeping when it is within its sched_slice.
 			 */
-			if (task_sleep && parent_entity(se))
-				set_next_buddy(parent_entity(se));
-
-			/* avoid re-evaluating load for this entity */
-			se = parent_entity(se);
+			if (task_sleep && se && !throttled_hierarchy(cfs_rq))
+				set_next_buddy(se);
 			break;
 		}
 		flags |= DEQUEUE_SLEEP;
@@ -8496,8 +8532,9 @@ void free_fair_sched_group(struct task_group *tg)
 
 int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
-	struct cfs_rq *cfs_rq;
 	struct sched_entity *se;
+	struct cfs_rq *cfs_rq;
+	struct rq *rq;
 	int i;
 
 	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8512,6 +8549,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
 	for_each_possible_cpu(i) {
+		rq = cpu_rq(i);
+
 		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
 				      GFP_KERNEL, cpu_to_node(i));
 		if (!cfs_rq)
@@ -8525,7 +8564,10 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		init_cfs_rq(cfs_rq);
 		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
 		init_entity_runnable_average(se);
+
+		raw_spin_lock_irq(&rq->lock);
 		post_init_entity_util_avg(se);
+		raw_spin_unlock_irq(&rq->lock);
 	}
 
 	return 1;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index bd12c6c714ec..c5aeedf4e93a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -127,7 +127,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
  */
 static void cpuidle_idle_call(void)
 {
-	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_device *dev = cpuidle_get_device();
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 	int next_state, entered_state;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 72f1f3087b04..7cbeb92a1cb9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -437,7 +437,7 @@ struct cfs_rq {
 
 	u64 throttled_clock, throttled_clock_task;
 	u64 throttled_clock_task_time;
-	int throttled, throttle_count;
+	int throttled, throttle_count, throttle_uptodate;
 	struct list_head throttled_list;
 #endif /* CONFIG_CFS_BANDWIDTH */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 70b3b6a20fb0..78955cbea31c 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -33,6 +33,8 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
 # define schedstat_inc(rq, field)	do { if (schedstat_enabled()) { (rq)->field++; } } while (0)
 # define schedstat_add(rq, field, amt)	do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0)
 # define schedstat_set(var, val)	do { if (schedstat_enabled()) { var = (val); } } while (0)
+# define schedstat_val(rq, field)	((schedstat_enabled()) ? (rq)->field : 0)
+
 #else /* !CONFIG_SCHEDSTATS */
 static inline void
 rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
@@ -47,6 +49,7 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
 # define schedstat_inc(rq, field)	do { } while (0)
 # define schedstat_add(rq, field, amt)	do { } while (0)
 # define schedstat_set(var, val)	do { } while (0)
+# define schedstat_val(rq, field)	0
 #endif
 
 #ifdef CONFIG_SCHED_INFO
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 780bcbe1d4de..19c5b4a5c3eb 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -188,25 +188,33 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 	return &bpf_trace_printk_proto;
 }
 
-static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
+static u64 bpf_perf_event_read(u64 r1, u64 flags, u64 r3, u64 r4, u64 r5)
 {
 	struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	unsigned int cpu = smp_processor_id();
+	u64 index = flags & BPF_F_INDEX_MASK;
+	struct bpf_event_entry *ee;
 	struct perf_event *event;
-	struct file *file;
 
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+		return -EINVAL;
+	if (index == BPF_F_CURRENT_CPU)
+		index = cpu;
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = (struct file *)array->ptrs[index];
-	if (unlikely(!file))
+	ee = READ_ONCE(array->ptrs[index]);
+	if (!ee)
 		return -ENOENT;
 
-	event = file->private_data;
+	event = ee->event;
+	if (unlikely(event->attr.type != PERF_TYPE_HARDWARE &&
+		     event->attr.type != PERF_TYPE_RAW))
+		return -EINVAL;
 
 	/* make sure event is local and doesn't have pmu::count */
-	if (event->oncpu != smp_processor_id() ||
-	    event->pmu->count)
+	if (unlikely(event->oncpu != cpu || event->pmu->count))
 		return -EINVAL;
 
 	/*
@@ -230,11 +238,12 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
 	struct pt_regs *regs = (struct pt_regs *) (long) r1;
 	struct bpf_map *map = (struct bpf_map *) (long) r2;
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	unsigned int cpu = smp_processor_id();
 	u64 index = flags & BPF_F_INDEX_MASK;
 	void *data = (void *) (long) r4;
 	struct perf_sample_data sample_data;
+	struct bpf_event_entry *ee;
 	struct perf_event *event;
-	struct file *file;
 	struct perf_raw_record raw = {
 		.size = size,
 		.data = data,
@@ -243,21 +252,20 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
 	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
 		return -EINVAL;
 	if (index == BPF_F_CURRENT_CPU)
-		index = raw_smp_processor_id();
+		index = cpu;
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = (struct file *)array->ptrs[index];
-	if (unlikely(!file))
+	ee = READ_ONCE(array->ptrs[index]);
+	if (!ee)
 		return -ENOENT;
 
-	event = file->private_data;
-
+	event = ee->event;
 	if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE ||
 		     event->attr.config != PERF_COUNT_SW_BPF_OUTPUT))
 		return -EINVAL;
 
-	if (unlikely(event->oncpu != smp_processor_id()))
+	if (unlikely(event->oncpu != cpu))
 		return -EOPNOTSUPP;
 
 	perf_sample_data_init(&sample_data, 0, 0);
@@ -349,20 +357,15 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 }
 
 /* bpf+kprobe programs can access fields of 'struct pt_regs' */
-static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+					enum bpf_reg_type *reg_type)
 {
-	/* check bounds */
 	if (off < 0 || off >= sizeof(struct pt_regs))
 		return false;
-
-	/* only read is allowed */
 	if (type != BPF_READ)
 		return false;
-
-	/* disallow misaligned access */
 	if (off % size != 0)
 		return false;
-
 	return true;
 }
 
@@ -427,7 +430,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 	}
 }
 
-static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+				    enum bpf_reg_type *reg_type)
 {
 	if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
 		return false;
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index f96f0383f6c6..ad1d6164e946 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -36,6 +36,10 @@ struct trace_bprintk_fmt {
 static inline struct trace_bprintk_fmt *lookup_format(const char *fmt)
 {
 	struct trace_bprintk_fmt *pos;
+
+	if (!fmt)
+		return ERR_PTR(-EINVAL);
+
 	list_for_each_entry(pos, &trace_bprintk_fmt_list, list) {
 		if (!strcmp(pos->fmt, fmt))
 			return pos;
@@ -57,7 +61,8 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
 	for (iter = start; iter < end; iter++) {
 		struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);
 		if (tb_fmt) {
-			*iter = tb_fmt->fmt;
+			if (!IS_ERR(tb_fmt))
+				*iter = tb_fmt->fmt;
 			continue;
 		}
 
diff --git a/mm/compaction.c b/mm/compaction.c
index 1427366ad673..79bfe0e06907 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -441,25 +441,23 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
+		if (!isolated)
+			break;
+
 		total_isolated += isolated;
+		cc->nr_freepages += isolated;
 		for (i = 0; i < isolated; i++) {
 			list_add(&page->lru, freelist);
 			page++;
 		}
-
-		/* If a page was split, advance to the end of it */
-		if (isolated) {
-			cc->nr_freepages += isolated;
-			if (!strict &&
-				cc->nr_migratepages <= cc->nr_freepages) {
-				blockpfn += isolated;
-				break;
-			}
-
-			blockpfn += isolated - 1;
-			cursor += isolated - 1;
-			continue;
+		if (!strict && cc->nr_migratepages <= cc->nr_freepages) {
+			blockpfn += isolated;
+			break;
 		}
+		/* Advance to the end of split page */
+		blockpfn += isolated - 1;
+		cursor += isolated - 1;
+		continue;
 
 isolate_fail:
 		if (strict)
@@ -469,6 +467,9 @@ isolate_fail:
 
 	}
 
+	if (locked)
+		spin_unlock_irqrestore(&cc->zone->lock, flags);
+
 	/*
 	 * There is a tiny chance that we have read bogus compound_order(),
 	 * so be careful to not go outside of the pageblock.
@@ -490,9 +491,6 @@ isolate_fail:
 	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
-	if (locked)
-		spin_unlock_irqrestore(&cc->zone->lock, flags);
-
 	/* Update the pageblock-skip if the whole pageblock was scanned */
 	if (blockpfn == end_pfn)
 		update_pageblock_skip(cc, valid_page, total_isolated, false);
@@ -1011,6 +1009,7 @@ static void isolate_freepages(struct compact_control *cc)
 				block_end_pfn = block_start_pfn,
 				block_start_pfn -= pageblock_nr_pages,
 				isolate_start_pfn = block_start_pfn) {
+		unsigned long isolated;
 
 		/*
 		 * This can iterate a massively long zone without finding any
@@ -1035,8 +1034,12 @@ static void isolate_freepages(struct compact_control *cc)
 			continue;
 
 		/* Found a block suitable for isolating free pages from. */
-		isolate_freepages_block(cc, &isolate_start_pfn,
-					block_end_pfn, freelist, false);
+		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
+						block_end_pfn, freelist, false);
+		/* If isolation failed early, do not continue needlessly */
+		if (!isolated && isolate_start_pfn < block_end_pfn &&
+		    cc->nr_migratepages > cc->nr_freepages)
+			break;
 
 		/*
 		 * If we isolated enough freepages, or aborted due to async
diff --git a/mm/fadvise.c b/mm/fadvise.c
index b8024fa7101d..6c707bfe02fd 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -126,6 +126,17 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 		 */
 		start_index = (offset+(PAGE_SIZE-1)) >> PAGE_SHIFT;
 		end_index = (endbyte >> PAGE_SHIFT);
+		if ((endbyte & ~PAGE_MASK) != ~PAGE_MASK) {
+			/* First page is tricky as 0 - 1 = -1, but pgoff_t
+			 * is unsigned, so the end_index >= start_index
+			 * check below would be true and we'll discard the whole
+			 * file cache which is not what was asked.
+			 */
+			if (end_index == 0)
+				break;
+
+			end_index--;
+		}
 
 		if (end_index >= start_index) {
 			unsigned long count = invalidate_mapping_pages(mapping,
diff --git a/mm/filemap.c b/mm/filemap.c
index 00ae878b2a38..20f3b1f33f0e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2186,7 +2186,7 @@ repeat:
 		if (file->f_ra.mmap_miss > 0)
 			file->f_ra.mmap_miss--;
 		addr = address + (page->index - vmf->pgoff) * PAGE_SIZE;
-		do_set_pte(vma, addr, page, pte, false, false, true);
+		do_set_pte(vma, addr, page, pte, false, false);
 		unlock_page(page);
 		goto next;
 unlock:
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d26162e81fea..c1f3c0be150a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -832,8 +832,27 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg)
 	 * Only the process that called mmap() has reserves for
 	 * private mappings.
 	 */
-	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
-		return true;
+	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+		/*
+		 * Like the shared case above, a hole punch or truncate
+		 * could have been performed on the private mapping.
+		 * Examine the value of chg to determine if reserves
+		 * actually exist or were previously consumed.
+		 * Very Subtle - The value of chg comes from a previous
+		 * call to vma_needs_reserves().  The reserve map for
+		 * private mappings has different (opposite) semantics
+		 * than that of shared mappings.  vma_needs_reserves()
+		 * has already taken this difference in semantics into
+		 * account.  Therefore, the meaning of chg is the same
+		 * as in the shared case above.  Code could easily be
+		 * combined, but keeping it separate draws attention to
+		 * subtle differences.
+		 */
+		if (chg)
+			return false;
+		else
+			return true;
+	}
 
 	return false;
 }
@@ -1011,6 +1030,7 @@ static void destroy_compound_gigantic_page(struct page *page,
 	int nr_pages = 1 << order;
 	struct page *p = page + 1;
 
+	atomic_set(compound_mapcount_ptr(page), 0);
 	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
 		clear_compound_head(p);
 		set_page_refcounted(p);
@@ -1816,6 +1836,25 @@ static long __vma_reservation_common(struct hstate *h,
 
 	if (vma->vm_flags & VM_MAYSHARE)
 		return ret;
+	else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) {
+		/*
+		 * In most cases, reserves always exist for private mappings.
+		 * However, a file associated with mapping could have been
+		 * hole punched or truncated after reserves were consumed.
+		 * As subsequent fault on such a range will not use reserves.
+		 * Subtle - The reserve map for private mappings has the
+		 * opposite meaning than that of shared mappings.  If NO
+		 * entry is in the reserve map, it means a reservation exists.
+		 * If an entry exists in the reserve map, it means the
+		 * reservation has already been consumed.  As a result, the
+		 * return value of this routine is the opposite of the
+		 * value returned from reserve map manipulation routines above.
+		 */
+		if (ret)
+			return 0;
+		else
+			return 1;
+	}
 	else
 		return ret < 0 ? ret : 0;
 }
@@ -4190,7 +4229,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 		if (saddr) {
 			spte = huge_pte_offset(svma->vm_mm, saddr);
 			if (spte) {
-				mm_inc_nr_pmds(mm);
 				get_page(virt_to_page(spte));
 				break;
 			}
@@ -4205,9 +4243,9 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	if (pud_none(*pud)) {
 		pud_populate(mm, pud,
 				(pmd_t *)((unsigned long)spte & PAGE_MASK));
+		mm_inc_nr_pmds(mm);
 	} else {
 		put_page(virt_to_page(spte));
-		mm_inc_nr_pmds(mm);
 	}
 	spin_unlock(ptl);
 out:
diff --git a/mm/internal.h b/mm/internal.h
index a37e5b6f9d25..2524ec880e24 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -24,7 +24,8 @@
  */
 #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
 			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
-			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
+			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
+			__GFP_ATOMIC)
 
 /* The GFP flags allowed during early boot */
 #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 18b6a2b8d183..6845f9294696 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -508,7 +508,7 @@ void kasan_slab_alloc(struct kmem_cache *cache, void *object, gfp_t flags)
 	kasan_kmalloc(cache, object, cache->object_size, flags);
 }
 
-void kasan_poison_slab_free(struct kmem_cache *cache, void *object)
+static void kasan_poison_slab_free(struct kmem_cache *cache, void *object)
 {
 	unsigned long size = cache->object_size;
 	unsigned long rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
@@ -626,7 +626,7 @@ void kasan_krealloc(const void *object, size_t size, gfp_t flags)
 		kasan_kmalloc(page->slab_cache, object, size, flags);
 }
 
-void kasan_kfree(void *ptr)
+void kasan_poison_kfree(void *ptr)
 {
 	struct page *page;
 
@@ -636,7 +636,7 @@ void kasan_kfree(void *ptr)
 		kasan_poison_shadow(ptr, PAGE_SIZE << compound_order(page),
 				KASAN_FREE_PAGE);
 	else
-		kasan_slab_free(page->slab_cache, ptr);
+		kasan_poison_slab_free(page->slab_cache, ptr);
 }
 
 void kasan_kfree_large(const void *ptr)
@@ -763,8 +763,8 @@ static int kasan_mem_notifier(struct notifier_block *nb,
 
 static int __init kasan_memhotplug_init(void)
 {
-	pr_err("WARNING: KASAN doesn't support memory hot-add\n");
-	pr_err("Memory hot-add will be disabled\n");
+	pr_info("WARNING: KASAN doesn't support memory hot-add\n");
+	pr_info("Memory hot-add will be disabled\n");
 
 	hotplug_memory_notifier(kasan_mem_notifier, 0);
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index e6429926e957..04320d3adbef 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -307,8 +307,10 @@ static void hex_dump_object(struct seq_file *seq,
 	len = min_t(size_t, object->size, HEX_MAX_LINES * HEX_ROW_SIZE);
 
 	seq_printf(seq, "  hex dump (first %zu bytes):\n", len);
+	kasan_disable_current();
 	seq_hex_dump(seq, "    ", DUMP_PREFIX_NONE, HEX_ROW_SIZE,
 		     HEX_GROUP_SIZE, ptr, len, HEX_ASCII);
+	kasan_enable_current();
 }
 
 /*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 925b431f3f03..ac8664db3823 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1608,7 +1608,7 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 
 static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
-	if (!current->memcg_may_oom || current->memcg_in_oom)
+	if (!current->memcg_may_oom)
 		return;
 	/*
 	 * We are in the middle of the charge context here, so we
@@ -2896,6 +2896,7 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 	 * ordering is imposed by list_lru_node->lock taken by
 	 * memcg_drain_all_list_lrus().
 	 */
+	rcu_read_lock(); /* can be called from css_free w/o cgroup_mutex */
 	css_for_each_descendant_pre(css, &memcg->css) {
 		child = mem_cgroup_from_css(css);
 		BUG_ON(child->kmemcg_id != kmemcg_id);
@@ -2903,6 +2904,8 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 		if (!memcg->use_hierarchy)
 			break;
 	}
+	rcu_read_unlock();
+
 	memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id);
 
 	memcg_free_cache_id(kmemcg_id);
@@ -4200,7 +4203,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	return &memcg->css;
 fail:
 	mem_cgroup_free(memcg);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 
 static int
@@ -5541,6 +5544,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 	struct mem_cgroup *memcg;
 	unsigned int nr_pages;
 	bool compound;
+	unsigned long flags;
 
 	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
 	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
@@ -5571,10 +5575,10 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 
 	commit_charge(newpage, memcg, false);
 
-	local_irq_disable();
+	local_irq_save(flags);
 	mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages);
 	memcg_check_events(memcg, newpage);
-	local_irq_enable();
+	local_irq_restore(flags);
 }
 
 DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key);
diff --git a/mm/memory.c b/mm/memory.c
index 15322b73636b..cd1f29e4897e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2877,7 +2877,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
  * vm_ops->map_pages.
  */
 void do_set_pte(struct vm_area_struct *vma, unsigned long address,
-		struct page *page, pte_t *pte, bool write, bool anon, bool old)
+		struct page *page, pte_t *pte, bool write, bool anon)
 {
 	pte_t entry;
 
@@ -2885,8 +2885,6 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
 	entry = mk_pte(page, vma->vm_page_prot);
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-	if (old)
-		entry = pte_mkold(entry);
 	if (anon) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 		page_add_new_anon_rmap(page, vma, address, false);
@@ -2900,16 +2898,8 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
 	update_mmu_cache(vma, address, pte);
 }
 
-/*
- * If architecture emulates "accessed" or "young" bit without HW support,
- * there is no much gain with fault_around.
- */
 static unsigned long fault_around_bytes __read_mostly =
-#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-	PAGE_SIZE;
-#else
 	rounddown_pow_of_two(65536);
-#endif
 
 #ifdef CONFIG_DEBUG_FS
 static int fault_around_bytes_get(void *data, u64 *val)
@@ -3032,20 +3022,9 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
 		pte = pte_offset_map_lock(mm, pmd, address, &ptl);
-		if (!pte_same(*pte, orig_pte))
-			goto unlock_out;
 		do_fault_around(vma, address, pte, pgoff, flags);
-		/* Check if the fault is handled by faultaround */
-		if (!pte_same(*pte, orig_pte)) {
-			/*
-			 * Faultaround produce old pte, but the pte we've
-			 * handler fault for should be young.
-			 */
-			pte_t entry = pte_mkyoung(*pte);
-			if (ptep_set_access_flags(vma, address, pte, entry, 0))
-				update_mmu_cache(vma, address, pte);
+		if (!pte_same(*pte, orig_pte))
 			goto unlock_out;
-		}
 		pte_unmap_unlock(pte, ptl);
 	}
 
@@ -3060,7 +3039,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		put_page(fault_page);
 		return ret;
 	}
-	do_set_pte(vma, address, fault_page, pte, false, false, false);
+	do_set_pte(vma, address, fault_page, pte, false, false);
 	unlock_page(fault_page);
 unlock_out:
 	pte_unmap_unlock(pte, ptl);
@@ -3111,7 +3090,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 		goto uncharge_out;
 	}
-	do_set_pte(vma, address, new_page, pte, true, true, false);
+	do_set_pte(vma, address, new_page, pte, true, true);
 	mem_cgroup_commit_charge(new_page, memcg, false, false);
 	lru_cache_add_active_or_unevictable(new_page, vma);
 	pte_unmap_unlock(pte, ptl);
@@ -3164,7 +3143,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		put_page(fault_page);
 		return ret;
 	}
-	do_set_pte(vma, address, fault_page, pte, true, false, false);
+	do_set_pte(vma, address, fault_page, pte, true, false);
 	pte_unmap_unlock(pte, ptl);
 
 	if (set_page_dirty(fault_page))
diff --git a/mm/mempool.c b/mm/mempool.c
index 9e075f829d0d..8f65464da5de 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -104,20 +104,16 @@ static inline void poison_element(mempool_t *pool, void *element)
 
 static void kasan_poison_element(mempool_t *pool, void *element)
 {
-	if (pool->alloc == mempool_alloc_slab)
-		kasan_poison_slab_free(pool->pool_data, element);
-	if (pool->alloc == mempool_kmalloc)
-		kasan_kfree(element);
+	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
+		kasan_poison_kfree(element);
 	if (pool->alloc == mempool_alloc_pages)
 		kasan_free_pages(element, (unsigned long)pool->pool_data);
 }
 
 static void kasan_unpoison_element(mempool_t *pool, void *element, gfp_t flags)
 {
-	if (pool->alloc == mempool_alloc_slab)
-		kasan_slab_alloc(pool->pool_data, element, flags);
-	if (pool->alloc == mempool_kmalloc)
-		kasan_krealloc(element, (size_t)pool->pool_data, flags);
+	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
+		kasan_unpoison_slab(element);
 	if (pool->alloc == mempool_alloc_pages)
 		kasan_alloc_pages(element, (unsigned long)pool->pool_data);
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 9baf41c877ff..bd3fdc202e8b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -431,6 +431,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 
 	return MIGRATEPAGE_SUCCESS;
 }
+EXPORT_SYMBOL(migrate_page_move_mapping);
 
 /*
  * The expected number of remaining references is the same as that
@@ -586,6 +587,7 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 
 	mem_cgroup_migrate(page, newpage);
 }
+EXPORT_SYMBOL(migrate_page_copy);
 
 /************************************************************
  *                    Migration functions
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index dfb1ab61fb23..ddf74487f848 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -474,13 +474,8 @@ static bool __oom_reap_task(struct task_struct *tsk)
 	p = find_lock_task_mm(tsk);
 	if (!p)
 		goto unlock_oom;
-
 	mm = p->mm;
-	if (!atomic_inc_not_zero(&mm->mm_users)) {
-		task_unlock(p);
-		goto unlock_oom;
-	}
-
+	atomic_inc(&mm->mm_users);
 	task_unlock(p);
 
 	if (!down_read_trylock(&mm->mmap_sem)) {
@@ -625,8 +620,6 @@ void try_oom_reaper(struct task_struct *tsk)
 	if (atomic_read(&mm->mm_users) > 1) {
 		rcu_read_lock();
 		for_each_process(p) {
-			bool exiting;
-
 			if (!process_shares_mm(p, mm))
 				continue;
 			if (fatal_signal_pending(p))
@@ -636,10 +629,7 @@ void try_oom_reaper(struct task_struct *tsk)
 			 * If the task is exiting make sure the whole thread group
 			 * is exiting and cannot acces mm anymore.
 			 */
-			spin_lock_irq(&p->sighand->siglock);
-			exiting = signal_group_exit(p->signal);
-			spin_unlock_irq(&p->sighand->siglock);
-			if (exiting)
+			if (signal_group_exit(p->signal))
 				continue;
 
 			/* Give up */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index b9956fdee8f5..e2481949494c 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -373,8 +373,9 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
 	struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc);
 	unsigned long bytes = vm_dirty_bytes;
 	unsigned long bg_bytes = dirty_background_bytes;
-	unsigned long ratio = vm_dirty_ratio;
-	unsigned long bg_ratio = dirty_background_ratio;
+	/* convert ratios to per-PAGE_SIZE for higher precision */
+	unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100;
+	unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100;
 	unsigned long thresh;
 	unsigned long bg_thresh;
 	struct task_struct *tsk;
@@ -386,26 +387,28 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
 		/*
 		 * The byte settings can't be applied directly to memcg
 		 * domains.  Convert them to ratios by scaling against
-		 * globally available memory.
+		 * globally available memory.  As the ratios are in
+		 * per-PAGE_SIZE, they can be obtained by dividing bytes by
+		 * number of pages.
 		 */
 		if (bytes)
-			ratio = min(DIV_ROUND_UP(bytes, PAGE_SIZE) * 100 /
-				    global_avail, 100UL);
+			ratio = min(DIV_ROUND_UP(bytes, global_avail),
+				    PAGE_SIZE);
 		if (bg_bytes)
-			bg_ratio = min(DIV_ROUND_UP(bg_bytes, PAGE_SIZE) * 100 /
-				       global_avail, 100UL);
+			bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail),
+				       PAGE_SIZE);
 		bytes = bg_bytes = 0;
 	}
 
 	if (bytes)
 		thresh = DIV_ROUND_UP(bytes, PAGE_SIZE);
 	else
-		thresh = (ratio * available_memory) / 100;
+		thresh = (ratio * available_memory) / PAGE_SIZE;
 
 	if (bg_bytes)
 		bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE);
 	else
-		bg_thresh = (bg_ratio * available_memory) / 100;
+		bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
 
 	if (bg_thresh >= thresh)
 		bg_thresh = thresh / 2;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f8f3bfc435ee..6903b695ebae 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -656,6 +656,9 @@ static inline void set_page_guard(struct zone *zone, struct page *page,
 		return;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
 
 	INIT_LIST_HEAD(&page->lru);
@@ -673,6 +676,9 @@ static inline void clear_page_guard(struct zone *zone, struct page *page,
 		return;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
 
 	set_page_private(page, 0);
@@ -2609,11 +2615,12 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 				page = list_last_entry(list, struct page, lru);
 			else
 				page = list_first_entry(list, struct page, lru);
-		} while (page && check_new_pcp(page));
 
-		__dec_zone_state(zone, NR_ALLOC_BATCH);
-		list_del(&page->lru);
-		pcp->count--;
+			__dec_zone_state(zone, NR_ALLOC_BATCH);
+			list_del(&page->lru);
+			pcp->count--;
+
+		} while (check_new_pcp(page));
 	} else {
 		/*
 		 * We most definitely don't want callers attempting to
@@ -3023,6 +3030,7 @@ reset_fair:
 		apply_fair = false;
 		fair_skipped = false;
 		reset_alloc_batches(ac->preferred_zoneref->zone);
+		z = ac->preferred_zoneref;
 		goto zonelist_scan;
 	}
 
@@ -3596,6 +3604,17 @@ retry:
 	 */
 	alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
+	/*
+	 * Reset the zonelist iterators if memory policies can be ignored.
+	 * These allocations are high priority and system rather than user
+	 * orientated.
+	 */
+	if ((alloc_flags & ALLOC_NO_WATERMARKS) || !(alloc_flags & ALLOC_CPUSET)) {
+		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
+		ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+					ac->high_zoneidx, ac->nodemask);
+	}
+
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, order,
 				alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
@@ -3604,12 +3623,6 @@ retry:
 
 	/* Allocate without watermarks if the context allows */
 	if (alloc_flags & ALLOC_NO_WATERMARKS) {
-		/*
-		 * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
-		 * the allocation is high priority and these type of
-		 * allocations are system rather than user orientated
-		 */
-		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
 		page = get_page_from_freelist(gfp_mask, order,
 						ALLOC_NO_WATERMARKS, ac);
 		if (page)
@@ -3808,7 +3821,11 @@ retry_cpuset:
 	/* Dirty zone balancing only done in the fast path */
 	ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
-	/* The preferred zone is used for statistics later */
+	/*
+	 * The preferred zone is used for statistics but crucially it is
+	 * also used as the starting point for the zonelist iterator. It
+	 * may get reset for allocations that ignore memory policies.
+	 */
 	ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
 					ac.high_zoneidx, ac.nodemask);
 	if (!ac.preferred_zoneref) {
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 792b56da13d8..fedeba88c9cb 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -55,6 +55,8 @@ void __reset_page_owner(struct page *page, unsigned int order)
 
 	for (i = 0; i < (1 << order); i++) {
 		page_ext = lookup_page_ext(page + i);
+		if (unlikely(!page_ext))
+			continue;
 		__clear_bit(PAGE_EXT_OWNER, &page_ext->flags);
 	}
 }
@@ -62,6 +64,7 @@ void __reset_page_owner(struct page *page, unsigned int order)
 void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
+
 	struct stack_trace trace = {
 		.nr_entries = 0,
 		.max_entries = ARRAY_SIZE(page_ext->trace_entries),
@@ -69,6 +72,9 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
 		.skip = 3,
 	};
 
+	if (unlikely(!page_ext))
+		return;
+
 	save_stack_trace(&trace);
 
 	page_ext->order = order;
@@ -82,6 +88,8 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
 void __set_page_owner_migrate_reason(struct page *page, int reason)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
 
 	page_ext->last_migrate_reason = reason;
 }
@@ -89,6 +97,12 @@ void __set_page_owner_migrate_reason(struct page *page, int reason)
 gfp_t __get_page_owner_gfp(struct page *page)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		/*
+		 * The caller just returns 0 if no valid gfp
+		 * So return 0 here too.
+		 */
+		return 0;
 
 	return page_ext->gfp_mask;
 }
@@ -99,6 +113,9 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage)
 	struct page_ext *new_ext = lookup_page_ext(newpage);
 	int i;
 
+	if (unlikely(!old_ext || !new_ext))
+		return;
+
 	new_ext->order = old_ext->order;
 	new_ext->gfp_mask = old_ext->gfp_mask;
 	new_ext->nr_entries = old_ext->nr_entries;
@@ -190,8 +207,15 @@ void __dump_page_owner(struct page *page)
 		.nr_entries = page_ext->nr_entries,
 		.entries = &page_ext->trace_entries[0],
 	};
-	gfp_t gfp_mask = page_ext->gfp_mask;
-	int mt = gfpflags_to_migratetype(gfp_mask);
+	gfp_t gfp_mask;
+	int mt;
+
+	if (unlikely(!page_ext)) {
+		pr_alert("There is not page extension available.\n");
+		return;
+	}
+	gfp_mask = page_ext->gfp_mask;
+	mt = gfpflags_to_migratetype(gfp_mask);
 
 	if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) {
 		pr_alert("page_owner info is not active (free page?)\n");
@@ -251,6 +275,8 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		}
 
 		page_ext = lookup_page_ext(page);
+		if (unlikely(!page_ext))
+			continue;
 
 		/*
 		 * Some pages could be missed by concurrent allocation or free,
@@ -317,6 +343,8 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
 				continue;
 
 			page_ext = lookup_page_ext(page);
+			if (unlikely(!page_ext))
+				continue;
 
 			/* Maybe overraping zone */
 			if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
diff --git a/mm/page_poison.c b/mm/page_poison.c
index 1eae5fad2446..2e647c65916b 100644
--- a/mm/page_poison.c
+++ b/mm/page_poison.c
@@ -54,6 +54,9 @@ static inline void set_page_poison(struct page *page)
 	struct page_ext *page_ext;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__set_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
 }
 
@@ -62,6 +65,9 @@ static inline void clear_page_poison(struct page *page)
 	struct page_ext *page_ext;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__clear_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
 }
 
@@ -70,7 +76,7 @@ bool page_is_poisoned(struct page *page)
 	struct page_ext *page_ext;
 
 	page_ext = lookup_page_ext(page);
-	if (!page_ext)
+	if (unlikely(!page_ext))
 		return false;
 
 	return test_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
diff --git a/mm/percpu.c b/mm/percpu.c
index 0c59684f1ff2..9903830aaebb 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -112,7 +112,7 @@ struct pcpu_chunk {
 	int			map_used;	/* # of map entries used before the sentry */
 	int			map_alloc;	/* # of map entries allocated */
 	int			*map;		/* allocation map */
-	struct work_struct	map_extend_work;/* async ->map[] extension */
+	struct list_head	map_extend_list;/* on pcpu_map_extend_chunks */
 
 	void			*data;		/* chunk data */
 	int			first_free;	/* no free below this */
@@ -162,10 +162,13 @@ static struct pcpu_chunk *pcpu_reserved_chunk;
 static int pcpu_reserved_chunk_limit;
 
 static DEFINE_SPINLOCK(pcpu_lock);	/* all internal data structures */
-static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop */
+static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop, map ext */
 
 static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
 
+/* chunks which need their map areas extended, protected by pcpu_lock */
+static LIST_HEAD(pcpu_map_extend_chunks);
+
 /*
  * The number of empty populated pages, protected by pcpu_lock.  The
  * reserved chunk doesn't contribute to the count.
@@ -395,13 +398,19 @@ static int pcpu_need_to_extend(struct pcpu_chunk *chunk, bool is_atomic)
 {
 	int margin, new_alloc;
 
+	lockdep_assert_held(&pcpu_lock);
+
 	if (is_atomic) {
 		margin = 3;
 
 		if (chunk->map_alloc <
-		    chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW &&
-		    pcpu_async_enabled)
-			schedule_work(&chunk->map_extend_work);
+		    chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW) {
+			if (list_empty(&chunk->map_extend_list)) {
+				list_add_tail(&chunk->map_extend_list,
+					      &pcpu_map_extend_chunks);
+				pcpu_schedule_balance_work();
+			}
+		}
 	} else {
 		margin = PCPU_ATOMIC_MAP_MARGIN_HIGH;
 	}
@@ -435,6 +444,8 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
 	size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
 	unsigned long flags;
 
+	lockdep_assert_held(&pcpu_alloc_mutex);
+
 	new = pcpu_mem_zalloc(new_size);
 	if (!new)
 		return -ENOMEM;
@@ -467,20 +478,6 @@ out_unlock:
 	return 0;
 }
 
-static void pcpu_map_extend_workfn(struct work_struct *work)
-{
-	struct pcpu_chunk *chunk = container_of(work, struct pcpu_chunk,
-						map_extend_work);
-	int new_alloc;
-
-	spin_lock_irq(&pcpu_lock);
-	new_alloc = pcpu_need_to_extend(chunk, false);
-	spin_unlock_irq(&pcpu_lock);
-
-	if (new_alloc)
-		pcpu_extend_area_map(chunk, new_alloc);
-}
-
 /**
  * pcpu_fit_in_area - try to fit the requested allocation in a candidate area
  * @chunk: chunk the candidate area belongs to
@@ -740,7 +737,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	chunk->map_used = 1;
 
 	INIT_LIST_HEAD(&chunk->list);
-	INIT_WORK(&chunk->map_extend_work, pcpu_map_extend_workfn);
+	INIT_LIST_HEAD(&chunk->map_extend_list);
 	chunk->free_size = pcpu_unit_size;
 	chunk->contig_hint = pcpu_unit_size;
 
@@ -895,6 +892,9 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 		return NULL;
 	}
 
+	if (!is_atomic)
+		mutex_lock(&pcpu_alloc_mutex);
+
 	spin_lock_irqsave(&pcpu_lock, flags);
 
 	/* serve reserved allocations from the reserved chunk if available */
@@ -967,12 +967,9 @@ restart:
 	if (is_atomic)
 		goto fail;
 
-	mutex_lock(&pcpu_alloc_mutex);
-
 	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
 		chunk = pcpu_create_chunk();
 		if (!chunk) {
-			mutex_unlock(&pcpu_alloc_mutex);
 			err = "failed to allocate new chunk";
 			goto fail;
 		}
@@ -983,7 +980,6 @@ restart:
 		spin_lock_irqsave(&pcpu_lock, flags);
 	}
 
-	mutex_unlock(&pcpu_alloc_mutex);
 	goto restart;
 
 area_found:
@@ -993,8 +989,6 @@ area_found:
 	if (!is_atomic) {
 		int page_start, page_end, rs, re;
 
-		mutex_lock(&pcpu_alloc_mutex);
-
 		page_start = PFN_DOWN(off);
 		page_end = PFN_UP(off + size);
 
@@ -1005,7 +999,6 @@ area_found:
 
 			spin_lock_irqsave(&pcpu_lock, flags);
 			if (ret) {
-				mutex_unlock(&pcpu_alloc_mutex);
 				pcpu_free_area(chunk, off, &occ_pages);
 				err = "failed to populate";
 				goto fail_unlock;
@@ -1045,6 +1038,8 @@ fail:
 		/* see the flag handling in pcpu_blance_workfn() */
 		pcpu_atomic_alloc_failed = true;
 		pcpu_schedule_balance_work();
+	} else {
+		mutex_unlock(&pcpu_alloc_mutex);
 	}
 	return NULL;
 }
@@ -1129,6 +1124,7 @@ static void pcpu_balance_workfn(struct work_struct *work)
 		if (chunk == list_first_entry(free_head, struct pcpu_chunk, list))
 			continue;
 
+		list_del_init(&chunk->map_extend_list);
 		list_move(&chunk->list, &to_free);
 	}
 
@@ -1146,6 +1142,25 @@ static void pcpu_balance_workfn(struct work_struct *work)
 		pcpu_destroy_chunk(chunk);
 	}
 
+	/* service chunks which requested async area map extension */
+	do {
+		int new_alloc = 0;
+
+		spin_lock_irq(&pcpu_lock);
+
+		chunk = list_first_entry_or_null(&pcpu_map_extend_chunks,
+					struct pcpu_chunk, map_extend_list);
+		if (chunk) {
+			list_del_init(&chunk->map_extend_list);
+			new_alloc = pcpu_need_to_extend(chunk, false);
+		}
+
+		spin_unlock_irq(&pcpu_lock);
+
+		if (new_alloc)
+			pcpu_extend_area_map(chunk, new_alloc);
+	} while (chunk);
+
 	/*
 	 * Ensure there are certain number of free populated pages for
 	 * atomic allocs.  Fill up from the most packed so that atomic
@@ -1644,7 +1659,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	 */
 	schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 	INIT_LIST_HEAD(&schunk->list);
-	INIT_WORK(&schunk->map_extend_work, pcpu_map_extend_workfn);
+	INIT_LIST_HEAD(&schunk->map_extend_list);
 	schunk->base_addr = base_addr;
 	schunk->map = smap;
 	schunk->map_alloc = ARRAY_SIZE(smap);
@@ -1673,7 +1688,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	if (dyn_size) {
 		dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 		INIT_LIST_HEAD(&dchunk->list);
-		INIT_WORK(&dchunk->map_extend_work, pcpu_map_extend_workfn);
+		INIT_LIST_HEAD(&dchunk->map_extend_list);
 		dchunk->base_addr = base_addr;
 		dchunk->map = dmap;
 		dchunk->map_alloc = ARRAY_SIZE(dmap);
diff --git a/mm/shmem.c b/mm/shmem.c
index a36144909b28..24463b67b6ef 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2227,7 +2227,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 			/* Remove the !PageUptodate pages we added */
 			shmem_undo_range(inode,
 				(loff_t)start << PAGE_SHIFT,
-				(loff_t)index << PAGE_SHIFT, true);
+				((loff_t)index << PAGE_SHIFT) - 1, true);
 			goto undone;
 		}
 
diff --git a/mm/swap.c b/mm/swap.c
index 95916142fc46..90530ff8ed16 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -242,7 +242,7 @@ void rotate_reclaimable_page(struct page *page)
 		get_page(page);
 		local_irq_save(flags);
 		pvec = this_cpu_ptr(&lru_rotate_pvecs);
-		if (!pagevec_add(pvec, page))
+		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_move_tail(pvec);
 		local_irq_restore(flags);
 	}
@@ -296,7 +296,7 @@ void activate_page(struct page *page)
 		struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
 
 		get_page(page);
-		if (!pagevec_add(pvec, page))
+		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, __activate_page, NULL);
 		put_cpu_var(activate_page_pvecs);
 	}
@@ -391,9 +391,8 @@ static void __lru_cache_add(struct page *page)
 	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
 
 	get_page(page);
-	if (!pagevec_space(pvec))
+	if (!pagevec_add(pvec, page) || PageCompound(page))
 		__pagevec_lru_add(pvec);
-	pagevec_add(pvec, page);
 	put_cpu_var(lru_add_pvec);
 }
 
@@ -628,7 +627,7 @@ void deactivate_file_page(struct page *page)
 	if (likely(get_page_unless_zero(page))) {
 		struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs);
 
-		if (!pagevec_add(pvec, page))
+		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
 		put_cpu_var(lru_deactivate_file_pvecs);
 	}
@@ -648,7 +647,7 @@ void deactivate_page(struct page *page)
 		struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
 
 		get_page(page);
-		if (!pagevec_add(pvec, page))
+		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
 		put_cpu_var(lru_deactivate_pvecs);
 	}
@@ -667,6 +666,24 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
 
 static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
 
+/*
+ * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM
+ * workqueue, aiding in getting memory freed.
+ */
+static struct workqueue_struct *lru_add_drain_wq;
+
+static int __init lru_init(void)
+{
+	lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0);
+
+	if (WARN(!lru_add_drain_wq,
+		"Failed to create workqueue lru_add_drain_wq"))
+		return -ENOMEM;
+
+	return 0;
+}
+early_initcall(lru_init);
+
 void lru_add_drain_all(void)
 {
 	static DEFINE_MUTEX(lock);
@@ -686,7 +703,7 @@ void lru_add_drain_all(void)
 		    pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
 		    need_activate_page_drain(cpu)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
-			schedule_work_on(cpu, work);
+			queue_work_on(cpu, lru_add_drain_wq, work);
 			cpumask_set_cpu(cpu, &has_work);
 		}
 	}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 0d457e7db8d6..c99463ac02fb 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -252,7 +252,10 @@ static inline void free_swap_cache(struct page *page)
 void free_page_and_swap_cache(struct page *page)
 {
 	free_swap_cache(page);
-	put_page(page);
+	if (is_huge_zero_page(page))
+		put_huge_zero_page();
+	else
+		put_page(page);
 }
 
 /*
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index cf7ad1a53be0..e11475cdeb7a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1105,7 +1105,7 @@ EXPORT_SYMBOL_GPL(vm_unmap_aliases);
  */
 void vm_unmap_ram(const void *mem, unsigned int count)
 {
-	unsigned long size = count << PAGE_SHIFT;
+	unsigned long size = (unsigned long)count << PAGE_SHIFT;
 	unsigned long addr = (unsigned long)mem;
 
 	BUG_ON(!addr);
@@ -1140,7 +1140,7 @@ EXPORT_SYMBOL(vm_unmap_ram);
  */
 void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
 {
-	unsigned long size = count << PAGE_SHIFT;
+	unsigned long size = (unsigned long)count << PAGE_SHIFT;
 	unsigned long addr;
 	void *mem;
 
@@ -1574,14 +1574,15 @@ void *vmap(struct page **pages, unsigned int count,
 		unsigned long flags, pgprot_t prot)
 {
 	struct vm_struct *area;
+	unsigned long size;		/* In bytes */
 
 	might_sleep();
 
 	if (count > totalram_pages)
 		return NULL;
 
-	area = get_vm_area_caller((count << PAGE_SHIFT), flags,
-					__builtin_return_address(0));
+	size = (unsigned long)count << PAGE_SHIFT;
+	area = get_vm_area_caller(size, flags, __builtin_return_address(0));
 	if (!area)
 		return NULL;
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 77e42ef388c2..cb2a67bb4158 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1061,6 +1061,8 @@ static void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 				continue;
 
 			page_ext = lookup_page_ext(page);
+			if (unlikely(!page_ext))
+				continue;
 
 			if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
 				continue;
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 34917d55d311..8f9e89ca1d31 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -412,7 +412,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		/* HEADLESS page stored */
 		bud = HEADLESS;
 	} else {
-		bud = (handle - zhdr->first_num) & BUDDY_MASK;
+		bud = handle_to_buddy(handle);
 
 		switch (bud) {
 		case FIRST:
@@ -572,15 +572,19 @@ next:
 			pool->pages_nr--;
 			spin_unlock(&pool->lock);
 			return 0;
-		} else if (zhdr->first_chunks != 0 &&
-			   zhdr->last_chunks != 0 && zhdr->middle_chunks != 0) {
-			/* Full, add to buddied list */
-			list_add(&zhdr->buddy, &pool->buddied);
-		} else if (!test_bit(PAGE_HEADLESS, &page->private)) {
-			z3fold_compact_page(zhdr);
-			/* add to unbuddied list */
-			freechunks = num_free_chunks(zhdr);
-			list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
+		}  else if (!test_bit(PAGE_HEADLESS, &page->private)) {
+			if (zhdr->first_chunks != 0 &&
+			    zhdr->last_chunks != 0 &&
+			    zhdr->middle_chunks != 0) {
+				/* Full, add to buddied list */
+				list_add(&zhdr->buddy, &pool->buddied);
+			} else {
+				z3fold_compact_page(zhdr);
+				/* add to unbuddied list */
+				freechunks = num_free_chunks(zhdr);
+				list_add(&zhdr->buddy,
+					 &pool->unbuddied[freechunks]);
+			}
 		}
 
 		/* add to beginning of LRU */
diff --git a/net/6lowpan/6lowpan_i.h b/net/6lowpan/6lowpan_i.h
index 97ecc27aeca6..a67caee11929 100644
--- a/net/6lowpan/6lowpan_i.h
+++ b/net/6lowpan/6lowpan_i.h
@@ -12,6 +12,10 @@ static inline bool lowpan_is_ll(const struct net_device *dev,
 	return lowpan_dev(dev)->lltype == lltype;
 }
 
+extern const struct ndisc_ops lowpan_ndisc_ops;
+
+int addrconf_ifid_802154_6lowpan(u8 *eui, struct net_device *dev);
+
 #ifdef CONFIG_6LOWPAN_DEBUGFS
 int lowpan_dev_debugfs_init(struct net_device *dev);
 void lowpan_dev_debugfs_exit(struct net_device *dev);
diff --git a/net/6lowpan/Makefile b/net/6lowpan/Makefile
index e44f3bf2dd42..12d131ab2324 100644
--- a/net/6lowpan/Makefile
+++ b/net/6lowpan/Makefile
@@ -1,6 +1,6 @@
 obj-$(CONFIG_6LOWPAN) += 6lowpan.o
 
-6lowpan-y := core.o iphc.o nhc.o
+6lowpan-y := core.o iphc.o nhc.o ndisc.o
 6lowpan-$(CONFIG_6LOWPAN_DEBUGFS) += debugfs.o
 
 #rfc6282 nhcs
diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c
index 7a240b3eaed1..5945f7e19c67 100644
--- a/net/6lowpan/core.c
+++ b/net/6lowpan/core.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 
 #include <net/6lowpan.h>
+#include <net/addrconf.h>
 
 #include "6lowpan_i.h"
 
@@ -33,6 +34,8 @@ int lowpan_register_netdevice(struct net_device *dev,
 	for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++)
 		lowpan_dev(dev)->ctx.table[i].id = i;
 
+	dev->ndisc_ops = &lowpan_ndisc_ops;
+
 	ret = register_netdevice(dev);
 	if (ret < 0)
 		return ret;
@@ -72,16 +75,61 @@ void lowpan_unregister_netdev(struct net_device *dev)
 }
 EXPORT_SYMBOL(lowpan_unregister_netdev);
 
+int addrconf_ifid_802154_6lowpan(u8 *eui, struct net_device *dev)
+{
+	struct wpan_dev *wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr;
+
+	/* Set short_addr autoconfiguration if short_addr is present only */
+	if (!lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr))
+		return -1;
+
+	/* For either address format, all zero addresses MUST NOT be used */
+	if (wpan_dev->pan_id == cpu_to_le16(0x0000) &&
+	    wpan_dev->short_addr == cpu_to_le16(0x0000))
+		return -1;
+
+	/* Alternatively, if no PAN ID is known, 16 zero bits may be used */
+	if (wpan_dev->pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST))
+		memset(eui, 0, 2);
+	else
+		ieee802154_le16_to_be16(eui, &wpan_dev->pan_id);
+
+	/* The "Universal/Local" (U/L) bit shall be set to zero */
+	eui[0] &= ~2;
+	eui[2] = 0;
+	eui[3] = 0xFF;
+	eui[4] = 0xFE;
+	eui[5] = 0;
+	ieee802154_le16_to_be16(&eui[6], &wpan_dev->short_addr);
+	return 0;
+}
+
 static int lowpan_event(struct notifier_block *unused,
 			unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct inet6_dev *idev;
+	struct in6_addr addr;
 	int i;
 
 	if (dev->type != ARPHRD_6LOWPAN)
 		return NOTIFY_DONE;
 
+	idev = __in6_dev_get(dev);
+	if (!idev)
+		return NOTIFY_DONE;
+
 	switch (event) {
+	case NETDEV_UP:
+	case NETDEV_CHANGE:
+		/* (802.15.4 6LoWPAN short address slaac handling */
+		if (lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154) &&
+		    addrconf_ifid_802154_6lowpan(addr.s6_addr + 8, dev) == 0) {
+			__ipv6_addr_set_half(&addr.s6_addr32[0],
+					     htonl(0xFE800000), 0);
+			addrconf_add_linklocal(idev, &addr, 0);
+		}
+		break;
 	case NETDEV_DOWN:
 		for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++)
 			clear_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE,
@@ -112,8 +160,6 @@ static int __init lowpan_module_init(void)
 		return ret;
 	}
 
-	request_module_nowait("ipv6");
-
 	request_module_nowait("nhc_dest");
 	request_module_nowait("nhc_fragment");
 	request_module_nowait("nhc_hop");
diff --git a/net/6lowpan/debugfs.c b/net/6lowpan/debugfs.c
index acbaa3db493b..24915e0bb9ea 100644
--- a/net/6lowpan/debugfs.c
+++ b/net/6lowpan/debugfs.c
@@ -245,6 +245,41 @@ static const struct file_operations lowpan_context_fops = {
 	.release	= single_release,
 };
 
+static int lowpan_short_addr_get(void *data, u64 *val)
+{
+	struct wpan_dev *wdev = data;
+
+	rtnl_lock();
+	*val = le16_to_cpu(wdev->short_addr);
+	rtnl_unlock();
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(lowpan_short_addr_fops, lowpan_short_addr_get,
+			NULL, "0x%04llx\n");
+
+static int lowpan_dev_debugfs_802154_init(const struct net_device *dev,
+					  struct lowpan_dev *ldev)
+{
+	struct dentry *dentry, *root;
+
+	if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+		return 0;
+
+	root = debugfs_create_dir("ieee802154", ldev->iface_debugfs);
+	if (!root)
+		return -EINVAL;
+
+	dentry = debugfs_create_file("short_addr", 0444, root,
+				     lowpan_802154_dev(dev)->wdev->ieee802154_ptr,
+				     &lowpan_short_addr_fops);
+	if (!dentry)
+		return -EINVAL;
+
+	return 0;
+}
+
 int lowpan_dev_debugfs_init(struct net_device *dev)
 {
 	struct lowpan_dev *ldev = lowpan_dev(dev);
@@ -272,6 +307,10 @@ int lowpan_dev_debugfs_init(struct net_device *dev)
 			goto remove_root;
 	}
 
+	ret = lowpan_dev_debugfs_802154_init(dev, ldev);
+	if (ret < 0)
+		goto remove_root;
+
 	return 0;
 
 remove_root:
diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c
index 8501dd532fe1..79f1fa22509a 100644
--- a/net/6lowpan/iphc.c
+++ b/net/6lowpan/iphc.c
@@ -761,22 +761,75 @@ static const u8 lowpan_iphc_dam_to_sam_value[] = {
 	[LOWPAN_IPHC_DAM_11] = LOWPAN_IPHC_SAM_11,
 };
 
-static u8 lowpan_compress_ctx_addr(u8 **hc_ptr, const struct in6_addr *ipaddr,
+static inline bool
+lowpan_iphc_compress_ctx_802154_lladdr(const struct in6_addr *ipaddr,
+				       const struct lowpan_iphc_ctx *ctx,
+				       const void *lladdr)
+{
+	const struct ieee802154_addr *addr = lladdr;
+	unsigned char extended_addr[EUI64_ADDR_LEN];
+	bool lladdr_compress = false;
+	struct in6_addr tmp = {};
+
+	switch (addr->mode) {
+	case IEEE802154_ADDR_LONG:
+		ieee802154_le64_to_be64(&extended_addr, &addr->extended_addr);
+		/* check for SAM/DAM = 11 */
+		memcpy(&tmp.s6_addr[8], &extended_addr, EUI64_ADDR_LEN);
+		/* second bit-flip (Universe/Local) is done according RFC2464 */
+		tmp.s6_addr[8] ^= 0x02;
+		/* context information are always used */
+		ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
+		if (ipv6_addr_equal(&tmp, ipaddr))
+			lladdr_compress = true;
+		break;
+	case IEEE802154_ADDR_SHORT:
+		tmp.s6_addr[11] = 0xFF;
+		tmp.s6_addr[12] = 0xFE;
+		ieee802154_le16_to_be16(&tmp.s6_addr16[7],
+					&addr->short_addr);
+		/* context information are always used */
+		ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
+		if (ipv6_addr_equal(&tmp, ipaddr))
+			lladdr_compress = true;
+		break;
+	default:
+		/* should never handled and filtered by 802154 6lowpan */
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return lladdr_compress;
+}
+
+static u8 lowpan_compress_ctx_addr(u8 **hc_ptr, const struct net_device *dev,
+				   const struct in6_addr *ipaddr,
 				   const struct lowpan_iphc_ctx *ctx,
 				   const unsigned char *lladdr, bool sam)
 {
 	struct in6_addr tmp = {};
 	u8 dam;
 
-	/* check for SAM/DAM = 11 */
-	memcpy(&tmp.s6_addr[8], lladdr, 8);
-	/* second bit-flip (Universe/Local) is done according RFC2464 */
-	tmp.s6_addr[8] ^= 0x02;
-	/* context information are always used */
-	ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
-	if (ipv6_addr_equal(&tmp, ipaddr)) {
-		dam = LOWPAN_IPHC_DAM_11;
-		goto out;
+	switch (lowpan_dev(dev)->lltype) {
+	case LOWPAN_LLTYPE_IEEE802154:
+		if (lowpan_iphc_compress_ctx_802154_lladdr(ipaddr, ctx,
+							   lladdr)) {
+			dam = LOWPAN_IPHC_DAM_11;
+			goto out;
+		}
+		break;
+	default:
+		/* check for SAM/DAM = 11 */
+		memcpy(&tmp.s6_addr[8], lladdr, EUI64_ADDR_LEN);
+		/* second bit-flip (Universe/Local) is done according RFC2464 */
+		tmp.s6_addr[8] ^= 0x02;
+		/* context information are always used */
+		ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
+		if (ipv6_addr_equal(&tmp, ipaddr)) {
+			dam = LOWPAN_IPHC_DAM_11;
+			goto out;
+		}
+		break;
 	}
 
 	memset(&tmp, 0, sizeof(tmp));
@@ -813,28 +866,85 @@ out:
 		return dam;
 }
 
-static u8 lowpan_compress_addr_64(u8 **hc_ptr, const struct in6_addr *ipaddr,
+static inline bool
+lowpan_iphc_compress_802154_lladdr(const struct in6_addr *ipaddr,
+				   const void *lladdr)
+{
+	const struct ieee802154_addr *addr = lladdr;
+	unsigned char extended_addr[EUI64_ADDR_LEN];
+	bool lladdr_compress = false;
+	struct in6_addr tmp = {};
+
+	switch (addr->mode) {
+	case IEEE802154_ADDR_LONG:
+		ieee802154_le64_to_be64(&extended_addr, &addr->extended_addr);
+		if (is_addr_mac_addr_based(ipaddr, extended_addr))
+			lladdr_compress = true;
+		break;
+	case IEEE802154_ADDR_SHORT:
+		/* fe:80::ff:fe00:XXXX
+		 *                \__/
+		 *             short_addr
+		 *
+		 * Universe/Local bit is zero.
+		 */
+		tmp.s6_addr[0] = 0xFE;
+		tmp.s6_addr[1] = 0x80;
+		tmp.s6_addr[11] = 0xFF;
+		tmp.s6_addr[12] = 0xFE;
+		ieee802154_le16_to_be16(&tmp.s6_addr16[7],
+					&addr->short_addr);
+		if (ipv6_addr_equal(&tmp, ipaddr))
+			lladdr_compress = true;
+		break;
+	default:
+		/* should never handled and filtered by 802154 6lowpan */
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return lladdr_compress;
+}
+
+static u8 lowpan_compress_addr_64(u8 **hc_ptr, const struct net_device *dev,
+				  const struct in6_addr *ipaddr,
 				  const unsigned char *lladdr, bool sam)
 {
-	u8 dam = LOWPAN_IPHC_DAM_00;
+	u8 dam = LOWPAN_IPHC_DAM_01;
 
-	if (is_addr_mac_addr_based(ipaddr, lladdr)) {
-		dam = LOWPAN_IPHC_DAM_11; /* 0-bits */
-		pr_debug("address compression 0 bits\n");
-	} else if (lowpan_is_iid_16_bit_compressable(ipaddr)) {
+	switch (lowpan_dev(dev)->lltype) {
+	case LOWPAN_LLTYPE_IEEE802154:
+		if (lowpan_iphc_compress_802154_lladdr(ipaddr, lladdr)) {
+			dam = LOWPAN_IPHC_DAM_11; /* 0-bits */
+			pr_debug("address compression 0 bits\n");
+			goto out;
+		}
+		break;
+	default:
+		if (is_addr_mac_addr_based(ipaddr, lladdr)) {
+			dam = LOWPAN_IPHC_DAM_11; /* 0-bits */
+			pr_debug("address compression 0 bits\n");
+			goto out;
+		}
+		break;
+	}
+
+	if (lowpan_is_iid_16_bit_compressable(ipaddr)) {
 		/* compress IID to 16 bits xxxx::XXXX */
 		lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr16[7], 2);
 		dam = LOWPAN_IPHC_DAM_10; /* 16-bits */
 		raw_dump_inline(NULL, "Compressed ipv6 addr is (16 bits)",
 				*hc_ptr - 2, 2);
-	} else {
-		/* do not compress IID => xxxx::IID */
-		lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr16[4], 8);
-		dam = LOWPAN_IPHC_DAM_01; /* 64-bits */
-		raw_dump_inline(NULL, "Compressed ipv6 addr is (64 bits)",
-				*hc_ptr - 8, 8);
+		goto out;
 	}
 
+	/* do not compress IID => xxxx::IID */
+	lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr16[4], 8);
+	raw_dump_inline(NULL, "Compressed ipv6 addr is (64 bits)",
+			*hc_ptr - 8, 8);
+
+out:
+
 	if (sam)
 		return lowpan_iphc_dam_to_sam_value[dam];
 	else
@@ -1013,9 +1123,6 @@ int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev,
 	iphc0 = LOWPAN_DISPATCH_IPHC;
 	iphc1 = 0;
 
-	raw_dump_inline(__func__, "saddr", saddr, EUI64_ADDR_LEN);
-	raw_dump_inline(__func__, "daddr", daddr, EUI64_ADDR_LEN);
-
 	raw_dump_table(__func__, "sending raw skb network uncompressed packet",
 		       skb->data, skb->len);
 
@@ -1088,14 +1195,15 @@ int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev,
 		iphc1 |= LOWPAN_IPHC_SAC;
 	} else {
 		if (sci) {
-			iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, &hdr->saddr,
+			iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, dev,
+							  &hdr->saddr,
 							  &sci_entry, saddr,
 							  true);
 			iphc1 |= LOWPAN_IPHC_SAC;
 		} else {
 			if (ipv6_saddr_type & IPV6_ADDR_LINKLOCAL &&
 			    lowpan_is_linklocal_zero_padded(hdr->saddr)) {
-				iphc1 |= lowpan_compress_addr_64(&hc_ptr,
+				iphc1 |= lowpan_compress_addr_64(&hc_ptr, dev,
 								 &hdr->saddr,
 								 saddr, true);
 				pr_debug("source address unicast link-local %pI6c iphc1 0x%02x\n",
@@ -1123,14 +1231,15 @@ int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev,
 		}
 	} else {
 		if (dci) {
-			iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, &hdr->daddr,
+			iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, dev,
+							  &hdr->daddr,
 							  &dci_entry, daddr,
 							  false);
 			iphc1 |= LOWPAN_IPHC_DAC;
 		} else {
 			if (ipv6_daddr_type & IPV6_ADDR_LINKLOCAL &&
 			    lowpan_is_linklocal_zero_padded(hdr->daddr)) {
-				iphc1 |= lowpan_compress_addr_64(&hc_ptr,
+				iphc1 |= lowpan_compress_addr_64(&hc_ptr, dev,
 								 &hdr->daddr,
 								 daddr, false);
 				pr_debug("dest address unicast link-local %pI6c iphc1 0x%02x\n",
diff --git a/net/6lowpan/ndisc.c b/net/6lowpan/ndisc.c
new file mode 100644
index 000000000000..ae1d4199aa4c
--- /dev/null
+++ b/net/6lowpan/ndisc.c
@@ -0,0 +1,234 @@
+/* This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors:
+ * (C) 2016 Pengutronix, Alexander Aring <[email protected]>
+ */
+
+#include <net/6lowpan.h>
+#include <net/addrconf.h>
+#include <net/ndisc.h>
+
+#include "6lowpan_i.h"
+
+static int lowpan_ndisc_is_useropt(u8 nd_opt_type)
+{
+	return nd_opt_type == ND_OPT_6CO;
+}
+
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+#define NDISC_802154_SHORT_ADDR_LENGTH	1
+static int lowpan_ndisc_parse_802154_options(const struct net_device *dev,
+					     struct nd_opt_hdr *nd_opt,
+					     struct ndisc_options *ndopts)
+{
+	switch (nd_opt->nd_opt_len) {
+	case NDISC_802154_SHORT_ADDR_LENGTH:
+		if (ndopts->nd_802154_opt_array[nd_opt->nd_opt_type])
+			ND_PRINTK(2, warn,
+				  "%s: duplicated short addr ND6 option found: type=%d\n",
+				  __func__, nd_opt->nd_opt_type);
+		else
+			ndopts->nd_802154_opt_array[nd_opt->nd_opt_type] = nd_opt;
+		return 1;
+	default:
+		/* all others will be handled by ndisc IPv6 option parsing */
+		return 0;
+	}
+}
+
+static int lowpan_ndisc_parse_options(const struct net_device *dev,
+				      struct nd_opt_hdr *nd_opt,
+				      struct ndisc_options *ndopts)
+{
+	switch (nd_opt->nd_opt_type) {
+	case ND_OPT_SOURCE_LL_ADDR:
+	case ND_OPT_TARGET_LL_ADDR:
+		return lowpan_ndisc_parse_802154_options(dev, nd_opt, ndopts);
+	default:
+		return 0;
+	}
+}
+
+static void lowpan_ndisc_802154_update(struct neighbour *n, u32 flags,
+				       u8 icmp6_type,
+				       const struct ndisc_options *ndopts)
+{
+	struct lowpan_802154_neigh *neigh = lowpan_802154_neigh(neighbour_priv(n));
+	u8 *lladdr_short = NULL;
+
+	switch (icmp6_type) {
+	case NDISC_ROUTER_SOLICITATION:
+	case NDISC_ROUTER_ADVERTISEMENT:
+	case NDISC_NEIGHBOUR_SOLICITATION:
+		if (ndopts->nd_802154_opts_src_lladdr) {
+			lladdr_short = __ndisc_opt_addr_data(ndopts->nd_802154_opts_src_lladdr,
+							     IEEE802154_SHORT_ADDR_LEN, 0);
+			if (!lladdr_short) {
+				ND_PRINTK(2, warn,
+					  "NA: invalid short link-layer address length\n");
+				return;
+			}
+		}
+		break;
+	case NDISC_REDIRECT:
+	case NDISC_NEIGHBOUR_ADVERTISEMENT:
+		if (ndopts->nd_802154_opts_tgt_lladdr) {
+			lladdr_short = __ndisc_opt_addr_data(ndopts->nd_802154_opts_tgt_lladdr,
+							     IEEE802154_SHORT_ADDR_LEN, 0);
+			if (!lladdr_short) {
+				ND_PRINTK(2, warn,
+					  "NA: invalid short link-layer address length\n");
+				return;
+			}
+		}
+		break;
+	default:
+		break;
+	}
+
+	write_lock_bh(&n->lock);
+	if (lladdr_short)
+		ieee802154_be16_to_le16(&neigh->short_addr, lladdr_short);
+	else
+		neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
+	write_unlock_bh(&n->lock);
+}
+
+static void lowpan_ndisc_update(const struct net_device *dev,
+				struct neighbour *n, u32 flags, u8 icmp6_type,
+				const struct ndisc_options *ndopts)
+{
+	if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+		return;
+
+	/* react on overrides only. TODO check if this is really right. */
+	if (flags & NEIGH_UPDATE_F_OVERRIDE)
+		lowpan_ndisc_802154_update(n, flags, icmp6_type, ndopts);
+}
+
+static int lowpan_ndisc_opt_addr_space(const struct net_device *dev,
+				       u8 icmp6_type, struct neighbour *neigh,
+				       u8 *ha_buf, u8 **ha)
+{
+	struct lowpan_802154_neigh *n;
+	struct wpan_dev *wpan_dev;
+	int addr_space = 0;
+
+	if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+		return 0;
+
+	switch (icmp6_type) {
+	case NDISC_REDIRECT:
+		n = lowpan_802154_neigh(neighbour_priv(neigh));
+
+		read_lock_bh(&neigh->lock);
+		if (lowpan_802154_is_valid_src_short_addr(n->short_addr)) {
+			memcpy(ha_buf, &n->short_addr,
+			       IEEE802154_SHORT_ADDR_LEN);
+			read_unlock_bh(&neigh->lock);
+			addr_space += __ndisc_opt_addr_space(IEEE802154_SHORT_ADDR_LEN, 0);
+			*ha = ha_buf;
+		}
+		read_unlock_bh(&neigh->lock);
+		break;
+	case NDISC_NEIGHBOUR_ADVERTISEMENT:
+	case NDISC_NEIGHBOUR_SOLICITATION:
+	case NDISC_ROUTER_SOLICITATION:
+		wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr;
+
+		if (lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr))
+			addr_space = __ndisc_opt_addr_space(IEEE802154_SHORT_ADDR_LEN, 0);
+		break;
+	default:
+		break;
+	}
+
+	return addr_space;
+}
+
+static void lowpan_ndisc_fill_addr_option(const struct net_device *dev,
+					  struct sk_buff *skb, u8 icmp6_type,
+					  const u8 *ha)
+{
+	struct wpan_dev *wpan_dev;
+	__be16 short_addr;
+	u8 opt_type;
+
+	if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+		return;
+
+	switch (icmp6_type) {
+	case NDISC_REDIRECT:
+		if (ha) {
+			ieee802154_le16_to_be16(&short_addr, ha);
+			__ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR,
+						 &short_addr,
+						 IEEE802154_SHORT_ADDR_LEN, 0);
+		}
+		return;
+	case NDISC_NEIGHBOUR_ADVERTISEMENT:
+		opt_type = ND_OPT_TARGET_LL_ADDR;
+		break;
+	case NDISC_ROUTER_SOLICITATION:
+	case NDISC_NEIGHBOUR_SOLICITATION:
+		opt_type = ND_OPT_SOURCE_LL_ADDR;
+		break;
+	default:
+		return;
+	}
+
+	wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr;
+
+	if (lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr)) {
+		ieee802154_le16_to_be16(&short_addr,
+					&wpan_dev->short_addr);
+		__ndisc_fill_addr_option(skb, opt_type, &short_addr,
+					 IEEE802154_SHORT_ADDR_LEN, 0);
+	}
+}
+
+static void lowpan_ndisc_prefix_rcv_add_addr(struct net *net,
+					     struct net_device *dev,
+					     const struct prefix_info *pinfo,
+					     struct inet6_dev *in6_dev,
+					     struct in6_addr *addr,
+					     int addr_type, u32 addr_flags,
+					     bool sllao, bool tokenized,
+					     __u32 valid_lft,
+					     u32 prefered_lft,
+					     bool dev_addr_generated)
+{
+	int err;
+
+	/* generates short based address for RA PIO's */
+	if (lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154) && dev_addr_generated &&
+	    !addrconf_ifid_802154_6lowpan(addr->s6_addr + 8, dev)) {
+		err = addrconf_prefix_rcv_add_addr(net, dev, pinfo, in6_dev,
+						   addr, addr_type, addr_flags,
+						   sllao, tokenized, valid_lft,
+						   prefered_lft);
+		if (err)
+			ND_PRINTK(2, warn,
+				  "RA: could not add a short address based address for prefix: %pI6c\n",
+				  &pinfo->prefix);
+	}
+}
+#endif
+
+const struct ndisc_ops lowpan_ndisc_ops = {
+	.is_useropt		= lowpan_ndisc_is_useropt,
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+	.parse_options		= lowpan_ndisc_parse_options,
+	.update			= lowpan_ndisc_update,
+	.opt_addr_space		= lowpan_ndisc_opt_addr_space,
+	.fill_addr_option	= lowpan_ndisc_fill_addr_option,
+	.prefix_rcv_add_addr	= lowpan_ndisc_prefix_rcv_add_addr,
+#endif
+};
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 86ae75b77390..c8f422c90856 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -790,6 +790,8 @@ static const struct net_device_ops vlan_netdev_ops = {
 	.ndo_netpoll_cleanup	= vlan_dev_netpoll_cleanup,
 #endif
 	.ndo_fix_features	= vlan_dev_fix_features,
+	.ndo_neigh_construct	= netdev_default_l2upper_neigh_construct,
+	.ndo_neigh_destroy	= netdev_default_l2upper_neigh_destroy,
 	.ndo_fdb_add		= switchdev_port_fdb_add,
 	.ndo_fdb_del		= switchdev_port_fdb_del,
 	.ndo_fdb_dump		= switchdev_port_fdb_dump,
diff --git a/net/atm/clip.c b/net/atm/clip.c
index e07f551a863c..53b4ac09e7b7 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -286,7 +286,7 @@ static const struct neigh_ops clip_neigh_ops = {
 	.connected_output =	neigh_direct_output,
 };
 
-static int clip_constructor(struct neighbour *neigh)
+static int clip_constructor(struct net_device *dev, struct neighbour *neigh)
 {
 	struct atmarp_entry *entry = neighbour_priv(neigh);
 
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index fbd0acf80b13..2fdebabbfacd 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -976,7 +976,8 @@ static int ax25_release(struct socket *sock)
 			release_sock(sk);
 			ax25_disconnect(ax25, 0);
 			lock_sock(sk);
-			ax25_destroy_socket(ax25);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_destroy_socket(ax25);
 			break;
 
 		case AX25_STATE_3:
diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c
index 951cd57bb07d..5237dff6941d 100644
--- a/net/ax25/ax25_ds_timer.c
+++ b/net/ax25/ax25_ds_timer.c
@@ -102,6 +102,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
 	switch (ax25->state) {
 
 	case AX25_STATE_0:
+	case AX25_STATE_2:
 		/* Magic here: If we listen() and a new link dies before it
 		   is accepted() it isn't 'dead' so doesn't get removed. */
 		if (!sk || sock_flag(sk, SOCK_DESTROY) ||
@@ -111,6 +112,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
 				sock_hold(sk);
 				ax25_destroy_socket(ax25);
 				bh_unlock_sock(sk);
+				/* Ungrab socket and destroy it */
 				sock_put(sk);
 			} else
 				ax25_destroy_socket(ax25);
@@ -213,7 +215,8 @@ void ax25_ds_t1_timeout(ax25_cb *ax25)
 	case AX25_STATE_2:
 		if (ax25->n2count == ax25->n2) {
 			ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND);
-			ax25_disconnect(ax25, ETIMEDOUT);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_disconnect(ax25, ETIMEDOUT);
 			return;
 		} else {
 			ax25->n2count++;
diff --git a/net/ax25/ax25_std_timer.c b/net/ax25/ax25_std_timer.c
index 004467c9e6e1..2c0d6ef66f9d 100644
--- a/net/ax25/ax25_std_timer.c
+++ b/net/ax25/ax25_std_timer.c
@@ -38,6 +38,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25)
 
 	switch (ax25->state) {
 	case AX25_STATE_0:
+	case AX25_STATE_2:
 		/* Magic here: If we listen() and a new link dies before it
 		   is accepted() it isn't 'dead' so doesn't get removed. */
 		if (!sk || sock_flag(sk, SOCK_DESTROY) ||
@@ -47,6 +48,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25)
 				sock_hold(sk);
 				ax25_destroy_socket(ax25);
 				bh_unlock_sock(sk);
+				/* Ungrab socket and destroy it */
 				sock_put(sk);
 			} else
 				ax25_destroy_socket(ax25);
@@ -144,7 +146,8 @@ void ax25_std_t1timer_expiry(ax25_cb *ax25)
 	case AX25_STATE_2:
 		if (ax25->n2count == ax25->n2) {
 			ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND);
-			ax25_disconnect(ax25, ETIMEDOUT);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_disconnect(ax25, ETIMEDOUT);
 			return;
 		} else {
 			ax25->n2count++;
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 3b78e8473a01..655a7d4c96e1 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -264,7 +264,8 @@ void ax25_disconnect(ax25_cb *ax25, int reason)
 {
 	ax25_clear_queues(ax25);
 
-	ax25_stop_heartbeat(ax25);
+	if (!sock_flag(ax25->sk, SOCK_DESTROY))
+		ax25_stop_heartbeat(ax25);
 	ax25_stop_t1timer(ax25);
 	ax25_stop_t2timer(ax25);
 	ax25_stop_t3timer(ax25);
diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index f66930ee3c0b..833bb145ba3c 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -66,7 +66,7 @@ config BATMAN_ADV_NC
 
 config BATMAN_ADV_MCAST
 	bool "Multicast optimisation"
-	depends on BATMAN_ADV
+	depends on BATMAN_ADV && INET && !(BRIDGE=m && BATMAN_ADV=y)
 	default n
 	help
 	  This option enables the multicast optimisation which aims to
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index 797cf2fc88c1..a83fc6c58d19 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -17,6 +17,7 @@
 #
 
 obj-$(CONFIG_BATMAN_ADV) += batman-adv.o
+batman-adv-y += bat_algo.o
 batman-adv-y += bat_iv_ogm.o
 batman-adv-$(CONFIG_BATMAN_ADV_BATMAN_V) += bat_v.o
 batman-adv-$(CONFIG_BATMAN_ADV_BATMAN_V) += bat_v_elp.o
@@ -31,12 +32,16 @@ batman-adv-y += gateway_common.o
 batman-adv-y += hard-interface.o
 batman-adv-y += hash.o
 batman-adv-y += icmp_socket.o
+batman-adv-$(CONFIG_BATMAN_ADV_DEBUG) += log.o
 batman-adv-y += main.o
 batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o
+batman-adv-y += netlink.o
 batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o
 batman-adv-y += originator.o
 batman-adv-y += routing.o
 batman-adv-y += send.o
 batman-adv-y += soft-interface.o
 batman-adv-y += sysfs.o
+batman-adv-y += tp_meter.o
 batman-adv-y += translation-table.o
+batman-adv-y += tvlv.o
diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c
new file mode 100644
index 000000000000..81dbbf569bd4
--- /dev/null
+++ b/net/batman-adv/bat_algo.c
@@ -0,0 +1,140 @@
+/* Copyright (C) 2007-2016  B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+#include <linux/errno.h>
+#include <linux/list.h>
+#include <linux/moduleparam.h>
+#include <linux/printk.h>
+#include <linux/seq_file.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+
+#include "bat_algo.h"
+
+char batadv_routing_algo[20] = "BATMAN_IV";
+static struct hlist_head batadv_algo_list;
+
+/**
+ * batadv_algo_init - Initialize batman-adv algorithm management data structures
+ */
+void batadv_algo_init(void)
+{
+	INIT_HLIST_HEAD(&batadv_algo_list);
+}
+
+static struct batadv_algo_ops *batadv_algo_get(char *name)
+{
+	struct batadv_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp;
+
+	hlist_for_each_entry(bat_algo_ops_tmp, &batadv_algo_list, list) {
+		if (strcmp(bat_algo_ops_tmp->name, name) != 0)
+			continue;
+
+		bat_algo_ops = bat_algo_ops_tmp;
+		break;
+	}
+
+	return bat_algo_ops;
+}
+
+int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops)
+{
+	struct batadv_algo_ops *bat_algo_ops_tmp;
+
+	bat_algo_ops_tmp = batadv_algo_get(bat_algo_ops->name);
+	if (bat_algo_ops_tmp) {
+		pr_info("Trying to register already registered routing algorithm: %s\n",
+			bat_algo_ops->name);
+		return -EEXIST;
+	}
+
+	/* all algorithms must implement all ops (for now) */
+	if (!bat_algo_ops->iface.enable ||
+	    !bat_algo_ops->iface.disable ||
+	    !bat_algo_ops->iface.update_mac ||
+	    !bat_algo_ops->iface.primary_set ||
+	    !bat_algo_ops->neigh.cmp ||
+	    !bat_algo_ops->neigh.is_similar_or_better) {
+		pr_info("Routing algo '%s' does not implement required ops\n",
+			bat_algo_ops->name);
+		return -EINVAL;
+	}
+
+	INIT_HLIST_NODE(&bat_algo_ops->list);
+	hlist_add_head(&bat_algo_ops->list, &batadv_algo_list);
+
+	return 0;
+}
+
+int batadv_algo_select(struct batadv_priv *bat_priv, char *name)
+{
+	struct batadv_algo_ops *bat_algo_ops;
+
+	bat_algo_ops = batadv_algo_get(name);
+	if (!bat_algo_ops)
+		return -EINVAL;
+
+	bat_priv->algo_ops = bat_algo_ops;
+
+	return 0;
+}
+
+int batadv_algo_seq_print_text(struct seq_file *seq, void *offset)
+{
+	struct batadv_algo_ops *bat_algo_ops;
+
+	seq_puts(seq, "Available routing algorithms:\n");
+
+	hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) {
+		seq_printf(seq, " * %s\n", bat_algo_ops->name);
+	}
+
+	return 0;
+}
+
+static int batadv_param_set_ra(const char *val, const struct kernel_param *kp)
+{
+	struct batadv_algo_ops *bat_algo_ops;
+	char *algo_name = (char *)val;
+	size_t name_len = strlen(algo_name);
+
+	if (name_len > 0 && algo_name[name_len - 1] == '\n')
+		algo_name[name_len - 1] = '\0';
+
+	bat_algo_ops = batadv_algo_get(algo_name);
+	if (!bat_algo_ops) {
+		pr_err("Routing algorithm '%s' is not supported\n", algo_name);
+		return -EINVAL;
+	}
+
+	return param_set_copystring(algo_name, kp);
+}
+
+static const struct kernel_param_ops batadv_param_ops_ra = {
+	.set = batadv_param_set_ra,
+	.get = param_get_string,
+};
+
+static struct kparam_string batadv_param_string_ra = {
+	.maxlen = sizeof(batadv_routing_algo),
+	.string = batadv_routing_algo,
+};
+
+module_param_cb(routing_algo, &batadv_param_ops_ra, &batadv_param_string_ra,
+		0644);
diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h
index 03dafd33d23b..860d773dd8fa 100644
--- a/net/batman-adv/bat_algo.h
+++ b/net/batman-adv/bat_algo.h
@@ -18,32 +18,18 @@
 #ifndef _NET_BATMAN_ADV_BAT_ALGO_H_
 #define _NET_BATMAN_ADV_BAT_ALGO_H_
 
-struct batadv_priv;
+#include "main.h"
 
-int batadv_iv_init(void);
+#include <linux/types.h>
 
-#ifdef CONFIG_BATMAN_ADV_BATMAN_V
+struct seq_file;
 
-int batadv_v_init(void);
-int batadv_v_mesh_init(struct batadv_priv *bat_priv);
-void batadv_v_mesh_free(struct batadv_priv *bat_priv);
+extern char batadv_routing_algo[];
+extern struct list_head batadv_hardif_list;
 
-#else
-
-static inline int batadv_v_init(void)
-{
-	return 0;
-}
-
-static inline int batadv_v_mesh_init(struct batadv_priv *bat_priv)
-{
-	return 0;
-}
-
-static inline void batadv_v_mesh_free(struct batadv_priv *bat_priv)
-{
-}
-
-#endif /* CONFIG_BATMAN_ADV_BATMAN_V */
+void batadv_algo_init(void);
+int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops);
+int batadv_algo_select(struct batadv_priv *bat_priv, char *name);
+int batadv_algo_seq_print_text(struct seq_file *seq, void *offset);
 
 #endif /* _NET_BATMAN_ADV_BAT_ALGO_H_ */
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index ce2f203048d3..19b0abd6c640 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -15,7 +15,7 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "bat_algo.h"
+#include "bat_iv_ogm.h"
 #include "main.h"
 
 #include <linux/atomic.h>
@@ -30,8 +30,9 @@
 #include <linux/if_ether.h>
 #include <linux/init.h>
 #include <linux/jiffies.h>
-#include <linux/list.h>
+#include <linux/kernel.h>
 #include <linux/kref.h>
+#include <linux/list.h>
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
 #include <linux/pkt_sched.h>
@@ -48,15 +49,20 @@
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
+#include "bat_algo.h"
 #include "bitarray.h"
 #include "hard-interface.h"
 #include "hash.h"
+#include "log.h"
 #include "network-coding.h"
 #include "originator.h"
 #include "packet.h"
 #include "routing.h"
 #include "send.h"
 #include "translation-table.h"
+#include "tvlv.h"
+
+static void batadv_iv_send_outstanding_bat_ogm_packet(struct work_struct *work);
 
 /**
  * enum batadv_dup_status - duplicate status
@@ -336,7 +342,8 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface,
 {
 	struct batadv_neigh_node *neigh_node;
 
-	neigh_node = batadv_neigh_node_new(orig_node, hard_iface, neigh_addr);
+	neigh_node = batadv_neigh_node_get_or_create(orig_node,
+						     hard_iface, neigh_addr);
 	if (!neigh_node)
 		goto out;
 
@@ -730,7 +737,7 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
 
 	/* start timer for this packet */
 	INIT_DELAYED_WORK(&forw_packet_aggr->delayed_work,
-			  batadv_send_outstanding_bat_ogm_packet);
+			  batadv_iv_send_outstanding_bat_ogm_packet);
 	queue_delayed_work(batadv_event_workqueue,
 			   &forw_packet_aggr->delayed_work,
 			   send_time - jiffies);
@@ -937,6 +944,19 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
 	u16 tvlv_len = 0;
 	unsigned long send_time;
 
+	if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) ||
+	    (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED))
+		return;
+
+	/* the interface gets activated here to avoid race conditions between
+	 * the moment of activating the interface in
+	 * hardif_activate_interface() where the originator mac is set and
+	 * outdated packets (especially uninitialized mac addresses) in the
+	 * packet queue
+	 */
+	if (hard_iface->if_status == BATADV_IF_TO_BE_ACTIVATED)
+		hard_iface->if_status = BATADV_IF_ACTIVE;
+
 	primary_if = batadv_primary_if_get_selected(bat_priv);
 
 	if (hard_iface == primary_if) {
@@ -1778,6 +1798,45 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset,
 	batadv_orig_node_put(orig_node);
 }
 
+static void batadv_iv_send_outstanding_bat_ogm_packet(struct work_struct *work)
+{
+	struct delayed_work *delayed_work;
+	struct batadv_forw_packet *forw_packet;
+	struct batadv_priv *bat_priv;
+
+	delayed_work = to_delayed_work(work);
+	forw_packet = container_of(delayed_work, struct batadv_forw_packet,
+				   delayed_work);
+	bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface);
+	spin_lock_bh(&bat_priv->forw_bat_list_lock);
+	hlist_del(&forw_packet->list);
+	spin_unlock_bh(&bat_priv->forw_bat_list_lock);
+
+	if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING)
+		goto out;
+
+	batadv_iv_ogm_emit(forw_packet);
+
+	/* we have to have at least one packet in the queue to determine the
+	 * queues wake up time unless we are shutting down.
+	 *
+	 * only re-schedule if this is the "original" copy, e.g. the OGM of the
+	 * primary interface should only be rescheduled once per period, but
+	 * this function will be called for the forw_packet instances of the
+	 * other secondary interfaces as well.
+	 */
+	if (forw_packet->own &&
+	    forw_packet->if_incoming == forw_packet->if_outgoing)
+		batadv_iv_ogm_schedule(forw_packet->if_incoming);
+
+out:
+	/* don't count own packet */
+	if (!forw_packet->own)
+		atomic_inc(&bat_priv->batman_queue_left);
+
+	batadv_forw_packet_free(forw_packet);
+}
+
 static int batadv_iv_ogm_receive(struct sk_buff *skb,
 				 struct batadv_hard_iface *if_incoming)
 {
@@ -1794,7 +1853,7 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb,
 	/* did we receive a B.A.T.M.A.N. IV OGM packet on an interface
 	 * that does not have B.A.T.M.A.N. IV enabled ?
 	 */
-	if (bat_priv->bat_algo_ops->bat_ogm_emit != batadv_iv_ogm_emit)
+	if (bat_priv->algo_ops->iface.enable != batadv_iv_ogm_iface_enable)
 		return NET_RX_DROP;
 
 	batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_RX);
@@ -2052,21 +2111,32 @@ out:
 	return ret;
 }
 
+static void batadv_iv_iface_activate(struct batadv_hard_iface *hard_iface)
+{
+	/* begin scheduling originator messages on that interface */
+	batadv_iv_ogm_schedule(hard_iface);
+}
+
 static struct batadv_algo_ops batadv_batman_iv __read_mostly = {
 	.name = "BATMAN_IV",
-	.bat_iface_enable = batadv_iv_ogm_iface_enable,
-	.bat_iface_disable = batadv_iv_ogm_iface_disable,
-	.bat_iface_update_mac = batadv_iv_ogm_iface_update_mac,
-	.bat_primary_iface_set = batadv_iv_ogm_primary_iface_set,
-	.bat_ogm_schedule = batadv_iv_ogm_schedule,
-	.bat_ogm_emit = batadv_iv_ogm_emit,
-	.bat_neigh_cmp = batadv_iv_ogm_neigh_cmp,
-	.bat_neigh_is_similar_or_better = batadv_iv_ogm_neigh_is_sob,
-	.bat_neigh_print = batadv_iv_neigh_print,
-	.bat_orig_print = batadv_iv_ogm_orig_print,
-	.bat_orig_free = batadv_iv_ogm_orig_free,
-	.bat_orig_add_if = batadv_iv_ogm_orig_add_if,
-	.bat_orig_del_if = batadv_iv_ogm_orig_del_if,
+	.iface = {
+		.activate = batadv_iv_iface_activate,
+		.enable = batadv_iv_ogm_iface_enable,
+		.disable = batadv_iv_ogm_iface_disable,
+		.update_mac = batadv_iv_ogm_iface_update_mac,
+		.primary_set = batadv_iv_ogm_primary_iface_set,
+	},
+	.neigh = {
+		.cmp = batadv_iv_ogm_neigh_cmp,
+		.is_similar_or_better = batadv_iv_ogm_neigh_is_sob,
+		.print = batadv_iv_neigh_print,
+	},
+	.orig = {
+		.print = batadv_iv_ogm_orig_print,
+		.free = batadv_iv_ogm_orig_free,
+		.add_if = batadv_iv_ogm_orig_add_if,
+		.del_if = batadv_iv_ogm_orig_del_if,
+	},
 };
 
 int __init batadv_iv_init(void)
diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h
new file mode 100644
index 000000000000..b9f3550faaf7
--- /dev/null
+++ b/net/batman-adv/bat_iv_ogm.h
@@ -0,0 +1,25 @@
+/* Copyright (C) 2007-2016  B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _BATMAN_ADV_BATADV_IV_OGM_H_
+#define _BATMAN_ADV_BATADV_IV_OGM_H_
+
+#include "main.h"
+
+int batadv_iv_init(void);
+
+#endif /* _BATMAN_ADV_BATADV_IV_OGM_H_ */
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 0a12e5cdd65d..0366cbf5e444 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -15,7 +15,7 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "bat_algo.h"
+#include "bat_v.h"
 #include "main.h"
 
 #include <linux/atomic.h>
@@ -31,6 +31,7 @@
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
+#include "bat_algo.h"
 #include "bat_v_elp.h"
 #include "bat_v_ogm.h"
 #include "hard-interface.h"
@@ -70,11 +71,6 @@ static int batadv_v_iface_enable(struct batadv_hard_iface *hard_iface)
 	if (ret < 0)
 		batadv_v_elp_iface_disable(hard_iface);
 
-	/* enable link throughput auto-detection by setting the throughput
-	 * override to zero
-	 */
-	atomic_set(&hard_iface->bat_v.throughput_override, 0);
-
 	return ret;
 }
 
@@ -119,14 +115,6 @@ batadv_v_hardif_neigh_init(struct batadv_hardif_neigh_node *hardif_neigh)
 		  batadv_v_elp_throughput_metric_update);
 }
 
-static void batadv_v_ogm_schedule(struct batadv_hard_iface *hard_iface)
-{
-}
-
-static void batadv_v_ogm_emit(struct batadv_forw_packet *forw_packet)
-{
-}
-
 /**
  * batadv_v_orig_print_neigh - print neighbors for the originator table
  * @orig_node: the orig_node for which the neighbors are printed
@@ -334,21 +322,39 @@ err_ifinfo1:
 
 static struct batadv_algo_ops batadv_batman_v __read_mostly = {
 	.name = "BATMAN_V",
-	.bat_iface_activate = batadv_v_iface_activate,
-	.bat_iface_enable = batadv_v_iface_enable,
-	.bat_iface_disable = batadv_v_iface_disable,
-	.bat_iface_update_mac = batadv_v_iface_update_mac,
-	.bat_primary_iface_set = batadv_v_primary_iface_set,
-	.bat_hardif_neigh_init = batadv_v_hardif_neigh_init,
-	.bat_ogm_emit = batadv_v_ogm_emit,
-	.bat_ogm_schedule = batadv_v_ogm_schedule,
-	.bat_orig_print = batadv_v_orig_print,
-	.bat_neigh_cmp = batadv_v_neigh_cmp,
-	.bat_neigh_is_similar_or_better = batadv_v_neigh_is_sob,
-	.bat_neigh_print = batadv_v_neigh_print,
+	.iface = {
+		.activate = batadv_v_iface_activate,
+		.enable = batadv_v_iface_enable,
+		.disable = batadv_v_iface_disable,
+		.update_mac = batadv_v_iface_update_mac,
+		.primary_set = batadv_v_primary_iface_set,
+	},
+	.neigh = {
+		.hardif_init = batadv_v_hardif_neigh_init,
+		.cmp = batadv_v_neigh_cmp,
+		.is_similar_or_better = batadv_v_neigh_is_sob,
+		.print = batadv_v_neigh_print,
+	},
+	.orig = {
+		.print = batadv_v_orig_print,
+	},
 };
 
 /**
+ * batadv_v_hardif_init - initialize the algorithm specific fields in the
+ *  hard-interface object
+ * @hard_iface: the hard-interface to initialize
+ */
+void batadv_v_hardif_init(struct batadv_hard_iface *hard_iface)
+{
+	/* enable link throughput auto-detection by setting the throughput
+	 * override to zero
+	 */
+	atomic_set(&hard_iface->bat_v.throughput_override, 0);
+	atomic_set(&hard_iface->bat_v.elp_interval, 500);
+}
+
+/**
  * batadv_v_mesh_init - initialize the B.A.T.M.A.N. V private resources for a
  *  mesh
  * @bat_priv: the object representing the mesh interface to initialise
diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h
new file mode 100644
index 000000000000..83b77639729e
--- /dev/null
+++ b/net/batman-adv/bat_v.h
@@ -0,0 +1,52 @@
+/* Copyright (C) 2011-2016  B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Linus Lüssing
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_BAT_V_H_
+#define _NET_BATMAN_ADV_BAT_V_H_
+
+#include "main.h"
+
+#ifdef CONFIG_BATMAN_ADV_BATMAN_V
+
+int batadv_v_init(void);
+void batadv_v_hardif_init(struct batadv_hard_iface *hardif);
+int batadv_v_mesh_init(struct batadv_priv *bat_priv);
+void batadv_v_mesh_free(struct batadv_priv *bat_priv);
+
+#else
+
+static inline int batadv_v_init(void)
+{
+	return 0;
+}
+
+static inline void batadv_v_hardif_init(struct batadv_hard_iface *hardif)
+{
+}
+
+static inline int batadv_v_mesh_init(struct batadv_priv *bat_priv)
+{
+	return 0;
+}
+
+static inline void batadv_v_mesh_free(struct batadv_priv *bat_priv)
+{
+}
+
+#endif /* CONFIG_BATMAN_ADV_BATMAN_V */
+
+#endif /* _NET_BATMAN_ADV_BAT_V_H_ */
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index df42eb1365a0..7d170010beb9 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -43,6 +43,7 @@
 #include "bat_algo.h"
 #include "bat_v_ogm.h"
 #include "hard-interface.h"
+#include "log.h"
 #include "originator.h"
 #include "packet.h"
 #include "routing.h"
@@ -344,7 +345,6 @@ int batadv_v_elp_iface_enable(struct batadv_hard_iface *hard_iface)
 	/* randomize initial seqno to avoid collision */
 	get_random_bytes(&random_seqno, sizeof(random_seqno));
 	atomic_set(&hard_iface->bat_v.elp_seqno, random_seqno);
-	atomic_set(&hard_iface->bat_v.elp_interval, 500);
 
 	/* assume full-duplex by default */
 	hard_iface->bat_v.flags |= BATADV_FULL_DUPLEX;
@@ -443,7 +443,8 @@ static void batadv_v_elp_neigh_update(struct batadv_priv *bat_priv,
 	if (!orig_neigh)
 		return;
 
-	neigh = batadv_neigh_node_new(orig_neigh, if_incoming, neigh_addr);
+	neigh = batadv_neigh_node_get_or_create(orig_neigh,
+						if_incoming, neigh_addr);
 	if (!neigh)
 		goto orig_free;
 
@@ -503,7 +504,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb,
 	/* did we receive a B.A.T.M.A.N. V ELP packet on an interface
 	 * that does not have B.A.T.M.A.N. V ELP enabled ?
 	 */
-	if (strcmp(bat_priv->bat_algo_ops->name, "BATMAN_V") != 0)
+	if (strcmp(bat_priv->algo_ops->name, "BATMAN_V") != 0)
 		return NET_RX_DROP;
 
 	elp_packet = (struct batadv_elp_packet *)skb->data;
diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h
index cc130b2d05e5..be17c0b1369e 100644
--- a/net/batman-adv/bat_v_elp.h
+++ b/net/batman-adv/bat_v_elp.h
@@ -15,11 +15,11 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "main.h"
-
 #ifndef _NET_BATMAN_ADV_BAT_V_ELP_H_
 #define _NET_BATMAN_ADV_BAT_V_ELP_H_
 
+#include "main.h"
+
 struct sk_buff;
 struct work_struct;
 
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 473ebb9a0e73..6fbba4eb0617 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -39,13 +39,16 @@
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
+#include "bat_algo.h"
 #include "hard-interface.h"
 #include "hash.h"
+#include "log.h"
 #include "originator.h"
 #include "packet.h"
 #include "routing.h"
 #include "send.h"
 #include "translation-table.h"
+#include "tvlv.h"
 
 /**
  * batadv_v_ogm_orig_get - retrieve and possibly create an originator node
@@ -683,8 +686,8 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset,
 	if (!orig_node)
 		return;
 
-	neigh_node = batadv_neigh_node_new(orig_node, if_incoming,
-					   ethhdr->h_source);
+	neigh_node = batadv_neigh_node_get_or_create(orig_node, if_incoming,
+						     ethhdr->h_source);
 	if (!neigh_node)
 		goto out;
 
@@ -751,7 +754,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb,
 	/* did we receive a OGM2 packet on an interface that does not have
 	 * B.A.T.M.A.N. V enabled ?
 	 */
-	if (strcmp(bat_priv->bat_algo_ops->name, "BATMAN_V") != 0)
+	if (strcmp(bat_priv->algo_ops->name, "BATMAN_V") != 0)
 		return NET_RX_DROP;
 
 	if (!batadv_check_management_packet(skb, if_incoming, BATADV_OGM2_HLEN))
diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h
index d849c75ada0e..4c4d45caa422 100644
--- a/net/batman-adv/bat_v_ogm.h
+++ b/net/batman-adv/bat_v_ogm.h
@@ -18,10 +18,10 @@
 #ifndef _BATMAN_ADV_BATADV_V_OGM_H_
 #define _BATMAN_ADV_BATADV_V_OGM_H_
 
+#include "main.h"
+
 #include <linux/types.h>
 
-struct batadv_hard_iface;
-struct batadv_priv;
 struct sk_buff;
 
 int batadv_v_ogm_init(struct batadv_priv *bat_priv);
diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c
index a0c7913837a5..032271421a20 100644
--- a/net/batman-adv/bitarray.c
+++ b/net/batman-adv/bitarray.c
@@ -20,6 +20,8 @@
 
 #include <linux/bitmap.h>
 
+#include "log.h"
+
 /* shift the packet array by n places. */
 static void batadv_bitmap_shift_left(unsigned long *seq_bits, s32 n)
 {
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 748a9ead7ce5..e4f7494fb974 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -48,6 +48,7 @@
 
 #include "hard-interface.h"
 #include "hash.h"
+#include "log.h"
 #include "originator.h"
 #include "packet.h"
 #include "sysfs.h"
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index 952900466d88..1d68b6e63b96 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -18,245 +18,33 @@
 #include "debugfs.h"
 #include "main.h"
 
-#include <linux/compiler.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/errno.h>
 #include <linux/export.h>
-#include <linux/fcntl.h>
 #include <linux/fs.h>
-#include <linux/jiffies.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/netdevice.h>
-#include <linux/poll.h>
 #include <linux/printk.h>
 #include <linux/sched.h> /* for linux/wait.h */
 #include <linux/seq_file.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
 #include <linux/stat.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
 #include <linux/sysfs.h>
-#include <linux/types.h>
-#include <linux/uaccess.h>
-#include <linux/wait.h>
-#include <stdarg.h>
 
+#include "bat_algo.h"
 #include "bridge_loop_avoidance.h"
 #include "distributed-arp-table.h"
 #include "gateway_client.h"
 #include "icmp_socket.h"
+#include "log.h"
+#include "multicast.h"
 #include "network-coding.h"
 #include "originator.h"
 #include "translation-table.h"
 
 static struct dentry *batadv_debugfs;
 
-#ifdef CONFIG_BATMAN_ADV_DEBUG
-#define BATADV_LOG_BUFF_MASK (batadv_log_buff_len - 1)
-
-static const int batadv_log_buff_len = BATADV_LOG_BUF_LEN;
-
-static char *batadv_log_char_addr(struct batadv_priv_debug_log *debug_log,
-				  size_t idx)
-{
-	return &debug_log->log_buff[idx & BATADV_LOG_BUFF_MASK];
-}
-
-static void batadv_emit_log_char(struct batadv_priv_debug_log *debug_log,
-				 char c)
-{
-	char *char_addr;
-
-	char_addr = batadv_log_char_addr(debug_log, debug_log->log_end);
-	*char_addr = c;
-	debug_log->log_end++;
-
-	if (debug_log->log_end - debug_log->log_start > batadv_log_buff_len)
-		debug_log->log_start = debug_log->log_end - batadv_log_buff_len;
-}
-
-__printf(2, 3)
-static int batadv_fdebug_log(struct batadv_priv_debug_log *debug_log,
-			     const char *fmt, ...)
-{
-	va_list args;
-	static char debug_log_buf[256];
-	char *p;
-
-	if (!debug_log)
-		return 0;
-
-	spin_lock_bh(&debug_log->lock);
-	va_start(args, fmt);
-	vscnprintf(debug_log_buf, sizeof(debug_log_buf), fmt, args);
-	va_end(args);
-
-	for (p = debug_log_buf; *p != 0; p++)
-		batadv_emit_log_char(debug_log, *p);
-
-	spin_unlock_bh(&debug_log->lock);
-
-	wake_up(&debug_log->queue_wait);
-
-	return 0;
-}
-
-int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
-{
-	va_list args;
-	char tmp_log_buf[256];
-
-	va_start(args, fmt);
-	vscnprintf(tmp_log_buf, sizeof(tmp_log_buf), fmt, args);
-	batadv_fdebug_log(bat_priv->debug_log, "[%10u] %s",
-			  jiffies_to_msecs(jiffies), tmp_log_buf);
-	va_end(args);
-
-	return 0;
-}
-
-static int batadv_log_open(struct inode *inode, struct file *file)
-{
-	if (!try_module_get(THIS_MODULE))
-		return -EBUSY;
-
-	nonseekable_open(inode, file);
-	file->private_data = inode->i_private;
-	return 0;
-}
-
-static int batadv_log_release(struct inode *inode, struct file *file)
-{
-	module_put(THIS_MODULE);
-	return 0;
-}
-
-static bool batadv_log_empty(struct batadv_priv_debug_log *debug_log)
-{
-	return !(debug_log->log_start - debug_log->log_end);
-}
-
-static ssize_t batadv_log_read(struct file *file, char __user *buf,
-			       size_t count, loff_t *ppos)
-{
-	struct batadv_priv *bat_priv = file->private_data;
-	struct batadv_priv_debug_log *debug_log = bat_priv->debug_log;
-	int error, i = 0;
-	char *char_addr;
-	char c;
-
-	if ((file->f_flags & O_NONBLOCK) && batadv_log_empty(debug_log))
-		return -EAGAIN;
-
-	if (!buf)
-		return -EINVAL;
-
-	if (count == 0)
-		return 0;
-
-	if (!access_ok(VERIFY_WRITE, buf, count))
-		return -EFAULT;
-
-	error = wait_event_interruptible(debug_log->queue_wait,
-					 (!batadv_log_empty(debug_log)));
-
-	if (error)
-		return error;
-
-	spin_lock_bh(&debug_log->lock);
-
-	while ((!error) && (i < count) &&
-	       (debug_log->log_start != debug_log->log_end)) {
-		char_addr = batadv_log_char_addr(debug_log,
-						 debug_log->log_start);
-		c = *char_addr;
-
-		debug_log->log_start++;
-
-		spin_unlock_bh(&debug_log->lock);
-
-		error = __put_user(c, buf);
-
-		spin_lock_bh(&debug_log->lock);
-
-		buf++;
-		i++;
-	}
-
-	spin_unlock_bh(&debug_log->lock);
-
-	if (!error)
-		return i;
-
-	return error;
-}
-
-static unsigned int batadv_log_poll(struct file *file, poll_table *wait)
-{
-	struct batadv_priv *bat_priv = file->private_data;
-	struct batadv_priv_debug_log *debug_log = bat_priv->debug_log;
-
-	poll_wait(file, &debug_log->queue_wait, wait);
-
-	if (!batadv_log_empty(debug_log))
-		return POLLIN | POLLRDNORM;
-
-	return 0;
-}
-
-static const struct file_operations batadv_log_fops = {
-	.open           = batadv_log_open,
-	.release        = batadv_log_release,
-	.read           = batadv_log_read,
-	.poll           = batadv_log_poll,
-	.llseek         = no_llseek,
-};
-
-static int batadv_debug_log_setup(struct batadv_priv *bat_priv)
-{
-	struct dentry *d;
-
-	if (!bat_priv->debug_dir)
-		goto err;
-
-	bat_priv->debug_log = kzalloc(sizeof(*bat_priv->debug_log), GFP_ATOMIC);
-	if (!bat_priv->debug_log)
-		goto err;
-
-	spin_lock_init(&bat_priv->debug_log->lock);
-	init_waitqueue_head(&bat_priv->debug_log->queue_wait);
-
-	d = debugfs_create_file("log", S_IFREG | S_IRUSR,
-				bat_priv->debug_dir, bat_priv,
-				&batadv_log_fops);
-	if (!d)
-		goto err;
-
-	return 0;
-
-err:
-	return -ENOMEM;
-}
-
-static void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
-{
-	kfree(bat_priv->debug_log);
-	bat_priv->debug_log = NULL;
-}
-#else /* CONFIG_BATMAN_ADV_DEBUG */
-static int batadv_debug_log_setup(struct batadv_priv *bat_priv)
-{
-	return 0;
-}
-
-static void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
-{
-}
-#endif
-
 static int batadv_algorithms_open(struct inode *inode, struct file *file)
 {
 	return single_open(file, batadv_algo_seq_print_text, NULL);
@@ -363,6 +151,22 @@ static int batadv_nc_nodes_open(struct inode *inode, struct file *file)
 }
 #endif
 
+#ifdef CONFIG_BATMAN_ADV_MCAST
+/**
+ * batadv_mcast_flags_open - prepare file handler for reads from mcast_flags
+ * @inode: inode which was opened
+ * @file: file handle to be initialized
+ *
+ * Return: 0 on success or negative error number in case of failure
+ */
+static int batadv_mcast_flags_open(struct inode *inode, struct file *file)
+{
+	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
+	return single_open(file, batadv_mcast_flags_seq_print_text, net_dev);
+}
+#endif
+
 #define BATADV_DEBUGINFO(_name, _mode, _open)		\
 struct batadv_debuginfo batadv_debuginfo_##_name = {	\
 	.attr = {					\
@@ -407,6 +211,9 @@ static BATADV_DEBUGINFO(transtable_local, S_IRUGO,
 #ifdef CONFIG_BATMAN_ADV_NC
 static BATADV_DEBUGINFO(nc_nodes, S_IRUGO, batadv_nc_nodes_open);
 #endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+static BATADV_DEBUGINFO(mcast_flags, S_IRUGO, batadv_mcast_flags_open);
+#endif
 
 static struct batadv_debuginfo *batadv_mesh_debuginfos[] = {
 	&batadv_debuginfo_neighbors,
@@ -424,6 +231,9 @@ static struct batadv_debuginfo *batadv_mesh_debuginfos[] = {
 #ifdef CONFIG_BATMAN_ADV_NC
 	&batadv_debuginfo_nc_nodes,
 #endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	&batadv_debuginfo_mcast_flags,
+#endif
 	NULL,
 };
 
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 278800a99c69..fa7646532a13 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -45,9 +45,11 @@
 
 #include "hard-interface.h"
 #include "hash.h"
+#include "log.h"
 #include "originator.h"
 #include "send.h"
 #include "translation-table.h"
+#include "tvlv.h"
 
 static void batadv_dat_purge(struct work_struct *work);
 
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 65536db1bff7..0934730fb7ff 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -27,7 +27,6 @@
 #include <linux/kernel.h>
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
-#include <linux/pkt_sched.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -414,7 +413,7 @@ static struct sk_buff *batadv_frag_create(struct sk_buff *skb,
 	if (!skb_fragment)
 		goto err;
 
-	skb->priority = TC_PRIO_CONTROL;
+	skb_fragment->priority = skb->priority;
 
 	/* Eat the last mtu-bytes of the skb */
 	skb_reserve(skb_fragment, header_size + ETH_HLEN);
@@ -434,11 +433,12 @@ err:
  * @orig_node: final destination of the created fragments
  * @neigh_node: next-hop of the created fragments
  *
- * Return: true on success, false otherwise.
+ * Return: the netdev tx status or -1 in case of error.
+ * When -1 is returned the skb is not consumed.
  */
-bool batadv_frag_send_packet(struct sk_buff *skb,
-			     struct batadv_orig_node *orig_node,
-			     struct batadv_neigh_node *neigh_node)
+int batadv_frag_send_packet(struct sk_buff *skb,
+			    struct batadv_orig_node *orig_node,
+			    struct batadv_neigh_node *neigh_node)
 {
 	struct batadv_priv *bat_priv;
 	struct batadv_hard_iface *primary_if = NULL;
@@ -447,7 +447,7 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 	unsigned int mtu = neigh_node->if_incoming->net_dev->mtu;
 	unsigned int header_size = sizeof(frag_header);
 	unsigned int max_fragment_size, max_packet_size;
-	bool ret = false;
+	int ret = -1;
 
 	/* To avoid merge and refragmentation at next-hops we never send
 	 * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE
@@ -458,12 +458,12 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 
 	/* Don't even try to fragment, if we need more than 16 fragments */
 	if (skb->len > max_packet_size)
-		goto out_err;
+		goto out;
 
 	bat_priv = orig_node->bat_priv;
 	primary_if = batadv_primary_if_get_selected(bat_priv);
 	if (!primary_if)
-		goto out_err;
+		goto out;
 
 	/* Create one header to be copied to all fragments */
 	frag_header.packet_type = BATADV_UNICAST_FRAG;
@@ -473,6 +473,15 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 	frag_header.reserved = 0;
 	frag_header.no = 0;
 	frag_header.total_size = htons(skb->len);
+
+	/* skb->priority values from 256->263 are magic values to
+	 * directly indicate a specific 802.1d priority.  This is used
+	 * to allow 802.1d priority to be passed directly in from VLAN
+	 * tags, etc.
+	 */
+	if (skb->priority >= 256 && skb->priority <= 263)
+		frag_header.priority = skb->priority - 256;
+
 	ether_addr_copy(frag_header.orig, primary_if->net_dev->dev_addr);
 	ether_addr_copy(frag_header.dest, orig_node->orig);
 
@@ -480,23 +489,33 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 	while (skb->len > max_fragment_size) {
 		skb_fragment = batadv_frag_create(skb, &frag_header, mtu);
 		if (!skb_fragment)
-			goto out_err;
+			goto out;
 
 		batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_TX);
 		batadv_add_counter(bat_priv, BATADV_CNT_FRAG_TX_BYTES,
 				   skb_fragment->len + ETH_HLEN);
-		batadv_send_unicast_skb(skb_fragment, neigh_node);
+		ret = batadv_send_unicast_skb(skb_fragment, neigh_node);
+		if (ret != NET_XMIT_SUCCESS) {
+			/* return -1 so that the caller can free the original
+			 * skb
+			 */
+			ret = -1;
+			goto out;
+		}
+
 		frag_header.no++;
 
 		/* The initial check in this function should cover this case */
-		if (frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1)
-			goto out_err;
+		if (frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1) {
+			ret = -1;
+			goto out;
+		}
 	}
 
 	/* Make room for the fragment header. */
 	if (batadv_skb_head_push(skb, header_size) < 0 ||
 	    pskb_expand_head(skb, header_size + ETH_HLEN, 0, GFP_ATOMIC) < 0)
-		goto out_err;
+		goto out;
 
 	memcpy(skb->data, &frag_header, header_size);
 
@@ -504,11 +523,9 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 	batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_TX);
 	batadv_add_counter(bat_priv, BATADV_CNT_FRAG_TX_BYTES,
 			   skb->len + ETH_HLEN);
-	batadv_send_unicast_skb(skb, neigh_node);
-
-	ret = true;
+	ret = batadv_send_unicast_skb(skb, neigh_node);
 
-out_err:
+out:
 	if (primary_if)
 		batadv_hardif_put(primary_if);
 
diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h
index 9ff77c7ef7c7..3202fe329e63 100644
--- a/net/batman-adv/fragmentation.h
+++ b/net/batman-adv/fragmentation.h
@@ -34,9 +34,9 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
 			 struct batadv_orig_node *orig_node_src);
 bool batadv_frag_skb_buffer(struct sk_buff **skb,
 			    struct batadv_orig_node *orig_node);
-bool batadv_frag_send_packet(struct sk_buff *skb,
-			     struct batadv_orig_node *orig_node,
-			     struct batadv_neigh_node *neigh_node);
+int batadv_frag_send_packet(struct sk_buff *skb,
+			    struct batadv_orig_node *orig_node,
+			    struct batadv_neigh_node *neigh_node);
 
 /**
  * batadv_frag_check_entry - check if a list of fragments has timed out
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 5839c569f769..63a805d3f96e 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -42,6 +42,7 @@
 
 #include "gateway_common.h"
 #include "hard-interface.h"
+#include "log.h"
 #include "originator.h"
 #include "packet.h"
 #include "routing.h"
@@ -192,7 +193,7 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv)
 
 		tq_avg = router_ifinfo->bat_iv.tq_avg;
 
-		switch (atomic_read(&bat_priv->gw_sel_class)) {
+		switch (atomic_read(&bat_priv->gw.sel_class)) {
 		case 1: /* fast connection */
 			tmp_gw_factor = tq_avg * tq_avg;
 			tmp_gw_factor *= gw_node->bandwidth_down;
@@ -255,7 +256,7 @@ void batadv_gw_check_client_stop(struct batadv_priv *bat_priv)
 {
 	struct batadv_gw_node *curr_gw;
 
-	if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_CLIENT)
+	if (atomic_read(&bat_priv->gw.mode) != BATADV_GW_MODE_CLIENT)
 		return;
 
 	curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
@@ -283,7 +284,7 @@ void batadv_gw_election(struct batadv_priv *bat_priv)
 	struct batadv_neigh_ifinfo *router_ifinfo = NULL;
 	char gw_addr[18] = { '\0' };
 
-	if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_CLIENT)
+	if (atomic_read(&bat_priv->gw.mode) != BATADV_GW_MODE_CLIENT)
 		goto out;
 
 	curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
@@ -402,8 +403,8 @@ void batadv_gw_check_election(struct batadv_priv *bat_priv,
 	/* if the routing class is greater than 3 the value tells us how much
 	 * greater the TQ value of the new gateway must be
 	 */
-	if ((atomic_read(&bat_priv->gw_sel_class) > 3) &&
-	    (orig_tq_avg - gw_tq_avg < atomic_read(&bat_priv->gw_sel_class)))
+	if ((atomic_read(&bat_priv->gw.sel_class) > 3) &&
+	    (orig_tq_avg - gw_tq_avg < atomic_read(&bat_priv->gw.sel_class)))
 		goto out;
 
 	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
@@ -638,8 +639,7 @@ int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset)
 		goto out;
 
 	seq_printf(seq,
-		   "      %-12s (%s/%i) %17s [%10s]: advertised uplink bandwidth ... [B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n",
-		   "Gateway", "#", BATADV_TQ_MAX_VALUE, "Nexthop", "outgoingIF",
+		   "      Gateway      (#/255)           Nexthop [outgoingIF]: advertised uplink bandwidth ... [B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n",
 		   BATADV_SOURCE_VERSION, primary_if->net_dev->name,
 		   primary_if->net_dev->dev_addr, net_dev->name);
 
@@ -821,7 +821,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
 	if (!gw_node)
 		goto out;
 
-	switch (atomic_read(&bat_priv->gw_mode)) {
+	switch (atomic_read(&bat_priv->gw.mode)) {
 	case BATADV_GW_MODE_SERVER:
 		/* If we are a GW then we are our best GW. We can artificially
 		 * set the tq towards ourself as the maximum value
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index 4423047889e1..d7bc6a87bcc9 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -19,8 +19,8 @@
 #include "main.h"
 
 #include <linux/atomic.h>
-#include <linux/errno.h>
 #include <linux/byteorder/generic.h>
+#include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/math64.h>
 #include <linux/netdevice.h>
@@ -28,7 +28,9 @@
 #include <linux/string.h>
 
 #include "gateway_client.h"
+#include "log.h"
 #include "packet.h"
+#include "tvlv.h"
 
 /**
  * batadv_parse_throughput - parse supplied string buffer to extract throughput
@@ -144,7 +146,7 @@ void batadv_gw_tvlv_container_update(struct batadv_priv *bat_priv)
 	u32 down, up;
 	char gw_mode;
 
-	gw_mode = atomic_read(&bat_priv->gw_mode);
+	gw_mode = atomic_read(&bat_priv->gw.mode);
 
 	switch (gw_mode) {
 	case BATADV_GW_MODE_OFF:
@@ -241,8 +243,8 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 
 	/* restart gateway selection if fast or late switching was enabled */
 	if ((gateway.bandwidth_down != 0) &&
-	    (atomic_read(&bat_priv->gw_mode) == BATADV_GW_MODE_CLIENT) &&
-	    (atomic_read(&bat_priv->gw_sel_class) > 2))
+	    (atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT) &&
+	    (atomic_read(&bat_priv->gw.sel_class) > 2))
 		batadv_gw_check_election(bat_priv, orig);
 }
 
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 8c2f39962fa5..1f9080840566 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -23,9 +23,9 @@
 #include <linux/byteorder/generic.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/if.h>
 #include <linux/if_arp.h>
 #include <linux/if_ether.h>
-#include <linux/if.h>
 #include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/list.h>
@@ -37,10 +37,12 @@
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 
+#include "bat_v.h"
 #include "bridge_loop_avoidance.h"
 #include "debugfs.h"
 #include "distributed-arp-table.h"
 #include "gateway_client.h"
+#include "log.h"
 #include "originator.h"
 #include "packet.h"
 #include "send.h"
@@ -245,7 +247,7 @@ static void batadv_primary_if_select(struct batadv_priv *bat_priv,
 	if (!new_hard_iface)
 		goto out;
 
-	bat_priv->bat_algo_ops->bat_primary_iface_set(new_hard_iface);
+	bat_priv->algo_ops->iface.primary_set(new_hard_iface);
 	batadv_primary_if_update_addr(bat_priv, curr_hard_iface);
 
 out:
@@ -392,7 +394,7 @@ batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface)
 
 	bat_priv = netdev_priv(hard_iface->soft_iface);
 
-	bat_priv->bat_algo_ops->bat_iface_update_mac(hard_iface);
+	bat_priv->algo_ops->iface.update_mac(hard_iface);
 	hard_iface->if_status = BATADV_IF_TO_BE_ACTIVATED;
 
 	/* the first active interface becomes our primary interface or
@@ -407,8 +409,8 @@ batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface)
 
 	batadv_update_min_mtu(hard_iface->soft_iface);
 
-	if (bat_priv->bat_algo_ops->bat_iface_activate)
-		bat_priv->bat_algo_ops->bat_iface_activate(hard_iface);
+	if (bat_priv->algo_ops->iface.activate)
+		bat_priv->algo_ops->iface.activate(hard_iface);
 
 out:
 	if (primary_if)
@@ -506,7 +508,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	if (ret)
 		goto err_dev;
 
-	ret = bat_priv->bat_algo_ops->bat_iface_enable(hard_iface);
+	ret = bat_priv->algo_ops->iface.enable(hard_iface);
 	if (ret < 0)
 		goto err_upper;
 
@@ -515,7 +517,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	hard_iface->if_status = BATADV_IF_INACTIVE;
 	ret = batadv_orig_hash_add_if(hard_iface, bat_priv->num_ifaces);
 	if (ret < 0) {
-		bat_priv->bat_algo_ops->bat_iface_disable(hard_iface);
+		bat_priv->algo_ops->iface.disable(hard_iface);
 		bat_priv->num_ifaces--;
 		hard_iface->if_status = BATADV_IF_NOT_IN_USE;
 		goto err_upper;
@@ -553,9 +555,6 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 
 	batadv_hardif_recalc_extra_skbroom(soft_iface);
 
-	/* begin scheduling originator messages on that interface */
-	batadv_schedule_bat_ogm(hard_iface);
-
 out:
 	return 0;
 
@@ -599,7 +598,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface,
 			batadv_hardif_put(new_if);
 	}
 
-	bat_priv->bat_algo_ops->bat_iface_disable(hard_iface);
+	bat_priv->algo_ops->iface.disable(hard_iface);
 	hard_iface->if_status = BATADV_IF_NOT_IN_USE;
 
 	/* delete all references to this hard_iface */
@@ -686,6 +685,8 @@ batadv_hardif_add_interface(struct net_device *net_dev)
 	if (batadv_is_wifi_netdev(net_dev))
 		hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS;
 
+	batadv_v_hardif_init(hard_iface);
+
 	/* extra reference for return */
 	kref_init(&hard_iface->refcount);
 	kref_get(&hard_iface->refcount);
@@ -782,7 +783,7 @@ static int batadv_hard_if_event(struct notifier_block *this,
 		batadv_check_known_mac_addr(hard_iface->net_dev);
 
 		bat_priv = netdev_priv(hard_iface->soft_iface);
-		bat_priv->bat_algo_ops->bat_iface_update_mac(hard_iface);
+		bat_priv->algo_ops->iface.update_mac(hard_iface);
 
 		primary_if = batadv_primary_if_get_selected(bat_priv);
 		if (!primary_if)
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 777aea10cd8f..378cc1119d66 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -45,6 +45,7 @@
 #include <linux/wait.h>
 
 #include "hard-interface.h"
+#include "log.h"
 #include "originator.h"
 #include "packet.h"
 #include "send.h"
diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c
new file mode 100644
index 000000000000..56dc532f7a2c
--- /dev/null
+++ b/net/batman-adv/log.c
@@ -0,0 +1,231 @@
+/* Copyright (C) 2010-2016  B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "log.h"
+#include "main.h"
+
+#include <linux/compiler.h>
+#include <linux/debugfs.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/fcntl.h>
+#include <linux/fs.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/poll.h>
+#include <linux/sched.h> /* for linux/wait.h */
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/wait.h>
+#include <stdarg.h>
+
+#define BATADV_LOG_BUFF_MASK (batadv_log_buff_len - 1)
+
+static const int batadv_log_buff_len = BATADV_LOG_BUF_LEN;
+
+static char *batadv_log_char_addr(struct batadv_priv_debug_log *debug_log,
+				  size_t idx)
+{
+	return &debug_log->log_buff[idx & BATADV_LOG_BUFF_MASK];
+}
+
+static void batadv_emit_log_char(struct batadv_priv_debug_log *debug_log,
+				 char c)
+{
+	char *char_addr;
+
+	char_addr = batadv_log_char_addr(debug_log, debug_log->log_end);
+	*char_addr = c;
+	debug_log->log_end++;
+
+	if (debug_log->log_end - debug_log->log_start > batadv_log_buff_len)
+		debug_log->log_start = debug_log->log_end - batadv_log_buff_len;
+}
+
+__printf(2, 3)
+static int batadv_fdebug_log(struct batadv_priv_debug_log *debug_log,
+			     const char *fmt, ...)
+{
+	va_list args;
+	static char debug_log_buf[256];
+	char *p;
+
+	if (!debug_log)
+		return 0;
+
+	spin_lock_bh(&debug_log->lock);
+	va_start(args, fmt);
+	vscnprintf(debug_log_buf, sizeof(debug_log_buf), fmt, args);
+	va_end(args);
+
+	for (p = debug_log_buf; *p != 0; p++)
+		batadv_emit_log_char(debug_log, *p);
+
+	spin_unlock_bh(&debug_log->lock);
+
+	wake_up(&debug_log->queue_wait);
+
+	return 0;
+}
+
+int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
+{
+	va_list args;
+	char tmp_log_buf[256];
+
+	va_start(args, fmt);
+	vscnprintf(tmp_log_buf, sizeof(tmp_log_buf), fmt, args);
+	batadv_fdebug_log(bat_priv->debug_log, "[%10u] %s",
+			  jiffies_to_msecs(jiffies), tmp_log_buf);
+	va_end(args);
+
+	return 0;
+}
+
+static int batadv_log_open(struct inode *inode, struct file *file)
+{
+	if (!try_module_get(THIS_MODULE))
+		return -EBUSY;
+
+	nonseekable_open(inode, file);
+	file->private_data = inode->i_private;
+	return 0;
+}
+
+static int batadv_log_release(struct inode *inode, struct file *file)
+{
+	module_put(THIS_MODULE);
+	return 0;
+}
+
+static bool batadv_log_empty(struct batadv_priv_debug_log *debug_log)
+{
+	return !(debug_log->log_start - debug_log->log_end);
+}
+
+static ssize_t batadv_log_read(struct file *file, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	struct batadv_priv *bat_priv = file->private_data;
+	struct batadv_priv_debug_log *debug_log = bat_priv->debug_log;
+	int error, i = 0;
+	char *char_addr;
+	char c;
+
+	if ((file->f_flags & O_NONBLOCK) && batadv_log_empty(debug_log))
+		return -EAGAIN;
+
+	if (!buf)
+		return -EINVAL;
+
+	if (count == 0)
+		return 0;
+
+	if (!access_ok(VERIFY_WRITE, buf, count))
+		return -EFAULT;
+
+	error = wait_event_interruptible(debug_log->queue_wait,
+					 (!batadv_log_empty(debug_log)));
+
+	if (error)
+		return error;
+
+	spin_lock_bh(&debug_log->lock);
+
+	while ((!error) && (i < count) &&
+	       (debug_log->log_start != debug_log->log_end)) {
+		char_addr = batadv_log_char_addr(debug_log,
+						 debug_log->log_start);
+		c = *char_addr;
+
+		debug_log->log_start++;
+
+		spin_unlock_bh(&debug_log->lock);
+
+		error = __put_user(c, buf);
+
+		spin_lock_bh(&debug_log->lock);
+
+		buf++;
+		i++;
+	}
+
+	spin_unlock_bh(&debug_log->lock);
+
+	if (!error)
+		return i;
+
+	return error;
+}
+
+static unsigned int batadv_log_poll(struct file *file, poll_table *wait)
+{
+	struct batadv_priv *bat_priv = file->private_data;
+	struct batadv_priv_debug_log *debug_log = bat_priv->debug_log;
+
+	poll_wait(file, &debug_log->queue_wait, wait);
+
+	if (!batadv_log_empty(debug_log))
+		return POLLIN | POLLRDNORM;
+
+	return 0;
+}
+
+static const struct file_operations batadv_log_fops = {
+	.open           = batadv_log_open,
+	.release        = batadv_log_release,
+	.read           = batadv_log_read,
+	.poll           = batadv_log_poll,
+	.llseek         = no_llseek,
+};
+
+int batadv_debug_log_setup(struct batadv_priv *bat_priv)
+{
+	struct dentry *d;
+
+	if (!bat_priv->debug_dir)
+		goto err;
+
+	bat_priv->debug_log = kzalloc(sizeof(*bat_priv->debug_log), GFP_ATOMIC);
+	if (!bat_priv->debug_log)
+		goto err;
+
+	spin_lock_init(&bat_priv->debug_log->lock);
+	init_waitqueue_head(&bat_priv->debug_log->queue_wait);
+
+	d = debugfs_create_file("log", S_IFREG | S_IRUSR,
+				bat_priv->debug_dir, bat_priv,
+				&batadv_log_fops);
+	if (!d)
+		goto err;
+
+	return 0;
+
+err:
+	return -ENOMEM;
+}
+
+void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
+{
+	kfree(bat_priv->debug_log);
+	bat_priv->debug_log = NULL;
+}
diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h
new file mode 100644
index 000000000000..e0e1a88c3e58
--- /dev/null
+++ b/net/batman-adv/log.h
@@ -0,0 +1,111 @@
+/* Copyright (C) 2007-2016  B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_LOG_H_
+#define _NET_BATMAN_ADV_LOG_H_
+
+#include "main.h"
+
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/printk.h>
+
+#ifdef CONFIG_BATMAN_ADV_DEBUG
+
+int batadv_debug_log_setup(struct batadv_priv *bat_priv);
+void batadv_debug_log_cleanup(struct batadv_priv *bat_priv);
+
+#else
+
+static inline int batadv_debug_log_setup(struct batadv_priv *bat_priv)
+{
+	return 0;
+}
+
+static inline void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
+{
+}
+
+#endif
+
+/**
+ * enum batadv_dbg_level - available log levels
+ * @BATADV_DBG_BATMAN: OGM and TQ computations related messages
+ * @BATADV_DBG_ROUTES: route added / changed / deleted
+ * @BATADV_DBG_TT: translation table messages
+ * @BATADV_DBG_BLA: bridge loop avoidance messages
+ * @BATADV_DBG_DAT: ARP snooping and DAT related messages
+ * @BATADV_DBG_NC: network coding related messages
+ * @BATADV_DBG_MCAST: multicast related messages
+ * @BATADV_DBG_TP_METER: throughput meter messages
+ * @BATADV_DBG_ALL: the union of all the above log levels
+ */
+enum batadv_dbg_level {
+	BATADV_DBG_BATMAN	= BIT(0),
+	BATADV_DBG_ROUTES	= BIT(1),
+	BATADV_DBG_TT		= BIT(2),
+	BATADV_DBG_BLA		= BIT(3),
+	BATADV_DBG_DAT		= BIT(4),
+	BATADV_DBG_NC		= BIT(5),
+	BATADV_DBG_MCAST	= BIT(6),
+	BATADV_DBG_TP_METER	= BIT(7),
+	BATADV_DBG_ALL		= 127,
+};
+
+#ifdef CONFIG_BATMAN_ADV_DEBUG
+int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
+__printf(2, 3);
+
+/* possibly ratelimited debug output */
+#define _batadv_dbg(type, bat_priv, ratelimited, fmt, arg...)	\
+	do {							\
+		if (atomic_read(&bat_priv->log_level) & type && \
+		    (!ratelimited || net_ratelimit()))		\
+			batadv_debug_log(bat_priv, fmt, ## arg);\
+	}							\
+	while (0)
+#else /* !CONFIG_BATMAN_ADV_DEBUG */
+__printf(4, 5)
+static inline void _batadv_dbg(int type __always_unused,
+			       struct batadv_priv *bat_priv __always_unused,
+			       int ratelimited __always_unused,
+			       const char *fmt __always_unused, ...)
+{
+}
+#endif
+
+#define batadv_dbg(type, bat_priv, arg...) \
+	_batadv_dbg(type, bat_priv, 0, ## arg)
+#define batadv_dbg_ratelimited(type, bat_priv, arg...) \
+	_batadv_dbg(type, bat_priv, 1, ## arg)
+
+#define batadv_info(net_dev, fmt, arg...)				\
+	do {								\
+		struct net_device *_netdev = (net_dev);                 \
+		struct batadv_priv *_batpriv = netdev_priv(_netdev);    \
+		batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg);	\
+		pr_info("%s: " fmt, _netdev->name, ## arg);		\
+	} while (0)
+#define batadv_err(net_dev, fmt, arg...)				\
+	do {								\
+		struct net_device *_netdev = (net_dev);                 \
+		struct batadv_priv *_batpriv = netdev_priv(_netdev);    \
+		batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg);	\
+		pr_err("%s: " fmt, _netdev->name, ## arg);		\
+	} while (0)
+
+#endif /* _NET_BATMAN_ADV_LOG_H_ */
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 5f2974bd1227..fe4c5e29f96b 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -31,16 +31,13 @@
 #include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/list.h>
-#include <linux/lockdep.h>
 #include <linux/module.h>
-#include <linux/moduleparam.h>
 #include <linux/netdevice.h>
-#include <linux/pkt_sched.h>
+#include <linux/printk.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
 #include <linux/seq_file.h>
 #include <linux/skbuff.h>
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/stddef.h>
 #include <linux/string.h>
@@ -49,6 +46,8 @@
 #include <net/rtnetlink.h>
 
 #include "bat_algo.h"
+#include "bat_iv_ogm.h"
+#include "bat_v.h"
 #include "bridge_loop_avoidance.h"
 #include "debugfs.h"
 #include "distributed-arp-table.h"
@@ -56,13 +55,16 @@
 #include "gateway_common.h"
 #include "hard-interface.h"
 #include "icmp_socket.h"
+#include "log.h"
 #include "multicast.h"
+#include "netlink.h"
 #include "network-coding.h"
 #include "originator.h"
 #include "packet.h"
 #include "routing.h"
 #include "send.h"
 #include "soft-interface.h"
+#include "tp_meter.h"
 #include "translation-table.h"
 
 /* List manipulations on hardif_list have to be rtnl_lock()'ed,
@@ -71,8 +73,6 @@
 struct list_head batadv_hardif_list;
 static int (*batadv_rx_handler[256])(struct sk_buff *,
 				     struct batadv_hard_iface *);
-char batadv_routing_algo[20] = "BATMAN_IV";
-static struct hlist_head batadv_algo_list;
 
 unsigned char batadv_broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
 
@@ -83,13 +83,14 @@ static void batadv_recv_handler_init(void);
 static int __init batadv_init(void)
 {
 	INIT_LIST_HEAD(&batadv_hardif_list);
-	INIT_HLIST_HEAD(&batadv_algo_list);
+	batadv_algo_init();
 
 	batadv_recv_handler_init();
 
 	batadv_v_init();
 	batadv_iv_init();
 	batadv_nc_init();
+	batadv_tp_meter_init();
 
 	batadv_event_workqueue = create_singlethread_workqueue("bat_events");
 
@@ -101,6 +102,7 @@ static int __init batadv_init(void)
 
 	register_netdevice_notifier(&batadv_hard_if_notifier);
 	rtnl_link_register(&batadv_link_ops);
+	batadv_netlink_register();
 
 	pr_info("B.A.T.M.A.N. advanced %s (compatibility version %i) loaded\n",
 		BATADV_SOURCE_VERSION, BATADV_COMPAT_VERSION);
@@ -111,6 +113,7 @@ static int __init batadv_init(void)
 static void __exit batadv_exit(void)
 {
 	batadv_debugfs_destroy();
+	batadv_netlink_unregister();
 	rtnl_link_unregister(&batadv_link_ops);
 	unregister_netdevice_notifier(&batadv_hard_if_notifier);
 	batadv_hardif_remove_interfaces();
@@ -141,6 +144,7 @@ int batadv_mesh_init(struct net_device *soft_iface)
 	spin_lock_init(&bat_priv->tvlv.container_list_lock);
 	spin_lock_init(&bat_priv->tvlv.handler_list_lock);
 	spin_lock_init(&bat_priv->softif_vlan_list_lock);
+	spin_lock_init(&bat_priv->tp_list_lock);
 
 	INIT_HLIST_HEAD(&bat_priv->forw_bat_list);
 	INIT_HLIST_HEAD(&bat_priv->forw_bcast_list);
@@ -159,6 +163,7 @@ int batadv_mesh_init(struct net_device *soft_iface)
 	INIT_HLIST_HEAD(&bat_priv->tvlv.container_list);
 	INIT_HLIST_HEAD(&bat_priv->tvlv.handler_list);
 	INIT_HLIST_HEAD(&bat_priv->softif_vlan_list);
+	INIT_HLIST_HEAD(&bat_priv->tp_list);
 
 	ret = batadv_v_mesh_init(bat_priv);
 	if (ret < 0)
@@ -538,78 +543,6 @@ void batadv_recv_handler_unregister(u8 packet_type)
 	batadv_rx_handler[packet_type] = batadv_recv_unhandled_packet;
 }
 
-static struct batadv_algo_ops *batadv_algo_get(char *name)
-{
-	struct batadv_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp;
-
-	hlist_for_each_entry(bat_algo_ops_tmp, &batadv_algo_list, list) {
-		if (strcmp(bat_algo_ops_tmp->name, name) != 0)
-			continue;
-
-		bat_algo_ops = bat_algo_ops_tmp;
-		break;
-	}
-
-	return bat_algo_ops;
-}
-
-int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops)
-{
-	struct batadv_algo_ops *bat_algo_ops_tmp;
-
-	bat_algo_ops_tmp = batadv_algo_get(bat_algo_ops->name);
-	if (bat_algo_ops_tmp) {
-		pr_info("Trying to register already registered routing algorithm: %s\n",
-			bat_algo_ops->name);
-		return -EEXIST;
-	}
-
-	/* all algorithms must implement all ops (for now) */
-	if (!bat_algo_ops->bat_iface_enable ||
-	    !bat_algo_ops->bat_iface_disable ||
-	    !bat_algo_ops->bat_iface_update_mac ||
-	    !bat_algo_ops->bat_primary_iface_set ||
-	    !bat_algo_ops->bat_ogm_schedule ||
-	    !bat_algo_ops->bat_ogm_emit ||
-	    !bat_algo_ops->bat_neigh_cmp ||
-	    !bat_algo_ops->bat_neigh_is_similar_or_better) {
-		pr_info("Routing algo '%s' does not implement required ops\n",
-			bat_algo_ops->name);
-		return -EINVAL;
-	}
-
-	INIT_HLIST_NODE(&bat_algo_ops->list);
-	hlist_add_head(&bat_algo_ops->list, &batadv_algo_list);
-
-	return 0;
-}
-
-int batadv_algo_select(struct batadv_priv *bat_priv, char *name)
-{
-	struct batadv_algo_ops *bat_algo_ops;
-
-	bat_algo_ops = batadv_algo_get(name);
-	if (!bat_algo_ops)
-		return -EINVAL;
-
-	bat_priv->bat_algo_ops = bat_algo_ops;
-
-	return 0;
-}
-
-int batadv_algo_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct batadv_algo_ops *bat_algo_ops;
-
-	seq_puts(seq, "Available routing algorithms:\n");
-
-	hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) {
-		seq_printf(seq, " * %s\n", bat_algo_ops->name);
-	}
-
-	return 0;
-}
-
 /**
  * batadv_skb_crc32 - calculate CRC32 of the whole packet and skip bytes in
  *  the header
@@ -644,594 +577,6 @@ __be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr)
 }
 
 /**
- * batadv_tvlv_handler_release - release tvlv handler from lists and queue for
- *  free after rcu grace period
- * @ref: kref pointer of the tvlv
- */
-static void batadv_tvlv_handler_release(struct kref *ref)
-{
-	struct batadv_tvlv_handler *tvlv_handler;
-
-	tvlv_handler = container_of(ref, struct batadv_tvlv_handler, refcount);
-	kfree_rcu(tvlv_handler, rcu);
-}
-
-/**
- * batadv_tvlv_handler_put - decrement the tvlv container refcounter and
- *  possibly release it
- * @tvlv_handler: the tvlv handler to free
- */
-static void batadv_tvlv_handler_put(struct batadv_tvlv_handler *tvlv_handler)
-{
-	kref_put(&tvlv_handler->refcount, batadv_tvlv_handler_release);
-}
-
-/**
- * batadv_tvlv_handler_get - retrieve tvlv handler from the tvlv handler list
- *  based on the provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
- * @type: tvlv handler type to look for
- * @version: tvlv handler version to look for
- *
- * Return: tvlv handler if found or NULL otherwise.
- */
-static struct batadv_tvlv_handler *
-batadv_tvlv_handler_get(struct batadv_priv *bat_priv, u8 type, u8 version)
-{
-	struct batadv_tvlv_handler *tvlv_handler_tmp, *tvlv_handler = NULL;
-
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(tvlv_handler_tmp,
-				 &bat_priv->tvlv.handler_list, list) {
-		if (tvlv_handler_tmp->type != type)
-			continue;
-
-		if (tvlv_handler_tmp->version != version)
-			continue;
-
-		if (!kref_get_unless_zero(&tvlv_handler_tmp->refcount))
-			continue;
-
-		tvlv_handler = tvlv_handler_tmp;
-		break;
-	}
-	rcu_read_unlock();
-
-	return tvlv_handler;
-}
-
-/**
- * batadv_tvlv_container_release - release tvlv from lists and free
- * @ref: kref pointer of the tvlv
- */
-static void batadv_tvlv_container_release(struct kref *ref)
-{
-	struct batadv_tvlv_container *tvlv;
-
-	tvlv = container_of(ref, struct batadv_tvlv_container, refcount);
-	kfree(tvlv);
-}
-
-/**
- * batadv_tvlv_container_put - decrement the tvlv container refcounter and
- *  possibly release it
- * @tvlv: the tvlv container to free
- */
-static void batadv_tvlv_container_put(struct batadv_tvlv_container *tvlv)
-{
-	kref_put(&tvlv->refcount, batadv_tvlv_container_release);
-}
-
-/**
- * batadv_tvlv_container_get - retrieve tvlv container from the tvlv container
- *  list based on the provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
- * @type: tvlv container type to look for
- * @version: tvlv container version to look for
- *
- * Has to be called with the appropriate locks being acquired
- * (tvlv.container_list_lock).
- *
- * Return: tvlv container if found or NULL otherwise.
- */
-static struct batadv_tvlv_container *
-batadv_tvlv_container_get(struct batadv_priv *bat_priv, u8 type, u8 version)
-{
-	struct batadv_tvlv_container *tvlv_tmp, *tvlv = NULL;
-
-	lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
-
-	hlist_for_each_entry(tvlv_tmp, &bat_priv->tvlv.container_list, list) {
-		if (tvlv_tmp->tvlv_hdr.type != type)
-			continue;
-
-		if (tvlv_tmp->tvlv_hdr.version != version)
-			continue;
-
-		kref_get(&tvlv_tmp->refcount);
-		tvlv = tvlv_tmp;
-		break;
-	}
-
-	return tvlv;
-}
-
-/**
- * batadv_tvlv_container_list_size - calculate the size of the tvlv container
- *  list entries
- * @bat_priv: the bat priv with all the soft interface information
- *
- * Has to be called with the appropriate locks being acquired
- * (tvlv.container_list_lock).
- *
- * Return: size of all currently registered tvlv containers in bytes.
- */
-static u16 batadv_tvlv_container_list_size(struct batadv_priv *bat_priv)
-{
-	struct batadv_tvlv_container *tvlv;
-	u16 tvlv_len = 0;
-
-	lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
-
-	hlist_for_each_entry(tvlv, &bat_priv->tvlv.container_list, list) {
-		tvlv_len += sizeof(struct batadv_tvlv_hdr);
-		tvlv_len += ntohs(tvlv->tvlv_hdr.len);
-	}
-
-	return tvlv_len;
-}
-
-/**
- * batadv_tvlv_container_remove - remove tvlv container from the tvlv container
- *  list
- * @bat_priv: the bat priv with all the soft interface information
- * @tvlv: the to be removed tvlv container
- *
- * Has to be called with the appropriate locks being acquired
- * (tvlv.container_list_lock).
- */
-static void batadv_tvlv_container_remove(struct batadv_priv *bat_priv,
-					 struct batadv_tvlv_container *tvlv)
-{
-	lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
-
-	if (!tvlv)
-		return;
-
-	hlist_del(&tvlv->list);
-
-	/* first call to decrement the counter, second call to free */
-	batadv_tvlv_container_put(tvlv);
-	batadv_tvlv_container_put(tvlv);
-}
-
-/**
- * batadv_tvlv_container_unregister - unregister tvlv container based on the
- *  provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
- * @type: tvlv container type to unregister
- * @version: tvlv container type to unregister
- */
-void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv,
-				      u8 type, u8 version)
-{
-	struct batadv_tvlv_container *tvlv;
-
-	spin_lock_bh(&bat_priv->tvlv.container_list_lock);
-	tvlv = batadv_tvlv_container_get(bat_priv, type, version);
-	batadv_tvlv_container_remove(bat_priv, tvlv);
-	spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
-}
-
-/**
- * batadv_tvlv_container_register - register tvlv type, version and content
- *  to be propagated with each (primary interface) OGM
- * @bat_priv: the bat priv with all the soft interface information
- * @type: tvlv container type
- * @version: tvlv container version
- * @tvlv_value: tvlv container content
- * @tvlv_value_len: tvlv container content length
- *
- * If a container of the same type and version was already registered the new
- * content is going to replace the old one.
- */
-void batadv_tvlv_container_register(struct batadv_priv *bat_priv,
-				    u8 type, u8 version,
-				    void *tvlv_value, u16 tvlv_value_len)
-{
-	struct batadv_tvlv_container *tvlv_old, *tvlv_new;
-
-	if (!tvlv_value)
-		tvlv_value_len = 0;
-
-	tvlv_new = kzalloc(sizeof(*tvlv_new) + tvlv_value_len, GFP_ATOMIC);
-	if (!tvlv_new)
-		return;
-
-	tvlv_new->tvlv_hdr.version = version;
-	tvlv_new->tvlv_hdr.type = type;
-	tvlv_new->tvlv_hdr.len = htons(tvlv_value_len);
-
-	memcpy(tvlv_new + 1, tvlv_value, ntohs(tvlv_new->tvlv_hdr.len));
-	INIT_HLIST_NODE(&tvlv_new->list);
-	kref_init(&tvlv_new->refcount);
-
-	spin_lock_bh(&bat_priv->tvlv.container_list_lock);
-	tvlv_old = batadv_tvlv_container_get(bat_priv, type, version);
-	batadv_tvlv_container_remove(bat_priv, tvlv_old);
-	hlist_add_head(&tvlv_new->list, &bat_priv->tvlv.container_list);
-	spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
-}
-
-/**
- * batadv_tvlv_realloc_packet_buff - reallocate packet buffer to accommodate
- *  requested packet size
- * @packet_buff: packet buffer
- * @packet_buff_len: packet buffer size
- * @min_packet_len: requested packet minimum size
- * @additional_packet_len: requested additional packet size on top of minimum
- *  size
- *
- * Return: true of the packet buffer could be changed to the requested size,
- * false otherwise.
- */
-static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff,
-					    int *packet_buff_len,
-					    int min_packet_len,
-					    int additional_packet_len)
-{
-	unsigned char *new_buff;
-
-	new_buff = kmalloc(min_packet_len + additional_packet_len, GFP_ATOMIC);
-
-	/* keep old buffer if kmalloc should fail */
-	if (!new_buff)
-		return false;
-
-	memcpy(new_buff, *packet_buff, min_packet_len);
-	kfree(*packet_buff);
-	*packet_buff = new_buff;
-	*packet_buff_len = min_packet_len + additional_packet_len;
-
-	return true;
-}
-
-/**
- * batadv_tvlv_container_ogm_append - append tvlv container content to given
- *  OGM packet buffer
- * @bat_priv: the bat priv with all the soft interface information
- * @packet_buff: ogm packet buffer
- * @packet_buff_len: ogm packet buffer size including ogm header and tvlv
- *  content
- * @packet_min_len: ogm header size to be preserved for the OGM itself
- *
- * The ogm packet might be enlarged or shrunk depending on the current size
- * and the size of the to-be-appended tvlv containers.
- *
- * Return: size of all appended tvlv containers in bytes.
- */
-u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv,
-				     unsigned char **packet_buff,
-				     int *packet_buff_len, int packet_min_len)
-{
-	struct batadv_tvlv_container *tvlv;
-	struct batadv_tvlv_hdr *tvlv_hdr;
-	u16 tvlv_value_len;
-	void *tvlv_value;
-	bool ret;
-
-	spin_lock_bh(&bat_priv->tvlv.container_list_lock);
-	tvlv_value_len = batadv_tvlv_container_list_size(bat_priv);
-
-	ret = batadv_tvlv_realloc_packet_buff(packet_buff, packet_buff_len,
-					      packet_min_len, tvlv_value_len);
-
-	if (!ret)
-		goto end;
-
-	if (!tvlv_value_len)
-		goto end;
-
-	tvlv_value = (*packet_buff) + packet_min_len;
-
-	hlist_for_each_entry(tvlv, &bat_priv->tvlv.container_list, list) {
-		tvlv_hdr = tvlv_value;
-		tvlv_hdr->type = tvlv->tvlv_hdr.type;
-		tvlv_hdr->version = tvlv->tvlv_hdr.version;
-		tvlv_hdr->len = tvlv->tvlv_hdr.len;
-		tvlv_value = tvlv_hdr + 1;
-		memcpy(tvlv_value, tvlv + 1, ntohs(tvlv->tvlv_hdr.len));
-		tvlv_value = (u8 *)tvlv_value + ntohs(tvlv->tvlv_hdr.len);
-	}
-
-end:
-	spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
-	return tvlv_value_len;
-}
-
-/**
- * batadv_tvlv_call_handler - parse the given tvlv buffer to call the
- *  appropriate handlers
- * @bat_priv: the bat priv with all the soft interface information
- * @tvlv_handler: tvlv callback function handling the tvlv content
- * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet
- * @orig_node: orig node emitting the ogm packet
- * @src: source mac address of the unicast packet
- * @dst: destination mac address of the unicast packet
- * @tvlv_value: tvlv content
- * @tvlv_value_len: tvlv content length
- *
- * Return: success if handler was not found or the return value of the handler
- * callback.
- */
-static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv,
-				    struct batadv_tvlv_handler *tvlv_handler,
-				    bool ogm_source,
-				    struct batadv_orig_node *orig_node,
-				    u8 *src, u8 *dst,
-				    void *tvlv_value, u16 tvlv_value_len)
-{
-	if (!tvlv_handler)
-		return NET_RX_SUCCESS;
-
-	if (ogm_source) {
-		if (!tvlv_handler->ogm_handler)
-			return NET_RX_SUCCESS;
-
-		if (!orig_node)
-			return NET_RX_SUCCESS;
-
-		tvlv_handler->ogm_handler(bat_priv, orig_node,
-					  BATADV_NO_FLAGS,
-					  tvlv_value, tvlv_value_len);
-		tvlv_handler->flags |= BATADV_TVLV_HANDLER_OGM_CALLED;
-	} else {
-		if (!src)
-			return NET_RX_SUCCESS;
-
-		if (!dst)
-			return NET_RX_SUCCESS;
-
-		if (!tvlv_handler->unicast_handler)
-			return NET_RX_SUCCESS;
-
-		return tvlv_handler->unicast_handler(bat_priv, src,
-						     dst, tvlv_value,
-						     tvlv_value_len);
-	}
-
-	return NET_RX_SUCCESS;
-}
-
-/**
- * batadv_tvlv_containers_process - parse the given tvlv buffer to call the
- *  appropriate handlers
- * @bat_priv: the bat priv with all the soft interface information
- * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet
- * @orig_node: orig node emitting the ogm packet
- * @src: source mac address of the unicast packet
- * @dst: destination mac address of the unicast packet
- * @tvlv_value: tvlv content
- * @tvlv_value_len: tvlv content length
- *
- * Return: success when processing an OGM or the return value of all called
- * handler callbacks.
- */
-int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
-				   bool ogm_source,
-				   struct batadv_orig_node *orig_node,
-				   u8 *src, u8 *dst,
-				   void *tvlv_value, u16 tvlv_value_len)
-{
-	struct batadv_tvlv_handler *tvlv_handler;
-	struct batadv_tvlv_hdr *tvlv_hdr;
-	u16 tvlv_value_cont_len;
-	u8 cifnotfound = BATADV_TVLV_HANDLER_OGM_CIFNOTFND;
-	int ret = NET_RX_SUCCESS;
-
-	while (tvlv_value_len >= sizeof(*tvlv_hdr)) {
-		tvlv_hdr = tvlv_value;
-		tvlv_value_cont_len = ntohs(tvlv_hdr->len);
-		tvlv_value = tvlv_hdr + 1;
-		tvlv_value_len -= sizeof(*tvlv_hdr);
-
-		if (tvlv_value_cont_len > tvlv_value_len)
-			break;
-
-		tvlv_handler = batadv_tvlv_handler_get(bat_priv,
-						       tvlv_hdr->type,
-						       tvlv_hdr->version);
-
-		ret |= batadv_tvlv_call_handler(bat_priv, tvlv_handler,
-						ogm_source, orig_node,
-						src, dst, tvlv_value,
-						tvlv_value_cont_len);
-		if (tvlv_handler)
-			batadv_tvlv_handler_put(tvlv_handler);
-		tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len;
-		tvlv_value_len -= tvlv_value_cont_len;
-	}
-
-	if (!ogm_source)
-		return ret;
-
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(tvlv_handler,
-				 &bat_priv->tvlv.handler_list, list) {
-		if ((tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) &&
-		    !(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CALLED))
-			tvlv_handler->ogm_handler(bat_priv, orig_node,
-						  cifnotfound, NULL, 0);
-
-		tvlv_handler->flags &= ~BATADV_TVLV_HANDLER_OGM_CALLED;
-	}
-	rcu_read_unlock();
-
-	return NET_RX_SUCCESS;
-}
-
-/**
- * batadv_tvlv_ogm_receive - process an incoming ogm and call the appropriate
- *  handlers
- * @bat_priv: the bat priv with all the soft interface information
- * @batadv_ogm_packet: ogm packet containing the tvlv containers
- * @orig_node: orig node emitting the ogm packet
- */
-void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv,
-			     struct batadv_ogm_packet *batadv_ogm_packet,
-			     struct batadv_orig_node *orig_node)
-{
-	void *tvlv_value;
-	u16 tvlv_value_len;
-
-	if (!batadv_ogm_packet)
-		return;
-
-	tvlv_value_len = ntohs(batadv_ogm_packet->tvlv_len);
-	if (!tvlv_value_len)
-		return;
-
-	tvlv_value = batadv_ogm_packet + 1;
-
-	batadv_tvlv_containers_process(bat_priv, true, orig_node, NULL, NULL,
-				       tvlv_value, tvlv_value_len);
-}
-
-/**
- * batadv_tvlv_handler_register - register tvlv handler based on the provided
- *  type and version (both need to match) for ogm tvlv payload and/or unicast
- *  payload
- * @bat_priv: the bat priv with all the soft interface information
- * @optr: ogm tvlv handler callback function. This function receives the orig
- *  node, flags and the tvlv content as argument to process.
- * @uptr: unicast tvlv handler callback function. This function receives the
- *  source & destination of the unicast packet as well as the tvlv content
- *  to process.
- * @type: tvlv handler type to be registered
- * @version: tvlv handler version to be registered
- * @flags: flags to enable or disable TVLV API behavior
- */
-void batadv_tvlv_handler_register(struct batadv_priv *bat_priv,
-				  void (*optr)(struct batadv_priv *bat_priv,
-					       struct batadv_orig_node *orig,
-					       u8 flags,
-					       void *tvlv_value,
-					       u16 tvlv_value_len),
-				  int (*uptr)(struct batadv_priv *bat_priv,
-					      u8 *src, u8 *dst,
-					      void *tvlv_value,
-					      u16 tvlv_value_len),
-				  u8 type, u8 version, u8 flags)
-{
-	struct batadv_tvlv_handler *tvlv_handler;
-
-	tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version);
-	if (tvlv_handler) {
-		batadv_tvlv_handler_put(tvlv_handler);
-		return;
-	}
-
-	tvlv_handler = kzalloc(sizeof(*tvlv_handler), GFP_ATOMIC);
-	if (!tvlv_handler)
-		return;
-
-	tvlv_handler->ogm_handler = optr;
-	tvlv_handler->unicast_handler = uptr;
-	tvlv_handler->type = type;
-	tvlv_handler->version = version;
-	tvlv_handler->flags = flags;
-	kref_init(&tvlv_handler->refcount);
-	INIT_HLIST_NODE(&tvlv_handler->list);
-
-	spin_lock_bh(&bat_priv->tvlv.handler_list_lock);
-	hlist_add_head_rcu(&tvlv_handler->list, &bat_priv->tvlv.handler_list);
-	spin_unlock_bh(&bat_priv->tvlv.handler_list_lock);
-}
-
-/**
- * batadv_tvlv_handler_unregister - unregister tvlv handler based on the
- *  provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
- * @type: tvlv handler type to be unregistered
- * @version: tvlv handler version to be unregistered
- */
-void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv,
-				    u8 type, u8 version)
-{
-	struct batadv_tvlv_handler *tvlv_handler;
-
-	tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version);
-	if (!tvlv_handler)
-		return;
-
-	batadv_tvlv_handler_put(tvlv_handler);
-	spin_lock_bh(&bat_priv->tvlv.handler_list_lock);
-	hlist_del_rcu(&tvlv_handler->list);
-	spin_unlock_bh(&bat_priv->tvlv.handler_list_lock);
-	batadv_tvlv_handler_put(tvlv_handler);
-}
-
-/**
- * batadv_tvlv_unicast_send - send a unicast packet with tvlv payload to the
- *  specified host
- * @bat_priv: the bat priv with all the soft interface information
- * @src: source mac address of the unicast packet
- * @dst: destination mac address of the unicast packet
- * @type: tvlv type
- * @version: tvlv version
- * @tvlv_value: tvlv content
- * @tvlv_value_len: tvlv content length
- */
-void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src,
-			      u8 *dst, u8 type, u8 version,
-			      void *tvlv_value, u16 tvlv_value_len)
-{
-	struct batadv_unicast_tvlv_packet *unicast_tvlv_packet;
-	struct batadv_tvlv_hdr *tvlv_hdr;
-	struct batadv_orig_node *orig_node;
-	struct sk_buff *skb;
-	unsigned char *tvlv_buff;
-	unsigned int tvlv_len;
-	ssize_t hdr_len = sizeof(*unicast_tvlv_packet);
-
-	orig_node = batadv_orig_hash_find(bat_priv, dst);
-	if (!orig_node)
-		return;
-
-	tvlv_len = sizeof(*tvlv_hdr) + tvlv_value_len;
-
-	skb = netdev_alloc_skb_ip_align(NULL, ETH_HLEN + hdr_len + tvlv_len);
-	if (!skb)
-		goto out;
-
-	skb->priority = TC_PRIO_CONTROL;
-	skb_reserve(skb, ETH_HLEN);
-	tvlv_buff = skb_put(skb, sizeof(*unicast_tvlv_packet) + tvlv_len);
-	unicast_tvlv_packet = (struct batadv_unicast_tvlv_packet *)tvlv_buff;
-	unicast_tvlv_packet->packet_type = BATADV_UNICAST_TVLV;
-	unicast_tvlv_packet->version = BATADV_COMPAT_VERSION;
-	unicast_tvlv_packet->ttl = BATADV_TTL;
-	unicast_tvlv_packet->reserved = 0;
-	unicast_tvlv_packet->tvlv_len = htons(tvlv_len);
-	unicast_tvlv_packet->align = 0;
-	ether_addr_copy(unicast_tvlv_packet->src, src);
-	ether_addr_copy(unicast_tvlv_packet->dst, dst);
-
-	tvlv_buff = (unsigned char *)(unicast_tvlv_packet + 1);
-	tvlv_hdr = (struct batadv_tvlv_hdr *)tvlv_buff;
-	tvlv_hdr->version = version;
-	tvlv_hdr->type = type;
-	tvlv_hdr->len = htons(tvlv_value_len);
-	tvlv_buff += sizeof(*tvlv_hdr);
-	memcpy(tvlv_buff, tvlv_value, tvlv_value_len);
-
-	if (batadv_send_skb_to_orig(skb, orig_node, NULL) == NET_XMIT_DROP)
-		kfree_skb(skb);
-out:
-	batadv_orig_node_put(orig_node);
-}
-
-/**
  * batadv_get_vid - extract the VLAN identifier from skb if any
  * @skb: the buffer containing the packet
  * @header_len: length of the batman header preceding the ethernet header
@@ -1284,36 +629,6 @@ bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid)
 	return ap_isolation_enabled;
 }
 
-static int batadv_param_set_ra(const char *val, const struct kernel_param *kp)
-{
-	struct batadv_algo_ops *bat_algo_ops;
-	char *algo_name = (char *)val;
-	size_t name_len = strlen(algo_name);
-
-	if (name_len > 0 && algo_name[name_len - 1] == '\n')
-		algo_name[name_len - 1] = '\0';
-
-	bat_algo_ops = batadv_algo_get(algo_name);
-	if (!bat_algo_ops) {
-		pr_err("Routing algorithm '%s' is not supported\n", algo_name);
-		return -EINVAL;
-	}
-
-	return param_set_copystring(algo_name, kp);
-}
-
-static const struct kernel_param_ops batadv_param_ops_ra = {
-	.set = batadv_param_set_ra,
-	.get = param_get_string,
-};
-
-static struct kparam_string batadv_param_string_ra = {
-	.maxlen = sizeof(batadv_routing_algo),
-	.string = batadv_routing_algo,
-};
-
-module_param_cb(routing_algo, &batadv_param_ops_ra, &batadv_param_string_ra,
-		0644);
 module_init(batadv_init);
 module_exit(batadv_exit);
 
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 76925266deed..06a860845434 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -24,7 +24,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2016.2"
+#define BATADV_SOURCE_VERSION "2016.3"
 #endif
 
 /* B.A.T.M.A.N. parameters */
@@ -100,6 +100,9 @@
 #define BATADV_NUM_BCASTS_WIRELESS 3
 #define BATADV_NUM_BCASTS_MAX 3
 
+/* length of the single packet used by the TP meter */
+#define BATADV_TP_PACKET_LEN ETH_DATA_LEN
+
 /* msecs after which an ARP_REQUEST is sent in broadcast as fallback */
 #define ARP_REQ_DELAY 250
 /* numbers of originator to contact for any PUT/GET DHT operation */
@@ -131,6 +134,11 @@
 
 #define BATADV_NC_NODE_TIMEOUT 10000 /* Milliseconds */
 
+/**
+ * BATADV_TP_MAX_NUM - maximum number of simultaneously active tp sessions
+ */
+#define BATADV_TP_MAX_NUM 5
+
 enum batadv_mesh_state {
 	BATADV_MESH_INACTIVE,
 	BATADV_MESH_ACTIVE,
@@ -175,29 +183,26 @@ enum batadv_uev_type {
 
 /* Kernel headers */
 
-#include <linux/atomic.h>
 #include <linux/bitops.h> /* for packet.h */
 #include <linux/compiler.h>
 #include <linux/cpumask.h>
 #include <linux/etherdevice.h>
 #include <linux/if_ether.h> /* for packet.h */
-#include <linux/netdevice.h>
-#include <linux/printk.h>
-#include <linux/types.h>
-#include <linux/percpu.h>
-#include <linux/jiffies.h>
 #include <linux/if_vlan.h>
+#include <linux/jiffies.h>
+#include <linux/percpu.h>
+#include <linux/types.h>
 
 #include "types.h"
 
-struct batadv_ogm_packet;
+struct net_device;
+struct packet_type;
 struct seq_file;
 struct sk_buff;
 
 #define BATADV_PRINT_VID(vid) ((vid & BATADV_VLAN_HAS_TAG) ? \
 			       (int)(vid & VLAN_VID_MASK) : -1)
 
-extern char batadv_routing_algo[];
 extern struct list_head batadv_hardif_list;
 
 extern unsigned char batadv_broadcast_addr[];
@@ -218,74 +223,9 @@ batadv_recv_handler_register(u8 packet_type,
 			     int (*recv_handler)(struct sk_buff *,
 						 struct batadv_hard_iface *));
 void batadv_recv_handler_unregister(u8 packet_type);
-int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops);
-int batadv_algo_select(struct batadv_priv *bat_priv, char *name);
-int batadv_algo_seq_print_text(struct seq_file *seq, void *offset);
 __be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr);
 
 /**
- * enum batadv_dbg_level - available log levels
- * @BATADV_DBG_BATMAN: OGM and TQ computations related messages
- * @BATADV_DBG_ROUTES: route added / changed / deleted
- * @BATADV_DBG_TT: translation table messages
- * @BATADV_DBG_BLA: bridge loop avoidance messages
- * @BATADV_DBG_DAT: ARP snooping and DAT related messages
- * @BATADV_DBG_NC: network coding related messages
- * @BATADV_DBG_ALL: the union of all the above log levels
- */
-enum batadv_dbg_level {
-	BATADV_DBG_BATMAN = BIT(0),
-	BATADV_DBG_ROUTES = BIT(1),
-	BATADV_DBG_TT	  = BIT(2),
-	BATADV_DBG_BLA    = BIT(3),
-	BATADV_DBG_DAT    = BIT(4),
-	BATADV_DBG_NC	  = BIT(5),
-	BATADV_DBG_ALL    = 63,
-};
-
-#ifdef CONFIG_BATMAN_ADV_DEBUG
-int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
-__printf(2, 3);
-
-/* possibly ratelimited debug output */
-#define _batadv_dbg(type, bat_priv, ratelimited, fmt, arg...)	\
-	do {							\
-		if (atomic_read(&bat_priv->log_level) & type && \
-		    (!ratelimited || net_ratelimit()))		\
-			batadv_debug_log(bat_priv, fmt, ## arg);\
-	}							\
-	while (0)
-#else /* !CONFIG_BATMAN_ADV_DEBUG */
-__printf(4, 5)
-static inline void _batadv_dbg(int type __always_unused,
-			       struct batadv_priv *bat_priv __always_unused,
-			       int ratelimited __always_unused,
-			       const char *fmt __always_unused, ...)
-{
-}
-#endif
-
-#define batadv_dbg(type, bat_priv, arg...) \
-	_batadv_dbg(type, bat_priv, 0, ## arg)
-#define batadv_dbg_ratelimited(type, bat_priv, arg...) \
-	_batadv_dbg(type, bat_priv, 1, ## arg)
-
-#define batadv_info(net_dev, fmt, arg...)				\
-	do {								\
-		struct net_device *_netdev = (net_dev);                 \
-		struct batadv_priv *_batpriv = netdev_priv(_netdev);    \
-		batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg);	\
-		pr_info("%s: " fmt, _netdev->name, ## arg);		\
-	} while (0)
-#define batadv_err(net_dev, fmt, arg...)				\
-	do {								\
-		struct net_device *_netdev = (net_dev);                 \
-		struct batadv_priv *_batpriv = netdev_priv(_netdev);    \
-		batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg);	\
-		pr_err("%s: " fmt, _netdev->name, ## arg);		\
-	} while (0)
-
-/**
  * batadv_compare_eth - Compare two not u16 aligned Ethernet addresses
  * @data1: Pointer to a six-byte array containing the Ethernet address
  * @data2: Pointer other six-byte array containing the Ethernet address
@@ -370,39 +310,6 @@ static inline u64 batadv_sum_counter(struct batadv_priv *bat_priv,  size_t idx)
  */
 #define BATADV_SKB_CB(__skb)       ((struct batadv_skb_cb *)&((__skb)->cb[0]))
 
-void batadv_tvlv_container_register(struct batadv_priv *bat_priv,
-				    u8 type, u8 version,
-				    void *tvlv_value, u16 tvlv_value_len);
-u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv,
-				     unsigned char **packet_buff,
-				     int *packet_buff_len, int packet_min_len);
-void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv,
-			     struct batadv_ogm_packet *batadv_ogm_packet,
-			     struct batadv_orig_node *orig_node);
-void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv,
-				      u8 type, u8 version);
-
-void batadv_tvlv_handler_register(struct batadv_priv *bat_priv,
-				  void (*optr)(struct batadv_priv *bat_priv,
-					       struct batadv_orig_node *orig,
-					       u8 flags,
-					       void *tvlv_value,
-					       u16 tvlv_value_len),
-				  int (*uptr)(struct batadv_priv *bat_priv,
-					      u8 *src, u8 *dst,
-					      void *tvlv_value,
-					      u16 tvlv_value_len),
-				  u8 type, u8 version, u8 flags);
-void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv,
-				    u8 type, u8 version);
-int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
-				   bool ogm_source,
-				   struct batadv_orig_node *orig_node,
-				   u8 *src, u8 *dst,
-				   void *tvlv_buff, u16 tvlv_buff_len);
-void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src,
-			      u8 *dst, u8 type, u8 version,
-			      void *tvlv_value, u16 tvlv_value_len);
 unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len);
 bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid);
 
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index c32f24fafe67..cc915073a753 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -25,17 +25,23 @@
 #include <linux/errno.h>
 #include <linux/etherdevice.h>
 #include <linux/fs.h>
+#include <linux/icmpv6.h>
+#include <linux/if_bridge.h>
 #include <linux/if_ether.h>
-#include <linux/in6.h>
+#include <linux/igmp.h>
 #include <linux/in.h>
+#include <linux/in6.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
+#include <linux/printk.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
+#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -43,18 +49,57 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <net/addrconf.h>
+#include <net/if_inet6.h>
+#include <net/ip.h>
 #include <net/ipv6.h>
 
+#include "hard-interface.h"
+#include "hash.h"
+#include "log.h"
 #include "packet.h"
 #include "translation-table.h"
+#include "tvlv.h"
+
+/**
+ * batadv_mcast_get_bridge - get the bridge on top of the softif if it exists
+ * @soft_iface: netdev struct of the mesh interface
+ *
+ * If the given soft interface has a bridge on top then the refcount
+ * of the according net device is increased.
+ *
+ * Return: NULL if no such bridge exists. Otherwise the net device of the
+ * bridge.
+ */
+static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface)
+{
+	struct net_device *upper = soft_iface;
+
+	rcu_read_lock();
+	do {
+		upper = netdev_master_upper_dev_get_rcu(upper);
+	} while (upper && !(upper->priv_flags & IFF_EBRIDGE));
+
+	if (upper)
+		dev_hold(upper);
+	rcu_read_unlock();
+
+	return upper;
+}
 
 /**
  * batadv_mcast_mla_softif_get - get softif multicast listeners
  * @dev: the device to collect multicast addresses from
  * @mcast_list: a list to put found addresses into
  *
- * Collect multicast addresses of the local multicast listeners
- * on the given soft interface, dev, in the given mcast_list.
+ * Collects multicast addresses of multicast listeners residing
+ * on this kernel on the given soft interface, dev, in
+ * the given mcast_list. In general, multicast listeners provided by
+ * your multicast receiving applications run directly on this node.
+ *
+ * If there is a bridge interface on top of dev, collects from that one
+ * instead. Just like with IP addresses and routes, multicast listeners
+ * will(/should) register to the bridge interface instead of an
+ * enslaved bat0.
  *
  * Return: -ENOMEM on memory allocation error or the number of
  * items added to the mcast_list otherwise.
@@ -62,12 +107,13 @@
 static int batadv_mcast_mla_softif_get(struct net_device *dev,
 				       struct hlist_head *mcast_list)
 {
+	struct net_device *bridge = batadv_mcast_get_bridge(dev);
 	struct netdev_hw_addr *mc_list_entry;
 	struct batadv_hw_addr *new;
 	int ret = 0;
 
-	netif_addr_lock_bh(dev);
-	netdev_for_each_mc_addr(mc_list_entry, dev) {
+	netif_addr_lock_bh(bridge ? bridge : dev);
+	netdev_for_each_mc_addr(mc_list_entry, bridge ? bridge : dev) {
 		new = kmalloc(sizeof(*new), GFP_ATOMIC);
 		if (!new) {
 			ret = -ENOMEM;
@@ -78,7 +124,10 @@ static int batadv_mcast_mla_softif_get(struct net_device *dev,
 		hlist_add_head(&new->list, mcast_list);
 		ret++;
 	}
-	netif_addr_unlock_bh(dev);
+	netif_addr_unlock_bh(bridge ? bridge : dev);
+
+	if (bridge)
+		dev_put(bridge);
 
 	return ret;
 }
@@ -104,6 +153,83 @@ static bool batadv_mcast_mla_is_duplicate(u8 *mcast_addr,
 }
 
 /**
+ * batadv_mcast_mla_br_addr_cpy - copy a bridge multicast address
+ * @dst: destination to write to - a multicast MAC address
+ * @src: source to read from - a multicast IP address
+ *
+ * Converts a given multicast IPv4/IPv6 address from a bridge
+ * to its matching multicast MAC address and copies it into the given
+ * destination buffer.
+ *
+ * Caller needs to make sure the destination buffer can hold
+ * at least ETH_ALEN bytes.
+ */
+static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src)
+{
+	if (src->proto == htons(ETH_P_IP))
+		ip_eth_mc_map(src->u.ip4, dst);
+#if IS_ENABLED(CONFIG_IPV6)
+	else if (src->proto == htons(ETH_P_IPV6))
+		ipv6_eth_mc_map(&src->u.ip6, dst);
+#endif
+	else
+		eth_zero_addr(dst);
+}
+
+/**
+ * batadv_mcast_mla_bridge_get - get bridged-in multicast listeners
+ * @dev: a bridge slave whose bridge to collect multicast addresses from
+ * @mcast_list: a list to put found addresses into
+ *
+ * Collects multicast addresses of multicast listeners residing
+ * on foreign, non-mesh devices which we gave access to our mesh via
+ * a bridge on top of the given soft interface, dev, in the given
+ * mcast_list.
+ *
+ * Return: -ENOMEM on memory allocation error or the number of
+ * items added to the mcast_list otherwise.
+ */
+static int batadv_mcast_mla_bridge_get(struct net_device *dev,
+				       struct hlist_head *mcast_list)
+{
+	struct list_head bridge_mcast_list = LIST_HEAD_INIT(bridge_mcast_list);
+	struct br_ip_list *br_ip_entry, *tmp;
+	struct batadv_hw_addr *new;
+	u8 mcast_addr[ETH_ALEN];
+	int ret;
+
+	/* we don't need to detect these devices/listeners, the IGMP/MLD
+	 * snooping code of the Linux bridge already does that for us
+	 */
+	ret = br_multicast_list_adjacent(dev, &bridge_mcast_list);
+	if (ret < 0)
+		goto out;
+
+	list_for_each_entry(br_ip_entry, &bridge_mcast_list, list) {
+		batadv_mcast_mla_br_addr_cpy(mcast_addr, &br_ip_entry->addr);
+		if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list))
+			continue;
+
+		new = kmalloc(sizeof(*new), GFP_ATOMIC);
+		if (!new) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		ether_addr_copy(new->addr, mcast_addr);
+		hlist_add_head(&new->list, mcast_list);
+	}
+
+out:
+	list_for_each_entry_safe(br_ip_entry, tmp, &bridge_mcast_list, list) {
+		list_del(&br_ip_entry->list);
+		kfree(br_ip_entry);
+	}
+
+	return ret;
+}
+
+/**
  * batadv_mcast_mla_list_free - free a list of multicast addresses
  * @bat_priv: the bat priv with all the soft interface information
  * @mcast_list: the list to free
@@ -214,44 +340,195 @@ static bool batadv_mcast_has_bridge(struct batadv_priv *bat_priv)
 }
 
 /**
+ * batadv_mcast_querier_log - debug output regarding the querier status on link
+ * @bat_priv: the bat priv with all the soft interface information
+ * @str_proto: a string for the querier protocol (e.g. "IGMP" or "MLD")
+ * @old_state: the previous querier state on our link
+ * @new_state: the new querier state on our link
+ *
+ * Outputs debug messages to the logging facility with log level 'mcast'
+ * regarding changes to the querier status on the link which are relevant
+ * to our multicast optimizations.
+ *
+ * Usually this is about whether a querier appeared or vanished in
+ * our mesh or whether the querier is in the suboptimal position of being
+ * behind our local bridge segment: Snooping switches will directly
+ * forward listener reports to the querier, therefore batman-adv and
+ * the bridge will potentially not see these listeners - the querier is
+ * potentially shadowing listeners from us then.
+ *
+ * This is only interesting for nodes with a bridge on top of their
+ * soft interface.
+ */
+static void
+batadv_mcast_querier_log(struct batadv_priv *bat_priv, char *str_proto,
+			 struct batadv_mcast_querier_state *old_state,
+			 struct batadv_mcast_querier_state *new_state)
+{
+	if (!old_state->exists && new_state->exists)
+		batadv_info(bat_priv->soft_iface, "%s Querier appeared\n",
+			    str_proto);
+	else if (old_state->exists && !new_state->exists)
+		batadv_info(bat_priv->soft_iface,
+			    "%s Querier disappeared - multicast optimizations disabled\n",
+			    str_proto);
+	else if (!bat_priv->mcast.bridged && !new_state->exists)
+		batadv_info(bat_priv->soft_iface,
+			    "No %s Querier present - multicast optimizations disabled\n",
+			    str_proto);
+
+	if (new_state->exists) {
+		if ((!old_state->shadowing && new_state->shadowing) ||
+		    (!old_state->exists && new_state->shadowing))
+			batadv_dbg(BATADV_DBG_MCAST, bat_priv,
+				   "%s Querier is behind our bridged segment: Might shadow listeners\n",
+				   str_proto);
+		else if (old_state->shadowing && !new_state->shadowing)
+			batadv_dbg(BATADV_DBG_MCAST, bat_priv,
+				   "%s Querier is not behind our bridged segment\n",
+				   str_proto);
+	}
+}
+
+/**
+ * batadv_mcast_bridge_log - debug output for topology changes in bridged setups
+ * @bat_priv: the bat priv with all the soft interface information
+ * @bridged: a flag about whether the soft interface is currently bridged or not
+ * @querier_ipv4: (maybe) new status of a potential, selected IGMP querier
+ * @querier_ipv6: (maybe) new status of a potential, selected MLD querier
+ *
+ * If no bridges are ever used on this node, then this function does nothing.
+ *
+ * Otherwise this function outputs debug information to the 'mcast' log level
+ * which might be relevant to our multicast optimizations.
+ *
+ * More precisely, it outputs information when a bridge interface is added or
+ * removed from a soft interface. And when a bridge is present, it further
+ * outputs information about the querier state which is relevant for the
+ * multicast flags this node is going to set.
+ */
+static void
+batadv_mcast_bridge_log(struct batadv_priv *bat_priv, bool bridged,
+			struct batadv_mcast_querier_state *querier_ipv4,
+			struct batadv_mcast_querier_state *querier_ipv6)
+{
+	if (!bat_priv->mcast.bridged && bridged)
+		batadv_dbg(BATADV_DBG_MCAST, bat_priv,
+			   "Bridge added: Setting Unsnoopables(U)-flag\n");
+	else if (bat_priv->mcast.bridged && !bridged)
+		batadv_dbg(BATADV_DBG_MCAST, bat_priv,
+			   "Bridge removed: Unsetting Unsnoopables(U)-flag\n");
+
+	if (bridged) {
+		batadv_mcast_querier_log(bat_priv, "IGMP",
+					 &bat_priv->mcast.querier_ipv4,
+					 querier_ipv4);
+		batadv_mcast_querier_log(bat_priv, "MLD",
+					 &bat_priv->mcast.querier_ipv6,
+					 querier_ipv6);
+	}
+}
+
+/**
+ * batadv_mcast_flags_logs - output debug information about mcast flag changes
+ * @bat_priv: the bat priv with all the soft interface information
+ * @flags: flags indicating the new multicast state
+ *
+ * Whenever the multicast flags this nodes announces changes (@mcast_flags vs.
+ * bat_priv->mcast.flags), this notifies userspace via the 'mcast' log level.
+ */
+static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags)
+{
+	u8 old_flags = bat_priv->mcast.flags;
+	char str_old_flags[] = "[...]";
+
+	sprintf(str_old_flags, "[%c%c%c]",
+		(old_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
+		(old_flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
+		(old_flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.');
+
+	batadv_dbg(BATADV_DBG_MCAST, bat_priv,
+		   "Changing multicast flags from '%s' to '[%c%c%c]'\n",
+		   bat_priv->mcast.enabled ? str_old_flags : "<undefined>",
+		   (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
+		   (flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
+		   (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.');
+}
+
+/**
  * batadv_mcast_mla_tvlv_update - update multicast tvlv
  * @bat_priv: the bat priv with all the soft interface information
  *
  * Updates the own multicast tvlv with our current multicast related settings,
  * capabilities and inabilities.
  *
- * Return: true if the tvlv container is registered afterwards. Otherwise
- * returns false.
+ * Return: false if we want all IPv4 && IPv6 multicast traffic and true
+ * otherwise.
  */
 static bool batadv_mcast_mla_tvlv_update(struct batadv_priv *bat_priv)
 {
 	struct batadv_tvlv_mcast_data mcast_data;
+	struct batadv_mcast_querier_state querier4 = {false, false};
+	struct batadv_mcast_querier_state querier6 = {false, false};
+	struct net_device *dev = bat_priv->soft_iface;
+	bool bridged;
 
 	mcast_data.flags = BATADV_NO_FLAGS;
 	memset(mcast_data.reserved, 0, sizeof(mcast_data.reserved));
 
-	/* Avoid attaching MLAs, if there is a bridge on top of our soft
-	 * interface, we don't support that yet (TODO)
+	bridged = batadv_mcast_has_bridge(bat_priv);
+	if (!bridged)
+		goto update;
+
+#if !IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
+	pr_warn_once("No bridge IGMP snooping compiled - multicast optimizations disabled\n");
+#endif
+
+	querier4.exists = br_multicast_has_querier_anywhere(dev, ETH_P_IP);
+	querier4.shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IP);
+
+	querier6.exists = br_multicast_has_querier_anywhere(dev, ETH_P_IPV6);
+	querier6.shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IPV6);
+
+	mcast_data.flags |= BATADV_MCAST_WANT_ALL_UNSNOOPABLES;
+
+	/* 1) If no querier exists at all, then multicast listeners on
+	 *    our local TT clients behind the bridge will keep silent.
+	 * 2) If the selected querier is on one of our local TT clients,
+	 *    behind the bridge, then this querier might shadow multicast
+	 *    listeners on our local TT clients, behind this bridge.
+	 *
+	 * In both cases, we will signalize other batman nodes that
+	 * we need all multicast traffic of the according protocol.
 	 */
-	if (batadv_mcast_has_bridge(bat_priv)) {
-		if (bat_priv->mcast.enabled) {
-			batadv_tvlv_container_unregister(bat_priv,
-							 BATADV_TVLV_MCAST, 1);
-			bat_priv->mcast.enabled = false;
-		}
+	if (!querier4.exists || querier4.shadowing)
+		mcast_data.flags |= BATADV_MCAST_WANT_ALL_IPV4;
 
-		return false;
-	}
+	if (!querier6.exists || querier6.shadowing)
+		mcast_data.flags |= BATADV_MCAST_WANT_ALL_IPV6;
+
+update:
+	batadv_mcast_bridge_log(bat_priv, bridged, &querier4, &querier6);
+
+	bat_priv->mcast.querier_ipv4.exists = querier4.exists;
+	bat_priv->mcast.querier_ipv4.shadowing = querier4.shadowing;
+
+	bat_priv->mcast.querier_ipv6.exists = querier6.exists;
+	bat_priv->mcast.querier_ipv6.shadowing = querier6.shadowing;
+
+	bat_priv->mcast.bridged = bridged;
 
 	if (!bat_priv->mcast.enabled ||
 	    mcast_data.flags != bat_priv->mcast.flags) {
-		batadv_tvlv_container_register(bat_priv, BATADV_TVLV_MCAST, 1,
+		batadv_mcast_flags_log(bat_priv, mcast_data.flags);
+		batadv_tvlv_container_register(bat_priv, BATADV_TVLV_MCAST, 2,
 					       &mcast_data, sizeof(mcast_data));
 		bat_priv->mcast.flags = mcast_data.flags;
 		bat_priv->mcast.enabled = true;
 	}
 
-	return true;
+	return !(mcast_data.flags &
+		 (BATADV_MCAST_WANT_ALL_IPV4 + BATADV_MCAST_WANT_ALL_IPV6));
 }
 
 /**
@@ -274,6 +551,10 @@ void batadv_mcast_mla_update(struct batadv_priv *bat_priv)
 	if (ret < 0)
 		goto out;
 
+	ret = batadv_mcast_mla_bridge_get(soft_iface, &mcast_list);
+	if (ret < 0)
+		goto out;
+
 update:
 	batadv_mcast_mla_tt_retract(bat_priv, &mcast_list);
 	batadv_mcast_mla_tt_add(bat_priv, &mcast_list);
@@ -283,6 +564,31 @@ out:
 }
 
 /**
+ * batadv_mcast_is_report_ipv4 - check for IGMP reports
+ * @skb: the ethernet frame destined for the mesh
+ *
+ * This call might reallocate skb data.
+ *
+ * Checks whether the given frame is a valid IGMP report.
+ *
+ * Return: If so then true, otherwise false.
+ */
+static bool batadv_mcast_is_report_ipv4(struct sk_buff *skb)
+{
+	if (ip_mc_check_igmp(skb, NULL) < 0)
+		return false;
+
+	switch (igmp_hdr(skb)->type) {
+	case IGMP_HOST_MEMBERSHIP_REPORT:
+	case IGMPV2_HOST_MEMBERSHIP_REPORT:
+	case IGMPV3_HOST_MEMBERSHIP_REPORT:
+		return true;
+	}
+
+	return false;
+}
+
+/**
  * batadv_mcast_forw_mode_check_ipv4 - check for optimized forwarding potential
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: the IPv4 packet to check
@@ -304,6 +610,9 @@ static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv,
 	if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*iphdr)))
 		return -ENOMEM;
 
+	if (batadv_mcast_is_report_ipv4(skb))
+		return -EINVAL;
+
 	iphdr = ip_hdr(skb);
 
 	/* TODO: Implement Multicast Router Discovery (RFC4286),
@@ -320,6 +629,31 @@ static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+/**
+ * batadv_mcast_is_report_ipv6 - check for MLD reports
+ * @skb: the ethernet frame destined for the mesh
+ *
+ * This call might reallocate skb data.
+ *
+ * Checks whether the given frame is a valid MLD report.
+ *
+ * Return: If so then true, otherwise false.
+ */
+static bool batadv_mcast_is_report_ipv6(struct sk_buff *skb)
+{
+	if (ipv6_mc_check_mld(skb, NULL) < 0)
+		return false;
+
+	switch (icmp6_hdr(skb)->icmp6_type) {
+	case ICMPV6_MGM_REPORT:
+	case ICMPV6_MLD2_REPORT:
+		return true;
+	}
+
+	return false;
+}
+
 /**
  * batadv_mcast_forw_mode_check_ipv6 - check for optimized forwarding potential
  * @bat_priv: the bat priv with all the soft interface information
@@ -341,6 +675,9 @@ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
 	if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*ip6hdr)))
 		return -ENOMEM;
 
+	if (batadv_mcast_is_report_ipv6(skb))
+		return -EINVAL;
+
 	ip6hdr = ipv6_hdr(skb);
 
 	/* TODO: Implement Multicast Router Discovery (RFC4286),
@@ -357,6 +694,7 @@ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
 
 	return 0;
 }
+#endif
 
 /**
  * batadv_mcast_forw_mode_check - check for optimized forwarding potential
@@ -385,9 +723,11 @@ static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv,
 	case ETH_P_IP:
 		return batadv_mcast_forw_mode_check_ipv4(bat_priv, skb,
 							 is_unsnoopable);
+#if IS_ENABLED(CONFIG_IPV6)
 	case ETH_P_IPV6:
 		return batadv_mcast_forw_mode_check_ipv6(bat_priv, skb,
 							 is_unsnoopable);
+#endif
 	default:
 		return -EINVAL;
 	}
@@ -728,18 +1068,18 @@ static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv,
 }
 
 /**
- * batadv_mcast_tvlv_ogm_handler_v1 - process incoming multicast tvlv container
+ * batadv_mcast_tvlv_ogm_handler - process incoming multicast tvlv container
  * @bat_priv: the bat priv with all the soft interface information
  * @orig: the orig_node of the ogm
  * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags)
  * @tvlv_value: tvlv buffer containing the multicast data
  * @tvlv_value_len: tvlv buffer length
  */
-static void batadv_mcast_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
-					     struct batadv_orig_node *orig,
-					     u8 flags,
-					     void *tvlv_value,
-					     u16 tvlv_value_len)
+static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv,
+					  struct batadv_orig_node *orig,
+					  u8 flags,
+					  void *tvlv_value,
+					  u16 tvlv_value_len)
 {
 	bool orig_mcast_enabled = !(flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
 	u8 mcast_flags = BATADV_NO_FLAGS;
@@ -789,19 +1129,120 @@ static void batadv_mcast_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
  */
 void batadv_mcast_init(struct batadv_priv *bat_priv)
 {
-	batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler_v1,
-				     NULL, BATADV_TVLV_MCAST, 1,
+	batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler,
+				     NULL, BATADV_TVLV_MCAST, 2,
 				     BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
 }
 
 /**
+ * batadv_mcast_flags_print_header - print own mcast flags to debugfs table
+ * @bat_priv: the bat priv with all the soft interface information
+ * @seq: debugfs table seq_file struct
+ *
+ * Prints our own multicast flags including a more specific reason why
+ * they are set, that is prints the bridge and querier state too, to
+ * the debugfs table specified via @seq.
+ */
+static void batadv_mcast_flags_print_header(struct batadv_priv *bat_priv,
+					    struct seq_file *seq)
+{
+	u8 flags = bat_priv->mcast.flags;
+	char querier4, querier6, shadowing4, shadowing6;
+	bool bridged = bat_priv->mcast.bridged;
+
+	if (bridged) {
+		querier4 = bat_priv->mcast.querier_ipv4.exists ? '.' : '4';
+		querier6 = bat_priv->mcast.querier_ipv6.exists ? '.' : '6';
+		shadowing4 = bat_priv->mcast.querier_ipv4.shadowing ? '4' : '.';
+		shadowing6 = bat_priv->mcast.querier_ipv6.shadowing ? '6' : '.';
+	} else {
+		querier4 = '?';
+		querier6 = '?';
+		shadowing4 = '?';
+		shadowing6 = '?';
+	}
+
+	seq_printf(seq, "Multicast flags (own flags: [%c%c%c])\n",
+		   (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
+		   (flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
+		   (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.');
+	seq_printf(seq, "* Bridged [U]\t\t\t\t%c\n", bridged ? 'U' : '.');
+	seq_printf(seq, "* No IGMP/MLD Querier [4/6]:\t\t%c/%c\n",
+		   querier4, querier6);
+	seq_printf(seq, "* Shadowing IGMP/MLD Querier [4/6]:\t%c/%c\n",
+		   shadowing4, shadowing6);
+	seq_puts(seq, "-------------------------------------------\n");
+	seq_printf(seq, "       %-10s %s\n", "Originator", "Flags");
+}
+
+/**
+ * batadv_mcast_flags_seq_print_text - print the mcast flags of other nodes
+ * @seq: seq file to print on
+ * @offset: not used
+ *
+ * This prints a table of (primary) originators and their according
+ * multicast flags, including (in the header) our own.
+ *
+ * Return: always 0
+ */
+int batadv_mcast_flags_seq_print_text(struct seq_file *seq, void *offset)
+{
+	struct net_device *net_dev = (struct net_device *)seq->private;
+	struct batadv_priv *bat_priv = netdev_priv(net_dev);
+	struct batadv_hard_iface *primary_if;
+	struct batadv_hashtable *hash = bat_priv->orig_hash;
+	struct batadv_orig_node *orig_node;
+	struct hlist_head *head;
+	u8 flags;
+	u32 i;
+
+	primary_if = batadv_seq_print_text_primary_if_get(seq);
+	if (!primary_if)
+		return 0;
+
+	batadv_mcast_flags_print_header(bat_priv, seq);
+
+	for (i = 0; i < hash->size; i++) {
+		head = &hash->table[i];
+
+		rcu_read_lock();
+		hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
+			if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST,
+				      &orig_node->capa_initialized))
+				continue;
+
+			if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST,
+				      &orig_node->capabilities)) {
+				seq_printf(seq, "%pM -\n", orig_node->orig);
+				continue;
+			}
+
+			flags = orig_node->mcast_flags;
+
+			seq_printf(seq, "%pM [%c%c%c]\n", orig_node->orig,
+				   (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES)
+				   ? 'U' : '.',
+				   (flags & BATADV_MCAST_WANT_ALL_IPV4)
+				   ? '4' : '.',
+				   (flags & BATADV_MCAST_WANT_ALL_IPV6)
+				   ? '6' : '.');
+		}
+		rcu_read_unlock();
+	}
+
+	batadv_hardif_put(primary_if);
+
+	return 0;
+}
+
+/**
  * batadv_mcast_free - free the multicast optimizations structures
  * @bat_priv: the bat priv with all the soft interface information
  */
 void batadv_mcast_free(struct batadv_priv *bat_priv)
 {
-	batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 1);
-	batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 1);
+	batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
+	batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
 
 	spin_lock_bh(&bat_priv->tt.commit_lock);
 	batadv_mcast_mla_tt_retract(bat_priv, NULL);
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
index 80bceec55592..1fb00ba84907 100644
--- a/net/batman-adv/multicast.h
+++ b/net/batman-adv/multicast.h
@@ -20,6 +20,7 @@
 
 #include "main.h"
 
+struct seq_file;
 struct sk_buff;
 
 /**
@@ -46,6 +47,8 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 void batadv_mcast_init(struct batadv_priv *bat_priv);
 
+int batadv_mcast_flags_seq_print_text(struct seq_file *seq, void *offset);
+
 void batadv_mcast_free(struct batadv_priv *bat_priv);
 
 void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node);
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
new file mode 100644
index 000000000000..231f8eaf075b
--- /dev/null
+++ b/net/batman-adv/netlink.c
@@ -0,0 +1,424 @@
+/* Copyright (C) 2016 B.A.T.M.A.N. contributors:
+ *
+ * Matthias Schiffer
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "netlink.h"
+#include "main.h"
+
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/genetlink.h>
+#include <linux/if_ether.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/netlink.h>
+#include <linux/printk.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <net/genetlink.h>
+#include <net/netlink.h>
+#include <uapi/linux/batman_adv.h>
+
+#include "hard-interface.h"
+#include "soft-interface.h"
+#include "tp_meter.h"
+
+struct sk_buff;
+
+static struct genl_family batadv_netlink_family = {
+	.id = GENL_ID_GENERATE,
+	.hdrsize = 0,
+	.name = BATADV_NL_NAME,
+	.version = 1,
+	.maxattr = BATADV_ATTR_MAX,
+};
+
+/* multicast groups */
+enum batadv_netlink_multicast_groups {
+	BATADV_NL_MCGRP_TPMETER,
+};
+
+static struct genl_multicast_group batadv_netlink_mcgrps[] = {
+	[BATADV_NL_MCGRP_TPMETER] = { .name = BATADV_NL_MCAST_GROUP_TPMETER },
+};
+
+static struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = {
+	[BATADV_ATTR_VERSION]		= { .type = NLA_STRING },
+	[BATADV_ATTR_ALGO_NAME]		= { .type = NLA_STRING },
+	[BATADV_ATTR_MESH_IFINDEX]	= { .type = NLA_U32 },
+	[BATADV_ATTR_MESH_IFNAME]	= { .type = NLA_STRING },
+	[BATADV_ATTR_MESH_ADDRESS]	= { .len = ETH_ALEN },
+	[BATADV_ATTR_HARD_IFINDEX]	= { .type = NLA_U32 },
+	[BATADV_ATTR_HARD_IFNAME]	= { .type = NLA_STRING },
+	[BATADV_ATTR_HARD_ADDRESS]	= { .len = ETH_ALEN },
+	[BATADV_ATTR_ORIG_ADDRESS]	= { .len = ETH_ALEN },
+	[BATADV_ATTR_TPMETER_RESULT]	= { .type = NLA_U8 },
+	[BATADV_ATTR_TPMETER_TEST_TIME]	= { .type = NLA_U32 },
+	[BATADV_ATTR_TPMETER_BYTES]	= { .type = NLA_U64 },
+	[BATADV_ATTR_TPMETER_COOKIE]	= { .type = NLA_U32 },
+};
+
+/**
+ * batadv_netlink_mesh_info_put - fill in generic information about mesh
+ *  interface
+ * @msg: netlink message to be sent back
+ * @soft_iface: interface for which the data should be taken
+ *
+ * Return: 0 on success, < 0 on error
+ */
+static int
+batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface)
+{
+	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+	struct batadv_hard_iface *primary_if = NULL;
+	struct net_device *hard_iface;
+	int ret = -ENOBUFS;
+
+	if (nla_put_string(msg, BATADV_ATTR_VERSION, BATADV_SOURCE_VERSION) ||
+	    nla_put_string(msg, BATADV_ATTR_ALGO_NAME,
+			   bat_priv->algo_ops->name) ||
+	    nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, soft_iface->ifindex) ||
+	    nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, soft_iface->name) ||
+	    nla_put(msg, BATADV_ATTR_MESH_ADDRESS, ETH_ALEN,
+		    soft_iface->dev_addr))
+		goto out;
+
+	primary_if = batadv_primary_if_get_selected(bat_priv);
+	if (primary_if && primary_if->if_status == BATADV_IF_ACTIVE) {
+		hard_iface = primary_if->net_dev;
+
+		if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
+				hard_iface->ifindex) ||
+		    nla_put_string(msg, BATADV_ATTR_HARD_IFNAME,
+				   hard_iface->name) ||
+		    nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN,
+			    hard_iface->dev_addr))
+			goto out;
+	}
+
+	ret = 0;
+
+ out:
+	if (primary_if)
+		batadv_hardif_put(primary_if);
+
+	return ret;
+}
+
+/**
+ * batadv_netlink_get_mesh_info - handle incoming BATADV_CMD_GET_MESH_INFO
+ *  netlink request
+ * @skb: received netlink message
+ * @info: receiver information
+ *
+ * Return: 0 on success, < 0 on error
+ */
+static int
+batadv_netlink_get_mesh_info(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	struct net_device *soft_iface;
+	struct sk_buff *msg = NULL;
+	void *msg_head;
+	int ifindex;
+	int ret;
+
+	if (!info->attrs[BATADV_ATTR_MESH_IFINDEX])
+		return -EINVAL;
+
+	ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]);
+	if (!ifindex)
+		return -EINVAL;
+
+	soft_iface = dev_get_by_index(net, ifindex);
+	if (!soft_iface || !batadv_softif_is_valid(soft_iface)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	msg_head = genlmsg_put(msg, info->snd_portid, info->snd_seq,
+			       &batadv_netlink_family, 0,
+			       BATADV_CMD_GET_MESH_INFO);
+	if (!msg_head) {
+		ret = -ENOBUFS;
+		goto out;
+	}
+
+	ret = batadv_netlink_mesh_info_put(msg, soft_iface);
+
+ out:
+	if (soft_iface)
+		dev_put(soft_iface);
+
+	if (ret) {
+		if (msg)
+			nlmsg_free(msg);
+		return ret;
+	}
+
+	genlmsg_end(msg, msg_head);
+	return genlmsg_reply(msg, info);
+}
+
+/**
+ * batadv_netlink_tp_meter_put - Fill information of started tp_meter session
+ * @msg: netlink message to be sent back
+ * @cookie: tp meter session cookie
+ *
+ *  Return: 0 on success, < 0 on error
+ */
+static int
+batadv_netlink_tp_meter_put(struct sk_buff *msg, u32 cookie)
+{
+	if (nla_put_u32(msg, BATADV_ATTR_TPMETER_COOKIE, cookie))
+		return -ENOBUFS;
+
+	return 0;
+}
+
+/**
+ * batadv_netlink_tpmeter_notify - send tp_meter result via netlink to client
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: destination of tp_meter session
+ * @result: reason for tp meter session stop
+ * @test_time: total time ot the tp_meter session
+ * @total_bytes: bytes acked to the receiver
+ * @cookie: cookie of tp_meter session
+ *
+ * Return: 0 on success, < 0 on error
+ */
+int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst,
+				  u8 result, u32 test_time, u64 total_bytes,
+				  u32 cookie)
+{
+	struct sk_buff *msg;
+	void *hdr;
+	int ret;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, 0, 0, &batadv_netlink_family, 0,
+			  BATADV_CMD_TP_METER);
+	if (!hdr) {
+		ret = -ENOBUFS;
+		goto err_genlmsg;
+	}
+
+	if (nla_put_u32(msg, BATADV_ATTR_TPMETER_COOKIE, cookie))
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, BATADV_ATTR_TPMETER_TEST_TIME, test_time))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, BATADV_ATTR_TPMETER_BYTES, total_bytes,
+			      BATADV_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u8(msg, BATADV_ATTR_TPMETER_RESULT, result))
+		goto nla_put_failure;
+
+	if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, dst))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+
+	genlmsg_multicast_netns(&batadv_netlink_family,
+				dev_net(bat_priv->soft_iface), msg, 0,
+				BATADV_NL_MCGRP_TPMETER, GFP_KERNEL);
+
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	ret = -EMSGSIZE;
+
+err_genlmsg:
+	nlmsg_free(msg);
+	return ret;
+}
+
+/**
+ * batadv_netlink_tp_meter_start - Start a new tp_meter session
+ * @skb: received netlink message
+ * @info: receiver information
+ *
+ * Return: 0 on success, < 0 on error
+ */
+static int
+batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	struct net_device *soft_iface;
+	struct batadv_priv *bat_priv;
+	struct sk_buff *msg = NULL;
+	u32 test_length;
+	void *msg_head;
+	int ifindex;
+	u32 cookie;
+	u8 *dst;
+	int ret;
+
+	if (!info->attrs[BATADV_ATTR_MESH_IFINDEX])
+		return -EINVAL;
+
+	if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS])
+		return -EINVAL;
+
+	if (!info->attrs[BATADV_ATTR_TPMETER_TEST_TIME])
+		return -EINVAL;
+
+	ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]);
+	if (!ifindex)
+		return -EINVAL;
+
+	dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]);
+
+	test_length = nla_get_u32(info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]);
+
+	soft_iface = dev_get_by_index(net, ifindex);
+	if (!soft_iface || !batadv_softif_is_valid(soft_iface)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	msg_head = genlmsg_put(msg, info->snd_portid, info->snd_seq,
+			       &batadv_netlink_family, 0,
+			       BATADV_CMD_TP_METER);
+	if (!msg_head) {
+		ret = -ENOBUFS;
+		goto out;
+	}
+
+	bat_priv = netdev_priv(soft_iface);
+	batadv_tp_start(bat_priv, dst, test_length, &cookie);
+
+	ret = batadv_netlink_tp_meter_put(msg, cookie);
+
+ out:
+	if (soft_iface)
+		dev_put(soft_iface);
+
+	if (ret) {
+		if (msg)
+			nlmsg_free(msg);
+		return ret;
+	}
+
+	genlmsg_end(msg, msg_head);
+	return genlmsg_reply(msg, info);
+}
+
+/**
+ * batadv_netlink_tp_meter_start - Cancel a running tp_meter session
+ * @skb: received netlink message
+ * @info: receiver information
+ *
+ * Return: 0 on success, < 0 on error
+ */
+static int
+batadv_netlink_tp_meter_cancel(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	struct net_device *soft_iface;
+	struct batadv_priv *bat_priv;
+	int ifindex;
+	u8 *dst;
+	int ret = 0;
+
+	if (!info->attrs[BATADV_ATTR_MESH_IFINDEX])
+		return -EINVAL;
+
+	if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS])
+		return -EINVAL;
+
+	ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]);
+	if (!ifindex)
+		return -EINVAL;
+
+	dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]);
+
+	soft_iface = dev_get_by_index(net, ifindex);
+	if (!soft_iface || !batadv_softif_is_valid(soft_iface)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	bat_priv = netdev_priv(soft_iface);
+	batadv_tp_stop(bat_priv, dst, BATADV_TP_REASON_CANCEL);
+
+out:
+	if (soft_iface)
+		dev_put(soft_iface);
+
+	return ret;
+}
+
+static struct genl_ops batadv_netlink_ops[] = {
+	{
+		.cmd = BATADV_CMD_GET_MESH_INFO,
+		.flags = GENL_ADMIN_PERM,
+		.policy = batadv_netlink_policy,
+		.doit = batadv_netlink_get_mesh_info,
+	},
+	{
+		.cmd = BATADV_CMD_TP_METER,
+		.flags = GENL_ADMIN_PERM,
+		.policy = batadv_netlink_policy,
+		.doit = batadv_netlink_tp_meter_start,
+	},
+	{
+		.cmd = BATADV_CMD_TP_METER_CANCEL,
+		.flags = GENL_ADMIN_PERM,
+		.policy = batadv_netlink_policy,
+		.doit = batadv_netlink_tp_meter_cancel,
+	},
+};
+
+/**
+ * batadv_netlink_register - register batadv genl netlink family
+ */
+void __init batadv_netlink_register(void)
+{
+	int ret;
+
+	ret = genl_register_family_with_ops_groups(&batadv_netlink_family,
+						   batadv_netlink_ops,
+						   batadv_netlink_mcgrps);
+	if (ret)
+		pr_warn("unable to register netlink family");
+}
+
+/**
+ * batadv_netlink_unregister - unregister batadv genl netlink family
+ */
+void batadv_netlink_unregister(void)
+{
+	genl_unregister_family(&batadv_netlink_family);
+}
diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h
new file mode 100644
index 000000000000..945653ab58c6
--- /dev/null
+++ b/net/batman-adv/netlink.h
@@ -0,0 +1,32 @@
+/* Copyright (C) 2016 B.A.T.M.A.N. contributors:
+ *
+ * Matthias Schiffer
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_NETLINK_H_
+#define _NET_BATMAN_ADV_NETLINK_H_
+
+#include "main.h"
+
+#include <linux/types.h>
+
+void batadv_netlink_register(void);
+void batadv_netlink_unregister(void);
+
+int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst,
+				  u8 result, u32 test_time, u64 total_bytes,
+				  u32 cookie);
+
+#endif /* _NET_BATMAN_ADV_NETLINK_H_ */
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 678f06865312..293ef4ffd4e1 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -51,10 +51,12 @@
 
 #include "hard-interface.h"
 #include "hash.h"
+#include "log.h"
 #include "originator.h"
 #include "packet.h"
 #include "routing.h"
 #include "send.h"
+#include "tvlv.h"
 
 static struct lock_class_key batadv_nc_coding_hash_lock_class_key;
 static struct lock_class_key batadv_nc_decoding_hash_lock_class_key;
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 7f51bc2c06eb..7d1e5421f6bc 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -34,11 +34,13 @@
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 
+#include "bat_algo.h"
 #include "distributed-arp-table.h"
 #include "fragmentation.h"
 #include "gateway_client.h"
 #include "hard-interface.h"
 #include "hash.h"
+#include "log.h"
 #include "multicast.h"
 #include "network-coding.h"
 #include "routing.h"
@@ -251,10 +253,8 @@ static void batadv_neigh_node_release(struct kref *ref)
 	struct hlist_node *node_tmp;
 	struct batadv_neigh_node *neigh_node;
 	struct batadv_neigh_ifinfo *neigh_ifinfo;
-	struct batadv_algo_ops *bao;
 
 	neigh_node = container_of(ref, struct batadv_neigh_node, refcount);
-	bao = neigh_node->orig_node->bat_priv->bat_algo_ops;
 
 	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
 				  &neigh_node->ifinfo_list, list) {
@@ -263,9 +263,6 @@ static void batadv_neigh_node_release(struct kref *ref)
 
 	batadv_hardif_neigh_put(neigh_node->hardif_neigh);
 
-	if (bao->bat_neigh_free)
-		bao->bat_neigh_free(neigh_node);
-
 	batadv_hardif_put(neigh_node->if_incoming);
 
 	kfree_rcu(neigh_node, rcu);
@@ -537,8 +534,8 @@ batadv_hardif_neigh_create(struct batadv_hard_iface *hard_iface,
 
 	kref_init(&hardif_neigh->refcount);
 
-	if (bat_priv->bat_algo_ops->bat_hardif_neigh_init)
-		bat_priv->bat_algo_ops->bat_hardif_neigh_init(hardif_neigh);
+	if (bat_priv->algo_ops->neigh.hardif_init)
+		bat_priv->algo_ops->neigh.hardif_init(hardif_neigh);
 
 	hlist_add_head(&hardif_neigh->list, &hard_iface->neigh_list);
 
@@ -602,19 +599,19 @@ batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface,
 }
 
 /**
- * batadv_neigh_node_new - create and init a new neigh_node object
+ * batadv_neigh_node_create - create a neigh node object
  * @orig_node: originator object representing the neighbour
  * @hard_iface: the interface where the neighbour is connected to
  * @neigh_addr: the mac address of the neighbour interface
  *
  * Allocates a new neigh_node object and initialises all the generic fields.
  *
- * Return: neighbor when found. Othwerwise NULL
+ * Return: the neighbour node if found or created or NULL otherwise.
  */
-struct batadv_neigh_node *
-batadv_neigh_node_new(struct batadv_orig_node *orig_node,
-		      struct batadv_hard_iface *hard_iface,
-		      const u8 *neigh_addr)
+static struct batadv_neigh_node *
+batadv_neigh_node_create(struct batadv_orig_node *orig_node,
+			 struct batadv_hard_iface *hard_iface,
+			 const u8 *neigh_addr)
 {
 	struct batadv_neigh_node *neigh_node;
 	struct batadv_hardif_neigh_node *hardif_neigh = NULL;
@@ -667,6 +664,29 @@ out:
 }
 
 /**
+ * batadv_neigh_node_get_or_create - retrieve or create a neigh node object
+ * @orig_node: originator object representing the neighbour
+ * @hard_iface: the interface where the neighbour is connected to
+ * @neigh_addr: the mac address of the neighbour interface
+ *
+ * Return: the neighbour node if found or created or NULL otherwise.
+ */
+struct batadv_neigh_node *
+batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node,
+				struct batadv_hard_iface *hard_iface,
+				const u8 *neigh_addr)
+{
+	struct batadv_neigh_node *neigh_node = NULL;
+
+	/* first check without locking to avoid the overhead */
+	neigh_node = batadv_neigh_node_get(orig_node, hard_iface, neigh_addr);
+	if (neigh_node)
+		return neigh_node;
+
+	return batadv_neigh_node_create(orig_node, hard_iface, neigh_addr);
+}
+
+/**
  * batadv_hardif_neigh_seq_print_text - print the single hop neighbour list
  * @seq: neighbour table seq_file struct
  * @offset: not used
@@ -686,17 +706,17 @@ int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset)
 	seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s %s)]\n",
 		   BATADV_SOURCE_VERSION, primary_if->net_dev->name,
 		   primary_if->net_dev->dev_addr, net_dev->name,
-		   bat_priv->bat_algo_ops->name);
+		   bat_priv->algo_ops->name);
 
 	batadv_hardif_put(primary_if);
 
-	if (!bat_priv->bat_algo_ops->bat_neigh_print) {
+	if (!bat_priv->algo_ops->neigh.print) {
 		seq_puts(seq,
 			 "No printing function for this routing protocol\n");
 		return 0;
 	}
 
-	bat_priv->bat_algo_ops->bat_neigh_print(bat_priv, seq);
+	bat_priv->algo_ops->neigh.print(bat_priv, seq);
 	return 0;
 }
 
@@ -747,8 +767,8 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu)
 
 	batadv_frag_purge_orig(orig_node, NULL);
 
-	if (orig_node->bat_priv->bat_algo_ops->bat_orig_free)
-		orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node);
+	if (orig_node->bat_priv->algo_ops->orig.free)
+		orig_node->bat_priv->algo_ops->orig.free(orig_node);
 
 	kfree(orig_node->tt_buff);
 	kfree(orig_node);
@@ -1077,12 +1097,12 @@ batadv_find_best_neighbor(struct batadv_priv *bat_priv,
 			  struct batadv_hard_iface *if_outgoing)
 {
 	struct batadv_neigh_node *best = NULL, *neigh;
-	struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+	struct batadv_algo_ops *bao = bat_priv->algo_ops;
 
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(neigh, &orig_node->neigh_list, list) {
-		if (best && (bao->bat_neigh_cmp(neigh, if_outgoing,
-						best, if_outgoing) <= 0))
+		if (best && (bao->neigh.cmp(neigh, if_outgoing, best,
+					    if_outgoing) <= 0))
 			continue;
 
 		if (!kref_get_unless_zero(&neigh->refcount))
@@ -1234,18 +1254,17 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset)
 	seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s %s)]\n",
 		   BATADV_SOURCE_VERSION, primary_if->net_dev->name,
 		   primary_if->net_dev->dev_addr, net_dev->name,
-		   bat_priv->bat_algo_ops->name);
+		   bat_priv->algo_ops->name);
 
 	batadv_hardif_put(primary_if);
 
-	if (!bat_priv->bat_algo_ops->bat_orig_print) {
+	if (!bat_priv->algo_ops->orig.print) {
 		seq_puts(seq,
 			 "No printing function for this routing protocol\n");
 		return 0;
 	}
 
-	bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq,
-					       BATADV_IF_DEFAULT);
+	bat_priv->algo_ops->orig.print(bat_priv, seq, BATADV_IF_DEFAULT);
 
 	return 0;
 }
@@ -1272,7 +1291,7 @@ int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset)
 	}
 
 	bat_priv = netdev_priv(hard_iface->soft_iface);
-	if (!bat_priv->bat_algo_ops->bat_orig_print) {
+	if (!bat_priv->algo_ops->orig.print) {
 		seq_puts(seq,
 			 "No printing function for this routing protocol\n");
 		goto out;
@@ -1286,9 +1305,9 @@ int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset)
 	seq_printf(seq, "[B.A.T.M.A.N. adv %s, IF/MAC: %s/%pM (%s %s)]\n",
 		   BATADV_SOURCE_VERSION, hard_iface->net_dev->name,
 		   hard_iface->net_dev->dev_addr,
-		   hard_iface->soft_iface->name, bat_priv->bat_algo_ops->name);
+		   hard_iface->soft_iface->name, bat_priv->algo_ops->name);
 
-	bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, hard_iface);
+	bat_priv->algo_ops->orig.print(bat_priv, seq, hard_iface);
 
 out:
 	if (hard_iface)
@@ -1300,7 +1319,7 @@ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface,
 			    int max_if_num)
 {
 	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
-	struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+	struct batadv_algo_ops *bao = bat_priv->algo_ops;
 	struct batadv_hashtable *hash = bat_priv->orig_hash;
 	struct hlist_head *head;
 	struct batadv_orig_node *orig_node;
@@ -1316,9 +1335,8 @@ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface,
 		rcu_read_lock();
 		hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
 			ret = 0;
-			if (bao->bat_orig_add_if)
-				ret = bao->bat_orig_add_if(orig_node,
-							   max_if_num);
+			if (bao->orig.add_if)
+				ret = bao->orig.add_if(orig_node, max_if_num);
 			if (ret == -ENOMEM)
 				goto err;
 		}
@@ -1340,7 +1358,7 @@ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface,
 	struct hlist_head *head;
 	struct batadv_hard_iface *hard_iface_tmp;
 	struct batadv_orig_node *orig_node;
-	struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+	struct batadv_algo_ops *bao = bat_priv->algo_ops;
 	u32 i;
 	int ret;
 
@@ -1353,10 +1371,9 @@ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface,
 		rcu_read_lock();
 		hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
 			ret = 0;
-			if (bao->bat_orig_del_if)
-				ret = bao->bat_orig_del_if(orig_node,
-							   max_if_num,
-							   hard_iface->if_num);
+			if (bao->orig.del_if)
+				ret = bao->orig.del_if(orig_node, max_if_num,
+						       hard_iface->if_num);
 			if (ret == -ENOMEM)
 				goto err;
 		}
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index 64a8951e5844..566306bf05dc 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -46,9 +46,9 @@ batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface,
 void
 batadv_hardif_neigh_put(struct batadv_hardif_neigh_node *hardif_neigh);
 struct batadv_neigh_node *
-batadv_neigh_node_new(struct batadv_orig_node *orig_node,
-		      struct batadv_hard_iface *hard_iface,
-		      const u8 *neigh_addr);
+batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node,
+				struct batadv_hard_iface *hard_iface,
+				const u8 *neigh_addr);
 void batadv_neigh_node_put(struct batadv_neigh_node *neigh_node);
 struct batadv_neigh_node *
 batadv_orig_router_get(struct batadv_orig_node *orig_node,
diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 372128ddb474..6b011ff64dd8 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -21,6 +21,8 @@
 #include <asm/byteorder.h>
 #include <linux/types.h>
 
+#define batadv_tp_is_error(n) ((u8)n > 127 ? 1 : 0)
+
 /**
  * enum batadv_packettype - types for batman-adv encapsulated packets
  * @BATADV_IV_OGM: originator messages for B.A.T.M.A.N. IV
@@ -93,6 +95,7 @@ enum batadv_icmp_packettype {
 	BATADV_ECHO_REQUEST	       = 8,
 	BATADV_TTL_EXCEEDED	       = 11,
 	BATADV_PARAMETER_PROBLEM       = 12,
+	BATADV_TP		       = 15,
 };
 
 /**
@@ -285,6 +288,16 @@ struct batadv_elp_packet {
 #define BATADV_ELP_HLEN sizeof(struct batadv_elp_packet)
 
 /**
+ * enum batadv_icmp_user_cmd_type - types for batman-adv icmp cmd modes
+ * @BATADV_TP_START: start a throughput meter run
+ * @BATADV_TP_STOP: stop a throughput meter run
+ */
+enum batadv_icmp_user_cmd_type {
+	BATADV_TP_START		= 0,
+	BATADV_TP_STOP		= 2,
+};
+
+/**
  * struct batadv_icmp_header - common members among all the ICMP packets
  * @packet_type: batman-adv packet type, part of the general header
  * @version: batman-adv protocol version, part of the genereal header
@@ -334,6 +347,47 @@ struct batadv_icmp_packet {
 	__be16 seqno;
 };
 
+/**
+ * struct batadv_icmp_tp_packet - ICMP TP Meter packet
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @msg_type: ICMP packet type
+ * @dst: address of the destination node
+ * @orig: address of the source node
+ * @uid: local ICMP socket identifier
+ * @subtype: TP packet subtype (see batadv_icmp_tp_subtype)
+ * @session: TP session identifier
+ * @seqno: the TP sequence number
+ * @timestamp: time when the packet has been sent. This value is filled in a
+ *  TP_MSG and echoed back in the next TP_ACK so that the sender can compute the
+ *  RTT. Since it is read only by the host which wrote it, there is no need to
+ *  store it using network order
+ */
+struct batadv_icmp_tp_packet {
+	u8  packet_type;
+	u8  version;
+	u8  ttl;
+	u8  msg_type; /* see ICMP message types above */
+	u8  dst[ETH_ALEN];
+	u8  orig[ETH_ALEN];
+	u8  uid;
+	u8  subtype;
+	u8  session[2];
+	__be32 seqno;
+	__be32 timestamp;
+};
+
+/**
+ * enum batadv_icmp_tp_subtype - ICMP TP Meter packet subtypes
+ * @BATADV_TP_MSG: Msg from sender to receiver
+ * @BATADV_TP_ACK: acknowledgment from receiver to sender
+ */
+enum batadv_icmp_tp_subtype {
+	BATADV_TP_MSG	= 0,
+	BATADV_TP_ACK,
+};
+
 #define BATADV_RR_LEN 16
 
 /**
@@ -420,6 +474,7 @@ struct batadv_unicast_4addr_packet {
  * @dest: final destination used when routing fragments
  * @orig: originator of the fragment used when merging the packet
  * @no: fragment number within this sequence
+ * @priority: priority of frame, from ToS IP precedence or 802.1p
  * @reserved: reserved byte for alignment
  * @seqno: sequence identification
  * @total_size: size of the merged packet
@@ -430,9 +485,11 @@ struct batadv_frag_packet {
 	u8     ttl;
 #if defined(__BIG_ENDIAN_BITFIELD)
 	u8     no:4;
-	u8     reserved:4;
+	u8     priority:3;
+	u8     reserved:1;
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-	u8     reserved:4;
+	u8     reserved:1;
+	u8     priority:3;
 	u8     no:4;
 #else
 #error "unknown bitfield endianness"
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index e3857ed4057f..af8e11933928 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -40,12 +40,15 @@
 #include "fragmentation.h"
 #include "hard-interface.h"
 #include "icmp_socket.h"
+#include "log.h"
 #include "network-coding.h"
 #include "originator.h"
 #include "packet.h"
 #include "send.h"
 #include "soft-interface.h"
+#include "tp_meter.h"
 #include "translation-table.h"
+#include "tvlv.h"
 
 static int batadv_route_unicast_packet(struct sk_buff *skb,
 				       struct batadv_hard_iface *recv_if);
@@ -268,10 +271,19 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv,
 		icmph->ttl = BATADV_TTL;
 
 		res = batadv_send_skb_to_orig(skb, orig_node, NULL);
-		if (res != NET_XMIT_DROP)
-			ret = NET_RX_SUCCESS;
+		if (res == -1)
+			goto out;
+
+		ret = NET_RX_SUCCESS;
 
 		break;
+	case BATADV_TP:
+		if (!pskb_may_pull(skb, sizeof(struct batadv_icmp_tp_packet)))
+			goto out;
+
+		batadv_tp_meter_recv(bat_priv, skb);
+		ret = NET_RX_SUCCESS;
+		goto out;
 	default:
 		/* drop unknown type */
 		goto out;
@@ -290,7 +302,7 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
 	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_orig_node *orig_node = NULL;
 	struct batadv_icmp_packet *icmp_packet;
-	int ret = NET_RX_DROP;
+	int res, ret = NET_RX_DROP;
 
 	icmp_packet = (struct batadv_icmp_packet *)skb->data;
 
@@ -321,7 +333,8 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
 	icmp_packet->msg_type = BATADV_TTL_EXCEEDED;
 	icmp_packet->ttl = BATADV_TTL;
 
-	if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
+	res = batadv_send_skb_to_orig(skb, orig_node, NULL);
+	if (res != -1)
 		ret = NET_RX_SUCCESS;
 
 out:
@@ -341,7 +354,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
 	struct ethhdr *ethhdr;
 	struct batadv_orig_node *orig_node = NULL;
 	int hdr_size = sizeof(struct batadv_icmp_header);
-	int ret = NET_RX_DROP;
+	int res, ret = NET_RX_DROP;
 
 	/* drop packet if it has not necessary minimum size */
 	if (unlikely(!pskb_may_pull(skb, hdr_size)))
@@ -374,6 +387,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
 		if (skb_cow(skb, ETH_HLEN) < 0)
 			goto out;
 
+		ethhdr = eth_hdr(skb);
 		icmph = (struct batadv_icmp_header *)skb->data;
 		icmp_packet_rr = (struct batadv_icmp_packet_rr *)icmph;
 		if (icmp_packet_rr->rr_cur >= BATADV_RR_LEN)
@@ -407,7 +421,8 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
 	icmph->ttl--;
 
 	/* route it */
-	if (batadv_send_skb_to_orig(skb, orig_node, recv_if) != NET_XMIT_DROP)
+	res = batadv_send_skb_to_orig(skb, orig_node, recv_if);
+	if (res != -1)
 		ret = NET_RX_SUCCESS;
 
 out:
@@ -468,7 +483,7 @@ batadv_find_router(struct batadv_priv *bat_priv,
 		   struct batadv_orig_node *orig_node,
 		   struct batadv_hard_iface *recv_if)
 {
-	struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+	struct batadv_algo_ops *bao = bat_priv->algo_ops;
 	struct batadv_neigh_node *first_candidate_router = NULL;
 	struct batadv_neigh_node *next_candidate_router = NULL;
 	struct batadv_neigh_node *router, *cand_router = NULL;
@@ -522,9 +537,9 @@ batadv_find_router(struct batadv_priv *bat_priv,
 		/* alternative candidate should be good enough to be
 		 * considered
 		 */
-		if (!bao->bat_neigh_is_similar_or_better(cand_router,
-							 cand->if_outgoing,
-							 router, recv_if))
+		if (!bao->neigh.is_similar_or_better(cand_router,
+						     cand->if_outgoing, router,
+						     recv_if))
 			goto next;
 
 		/* don't use the same router twice */
@@ -644,6 +659,8 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
 
 	len = skb->len;
 	res = batadv_send_skb_to_orig(skb, orig_node, recv_if);
+	if (res == -1)
+		goto out;
 
 	/* translate transmit result into receive result */
 	if (res == NET_XMIT_SUCCESS) {
@@ -651,13 +668,10 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
 		batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD);
 		batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES,
 				   len + ETH_HLEN);
-
-		ret = NET_RX_SUCCESS;
-	} else if (res == NET_XMIT_POLICED) {
-		/* skb was buffered and consumed */
-		ret = NET_RX_SUCCESS;
 	}
 
+	ret = NET_RX_SUCCESS;
+
 out:
 	if (orig_node)
 		batadv_orig_node_put(orig_node);
@@ -1006,6 +1020,8 @@ int batadv_recv_frag_packet(struct sk_buff *skb,
 	if (!orig_node_src)
 		goto out;
 
+	skb->priority = frag_packet->priority + 256;
+
 	/* Route the fragment if it is not for us and too big to be merged. */
 	if (!batadv_is_my_mac(bat_priv, frag_packet->dest) &&
 	    batadv_frag_skb_fwd(skb, recv_if, orig_node_src)) {
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index f2f125684ed9..3a10d87b4b76 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -20,10 +20,11 @@
 
 #include <linux/atomic.h>
 #include <linux/byteorder/generic.h>
+#include <linux/errno.h>
 #include <linux/etherdevice.h>
 #include <linux/fs.h>
-#include <linux/if_ether.h>
 #include <linux/if.h>
+#include <linux/if_ether.h>
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/kref.h>
@@ -42,6 +43,7 @@
 #include "fragmentation.h"
 #include "gateway_client.h"
 #include "hard-interface.h"
+#include "log.h"
 #include "network-coding.h"
 #include "originator.h"
 #include "routing.h"
@@ -71,6 +73,7 @@ int batadv_send_skb_packet(struct sk_buff *skb,
 {
 	struct batadv_priv *bat_priv;
 	struct ethhdr *ethhdr;
+	int ret;
 
 	bat_priv = netdev_priv(hard_iface->soft_iface);
 
@@ -108,8 +111,15 @@ int batadv_send_skb_packet(struct sk_buff *skb,
 	/* dev_queue_xmit() returns a negative result on error.	 However on
 	 * congestion and traffic shaping, it drops and returns NET_XMIT_DROP
 	 * (which is > 0). This will not be treated as an error.
+	 *
+	 * a negative value cannot be returned because it could be interepreted
+	 * as not consumed skb by callers of batadv_send_skb_to_orig.
 	 */
-	return dev_queue_xmit(skb);
+	ret = dev_queue_xmit(skb);
+	if (ret < 0)
+		ret = NET_XMIT_DROP;
+
+	return ret;
 send_skb_err:
 	kfree_skb(skb);
 	return NET_XMIT_DROP;
@@ -155,8 +165,11 @@ int batadv_send_unicast_skb(struct sk_buff *skb,
  * host, NULL can be passed as recv_if and no interface alternating is
  * attempted.
  *
- * Return: NET_XMIT_SUCCESS on success, NET_XMIT_DROP on failure, or
- * NET_XMIT_POLICED if the skb is buffered for later transmit.
+ * Return: -1 on failure (and the skb is not consumed), -EINPROGRESS if the
+ * skb is buffered for later transmit or the NET_XMIT status returned by the
+ * lower routine if the packet has been passed down.
+ *
+ * If the returning value is not -1 the skb has been consumed.
  */
 int batadv_send_skb_to_orig(struct sk_buff *skb,
 			    struct batadv_orig_node *orig_node,
@@ -164,7 +177,7 @@ int batadv_send_skb_to_orig(struct sk_buff *skb,
 {
 	struct batadv_priv *bat_priv = orig_node->bat_priv;
 	struct batadv_neigh_node *neigh_node;
-	int ret = NET_XMIT_DROP;
+	int ret = -1;
 
 	/* batadv_find_router() increases neigh_nodes refcount if found. */
 	neigh_node = batadv_find_router(bat_priv, orig_node, recv_if);
@@ -177,8 +190,7 @@ int batadv_send_skb_to_orig(struct sk_buff *skb,
 	if (atomic_read(&bat_priv->fragmentation) &&
 	    skb->len > neigh_node->if_incoming->net_dev->mtu) {
 		/* Fragment and send packet. */
-		if (batadv_frag_send_packet(skb, orig_node, neigh_node))
-			ret = NET_XMIT_SUCCESS;
+		ret = batadv_frag_send_packet(skb, orig_node, neigh_node);
 
 		goto out;
 	}
@@ -187,12 +199,10 @@ int batadv_send_skb_to_orig(struct sk_buff *skb,
 	 * (i.e. being forwarded). If the packet originates from this node or if
 	 * network coding fails, then send the packet as usual.
 	 */
-	if (recv_if && batadv_nc_skb_forward(skb, neigh_node)) {
-		ret = NET_XMIT_POLICED;
-	} else {
-		batadv_send_unicast_skb(skb, neigh_node);
-		ret = NET_XMIT_SUCCESS;
-	}
+	if (recv_if && batadv_nc_skb_forward(skb, neigh_node))
+		ret = -EINPROGRESS;
+	else
+		ret = batadv_send_unicast_skb(skb, neigh_node);
 
 out:
 	if (neigh_node)
@@ -318,7 +328,7 @@ int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
 {
 	struct batadv_unicast_packet *unicast_packet;
 	struct ethhdr *ethhdr;
-	int ret = NET_XMIT_DROP;
+	int res, ret = NET_XMIT_DROP;
 
 	if (!orig_node)
 		goto out;
@@ -355,7 +365,8 @@ int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
 	if (batadv_tt_global_client_is_roaming(bat_priv, ethhdr->h_dest, vid))
 		unicast_packet->ttvn = unicast_packet->ttvn - 1;
 
-	if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
+	res = batadv_send_skb_to_orig(skb, orig_node, NULL);
+	if (res != -1)
 		ret = NET_XMIT_SUCCESS;
 
 out:
@@ -428,27 +439,7 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb,
 				       orig_node, vid);
 }
 
-void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface)
-{
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
-
-	if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) ||
-	    (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED))
-		return;
-
-	/* the interface gets activated here to avoid race conditions between
-	 * the moment of activating the interface in
-	 * hardif_activate_interface() where the originator mac is set and
-	 * outdated packets (especially uninitialized mac addresses) in the
-	 * packet queue
-	 */
-	if (hard_iface->if_status == BATADV_IF_TO_BE_ACTIVATED)
-		hard_iface->if_status = BATADV_IF_ACTIVE;
-
-	bat_priv->bat_algo_ops->bat_ogm_schedule(hard_iface);
-}
-
-static void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet)
+void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet)
 {
 	kfree_skb(forw_packet->skb);
 	if (forw_packet->if_incoming)
@@ -604,45 +595,6 @@ out:
 	atomic_inc(&bat_priv->bcast_queue_left);
 }
 
-void batadv_send_outstanding_bat_ogm_packet(struct work_struct *work)
-{
-	struct delayed_work *delayed_work;
-	struct batadv_forw_packet *forw_packet;
-	struct batadv_priv *bat_priv;
-
-	delayed_work = to_delayed_work(work);
-	forw_packet = container_of(delayed_work, struct batadv_forw_packet,
-				   delayed_work);
-	bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface);
-	spin_lock_bh(&bat_priv->forw_bat_list_lock);
-	hlist_del(&forw_packet->list);
-	spin_unlock_bh(&bat_priv->forw_bat_list_lock);
-
-	if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING)
-		goto out;
-
-	bat_priv->bat_algo_ops->bat_ogm_emit(forw_packet);
-
-	/* we have to have at least one packet in the queue to determine the
-	 * queues wake up time unless we are shutting down.
-	 *
-	 * only re-schedule if this is the "original" copy, e.g. the OGM of the
-	 * primary interface should only be rescheduled once per period, but
-	 * this function will be called for the forw_packet instances of the
-	 * other secondary interfaces as well.
-	 */
-	if (forw_packet->own &&
-	    forw_packet->if_incoming == forw_packet->if_outgoing)
-		batadv_schedule_bat_ogm(forw_packet->if_incoming);
-
-out:
-	/* don't count own packet */
-	if (!forw_packet->own)
-		atomic_inc(&bat_priv->batman_queue_left);
-
-	batadv_forw_packet_free(forw_packet);
-}
-
 void
 batadv_purge_outstanding_packets(struct batadv_priv *bat_priv,
 				 const struct batadv_hard_iface *hard_iface)
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index 6fd7270d8ce6..7cecb7563b45 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -26,8 +26,8 @@
 #include "packet.h"
 
 struct sk_buff;
-struct work_struct;
 
+void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet);
 int batadv_send_skb_to_orig(struct sk_buff *skb,
 			    struct batadv_orig_node *orig_node,
 			    struct batadv_hard_iface *recv_if);
@@ -38,11 +38,9 @@ int batadv_send_broadcast_skb(struct sk_buff *skb,
 			      struct batadv_hard_iface *hard_iface);
 int batadv_send_unicast_skb(struct sk_buff *skb,
 			    struct batadv_neigh_node *neigh_node);
-void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface);
 int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
 				    const struct sk_buff *skb,
 				    unsigned long delay);
-void batadv_send_outstanding_bat_ogm_packet(struct work_struct *work);
 void
 batadv_purge_outstanding_packets(struct batadv_priv *bat_priv,
 				 const struct batadv_hard_iface *hard_iface);
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 343d2c904399..7527c0652dd5 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -48,6 +48,7 @@
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
+#include "bat_algo.h"
 #include "bridge_loop_avoidance.h"
 #include "debugfs.h"
 #include "distributed-arp-table.h"
@@ -255,7 +256,7 @@ static int batadv_interface_tx(struct sk_buff *skb,
 	if (batadv_compare_eth(ethhdr->h_dest, ectp_addr))
 		goto dropped;
 
-	gw_mode = atomic_read(&bat_priv->gw_mode);
+	gw_mode = atomic_read(&bat_priv->gw.mode);
 	if (is_multicast_ether_addr(ethhdr->h_dest)) {
 		/* if gw mode is off, broadcast every packet */
 		if (gw_mode == BATADV_GW_MODE_OFF) {
@@ -808,6 +809,10 @@ static int batadv_softif_init_late(struct net_device *dev)
 	atomic_set(&bat_priv->distributed_arp_table, 1);
 #endif
 #ifdef CONFIG_BATMAN_ADV_MCAST
+	bat_priv->mcast.querier_ipv4.exists = false;
+	bat_priv->mcast.querier_ipv4.shadowing = false;
+	bat_priv->mcast.querier_ipv6.exists = false;
+	bat_priv->mcast.querier_ipv6.shadowing = false;
 	bat_priv->mcast.flags = BATADV_NO_FLAGS;
 	atomic_set(&bat_priv->multicast_mode, 1);
 	atomic_set(&bat_priv->mcast.num_disabled, 0);
@@ -815,8 +820,8 @@ static int batadv_softif_init_late(struct net_device *dev)
 	atomic_set(&bat_priv->mcast.num_want_all_ipv4, 0);
 	atomic_set(&bat_priv->mcast.num_want_all_ipv6, 0);
 #endif
-	atomic_set(&bat_priv->gw_mode, BATADV_GW_MODE_OFF);
-	atomic_set(&bat_priv->gw_sel_class, 20);
+	atomic_set(&bat_priv->gw.mode, BATADV_GW_MODE_OFF);
+	atomic_set(&bat_priv->gw.sel_class, 20);
 	atomic_set(&bat_priv->gw.bandwidth_down, 100);
 	atomic_set(&bat_priv->gw.bandwidth_up, 20);
 	atomic_set(&bat_priv->orig_interval, 1000);
@@ -837,6 +842,8 @@ static int batadv_softif_init_late(struct net_device *dev)
 #ifdef CONFIG_BATMAN_ADV_BLA
 	atomic_set(&bat_priv->bla.num_requests, 0);
 #endif
+	atomic_set(&bat_priv->tp_num, 0);
+
 	bat_priv->tt.last_changeset = NULL;
 	bat_priv->tt.last_changeset_len = 0;
 	bat_priv->isolation_mark = 0;
@@ -1033,7 +1040,9 @@ void batadv_softif_destroy_sysfs(struct net_device *soft_iface)
 static void batadv_softif_destroy_netlink(struct net_device *soft_iface,
 					  struct list_head *head)
 {
+	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
 	struct batadv_hard_iface *hard_iface;
+	struct batadv_softif_vlan *vlan;
 
 	list_for_each_entry(hard_iface, &batadv_hardif_list, list) {
 		if (hard_iface->soft_iface == soft_iface)
@@ -1041,6 +1050,13 @@ static void batadv_softif_destroy_netlink(struct net_device *soft_iface,
 							BATADV_IF_CLEANUP_KEEP);
 	}
 
+	/* destroy the "untagged" VLAN */
+	vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS);
+	if (vlan) {
+		batadv_softif_destroy_vlan(bat_priv, vlan);
+		batadv_softif_vlan_put(vlan);
+	}
+
 	batadv_sysfs_del_meshif(soft_iface);
 	unregister_netdevice_queue(soft_iface, head);
 }
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 414b2074165f..fe9ca94ddee2 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -25,8 +25,8 @@
 #include <linux/fs.h>
 #include <linux/if.h>
 #include <linux/if_vlan.h>
-#include <linux/kref.h>
 #include <linux/kernel.h>
+#include <linux/kref.h>
 #include <linux/netdevice.h>
 #include <linux/printk.h>
 #include <linux/rculist.h>
@@ -38,11 +38,12 @@
 #include <linux/string.h>
 #include <linux/stringify.h>
 
+#include "bridge_loop_avoidance.h"
 #include "distributed-arp-table.h"
 #include "gateway_client.h"
 #include "gateway_common.h"
-#include "bridge_loop_avoidance.h"
 #include "hard-interface.h"
+#include "log.h"
 #include "network-coding.h"
 #include "packet.h"
 #include "soft-interface.h"
@@ -389,12 +390,12 @@ static int batadv_store_uint_attr(const char *buff, size_t count,
 	return count;
 }
 
-static inline ssize_t
-__batadv_store_uint_attr(const char *buff, size_t count,
-			 int min, int max,
-			 void (*post_func)(struct net_device *),
-			 const struct attribute *attr,
-			 atomic_t *attr_store, struct net_device *net_dev)
+static ssize_t __batadv_store_uint_attr(const char *buff, size_t count,
+					int min, int max,
+					void (*post_func)(struct net_device *),
+					const struct attribute *attr,
+					atomic_t *attr_store,
+					struct net_device *net_dev)
 {
 	int ret;
 
@@ -411,7 +412,7 @@ static ssize_t batadv_show_bat_algo(struct kobject *kobj,
 {
 	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
 
-	return sprintf(buff, "%s\n", bat_priv->bat_algo_ops->name);
+	return sprintf(buff, "%s\n", bat_priv->algo_ops->name);
 }
 
 static void batadv_post_gw_reselect(struct net_device *net_dev)
@@ -427,7 +428,7 @@ static ssize_t batadv_show_gw_mode(struct kobject *kobj, struct attribute *attr,
 	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
 	int bytes_written;
 
-	switch (atomic_read(&bat_priv->gw_mode)) {
+	switch (atomic_read(&bat_priv->gw.mode)) {
 	case BATADV_GW_MODE_CLIENT:
 		bytes_written = sprintf(buff, "%s\n",
 					BATADV_GW_MODE_CLIENT_NAME);
@@ -476,10 +477,10 @@ static ssize_t batadv_store_gw_mode(struct kobject *kobj,
 		return -EINVAL;
 	}
 
-	if (atomic_read(&bat_priv->gw_mode) == gw_mode_tmp)
+	if (atomic_read(&bat_priv->gw.mode) == gw_mode_tmp)
 		return count;
 
-	switch (atomic_read(&bat_priv->gw_mode)) {
+	switch (atomic_read(&bat_priv->gw.mode)) {
 	case BATADV_GW_MODE_CLIENT:
 		curr_gw_mode_str = BATADV_GW_MODE_CLIENT_NAME;
 		break;
@@ -508,7 +509,7 @@ static ssize_t batadv_store_gw_mode(struct kobject *kobj,
 	 * state
 	 */
 	batadv_gw_check_client_stop(bat_priv);
-	atomic_set(&bat_priv->gw_mode, (unsigned int)gw_mode_tmp);
+	atomic_set(&bat_priv->gw.mode, (unsigned int)gw_mode_tmp);
 	batadv_gw_tvlv_container_update(bat_priv);
 	return count;
 }
@@ -624,7 +625,7 @@ BATADV_ATTR_SIF_UINT(orig_interval, orig_interval, S_IRUGO | S_IWUSR,
 		     2 * BATADV_JITTER, INT_MAX, NULL);
 BATADV_ATTR_SIF_UINT(hop_penalty, hop_penalty, S_IRUGO | S_IWUSR, 0,
 		     BATADV_TQ_MAX_VALUE, NULL);
-BATADV_ATTR_SIF_UINT(gw_sel_class, gw_sel_class, S_IRUGO | S_IWUSR, 1,
+BATADV_ATTR_SIF_UINT(gw_sel_class, gw.sel_class, S_IRUGO | S_IWUSR, 1,
 		     BATADV_TQ_MAX_VALUE, batadv_post_gw_reselect);
 static BATADV_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, batadv_show_gw_bwidth,
 		   batadv_store_gw_bwidth);
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
new file mode 100644
index 000000000000..2333777f919d
--- /dev/null
+++ b/net/batman-adv/tp_meter.c
@@ -0,0 +1,1507 @@
+/* Copyright (C) 2012-2016 B.A.T.M.A.N. contributors:
+ *
+ * Edo Monticelli, Antonio Quartulli
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "tp_meter.h"
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/byteorder/generic.h>
+#include <linux/cache.h>
+#include <linux/compiler.h>
+#include <linux/device.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/kref.h>
+#include <linux/kthread.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/param.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+#include <uapi/linux/batman_adv.h>
+
+#include "hard-interface.h"
+#include "log.h"
+#include "netlink.h"
+#include "originator.h"
+#include "packet.h"
+#include "send.h"
+
+/**
+ * BATADV_TP_DEF_TEST_LENGTH - Default test length if not specified by the user
+ *  in milliseconds
+ */
+#define BATADV_TP_DEF_TEST_LENGTH 10000
+
+/**
+ * BATADV_TP_AWND - Advertised window by the receiver (in bytes)
+ */
+#define BATADV_TP_AWND 0x20000000
+
+/**
+ * BATADV_TP_RECV_TIMEOUT - Receiver activity timeout. If the receiver does not
+ *  get anything for such amount of milliseconds, the connection is killed
+ */
+#define BATADV_TP_RECV_TIMEOUT 1000
+
+/**
+ * BATADV_TP_MAX_RTO - Maximum sender timeout. If the sender RTO gets beyond
+ * such amound of milliseconds, the receiver is considered unreachable and the
+ * connection is killed
+ */
+#define BATADV_TP_MAX_RTO 30000
+
+/**
+ * BATADV_TP_FIRST_SEQ - First seqno of each session. The number is rather high
+ *  in order to immediately trigger a wrap around (test purposes)
+ */
+#define BATADV_TP_FIRST_SEQ ((u32)-1 - 2000)
+
+/**
+ * BATADV_TP_PLEN - length of the payload (data after the batadv_unicast header)
+ *  to simulate
+ */
+#define BATADV_TP_PLEN (BATADV_TP_PACKET_LEN - ETH_HLEN - \
+			sizeof(struct batadv_unicast_packet))
+
+static u8 batadv_tp_prerandom[4096] __read_mostly;
+
+/**
+ * batadv_tp_session_cookie - generate session cookie based on session ids
+ * @session: TP session identifier
+ * @icmp_uid: icmp pseudo uid of the tp session
+ *
+ * Return: 32 bit tp_meter session cookie
+ */
+static u32 batadv_tp_session_cookie(const u8 session[2], u8 icmp_uid)
+{
+	u32 cookie;
+
+	cookie = icmp_uid << 16;
+	cookie |= session[0] << 8;
+	cookie |= session[1];
+
+	return cookie;
+}
+
+/**
+ * batadv_tp_cwnd - compute the new cwnd size
+ * @base: base cwnd size value
+ * @increment: the value to add to base to get the new size
+ * @min: minumim cwnd value (usually MSS)
+ *
+ * Return the new cwnd size and ensures it does not exceed the Advertised
+ * Receiver Window size. It is wrap around safe.
+ * For details refer to Section 3.1 of RFC5681
+ *
+ * Return: new congestion window size in bytes
+ */
+static u32 batadv_tp_cwnd(u32 base, u32 increment, u32 min)
+{
+	u32 new_size = base + increment;
+
+	/* check for wrap-around */
+	if (new_size < base)
+		new_size = (u32)ULONG_MAX;
+
+	new_size = min_t(u32, new_size, BATADV_TP_AWND);
+
+	return max_t(u32, new_size, min);
+}
+
+/**
+ * batadv_tp_updated_cwnd - update the Congestion Windows
+ * @tp_vars: the private data of the current TP meter session
+ * @mss: maximum segment size of transmission
+ *
+ * 1) if the session is in Slow Start, the CWND has to be increased by 1
+ * MSS every unique received ACK
+ * 2) if the session is in Congestion Avoidance, the CWND has to be
+ * increased by MSS * MSS / CWND for every unique received ACK
+ */
+static void batadv_tp_update_cwnd(struct batadv_tp_vars *tp_vars, u32 mss)
+{
+	spin_lock_bh(&tp_vars->cwnd_lock);
+
+	/* slow start... */
+	if (tp_vars->cwnd <= tp_vars->ss_threshold) {
+		tp_vars->dec_cwnd = 0;
+		tp_vars->cwnd = batadv_tp_cwnd(tp_vars->cwnd, mss, mss);
+		spin_unlock_bh(&tp_vars->cwnd_lock);
+		return;
+	}
+
+	/* increment CWND at least of 1 (section 3.1 of RFC5681) */
+	tp_vars->dec_cwnd += max_t(u32, 1U << 3,
+				   ((mss * mss) << 6) / (tp_vars->cwnd << 3));
+	if (tp_vars->dec_cwnd < (mss << 3)) {
+		spin_unlock_bh(&tp_vars->cwnd_lock);
+		return;
+	}
+
+	tp_vars->cwnd = batadv_tp_cwnd(tp_vars->cwnd, mss, mss);
+	tp_vars->dec_cwnd = 0;
+
+	spin_unlock_bh(&tp_vars->cwnd_lock);
+}
+
+/**
+ * batadv_tp_update_rto - calculate new retransmission timeout
+ * @tp_vars: the private data of the current TP meter session
+ * @new_rtt: new roundtrip time in msec
+ */
+static void batadv_tp_update_rto(struct batadv_tp_vars *tp_vars,
+				 u32 new_rtt)
+{
+	long m = new_rtt;
+
+	/* RTT update
+	 * Details in Section 2.2 and 2.3 of RFC6298
+	 *
+	 * It's tricky to understand. Don't lose hair please.
+	 * Inspired by tcp_rtt_estimator() tcp_input.c
+	 */
+	if (tp_vars->srtt != 0) {
+		m -= (tp_vars->srtt >> 3); /* m is now error in rtt est */
+		tp_vars->srtt += m; /* rtt = 7/8 srtt + 1/8 new */
+		if (m < 0)
+			m = -m;
+
+		m -= (tp_vars->rttvar >> 2);
+		tp_vars->rttvar += m; /* mdev ~= 3/4 rttvar + 1/4 new */
+	} else {
+		/* first measure getting in */
+		tp_vars->srtt = m << 3;	/* take the measured time to be srtt */
+		tp_vars->rttvar = m << 1; /* new_rtt / 2 */
+	}
+
+	/* rto = srtt + 4 * rttvar.
+	 * rttvar is scaled by 4, therefore doesn't need to be multiplied
+	 */
+	tp_vars->rto = (tp_vars->srtt >> 3) + tp_vars->rttvar;
+}
+
+/**
+ * batadv_tp_batctl_notify - send client status result to client
+ * @reason: reason for tp meter session stop
+ * @dst: destination of tp_meter session
+ * @bat_priv: the bat priv with all the soft interface information
+ * @start_time: start of transmission in jiffies
+ * @total_sent: bytes acked to the receiver
+ * @cookie: cookie of tp_meter session
+ */
+static void batadv_tp_batctl_notify(enum batadv_tp_meter_reason reason,
+				    const u8 *dst, struct batadv_priv *bat_priv,
+				    unsigned long start_time, u64 total_sent,
+				    u32 cookie)
+{
+	u32 test_time;
+	u8 result;
+	u32 total_bytes;
+
+	if (!batadv_tp_is_error(reason)) {
+		result = BATADV_TP_REASON_COMPLETE;
+		test_time = jiffies_to_msecs(jiffies - start_time);
+		total_bytes = total_sent;
+	} else {
+		result = reason;
+		test_time = 0;
+		total_bytes = 0;
+	}
+
+	batadv_netlink_tpmeter_notify(bat_priv, dst, result, test_time,
+				      total_bytes, cookie);
+}
+
+/**
+ * batadv_tp_batctl_error_notify - send client error result to client
+ * @reason: reason for tp meter session stop
+ * @dst: destination of tp_meter session
+ * @bat_priv: the bat priv with all the soft interface information
+ * @cookie: cookie of tp_meter session
+ */
+static void batadv_tp_batctl_error_notify(enum batadv_tp_meter_reason reason,
+					  const u8 *dst,
+					  struct batadv_priv *bat_priv,
+					  u32 cookie)
+{
+	batadv_tp_batctl_notify(reason, dst, bat_priv, 0, 0, cookie);
+}
+
+/**
+ * batadv_tp_list_find - find a tp_vars object in the global list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: the other endpoint MAC address to look for
+ *
+ * Look for a tp_vars object matching dst as end_point and return it after
+ * having incremented the refcounter. Return NULL is not found
+ *
+ * Return: matching tp_vars or NULL when no tp_vars with @dst was found
+ */
+static struct batadv_tp_vars *batadv_tp_list_find(struct batadv_priv *bat_priv,
+						  const u8 *dst)
+{
+	struct batadv_tp_vars *pos, *tp_vars = NULL;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(pos, &bat_priv->tp_list, list) {
+		if (!batadv_compare_eth(pos->other_end, dst))
+			continue;
+
+		/* most of the time this function is invoked during the normal
+		 * process..it makes sens to pay more when the session is
+		 * finished and to speed the process up during the measurement
+		 */
+		if (unlikely(!kref_get_unless_zero(&pos->refcount)))
+			continue;
+
+		tp_vars = pos;
+		break;
+	}
+	rcu_read_unlock();
+
+	return tp_vars;
+}
+
+/**
+ * batadv_tp_list_find_session - find tp_vars session object in the global list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: the other endpoint MAC address to look for
+ * @session: session identifier
+ *
+ * Look for a tp_vars object matching dst as end_point, session as tp meter
+ * session and return it after having incremented the refcounter. Return NULL
+ * is not found
+ *
+ * Return: matching tp_vars or NULL when no tp_vars was found
+ */
+static struct batadv_tp_vars *
+batadv_tp_list_find_session(struct batadv_priv *bat_priv, const u8 *dst,
+			    const u8 *session)
+{
+	struct batadv_tp_vars *pos, *tp_vars = NULL;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(pos, &bat_priv->tp_list, list) {
+		if (!batadv_compare_eth(pos->other_end, dst))
+			continue;
+
+		if (memcmp(pos->session, session, sizeof(pos->session)) != 0)
+			continue;
+
+		/* most of the time this function is invoked during the normal
+		 * process..it makes sense to pay more when the session is
+		 * finished and to speed the process up during the measurement
+		 */
+		if (unlikely(!kref_get_unless_zero(&pos->refcount)))
+			continue;
+
+		tp_vars = pos;
+		break;
+	}
+	rcu_read_unlock();
+
+	return tp_vars;
+}
+
+/**
+ * batadv_tp_vars_release - release batadv_tp_vars from lists and queue for
+ *  free after rcu grace period
+ * @ref: kref pointer of the batadv_tp_vars
+ */
+static void batadv_tp_vars_release(struct kref *ref)
+{
+	struct batadv_tp_vars *tp_vars;
+	struct batadv_tp_unacked *un, *safe;
+
+	tp_vars = container_of(ref, struct batadv_tp_vars, refcount);
+
+	/* lock should not be needed because this object is now out of any
+	 * context!
+	 */
+	spin_lock_bh(&tp_vars->unacked_lock);
+	list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) {
+		list_del(&un->list);
+		kfree(un);
+	}
+	spin_unlock_bh(&tp_vars->unacked_lock);
+
+	kfree_rcu(tp_vars, rcu);
+}
+
+/**
+ * batadv_tp_vars_put - decrement the batadv_tp_vars refcounter and possibly
+ *  release it
+ * @tp_vars: the private data of the current TP meter session to be free'd
+ */
+static void batadv_tp_vars_put(struct batadv_tp_vars *tp_vars)
+{
+	kref_put(&tp_vars->refcount, batadv_tp_vars_release);
+}
+
+/**
+ * batadv_tp_sender_cleanup - cleanup sender data and drop and timer
+ * @bat_priv: the bat priv with all the soft interface information
+ * @tp_vars: the private data of the current TP meter session to cleanup
+ */
+static void batadv_tp_sender_cleanup(struct batadv_priv *bat_priv,
+				     struct batadv_tp_vars *tp_vars)
+{
+	cancel_delayed_work(&tp_vars->finish_work);
+
+	spin_lock_bh(&tp_vars->bat_priv->tp_list_lock);
+	hlist_del_rcu(&tp_vars->list);
+	spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock);
+
+	/* drop list reference */
+	batadv_tp_vars_put(tp_vars);
+
+	atomic_dec(&tp_vars->bat_priv->tp_num);
+
+	/* kill the timer and remove its reference */
+	del_timer_sync(&tp_vars->timer);
+	/* the worker might have rearmed itself therefore we kill it again. Note
+	 * that if the worker should run again before invoking the following
+	 * del_timer(), it would not re-arm itself once again because the status
+	 * is OFF now
+	 */
+	del_timer(&tp_vars->timer);
+	batadv_tp_vars_put(tp_vars);
+}
+
+/**
+ * batadv_tp_sender_end - print info about ended session and inform client
+ * @bat_priv: the bat priv with all the soft interface information
+ * @tp_vars: the private data of the current TP meter session
+ */
+static void batadv_tp_sender_end(struct batadv_priv *bat_priv,
+				 struct batadv_tp_vars *tp_vars)
+{
+	u32 session_cookie;
+
+	batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+		   "Test towards %pM finished..shutting down (reason=%d)\n",
+		   tp_vars->other_end, tp_vars->reason);
+
+	batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+		   "Last timing stats: SRTT=%ums RTTVAR=%ums RTO=%ums\n",
+		   tp_vars->srtt >> 3, tp_vars->rttvar >> 2, tp_vars->rto);
+
+	batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+		   "Final values: cwnd=%u ss_threshold=%u\n",
+		   tp_vars->cwnd, tp_vars->ss_threshold);
+
+	session_cookie = batadv_tp_session_cookie(tp_vars->session,
+						  tp_vars->icmp_uid);
+
+	batadv_tp_batctl_notify(tp_vars->reason,
+				tp_vars->other_end,
+				bat_priv,
+				tp_vars->start_time,
+				atomic64_read(&tp_vars->tot_sent),
+				session_cookie);
+}
+
+/**
+ * batadv_tp_sender_shutdown - let sender thread/timer stop gracefully
+ * @tp_vars: the private data of the current TP meter session
+ * @reason: reason for tp meter session stop
+ */
+static void batadv_tp_sender_shutdown(struct batadv_tp_vars *tp_vars,
+				      enum batadv_tp_meter_reason reason)
+{
+	if (!atomic_dec_and_test(&tp_vars->sending))
+		return;
+
+	tp_vars->reason = reason;
+}
+
+/**
+ * batadv_tp_sender_finish - stop sender session after test_length was reached
+ * @work: delayed work reference of the related tp_vars
+ */
+static void batadv_tp_sender_finish(struct work_struct *work)
+{
+	struct delayed_work *delayed_work;
+	struct batadv_tp_vars *tp_vars;
+
+	delayed_work = to_delayed_work(work);
+	tp_vars = container_of(delayed_work, struct batadv_tp_vars,
+			       finish_work);
+
+	batadv_tp_sender_shutdown(tp_vars, BATADV_TP_REASON_COMPLETE);
+}
+
+/**
+ * batadv_tp_reset_sender_timer - reschedule the sender timer
+ * @tp_vars: the private TP meter data for this session
+ *
+ * Reschedule the timer using tp_vars->rto as delay
+ */
+static void batadv_tp_reset_sender_timer(struct batadv_tp_vars *tp_vars)
+{
+	/* most of the time this function is invoked while normal packet
+	 * reception...
+	 */
+	if (unlikely(atomic_read(&tp_vars->sending) == 0))
+		/* timer ref will be dropped in batadv_tp_sender_cleanup */
+		return;
+
+	mod_timer(&tp_vars->timer, jiffies + msecs_to_jiffies(tp_vars->rto));
+}
+
+/**
+ * batadv_tp_sender_timeout - timer that fires in case of packet loss
+ * @arg: address of the related tp_vars
+ *
+ * If fired it means that there was packet loss.
+ * Switch to Slow Start, set the ss_threshold to half of the current cwnd and
+ * reset the cwnd to 3*MSS
+ */
+static void batadv_tp_sender_timeout(unsigned long arg)
+{
+	struct batadv_tp_vars *tp_vars = (struct batadv_tp_vars *)arg;
+	struct batadv_priv *bat_priv = tp_vars->bat_priv;
+
+	if (atomic_read(&tp_vars->sending) == 0)
+		return;
+
+	/* if the user waited long enough...shutdown the test */
+	if (unlikely(tp_vars->rto >= BATADV_TP_MAX_RTO)) {
+		batadv_tp_sender_shutdown(tp_vars,
+					  BATADV_TP_REASON_DST_UNREACHABLE);
+		return;
+	}
+
+	/* RTO exponential backoff
+	 * Details in Section 5.5 of RFC6298
+	 */
+	tp_vars->rto <<= 1;
+
+	spin_lock_bh(&tp_vars->cwnd_lock);
+
+	tp_vars->ss_threshold = tp_vars->cwnd >> 1;
+	if (tp_vars->ss_threshold < BATADV_TP_PLEN * 2)
+		tp_vars->ss_threshold = BATADV_TP_PLEN * 2;
+
+	batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+		   "Meter: RTO fired during test towards %pM! cwnd=%u new ss_thr=%u, resetting last_sent to %u\n",
+		   tp_vars->other_end, tp_vars->cwnd, tp_vars->ss_threshold,
+		   atomic_read(&tp_vars->last_acked));
+
+	tp_vars->cwnd = BATADV_TP_PLEN * 3;
+
+	spin_unlock_bh(&tp_vars->cwnd_lock);
+
+	/* resend the non-ACKed packets.. */
+	tp_vars->last_sent = atomic_read(&tp_vars->last_acked);
+	wake_up(&tp_vars->more_bytes);
+
+	batadv_tp_reset_sender_timer(tp_vars);
+}
+
+/**
+ * batadv_tp_fill_prerandom - Fill buffer with prefetched random bytes
+ * @tp_vars: the private TP meter data for this session
+ * @buf: Buffer to fill with bytes
+ * @nbytes: amount of pseudorandom bytes
+ */
+static void batadv_tp_fill_prerandom(struct batadv_tp_vars *tp_vars,
+				     u8 *buf, size_t nbytes)
+{
+	u32 local_offset;
+	size_t bytes_inbuf;
+	size_t to_copy;
+	size_t pos = 0;
+
+	spin_lock_bh(&tp_vars->prerandom_lock);
+	local_offset = tp_vars->prerandom_offset;
+	tp_vars->prerandom_offset += nbytes;
+	tp_vars->prerandom_offset %= sizeof(batadv_tp_prerandom);
+	spin_unlock_bh(&tp_vars->prerandom_lock);
+
+	while (nbytes) {
+		local_offset %= sizeof(batadv_tp_prerandom);
+		bytes_inbuf = sizeof(batadv_tp_prerandom) - local_offset;
+		to_copy = min(nbytes, bytes_inbuf);
+
+		memcpy(&buf[pos], &batadv_tp_prerandom[local_offset], to_copy);
+		pos += to_copy;
+		nbytes -= to_copy;
+		local_offset = 0;
+	}
+}
+
+/**
+ * batadv_tp_send_msg - send a single message
+ * @tp_vars: the private TP meter data for this session
+ * @src: source mac address
+ * @orig_node: the originator of the destination
+ * @seqno: sequence number of this packet
+ * @len: length of the entire packet
+ * @session: session identifier
+ * @uid: local ICMP "socket" index
+ * @timestamp: timestamp in jiffies which is replied in ack
+ *
+ * Create and send a single TP Meter message.
+ *
+ * Return: 0 on success, BATADV_TP_REASON_DST_UNREACHABLE if the destination is
+ * not reachable, BATADV_TP_REASON_MEMORY_ERROR if the packet couldn't be
+ * allocated
+ */
+static int batadv_tp_send_msg(struct batadv_tp_vars *tp_vars, const u8 *src,
+			      struct batadv_orig_node *orig_node,
+			      u32 seqno, size_t len, const u8 *session,
+			      int uid, u32 timestamp)
+{
+	struct batadv_icmp_tp_packet *icmp;
+	struct sk_buff *skb;
+	int r;
+	u8 *data;
+	size_t data_len;
+
+	skb = netdev_alloc_skb_ip_align(NULL, len + ETH_HLEN);
+	if (unlikely(!skb))
+		return BATADV_TP_REASON_MEMORY_ERROR;
+
+	skb_reserve(skb, ETH_HLEN);
+	icmp = (struct batadv_icmp_tp_packet *)skb_put(skb, sizeof(*icmp));
+
+	/* fill the icmp header */
+	ether_addr_copy(icmp->dst, orig_node->orig);
+	ether_addr_copy(icmp->orig, src);
+	icmp->version = BATADV_COMPAT_VERSION;
+	icmp->packet_type = BATADV_ICMP;
+	icmp->ttl = BATADV_TTL;
+	icmp->msg_type = BATADV_TP;
+	icmp->uid = uid;
+
+	icmp->subtype = BATADV_TP_MSG;
+	memcpy(icmp->session, session, sizeof(icmp->session));
+	icmp->seqno = htonl(seqno);
+	icmp->timestamp = htonl(timestamp);
+
+	data_len = len - sizeof(*icmp);
+	data = (u8 *)skb_put(skb, data_len);
+	batadv_tp_fill_prerandom(tp_vars, data, data_len);
+
+	r = batadv_send_skb_to_orig(skb, orig_node, NULL);
+	if (r == -1)
+		kfree_skb(skb);
+
+	if (r == NET_XMIT_SUCCESS)
+		return 0;
+
+	return BATADV_TP_REASON_CANT_SEND;
+}
+
+/**
+ * batadv_tp_recv_ack - ACK receiving function
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the buffer containing the received packet
+ *
+ * Process a received TP ACK packet
+ */
+static void batadv_tp_recv_ack(struct batadv_priv *bat_priv,
+			       const struct sk_buff *skb)
+{
+	struct batadv_hard_iface *primary_if = NULL;
+	struct batadv_orig_node *orig_node = NULL;
+	const struct batadv_icmp_tp_packet *icmp;
+	struct batadv_tp_vars *tp_vars;
+	size_t packet_len, mss;
+	u32 rtt, recv_ack, cwnd;
+	unsigned char *dev_addr;
+
+	packet_len = BATADV_TP_PLEN;
+	mss = BATADV_TP_PLEN;
+	packet_len += sizeof(struct batadv_unicast_packet);
+
+	icmp = (struct batadv_icmp_tp_packet *)skb->data;
+
+	/* find the tp_vars */
+	tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig,
+					      icmp->session);
+	if (unlikely(!tp_vars))
+		return;
+
+	if (unlikely(atomic_read(&tp_vars->sending) == 0))
+		goto out;
+
+	/* old ACK? silently drop it.. */
+	if (batadv_seq_before(ntohl(icmp->seqno),
+			      (u32)atomic_read(&tp_vars->last_acked)))
+		goto out;
+
+	primary_if = batadv_primary_if_get_selected(bat_priv);
+	if (unlikely(!primary_if))
+		goto out;
+
+	orig_node = batadv_orig_hash_find(bat_priv, icmp->orig);
+	if (unlikely(!orig_node))
+		goto out;
+
+	/* update RTO with the new sampled RTT, if any */
+	rtt = jiffies_to_msecs(jiffies) - ntohl(icmp->timestamp);
+	if (icmp->timestamp && rtt)
+		batadv_tp_update_rto(tp_vars, rtt);
+
+	/* ACK for new data... reset the timer */
+	batadv_tp_reset_sender_timer(tp_vars);
+
+	recv_ack = ntohl(icmp->seqno);
+
+	/* check if this ACK is a duplicate */
+	if (atomic_read(&tp_vars->last_acked) == recv_ack) {
+		atomic_inc(&tp_vars->dup_acks);
+		if (atomic_read(&tp_vars->dup_acks) != 3)
+			goto out;
+
+		if (recv_ack >= tp_vars->recover)
+			goto out;
+
+		/* if this is the third duplicate ACK do Fast Retransmit */
+		batadv_tp_send_msg(tp_vars, primary_if->net_dev->dev_addr,
+				   orig_node, recv_ack, packet_len,
+				   icmp->session, icmp->uid,
+				   jiffies_to_msecs(jiffies));
+
+		spin_lock_bh(&tp_vars->cwnd_lock);
+
+		/* Fast Recovery */
+		tp_vars->fast_recovery = true;
+		/* Set recover to the last outstanding seqno when Fast Recovery
+		 * is entered. RFC6582, Section 3.2, step 1
+		 */
+		tp_vars->recover = tp_vars->last_sent;
+		tp_vars->ss_threshold = tp_vars->cwnd >> 1;
+		batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+			   "Meter: Fast Recovery, (cur cwnd=%u) ss_thr=%u last_sent=%u recv_ack=%u\n",
+			   tp_vars->cwnd, tp_vars->ss_threshold,
+			   tp_vars->last_sent, recv_ack);
+		tp_vars->cwnd = batadv_tp_cwnd(tp_vars->ss_threshold, 3 * mss,
+					       mss);
+		tp_vars->dec_cwnd = 0;
+		tp_vars->last_sent = recv_ack;
+
+		spin_unlock_bh(&tp_vars->cwnd_lock);
+	} else {
+		/* count the acked data */
+		atomic64_add(recv_ack - atomic_read(&tp_vars->last_acked),
+			     &tp_vars->tot_sent);
+		/* reset the duplicate ACKs counter */
+		atomic_set(&tp_vars->dup_acks, 0);
+
+		if (tp_vars->fast_recovery) {
+			/* partial ACK */
+			if (batadv_seq_before(recv_ack, tp_vars->recover)) {
+				/* this is another hole in the window. React
+				 * immediately as specified by NewReno (see
+				 * Section 3.2 of RFC6582 for details)
+				 */
+				dev_addr = primary_if->net_dev->dev_addr;
+				batadv_tp_send_msg(tp_vars, dev_addr,
+						   orig_node, recv_ack,
+						   packet_len, icmp->session,
+						   icmp->uid,
+						   jiffies_to_msecs(jiffies));
+				tp_vars->cwnd = batadv_tp_cwnd(tp_vars->cwnd,
+							       mss, mss);
+			} else {
+				tp_vars->fast_recovery = false;
+				/* set cwnd to the value of ss_threshold at the
+				 * moment that Fast Recovery was entered.
+				 * RFC6582, Section 3.2, step 3
+				 */
+				cwnd = batadv_tp_cwnd(tp_vars->ss_threshold, 0,
+						      mss);
+				tp_vars->cwnd = cwnd;
+			}
+			goto move_twnd;
+		}
+
+		if (recv_ack - atomic_read(&tp_vars->last_acked) >= mss)
+			batadv_tp_update_cwnd(tp_vars, mss);
+move_twnd:
+		/* move the Transmit Window */
+		atomic_set(&tp_vars->last_acked, recv_ack);
+	}
+
+	wake_up(&tp_vars->more_bytes);
+out:
+	if (likely(primary_if))
+		batadv_hardif_put(primary_if);
+	if (likely(orig_node))
+		batadv_orig_node_put(orig_node);
+	if (likely(tp_vars))
+		batadv_tp_vars_put(tp_vars);
+}
+
+/**
+ * batadv_tp_avail - check if congestion window is not full
+ * @tp_vars: the private data of the current TP meter session
+ * @payload_len: size of the payload of a single message
+ *
+ * Return: true when congestion window is not full, false otherwise
+ */
+static bool batadv_tp_avail(struct batadv_tp_vars *tp_vars,
+			    size_t payload_len)
+{
+	u32 win_left, win_limit;
+
+	win_limit = atomic_read(&tp_vars->last_acked) + tp_vars->cwnd;
+	win_left = win_limit - tp_vars->last_sent;
+
+	return win_left >= payload_len;
+}
+
+/**
+ * batadv_tp_wait_available - wait until congestion window becomes free or
+ *  timeout is reached
+ * @tp_vars: the private data of the current TP meter session
+ * @plen: size of the payload of a single message
+ *
+ * Return: 0 if the condition evaluated to false after the timeout elapsed,
+ *  1 if the condition evaluated to true after the timeout elapsed, the
+ *  remaining jiffies (at least 1) if the condition evaluated to true before
+ *  the timeout elapsed, or -ERESTARTSYS if it was interrupted by a signal.
+ */
+static int batadv_tp_wait_available(struct batadv_tp_vars *tp_vars, size_t plen)
+{
+	int ret;
+
+	ret = wait_event_interruptible_timeout(tp_vars->more_bytes,
+					       batadv_tp_avail(tp_vars, plen),
+					       HZ / 10);
+
+	return ret;
+}
+
+/**
+ * batadv_tp_send - main sending thread of a tp meter session
+ * @arg: address of the related tp_vars
+ *
+ * Return: nothing, this function never returns
+ */
+static int batadv_tp_send(void *arg)
+{
+	struct batadv_tp_vars *tp_vars = arg;
+	struct batadv_priv *bat_priv = tp_vars->bat_priv;
+	struct batadv_hard_iface *primary_if = NULL;
+	struct batadv_orig_node *orig_node = NULL;
+	size_t payload_len, packet_len;
+	int err = 0;
+
+	if (unlikely(tp_vars->role != BATADV_TP_SENDER)) {
+		err = BATADV_TP_REASON_DST_UNREACHABLE;
+		tp_vars->reason = err;
+		goto out;
+	}
+
+	orig_node = batadv_orig_hash_find(bat_priv, tp_vars->other_end);
+	if (unlikely(!orig_node)) {
+		err = BATADV_TP_REASON_DST_UNREACHABLE;
+		tp_vars->reason = err;
+		goto out;
+	}
+
+	primary_if = batadv_primary_if_get_selected(bat_priv);
+	if (unlikely(!primary_if)) {
+		err = BATADV_TP_REASON_DST_UNREACHABLE;
+		goto out;
+	}
+
+	/* assume that all the hard_interfaces have a correctly
+	 * configured MTU, so use the soft_iface MTU as MSS.
+	 * This might not be true and in that case the fragmentation
+	 * should be used.
+	 * Now, try to send the packet as it is
+	 */
+	payload_len = BATADV_TP_PLEN;
+	BUILD_BUG_ON(sizeof(struct batadv_icmp_tp_packet) > BATADV_TP_PLEN);
+
+	batadv_tp_reset_sender_timer(tp_vars);
+
+	/* queue the worker in charge of terminating the test */
+	queue_delayed_work(batadv_event_workqueue, &tp_vars->finish_work,
+			   msecs_to_jiffies(tp_vars->test_length));
+
+	while (atomic_read(&tp_vars->sending) != 0) {
+		if (unlikely(!batadv_tp_avail(tp_vars, payload_len))) {
+			batadv_tp_wait_available(tp_vars, payload_len);
+			continue;
+		}
+
+		/* to emulate normal unicast traffic, add to the payload len
+		 * the size of the unicast header
+		 */
+		packet_len = payload_len + sizeof(struct batadv_unicast_packet);
+
+		err = batadv_tp_send_msg(tp_vars, primary_if->net_dev->dev_addr,
+					 orig_node, tp_vars->last_sent,
+					 packet_len,
+					 tp_vars->session, tp_vars->icmp_uid,
+					 jiffies_to_msecs(jiffies));
+
+		/* something went wrong during the preparation/transmission */
+		if (unlikely(err && err != BATADV_TP_REASON_CANT_SEND)) {
+			batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+				   "Meter: batadv_tp_send() cannot send packets (%d)\n",
+				   err);
+			/* ensure nobody else tries to stop the thread now */
+			if (atomic_dec_and_test(&tp_vars->sending))
+				tp_vars->reason = err;
+			break;
+		}
+
+		/* right-shift the TWND */
+		if (!err)
+			tp_vars->last_sent += payload_len;
+
+		cond_resched();
+	}
+
+out:
+	if (likely(primary_if))
+		batadv_hardif_put(primary_if);
+	if (likely(orig_node))
+		batadv_orig_node_put(orig_node);
+
+	batadv_tp_sender_end(bat_priv, tp_vars);
+	batadv_tp_sender_cleanup(bat_priv, tp_vars);
+
+	batadv_tp_vars_put(tp_vars);
+
+	do_exit(0);
+}
+
+/**
+ * batadv_tp_start_kthread - start new thread which manages the tp meter sender
+ * @tp_vars: the private data of the current TP meter session
+ */
+static void batadv_tp_start_kthread(struct batadv_tp_vars *tp_vars)
+{
+	struct task_struct *kthread;
+	struct batadv_priv *bat_priv = tp_vars->bat_priv;
+	u32 session_cookie;
+
+	kref_get(&tp_vars->refcount);
+	kthread = kthread_create(batadv_tp_send, tp_vars, "kbatadv_tp_meter");
+	if (IS_ERR(kthread)) {
+		session_cookie = batadv_tp_session_cookie(tp_vars->session,
+							  tp_vars->icmp_uid);
+		pr_err("batadv: cannot create tp meter kthread\n");
+		batadv_tp_batctl_error_notify(BATADV_TP_REASON_MEMORY_ERROR,
+					      tp_vars->other_end,
+					      bat_priv, session_cookie);
+
+		/* drop reserved reference for kthread */
+		batadv_tp_vars_put(tp_vars);
+
+		/* cleanup of failed tp meter variables */
+		batadv_tp_sender_cleanup(bat_priv, tp_vars);
+		return;
+	}
+
+	wake_up_process(kthread);
+}
+
+/**
+ * batadv_tp_start - start a new tp meter session
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: the receiver MAC address
+ * @test_length: test length in milliseconds
+ * @cookie: session cookie
+ */
+void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
+		     u32 test_length, u32 *cookie)
+{
+	struct batadv_tp_vars *tp_vars;
+	u8 session_id[2];
+	u8 icmp_uid;
+	u32 session_cookie;
+
+	get_random_bytes(session_id, sizeof(session_id));
+	get_random_bytes(&icmp_uid, 1);
+	session_cookie = batadv_tp_session_cookie(session_id, icmp_uid);
+	*cookie = session_cookie;
+
+	/* look for an already existing test towards this node */
+	spin_lock_bh(&bat_priv->tp_list_lock);
+	tp_vars = batadv_tp_list_find(bat_priv, dst);
+	if (tp_vars) {
+		spin_unlock_bh(&bat_priv->tp_list_lock);
+		batadv_tp_vars_put(tp_vars);
+		batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+			   "Meter: test to or from the same node already ongoing, aborting\n");
+		batadv_tp_batctl_error_notify(BATADV_TP_REASON_ALREADY_ONGOING,
+					      dst, bat_priv, session_cookie);
+		return;
+	}
+
+	if (!atomic_add_unless(&bat_priv->tp_num, 1, BATADV_TP_MAX_NUM)) {
+		spin_unlock_bh(&bat_priv->tp_list_lock);
+		batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+			   "Meter: too many ongoing sessions, aborting (SEND)\n");
+		batadv_tp_batctl_error_notify(BATADV_TP_REASON_TOO_MANY, dst,
+					      bat_priv, session_cookie);
+		return;
+	}
+
+	tp_vars = kmalloc(sizeof(*tp_vars), GFP_ATOMIC);
+	if (!tp_vars) {
+		spin_unlock_bh(&bat_priv->tp_list_lock);
+		batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+			   "Meter: batadv_tp_start cannot allocate list elements\n");
+		batadv_tp_batctl_error_notify(BATADV_TP_REASON_MEMORY_ERROR,
+					      dst, bat_priv, session_cookie);
+		return;
+	}
+
+	/* initialize tp_vars */
+	ether_addr_copy(tp_vars->other_end, dst);
+	kref_init(&tp_vars->refcount);
+	tp_vars->role = BATADV_TP_SENDER;
+	atomic_set(&tp_vars->sending, 1);
+	memcpy(tp_vars->session, session_id, sizeof(session_id));
+	tp_vars->icmp_uid = icmp_uid;
+
+	tp_vars->last_sent = BATADV_TP_FIRST_SEQ;
+	atomic_set(&tp_vars->last_acked, BATADV_TP_FIRST_SEQ);
+	tp_vars->fast_recovery = false;
+	tp_vars->recover = BATADV_TP_FIRST_SEQ;
+
+	/* initialise the CWND to 3*MSS (Section 3.1 in RFC5681).
+	 * For batman-adv the MSS is the size of the payload received by the
+	 * soft_interface, hence its MTU
+	 */
+	tp_vars->cwnd = BATADV_TP_PLEN * 3;
+	/* at the beginning initialise the SS threshold to the biggest possible
+	 * window size, hence the AWND size
+	 */
+	tp_vars->ss_threshold = BATADV_TP_AWND;
+
+	/* RTO initial value is 3 seconds.
+	 * Details in Section 2.1 of RFC6298
+	 */
+	tp_vars->rto = 1000;
+	tp_vars->srtt = 0;
+	tp_vars->rttvar = 0;
+
+	atomic64_set(&tp_vars->tot_sent, 0);
+
+	kref_get(&tp_vars->refcount);
+	setup_timer(&tp_vars->timer, batadv_tp_sender_timeout,
+		    (unsigned long)tp_vars);
+
+	tp_vars->bat_priv = bat_priv;
+	tp_vars->start_time = jiffies;
+
+	init_waitqueue_head(&tp_vars->more_bytes);
+
+	spin_lock_init(&tp_vars->unacked_lock);
+	INIT_LIST_HEAD(&tp_vars->unacked_list);
+
+	spin_lock_init(&tp_vars->cwnd_lock);
+
+	tp_vars->prerandom_offset = 0;
+	spin_lock_init(&tp_vars->prerandom_lock);
+
+	kref_get(&tp_vars->refcount);
+	hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
+	spin_unlock_bh(&bat_priv->tp_list_lock);
+
+	tp_vars->test_length = test_length;
+	if (!tp_vars->test_length)
+		tp_vars->test_length = BATADV_TP_DEF_TEST_LENGTH;
+
+	batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+		   "Meter: starting throughput meter towards %pM (length=%ums)\n",
+		   dst, test_length);
+
+	/* init work item for finished tp tests */
+	INIT_DELAYED_WORK(&tp_vars->finish_work, batadv_tp_sender_finish);
+
+	/* start tp kthread. This way the write() call issued from userspace can
+	 * happily return and avoid to block
+	 */
+	batadv_tp_start_kthread(tp_vars);
+
+	/* don't return reference to new tp_vars */
+	batadv_tp_vars_put(tp_vars);
+}
+
+/**
+ * batadv_tp_stop - stop currently running tp meter session
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: the receiver MAC address
+ * @return_value: reason for tp meter session stop
+ */
+void batadv_tp_stop(struct batadv_priv *bat_priv, const u8 *dst,
+		    u8 return_value)
+{
+	struct batadv_orig_node *orig_node;
+	struct batadv_tp_vars *tp_vars;
+
+	batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+		   "Meter: stopping test towards %pM\n", dst);
+
+	orig_node = batadv_orig_hash_find(bat_priv, dst);
+	if (!orig_node)
+		return;
+
+	tp_vars = batadv_tp_list_find(bat_priv, orig_node->orig);
+	if (!tp_vars) {
+		batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+			   "Meter: trying to interrupt an already over connection\n");
+		goto out;
+	}
+
+	batadv_tp_sender_shutdown(tp_vars, return_value);
+	batadv_tp_vars_put(tp_vars);
+out:
+	batadv_orig_node_put(orig_node);
+}
+
+/**
+ * batadv_tp_reset_receiver_timer - reset the receiver shutdown timer
+ * @tp_vars: the private data of the current TP meter session
+ *
+ * start the receiver shutdown timer or reset it if already started
+ */
+static void batadv_tp_reset_receiver_timer(struct batadv_tp_vars *tp_vars)
+{
+	mod_timer(&tp_vars->timer,
+		  jiffies + msecs_to_jiffies(BATADV_TP_RECV_TIMEOUT));
+}
+
+/**
+ * batadv_tp_receiver_shutdown - stop a tp meter receiver when timeout is
+ *  reached without received ack
+ * @arg: address of the related tp_vars
+ */
+static void batadv_tp_receiver_shutdown(unsigned long arg)
+{
+	struct batadv_tp_vars *tp_vars = (struct batadv_tp_vars *)arg;
+	struct batadv_tp_unacked *un, *safe;
+	struct batadv_priv *bat_priv;
+
+	bat_priv = tp_vars->bat_priv;
+
+	/* if there is recent activity rearm the timer */
+	if (!batadv_has_timed_out(tp_vars->last_recv_time,
+				  BATADV_TP_RECV_TIMEOUT)) {
+		/* reset the receiver shutdown timer */
+		batadv_tp_reset_receiver_timer(tp_vars);
+		return;
+	}
+
+	batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+		   "Shutting down for inactivity (more than %dms) from %pM\n",
+		   BATADV_TP_RECV_TIMEOUT, tp_vars->other_end);
+
+	spin_lock_bh(&tp_vars->bat_priv->tp_list_lock);
+	hlist_del_rcu(&tp_vars->list);
+	spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock);
+
+	/* drop list reference */
+	batadv_tp_vars_put(tp_vars);
+
+	atomic_dec(&bat_priv->tp_num);
+
+	spin_lock_bh(&tp_vars->unacked_lock);
+	list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) {
+		list_del(&un->list);
+		kfree(un);
+	}
+	spin_unlock_bh(&tp_vars->unacked_lock);
+
+	/* drop reference of timer */
+	batadv_tp_vars_put(tp_vars);
+}
+
+/**
+ * batadv_tp_send_ack - send an ACK packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @dst: the mac address of the destination originator
+ * @seq: the sequence number to ACK
+ * @timestamp: the timestamp to echo back in the ACK
+ * @session: session identifier
+ * @socket_index: local ICMP socket identifier
+ *
+ * Return: 0 on success, a positive integer representing the reason of the
+ * failure otherwise
+ */
+static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst,
+			      u32 seq, __be32 timestamp, const u8 *session,
+			      int socket_index)
+{
+	struct batadv_hard_iface *primary_if = NULL;
+	struct batadv_orig_node *orig_node;
+	struct batadv_icmp_tp_packet *icmp;
+	struct sk_buff *skb;
+	int r, ret;
+
+	orig_node = batadv_orig_hash_find(bat_priv, dst);
+	if (unlikely(!orig_node)) {
+		ret = BATADV_TP_REASON_DST_UNREACHABLE;
+		goto out;
+	}
+
+	primary_if = batadv_primary_if_get_selected(bat_priv);
+	if (unlikely(!primary_if)) {
+		ret = BATADV_TP_REASON_DST_UNREACHABLE;
+		goto out;
+	}
+
+	skb = netdev_alloc_skb_ip_align(NULL, sizeof(*icmp) + ETH_HLEN);
+	if (unlikely(!skb)) {
+		ret = BATADV_TP_REASON_MEMORY_ERROR;
+		goto out;
+	}
+
+	skb_reserve(skb, ETH_HLEN);
+	icmp = (struct batadv_icmp_tp_packet *)skb_put(skb, sizeof(*icmp));
+	icmp->packet_type = BATADV_ICMP;
+	icmp->version = BATADV_COMPAT_VERSION;
+	icmp->ttl = BATADV_TTL;
+	icmp->msg_type = BATADV_TP;
+	ether_addr_copy(icmp->dst, orig_node->orig);
+	ether_addr_copy(icmp->orig, primary_if->net_dev->dev_addr);
+	icmp->uid = socket_index;
+
+	icmp->subtype = BATADV_TP_ACK;
+	memcpy(icmp->session, session, sizeof(icmp->session));
+	icmp->seqno = htonl(seq);
+	icmp->timestamp = timestamp;
+
+	/* send the ack */
+	r = batadv_send_skb_to_orig(skb, orig_node, NULL);
+	if (r == -1)
+		kfree_skb(skb);
+
+	if (unlikely(r < 0) || (r == NET_XMIT_DROP)) {
+		ret = BATADV_TP_REASON_DST_UNREACHABLE;
+		goto out;
+	}
+	ret = 0;
+
+out:
+	if (likely(orig_node))
+		batadv_orig_node_put(orig_node);
+	if (likely(primary_if))
+		batadv_hardif_put(primary_if);
+
+	return ret;
+}
+
+/**
+ * batadv_tp_handle_out_of_order - store an out of order packet
+ * @tp_vars: the private data of the current TP meter session
+ * @skb: the buffer containing the received packet
+ *
+ * Store the out of order packet in the unacked list for late processing. This
+ * packets are kept in this list so that they can be ACKed at once as soon as
+ * all the previous packets have been received
+ *
+ * Return: true if the packed has been successfully processed, false otherwise
+ */
+static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
+					  const struct sk_buff *skb)
+{
+	const struct batadv_icmp_tp_packet *icmp;
+	struct batadv_tp_unacked *un, *new;
+	u32 payload_len;
+	bool added = false;
+
+	new = kmalloc(sizeof(*new), GFP_ATOMIC);
+	if (unlikely(!new))
+		return false;
+
+	icmp = (struct batadv_icmp_tp_packet *)skb->data;
+
+	new->seqno = ntohl(icmp->seqno);
+	payload_len = skb->len - sizeof(struct batadv_unicast_packet);
+	new->len = payload_len;
+
+	spin_lock_bh(&tp_vars->unacked_lock);
+	/* if the list is empty immediately attach this new object */
+	if (list_empty(&tp_vars->unacked_list)) {
+		list_add(&new->list, &tp_vars->unacked_list);
+		goto out;
+	}
+
+	/* otherwise loop over the list and either drop the packet because this
+	 * is a duplicate or store it at the right position.
+	 *
+	 * The iteration is done in the reverse way because it is likely that
+	 * the last received packet (the one being processed now) has a bigger
+	 * seqno than all the others already stored.
+	 */
+	list_for_each_entry_reverse(un, &tp_vars->unacked_list, list) {
+		/* check for duplicates */
+		if (new->seqno == un->seqno) {
+			if (new->len > un->len)
+				un->len = new->len;
+			kfree(new);
+			added = true;
+			break;
+		}
+
+		/* look for the right position */
+		if (batadv_seq_before(new->seqno, un->seqno))
+			continue;
+
+		/* as soon as an entry having a bigger seqno is found, the new
+		 * one is attached _after_ it. In this way the list is kept in
+		 * ascending order
+		 */
+		list_add_tail(&new->list, &un->list);
+		added = true;
+		break;
+	}
+
+	/* received packet with smallest seqno out of order; add it to front */
+	if (!added)
+		list_add(&new->list, &tp_vars->unacked_list);
+
+out:
+	spin_unlock_bh(&tp_vars->unacked_lock);
+
+	return true;
+}
+
+/**
+ * batadv_tp_ack_unordered - update number received bytes in current stream
+ *  without gaps
+ * @tp_vars: the private data of the current TP meter session
+ */
+static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars)
+{
+	struct batadv_tp_unacked *un, *safe;
+	u32 to_ack;
+
+	/* go through the unacked packet list and possibly ACK them as
+	 * well
+	 */
+	spin_lock_bh(&tp_vars->unacked_lock);
+	list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) {
+		/* the list is ordered, therefore it is possible to stop as soon
+		 * there is a gap between the last acked seqno and the seqno of
+		 * the packet under inspection
+		 */
+		if (batadv_seq_before(tp_vars->last_recv, un->seqno))
+			break;
+
+		to_ack = un->seqno + un->len - tp_vars->last_recv;
+
+		if (batadv_seq_before(tp_vars->last_recv, un->seqno + un->len))
+			tp_vars->last_recv += to_ack;
+
+		list_del(&un->list);
+		kfree(un);
+	}
+	spin_unlock_bh(&tp_vars->unacked_lock);
+}
+
+/**
+ * batadv_tp_init_recv - return matching or create new receiver tp_vars
+ * @bat_priv: the bat priv with all the soft interface information
+ * @icmp: received icmp tp msg
+ *
+ * Return: corresponding tp_vars or NULL on errors
+ */
+static struct batadv_tp_vars *
+batadv_tp_init_recv(struct batadv_priv *bat_priv,
+		    const struct batadv_icmp_tp_packet *icmp)
+{
+	struct batadv_tp_vars *tp_vars;
+
+	spin_lock_bh(&bat_priv->tp_list_lock);
+	tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig,
+					      icmp->session);
+	if (tp_vars)
+		goto out_unlock;
+
+	if (!atomic_add_unless(&bat_priv->tp_num, 1, BATADV_TP_MAX_NUM)) {
+		batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+			   "Meter: too many ongoing sessions, aborting (RECV)\n");
+		goto out_unlock;
+	}
+
+	tp_vars = kmalloc(sizeof(*tp_vars), GFP_ATOMIC);
+	if (!tp_vars)
+		goto out_unlock;
+
+	ether_addr_copy(tp_vars->other_end, icmp->orig);
+	tp_vars->role = BATADV_TP_RECEIVER;
+	memcpy(tp_vars->session, icmp->session, sizeof(tp_vars->session));
+	tp_vars->last_recv = BATADV_TP_FIRST_SEQ;
+	tp_vars->bat_priv = bat_priv;
+	kref_init(&tp_vars->refcount);
+
+	spin_lock_init(&tp_vars->unacked_lock);
+	INIT_LIST_HEAD(&tp_vars->unacked_list);
+
+	kref_get(&tp_vars->refcount);
+	hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
+
+	kref_get(&tp_vars->refcount);
+	setup_timer(&tp_vars->timer, batadv_tp_receiver_shutdown,
+		    (unsigned long)tp_vars);
+
+	batadv_tp_reset_receiver_timer(tp_vars);
+
+out_unlock:
+	spin_unlock_bh(&bat_priv->tp_list_lock);
+
+	return tp_vars;
+}
+
+/**
+ * batadv_tp_recv_msg - process a single data message
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the buffer containing the received packet
+ *
+ * Process a received TP MSG packet
+ */
+static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
+			       const struct sk_buff *skb)
+{
+	const struct batadv_icmp_tp_packet *icmp;
+	struct batadv_tp_vars *tp_vars;
+	size_t packet_size;
+	u32 seqno;
+
+	icmp = (struct batadv_icmp_tp_packet *)skb->data;
+
+	seqno = ntohl(icmp->seqno);
+	/* check if this is the first seqno. This means that if the
+	 * first packet is lost, the tp meter does not work anymore!
+	 */
+	if (seqno == BATADV_TP_FIRST_SEQ) {
+		tp_vars = batadv_tp_init_recv(bat_priv, icmp);
+		if (!tp_vars) {
+			batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+				   "Meter: seqno != BATADV_TP_FIRST_SEQ cannot initiate connection\n");
+			goto out;
+		}
+	} else {
+		tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig,
+						      icmp->session);
+		if (!tp_vars) {
+			batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+				   "Unexpected packet from %pM!\n",
+				   icmp->orig);
+			goto out;
+		}
+	}
+
+	if (unlikely(tp_vars->role != BATADV_TP_RECEIVER)) {
+		batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+			   "Meter: dropping packet: not expected (role=%u)\n",
+			   tp_vars->role);
+		goto out;
+	}
+
+	tp_vars->last_recv_time = jiffies;
+
+	/* if the packet is a duplicate, it may be the case that an ACK has been
+	 * lost. Resend the ACK
+	 */
+	if (batadv_seq_before(seqno, tp_vars->last_recv))
+		goto send_ack;
+
+	/* if the packet is out of order enqueue it */
+	if (ntohl(icmp->seqno) != tp_vars->last_recv) {
+		/* exit immediately (and do not send any ACK) if the packet has
+		 * not been enqueued correctly
+		 */
+		if (!batadv_tp_handle_out_of_order(tp_vars, skb))
+			goto out;
+
+		/* send a duplicate ACK */
+		goto send_ack;
+	}
+
+	/* if everything was fine count the ACKed bytes */
+	packet_size = skb->len - sizeof(struct batadv_unicast_packet);
+	tp_vars->last_recv += packet_size;
+
+	/* check if this ordered message filled a gap.... */
+	batadv_tp_ack_unordered(tp_vars);
+
+send_ack:
+	/* send the ACK. If the received packet was out of order, the ACK that
+	 * is going to be sent is a duplicate (the sender will count them and
+	 * possibly enter Fast Retransmit as soon as it has reached 3)
+	 */
+	batadv_tp_send_ack(bat_priv, icmp->orig, tp_vars->last_recv,
+			   icmp->timestamp, icmp->session, icmp->uid);
+out:
+	if (likely(tp_vars))
+		batadv_tp_vars_put(tp_vars);
+}
+
+/**
+ * batadv_tp_meter_recv - main TP Meter receiving function
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the buffer containing the received packet
+ */
+void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb)
+{
+	struct batadv_icmp_tp_packet *icmp;
+
+	icmp = (struct batadv_icmp_tp_packet *)skb->data;
+
+	switch (icmp->subtype) {
+	case BATADV_TP_MSG:
+		batadv_tp_recv_msg(bat_priv, skb);
+		break;
+	case BATADV_TP_ACK:
+		batadv_tp_recv_ack(bat_priv, skb);
+		break;
+	default:
+		batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
+			   "Received unknown TP Metric packet type %u\n",
+			   icmp->subtype);
+	}
+	consume_skb(skb);
+}
+
+/**
+ * batadv_tp_meter_init - initialize global tp_meter structures
+ */
+void batadv_tp_meter_init(void)
+{
+	get_random_bytes(batadv_tp_prerandom, sizeof(batadv_tp_prerandom));
+}
diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h
new file mode 100644
index 000000000000..ba922c425e56
--- /dev/null
+++ b/net/batman-adv/tp_meter.h
@@ -0,0 +1,34 @@
+/* Copyright (C) 2012-2016 B.A.T.M.A.N. contributors:
+ *
+ * Edo Monticelli, Antonio Quartulli
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_TP_METER_H_
+#define _NET_BATMAN_ADV_TP_METER_H_
+
+#include "main.h"
+
+#include <linux/types.h>
+
+struct sk_buff;
+
+void batadv_tp_meter_init(void);
+void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
+		     u32 test_length, u32 *cookie);
+void batadv_tp_stop(struct batadv_priv *bat_priv, const u8 *dst,
+		    u8 return_value);
+void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb);
+
+#endif /* _NET_BATMAN_ADV_TP_METER_H_ */
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index feaf492b01ca..7e6df7a4964a 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -47,10 +47,12 @@
 #include "bridge_loop_avoidance.h"
 #include "hard-interface.h"
 #include "hash.h"
+#include "log.h"
 #include "multicast.h"
 #include "originator.h"
 #include "packet.h"
 #include "soft-interface.h"
+#include "tvlv.h"
 
 /* hash class keys */
 static struct lock_class_key batadv_tt_local_hash_lock_class_key;
@@ -650,8 +652,10 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
 
 	/* increase the refcounter of the related vlan */
 	vlan = batadv_softif_vlan_get(bat_priv, vid);
-	if (WARN(!vlan, "adding TT local entry %pM to non-existent VLAN %d",
-		 addr, BATADV_PRINT_VID(vid))) {
+	if (!vlan) {
+		net_ratelimited_function(batadv_info, soft_iface,
+					 "adding TT local entry %pM to non-existent VLAN %d\n",
+					 addr, BATADV_PRINT_VID(vid));
 		kfree(tt_local);
 		tt_local = NULL;
 		goto out;
@@ -691,7 +695,6 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
 	if (unlikely(hash_added != 0)) {
 		/* remove the reference for the hash */
 		batadv_tt_local_entry_put(tt_local);
-		batadv_softif_vlan_put(vlan);
 		goto out;
 	}
 
@@ -995,7 +998,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset)
 	struct batadv_tt_local_entry *tt_local;
 	struct batadv_hard_iface *primary_if;
 	struct hlist_head *head;
-	unsigned short vid;
 	u32 i;
 	int last_seen_secs;
 	int last_seen_msecs;
@@ -1022,7 +1024,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset)
 			tt_local = container_of(tt_common_entry,
 						struct batadv_tt_local_entry,
 						common);
-			vid = tt_common_entry->vid;
 			last_seen_jiffies = jiffies - tt_local->last_seen;
 			last_seen_msecs = jiffies_to_msecs(last_seen_jiffies);
 			last_seen_secs = last_seen_msecs / 1000;
@@ -1546,7 +1547,7 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv,
 			    struct batadv_tt_global_entry *tt_global_entry)
 {
 	struct batadv_neigh_node *router, *best_router = NULL;
-	struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+	struct batadv_algo_ops *bao = bat_priv->algo_ops;
 	struct hlist_head *head;
 	struct batadv_tt_orig_list_entry *orig_entry, *best_entry = NULL;
 
@@ -1558,8 +1559,8 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv,
 			continue;
 
 		if (best_router &&
-		    bao->bat_neigh_cmp(router, BATADV_IF_DEFAULT,
-				       best_router, BATADV_IF_DEFAULT) <= 0) {
+		    bao->neigh.cmp(router, BATADV_IF_DEFAULT, best_router,
+				   BATADV_IF_DEFAULT) <= 0) {
 			batadv_neigh_node_put(router);
 			continue;
 		}
@@ -2269,6 +2270,29 @@ static u32 batadv_tt_local_crc(struct batadv_priv *bat_priv,
 	return crc;
 }
 
+/**
+ * batadv_tt_req_node_release - free tt_req node entry
+ * @ref: kref pointer of the tt req_node entry
+ */
+static void batadv_tt_req_node_release(struct kref *ref)
+{
+	struct batadv_tt_req_node *tt_req_node;
+
+	tt_req_node = container_of(ref, struct batadv_tt_req_node, refcount);
+
+	kfree(tt_req_node);
+}
+
+/**
+ * batadv_tt_req_node_put - decrement the tt_req_node refcounter and
+ *  possibly release it
+ * @tt_req_node: tt_req_node to be free'd
+ */
+static void batadv_tt_req_node_put(struct batadv_tt_req_node *tt_req_node)
+{
+	kref_put(&tt_req_node->refcount, batadv_tt_req_node_release);
+}
+
 static void batadv_tt_req_list_free(struct batadv_priv *bat_priv)
 {
 	struct batadv_tt_req_node *node;
@@ -2278,7 +2302,7 @@ static void batadv_tt_req_list_free(struct batadv_priv *bat_priv)
 
 	hlist_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) {
 		hlist_del_init(&node->list);
-		kfree(node);
+		batadv_tt_req_node_put(node);
 	}
 
 	spin_unlock_bh(&bat_priv->tt.req_list_lock);
@@ -2315,7 +2339,7 @@ static void batadv_tt_req_purge(struct batadv_priv *bat_priv)
 		if (batadv_has_timed_out(node->issued_at,
 					 BATADV_TT_REQUEST_TIMEOUT)) {
 			hlist_del_init(&node->list);
-			kfree(node);
+			batadv_tt_req_node_put(node);
 		}
 	}
 	spin_unlock_bh(&bat_priv->tt.req_list_lock);
@@ -2347,9 +2371,11 @@ batadv_tt_req_node_new(struct batadv_priv *bat_priv,
 	if (!tt_req_node)
 		goto unlock;
 
+	kref_init(&tt_req_node->refcount);
 	ether_addr_copy(tt_req_node->addr, orig_node->orig);
 	tt_req_node->issued_at = jiffies;
 
+	kref_get(&tt_req_node->refcount);
 	hlist_add_head(&tt_req_node->list, &bat_priv->tt.req_list);
 unlock:
 	spin_unlock_bh(&bat_priv->tt.req_list_lock);
@@ -2613,13 +2639,19 @@ static bool batadv_send_tt_request(struct batadv_priv *bat_priv,
 out:
 	if (primary_if)
 		batadv_hardif_put(primary_if);
+
 	if (ret && tt_req_node) {
 		spin_lock_bh(&bat_priv->tt.req_list_lock);
-		/* hlist_del_init() verifies tt_req_node still is in the list */
-		hlist_del_init(&tt_req_node->list);
+		if (!hlist_unhashed(&tt_req_node->list)) {
+			hlist_del_init(&tt_req_node->list);
+			batadv_tt_req_node_put(tt_req_node);
+		}
 		spin_unlock_bh(&bat_priv->tt.req_list_lock);
-		kfree(tt_req_node);
 	}
+
+	if (tt_req_node)
+		batadv_tt_req_node_put(tt_req_node);
+
 	kfree(tvlv_tt_data);
 	return ret;
 }
@@ -3055,7 +3087,7 @@ static void batadv_handle_tt_response(struct batadv_priv *bat_priv,
 		if (!batadv_compare_eth(node->addr, resp_src))
 			continue;
 		hlist_del_init(&node->list);
-		kfree(node);
+		batadv_tt_req_node_put(node);
 	}
 
 	spin_unlock_bh(&bat_priv->tt.req_list_lock);
diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c
new file mode 100644
index 000000000000..3d1cf0fb112d
--- /dev/null
+++ b/net/batman-adv/tvlv.c
@@ -0,0 +1,632 @@
+/* Copyright (C) 2007-2016  B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+#include <linux/byteorder/generic.h>
+#include <linux/etherdevice.h>
+#include <linux/fs.h>
+#include <linux/if_ether.h>
+#include <linux/kernel.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/lockdep.h>
+#include <linux/netdevice.h>
+#include <linux/pkt_sched.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "originator.h"
+#include "packet.h"
+#include "send.h"
+#include "tvlv.h"
+
+/**
+ * batadv_tvlv_handler_release - release tvlv handler from lists and queue for
+ *  free after rcu grace period
+ * @ref: kref pointer of the tvlv
+ */
+static void batadv_tvlv_handler_release(struct kref *ref)
+{
+	struct batadv_tvlv_handler *tvlv_handler;
+
+	tvlv_handler = container_of(ref, struct batadv_tvlv_handler, refcount);
+	kfree_rcu(tvlv_handler, rcu);
+}
+
+/**
+ * batadv_tvlv_handler_put - decrement the tvlv container refcounter and
+ *  possibly release it
+ * @tvlv_handler: the tvlv handler to free
+ */
+static void batadv_tvlv_handler_put(struct batadv_tvlv_handler *tvlv_handler)
+{
+	kref_put(&tvlv_handler->refcount, batadv_tvlv_handler_release);
+}
+
+/**
+ * batadv_tvlv_handler_get - retrieve tvlv handler from the tvlv handler list
+ *  based on the provided type and version (both need to match)
+ * @bat_priv: the bat priv with all the soft interface information
+ * @type: tvlv handler type to look for
+ * @version: tvlv handler version to look for
+ *
+ * Return: tvlv handler if found or NULL otherwise.
+ */
+static struct batadv_tvlv_handler *
+batadv_tvlv_handler_get(struct batadv_priv *bat_priv, u8 type, u8 version)
+{
+	struct batadv_tvlv_handler *tvlv_handler_tmp, *tvlv_handler = NULL;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tvlv_handler_tmp,
+				 &bat_priv->tvlv.handler_list, list) {
+		if (tvlv_handler_tmp->type != type)
+			continue;
+
+		if (tvlv_handler_tmp->version != version)
+			continue;
+
+		if (!kref_get_unless_zero(&tvlv_handler_tmp->refcount))
+			continue;
+
+		tvlv_handler = tvlv_handler_tmp;
+		break;
+	}
+	rcu_read_unlock();
+
+	return tvlv_handler;
+}
+
+/**
+ * batadv_tvlv_container_release - release tvlv from lists and free
+ * @ref: kref pointer of the tvlv
+ */
+static void batadv_tvlv_container_release(struct kref *ref)
+{
+	struct batadv_tvlv_container *tvlv;
+
+	tvlv = container_of(ref, struct batadv_tvlv_container, refcount);
+	kfree(tvlv);
+}
+
+/**
+ * batadv_tvlv_container_put - decrement the tvlv container refcounter and
+ *  possibly release it
+ * @tvlv: the tvlv container to free
+ */
+static void batadv_tvlv_container_put(struct batadv_tvlv_container *tvlv)
+{
+	kref_put(&tvlv->refcount, batadv_tvlv_container_release);
+}
+
+/**
+ * batadv_tvlv_container_get - retrieve tvlv container from the tvlv container
+ *  list based on the provided type and version (both need to match)
+ * @bat_priv: the bat priv with all the soft interface information
+ * @type: tvlv container type to look for
+ * @version: tvlv container version to look for
+ *
+ * Has to be called with the appropriate locks being acquired
+ * (tvlv.container_list_lock).
+ *
+ * Return: tvlv container if found or NULL otherwise.
+ */
+static struct batadv_tvlv_container *
+batadv_tvlv_container_get(struct batadv_priv *bat_priv, u8 type, u8 version)
+{
+	struct batadv_tvlv_container *tvlv_tmp, *tvlv = NULL;
+
+	lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
+
+	hlist_for_each_entry(tvlv_tmp, &bat_priv->tvlv.container_list, list) {
+		if (tvlv_tmp->tvlv_hdr.type != type)
+			continue;
+
+		if (tvlv_tmp->tvlv_hdr.version != version)
+			continue;
+
+		kref_get(&tvlv_tmp->refcount);
+		tvlv = tvlv_tmp;
+		break;
+	}
+
+	return tvlv;
+}
+
+/**
+ * batadv_tvlv_container_list_size - calculate the size of the tvlv container
+ *  list entries
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Has to be called with the appropriate locks being acquired
+ * (tvlv.container_list_lock).
+ *
+ * Return: size of all currently registered tvlv containers in bytes.
+ */
+static u16 batadv_tvlv_container_list_size(struct batadv_priv *bat_priv)
+{
+	struct batadv_tvlv_container *tvlv;
+	u16 tvlv_len = 0;
+
+	lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
+
+	hlist_for_each_entry(tvlv, &bat_priv->tvlv.container_list, list) {
+		tvlv_len += sizeof(struct batadv_tvlv_hdr);
+		tvlv_len += ntohs(tvlv->tvlv_hdr.len);
+	}
+
+	return tvlv_len;
+}
+
+/**
+ * batadv_tvlv_container_remove - remove tvlv container from the tvlv container
+ *  list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @tvlv: the to be removed tvlv container
+ *
+ * Has to be called with the appropriate locks being acquired
+ * (tvlv.container_list_lock).
+ */
+static void batadv_tvlv_container_remove(struct batadv_priv *bat_priv,
+					 struct batadv_tvlv_container *tvlv)
+{
+	lockdep_assert_held(&bat_priv->tvlv.container_list_lock);
+
+	if (!tvlv)
+		return;
+
+	hlist_del(&tvlv->list);
+
+	/* first call to decrement the counter, second call to free */
+	batadv_tvlv_container_put(tvlv);
+	batadv_tvlv_container_put(tvlv);
+}
+
+/**
+ * batadv_tvlv_container_unregister - unregister tvlv container based on the
+ *  provided type and version (both need to match)
+ * @bat_priv: the bat priv with all the soft interface information
+ * @type: tvlv container type to unregister
+ * @version: tvlv container type to unregister
+ */
+void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv,
+				      u8 type, u8 version)
+{
+	struct batadv_tvlv_container *tvlv;
+
+	spin_lock_bh(&bat_priv->tvlv.container_list_lock);
+	tvlv = batadv_tvlv_container_get(bat_priv, type, version);
+	batadv_tvlv_container_remove(bat_priv, tvlv);
+	spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
+}
+
+/**
+ * batadv_tvlv_container_register - register tvlv type, version and content
+ *  to be propagated with each (primary interface) OGM
+ * @bat_priv: the bat priv with all the soft interface information
+ * @type: tvlv container type
+ * @version: tvlv container version
+ * @tvlv_value: tvlv container content
+ * @tvlv_value_len: tvlv container content length
+ *
+ * If a container of the same type and version was already registered the new
+ * content is going to replace the old one.
+ */
+void batadv_tvlv_container_register(struct batadv_priv *bat_priv,
+				    u8 type, u8 version,
+				    void *tvlv_value, u16 tvlv_value_len)
+{
+	struct batadv_tvlv_container *tvlv_old, *tvlv_new;
+
+	if (!tvlv_value)
+		tvlv_value_len = 0;
+
+	tvlv_new = kzalloc(sizeof(*tvlv_new) + tvlv_value_len, GFP_ATOMIC);
+	if (!tvlv_new)
+		return;
+
+	tvlv_new->tvlv_hdr.version = version;
+	tvlv_new->tvlv_hdr.type = type;
+	tvlv_new->tvlv_hdr.len = htons(tvlv_value_len);
+
+	memcpy(tvlv_new + 1, tvlv_value, ntohs(tvlv_new->tvlv_hdr.len));
+	INIT_HLIST_NODE(&tvlv_new->list);
+	kref_init(&tvlv_new->refcount);
+
+	spin_lock_bh(&bat_priv->tvlv.container_list_lock);
+	tvlv_old = batadv_tvlv_container_get(bat_priv, type, version);
+	batadv_tvlv_container_remove(bat_priv, tvlv_old);
+	hlist_add_head(&tvlv_new->list, &bat_priv->tvlv.container_list);
+	spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
+}
+
+/**
+ * batadv_tvlv_realloc_packet_buff - reallocate packet buffer to accommodate
+ *  requested packet size
+ * @packet_buff: packet buffer
+ * @packet_buff_len: packet buffer size
+ * @min_packet_len: requested packet minimum size
+ * @additional_packet_len: requested additional packet size on top of minimum
+ *  size
+ *
+ * Return: true of the packet buffer could be changed to the requested size,
+ * false otherwise.
+ */
+static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff,
+					    int *packet_buff_len,
+					    int min_packet_len,
+					    int additional_packet_len)
+{
+	unsigned char *new_buff;
+
+	new_buff = kmalloc(min_packet_len + additional_packet_len, GFP_ATOMIC);
+
+	/* keep old buffer if kmalloc should fail */
+	if (!new_buff)
+		return false;
+
+	memcpy(new_buff, *packet_buff, min_packet_len);
+	kfree(*packet_buff);
+	*packet_buff = new_buff;
+	*packet_buff_len = min_packet_len + additional_packet_len;
+
+	return true;
+}
+
+/**
+ * batadv_tvlv_container_ogm_append - append tvlv container content to given
+ *  OGM packet buffer
+ * @bat_priv: the bat priv with all the soft interface information
+ * @packet_buff: ogm packet buffer
+ * @packet_buff_len: ogm packet buffer size including ogm header and tvlv
+ *  content
+ * @packet_min_len: ogm header size to be preserved for the OGM itself
+ *
+ * The ogm packet might be enlarged or shrunk depending on the current size
+ * and the size of the to-be-appended tvlv containers.
+ *
+ * Return: size of all appended tvlv containers in bytes.
+ */
+u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv,
+				     unsigned char **packet_buff,
+				     int *packet_buff_len, int packet_min_len)
+{
+	struct batadv_tvlv_container *tvlv;
+	struct batadv_tvlv_hdr *tvlv_hdr;
+	u16 tvlv_value_len;
+	void *tvlv_value;
+	bool ret;
+
+	spin_lock_bh(&bat_priv->tvlv.container_list_lock);
+	tvlv_value_len = batadv_tvlv_container_list_size(bat_priv);
+
+	ret = batadv_tvlv_realloc_packet_buff(packet_buff, packet_buff_len,
+					      packet_min_len, tvlv_value_len);
+
+	if (!ret)
+		goto end;
+
+	if (!tvlv_value_len)
+		goto end;
+
+	tvlv_value = (*packet_buff) + packet_min_len;
+
+	hlist_for_each_entry(tvlv, &bat_priv->tvlv.container_list, list) {
+		tvlv_hdr = tvlv_value;
+		tvlv_hdr->type = tvlv->tvlv_hdr.type;
+		tvlv_hdr->version = tvlv->tvlv_hdr.version;
+		tvlv_hdr->len = tvlv->tvlv_hdr.len;
+		tvlv_value = tvlv_hdr + 1;
+		memcpy(tvlv_value, tvlv + 1, ntohs(tvlv->tvlv_hdr.len));
+		tvlv_value = (u8 *)tvlv_value + ntohs(tvlv->tvlv_hdr.len);
+	}
+
+end:
+	spin_unlock_bh(&bat_priv->tvlv.container_list_lock);
+	return tvlv_value_len;
+}
+
+/**
+ * batadv_tvlv_call_handler - parse the given tvlv buffer to call the
+ *  appropriate handlers
+ * @bat_priv: the bat priv with all the soft interface information
+ * @tvlv_handler: tvlv callback function handling the tvlv content
+ * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet
+ * @orig_node: orig node emitting the ogm packet
+ * @src: source mac address of the unicast packet
+ * @dst: destination mac address of the unicast packet
+ * @tvlv_value: tvlv content
+ * @tvlv_value_len: tvlv content length
+ *
+ * Return: success if handler was not found or the return value of the handler
+ * callback.
+ */
+static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv,
+				    struct batadv_tvlv_handler *tvlv_handler,
+				    bool ogm_source,
+				    struct batadv_orig_node *orig_node,
+				    u8 *src, u8 *dst,
+				    void *tvlv_value, u16 tvlv_value_len)
+{
+	if (!tvlv_handler)
+		return NET_RX_SUCCESS;
+
+	if (ogm_source) {
+		if (!tvlv_handler->ogm_handler)
+			return NET_RX_SUCCESS;
+
+		if (!orig_node)
+			return NET_RX_SUCCESS;
+
+		tvlv_handler->ogm_handler(bat_priv, orig_node,
+					  BATADV_NO_FLAGS,
+					  tvlv_value, tvlv_value_len);
+		tvlv_handler->flags |= BATADV_TVLV_HANDLER_OGM_CALLED;
+	} else {
+		if (!src)
+			return NET_RX_SUCCESS;
+
+		if (!dst)
+			return NET_RX_SUCCESS;
+
+		if (!tvlv_handler->unicast_handler)
+			return NET_RX_SUCCESS;
+
+		return tvlv_handler->unicast_handler(bat_priv, src,
+						     dst, tvlv_value,
+						     tvlv_value_len);
+	}
+
+	return NET_RX_SUCCESS;
+}
+
+/**
+ * batadv_tvlv_containers_process - parse the given tvlv buffer to call the
+ *  appropriate handlers
+ * @bat_priv: the bat priv with all the soft interface information
+ * @ogm_source: flag indicating whether the tvlv is an ogm or a unicast packet
+ * @orig_node: orig node emitting the ogm packet
+ * @src: source mac address of the unicast packet
+ * @dst: destination mac address of the unicast packet
+ * @tvlv_value: tvlv content
+ * @tvlv_value_len: tvlv content length
+ *
+ * Return: success when processing an OGM or the return value of all called
+ * handler callbacks.
+ */
+int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
+				   bool ogm_source,
+				   struct batadv_orig_node *orig_node,
+				   u8 *src, u8 *dst,
+				   void *tvlv_value, u16 tvlv_value_len)
+{
+	struct batadv_tvlv_handler *tvlv_handler;
+	struct batadv_tvlv_hdr *tvlv_hdr;
+	u16 tvlv_value_cont_len;
+	u8 cifnotfound = BATADV_TVLV_HANDLER_OGM_CIFNOTFND;
+	int ret = NET_RX_SUCCESS;
+
+	while (tvlv_value_len >= sizeof(*tvlv_hdr)) {
+		tvlv_hdr = tvlv_value;
+		tvlv_value_cont_len = ntohs(tvlv_hdr->len);
+		tvlv_value = tvlv_hdr + 1;
+		tvlv_value_len -= sizeof(*tvlv_hdr);
+
+		if (tvlv_value_cont_len > tvlv_value_len)
+			break;
+
+		tvlv_handler = batadv_tvlv_handler_get(bat_priv,
+						       tvlv_hdr->type,
+						       tvlv_hdr->version);
+
+		ret |= batadv_tvlv_call_handler(bat_priv, tvlv_handler,
+						ogm_source, orig_node,
+						src, dst, tvlv_value,
+						tvlv_value_cont_len);
+		if (tvlv_handler)
+			batadv_tvlv_handler_put(tvlv_handler);
+		tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len;
+		tvlv_value_len -= tvlv_value_cont_len;
+	}
+
+	if (!ogm_source)
+		return ret;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tvlv_handler,
+				 &bat_priv->tvlv.handler_list, list) {
+		if ((tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) &&
+		    !(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CALLED))
+			tvlv_handler->ogm_handler(bat_priv, orig_node,
+						  cifnotfound, NULL, 0);
+
+		tvlv_handler->flags &= ~BATADV_TVLV_HANDLER_OGM_CALLED;
+	}
+	rcu_read_unlock();
+
+	return NET_RX_SUCCESS;
+}
+
+/**
+ * batadv_tvlv_ogm_receive - process an incoming ogm and call the appropriate
+ *  handlers
+ * @bat_priv: the bat priv with all the soft interface information
+ * @batadv_ogm_packet: ogm packet containing the tvlv containers
+ * @orig_node: orig node emitting the ogm packet
+ */
+void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv,
+			     struct batadv_ogm_packet *batadv_ogm_packet,
+			     struct batadv_orig_node *orig_node)
+{
+	void *tvlv_value;
+	u16 tvlv_value_len;
+
+	if (!batadv_ogm_packet)
+		return;
+
+	tvlv_value_len = ntohs(batadv_ogm_packet->tvlv_len);
+	if (!tvlv_value_len)
+		return;
+
+	tvlv_value = batadv_ogm_packet + 1;
+
+	batadv_tvlv_containers_process(bat_priv, true, orig_node, NULL, NULL,
+				       tvlv_value, tvlv_value_len);
+}
+
+/**
+ * batadv_tvlv_handler_register - register tvlv handler based on the provided
+ *  type and version (both need to match) for ogm tvlv payload and/or unicast
+ *  payload
+ * @bat_priv: the bat priv with all the soft interface information
+ * @optr: ogm tvlv handler callback function. This function receives the orig
+ *  node, flags and the tvlv content as argument to process.
+ * @uptr: unicast tvlv handler callback function. This function receives the
+ *  source & destination of the unicast packet as well as the tvlv content
+ *  to process.
+ * @type: tvlv handler type to be registered
+ * @version: tvlv handler version to be registered
+ * @flags: flags to enable or disable TVLV API behavior
+ */
+void batadv_tvlv_handler_register(struct batadv_priv *bat_priv,
+				  void (*optr)(struct batadv_priv *bat_priv,
+					       struct batadv_orig_node *orig,
+					       u8 flags,
+					       void *tvlv_value,
+					       u16 tvlv_value_len),
+				  int (*uptr)(struct batadv_priv *bat_priv,
+					      u8 *src, u8 *dst,
+					      void *tvlv_value,
+					      u16 tvlv_value_len),
+				  u8 type, u8 version, u8 flags)
+{
+	struct batadv_tvlv_handler *tvlv_handler;
+
+	tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version);
+	if (tvlv_handler) {
+		batadv_tvlv_handler_put(tvlv_handler);
+		return;
+	}
+
+	tvlv_handler = kzalloc(sizeof(*tvlv_handler), GFP_ATOMIC);
+	if (!tvlv_handler)
+		return;
+
+	tvlv_handler->ogm_handler = optr;
+	tvlv_handler->unicast_handler = uptr;
+	tvlv_handler->type = type;
+	tvlv_handler->version = version;
+	tvlv_handler->flags = flags;
+	kref_init(&tvlv_handler->refcount);
+	INIT_HLIST_NODE(&tvlv_handler->list);
+
+	spin_lock_bh(&bat_priv->tvlv.handler_list_lock);
+	hlist_add_head_rcu(&tvlv_handler->list, &bat_priv->tvlv.handler_list);
+	spin_unlock_bh(&bat_priv->tvlv.handler_list_lock);
+}
+
+/**
+ * batadv_tvlv_handler_unregister - unregister tvlv handler based on the
+ *  provided type and version (both need to match)
+ * @bat_priv: the bat priv with all the soft interface information
+ * @type: tvlv handler type to be unregistered
+ * @version: tvlv handler version to be unregistered
+ */
+void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv,
+				    u8 type, u8 version)
+{
+	struct batadv_tvlv_handler *tvlv_handler;
+
+	tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version);
+	if (!tvlv_handler)
+		return;
+
+	batadv_tvlv_handler_put(tvlv_handler);
+	spin_lock_bh(&bat_priv->tvlv.handler_list_lock);
+	hlist_del_rcu(&tvlv_handler->list);
+	spin_unlock_bh(&bat_priv->tvlv.handler_list_lock);
+	batadv_tvlv_handler_put(tvlv_handler);
+}
+
+/**
+ * batadv_tvlv_unicast_send - send a unicast packet with tvlv payload to the
+ *  specified host
+ * @bat_priv: the bat priv with all the soft interface information
+ * @src: source mac address of the unicast packet
+ * @dst: destination mac address of the unicast packet
+ * @type: tvlv type
+ * @version: tvlv version
+ * @tvlv_value: tvlv content
+ * @tvlv_value_len: tvlv content length
+ */
+void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src,
+			      u8 *dst, u8 type, u8 version,
+			      void *tvlv_value, u16 tvlv_value_len)
+{
+	struct batadv_unicast_tvlv_packet *unicast_tvlv_packet;
+	struct batadv_tvlv_hdr *tvlv_hdr;
+	struct batadv_orig_node *orig_node;
+	struct sk_buff *skb;
+	unsigned char *tvlv_buff;
+	unsigned int tvlv_len;
+	ssize_t hdr_len = sizeof(*unicast_tvlv_packet);
+	int res;
+
+	orig_node = batadv_orig_hash_find(bat_priv, dst);
+	if (!orig_node)
+		return;
+
+	tvlv_len = sizeof(*tvlv_hdr) + tvlv_value_len;
+
+	skb = netdev_alloc_skb_ip_align(NULL, ETH_HLEN + hdr_len + tvlv_len);
+	if (!skb)
+		goto out;
+
+	skb->priority = TC_PRIO_CONTROL;
+	skb_reserve(skb, ETH_HLEN);
+	tvlv_buff = skb_put(skb, sizeof(*unicast_tvlv_packet) + tvlv_len);
+	unicast_tvlv_packet = (struct batadv_unicast_tvlv_packet *)tvlv_buff;
+	unicast_tvlv_packet->packet_type = BATADV_UNICAST_TVLV;
+	unicast_tvlv_packet->version = BATADV_COMPAT_VERSION;
+	unicast_tvlv_packet->ttl = BATADV_TTL;
+	unicast_tvlv_packet->reserved = 0;
+	unicast_tvlv_packet->tvlv_len = htons(tvlv_len);
+	unicast_tvlv_packet->align = 0;
+	ether_addr_copy(unicast_tvlv_packet->src, src);
+	ether_addr_copy(unicast_tvlv_packet->dst, dst);
+
+	tvlv_buff = (unsigned char *)(unicast_tvlv_packet + 1);
+	tvlv_hdr = (struct batadv_tvlv_hdr *)tvlv_buff;
+	tvlv_hdr->version = version;
+	tvlv_hdr->type = type;
+	tvlv_hdr->len = htons(tvlv_value_len);
+	tvlv_buff += sizeof(*tvlv_hdr);
+	memcpy(tvlv_buff, tvlv_value, tvlv_value_len);
+
+	res = batadv_send_skb_to_orig(skb, orig_node, NULL);
+	if (res == -1)
+		kfree_skb(skb);
+out:
+	batadv_orig_node_put(orig_node);
+}
diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h
new file mode 100644
index 000000000000..e4369b547b43
--- /dev/null
+++ b/net/batman-adv/tvlv.h
@@ -0,0 +1,61 @@
+/* Copyright (C) 2007-2016  B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_TVLV_H_
+#define _NET_BATMAN_ADV_TVLV_H_
+
+#include "main.h"
+
+#include <linux/types.h>
+
+struct batadv_ogm_packet;
+
+void batadv_tvlv_container_register(struct batadv_priv *bat_priv,
+				    u8 type, u8 version,
+				    void *tvlv_value, u16 tvlv_value_len);
+u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv,
+				     unsigned char **packet_buff,
+				     int *packet_buff_len, int packet_min_len);
+void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv,
+			     struct batadv_ogm_packet *batadv_ogm_packet,
+			     struct batadv_orig_node *orig_node);
+void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv,
+				      u8 type, u8 version);
+
+void batadv_tvlv_handler_register(struct batadv_priv *bat_priv,
+				  void (*optr)(struct batadv_priv *bat_priv,
+					       struct batadv_orig_node *orig,
+					       u8 flags,
+					       void *tvlv_value,
+					       u16 tvlv_value_len),
+				  int (*uptr)(struct batadv_priv *bat_priv,
+					      u8 *src, u8 *dst,
+					      void *tvlv_value,
+					      u16 tvlv_value_len),
+				  u8 type, u8 version, u8 flags);
+void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv,
+				    u8 type, u8 version);
+int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
+				   bool ogm_source,
+				   struct batadv_orig_node *orig_node,
+				   u8 *src, u8 *dst,
+				   void *tvlv_buff, u16 tvlv_buff_len);
+void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src,
+			      u8 *dst, u8 type, u8 version,
+			      void *tvlv_value, u16 tvlv_value_len);
+
+#endif /* _NET_BATMAN_ADV_TVLV_H_ */
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 6a577f4f8ba7..43db7b61f8eb 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -33,6 +33,7 @@
 #include <linux/types.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <uapi/linux/batman_adv.h>
 
 #include "packet.h"
 
@@ -707,6 +708,8 @@ struct batadv_priv_debug_log {
  * @list: list of available gateway nodes
  * @list_lock: lock protecting gw_list & curr_gw
  * @curr_gw: pointer to currently selected gateway node
+ * @mode: gateway operation: off, client or server (see batadv_gw_modes)
+ * @sel_class: gateway selection class (applies if gw_mode client)
  * @bandwidth_down: advertised uplink download bandwidth (if gw_mode server)
  * @bandwidth_up: advertised uplink upload bandwidth (if gw_mode server)
  * @reselect: bool indicating a gateway re-selection is in progress
@@ -715,6 +718,8 @@ struct batadv_priv_gw {
 	struct hlist_head list;
 	spinlock_t list_lock; /* protects gw_list & curr_gw */
 	struct batadv_gw_node __rcu *curr_gw;  /* rcu protected pointer */
+	atomic_t mode;
+	atomic_t sel_class;
 	atomic_t bandwidth_down;
 	atomic_t bandwidth_up;
 	atomic_t reselect;
@@ -751,14 +756,28 @@ struct batadv_priv_dat {
 
 #ifdef CONFIG_BATMAN_ADV_MCAST
 /**
+ * struct batadv_mcast_querier_state - IGMP/MLD querier state when bridged
+ * @exists: whether a querier exists in the mesh
+ * @shadowing: if a querier exists, whether it is potentially shadowing
+ *  multicast listeners (i.e. querier is behind our own bridge segment)
+ */
+struct batadv_mcast_querier_state {
+	bool exists;
+	bool shadowing;
+};
+
+/**
  * struct batadv_priv_mcast - per mesh interface mcast data
  * @mla_list: list of multicast addresses we are currently announcing via TT
  * @want_all_unsnoopables_list: a list of orig_nodes wanting all unsnoopable
  *  multicast traffic
  * @want_all_ipv4_list: a list of orig_nodes wanting all IPv4 multicast traffic
  * @want_all_ipv6_list: a list of orig_nodes wanting all IPv6 multicast traffic
+ * @querier_ipv4: the current state of an IGMP querier in the mesh
+ * @querier_ipv6: the current state of an MLD querier in the mesh
  * @flags: the flags we have last sent in our mcast tvlv
  * @enabled: whether the multicast tvlv is currently enabled
+ * @bridged: whether the soft interface has a bridge on top
  * @num_disabled: number of nodes that have no mcast tvlv
  * @num_want_all_unsnoopables: number of nodes wanting unsnoopable IP traffic
  * @num_want_all_ipv4: counter for items in want_all_ipv4_list
@@ -771,8 +790,11 @@ struct batadv_priv_mcast {
 	struct hlist_head want_all_unsnoopables_list;
 	struct hlist_head want_all_ipv4_list;
 	struct hlist_head want_all_ipv6_list;
+	struct batadv_mcast_querier_state querier_ipv4;
+	struct batadv_mcast_querier_state querier_ipv6;
 	u8 flags;
 	bool enabled;
+	bool bridged;
 	atomic_t num_disabled;
 	atomic_t num_want_all_unsnoopables;
 	atomic_t num_want_all_ipv4;
@@ -812,6 +834,111 @@ struct batadv_priv_nc {
 };
 
 /**
+ * struct batadv_tp_unacked - unacked packet meta-information
+ * @seqno: seqno of the unacked packet
+ * @len: length of the packet
+ * @list: list node for batadv_tp_vars::unacked_list
+ *
+ * This struct is supposed to represent a buffer unacked packet. However, since
+ * the purpose of the TP meter is to count the traffic only, there is no need to
+ * store the entire sk_buff, the starting offset and the length are enough
+ */
+struct batadv_tp_unacked {
+	u32 seqno;
+	u16 len;
+	struct list_head list;
+};
+
+/**
+ * enum batadv_tp_meter_role - Modus in tp meter session
+ * @BATADV_TP_RECEIVER: Initialized as receiver
+ * @BATADV_TP_SENDER: Initialized as sender
+ */
+enum batadv_tp_meter_role {
+	BATADV_TP_RECEIVER,
+	BATADV_TP_SENDER
+};
+
+/**
+ * struct batadv_tp_vars - tp meter private variables per session
+ * @list: list node for bat_priv::tp_list
+ * @timer: timer for ack (receiver) and retry (sender)
+ * @bat_priv: pointer to the mesh object
+ * @start_time: start time in jiffies
+ * @other_end: mac address of remote
+ * @role: receiver/sender modi
+ * @sending: sending binary semaphore: 1 if sending, 0 is not
+ * @reason: reason for a stopped session
+ * @finish_work: work item for the finishing procedure
+ * @test_length: test length in milliseconds
+ * @session: TP session identifier
+ * @icmp_uid: local ICMP "socket" index
+ * @dec_cwnd: decimal part of the cwnd used during linear growth
+ * @cwnd: current size of the congestion window
+ * @cwnd_lock: lock do protect @cwnd & @dec_cwnd
+ * @ss_threshold: Slow Start threshold. Once cwnd exceeds this value the
+ *  connection switches to the Congestion Avoidance state
+ * @last_acked: last acked byte
+ * @last_sent: last sent byte, not yet acked
+ * @tot_sent: amount of data sent/ACKed so far
+ * @dup_acks: duplicate ACKs counter
+ * @fast_recovery: true if in Fast Recovery mode
+ * @recover: last sent seqno when entering Fast Recovery
+ * @rto: sender timeout
+ * @srtt: smoothed RTT scaled by 2^3
+ * @rttvar: RTT variation scaled by 2^2
+ * @more_bytes: waiting queue anchor when waiting for more ack/retry timeout
+ * @prerandom_offset: offset inside the prerandom buffer
+ * @prerandom_lock: spinlock protecting access to prerandom_offset
+ * @last_recv: last in-order received packet
+ * @unacked_list: list of unacked packets (meta-info only)
+ * @unacked_lock: protect unacked_list
+ * @last_recv_time: time time (jiffies) a msg was received
+ * @refcount: number of context where the object is used
+ * @rcu: struct used for freeing in an RCU-safe manner
+ */
+struct batadv_tp_vars {
+	struct hlist_node list;
+	struct timer_list timer;
+	struct batadv_priv *bat_priv;
+	unsigned long start_time;
+	u8 other_end[ETH_ALEN];
+	enum batadv_tp_meter_role role;
+	atomic_t sending;
+	enum batadv_tp_meter_reason reason;
+	struct delayed_work finish_work;
+	u32 test_length;
+	u8 session[2];
+	u8 icmp_uid;
+
+	/* sender variables */
+	u16 dec_cwnd;
+	u32 cwnd;
+	spinlock_t cwnd_lock; /* Protects cwnd & dec_cwnd */
+	u32 ss_threshold;
+	atomic_t last_acked;
+	u32 last_sent;
+	atomic64_t tot_sent;
+	atomic_t dup_acks;
+	bool fast_recovery;
+	u32 recover;
+	u32 rto;
+	u32 srtt;
+	u32 rttvar;
+	wait_queue_head_t more_bytes;
+	u32 prerandom_offset;
+	spinlock_t prerandom_lock; /* Protects prerandom_offset */
+
+	/* receiver variables */
+	u32 last_recv;
+	struct list_head unacked_list;
+	spinlock_t unacked_lock; /* Protects unacked_list */
+	unsigned long last_recv_time;
+	struct kref refcount;
+	struct rcu_head rcu;
+};
+
+/**
  * struct batadv_softif_vlan - per VLAN attributes set
  * @bat_priv: pointer to the mesh object
  * @vid: VLAN identifier
@@ -865,8 +992,6 @@ struct batadv_priv_bat_v {
  *  enabled
  * @multicast_mode: Enable or disable multicast optimizations on this node's
  *  sender/originating side
- * @gw_mode: gateway operation: off, client or server (see batadv_gw_modes)
- * @gw_sel_class: gateway selection class (applies if gw_mode client)
  * @orig_interval: OGM broadcast interval in milliseconds
  * @hop_penalty: penalty which will be applied to an OGM's tq-field on every hop
  * @log_level: configured log level (see batadv_dbg_level)
@@ -881,14 +1006,17 @@ struct batadv_priv_bat_v {
  * @debug_dir: dentry for debugfs batman-adv subdirectory
  * @forw_bat_list: list of aggregated OGMs that will be forwarded
  * @forw_bcast_list: list of broadcast packets that will be rebroadcasted
+ * @tp_list: list of tp sessions
+ * @tp_num: number of currently active tp sessions
  * @orig_hash: hash table containing mesh participants (orig nodes)
  * @forw_bat_list_lock: lock protecting forw_bat_list
  * @forw_bcast_list_lock: lock protecting forw_bcast_list
+ * @tp_list_lock: spinlock protecting @tp_list
  * @orig_work: work queue callback item for orig node purging
  * @cleanup_work: work queue callback item for soft-interface deinit
  * @primary_if: one of the hard-interfaces assigned to this mesh interface
  *  becomes the primary interface
- * @bat_algo_ops: routing algorithm used by this mesh interface
+ * @algo_ops: routing algorithm used by this mesh interface
  * @softif_vlan_list: a list of softif_vlan structs, one per VLAN created on top
  *  of the mesh interface represented by this object
  * @softif_vlan_list_lock: lock protecting softif_vlan_list
@@ -922,8 +1050,6 @@ struct batadv_priv {
 #ifdef CONFIG_BATMAN_ADV_MCAST
 	atomic_t multicast_mode;
 #endif
-	atomic_t gw_mode;
-	atomic_t gw_sel_class;
 	atomic_t orig_interval;
 	atomic_t hop_penalty;
 #ifdef CONFIG_BATMAN_ADV_DEBUG
@@ -939,13 +1065,16 @@ struct batadv_priv {
 	struct dentry *debug_dir;
 	struct hlist_head forw_bat_list;
 	struct hlist_head forw_bcast_list;
+	struct hlist_head tp_list;
 	struct batadv_hashtable *orig_hash;
 	spinlock_t forw_bat_list_lock; /* protects forw_bat_list */
 	spinlock_t forw_bcast_list_lock; /* protects forw_bcast_list */
+	spinlock_t tp_list_lock; /* protects tp_list */
+	atomic_t tp_num;
 	struct delayed_work orig_work;
 	struct work_struct cleanup_work;
 	struct batadv_hard_iface __rcu *primary_if;  /* rcu protected pointer */
-	struct batadv_algo_ops *bat_algo_ops;
+	struct batadv_algo_ops *algo_ops;
 	struct hlist_head softif_vlan_list;
 	spinlock_t softif_vlan_list_lock; /* protects softif_vlan_list */
 #ifdef CONFIG_BATMAN_ADV_BLA
@@ -1137,11 +1266,13 @@ struct batadv_tt_change_node {
  * struct batadv_tt_req_node - data to keep track of the tt requests in flight
  * @addr: mac address address of the originator this request was sent to
  * @issued_at: timestamp used for purging stale tt requests
+ * @refcount: number of contexts the object is used by
  * @list: list node for batadv_priv_tt::req_list
  */
 struct batadv_tt_req_node {
 	u8 addr[ETH_ALEN];
 	unsigned long issued_at;
+	struct kref refcount;
 	struct hlist_node list;
 };
 
@@ -1259,66 +1390,77 @@ struct batadv_forw_packet {
 };
 
 /**
+ * struct batadv_algo_iface_ops - mesh algorithm callbacks (interface specific)
+ * @activate: start routing mechanisms when hard-interface is brought up
+ * @enable: init routing info when hard-interface is enabled
+ * @disable: de-init routing info when hard-interface is disabled
+ * @update_mac: (re-)init mac addresses of the protocol information
+ *  belonging to this hard-interface
+ * @primary_set: called when primary interface is selected / changed
+ */
+struct batadv_algo_iface_ops {
+	void (*activate)(struct batadv_hard_iface *hard_iface);
+	int (*enable)(struct batadv_hard_iface *hard_iface);
+	void (*disable)(struct batadv_hard_iface *hard_iface);
+	void (*update_mac)(struct batadv_hard_iface *hard_iface);
+	void (*primary_set)(struct batadv_hard_iface *hard_iface);
+};
+
+/**
+ * struct batadv_algo_neigh_ops - mesh algorithm callbacks (neighbour specific)
+ * @hardif_init: called on creation of single hop entry
+ * @cmp: compare the metrics of two neighbors for their respective outgoing
+ *  interfaces
+ * @is_similar_or_better: check if neigh1 is equally similar or better than
+ *  neigh2 for their respective outgoing interface from the metric prospective
+ * @print: print the single hop neighbor list (optional)
+ */
+struct batadv_algo_neigh_ops {
+	void (*hardif_init)(struct batadv_hardif_neigh_node *neigh);
+	int (*cmp)(struct batadv_neigh_node *neigh1,
+		   struct batadv_hard_iface *if_outgoing1,
+		   struct batadv_neigh_node *neigh2,
+		   struct batadv_hard_iface *if_outgoing2);
+	bool (*is_similar_or_better)(struct batadv_neigh_node *neigh1,
+				     struct batadv_hard_iface *if_outgoing1,
+				     struct batadv_neigh_node *neigh2,
+				     struct batadv_hard_iface *if_outgoing2);
+	void (*print)(struct batadv_priv *priv, struct seq_file *seq);
+};
+
+/**
+ * struct batadv_algo_orig_ops - mesh algorithm callbacks (originator specific)
+ * @free: free the resources allocated by the routing algorithm for an orig_node
+ *  object
+ * @add_if: ask the routing algorithm to apply the needed changes to the
+ *  orig_node due to a new hard-interface being added into the mesh
+ * @del_if: ask the routing algorithm to apply the needed changes to the
+ *  orig_node due to an hard-interface being removed from the mesh
+ * @print: print the originator table (optional)
+ */
+struct batadv_algo_orig_ops {
+	void (*free)(struct batadv_orig_node *orig_node);
+	int (*add_if)(struct batadv_orig_node *orig_node, int max_if_num);
+	int (*del_if)(struct batadv_orig_node *orig_node, int max_if_num,
+		      int del_if_num);
+	void (*print)(struct batadv_priv *priv, struct seq_file *seq,
+		      struct batadv_hard_iface *hard_iface);
+};
+
+/**
  * struct batadv_algo_ops - mesh algorithm callbacks
  * @list: list node for the batadv_algo_list
  * @name: name of the algorithm
- * @bat_iface_activate: start routing mechanisms when hard-interface is brought
- *  up
- * @bat_iface_enable: init routing info when hard-interface is enabled
- * @bat_iface_disable: de-init routing info when hard-interface is disabled
- * @bat_iface_update_mac: (re-)init mac addresses of the protocol information
- *  belonging to this hard-interface
- * @bat_primary_iface_set: called when primary interface is selected / changed
- * @bat_ogm_schedule: prepare a new outgoing OGM for the send queue
- * @bat_ogm_emit: send scheduled OGM
- * @bat_hardif_neigh_init: called on creation of single hop entry
- * @bat_neigh_cmp: compare the metrics of two neighbors for their respective
- *  outgoing interfaces
- * @bat_neigh_is_similar_or_better: check if neigh1 is equally similar or
- *  better than neigh2 for their respective outgoing interface from the metric
- *  prospective
- * @bat_neigh_print: print the single hop neighbor list (optional)
- * @bat_neigh_free: free the resources allocated by the routing algorithm for a
- *  neigh_node object
- * @bat_orig_print: print the originator table (optional)
- * @bat_orig_free: free the resources allocated by the routing algorithm for an
- *  orig_node object
- * @bat_orig_add_if: ask the routing algorithm to apply the needed changes to
- *  the orig_node due to a new hard-interface being added into the mesh
- * @bat_orig_del_if: ask the routing algorithm to apply the needed changes to
- *  the orig_node due to an hard-interface being removed from the mesh
+ * @iface: callbacks related to interface handling
+ * @neigh: callbacks related to neighbors handling
+ * @orig: callbacks related to originators handling
  */
 struct batadv_algo_ops {
 	struct hlist_node list;
 	char *name;
-	void (*bat_iface_activate)(struct batadv_hard_iface *hard_iface);
-	int (*bat_iface_enable)(struct batadv_hard_iface *hard_iface);
-	void (*bat_iface_disable)(struct batadv_hard_iface *hard_iface);
-	void (*bat_iface_update_mac)(struct batadv_hard_iface *hard_iface);
-	void (*bat_primary_iface_set)(struct batadv_hard_iface *hard_iface);
-	void (*bat_ogm_schedule)(struct batadv_hard_iface *hard_iface);
-	void (*bat_ogm_emit)(struct batadv_forw_packet *forw_packet);
-	/* neigh_node handling API */
-	void (*bat_hardif_neigh_init)(struct batadv_hardif_neigh_node *neigh);
-	int (*bat_neigh_cmp)(struct batadv_neigh_node *neigh1,
-			     struct batadv_hard_iface *if_outgoing1,
-			     struct batadv_neigh_node *neigh2,
-			     struct batadv_hard_iface *if_outgoing2);
-	bool (*bat_neigh_is_similar_or_better)
-		(struct batadv_neigh_node *neigh1,
-		 struct batadv_hard_iface *if_outgoing1,
-		 struct batadv_neigh_node *neigh2,
-		 struct batadv_hard_iface *if_outgoing2);
-	void (*bat_neigh_print)(struct batadv_priv *priv, struct seq_file *seq);
-	void (*bat_neigh_free)(struct batadv_neigh_node *neigh);
-	/* orig_node handling API */
-	void (*bat_orig_print)(struct batadv_priv *priv, struct seq_file *seq,
-			       struct batadv_hard_iface *hard_iface);
-	void (*bat_orig_free)(struct batadv_orig_node *orig_node);
-	int (*bat_orig_add_if)(struct batadv_orig_node *orig_node,
-			       int max_if_num);
-	int (*bat_orig_del_if)(struct batadv_orig_node *orig_node,
-			       int max_if_num, int del_if_num);
+	struct batadv_algo_iface_ops iface;
+	struct batadv_algo_neigh_ops neigh;
+	struct batadv_algo_orig_ops orig;
 };
 
 /**
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 780089d75915..d020299baba4 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -627,20 +627,9 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
 	return err < 0 ? NET_XMIT_DROP : err;
 }
 
-static struct lock_class_key bt_tx_busylock;
-static struct lock_class_key bt_netdev_xmit_lock_key;
-
-static void bt_set_lockdep_class_one(struct net_device *dev,
-				     struct netdev_queue *txq,
-				     void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &bt_netdev_xmit_lock_key);
-}
-
 static int bt_dev_init(struct net_device *dev)
 {
-	netdev_for_each_tx_queue(dev, bt_set_lockdep_class_one, NULL);
-	dev->qdisc_tx_busylock = &bt_tx_busylock;
+	netdev_lockdep_set_classes(dev);
 
 	return 0;
 }
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 2c8095a5d824..8eecd0ec22f2 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -104,8 +104,16 @@ static int br_dev_init(struct net_device *dev)
 		return -ENOMEM;
 
 	err = br_vlan_init(br);
-	if (err)
+	if (err) {
 		free_percpu(br->stats);
+		return err;
+	}
+
+	err = br_multicast_init_stats(br);
+	if (err) {
+		free_percpu(br->stats);
+		br_vlan_flush(br);
+	}
 	br_set_lockdep_class(dev);
 
 	return err;
@@ -341,6 +349,8 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_add_slave		 = br_add_slave,
 	.ndo_del_slave		 = br_del_slave,
 	.ndo_fix_features        = br_fix_features,
+	.ndo_neigh_construct	 = netdev_default_l2upper_neigh_construct,
+	.ndo_neigh_destroy	 = netdev_default_l2upper_neigh_destroy,
 	.ndo_fdb_add		 = br_fdb_add,
 	.ndo_fdb_del		 = br_fdb_delete,
 	.ndo_fdb_dump		 = br_fdb_dump,
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index dcea4f4c62b3..c18080ad4085 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -279,6 +279,8 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
 	 * change from under us.
 	 */
 	list_for_each_entry(v, &vg->vlan_list, vlist) {
+		if (!br_vlan_should_use(v))
+			continue;
 		f = __br_fdb_get(br, br->dev->dev_addr, v->vid);
 		if (f && f->is_local && !f->dst)
 			fdb_delete_local(br, NULL, f);
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index f47759f05b6d..6c196037d818 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -198,8 +198,10 @@ static void br_flood(struct net_bridge *br, struct sk_buff *skb,
 					   struct sk_buff *skb),
 		     bool unicast)
 {
-	struct net_bridge_port *p;
+	u8 igmp_type = br_multicast_igmp_type(skb);
+	__be16 proto = skb->protocol;
 	struct net_bridge_port *prev;
+	struct net_bridge_port *p;
 
 	prev = NULL;
 
@@ -218,6 +220,9 @@ static void br_flood(struct net_bridge *br, struct sk_buff *skb,
 		prev = maybe_deliver(prev, p, skb, __packet_hook);
 		if (IS_ERR(prev))
 			goto out;
+		if (prev == p)
+			br_multicast_count(p->br, p, proto, igmp_type,
+					   BR_MCAST_DIR_TX);
 	}
 
 	if (!prev)
@@ -257,9 +262,12 @@ static void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
 					struct sk_buff *skb))
 {
 	struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
+	u8 igmp_type = br_multicast_igmp_type(skb);
 	struct net_bridge *br = netdev_priv(dev);
 	struct net_bridge_port *prev = NULL;
 	struct net_bridge_port_group *p;
+	__be16 proto = skb->protocol;
+
 	struct hlist_node *rp;
 
 	rp = rcu_dereference(hlist_first_rcu(&br->router_list));
@@ -277,6 +285,9 @@ static void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
 		prev = maybe_deliver(prev, port, skb, __packet_hook);
 		if (IS_ERR(prev))
 			goto out;
+		if (prev == port)
+			br_multicast_count(port->br, port, proto, igmp_type,
+					   BR_MCAST_DIR_TX);
 
 		if ((unsigned long)lport >= (unsigned long)port)
 			p = rcu_dereference(p->next);
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 8217aecf025b..f2fede05d32c 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -345,8 +345,8 @@ static int find_portno(struct net_bridge *br)
 static struct net_bridge_port *new_nbp(struct net_bridge *br,
 				       struct net_device *dev)
 {
-	int index;
 	struct net_bridge_port *p;
+	int index, err;
 
 	index = find_portno(br);
 	if (index < 0)
@@ -366,7 +366,12 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br,
 	br_init_port(p);
 	br_set_state(p, BR_STATE_DISABLED);
 	br_stp_port_timer_init(p);
-	br_multicast_add_port(p);
+	err = br_multicast_add_port(p);
+	if (err) {
+		dev_put(dev);
+		kfree(p);
+		p = ERR_PTR(err);
+	}
 
 	return p;
 }
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 160797722228..786602bc0567 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -60,6 +60,9 @@ static int br_pass_frame_up(struct sk_buff *skb)
 	skb = br_handle_vlan(br, vg, skb);
 	if (!skb)
 		return NET_RX_DROP;
+	/* update the multicast stats if the packet is IGMP/MLD */
+	br_multicast_count(br, NULL, skb->protocol, br_multicast_igmp_type(skb),
+			   BR_MCAST_DIR_TX);
 
 	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
 		       dev_net(indev), NULL, skb, indev, NULL,
@@ -213,8 +216,7 @@ drop:
 }
 EXPORT_SYMBOL_GPL(br_handle_frame_finish);
 
-/* note: already called with rcu_read_lock */
-static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+static void __br_handle_local_finish(struct sk_buff *skb)
 {
 	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
 	u16 vid = 0;
@@ -222,6 +224,14 @@ static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_bu
 	/* check if vlan is allowed, to avoid spoofing */
 	if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid))
 		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
+}
+
+/* note: already called with rcu_read_lock */
+static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
+
+	__br_handle_local_finish(skb);
 
 	BR_INPUT_SKB_CB(skb)->brdev = p->br->dev;
 	br_pass_frame_up(skb);
@@ -274,7 +284,9 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 			if (p->br->stp_enabled == BR_NO_STP ||
 			    fwd_mask & (1u << dest[5]))
 				goto forward;
-			break;
+			*pskb = skb;
+			__br_handle_local_finish(skb);
+			return RX_HANDLER_PASS;
 
 		case 0x01:	/* IEEE MAC (Pause) */
 			goto drop;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 6852f3c7009c..e405eef0ae2e 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -361,7 +361,8 @@ out:
 }
 
 static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
-						    __be32 group)
+						    __be32 group,
+						    u8 *igmp_type)
 {
 	struct sk_buff *skb;
 	struct igmphdr *ih;
@@ -411,6 +412,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
 
 	skb_set_transport_header(skb, skb->len);
 	ih = igmp_hdr(skb);
+	*igmp_type = IGMP_HOST_MEMBERSHIP_QUERY;
 	ih->type = IGMP_HOST_MEMBERSHIP_QUERY;
 	ih->code = (group ? br->multicast_last_member_interval :
 			    br->multicast_query_response_interval) /
@@ -428,7 +430,8 @@ out:
 
 #if IS_ENABLED(CONFIG_IPV6)
 static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
-						    const struct in6_addr *group)
+						    const struct in6_addr *grp,
+						    u8 *igmp_type)
 {
 	struct sk_buff *skb;
 	struct ipv6hdr *ip6h;
@@ -464,8 +467,11 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 	if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0,
 			       &ip6h->saddr)) {
 		kfree_skb(skb);
+		br->has_ipv6_addr = 0;
 		return NULL;
 	}
+
+	br->has_ipv6_addr = 1;
 	ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest);
 
 	hopopt = (u8 *)(ip6h + 1);
@@ -484,16 +490,17 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 	skb_set_transport_header(skb, skb->len);
 	mldq = (struct mld_msg *) icmp6_hdr(skb);
 
-	interval = ipv6_addr_any(group) ?
+	interval = ipv6_addr_any(grp) ?
 			br->multicast_query_response_interval :
 			br->multicast_last_member_interval;
 
+	*igmp_type = ICMPV6_MGM_QUERY;
 	mldq->mld_type = ICMPV6_MGM_QUERY;
 	mldq->mld_code = 0;
 	mldq->mld_cksum = 0;
 	mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval));
 	mldq->mld_reserved = 0;
-	mldq->mld_mca = *group;
+	mldq->mld_mca = *grp;
 
 	/* checksum */
 	mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
@@ -510,14 +517,16 @@ out:
 #endif
 
 static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
-						struct br_ip *addr)
+						struct br_ip *addr,
+						u8 *igmp_type)
 {
 	switch (addr->proto) {
 	case htons(ETH_P_IP):
-		return br_ip4_multicast_alloc_query(br, addr->u.ip4);
+		return br_ip4_multicast_alloc_query(br, addr->u.ip4, igmp_type);
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		return br_ip6_multicast_alloc_query(br, &addr->u.ip6);
+		return br_ip6_multicast_alloc_query(br, &addr->u.ip6,
+						    igmp_type);
 #endif
 	}
 	return NULL;
@@ -826,18 +835,23 @@ static void __br_multicast_send_query(struct net_bridge *br,
 				      struct br_ip *ip)
 {
 	struct sk_buff *skb;
+	u8 igmp_type;
 
-	skb = br_multicast_alloc_query(br, ip);
+	skb = br_multicast_alloc_query(br, ip, &igmp_type);
 	if (!skb)
 		return;
 
 	if (port) {
 		skb->dev = port->dev;
+		br_multicast_count(br, port, skb->protocol, igmp_type,
+				   BR_MCAST_DIR_TX);
 		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT,
 			dev_net(port->dev), NULL, skb, NULL, skb->dev,
 			br_dev_queue_push_xmit);
 	} else {
 		br_multicast_select_own_querier(br, ip, skb);
+		br_multicast_count(br, port, skb->protocol, igmp_type,
+				   BR_MCAST_DIR_RX);
 		netif_rx(skb);
 	}
 }
@@ -915,7 +929,7 @@ static void br_ip6_multicast_port_query_expired(unsigned long data)
 }
 #endif
 
-void br_multicast_add_port(struct net_bridge_port *port)
+int br_multicast_add_port(struct net_bridge_port *port)
 {
 	port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY;
 
@@ -927,6 +941,11 @@ void br_multicast_add_port(struct net_bridge_port *port)
 	setup_timer(&port->ip6_own_query.timer,
 		    br_ip6_multicast_port_query_expired, (unsigned long)port);
 #endif
+	port->mcast_stats = netdev_alloc_pcpu_stats(struct bridge_mcast_stats);
+	if (!port->mcast_stats)
+		return -ENOMEM;
+
+	return 0;
 }
 
 void br_multicast_del_port(struct net_bridge_port *port)
@@ -941,6 +960,7 @@ void br_multicast_del_port(struct net_bridge_port *port)
 		br_multicast_del_pg(br, pg);
 	spin_unlock_bh(&br->multicast_lock);
 	del_timer_sync(&port->multicast_router_timer);
+	free_percpu(port->mcast_stats);
 }
 
 static void br_multicast_enable(struct bridge_mcast_own_query *query)
@@ -1580,6 +1600,39 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 }
 #endif
 
+static void br_multicast_err_count(const struct net_bridge *br,
+				   const struct net_bridge_port *p,
+				   __be16 proto)
+{
+	struct bridge_mcast_stats __percpu *stats;
+	struct bridge_mcast_stats *pstats;
+
+	if (!br->multicast_stats_enabled)
+		return;
+
+	if (p)
+		stats = p->mcast_stats;
+	else
+		stats = br->mcast_stats;
+	if (WARN_ON(!stats))
+		return;
+
+	pstats = this_cpu_ptr(stats);
+
+	u64_stats_update_begin(&pstats->syncp);
+	switch (proto) {
+	case htons(ETH_P_IP):
+		pstats->mstats.igmp_parse_errors++;
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		pstats->mstats.mld_parse_errors++;
+		break;
+#endif
+	}
+	u64_stats_update_end(&pstats->syncp);
+}
+
 static int br_multicast_ipv4_rcv(struct net_bridge *br,
 				 struct net_bridge_port *port,
 				 struct sk_buff *skb,
@@ -1596,11 +1649,12 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
 			BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
 		return 0;
 	} else if (err < 0) {
+		br_multicast_err_count(br, port, skb->protocol);
 		return err;
 	}
 
-	BR_INPUT_SKB_CB(skb)->igmp = 1;
 	ih = igmp_hdr(skb);
+	BR_INPUT_SKB_CB(skb)->igmp = ih->type;
 
 	switch (ih->type) {
 	case IGMP_HOST_MEMBERSHIP_REPORT:
@@ -1622,6 +1676,9 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
 	if (skb_trimmed && skb_trimmed != skb)
 		kfree_skb(skb_trimmed);
 
+	br_multicast_count(br, port, skb->protocol, BR_INPUT_SKB_CB(skb)->igmp,
+			   BR_MCAST_DIR_RX);
+
 	return err;
 }
 
@@ -1642,11 +1699,12 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 			BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
 		return 0;
 	} else if (err < 0) {
+		br_multicast_err_count(br, port, skb->protocol);
 		return err;
 	}
 
-	BR_INPUT_SKB_CB(skb)->igmp = 1;
 	mld = (struct mld_msg *)skb_transport_header(skb);
+	BR_INPUT_SKB_CB(skb)->igmp = mld->mld_type;
 
 	switch (mld->mld_type) {
 	case ICMPV6_MGM_REPORT:
@@ -1667,6 +1725,9 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 	if (skb_trimmed && skb_trimmed != skb)
 		kfree_skb(skb_trimmed);
 
+	br_multicast_count(br, port, skb->protocol, BR_INPUT_SKB_CB(skb)->igmp,
+			   BR_MCAST_DIR_RX);
+
 	return err;
 }
 #endif
@@ -1674,6 +1735,8 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
 		     struct sk_buff *skb, u16 vid)
 {
+	int ret = 0;
+
 	BR_INPUT_SKB_CB(skb)->igmp = 0;
 	BR_INPUT_SKB_CB(skb)->mrouters_only = 0;
 
@@ -1682,14 +1745,16 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		return br_multicast_ipv4_rcv(br, port, skb, vid);
+		ret = br_multicast_ipv4_rcv(br, port, skb, vid);
+		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		return br_multicast_ipv6_rcv(br, port, skb, vid);
+		ret = br_multicast_ipv6_rcv(br, port, skb, vid);
+		break;
 #endif
 	}
 
-	return 0;
+	return ret;
 }
 
 static void br_multicast_query_expired(struct net_bridge *br,
@@ -1745,6 +1810,7 @@ void br_multicast_init(struct net_bridge *br)
 	br->ip6_other_query.delay_time = 0;
 	br->ip6_querier.port = NULL;
 #endif
+	br->has_ipv6_addr = 1;
 
 	spin_lock_init(&br->multicast_lock);
 	setup_timer(&br->multicast_router_timer,
@@ -1827,6 +1893,8 @@ void br_multicast_dev_del(struct net_bridge *br)
 
 out:
 	spin_unlock_bh(&br->multicast_lock);
+
+	free_percpu(br->mcast_stats);
 }
 
 int br_multicast_set_router(struct net_bridge *br, unsigned long val)
@@ -2181,3 +2249,128 @@ unlock:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent);
+
+static void br_mcast_stats_add(struct bridge_mcast_stats __percpu *stats,
+			       __be16 proto, u8 type, u8 dir)
+{
+	struct bridge_mcast_stats *pstats = this_cpu_ptr(stats);
+
+	u64_stats_update_begin(&pstats->syncp);
+	switch (proto) {
+	case htons(ETH_P_IP):
+		switch (type) {
+		case IGMP_HOST_MEMBERSHIP_REPORT:
+			pstats->mstats.igmp_v1reports[dir]++;
+			break;
+		case IGMPV2_HOST_MEMBERSHIP_REPORT:
+			pstats->mstats.igmp_v2reports[dir]++;
+			break;
+		case IGMPV3_HOST_MEMBERSHIP_REPORT:
+			pstats->mstats.igmp_v3reports[dir]++;
+			break;
+		case IGMP_HOST_MEMBERSHIP_QUERY:
+			pstats->mstats.igmp_queries[dir]++;
+			break;
+		case IGMP_HOST_LEAVE_MESSAGE:
+			pstats->mstats.igmp_leaves[dir]++;
+			break;
+		}
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		switch (type) {
+		case ICMPV6_MGM_REPORT:
+			pstats->mstats.mld_v1reports[dir]++;
+			break;
+		case ICMPV6_MLD2_REPORT:
+			pstats->mstats.mld_v2reports[dir]++;
+			break;
+		case ICMPV6_MGM_QUERY:
+			pstats->mstats.mld_queries[dir]++;
+			break;
+		case ICMPV6_MGM_REDUCTION:
+			pstats->mstats.mld_leaves[dir]++;
+			break;
+		}
+		break;
+#endif /* CONFIG_IPV6 */
+	}
+	u64_stats_update_end(&pstats->syncp);
+}
+
+void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p,
+			__be16 proto, u8 type, u8 dir)
+{
+	struct bridge_mcast_stats __percpu *stats;
+
+	/* if multicast_disabled is true then igmp type can't be set */
+	if (!type || !br->multicast_stats_enabled)
+		return;
+
+	if (p)
+		stats = p->mcast_stats;
+	else
+		stats = br->mcast_stats;
+	if (WARN_ON(!stats))
+		return;
+
+	br_mcast_stats_add(stats, proto, type, dir);
+}
+
+int br_multicast_init_stats(struct net_bridge *br)
+{
+	br->mcast_stats = netdev_alloc_pcpu_stats(struct bridge_mcast_stats);
+	if (!br->mcast_stats)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void mcast_stats_add_dir(u64 *dst, u64 *src)
+{
+	dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX];
+	dst[BR_MCAST_DIR_TX] += src[BR_MCAST_DIR_TX];
+}
+
+void br_multicast_get_stats(const struct net_bridge *br,
+			    const struct net_bridge_port *p,
+			    struct br_mcast_stats *dest)
+{
+	struct bridge_mcast_stats __percpu *stats;
+	struct br_mcast_stats tdst;
+	int i;
+
+	memset(dest, 0, sizeof(*dest));
+	if (p)
+		stats = p->mcast_stats;
+	else
+		stats = br->mcast_stats;
+	if (WARN_ON(!stats))
+		return;
+
+	memset(&tdst, 0, sizeof(tdst));
+	for_each_possible_cpu(i) {
+		struct bridge_mcast_stats *cpu_stats = per_cpu_ptr(stats, i);
+		struct br_mcast_stats temp;
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
+			memcpy(&temp, &cpu_stats->mstats, sizeof(temp));
+		} while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));
+
+		mcast_stats_add_dir(tdst.igmp_queries, temp.igmp_queries);
+		mcast_stats_add_dir(tdst.igmp_leaves, temp.igmp_leaves);
+		mcast_stats_add_dir(tdst.igmp_v1reports, temp.igmp_v1reports);
+		mcast_stats_add_dir(tdst.igmp_v2reports, temp.igmp_v2reports);
+		mcast_stats_add_dir(tdst.igmp_v3reports, temp.igmp_v3reports);
+		tdst.igmp_parse_errors += temp.igmp_parse_errors;
+
+		mcast_stats_add_dir(tdst.mld_queries, temp.mld_queries);
+		mcast_stats_add_dir(tdst.mld_leaves, temp.mld_leaves);
+		mcast_stats_add_dir(tdst.mld_v1reports, temp.mld_v1reports);
+		mcast_stats_add_dir(tdst.mld_v2reports, temp.mld_v2reports);
+		tdst.mld_parse_errors += temp.mld_parse_errors;
+	}
+	memcpy(dest, &tdst, sizeof(*dest));
+}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index a5343c7232bf..f2a29e467e78 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -851,6 +851,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
 	[IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 },
 	[IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 },
 	[IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 },
+	[IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 },
 };
 
 static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
@@ -1055,6 +1056,13 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 
 		br->multicast_startup_query_interval = clock_t_to_jiffies(val);
 	}
+
+	if (data[IFLA_BR_MCAST_STATS_ENABLED]) {
+		__u8 mcast_stats;
+
+		mcast_stats = nla_get_u8(data[IFLA_BR_MCAST_STATS_ENABLED]);
+		br->multicast_stats_enabled = !!mcast_stats;
+	}
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (data[IFLA_BR_NF_CALL_IPTABLES]) {
@@ -1110,6 +1118,7 @@ static size_t br_get_size(const struct net_device *brdev)
 	       nla_total_size(sizeof(u8)) +     /* IFLA_BR_MCAST_SNOOPING */
 	       nla_total_size(sizeof(u8)) +     /* IFLA_BR_MCAST_QUERY_USE_IFADDR */
 	       nla_total_size(sizeof(u8)) +     /* IFLA_BR_MCAST_QUERIER */
+	       nla_total_size(sizeof(u8)) +     /* IFLA_BR_MCAST_STATS_ENABLED */
 	       nla_total_size(sizeof(u32)) +    /* IFLA_BR_MCAST_HASH_ELASTICITY */
 	       nla_total_size(sizeof(u32)) +    /* IFLA_BR_MCAST_HASH_MAX */
 	       nla_total_size(sizeof(u32)) +    /* IFLA_BR_MCAST_LAST_MEMBER_CNT */
@@ -1187,6 +1196,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 	    nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR,
 		       br->multicast_query_use_ifaddr) ||
 	    nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier) ||
+	    nla_put_u8(skb, IFLA_BR_MCAST_STATS_ENABLED,
+		       br->multicast_stats_enabled) ||
 	    nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY,
 			br->hash_elasticity) ||
 	    nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) ||
@@ -1234,7 +1245,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 	return 0;
 }
 
-static size_t br_get_linkxstats_size(const struct net_device *dev)
+static size_t bridge_get_linkxstats_size(const struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
 	struct net_bridge_vlan_group *vg;
@@ -1242,53 +1253,88 @@ static size_t br_get_linkxstats_size(const struct net_device *dev)
 	int numvls = 0;
 
 	vg = br_vlan_group(br);
-	if (!vg)
-		return 0;
-
-	/* we need to count all, even placeholder entries */
-	list_for_each_entry(v, &vg->vlan_list, vlist)
-		numvls++;
+	if (vg) {
+		/* we need to count all, even placeholder entries */
+		list_for_each_entry(v, &vg->vlan_list, vlist)
+			numvls++;
+	}
 
-	/* account for the vlans and the link xstats type nest attribute */
 	return numvls * nla_total_size(sizeof(struct bridge_vlan_xstats)) +
+	       nla_total_size(sizeof(struct br_mcast_stats)) +
 	       nla_total_size(0);
 }
 
-static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev,
-			      int *prividx)
+static size_t brport_get_linkxstats_size(const struct net_device *dev)
+{
+	return nla_total_size(sizeof(struct br_mcast_stats)) +
+	       nla_total_size(0);
+}
+
+static size_t br_get_linkxstats_size(const struct net_device *dev, int attr)
+{
+	size_t retsize = 0;
+
+	switch (attr) {
+	case IFLA_STATS_LINK_XSTATS:
+		retsize = bridge_get_linkxstats_size(dev);
+		break;
+	case IFLA_STATS_LINK_XSTATS_SLAVE:
+		retsize = brport_get_linkxstats_size(dev);
+		break;
+	}
+
+	return retsize;
+}
+
+static int bridge_fill_linkxstats(struct sk_buff *skb,
+				  const struct net_device *dev,
+				  int *prividx)
 {
 	struct net_bridge *br = netdev_priv(dev);
+	struct nlattr *nla __maybe_unused;
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_vlan *v;
 	struct nlattr *nest;
 	int vl_idx = 0;
 
-	vg = br_vlan_group(br);
-	if (!vg)
-		goto out;
 	nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BRIDGE);
 	if (!nest)
 		return -EMSGSIZE;
-	list_for_each_entry(v, &vg->vlan_list, vlist) {
-		struct bridge_vlan_xstats vxi;
-		struct br_vlan_stats stats;
 
-		if (vl_idx++ < *prividx)
-			continue;
-		memset(&vxi, 0, sizeof(vxi));
-		vxi.vid = v->vid;
-		br_vlan_get_stats(v, &stats);
-		vxi.rx_bytes = stats.rx_bytes;
-		vxi.rx_packets = stats.rx_packets;
-		vxi.tx_bytes = stats.tx_bytes;
-		vxi.tx_packets = stats.tx_packets;
-
-		if (nla_put(skb, BRIDGE_XSTATS_VLAN, sizeof(vxi), &vxi))
+	vg = br_vlan_group(br);
+	if (vg) {
+		list_for_each_entry(v, &vg->vlan_list, vlist) {
+			struct bridge_vlan_xstats vxi;
+			struct br_vlan_stats stats;
+
+			if (++vl_idx < *prividx)
+				continue;
+			memset(&vxi, 0, sizeof(vxi));
+			vxi.vid = v->vid;
+			br_vlan_get_stats(v, &stats);
+			vxi.rx_bytes = stats.rx_bytes;
+			vxi.rx_packets = stats.rx_packets;
+			vxi.tx_bytes = stats.tx_bytes;
+			vxi.tx_packets = stats.tx_packets;
+
+			if (nla_put(skb, BRIDGE_XSTATS_VLAN, sizeof(vxi), &vxi))
+				goto nla_put_failure;
+		}
+	}
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+	if (++vl_idx >= *prividx) {
+		nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST,
+					sizeof(struct br_mcast_stats),
+					BRIDGE_XSTATS_PAD);
+		if (!nla)
 			goto nla_put_failure;
+		br_multicast_get_stats(br, NULL, nla_data(nla));
 	}
+#endif
 	nla_nest_end(skb, nest);
 	*prividx = 0;
-out:
+
 	return 0;
 
 nla_put_failure:
@@ -1298,6 +1344,52 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static int brport_fill_linkxstats(struct sk_buff *skb,
+				  const struct net_device *dev,
+				  int *prividx)
+{
+	struct net_bridge_port *p = br_port_get_rtnl(dev);
+	struct nlattr *nla __maybe_unused;
+	struct nlattr *nest;
+
+	if (!p)
+		return 0;
+
+	nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BRIDGE);
+	if (!nest)
+		return -EMSGSIZE;
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+	nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST,
+				sizeof(struct br_mcast_stats),
+				BRIDGE_XSTATS_PAD);
+	if (!nla) {
+		nla_nest_end(skb, nest);
+		return -EMSGSIZE;
+	}
+	br_multicast_get_stats(p->br, p, nla_data(nla));
+#endif
+	nla_nest_end(skb, nest);
+
+	return 0;
+}
+
+static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev,
+			      int *prividx, int attr)
+{
+	int ret = -EINVAL;
+
+	switch (attr) {
+	case IFLA_STATS_LINK_XSTATS:
+		ret = bridge_fill_linkxstats(skb, dev, prividx);
+		break;
+	case IFLA_STATS_LINK_XSTATS_SLAVE:
+		ret = brport_fill_linkxstats(skb, dev, prividx);
+		break;
+	}
+
+	return ret;
+}
+
 static struct rtnl_af_ops br_af_ops __read_mostly = {
 	.family			= AF_BRIDGE,
 	.get_link_af_size	= br_get_link_af_size_filtered,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index c7fb5d7a7218..4dc851166ad1 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -75,6 +75,12 @@ struct bridge_mcast_querier {
 	struct br_ip addr;
 	struct net_bridge_port __rcu	*port;
 };
+
+/* IGMP/MLD statistics */
+struct bridge_mcast_stats {
+	struct br_mcast_stats mstats;
+	struct u64_stats_sync syncp;
+};
 #endif
 
 struct br_vlan_stats {
@@ -229,6 +235,7 @@ struct net_bridge_port
 	struct bridge_mcast_own_query	ip6_own_query;
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 	unsigned char			multicast_router;
+	struct bridge_mcast_stats	__percpu *mcast_stats;
 	struct timer_list		multicast_router_timer;
 	struct hlist_head		mglist;
 	struct hlist_node		rlist;
@@ -314,6 +321,8 @@ struct net_bridge
 	u8				multicast_disabled:1;
 	u8				multicast_querier:1;
 	u8				multicast_query_use_ifaddr:1;
+	u8				has_ipv6_addr:1;
+	u8				multicast_stats_enabled:1;
 
 	u32				hash_elasticity;
 	u32				hash_max;
@@ -336,6 +345,7 @@ struct net_bridge
 	struct bridge_mcast_other_query	ip4_other_query;
 	struct bridge_mcast_own_query	ip4_own_query;
 	struct bridge_mcast_querier	ip4_querier;
+	struct bridge_mcast_stats	__percpu *mcast_stats;
 #if IS_ENABLED(CONFIG_IPV6)
 	struct bridge_mcast_other_query	ip6_other_query;
 	struct bridge_mcast_own_query	ip6_own_query;
@@ -542,7 +552,7 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
 		     struct sk_buff *skb, u16 vid);
 struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 					struct sk_buff *skb, u16 vid);
-void br_multicast_add_port(struct net_bridge_port *port);
+int br_multicast_add_port(struct net_bridge_port *port);
 void br_multicast_del_port(struct net_bridge_port *port);
 void br_multicast_enable_port(struct net_bridge_port *port);
 void br_multicast_disable_port(struct net_bridge_port *port);
@@ -575,6 +585,12 @@ void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
 		   struct br_ip *group, int type, u8 flags);
 void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port,
 		   int type);
+void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p,
+			__be16 proto, u8 type, u8 dir);
+int br_multicast_init_stats(struct net_bridge *br);
+void br_multicast_get_stats(const struct net_bridge *br,
+			    const struct net_bridge_port *p,
+			    struct br_mcast_stats *dest);
 
 #define mlock_dereference(X, br) \
 	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
@@ -588,10 +604,22 @@ static inline bool br_multicast_is_router(struct net_bridge *br)
 
 static inline bool
 __br_multicast_querier_exists(struct net_bridge *br,
-			      struct bridge_mcast_other_query *querier)
+				struct bridge_mcast_other_query *querier,
+				const bool is_ipv6)
 {
+	bool own_querier_enabled;
+
+	if (br->multicast_querier) {
+		if (is_ipv6 && !br->has_ipv6_addr)
+			own_querier_enabled = false;
+		else
+			own_querier_enabled = true;
+	} else {
+		own_querier_enabled = false;
+	}
+
 	return time_is_before_jiffies(querier->delay_time) &&
-	       (br->multicast_querier || timer_pending(&querier->timer));
+	       (own_querier_enabled || timer_pending(&querier->timer));
 }
 
 static inline bool br_multicast_querier_exists(struct net_bridge *br,
@@ -599,15 +627,22 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
 {
 	switch (eth->h_proto) {
 	case (htons(ETH_P_IP)):
-		return __br_multicast_querier_exists(br, &br->ip4_other_query);
+		return __br_multicast_querier_exists(br,
+			&br->ip4_other_query, false);
 #if IS_ENABLED(CONFIG_IPV6)
 	case (htons(ETH_P_IPV6)):
-		return __br_multicast_querier_exists(br, &br->ip6_other_query);
+		return __br_multicast_querier_exists(br,
+			&br->ip6_other_query, true);
 #endif
 	default:
 		return false;
 	}
 }
+
+static inline int br_multicast_igmp_type(const struct sk_buff *skb)
+{
+	return BR_INPUT_SKB_CB(skb)->igmp;
+}
 #else
 static inline int br_multicast_rcv(struct net_bridge *br,
 				   struct net_bridge_port *port,
@@ -623,8 +658,9 @@ static inline struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 	return NULL;
 }
 
-static inline void br_multicast_add_port(struct net_bridge_port *port)
+static inline int br_multicast_add_port(struct net_bridge_port *port)
 {
+	return 0;
 }
 
 static inline void br_multicast_del_port(struct net_bridge_port *port)
@@ -680,6 +716,22 @@ static inline void br_mdb_init(void)
 static inline void br_mdb_uninit(void)
 {
 }
+
+static inline void br_multicast_count(struct net_bridge *br,
+				      const struct net_bridge_port *p,
+				      __be16 proto, u8 type, u8 dir)
+{
+}
+
+static inline int br_multicast_init_stats(struct net_bridge *br)
+{
+	return 0;
+}
+
+static inline int br_multicast_igmp_type(const struct sk_buff *skb)
+{
+	return 0;
+}
 #endif
 
 /* br_vlan.c */
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index beb47071e38d..e120307c6e36 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -618,6 +618,30 @@ static ssize_t multicast_startup_query_interval_store(
 	return store_bridge_parm(d, buf, len, set_startup_query_interval);
 }
 static DEVICE_ATTR_RW(multicast_startup_query_interval);
+
+static ssize_t multicast_stats_enabled_show(struct device *d,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+
+	return sprintf(buf, "%u\n", br->multicast_stats_enabled);
+}
+
+static int set_stats_enabled(struct net_bridge *br, unsigned long val)
+{
+	br->multicast_stats_enabled = !!val;
+	return 0;
+}
+
+static ssize_t multicast_stats_enabled_store(struct device *d,
+					     struct device_attribute *attr,
+					     const char *buf,
+					     size_t len)
+{
+	return store_bridge_parm(d, buf, len, set_stats_enabled);
+}
+static DEVICE_ATTR_RW(multicast_stats_enabled);
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 static ssize_t nf_call_iptables_show(
@@ -784,6 +808,7 @@ static struct attribute *bridge_attrs[] = {
 	&dev_attr_multicast_query_interval.attr,
 	&dev_attr_multicast_query_response_interval.attr,
 	&dev_attr_multicast_startup_query_interval.attr,
+	&dev_attr_multicast_stats_enabled.attr,
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	&dev_attr_nf_call_iptables.attr,
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 67a4a36febd1..3408ed51b611 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/if_ether.h>
-#include <linux/moduleparam.h>
 #include <linux/ip.h>
 #include <linux/sched.h>
 #include <linux/sockios.h>
diff --git a/net/can/Makefile b/net/can/Makefile
index cef49eb1f5c7..10936754e3f2 100644
--- a/net/can/Makefile
+++ b/net/can/Makefile
@@ -3,7 +3,8 @@
 #
 
 obj-$(CONFIG_CAN)	+= can.o
-can-y			:= af_can.o proc.o
+can-y			:= af_can.o
+can-$(CONFIG_PROC_FS)	+= proc.o
 
 obj-$(CONFIG_CAN_RAW)	+= can-raw.o
 can-raw-y		:= raw.o
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 166d436196c1..1108079d934f 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -911,14 +911,14 @@ static __init int can_init(void)
 	if (!rcv_cache)
 		return -ENOMEM;
 
-	if (stats_timer) {
+	if (IS_ENABLED(CONFIG_PROC_FS)) {
+		if (stats_timer) {
 		/* the statistics are updated every second (timer triggered) */
-		setup_timer(&can_stattimer, can_stat_update, 0);
-		mod_timer(&can_stattimer, round_jiffies(jiffies + HZ));
-	} else
-		can_stattimer.function = NULL;
-
-	can_init_proc();
+			setup_timer(&can_stattimer, can_stat_update, 0);
+			mod_timer(&can_stattimer, round_jiffies(jiffies + HZ));
+		}
+		can_init_proc();
+	}
 
 	/* protocol register */
 	sock_register(&can_family_ops);
@@ -933,10 +933,12 @@ static __exit void can_exit(void)
 {
 	struct net_device *dev;
 
-	if (stats_timer)
-		del_timer_sync(&can_stattimer);
+	if (IS_ENABLED(CONFIG_PROC_FS)) {
+		if (stats_timer)
+			del_timer_sync(&can_stattimer);
 
-	can_remove_proc();
+		can_remove_proc();
+	}
 
 	/* protocol unregister */
 	dev_remove_pack(&canfd_packet);
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 6863310d6973..8e999ffdf28b 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1,7 +1,7 @@
 /*
  * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content
  *
- * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
+ * Copyright (c) 2002-2016 Volkswagen Group Electronic Research
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -67,27 +67,31 @@
  */
 #define MAX_NFRAMES 256
 
-/* use of last_frames[index].can_dlc */
+/* use of last_frames[index].flags */
 #define RX_RECV    0x40 /* received data for this element */
 #define RX_THR     0x80 /* element not been sent due to throttle feature */
-#define BCM_CAN_DLC_MASK 0x0F /* clean private flags in can_dlc by masking */
+#define BCM_CAN_FLAGS_MASK 0x3F /* to clean private flags after usage */
 
 /* get best masking value for can_rx_register() for a given single can_id */
 #define REGMASK(id) ((id & CAN_EFF_FLAG) ? \
 		     (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
 		     (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
 
-#define CAN_BCM_VERSION CAN_VERSION
+#define CAN_BCM_VERSION "20160617"
 
 MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <[email protected]>");
 MODULE_ALIAS("can-proto-2");
 
-/* easy access to can_frame payload */
-static inline u64 GET_U64(const struct can_frame *cp)
+/*
+ * easy access to the first 64 bit of can(fd)_frame payload. cp->data is
+ * 64 bit aligned so the offset has to be multiples of 8 which is ensured
+ * by the only callers in bcm_rx_cmp_to_index() bcm_rx_handler().
+ */
+static inline u64 get_u64(const struct canfd_frame *cp, int offset)
 {
-	return *(u64 *)cp->data;
+	return *(u64 *)(cp->data + offset);
 }
 
 struct bcm_op {
@@ -101,13 +105,14 @@ struct bcm_op {
 	struct tasklet_struct tsklet, thrtsklet;
 	ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg;
 	int rx_ifindex;
+	int cfsiz;
 	u32 count;
 	u32 nframes;
 	u32 currframe;
-	struct can_frame *frames;
-	struct can_frame *last_frames;
-	struct can_frame sframe;
-	struct can_frame last_sframe;
+	struct canfd_frame *frames;
+	struct canfd_frame *last_frames;
+	struct canfd_frame sframe;
+	struct canfd_frame last_sframe;
 	struct sock *sk;
 	struct net_device *rx_reg_dev;
 };
@@ -136,7 +141,7 @@ static inline ktime_t bcm_timeval_to_ktime(struct bcm_timeval tv)
 	return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC);
 }
 
-#define CFSIZ sizeof(struct can_frame)
+#define CFSIZ(flags) ((flags & CAN_FD_FRAME) ? CANFD_MTU : CAN_MTU)
 #define OPSIZ sizeof(struct bcm_op)
 #define MHSIZ sizeof(struct bcm_msg_head)
 
@@ -183,43 +188,50 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 		if (!op->frames_abs)
 			continue;
 
-		seq_printf(m, "rx_op: %03X %-5s ",
-				op->can_id, bcm_proc_getifname(ifname, op->ifindex));
-		seq_printf(m, "[%u]%c ", op->nframes,
-				(op->flags & RX_CHECK_DLC)?'d':' ');
+		seq_printf(m, "rx_op: %03X %-5s ", op->can_id,
+			   bcm_proc_getifname(ifname, op->ifindex));
+
+		if (op->flags & CAN_FD_FRAME)
+			seq_printf(m, "(%u)", op->nframes);
+		else
+			seq_printf(m, "[%u]", op->nframes);
+
+		seq_printf(m, "%c ", (op->flags & RX_CHECK_DLC) ? 'd' : ' ');
+
 		if (op->kt_ival1.tv64)
 			seq_printf(m, "timeo=%lld ",
-					(long long)
-					ktime_to_us(op->kt_ival1));
+				   (long long)ktime_to_us(op->kt_ival1));
 
 		if (op->kt_ival2.tv64)
 			seq_printf(m, "thr=%lld ",
-					(long long)
-					ktime_to_us(op->kt_ival2));
+				   (long long)ktime_to_us(op->kt_ival2));
 
 		seq_printf(m, "# recv %ld (%ld) => reduction: ",
-				op->frames_filtered, op->frames_abs);
+			   op->frames_filtered, op->frames_abs);
 
 		reduction = 100 - (op->frames_filtered * 100) / op->frames_abs;
 
 		seq_printf(m, "%s%ld%%\n",
-				(reduction == 100)?"near ":"", reduction);
+			   (reduction == 100) ? "near " : "", reduction);
 	}
 
 	list_for_each_entry(op, &bo->tx_ops, list) {
 
-		seq_printf(m, "tx_op: %03X %s [%u] ",
-				op->can_id,
-				bcm_proc_getifname(ifname, op->ifindex),
-				op->nframes);
+		seq_printf(m, "tx_op: %03X %s ", op->can_id,
+			   bcm_proc_getifname(ifname, op->ifindex));
+
+		if (op->flags & CAN_FD_FRAME)
+			seq_printf(m, "(%u) ", op->nframes);
+		else
+			seq_printf(m, "[%u] ", op->nframes);
 
 		if (op->kt_ival1.tv64)
 			seq_printf(m, "t1=%lld ",
-					(long long) ktime_to_us(op->kt_ival1));
+				   (long long)ktime_to_us(op->kt_ival1));
 
 		if (op->kt_ival2.tv64)
 			seq_printf(m, "t2=%lld ",
-					(long long) ktime_to_us(op->kt_ival2));
+				   (long long)ktime_to_us(op->kt_ival2));
 
 		seq_printf(m, "# sent %ld\n", op->frames_abs);
 	}
@@ -248,7 +260,7 @@ static void bcm_can_tx(struct bcm_op *op)
 {
 	struct sk_buff *skb;
 	struct net_device *dev;
-	struct can_frame *cf = &op->frames[op->currframe];
+	struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe;
 
 	/* no target device? => exit */
 	if (!op->ifindex)
@@ -260,7 +272,7 @@ static void bcm_can_tx(struct bcm_op *op)
 		return;
 	}
 
-	skb = alloc_skb(CFSIZ + sizeof(struct can_skb_priv), gfp_any());
+	skb = alloc_skb(op->cfsiz + sizeof(struct can_skb_priv), gfp_any());
 	if (!skb)
 		goto out;
 
@@ -268,7 +280,7 @@ static void bcm_can_tx(struct bcm_op *op)
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 	can_skb_prv(skb)->skbcnt = 0;
 
-	memcpy(skb_put(skb, CFSIZ), cf, CFSIZ);
+	memcpy(skb_put(skb, op->cfsiz), cf, op->cfsiz);
 
 	/* send with loopback */
 	skb->dev = dev;
@@ -282,7 +294,7 @@ static void bcm_can_tx(struct bcm_op *op)
 	/* reached last frame? */
 	if (op->currframe >= op->nframes)
 		op->currframe = 0;
- out:
+out:
 	dev_put(dev);
 }
 
@@ -291,13 +303,13 @@ static void bcm_can_tx(struct bcm_op *op)
  *                    (consisting of bcm_msg_head + x CAN frames)
  */
 static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head,
-			     struct can_frame *frames, int has_timestamp)
+			     struct canfd_frame *frames, int has_timestamp)
 {
 	struct sk_buff *skb;
-	struct can_frame *firstframe;
+	struct canfd_frame *firstframe;
 	struct sockaddr_can *addr;
 	struct sock *sk = op->sk;
-	unsigned int datalen = head->nframes * CFSIZ;
+	unsigned int datalen = head->nframes * op->cfsiz;
 	int err;
 
 	skb = alloc_skb(sizeof(*head) + datalen, gfp_any());
@@ -307,19 +319,19 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head,
 	memcpy(skb_put(skb, sizeof(*head)), head, sizeof(*head));
 
 	if (head->nframes) {
-		/* can_frames starting here */
-		firstframe = (struct can_frame *)skb_tail_pointer(skb);
+		/* CAN frames starting here */
+		firstframe = (struct canfd_frame *)skb_tail_pointer(skb);
 
 		memcpy(skb_put(skb, datalen), frames, datalen);
 
 		/*
-		 * the BCM uses the can_dlc-element of the can_frame
+		 * the BCM uses the flags-element of the canfd_frame
 		 * structure for internal purposes. This is only
 		 * relevant for updates that are generated by the
 		 * BCM, where nframes is 1
 		 */
 		if (head->nframes == 1)
-			firstframe->can_dlc &= BCM_CAN_DLC_MASK;
+			firstframe->flags &= BCM_CAN_FLAGS_MASK;
 	}
 
 	if (has_timestamp) {
@@ -406,7 +418,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
 /*
  * bcm_rx_changed - create a RX_CHANGED notification due to changed content
  */
-static void bcm_rx_changed(struct bcm_op *op, struct can_frame *data)
+static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data)
 {
 	struct bcm_msg_head head;
 
@@ -418,7 +430,7 @@ static void bcm_rx_changed(struct bcm_op *op, struct can_frame *data)
 		op->frames_filtered = op->frames_abs = 0;
 
 	/* this element is not throttled anymore */
-	data->can_dlc &= (BCM_CAN_DLC_MASK|RX_RECV);
+	data->flags &= (BCM_CAN_FLAGS_MASK|RX_RECV);
 
 	head.opcode  = RX_CHANGED;
 	head.flags   = op->flags;
@@ -437,13 +449,13 @@ static void bcm_rx_changed(struct bcm_op *op, struct can_frame *data)
  *                          2. send a notification to the user (if possible)
  */
 static void bcm_rx_update_and_send(struct bcm_op *op,
-				   struct can_frame *lastdata,
-				   const struct can_frame *rxdata)
+				   struct canfd_frame *lastdata,
+				   const struct canfd_frame *rxdata)
 {
-	memcpy(lastdata, rxdata, CFSIZ);
+	memcpy(lastdata, rxdata, op->cfsiz);
 
 	/* mark as used and throttled by default */
-	lastdata->can_dlc |= (RX_RECV|RX_THR);
+	lastdata->flags |= (RX_RECV|RX_THR);
 
 	/* throttling mode inactive ? */
 	if (!op->kt_ival2.tv64) {
@@ -481,33 +493,36 @@ rx_changed_settime:
  *                       received data stored in op->last_frames[]
  */
 static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index,
-				const struct can_frame *rxdata)
+				const struct canfd_frame *rxdata)
 {
+	struct canfd_frame *cf = op->frames + op->cfsiz * index;
+	struct canfd_frame *lcf = op->last_frames + op->cfsiz * index;
+	int i;
+
 	/*
-	 * no one uses the MSBs of can_dlc for comparison,
+	 * no one uses the MSBs of flags for comparison,
 	 * so we use it here to detect the first time of reception
 	 */
 
-	if (!(op->last_frames[index].can_dlc & RX_RECV)) {
+	if (!(lcf->flags & RX_RECV)) {
 		/* received data for the first time => send update to user */
-		bcm_rx_update_and_send(op, &op->last_frames[index], rxdata);
+		bcm_rx_update_and_send(op, lcf, rxdata);
 		return;
 	}
 
-	/* do a real check in can_frame data section */
-
-	if ((GET_U64(&op->frames[index]) & GET_U64(rxdata)) !=
-	    (GET_U64(&op->frames[index]) & GET_U64(&op->last_frames[index]))) {
-		bcm_rx_update_and_send(op, &op->last_frames[index], rxdata);
-		return;
+	/* do a real check in CAN frame data section */
+	for (i = 0; i < rxdata->len; i += 8) {
+		if ((get_u64(cf, i) & get_u64(rxdata, i)) !=
+		    (get_u64(cf, i) & get_u64(lcf, i))) {
+			bcm_rx_update_and_send(op, lcf, rxdata);
+			return;
+		}
 	}
 
 	if (op->flags & RX_CHECK_DLC) {
-		/* do a real check in can_frame dlc */
-		if (rxdata->can_dlc != (op->last_frames[index].can_dlc &
-					BCM_CAN_DLC_MASK)) {
-			bcm_rx_update_and_send(op, &op->last_frames[index],
-					       rxdata);
+		/* do a real check in CAN frame length */
+		if (rxdata->len != lcf->len) {
+			bcm_rx_update_and_send(op, lcf, rxdata);
 			return;
 		}
 	}
@@ -556,8 +571,8 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
 
 	/* if user wants to be informed, when cyclic CAN-Messages come back */
 	if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) {
-		/* clear received can_frames to indicate 'nothing received' */
-		memset(op->last_frames, 0, op->nframes * CFSIZ);
+		/* clear received CAN frames to indicate 'nothing received' */
+		memset(op->last_frames, 0, op->nframes * op->cfsiz);
 	}
 
 	return HRTIMER_NORESTART;
@@ -569,9 +584,11 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
 static inline int bcm_rx_do_flush(struct bcm_op *op, int update,
 				  unsigned int index)
 {
-	if ((op->last_frames) && (op->last_frames[index].can_dlc & RX_THR)) {
+	struct canfd_frame *lcf = op->last_frames + op->cfsiz * index;
+
+	if ((op->last_frames) && (lcf->flags & RX_THR)) {
 		if (update)
-			bcm_rx_changed(op, &op->last_frames[index]);
+			bcm_rx_changed(op, lcf);
 		return 1;
 	}
 	return 0;
@@ -636,15 +653,19 @@ static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer)
 static void bcm_rx_handler(struct sk_buff *skb, void *data)
 {
 	struct bcm_op *op = (struct bcm_op *)data;
-	const struct can_frame *rxframe = (struct can_frame *)skb->data;
+	const struct canfd_frame *rxframe = (struct canfd_frame *)skb->data;
 	unsigned int i;
 
-	/* disable timeout */
-	hrtimer_cancel(&op->timer);
-
 	if (op->can_id != rxframe->can_id)
 		return;
 
+	/* make sure to handle the correct frame type (CAN / CAN FD) */
+	if (skb->len != op->cfsiz)
+		return;
+
+	/* disable timeout */
+	hrtimer_cancel(&op->timer);
+
 	/* save rx timestamp */
 	op->rx_stamp = skb->tstamp;
 	/* save originator for recvfrom() */
@@ -675,13 +696,14 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 		 * multiplex compare
 		 *
 		 * find the first multiplex mask that fits.
-		 * Remark: The MUX-mask is stored in index 0
+		 * Remark: The MUX-mask is stored in index 0 - but only the
+		 * first 64 bits of the frame data[] are relevant (CAN FD)
 		 */
 
 		for (i = 1; i < op->nframes; i++) {
-			if ((GET_U64(&op->frames[0]) & GET_U64(rxframe)) ==
-			    (GET_U64(&op->frames[0]) &
-			     GET_U64(&op->frames[i]))) {
+			if ((get_u64(op->frames, 0) & get_u64(rxframe, 0)) ==
+			    (get_u64(op->frames, 0) &
+			     get_u64(op->frames + op->cfsiz * i, 0))) {
 				bcm_rx_cmp_to_index(op, i, rxframe);
 				break;
 			}
@@ -695,13 +717,14 @@ rx_starttimer:
 /*
  * helpers for bcm_op handling: find & delete bcm [rx|tx] op elements
  */
-static struct bcm_op *bcm_find_op(struct list_head *ops, canid_t can_id,
-				  int ifindex)
+static struct bcm_op *bcm_find_op(struct list_head *ops,
+				  struct bcm_msg_head *mh, int ifindex)
 {
 	struct bcm_op *op;
 
 	list_for_each_entry(op, ops, list) {
-		if ((op->can_id == can_id) && (op->ifindex == ifindex))
+		if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
+		    (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME))
 			return op;
 	}
 
@@ -744,12 +767,14 @@ static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op)
 /*
  * bcm_delete_rx_op - find and remove a rx op (returns number of removed ops)
  */
-static int bcm_delete_rx_op(struct list_head *ops, canid_t can_id, int ifindex)
+static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
+			    int ifindex)
 {
 	struct bcm_op *op, *n;
 
 	list_for_each_entry_safe(op, n, ops, list) {
-		if ((op->can_id == can_id) && (op->ifindex == ifindex)) {
+		if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
+		    (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
 
 			/*
 			 * Don't care if we're bound or not (due to netdev
@@ -789,12 +814,14 @@ static int bcm_delete_rx_op(struct list_head *ops, canid_t can_id, int ifindex)
 /*
  * bcm_delete_tx_op - find and remove a tx op (returns number of removed ops)
  */
-static int bcm_delete_tx_op(struct list_head *ops, canid_t can_id, int ifindex)
+static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh,
+			    int ifindex)
 {
 	struct bcm_op *op, *n;
 
 	list_for_each_entry_safe(op, n, ops, list) {
-		if ((op->can_id == can_id) && (op->ifindex == ifindex)) {
+		if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
+		    (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
 			list_del(&op->list);
 			bcm_remove_op(op);
 			return 1; /* done */
@@ -810,7 +837,7 @@ static int bcm_delete_tx_op(struct list_head *ops, canid_t can_id, int ifindex)
 static int bcm_read_op(struct list_head *ops, struct bcm_msg_head *msg_head,
 		       int ifindex)
 {
-	struct bcm_op *op = bcm_find_op(ops, msg_head->can_id, ifindex);
+	struct bcm_op *op = bcm_find_op(ops, msg_head, ifindex);
 
 	if (!op)
 		return -EINVAL;
@@ -835,6 +862,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 {
 	struct bcm_sock *bo = bcm_sk(sk);
 	struct bcm_op *op;
+	struct canfd_frame *cf;
 	unsigned int i;
 	int err;
 
@@ -842,39 +870,46 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	if (!ifindex)
 		return -ENODEV;
 
-	/* check nframes boundaries - we need at least one can_frame */
+	/* check nframes boundaries - we need at least one CAN frame */
 	if (msg_head->nframes < 1 || msg_head->nframes > MAX_NFRAMES)
 		return -EINVAL;
 
 	/* check the given can_id */
-	op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex);
-
+	op = bcm_find_op(&bo->tx_ops, msg_head, ifindex);
 	if (op) {
 		/* update existing BCM operation */
 
 		/*
-		 * Do we need more space for the can_frames than currently
+		 * Do we need more space for the CAN frames than currently
 		 * allocated? -> This is a _really_ unusual use-case and
 		 * therefore (complexity / locking) it is not supported.
 		 */
 		if (msg_head->nframes > op->nframes)
 			return -E2BIG;
 
-		/* update can_frames content */
+		/* update CAN frames content */
 		for (i = 0; i < msg_head->nframes; i++) {
-			err = memcpy_from_msg((u8 *)&op->frames[i], msg, CFSIZ);
 
-			if (op->frames[i].can_dlc > 8)
-				err = -EINVAL;
+			cf = op->frames + op->cfsiz * i;
+			err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz);
+
+			if (op->flags & CAN_FD_FRAME) {
+				if (cf->len > 64)
+					err = -EINVAL;
+			} else {
+				if (cf->len > 8)
+					err = -EINVAL;
+			}
 
 			if (err < 0)
 				return err;
 
 			if (msg_head->flags & TX_CP_CAN_ID) {
 				/* copy can_id into frame */
-				op->frames[i].can_id = msg_head->can_id;
+				cf->can_id = msg_head->can_id;
 			}
 		}
+		op->flags = msg_head->flags;
 
 	} else {
 		/* insert new BCM operation for the given can_id */
@@ -883,11 +918,13 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		if (!op)
 			return -ENOMEM;
 
-		op->can_id    = msg_head->can_id;
+		op->can_id = msg_head->can_id;
+		op->cfsiz = CFSIZ(msg_head->flags);
+		op->flags = msg_head->flags;
 
-		/* create array for can_frames and copy the data */
+		/* create array for CAN frames and copy the data */
 		if (msg_head->nframes > 1) {
-			op->frames = kmalloc(msg_head->nframes * CFSIZ,
+			op->frames = kmalloc(msg_head->nframes * op->cfsiz,
 					     GFP_KERNEL);
 			if (!op->frames) {
 				kfree(op);
@@ -897,10 +934,17 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			op->frames = &op->sframe;
 
 		for (i = 0; i < msg_head->nframes; i++) {
-			err = memcpy_from_msg((u8 *)&op->frames[i], msg, CFSIZ);
 
-			if (op->frames[i].can_dlc > 8)
-				err = -EINVAL;
+			cf = op->frames + op->cfsiz * i;
+			err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz);
+
+			if (op->flags & CAN_FD_FRAME) {
+				if (cf->len > 64)
+					err = -EINVAL;
+			} else {
+				if (cf->len > 8)
+					err = -EINVAL;
+			}
 
 			if (err < 0) {
 				if (op->frames != &op->sframe)
@@ -911,7 +955,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 			if (msg_head->flags & TX_CP_CAN_ID) {
 				/* copy can_id into frame */
-				op->frames[i].can_id = msg_head->can_id;
+				cf->can_id = msg_head->can_id;
 			}
 		}
 
@@ -946,8 +990,6 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 	/* check flags */
 
-	op->flags = msg_head->flags;
-
 	if (op->flags & TX_RESET_MULTI_IDX) {
 		/* start multiple frame transmission with index 0 */
 		op->currframe = 0;
@@ -968,7 +1010,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 	if (op->flags & STARTTIMER) {
 		hrtimer_cancel(&op->timer);
-		/* spec: send can_frame when starting timer */
+		/* spec: send CAN frame when starting timer */
 		op->flags |= TX_ANNOUNCE;
 	}
 
@@ -981,7 +1023,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	if (op->flags & STARTTIMER)
 		bcm_tx_start_timer(op);
 
-	return msg_head->nframes * CFSIZ + MHSIZ;
+	return msg_head->nframes * op->cfsiz + MHSIZ;
 }
 
 /*
@@ -1012,12 +1054,12 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		return -EINVAL;
 
 	/* check the given can_id */
-	op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex);
+	op = bcm_find_op(&bo->rx_ops, msg_head, ifindex);
 	if (op) {
 		/* update existing BCM operation */
 
 		/*
-		 * Do we need more space for the can_frames than currently
+		 * Do we need more space for the CAN frames than currently
 		 * allocated? -> This is a _really_ unusual use-case and
 		 * therefore (complexity / locking) it is not supported.
 		 */
@@ -1025,17 +1067,18 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			return -E2BIG;
 
 		if (msg_head->nframes) {
-			/* update can_frames content */
+			/* update CAN frames content */
 			err = memcpy_from_msg((u8 *)op->frames, msg,
-					      msg_head->nframes * CFSIZ);
+					      msg_head->nframes * op->cfsiz);
 			if (err < 0)
 				return err;
 
 			/* clear last_frames to indicate 'nothing received' */
-			memset(op->last_frames, 0, msg_head->nframes * CFSIZ);
+			memset(op->last_frames, 0, msg_head->nframes * op->cfsiz);
 		}
 
 		op->nframes = msg_head->nframes;
+		op->flags = msg_head->flags;
 
 		/* Only an update -> do not call can_rx_register() */
 		do_rx_register = 0;
@@ -1046,20 +1089,22 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		if (!op)
 			return -ENOMEM;
 
-		op->can_id    = msg_head->can_id;
-		op->nframes   = msg_head->nframes;
+		op->can_id = msg_head->can_id;
+		op->nframes = msg_head->nframes;
+		op->cfsiz = CFSIZ(msg_head->flags);
+		op->flags = msg_head->flags;
 
 		if (msg_head->nframes > 1) {
-			/* create array for can_frames and copy the data */
-			op->frames = kmalloc(msg_head->nframes * CFSIZ,
+			/* create array for CAN frames and copy the data */
+			op->frames = kmalloc(msg_head->nframes * op->cfsiz,
 					     GFP_KERNEL);
 			if (!op->frames) {
 				kfree(op);
 				return -ENOMEM;
 			}
 
-			/* create and init array for received can_frames */
-			op->last_frames = kzalloc(msg_head->nframes * CFSIZ,
+			/* create and init array for received CAN frames */
+			op->last_frames = kzalloc(msg_head->nframes * op->cfsiz,
 						  GFP_KERNEL);
 			if (!op->last_frames) {
 				kfree(op->frames);
@@ -1074,7 +1119,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 		if (msg_head->nframes) {
 			err = memcpy_from_msg((u8 *)op->frames, msg,
-					      msg_head->nframes * CFSIZ);
+					      msg_head->nframes * op->cfsiz);
 			if (err < 0) {
 				if (op->frames != &op->sframe)
 					kfree(op->frames);
@@ -1116,7 +1161,6 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	} /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */
 
 	/* check flags */
-	op->flags = msg_head->flags;
 
 	if (op->flags & RX_RTR_FRAME) {
 
@@ -1188,13 +1232,14 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		}
 	}
 
-	return msg_head->nframes * CFSIZ + MHSIZ;
+	return msg_head->nframes * op->cfsiz + MHSIZ;
 }
 
 /*
  * bcm_tx_send - send a single CAN frame to the CAN interface (for bcm_sendmsg)
  */
-static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
+static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk,
+		       int cfsiz)
 {
 	struct sk_buff *skb;
 	struct net_device *dev;
@@ -1204,13 +1249,13 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
 	if (!ifindex)
 		return -ENODEV;
 
-	skb = alloc_skb(CFSIZ + sizeof(struct can_skb_priv), GFP_KERNEL);
+	skb = alloc_skb(cfsiz + sizeof(struct can_skb_priv), GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
 	can_skb_reserve(skb);
 
-	err = memcpy_from_msg(skb_put(skb, CFSIZ), msg, CFSIZ);
+	err = memcpy_from_msg(skb_put(skb, cfsiz), msg, cfsiz);
 	if (err < 0) {
 		kfree_skb(skb);
 		return err;
@@ -1232,7 +1277,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
 	if (err)
 		return err;
 
-	return CFSIZ + MHSIZ;
+	return cfsiz + MHSIZ;
 }
 
 /*
@@ -1244,13 +1289,23 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	struct bcm_sock *bo = bcm_sk(sk);
 	int ifindex = bo->ifindex; /* default ifindex for this bcm_op */
 	struct bcm_msg_head msg_head;
+	int cfsiz;
 	int ret; /* read bytes or error codes as return value */
 
 	if (!bo->bound)
 		return -ENOTCONN;
 
 	/* check for valid message length from userspace */
-	if (size < MHSIZ || (size - MHSIZ) % CFSIZ)
+	if (size < MHSIZ)
+		return -EINVAL;
+
+	/* read message head information */
+	ret = memcpy_from_msg((u8 *)&msg_head, msg, MHSIZ);
+	if (ret < 0)
+		return ret;
+
+	cfsiz = CFSIZ(msg_head.flags);
+	if ((size - MHSIZ) % cfsiz)
 		return -EINVAL;
 
 	/* check for alternative ifindex for this bcm_op */
@@ -1284,12 +1339,6 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		}
 	}
 
-	/* read message head information */
-
-	ret = memcpy_from_msg((u8 *)&msg_head, msg, MHSIZ);
-	if (ret < 0)
-		return ret;
-
 	lock_sock(sk);
 
 	switch (msg_head.opcode) {
@@ -1303,14 +1352,14 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		break;
 
 	case TX_DELETE:
-		if (bcm_delete_tx_op(&bo->tx_ops, msg_head.can_id, ifindex))
+		if (bcm_delete_tx_op(&bo->tx_ops, &msg_head, ifindex))
 			ret = MHSIZ;
 		else
 			ret = -EINVAL;
 		break;
 
 	case RX_DELETE:
-		if (bcm_delete_rx_op(&bo->rx_ops, msg_head.can_id, ifindex))
+		if (bcm_delete_rx_op(&bo->rx_ops, &msg_head, ifindex))
 			ret = MHSIZ;
 		else
 			ret = -EINVAL;
@@ -1329,11 +1378,11 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		break;
 
 	case TX_SEND:
-		/* we need exactly one can_frame behind the msg head */
-		if ((msg_head.nframes != 1) || (size != CFSIZ + MHSIZ))
+		/* we need exactly one CAN frame behind the msg head */
+		if ((msg_head.nframes != 1) || (size != cfsiz + MHSIZ))
 			ret = -EINVAL;
 		else
-			ret = bcm_tx_send(msg, ifindex, sk);
+			ret = bcm_tx_send(msg, ifindex, sk, cfsiz);
 		break;
 
 	default:
diff --git a/net/can/proc.c b/net/can/proc.c
index 1a19b985a868..85ef7bb0f176 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -517,8 +517,7 @@ void can_init_proc(void)
 	can_dir = proc_mkdir("can", init_net.proc_net);
 
 	if (!can_dir) {
-		printk(KERN_INFO "can: failed to create /proc/net/can . "
-		       "CONFIG_PROC_FS missing?\n");
+		pr_info("can: failed to create /proc/net/can.\n");
 		return;
 	}
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 0160d7d09a1e..89469592076c 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1276,9 +1276,9 @@ static bool target_should_be_paused(struct ceph_osd_client *osdc,
 				    const struct ceph_osd_request_target *t,
 				    struct ceph_pg_pool_info *pi)
 {
-	bool pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
-	bool pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
-		       ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
+	bool pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
+	bool pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
+		       ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
 		       __pool_full(pi);
 
 	WARN_ON(pi->id != t->base_oloc.pool);
@@ -1303,8 +1303,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
 	bool force_resend = false;
 	bool need_check_tiering = false;
 	bool need_resend = false;
-	bool sort_bitwise = ceph_osdmap_flag(osdc->osdmap,
-					     CEPH_OSDMAP_SORTBITWISE);
+	bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE);
 	enum calc_target_result ct_res;
 	int ret;
 
@@ -1540,9 +1539,9 @@ static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg)
 	 */
 	msg->hdr.data_off = cpu_to_le16(req->r_data_offset);
 
-	dout("%s req %p oid %*pE oid_len %d front %zu data %u\n", __func__,
-	     req, req->r_t.target_oid.name_len, req->r_t.target_oid.name,
-	     req->r_t.target_oid.name_len, msg->front.iov_len, data_len);
+	dout("%s req %p oid %s oid_len %d front %zu data %u\n", __func__,
+	     req, req->r_t.target_oid.name, req->r_t.target_oid.name_len,
+	     msg->front.iov_len, data_len);
 }
 
 /*
@@ -1590,9 +1589,9 @@ static void maybe_request_map(struct ceph_osd_client *osdc)
 	verify_osdc_locked(osdc);
 	WARN_ON(!osdc->osdmap->epoch);
 
-	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
-	    ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD) ||
-	    ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR)) {
+	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
+	    ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD) ||
+	    ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
 		dout("%s osdc %p continuous\n", __func__, osdc);
 		continuous = true;
 	} else {
@@ -1629,19 +1628,19 @@ again:
 	}
 
 	if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
-	    ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR)) {
+	    ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
 		dout("req %p pausewr\n", req);
 		req->r_t.paused = true;
 		maybe_request_map(osdc);
 	} else if ((req->r_flags & CEPH_OSD_FLAG_READ) &&
-		   ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD)) {
+		   ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
 		dout("req %p pauserd\n", req);
 		req->r_t.paused = true;
 		maybe_request_map(osdc);
 	} else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
 		   !(req->r_flags & (CEPH_OSD_FLAG_FULL_TRY |
 				     CEPH_OSD_FLAG_FULL_FORCE)) &&
-		   (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
+		   (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
 		    pool_full(osdc, req->r_t.base_oloc.pool))) {
 		dout("req %p full/pool_full\n", req);
 		pr_warn_ratelimited("FULL or reached pool quota\n");
@@ -2280,7 +2279,7 @@ static void send_linger_ping(struct ceph_osd_linger_request *lreq)
 	struct ceph_osd_request *req = lreq->ping_req;
 	struct ceph_osd_req_op *op = &req->r_ops[0];
 
-	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD)) {
+	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
 		dout("%s PAUSERD\n", __func__);
 		return;
 	}
@@ -2893,6 +2892,9 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
 			dout("req %p tid %llu cb\n", req, req->r_tid);
 			__complete_request(req);
 		}
+		if (m.flags & CEPH_OSD_FLAG_ONDISK)
+			complete_all(&req->r_safe_completion);
+		ceph_osdc_put_request(req);
 	} else {
 		if (req->r_unsafe_callback) {
 			dout("req %p tid %llu unsafe-cb\n", req, req->r_tid);
@@ -2901,10 +2903,7 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
 			WARN_ON(1);
 		}
 	}
-	if (m.flags & CEPH_OSD_FLAG_ONDISK)
-		complete_all(&req->r_safe_completion);
 
-	ceph_osdc_put_request(req);
 	return;
 
 fail_request:
@@ -3050,7 +3049,7 @@ static int handle_one_map(struct ceph_osd_client *osdc,
 	bool skipped_map = false;
 	bool was_full;
 
-	was_full = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
+	was_full = ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL);
 	set_pool_was_full(osdc);
 
 	if (incremental)
@@ -3088,7 +3087,7 @@ static int handle_one_map(struct ceph_osd_client *osdc,
 		osdc->osdmap = newmap;
 	}
 
-	was_full &= !ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
+	was_full &= !ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL);
 	scan_requests(&osdc->homeless_osd, skipped_map, was_full, true,
 		      need_resend, need_resend_linger);
 
@@ -3174,9 +3173,9 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 	if (ceph_check_fsid(osdc->client, &fsid) < 0)
 		goto bad;
 
-	was_pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
-	was_pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
-		      ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
+	was_pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
+	was_pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
+		      ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
 		      have_pool_full(osdc);
 
 	/* incremental maps */
@@ -3238,9 +3237,9 @@ done:
 	 * we find out when we are no longer full and stop returning
 	 * ENOSPC.
 	 */
-	pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
-	pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
-		  ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
+	pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
+	pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
+		  ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
 		  have_pool_full(osdc);
 	if (was_pauserd || was_pausewr || pauserd || pausewr)
 		maybe_request_map(osdc);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index cde52e94732f..03062bb763b3 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1778,8 +1778,8 @@ int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
 	raw_pgid->seed = ceph_str_hash(pi->object_hash, oid->name,
 				       oid->name_len);
 
-	dout("%s %*pE -> raw_pgid %llu.%x\n", __func__, oid->name_len,
-	     oid->name, raw_pgid->pool, raw_pgid->seed);
+	dout("%s %s -> raw_pgid %llu.%x\n", __func__, oid->name,
+	     raw_pgid->pool, raw_pgid->seed);
 	return 0;
 }
 EXPORT_SYMBOL(ceph_object_locator_to_pg);
diff --git a/net/compat.c b/net/compat.c
index 5cfd26a0006f..1cd2ec046164 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -309,8 +309,8 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
 	__scm_destroy(scm);
 }
 
-static int do_set_attach_filter(struct socket *sock, int level, int optname,
-				char __user *optval, unsigned int optlen)
+/* allocate a 64-bit sock_fprog on the user stack for duration of syscall. */
+struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval)
 {
 	struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval;
 	struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog));
@@ -323,6 +323,19 @@ static int do_set_attach_filter(struct socket *sock, int level, int optname,
 	    __get_user(ptr, &fprog32->filter) ||
 	    __put_user(len, &kfprog->len) ||
 	    __put_user(compat_ptr(ptr), &kfprog->filter))
+		return NULL;
+
+	return kfprog;
+}
+EXPORT_SYMBOL_GPL(get_compat_bpf_fprog);
+
+static int do_set_attach_filter(struct socket *sock, int level, int optname,
+				char __user *optval, unsigned int optlen)
+{
+	struct sock_fprog __user *kfprog;
+
+	kfprog = get_compat_bpf_fprog(optval);
+	if (!kfprog)
 		return -EFAULT;
 
 	return sock_setsockopt(sock, level, optname, (char __user *)kfprog,
@@ -354,7 +367,8 @@ static int do_set_sock_timeout(struct socket *sock, int level,
 static int compat_sock_setsockopt(struct socket *sock, int level, int optname,
 				char __user *optval, unsigned int optlen)
 {
-	if (optname == SO_ATTACH_FILTER)
+	if (optname == SO_ATTACH_FILTER ||
+	    optname == SO_ATTACH_REUSEPORT_CBPF)
 		return do_set_attach_filter(sock, level, optname,
 					    optval, optlen);
 	if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
diff --git a/net/core/dev.c b/net/core/dev.c
index 904ff431d570..b92d63bfde7a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -139,6 +139,7 @@
 #include <linux/hrtimer.h>
 #include <linux/netfilter_ingress.h>
 #include <linux/sctp.h>
+#include <linux/crash_dump.h>
 
 #include "net-sysfs.h"
 
@@ -2249,11 +2250,12 @@ EXPORT_SYMBOL(netif_set_real_num_rx_queues);
  */
 int netif_get_num_default_rss_queues(void)
 {
-	return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
+	return is_kdump_kernel() ?
+		1 : min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
 }
 EXPORT_SYMBOL(netif_get_num_default_rss_queues);
 
-static inline void __netif_reschedule(struct Qdisc *q)
+static void __netif_reschedule(struct Qdisc *q)
 {
 	struct softnet_data *sd;
 	unsigned long flags;
@@ -2420,7 +2422,7 @@ EXPORT_SYMBOL(__skb_tx_hash);
 
 static void skb_warn_bad_offload(const struct sk_buff *skb)
 {
-	static const netdev_features_t null_features = 0;
+	static const netdev_features_t null_features;
 	struct net_device *dev = skb->dev;
 	const char *name = "";
 
@@ -3068,6 +3070,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 				 struct netdev_queue *txq)
 {
 	spinlock_t *root_lock = qdisc_lock(q);
+	struct sk_buff *to_free = NULL;
 	bool contended;
 	int rc;
 
@@ -3075,7 +3078,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	/*
 	 * Heuristic to force contended enqueues to serialize on a
 	 * separate lock before trying to get qdisc main lock.
-	 * This permits __QDISC___STATE_RUNNING owner to get the lock more
+	 * This permits qdisc->running owner to get the lock more
 	 * often and dequeue packets faster.
 	 */
 	contended = qdisc_is_running(q);
@@ -3084,7 +3087,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 	spin_lock(root_lock);
 	if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
-		kfree_skb(skb);
+		__qdisc_drop(skb, &to_free);
 		rc = NET_XMIT_DROP;
 	} else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
 		   qdisc_run_begin(q)) {
@@ -3107,7 +3110,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 		rc = NET_XMIT_SUCCESS;
 	} else {
-		rc = q->enqueue(skb, q) & NET_XMIT_MASK;
+		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
 		if (qdisc_run_begin(q)) {
 			if (unlikely(contended)) {
 				spin_unlock(&q->busylock);
@@ -3117,6 +3120,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 		}
 	}
 	spin_unlock(root_lock);
+	if (unlikely(to_free))
+		kfree_skb_list(to_free);
 	if (unlikely(contended))
 		spin_unlock(&q->busylock);
 	return rc;
@@ -3142,8 +3147,6 @@ static void skb_update_prio(struct sk_buff *skb)
 DEFINE_PER_CPU(int, xmit_recursion);
 EXPORT_SYMBOL(xmit_recursion);
 
-#define RECURSION_LIMIT 10
-
 /**
  *	dev_loopback_xmit - loop back @skb
  *	@net: network namespace this loopback is happening in
@@ -3386,8 +3389,8 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 		int cpu = smp_processor_id(); /* ok because BHs are off */
 
 		if (txq->xmit_lock_owner != cpu) {
-
-			if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
+			if (unlikely(__this_cpu_read(xmit_recursion) >
+				     XMIT_RECURSION_LIMIT))
 				goto recursion_alert;
 
 			skb = validate_xmit_skb(skb, dev);
@@ -3898,22 +3901,14 @@ static void net_tx_action(struct softirq_action *h)
 			head = head->next_sched;
 
 			root_lock = qdisc_lock(q);
-			if (spin_trylock(root_lock)) {
-				smp_mb__before_atomic();
-				clear_bit(__QDISC_STATE_SCHED,
-					  &q->state);
-				qdisc_run(q);
-				spin_unlock(root_lock);
-			} else {
-				if (!test_bit(__QDISC_STATE_DEACTIVATED,
-					      &q->state)) {
-					__netif_reschedule(q);
-				} else {
-					smp_mb__before_atomic();
-					clear_bit(__QDISC_STATE_SCHED,
-						  &q->state);
-				}
-			}
+			spin_lock(root_lock);
+			/* We need to make sure head->next_sched is read
+			 * before clearing __QDISC_STATE_SCHED
+			 */
+			smp_mb__before_atomic();
+			clear_bit(__QDISC_STATE_SCHED, &q->state);
+			qdisc_run(q);
+			spin_unlock(root_lock);
 		}
 	}
 }
@@ -5450,6 +5445,52 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
 EXPORT_SYMBOL(netdev_lower_get_next);
 
 /**
+ * netdev_all_lower_get_next - Get the next device from all lower neighbour list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's all lower neighbour
+ * list, starting from iter position. The caller must hold RTNL lock or
+ * its own locking that guarantees that the neighbour all lower
+ * list will remain unchanged.
+ */
+struct net_device *netdev_all_lower_get_next(struct net_device *dev, struct list_head **iter)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_entry(*iter, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->all_adj_list.lower)
+		return NULL;
+
+	*iter = lower->list.next;
+
+	return lower->dev;
+}
+EXPORT_SYMBOL(netdev_all_lower_get_next);
+
+/**
+ * netdev_all_lower_get_next_rcu - Get the next device from all
+ *				   lower neighbour list, RCU variant
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's all lower neighbour
+ * list, starting from iter position. The caller must hold RCU read lock.
+ */
+struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
+						 struct list_head **iter)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_first_or_null_rcu(&dev->all_adj_list.lower,
+				       struct netdev_adjacent, list);
+
+	return lower ? lower->dev : NULL;
+}
+EXPORT_SYMBOL(netdev_all_lower_get_next_rcu);
+
+/**
  * netdev_lower_get_first_private_rcu - Get the first ->private from the
  *				       lower neighbour list, RCU
  *				       variant
@@ -5919,7 +5960,7 @@ static void netdev_adjacent_add_links(struct net_device *dev)
 	struct net *net = dev_net(dev);
 
 	list_for_each_entry(iter, &dev->adj_list.upper, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_add(iter->dev, dev,
 					  &iter->dev->adj_list.lower);
@@ -5928,7 +5969,7 @@ static void netdev_adjacent_add_links(struct net_device *dev)
 	}
 
 	list_for_each_entry(iter, &dev->adj_list.lower, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_add(iter->dev, dev,
 					  &iter->dev->adj_list.upper);
@@ -5944,7 +5985,7 @@ static void netdev_adjacent_del_links(struct net_device *dev)
 	struct net *net = dev_net(dev);
 
 	list_for_each_entry(iter, &dev->adj_list.upper, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, dev->name,
 					  &iter->dev->adj_list.lower);
@@ -5953,7 +5994,7 @@ static void netdev_adjacent_del_links(struct net_device *dev)
 	}
 
 	list_for_each_entry(iter, &dev->adj_list.lower, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, dev->name,
 					  &iter->dev->adj_list.upper);
@@ -5969,7 +6010,7 @@ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
 	struct net *net = dev_net(dev);
 
 	list_for_each_entry(iter, &dev->adj_list.upper, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, oldname,
 					  &iter->dev->adj_list.lower);
@@ -5978,7 +6019,7 @@ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
 	}
 
 	list_for_each_entry(iter, &dev->adj_list.lower, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, oldname,
 					  &iter->dev->adj_list.upper);
@@ -6046,6 +6087,50 @@ void netdev_lower_state_changed(struct net_device *lower_dev,
 }
 EXPORT_SYMBOL(netdev_lower_state_changed);
 
+int netdev_default_l2upper_neigh_construct(struct net_device *dev,
+					   struct neighbour *n)
+{
+	struct net_device *lower_dev, *stop_dev;
+	struct list_head *iter;
+	int err;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		if (!lower_dev->netdev_ops->ndo_neigh_construct)
+			continue;
+		err = lower_dev->netdev_ops->ndo_neigh_construct(lower_dev, n);
+		if (err) {
+			stop_dev = lower_dev;
+			goto rollback;
+		}
+	}
+	return 0;
+
+rollback:
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		if (lower_dev == stop_dev)
+			break;
+		if (!lower_dev->netdev_ops->ndo_neigh_destroy)
+			continue;
+		lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n);
+	}
+	return err;
+}
+EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_construct);
+
+void netdev_default_l2upper_neigh_destroy(struct net_device *dev,
+					  struct neighbour *n)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		if (!lower_dev->netdev_ops->ndo_neigh_destroy)
+			continue;
+		lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n);
+	}
+}
+EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_destroy);
+
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 933e8d4d3968..b2e592a198c0 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1394,6 +1394,78 @@ static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb,
 	return -EOPNOTSUPP;
 }
 
+static int devlink_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
+				enum devlink_command cmd, u32 portid,
+				u32 seq, int flags, u16 mode)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	if (nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb,
+						struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const struct devlink_ops *ops = devlink->ops;
+	struct sk_buff *msg;
+	u16 mode;
+	int err;
+
+	if (!ops || !ops->eswitch_mode_get)
+		return -EOPNOTSUPP;
+
+	err = ops->eswitch_mode_get(devlink, &mode);
+	if (err)
+		return err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_MODE_GET,
+				   info->snd_portid, info->snd_seq, 0, mode);
+
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_eswitch_mode_set_doit(struct sk_buff *skb,
+						struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const struct devlink_ops *ops = devlink->ops;
+	u16 mode;
+
+	if (!info->attrs[DEVLINK_ATTR_ESWITCH_MODE])
+		return -EINVAL;
+
+	mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]);
+
+	if (ops && ops->eswitch_mode_set)
+		return ops->eswitch_mode_set(devlink, mode);
+	return -EOPNOTSUPP;
+}
+
 static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -1407,6 +1479,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
 };
 
 static const struct genl_ops devlink_nl_ops[] = {
@@ -1525,6 +1598,20 @@ static const struct genl_ops devlink_nl_ops[] = {
 				  DEVLINK_NL_FLAG_NEED_SB |
 				  DEVLINK_NL_FLAG_LOCK_PORTS,
 	},
+	{
+		.cmd = DEVLINK_CMD_ESWITCH_MODE_GET,
+		.doit = devlink_nl_cmd_eswitch_mode_get_doit,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
+	{
+		.cmd = DEVLINK_CMD_ESWITCH_MODE_SET,
+		.doit = devlink_nl_cmd_eswitch_mode_set_doit,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
 };
 
 /**
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 840acebbb80c..be4629c344a6 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -173,7 +173,8 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
 EXPORT_SYMBOL_GPL(fib_rules_unregister);
 
 static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
-			  struct flowi *fl, int flags)
+			  struct flowi *fl, int flags,
+			  struct fib_lookup_arg *arg)
 {
 	int ret = 0;
 
@@ -189,6 +190,9 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 	if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id))
 		goto out;
 
+	if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg))
+		goto out;
+
 	ret = ops->match(rule, fl, flags);
 out:
 	return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
@@ -204,7 +208,7 @@ int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl,
 
 	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
 jumped:
-		if (!fib_rule_match(rule, ops, fl, flags))
+		if (!fib_rule_match(rule, ops, fl, flags, arg))
 			continue;
 
 		if (rule->action == FR_ACT_GOTO) {
@@ -265,7 +269,50 @@ errout:
 	return err;
 }
 
-static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
+static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
+		       struct nlattr **tb, struct fib_rule *rule)
+{
+	struct fib_rule *r;
+
+	list_for_each_entry(r, &ops->rules_list, list) {
+		if (r->action != rule->action)
+			continue;
+
+		if (r->table != rule->table)
+			continue;
+
+		if (r->pref != rule->pref)
+			continue;
+
+		if (memcmp(r->iifname, rule->iifname, IFNAMSIZ))
+			continue;
+
+		if (memcmp(r->oifname, rule->oifname, IFNAMSIZ))
+			continue;
+
+		if (r->mark != rule->mark)
+			continue;
+
+		if (r->mark_mask != rule->mark_mask)
+			continue;
+
+		if (r->tun_id != rule->tun_id)
+			continue;
+
+		if (r->fr_net != rule->fr_net)
+			continue;
+
+		if (r->l3mdev != rule->l3mdev)
+			continue;
+
+		if (!ops->compare(r, frh, tb))
+			continue;
+		return 1;
+	}
+	return 0;
+}
+
+int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -336,6 +383,14 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 	if (tb[FRA_TUN_ID])
 		rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
 
+	if (tb[FRA_L3MDEV]) {
+#ifdef CONFIG_NET_L3_MASTER_DEV
+		rule->l3mdev = nla_get_u8(tb[FRA_L3MDEV]);
+		if (rule->l3mdev != 1)
+#endif
+			goto errout_free;
+	}
+
 	rule->action = frh->action;
 	rule->flags = frh->flags;
 	rule->table = frh_get_table(frh, tb);
@@ -371,6 +426,15 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 	} else if (rule->action == FR_ACT_GOTO)
 		goto errout_free;
 
+	if (rule->l3mdev && rule->table)
+		goto errout_free;
+
+	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
+	    rule_exists(ops, frh, tb, rule)) {
+		err = -EEXIST;
+		goto errout_free;
+	}
+
 	err = ops->configure(rule, skb, frh, tb);
 	if (err < 0)
 		goto errout_free;
@@ -424,8 +488,9 @@ errout:
 	rules_ops_put(ops);
 	return err;
 }
+EXPORT_SYMBOL_GPL(fib_nl_newrule);
 
-static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
+int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -483,6 +548,10 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 		    (rule->tun_id != nla_get_be64(tb[FRA_TUN_ID])))
 			continue;
 
+		if (tb[FRA_L3MDEV] &&
+		    (rule->l3mdev != nla_get_u8(tb[FRA_L3MDEV])))
+			continue;
+
 		if (!ops->compare(rule, frh, tb))
 			continue;
 
@@ -536,6 +605,7 @@ errout:
 	rules_ops_put(ops);
 	return err;
 }
+EXPORT_SYMBOL_GPL(fib_nl_delrule);
 
 static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 					 struct fib_rule *rule)
@@ -607,7 +677,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	    (rule->target &&
 	     nla_put_u32(skb, FRA_GOTO, rule->target)) ||
 	    (rule->tun_id &&
-	     nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)))
+	     nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) ||
+	    (rule->l3mdev &&
+	     nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)))
 		goto nla_put_failure;
 
 	if (rule->suppress_ifgroup != -1) {
diff --git a/net/core/filter.c b/net/core/filter.c
index 68adb5f52110..10c4a2f9e8bb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -150,6 +150,12 @@ static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 	return raw_smp_processor_id();
 }
 
+static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
+	.func		= __get_raw_cpu_id,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
 static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
 			      struct bpf_insn *insn_buf)
 {
@@ -748,6 +754,17 @@ static bool chk_code_allowed(u16 code_to_probe)
 	return codes[code_to_probe];
 }
 
+static bool bpf_check_basics_ok(const struct sock_filter *filter,
+				unsigned int flen)
+{
+	if (filter == NULL)
+		return false;
+	if (flen == 0 || flen > BPF_MAXINSNS)
+		return false;
+
+	return true;
+}
+
 /**
  *	bpf_check_classic - verify socket filter code
  *	@filter: filter to verify
@@ -768,9 +785,6 @@ static int bpf_check_classic(const struct sock_filter *filter,
 	bool anc_found;
 	int pc;
 
-	if (flen == 0 || flen > BPF_MAXINSNS)
-		return -EINVAL;
-
 	/* Check the filter code now */
 	for (pc = 0; pc < flen; pc++) {
 		const struct sock_filter *ftest = &filter[pc];
@@ -1065,7 +1079,7 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)
 	struct bpf_prog *fp;
 
 	/* Make sure new filter is there and in the right amounts. */
-	if (fprog->filter == NULL)
+	if (!bpf_check_basics_ok(fprog->filter, fprog->len))
 		return -EINVAL;
 
 	fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
@@ -1112,7 +1126,7 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
 	int err;
 
 	/* Make sure new filter is there and in the right amounts. */
-	if (fprog->filter == NULL)
+	if (!bpf_check_basics_ok(fprog->filter, fprog->len))
 		return -EINVAL;
 
 	fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
@@ -1207,7 +1221,6 @@ static
 struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk)
 {
 	unsigned int fsize = bpf_classic_proglen(fprog);
-	unsigned int bpf_fsize = bpf_prog_size(fprog->len);
 	struct bpf_prog *prog;
 	int err;
 
@@ -1215,10 +1228,10 @@ struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk)
 		return ERR_PTR(-EPERM);
 
 	/* Make sure new filter is there and in the right amounts. */
-	if (fprog->filter == NULL)
+	if (!bpf_check_basics_ok(fprog->filter, fprog->len))
 		return ERR_PTR(-EINVAL);
 
-	prog = bpf_prog_alloc(bpf_fsize, 0);
+	prog = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
 	if (!prog)
 		return ERR_PTR(-ENOMEM);
 
@@ -1288,21 +1301,10 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 
 static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk)
 {
-	struct bpf_prog *prog;
-
 	if (sock_flag(sk, SOCK_FILTER_LOCKED))
 		return ERR_PTR(-EPERM);
 
-	prog = bpf_prog_get(ufd);
-	if (IS_ERR(prog))
-		return prog;
-
-	if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) {
-		bpf_prog_put(prog);
-		return ERR_PTR(-EINVAL);
-	}
-
-	return prog;
+	return bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER);
 }
 
 int sk_attach_bpf(u32 ufd, struct sock *sk)
@@ -1603,9 +1605,36 @@ static const struct bpf_func_proto bpf_csum_diff_proto = {
 	.arg5_type	= ARG_ANYTHING,
 };
 
+static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	if (skb_at_tc_ingress(skb))
+		skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len);
+
+	return dev_forward_skb(dev, skb);
+}
+
+static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	int ret;
+
+	if (unlikely(__this_cpu_read(xmit_recursion) > XMIT_RECURSION_LIMIT)) {
+		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
+		kfree_skb(skb);
+		return -ENETDOWN;
+	}
+
+	skb->dev = dev;
+
+	__this_cpu_inc(xmit_recursion);
+	ret = dev_queue_xmit(skb);
+	__this_cpu_dec(xmit_recursion);
+
+	return ret;
+}
+
 static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
 {
-	struct sk_buff *skb = (struct sk_buff *) (long) r1, *skb2;
+	struct sk_buff *skb = (struct sk_buff *) (long) r1;
 	struct net_device *dev;
 
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
@@ -1615,19 +1644,12 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
 	if (unlikely(!dev))
 		return -EINVAL;
 
-	skb2 = skb_clone(skb, GFP_ATOMIC);
-	if (unlikely(!skb2))
+	skb = skb_clone(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
 		return -ENOMEM;
 
-	if (flags & BPF_F_INGRESS) {
-		if (skb_at_tc_ingress(skb2))
-			skb_postpush_rcsum(skb2, skb_mac_header(skb2),
-					   skb2->mac_len);
-		return dev_forward_skb(dev, skb2);
-	}
-
-	skb2->dev = dev;
-	return dev_queue_xmit(skb2);
+	return flags & BPF_F_INGRESS ?
+	       __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
 }
 
 static const struct bpf_func_proto bpf_clone_redirect_proto = {
@@ -1671,15 +1693,8 @@ int skb_do_redirect(struct sk_buff *skb)
 		return -EINVAL;
 	}
 
-	if (ri->flags & BPF_F_INGRESS) {
-		if (skb_at_tc_ingress(skb))
-			skb_postpush_rcsum(skb, skb_mac_header(skb),
-					   skb->mac_len);
-		return dev_forward_skb(dev, skb);
-	}
-
-	skb->dev = dev;
-	return dev_queue_xmit(skb);
+	return ri->flags & BPF_F_INGRESS ?
+	       __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
 }
 
 static const struct bpf_func_proto bpf_redirect_proto = {
@@ -1714,6 +1729,23 @@ static const struct bpf_func_proto bpf_get_route_realm_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
+static u64 bpf_get_hash_recalc(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	/* If skb_clear_hash() was called due to mangling, we can
+	 * trigger SW recalculation here. Later access to hash
+	 * can then use the inline skb->hash via context directly
+	 * instead of calling this helper again.
+	 */
+	return skb_get_hash((struct sk_buff *) (unsigned long) r1);
+}
+
+static const struct bpf_func_proto bpf_get_hash_recalc_proto = {
+	.func		= bpf_get_hash_recalc,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5)
 {
 	struct sk_buff *skb = (struct sk_buff *) (long) r1;
@@ -1757,6 +1789,224 @@ const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
 };
 EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto);
 
+static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
+{
+	/* Caller already did skb_cow() with len as headroom,
+	 * so no need to do it here.
+	 */
+	skb_push(skb, len);
+	memmove(skb->data, skb->data + len, off);
+	memset(skb->data + off, 0, len);
+
+	/* No skb_postpush_rcsum(skb, skb->data + off, len)
+	 * needed here as it does not change the skb->csum
+	 * result for checksum complete when summing over
+	 * zeroed blocks.
+	 */
+	return 0;
+}
+
+static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len)
+{
+	/* skb_ensure_writable() is not needed here, as we're
+	 * already working on an uncloned skb.
+	 */
+	if (unlikely(!pskb_may_pull(skb, off + len)))
+		return -ENOMEM;
+
+	skb_postpull_rcsum(skb, skb->data + off, len);
+	memmove(skb->data + len, skb->data, off);
+	__skb_pull(skb, len);
+
+	return 0;
+}
+
+static int bpf_skb_net_hdr_push(struct sk_buff *skb, u32 off, u32 len)
+{
+	bool trans_same = skb->transport_header == skb->network_header;
+	int ret;
+
+	/* There's no need for __skb_push()/__skb_pull() pair to
+	 * get to the start of the mac header as we're guaranteed
+	 * to always start from here under eBPF.
+	 */
+	ret = bpf_skb_generic_push(skb, off, len);
+	if (likely(!ret)) {
+		skb->mac_header -= len;
+		skb->network_header -= len;
+		if (trans_same)
+			skb->transport_header = skb->network_header;
+	}
+
+	return ret;
+}
+
+static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len)
+{
+	bool trans_same = skb->transport_header == skb->network_header;
+	int ret;
+
+	/* Same here, __skb_push()/__skb_pull() pair not needed. */
+	ret = bpf_skb_generic_pop(skb, off, len);
+	if (likely(!ret)) {
+		skb->mac_header += len;
+		skb->network_header += len;
+		if (trans_same)
+			skb->transport_header = skb->network_header;
+	}
+
+	return ret;
+}
+
+static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
+{
+	const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr);
+	u32 off = skb->network_header - skb->mac_header;
+	int ret;
+
+	ret = skb_cow(skb, len_diff);
+	if (unlikely(ret < 0))
+		return ret;
+
+	ret = bpf_skb_net_hdr_push(skb, off, len_diff);
+	if (unlikely(ret < 0))
+		return ret;
+
+	if (skb_is_gso(skb)) {
+		/* SKB_GSO_UDP stays as is. SKB_GSO_TCPV4 needs to
+		 * be changed into SKB_GSO_TCPV6.
+		 */
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
+			skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV4;
+			skb_shinfo(skb)->gso_type |=  SKB_GSO_TCPV6;
+		}
+
+		/* Due to IPv6 header, MSS needs to be downgraded. */
+		skb_shinfo(skb)->gso_size -= len_diff;
+		/* Header must be checked, and gso_segs recomputed. */
+		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
+		skb_shinfo(skb)->gso_segs = 0;
+	}
+
+	skb->protocol = htons(ETH_P_IPV6);
+	skb_clear_hash(skb);
+
+	return 0;
+}
+
+static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
+{
+	const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr);
+	u32 off = skb->network_header - skb->mac_header;
+	int ret;
+
+	ret = skb_unclone(skb, GFP_ATOMIC);
+	if (unlikely(ret < 0))
+		return ret;
+
+	ret = bpf_skb_net_hdr_pop(skb, off, len_diff);
+	if (unlikely(ret < 0))
+		return ret;
+
+	if (skb_is_gso(skb)) {
+		/* SKB_GSO_UDP stays as is. SKB_GSO_TCPV6 needs to
+		 * be changed into SKB_GSO_TCPV4.
+		 */
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) {
+			skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV6;
+			skb_shinfo(skb)->gso_type |=  SKB_GSO_TCPV4;
+		}
+
+		/* Due to IPv4 header, MSS can be upgraded. */
+		skb_shinfo(skb)->gso_size += len_diff;
+		/* Header must be checked, and gso_segs recomputed. */
+		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
+		skb_shinfo(skb)->gso_segs = 0;
+	}
+
+	skb->protocol = htons(ETH_P_IP);
+	skb_clear_hash(skb);
+
+	return 0;
+}
+
+static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto)
+{
+	__be16 from_proto = skb->protocol;
+
+	if (from_proto == htons(ETH_P_IP) &&
+	      to_proto == htons(ETH_P_IPV6))
+		return bpf_skb_proto_4_to_6(skb);
+
+	if (from_proto == htons(ETH_P_IPV6) &&
+	      to_proto == htons(ETH_P_IP))
+		return bpf_skb_proto_6_to_4(skb);
+
+	return -ENOTSUPP;
+}
+
+static u64 bpf_skb_change_proto(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
+{
+	struct sk_buff *skb = (struct sk_buff *) (long) r1;
+	__be16 proto = (__force __be16) r2;
+	int ret;
+
+	if (unlikely(flags))
+		return -EINVAL;
+
+	/* General idea is that this helper does the basic groundwork
+	 * needed for changing the protocol, and eBPF program fills the
+	 * rest through bpf_skb_store_bytes(), bpf_lX_csum_replace()
+	 * and other helpers, rather than passing a raw buffer here.
+	 *
+	 * The rationale is to keep this minimal and without a need to
+	 * deal with raw packet data. F.e. even if we would pass buffers
+	 * here, the program still needs to call the bpf_lX_csum_replace()
+	 * helpers anyway. Plus, this way we keep also separation of
+	 * concerns, since f.e. bpf_skb_store_bytes() should only take
+	 * care of stores.
+	 *
+	 * Currently, additional options and extension header space are
+	 * not supported, but flags register is reserved so we can adapt
+	 * that. For offloads, we mark packet as dodgy, so that headers
+	 * need to be verified first.
+	 */
+	ret = bpf_skb_proto_xlat(skb, proto);
+	bpf_compute_data_end(skb);
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_skb_change_proto_proto = {
+	.func		= bpf_skb_change_proto,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static u64 bpf_skb_change_type(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	struct sk_buff *skb = (struct sk_buff *) (long) r1;
+	u32 pkt_type = r2;
+
+	/* We only allow a restricted subset to be changed for now. */
+	if (unlikely(skb->pkt_type > PACKET_OTHERHOST ||
+		     pkt_type > PACKET_OTHERHOST))
+		return -EINVAL;
+
+	skb->pkt_type = pkt_type;
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_skb_change_type_proto = {
+	.func		= bpf_skb_change_type,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 bool bpf_helper_changes_skb_data(void *func)
 {
 	if (func == bpf_skb_vlan_push)
@@ -1765,6 +2015,8 @@ bool bpf_helper_changes_skb_data(void *func)
 		return true;
 	if (func == bpf_skb_store_bytes)
 		return true;
+	if (func == bpf_skb_change_proto)
+		return true;
 	if (func == bpf_l3_csum_replace)
 		return true;
 	if (func == bpf_l4_csum_replace)
@@ -2004,6 +2256,40 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which)
 	}
 }
 
+#ifdef CONFIG_SOCK_CGROUP_DATA
+static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	struct sk_buff *skb = (struct sk_buff *)(long)r1;
+	struct bpf_map *map = (struct bpf_map *)(long)r2;
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct cgroup *cgrp;
+	struct sock *sk;
+	u32 i = (u32)r3;
+
+	sk = skb->sk;
+	if (!sk || !sk_fullsock(sk))
+		return -ENOENT;
+
+	if (unlikely(i >= array->map.max_entries))
+		return -E2BIG;
+
+	cgrp = READ_ONCE(array->ptrs[i]);
+	if (unlikely(!cgrp))
+		return -EAGAIN;
+
+	return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), cgrp);
+}
+
+static const struct bpf_func_proto bpf_skb_in_cgroup_proto = {
+	.func		= bpf_skb_in_cgroup,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+};
+#endif
+
 static const struct bpf_func_proto *
 sk_filter_func_proto(enum bpf_func_id func_id)
 {
@@ -2017,7 +2303,7 @@ sk_filter_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
 	case BPF_FUNC_get_smp_processor_id:
-		return &bpf_get_smp_processor_id_proto;
+		return &bpf_get_raw_smp_processor_id_proto;
 	case BPF_FUNC_tail_call:
 		return &bpf_tail_call_proto;
 	case BPF_FUNC_ktime_get_ns:
@@ -2052,6 +2338,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 		return &bpf_skb_vlan_push_proto;
 	case BPF_FUNC_skb_vlan_pop:
 		return &bpf_skb_vlan_pop_proto;
+	case BPF_FUNC_skb_change_proto:
+		return &bpf_skb_change_proto_proto;
+	case BPF_FUNC_skb_change_type:
+		return &bpf_skb_change_type_proto;
 	case BPF_FUNC_skb_get_tunnel_key:
 		return &bpf_skb_get_tunnel_key_proto;
 	case BPF_FUNC_skb_set_tunnel_key:
@@ -2064,8 +2354,16 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 		return &bpf_redirect_proto;
 	case BPF_FUNC_get_route_realm:
 		return &bpf_get_route_realm_proto;
+	case BPF_FUNC_get_hash_recalc:
+		return &bpf_get_hash_recalc_proto;
 	case BPF_FUNC_perf_event_output:
 		return bpf_get_event_output_proto();
+	case BPF_FUNC_get_smp_processor_id:
+		return &bpf_get_smp_processor_id_proto;
+#ifdef CONFIG_SOCK_CGROUP_DATA
+	case BPF_FUNC_skb_in_cgroup:
+		return &bpf_skb_in_cgroup_proto;
+#endif
 	default:
 		return sk_filter_func_proto(func_id);
 	}
@@ -2085,7 +2383,8 @@ static bool __is_valid_access(int off, int size, enum bpf_access_type type)
 }
 
 static bool sk_filter_is_valid_access(int off, int size,
-				      enum bpf_access_type type)
+				      enum bpf_access_type type,
+				      enum bpf_reg_type *reg_type)
 {
 	switch (off) {
 	case offsetof(struct __sk_buff, tc_classid):
@@ -2108,7 +2407,8 @@ static bool sk_filter_is_valid_access(int off, int size,
 }
 
 static bool tc_cls_act_is_valid_access(int off, int size,
-				       enum bpf_access_type type)
+				       enum bpf_access_type type,
+				       enum bpf_reg_type *reg_type)
 {
 	if (type == BPF_WRITE) {
 		switch (off) {
@@ -2123,6 +2423,16 @@ static bool tc_cls_act_is_valid_access(int off, int size,
 			return false;
 		}
 	}
+
+	switch (off) {
+	case offsetof(struct __sk_buff, data):
+		*reg_type = PTR_TO_PACKET;
+		break;
+	case offsetof(struct __sk_buff, data_end):
+		*reg_type = PTR_TO_PACKET_END;
+		break;
+	}
+
 	return __is_valid_access(off, size, type);
 }
 
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 4573d81093fe..cad8e791f28e 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -84,6 +84,7 @@ struct gen_estimator
 	struct gnet_stats_basic_packed	*bstats;
 	struct gnet_stats_rate_est64	*rate_est;
 	spinlock_t		*stats_lock;
+	seqcount_t		*running;
 	int			ewma_log;
 	u32			last_packets;
 	unsigned long		avpps;
@@ -121,26 +122,28 @@ static void est_timer(unsigned long arg)
 		unsigned long rate;
 		u64 brate;
 
-		spin_lock(e->stats_lock);
+		if (e->stats_lock)
+			spin_lock(e->stats_lock);
 		read_lock(&est_lock);
 		if (e->bstats == NULL)
 			goto skip;
 
-		__gnet_stats_copy_basic(&b, e->cpu_bstats, e->bstats);
+		__gnet_stats_copy_basic(e->running, &b, e->cpu_bstats, e->bstats);
 
 		brate = (b.bytes - e->last_bytes)<<(7 - idx);
 		e->last_bytes = b.bytes;
 		e->avbps += (brate >> e->ewma_log) - (e->avbps >> e->ewma_log);
-		e->rate_est->bps = (e->avbps+0xF)>>5;
+		WRITE_ONCE(e->rate_est->bps, (e->avbps + 0xF) >> 5);
 
 		rate = b.packets - e->last_packets;
 		rate <<= (7 - idx);
 		e->last_packets = b.packets;
 		e->avpps += (rate >> e->ewma_log) - (e->avpps >> e->ewma_log);
-		e->rate_est->pps = (e->avpps + 0xF) >> 5;
+		WRITE_ONCE(e->rate_est->pps, (e->avpps + 0xF) >> 5);
 skip:
 		read_unlock(&est_lock);
-		spin_unlock(e->stats_lock);
+		if (e->stats_lock)
+			spin_unlock(e->stats_lock);
 	}
 
 	if (!list_empty(&elist[idx].list))
@@ -194,6 +197,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats
  * @cpu_bstats: bstats per cpu
  * @rate_est: rate estimator statistics
  * @stats_lock: statistics lock
+ * @running: qdisc running seqcount
  * @opt: rate estimator configuration TLV
  *
  * Creates a new rate estimator with &bstats as source and &rate_est
@@ -209,6 +213,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct gnet_stats_rate_est64 *rate_est,
 		      spinlock_t *stats_lock,
+		      seqcount_t *running,
 		      struct nlattr *opt)
 {
 	struct gen_estimator *est;
@@ -226,12 +231,13 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 	if (est == NULL)
 		return -ENOBUFS;
 
-	__gnet_stats_copy_basic(&b, cpu_bstats, bstats);
+	__gnet_stats_copy_basic(running, &b, cpu_bstats, bstats);
 
 	idx = parm->interval + 2;
 	est->bstats = bstats;
 	est->rate_est = rate_est;
 	est->stats_lock = stats_lock;
+	est->running  = running;
 	est->ewma_log = parm->ewma_log;
 	est->last_bytes = b.bytes;
 	est->avbps = rate_est->bps<<5;
@@ -291,6 +297,7 @@ EXPORT_SYMBOL(gen_kill_estimator);
  * @cpu_bstats: bstats per cpu
  * @rate_est: rate estimator statistics
  * @stats_lock: statistics lock
+ * @running: qdisc running seqcount (might be NULL)
  * @opt: rate estimator configuration TLV
  *
  * Replaces the configuration of a rate estimator by calling
@@ -301,10 +308,11 @@ EXPORT_SYMBOL(gen_kill_estimator);
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
 			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct gnet_stats_rate_est64 *rate_est,
-			  spinlock_t *stats_lock, struct nlattr *opt)
+			  spinlock_t *stats_lock,
+			  seqcount_t *running, struct nlattr *opt)
 {
 	gen_kill_estimator(bstats, rate_est);
-	return gen_new_estimator(bstats, cpu_bstats, rate_est, stats_lock, opt);
+	return gen_new_estimator(bstats, cpu_bstats, rate_est, stats_lock, running, opt);
 }
 EXPORT_SYMBOL(gen_replace_estimator);
 
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index f96ee8b9478d..508e051304fb 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -32,10 +32,11 @@ gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size, int padattr)
 	return 0;
 
 nla_put_failure:
+	if (d->lock)
+		spin_unlock_bh(d->lock);
 	kfree(d->xstats);
 	d->xstats = NULL;
 	d->xstats_len = 0;
-	spin_unlock_bh(d->lock);
 	return -1;
 }
 
@@ -47,6 +48,7 @@ nla_put_failure:
  * @xstats_type: TLV type for backward compatibility xstats TLV
  * @lock: statistics lock
  * @d: dumping handle
+ * @padattr: padding attribute
  *
  * Initializes the dumping handle, grabs the statistic lock and appends
  * an empty TLV header to the socket buffer for use a container for all
@@ -65,15 +67,16 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type,
 {
 	memset(d, 0, sizeof(*d));
 
-	spin_lock_bh(lock);
-	d->lock = lock;
 	if (type)
 		d->tail = (struct nlattr *)skb_tail_pointer(skb);
 	d->skb = skb;
 	d->compat_tc_stats = tc_stats_type;
 	d->compat_xstats = xstats_type;
 	d->padattr = padattr;
-
+	if (lock) {
+		d->lock = lock;
+		spin_lock_bh(lock);
+	}
 	if (d->tail)
 		return gnet_stats_copy(d, type, NULL, 0, padattr);
 
@@ -87,6 +90,7 @@ EXPORT_SYMBOL(gnet_stats_start_copy_compat);
  * @type: TLV type for top level statistic TLV
  * @lock: statistics lock
  * @d: dumping handle
+ * @padattr: padding attribute
  *
  * Initializes the dumping handle, grabs the statistic lock and appends
  * an empty TLV header to the socket buffer for use a container for all
@@ -126,21 +130,29 @@ __gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats,
 }
 
 void
-__gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats,
+__gnet_stats_copy_basic(const seqcount_t *running,
+			struct gnet_stats_basic_packed *bstats,
 			struct gnet_stats_basic_cpu __percpu *cpu,
 			struct gnet_stats_basic_packed *b)
 {
+	unsigned int seq;
+
 	if (cpu) {
 		__gnet_stats_copy_basic_cpu(bstats, cpu);
-	} else {
+		return;
+	}
+	do {
+		if (running)
+			seq = read_seqcount_begin(running);
 		bstats->bytes = b->bytes;
 		bstats->packets = b->packets;
-	}
+	} while (running && read_seqcount_retry(running, seq));
 }
 EXPORT_SYMBOL(__gnet_stats_copy_basic);
 
 /**
  * gnet_stats_copy_basic - copy basic statistics into statistic TLV
+ * @running: seqcount_t pointer
  * @d: dumping handle
  * @cpu: copy statistic per cpu
  * @b: basic statistics
@@ -152,13 +164,14 @@ EXPORT_SYMBOL(__gnet_stats_copy_basic);
  * if the room in the socket buffer was not sufficient.
  */
 int
-gnet_stats_copy_basic(struct gnet_dump *d,
+gnet_stats_copy_basic(const seqcount_t *running,
+		      struct gnet_dump *d,
 		      struct gnet_stats_basic_cpu __percpu *cpu,
 		      struct gnet_stats_basic_packed *b)
 {
 	struct gnet_stats_basic_packed bstats = {0};
 
-	__gnet_stats_copy_basic(&bstats, cpu, b);
+	__gnet_stats_copy_basic(running, &bstats, cpu, b);
 
 	if (d->compat_tc_stats) {
 		d->tc_stats.bytes = bstats.bytes;
@@ -328,8 +341,9 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
 	return 0;
 
 err_out:
+	if (d->lock)
+		spin_unlock_bh(d->lock);
 	d->xstats_len = 0;
-	spin_unlock_bh(d->lock);
 	return -1;
 }
 EXPORT_SYMBOL(gnet_stats_copy_app);
@@ -363,10 +377,11 @@ gnet_stats_finish_copy(struct gnet_dump *d)
 			return -1;
 	}
 
+	if (d->lock)
+		spin_unlock_bh(d->lock);
 	kfree(d->xstats);
 	d->xstats = NULL;
 	d->xstats_len = 0;
-	spin_unlock_bh(d->lock);
 	return 0;
 }
 EXPORT_SYMBOL(gnet_stats_finish_copy);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 29dd8cc22bbf..5cdc62a8eb84 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -473,7 +473,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
 	}
 
 	if (dev->netdev_ops->ndo_neigh_construct) {
-		error = dev->netdev_ops->ndo_neigh_construct(n);
+		error = dev->netdev_ops->ndo_neigh_construct(dev, n);
 		if (error < 0) {
 			rc = ERR_PTR(error);
 			goto out_neigh_release;
@@ -701,7 +701,7 @@ void neigh_destroy(struct neighbour *neigh)
 	neigh->arp_queue_len_bytes = 0;
 
 	if (dev->netdev_ops->ndo_neigh_destroy)
-		dev->netdev_ops->ndo_neigh_destroy(neigh);
+		dev->netdev_ops->ndo_neigh_destroy(dev, neigh);
 
 	dev_put(dev);
 	neigh_parms_put(neigh->parms);
@@ -2047,6 +2047,7 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 			case NDTPA_DELAY_PROBE_TIME:
 				NEIGH_VAR_SET(p, DELAY_PROBE_TIME,
 					      nla_get_msecs(tbp[i]));
+				call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p);
 				break;
 			case NDTPA_RETRANS_TIME:
 				NEIGH_VAR_SET(p, RETRANS_TIME,
@@ -2469,13 +2470,17 @@ int neigh_xmit(int index, struct net_device *dev,
 		tbl = neigh_tables[index];
 		if (!tbl)
 			goto out;
+		rcu_read_lock_bh();
 		neigh = __neigh_lookup_noref(tbl, addr, dev);
 		if (!neigh)
 			neigh = __neigh_create(tbl, addr, dev, false);
 		err = PTR_ERR(neigh);
-		if (IS_ERR(neigh))
+		if (IS_ERR(neigh)) {
+			rcu_read_unlock_bh();
 			goto out_kfree_skb;
+		}
 		err = neigh->output(neigh, skb);
+		rcu_read_unlock_bh();
 	}
 	else if (index == NEIGH_LINK_TABLE) {
 		err = dev_hard_header(skb, dev, ntohs(skb->protocol),
@@ -2926,6 +2931,7 @@ static void neigh_proc_update(struct ctl_table *ctl, int write)
 		return;
 
 	set_bit(index, p->data_state);
+	call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p);
 	if (!dev) /* NULL dev means this is default value */
 		neigh_copy_dflt_parms(net, p, index);
 }
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 2b3f76fe65f4..6e4f34721080 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -24,6 +24,7 @@
 #include <linux/jiffies.h>
 #include <linux/pm_runtime.h>
 #include <linux/of.h>
+#include <linux/of_net.h>
 
 #include "net-sysfs.h"
 
@@ -321,7 +322,20 @@ NETDEVICE_SHOW_RW(flags, fmt_hex);
 
 static int change_tx_queue_len(struct net_device *dev, unsigned long new_len)
 {
-	dev->tx_queue_len = new_len;
+	int res, orig_len = dev->tx_queue_len;
+
+	if (new_len != orig_len) {
+		dev->tx_queue_len = new_len;
+		res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev);
+		res = notifier_to_errno(res);
+		if (res) {
+			netdev_err(dev,
+				   "refused to change device tx_queue_len\n");
+			dev->tx_queue_len = orig_len;
+			return -EFAULT;
+		}
+	}
+
 	return 0;
 }
 
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 8b02df0d354d..bbd118b19aef 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -213,6 +213,7 @@
 /* Xmit modes */
 #define M_START_XMIT		0	/* Default normal TX */
 #define M_NETIF_RECEIVE 	1	/* Inject packets into stack */
+#define M_QUEUE_XMIT		2	/* Inject packet into qdisc */
 
 /* If lock -- protects updating of if_list */
 #define   if_lock(t)           spin_lock(&(t->if_lock));
@@ -626,6 +627,8 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 
 	if (pkt_dev->xmit_mode == M_NETIF_RECEIVE)
 		seq_puts(seq, "     xmit_mode: netif_receive\n");
+	else if (pkt_dev->xmit_mode == M_QUEUE_XMIT)
+		seq_puts(seq, "     xmit_mode: xmit_queue\n");
 
 	seq_puts(seq, "     Flags: ");
 
@@ -1142,8 +1145,10 @@ static ssize_t pktgen_if_write(struct file *file,
 			return len;
 
 		i += len;
-		if ((value > 1) && (pkt_dev->xmit_mode == M_START_XMIT) &&
-		    (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))
+		if ((value > 1) &&
+		    ((pkt_dev->xmit_mode == M_QUEUE_XMIT) ||
+		     ((pkt_dev->xmit_mode == M_START_XMIT) &&
+		     (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))))
 			return -ENOTSUPP;
 		pkt_dev->burst = value < 1 ? 1 : value;
 		sprintf(pg_result, "OK: burst=%d", pkt_dev->burst);
@@ -1198,6 +1203,9 @@ static ssize_t pktgen_if_write(struct file *file,
 			 * at module loading time
 			 */
 			pkt_dev->clone_skb = 0;
+		} else if (strcmp(f, "queue_xmit") == 0) {
+			pkt_dev->xmit_mode = M_QUEUE_XMIT;
+			pkt_dev->last_ok = 1;
 		} else {
 			sprintf(pg_result,
 				"xmit_mode -:%s:- unknown\nAvailable modes: %s",
@@ -3434,6 +3442,36 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 #endif
 		} while (--burst > 0);
 		goto out; /* Skips xmit_mode M_START_XMIT */
+	} else if (pkt_dev->xmit_mode == M_QUEUE_XMIT) {
+		local_bh_disable();
+		atomic_inc(&pkt_dev->skb->users);
+
+		ret = dev_queue_xmit(pkt_dev->skb);
+		switch (ret) {
+		case NET_XMIT_SUCCESS:
+			pkt_dev->sofar++;
+			pkt_dev->seq_num++;
+			pkt_dev->tx_bytes += pkt_dev->last_pkt_size;
+			break;
+		case NET_XMIT_DROP:
+		case NET_XMIT_CN:
+		/* These are all valid return codes for a qdisc but
+		 * indicate packets are being dropped or will likely
+		 * be dropped soon.
+		 */
+		case NETDEV_TX_BUSY:
+		/* qdisc may call dev_hard_start_xmit directly in cases
+		 * where no queues exist e.g. loopback device, virtual
+		 * devices, etc. In this case we need to handle
+		 * NETDEV_TX_ codes.
+		 */
+		default:
+			pkt_dev->errors++;
+			net_info_ratelimited("%s xmit error: %d\n",
+					     pkt_dev->odevname, ret);
+			break;
+		}
+		goto out;
 	}
 
 	txq = skb_get_tx_queue(odev, pkt_dev->skb);
@@ -3463,7 +3501,6 @@ xmit_more:
 		break;
 	case NET_XMIT_DROP:
 	case NET_XMIT_CN:
-	case NET_XMIT_POLICED:
 		/* skb has been consumed */
 		pkt_dev->errors++;
 		break;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d69c4644f8f2..a9e3805af739 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -71,9 +71,31 @@ void rtnl_lock(void)
 }
 EXPORT_SYMBOL(rtnl_lock);
 
+static struct sk_buff *defer_kfree_skb_list;
+void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail)
+{
+	if (head && tail) {
+		tail->next = defer_kfree_skb_list;
+		defer_kfree_skb_list = head;
+	}
+}
+EXPORT_SYMBOL(rtnl_kfree_skbs);
+
 void __rtnl_unlock(void)
 {
+	struct sk_buff *head = defer_kfree_skb_list;
+
+	defer_kfree_skb_list = NULL;
+
 	mutex_unlock(&rtnl_mutex);
+
+	while (head) {
+		struct sk_buff *next = head->next;
+
+		kfree_skb(head);
+		cond_resched();
+		head = next;
+	}
 }
 
 void rtnl_unlock(void)
@@ -1905,11 +1927,19 @@ static int do_setlink(const struct sk_buff *skb,
 
 	if (tb[IFLA_TXQLEN]) {
 		unsigned long value = nla_get_u32(tb[IFLA_TXQLEN]);
-
-		if (dev->tx_queue_len ^ value)
+		unsigned long orig_len = dev->tx_queue_len;
+
+		if (dev->tx_queue_len ^ value) {
+			dev->tx_queue_len = value;
+			err = call_netdevice_notifiers(
+			      NETDEV_CHANGE_TX_QUEUE_LEN, dev);
+			err = notifier_to_errno(err);
+			if (err) {
+				dev->tx_queue_len = orig_len;
+				goto errout;
+			}
 			status |= DO_SETLINK_NOTIFY;
-
-		dev->tx_queue_len = value;
+		}
 	}
 
 	if (tb[IFLA_OPERSTATE])
@@ -3497,7 +3527,32 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
 			if (!attr)
 				goto nla_put_failure;
 
-			err = ops->fill_linkxstats(skb, dev, prividx);
+			err = ops->fill_linkxstats(skb, dev, prividx, *idxattr);
+			nla_nest_end(skb, attr);
+			if (err)
+				goto nla_put_failure;
+			*idxattr = 0;
+		}
+	}
+
+	if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_XSTATS_SLAVE,
+			     *idxattr)) {
+		const struct rtnl_link_ops *ops = NULL;
+		const struct net_device *master;
+
+		master = netdev_master_upper_dev_get(dev);
+		if (master)
+			ops = master->rtnl_link_ops;
+		if (ops && ops->fill_linkxstats) {
+			int err;
+
+			*idxattr = IFLA_STATS_LINK_XSTATS_SLAVE;
+			attr = nla_nest_start(skb,
+					      IFLA_STATS_LINK_XSTATS_SLAVE);
+			if (!attr)
+				goto nla_put_failure;
+
+			err = ops->fill_linkxstats(skb, dev, prividx, *idxattr);
 			nla_nest_end(skb, attr);
 			if (err)
 				goto nla_put_failure;
@@ -3533,14 +3588,35 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev,
 
 	if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_XSTATS, 0)) {
 		const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
+		int attr = IFLA_STATS_LINK_XSTATS;
 
 		if (ops && ops->get_linkxstats_size) {
-			size += nla_total_size(ops->get_linkxstats_size(dev));
+			size += nla_total_size(ops->get_linkxstats_size(dev,
+									attr));
 			/* for IFLA_STATS_LINK_XSTATS */
 			size += nla_total_size(0);
 		}
 	}
 
+	if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_XSTATS_SLAVE, 0)) {
+		struct net_device *_dev = (struct net_device *)dev;
+		const struct rtnl_link_ops *ops = NULL;
+		const struct net_device *master;
+
+		/* netdev_master_upper_dev_get can't take const */
+		master = netdev_master_upper_dev_get(_dev);
+		if (master)
+			ops = master->rtnl_link_ops;
+		if (ops && ops->get_linkxstats_size) {
+			int attr = IFLA_STATS_LINK_XSTATS_SLAVE;
+
+			size += nla_total_size(ops->get_linkxstats_size(dev,
+									attr));
+			/* for IFLA_STATS_LINK_XSTATS_SLAVE */
+			size += nla_total_size(0);
+		}
+	}
+
 	return size;
 }
 
diff --git a/net/core/utils.c b/net/core/utils.c
index 3d17ca8b4744..cf5622b9ccc4 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -133,7 +133,7 @@ int in4_pton(const char *src, int srclen,
 	s = src;
 	d = dbuf;
 	i = 0;
-	while(1) {
+	while (1) {
 		int c;
 		c = xdigit2bin(srclen > 0 ? *s : '\0', delim);
 		if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK))) {
@@ -283,11 +283,11 @@ cont:
 	i = 15; d--;
 
 	if (dc) {
-		while(d >= dc)
+		while (d >= dc)
 			dst[i--] = *d--;
-		while(i >= dc - dbuf)
+		while (i >= dc - dbuf)
 			dst[i--] = 0;
-		while(i >= 0)
+		while (i >= 0)
 			dst[i--] = *d--;
 	} else
 		memcpy(dst, dbuf, sizeof(dbuf));
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index ce3b942dce76..766d2a525ada 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -266,6 +266,41 @@ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol)
 	return ops;
 }
 
+int dsa_cpu_port_ethtool_setup(struct dsa_switch *ds)
+{
+	struct net_device *master;
+	struct ethtool_ops *cpu_ops;
+
+	master = ds->dst->master_netdev;
+	if (ds->master_netdev)
+		master = ds->master_netdev;
+
+	cpu_ops = devm_kzalloc(ds->dev, sizeof(*cpu_ops), GFP_KERNEL);
+	if (!cpu_ops)
+		return -ENOMEM;
+
+	memcpy(&ds->dst->master_ethtool_ops, master->ethtool_ops,
+	       sizeof(struct ethtool_ops));
+	ds->dst->master_orig_ethtool_ops = master->ethtool_ops;
+	memcpy(cpu_ops, &ds->dst->master_ethtool_ops,
+	       sizeof(struct ethtool_ops));
+	dsa_cpu_port_ethtool_init(cpu_ops);
+	master->ethtool_ops = cpu_ops;
+
+	return 0;
+}
+
+void dsa_cpu_port_ethtool_restore(struct dsa_switch *ds)
+{
+	struct net_device *master;
+
+	master = ds->dst->master_netdev;
+	if (ds->master_netdev)
+		master = ds->master_netdev;
+
+	master->ethtool_ops = ds->dst->master_orig_ethtool_ops;
+}
+
 static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent)
 {
 	struct dsa_switch_driver *drv = ds->drv;
@@ -379,6 +414,10 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent)
 		ret = 0;
 	}
 
+	ret = dsa_cpu_port_ethtool_setup(ds);
+	if (ret)
+		return ret;
+
 #ifdef CONFIG_NET_DSA_HWMON
 	/* If the switch provides a temperature sensor,
 	 * register with hardware monitoring subsystem.
@@ -963,6 +1002,8 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst)
 			dsa_switch_destroy(ds);
 	}
 
+	dsa_cpu_port_ethtool_restore(dst->ds[0]);
+
 	dev_put(dst->master_netdev);
 }
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 80dfe08db825..83b95fc4cede 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -283,6 +283,7 @@ static void dsa_user_port_unapply(struct device_node *port, u32 index,
 	if (ds->ports[index].netdev) {
 		dsa_slave_destroy(ds->ports[index].netdev);
 		ds->ports[index].netdev = NULL;
+		ds->enabled_port_mask &= ~(1 << index);
 	}
 }
 
@@ -292,6 +293,13 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
 	u32 index;
 	int err;
 
+	/* Initialize ds->phys_mii_mask before registering the slave MDIO bus
+	 * driver and before drv->setup() has run, since the switch drivers and
+	 * the slave MDIO bus driver rely on these values for probing PHY
+	 * devices or not
+	 */
+	ds->phys_mii_mask = ds->enabled_port_mask;
+
 	err = ds->drv->setup(ds);
 	if (err < 0)
 		return err;
@@ -304,6 +312,18 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
 	if (err < 0)
 		return err;
 
+	if (!ds->slave_mii_bus && ds->drv->phy_read) {
+		ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
+		if (!ds->slave_mii_bus)
+			return -ENOMEM;
+
+		dsa_slave_mii_bus_init(ds);
+
+		err = mdiobus_register(ds->slave_mii_bus);
+		if (err < 0)
+			return err;
+	}
+
 	for (index = 0; index < DSA_MAX_PORTS; index++) {
 		port = ds->ports[index].dn;
 		if (!port)
@@ -353,6 +373,9 @@ static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
 
 		dsa_user_port_unapply(port, index, ds);
 	}
+
+	if (ds->slave_mii_bus && ds->drv->phy_read)
+		mdiobus_unregister(ds->slave_mii_bus);
 }
 
 static int dsa_dst_apply(struct dsa_switch_tree *dst)
@@ -371,6 +394,10 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst)
 			return err;
 	}
 
+	err = dsa_cpu_port_ethtool_setup(dst->ds[0]);
+	if (err)
+		return err;
+
 	/* If we use a tagging format that doesn't have an ethertype
 	 * field, make sure that all packets from this point on get
 	 * sent to the tag format's receive function.
@@ -406,6 +433,8 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst)
 		dsa_ds_unapply(dst, ds);
 	}
 
+	dsa_cpu_port_ethtool_restore(dst->ds[0]);
+
 	pr_info("DSA: tree %d unapplied\n", dst->tree);
 	dst->applied = false;
 }
@@ -511,6 +540,13 @@ static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds)
 			return -EINVAL;
 
 		ds->ports[reg].dn = port;
+
+		/* Initialize enabled_port_mask now for drv->setup()
+		 * to have access to a correct value, just like what
+		 * net/dsa/dsa.c::dsa_switch_setup_one does.
+		 */
+		if (!dsa_port_is_cpu(port))
+			ds->enabled_port_mask |= 1 << reg;
 	}
 
 	return 0;
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index b42f1a5f95f3..00077a9c97f4 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -54,10 +54,13 @@ int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev,
 		      struct device_node *port_dn, int port);
 void dsa_cpu_dsa_destroy(struct device_node *port_dn);
 const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol);
+int dsa_cpu_port_ethtool_setup(struct dsa_switch *ds);
+void dsa_cpu_port_ethtool_restore(struct dsa_switch *ds);
 
 /* slave.c */
 extern const struct dsa_device_ops notag_netdev_ops;
 void dsa_slave_mii_bus_init(struct dsa_switch *ds);
+void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops);
 int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 		     int port, const char *name);
 void dsa_slave_destroy(struct net_device *slave_dev);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 15a492261895..7236eb26dc97 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -49,7 +49,8 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds)
 	ds->slave_mii_bus->name = "dsa slave smi";
 	ds->slave_mii_bus->read = dsa_slave_phy_read;
 	ds->slave_mii_bus->write = dsa_slave_phy_write;
-	snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d", ds->index);
+	snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d",
+		 ds->dst->tree, ds->index);
 	ds->slave_mii_bus->parent = ds->dev;
 	ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask;
 }
@@ -864,6 +865,13 @@ static void dsa_slave_poll_controller(struct net_device *dev)
 }
 #endif
 
+void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops)
+{
+	ops->get_sset_count = dsa_cpu_port_get_sset_count;
+	ops->get_ethtool_stats = dsa_cpu_port_get_ethtool_stats;
+	ops->get_strings = dsa_cpu_port_get_strings;
+}
+
 static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_settings		= dsa_slave_get_settings,
 	.set_settings		= dsa_slave_set_settings,
@@ -884,8 +892,6 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_eee		= dsa_slave_get_eee,
 };
 
-static struct ethtool_ops dsa_cpu_port_ethtool_ops;
-
 static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_open	 	= dsa_slave_open,
 	.ndo_stop		= dsa_slave_close,
@@ -1118,19 +1124,6 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 
 	slave_dev->features = master->vlan_features;
 	slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
-	if (master->ethtool_ops != &dsa_cpu_port_ethtool_ops) {
-		memcpy(&dst->master_ethtool_ops, master->ethtool_ops,
-		       sizeof(struct ethtool_ops));
-		memcpy(&dsa_cpu_port_ethtool_ops, &dst->master_ethtool_ops,
-		       sizeof(struct ethtool_ops));
-		dsa_cpu_port_ethtool_ops.get_sset_count =
-					dsa_cpu_port_get_sset_count;
-		dsa_cpu_port_ethtool_ops.get_ethtool_stats =
-					dsa_cpu_port_get_ethtool_stats;
-		dsa_cpu_port_ethtool_ops.get_strings =
-					dsa_cpu_port_get_strings;
-		master->ethtool_ops = &dsa_cpu_port_ethtool_ops;
-	}
 	eth_hw_addr_inherit(slave_dev, master);
 	slave_dev->priv_flags |= IFF_NO_QUEUE;
 	slave_dev->netdev_ops = &dsa_slave_netdev_ops;
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index dd085db8580e..935ab932e841 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -58,21 +58,10 @@ static struct header_ops lowpan_header_ops = {
 	.create	= lowpan_header_create,
 };
 
-static struct lock_class_key lowpan_tx_busylock;
-static struct lock_class_key lowpan_netdev_xmit_lock_key;
-
-static void lowpan_set_lockdep_class_one(struct net_device *ldev,
-					 struct netdev_queue *txq,
-					 void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock,
-			  &lowpan_netdev_xmit_lock_key);
-}
-
 static int lowpan_dev_init(struct net_device *ldev)
 {
-	netdev_for_each_tx_queue(ldev, lowpan_set_lockdep_class_one, NULL);
-	ldev->qdisc_tx_busylock = &lowpan_tx_busylock;
+	netdev_lockdep_set_classes(ldev);
+
 	return 0;
 }
 
@@ -92,11 +81,21 @@ static int lowpan_stop(struct net_device *dev)
 	return 0;
 }
 
+static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n)
+{
+	struct lowpan_802154_neigh *neigh = lowpan_802154_neigh(neighbour_priv(n));
+
+	/* default no short_addr is available for a neighbour */
+	neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
+	return 0;
+}
+
 static const struct net_device_ops lowpan_netdev_ops = {
 	.ndo_init		= lowpan_dev_init,
 	.ndo_start_xmit		= lowpan_xmit,
 	.ndo_open		= lowpan_open,
 	.ndo_stop		= lowpan_stop,
+	.ndo_neigh_construct    = lowpan_neigh_construct,
 };
 
 static void lowpan_setup(struct net_device *ldev)
@@ -161,6 +160,8 @@ static int lowpan_newlink(struct net *src_net, struct net_device *ldev,
 				wdev->needed_headroom;
 	ldev->needed_tailroom = wdev->needed_tailroom;
 
+	ldev->neigh_priv_len = sizeof(struct lowpan_802154_neigh);
+
 	ret = lowpan_register_netdevice(ldev, LOWPAN_LLTYPE_IEEE802154);
 	if (ret < 0) {
 		dev_put(wdev);
diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c
index e459afd16bb3..dbb476d7d38f 100644
--- a/net/ieee802154/6lowpan/tx.c
+++ b/net/ieee802154/6lowpan/tx.c
@@ -9,6 +9,7 @@
  */
 
 #include <net/6lowpan.h>
+#include <net/ndisc.h>
 #include <net/ieee802154_netdev.h>
 #include <net/mac802154.h>
 
@@ -17,19 +18,9 @@
 #define LOWPAN_FRAG1_HEAD_SIZE	0x4
 #define LOWPAN_FRAGN_HEAD_SIZE	0x5
 
-/* don't save pan id, it's intra pan */
-struct lowpan_addr {
-	u8 mode;
-	union {
-		/* IPv6 needs big endian here */
-		__be64 extended_addr;
-		__be16 short_addr;
-	} u;
-};
-
 struct lowpan_addr_info {
-	struct lowpan_addr daddr;
-	struct lowpan_addr saddr;
+	struct ieee802154_addr daddr;
+	struct ieee802154_addr saddr;
 };
 
 static inline struct
@@ -48,12 +39,14 @@ lowpan_addr_info *lowpan_skb_priv(const struct sk_buff *skb)
  * RAW/DGRAM sockets.
  */
 int lowpan_header_create(struct sk_buff *skb, struct net_device *ldev,
-			 unsigned short type, const void *_daddr,
-			 const void *_saddr, unsigned int len)
+			 unsigned short type, const void *daddr,
+			 const void *saddr, unsigned int len)
 {
-	const u8 *saddr = _saddr;
-	const u8 *daddr = _daddr;
-	struct lowpan_addr_info *info;
+	struct wpan_dev *wpan_dev = lowpan_802154_dev(ldev)->wdev->ieee802154_ptr;
+	struct lowpan_addr_info *info = lowpan_skb_priv(skb);
+	struct lowpan_802154_neigh *llneigh = NULL;
+	const struct ipv6hdr *hdr = ipv6_hdr(skb);
+	struct neighbour *n;
 
 	/* TODO:
 	 * if this package isn't ipv6 one, where should it be routed?
@@ -61,21 +54,50 @@ int lowpan_header_create(struct sk_buff *skb, struct net_device *ldev,
 	if (type != ETH_P_IPV6)
 		return 0;
 
-	if (!saddr)
-		saddr = ldev->dev_addr;
+	/* intra-pan communication */
+	info->saddr.pan_id = wpan_dev->pan_id;
+	info->daddr.pan_id = info->saddr.pan_id;
 
-	raw_dump_inline(__func__, "saddr", (unsigned char *)saddr, 8);
-	raw_dump_inline(__func__, "daddr", (unsigned char *)daddr, 8);
+	if (!memcmp(daddr, ldev->broadcast, EUI64_ADDR_LEN)) {
+		info->daddr.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
+		info->daddr.mode = IEEE802154_ADDR_SHORT;
+	} else {
+		__le16 short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
+
+		n = neigh_lookup(&nd_tbl, &hdr->daddr, ldev);
+		if (n) {
+			llneigh = lowpan_802154_neigh(neighbour_priv(n));
+			read_lock_bh(&n->lock);
+			short_addr = llneigh->short_addr;
+			read_unlock_bh(&n->lock);
+		}
 
-	info = lowpan_skb_priv(skb);
+		if (llneigh &&
+		    lowpan_802154_is_valid_src_short_addr(short_addr)) {
+			info->daddr.short_addr = short_addr;
+			info->daddr.mode = IEEE802154_ADDR_SHORT;
+		} else {
+			info->daddr.mode = IEEE802154_ADDR_LONG;
+			ieee802154_be64_to_le64(&info->daddr.extended_addr,
+						daddr);
+		}
 
-	/* TODO: Currently we only support extended_addr */
-	info->daddr.mode = IEEE802154_ADDR_LONG;
-	memcpy(&info->daddr.u.extended_addr, daddr,
-	       sizeof(info->daddr.u.extended_addr));
-	info->saddr.mode = IEEE802154_ADDR_LONG;
-	memcpy(&info->saddr.u.extended_addr, saddr,
-	       sizeof(info->daddr.u.extended_addr));
+		if (n)
+			neigh_release(n);
+	}
+
+	if (!saddr) {
+		if (lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr)) {
+			info->saddr.mode = IEEE802154_ADDR_SHORT;
+			info->saddr.short_addr = wpan_dev->short_addr;
+		} else {
+			info->saddr.mode = IEEE802154_ADDR_LONG;
+			info->saddr.extended_addr = wpan_dev->extended_addr;
+		}
+	} else {
+		info->saddr.mode = IEEE802154_ADDR_LONG;
+		ieee802154_be64_to_le64(&info->saddr.extended_addr, saddr);
+	}
 
 	return 0;
 }
@@ -209,47 +231,26 @@ static int lowpan_header(struct sk_buff *skb, struct net_device *ldev,
 			 u16 *dgram_size, u16 *dgram_offset)
 {
 	struct wpan_dev *wpan_dev = lowpan_802154_dev(ldev)->wdev->ieee802154_ptr;
-	struct ieee802154_addr sa, da;
 	struct ieee802154_mac_cb *cb = mac_cb_init(skb);
 	struct lowpan_addr_info info;
-	void *daddr, *saddr;
 
 	memcpy(&info, lowpan_skb_priv(skb), sizeof(info));
 
-	/* TODO: Currently we only support extended_addr */
-	daddr = &info.daddr.u.extended_addr;
-	saddr = &info.saddr.u.extended_addr;
-
 	*dgram_size = skb->len;
-	lowpan_header_compress(skb, ldev, daddr, saddr);
+	lowpan_header_compress(skb, ldev, &info.daddr, &info.saddr);
 	/* dgram_offset = (saved bytes after compression) + lowpan header len */
 	*dgram_offset = (*dgram_size - skb->len) + skb_network_header_len(skb);
 
 	cb->type = IEEE802154_FC_TYPE_DATA;
 
-	/* prepare wpan address data */
-	sa.mode = IEEE802154_ADDR_LONG;
-	sa.pan_id = wpan_dev->pan_id;
-	sa.extended_addr = ieee802154_devaddr_from_raw(saddr);
-
-	/* intra-PAN communications */
-	da.pan_id = sa.pan_id;
-
-	/* if the destination address is the broadcast address, use the
-	 * corresponding short address
-	 */
-	if (!memcmp(daddr, ldev->broadcast, EUI64_ADDR_LEN)) {
-		da.mode = IEEE802154_ADDR_SHORT;
-		da.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
+	if (info.daddr.mode == IEEE802154_ADDR_SHORT &&
+	    ieee802154_is_broadcast_short_addr(info.daddr.short_addr))
 		cb->ackreq = false;
-	} else {
-		da.mode = IEEE802154_ADDR_LONG;
-		da.extended_addr = ieee802154_devaddr_from_raw(daddr);
+	else
 		cb->ackreq = wpan_dev->ackreq;
-	}
 
-	return wpan_dev_hard_header(skb, lowpan_802154_dev(ldev)->wdev, &da,
-				    &sa, 0);
+	return wpan_dev_hard_header(skb, lowpan_802154_dev(ldev)->wdev,
+				    &info.daddr, &info.saddr, 0);
 }
 
 netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev)
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 238225b0c970..50d6a9b49f6c 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -532,6 +532,22 @@ config TCP_CONG_VEGAS
 	window. TCP Vegas should provide less packet loss, but it is
 	not as aggressive as TCP Reno.
 
+config TCP_CONG_NV
+       tristate "TCP NV"
+       default n
+       ---help---
+       TCP NV is a follow up to TCP Vegas. It has been modified to deal with
+       10G networks, measurement noise introduced by LRO, GRO and interrupt
+       coalescence. In addition, it will decrease its cwnd multiplicatively
+       instead of linearly.
+
+       Note that in general congestion avoidance (cwnd decreased when # packets
+       queued grows) cannot coexist with congestion control (cwnd decreased only
+       when there is packet loss) due to fairness issues. One scenario when they
+       can coexist safely is when the CA flows have RTTs << CC flows RTTs.
+
+       For further details see http://www.brakmo.org/networking/tcp-nv/
+
 config TCP_CONG_SCALABLE
 	tristate "Scalable TCP"
 	default n
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index bfa133691cde..24629b6f57cc 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_TCP_CONG_HSTCP) += tcp_highspeed.o
 obj-$(CONFIG_TCP_CONG_HYBLA) += tcp_hybla.o
 obj-$(CONFIG_TCP_CONG_HTCP) += tcp_htcp.o
 obj-$(CONFIG_TCP_CONG_VEGAS) += tcp_vegas.o
+obj-$(CONFIG_TCP_CONG_NV) += tcp_nv.o
 obj-$(CONFIG_TCP_CONG_VENO) += tcp_veno.o
 obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
 obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 477937465a20..d95631d09248 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -23,6 +23,11 @@ struct esp_skb_cb {
 	void *tmp;
 };
 
+struct esp_output_extra {
+	__be32 seqhi;
+	u32 esphoff;
+};
+
 #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0]))
 
 static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
@@ -35,11 +40,11 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
  *
  * TODO: Use spare space in skb for this where possible.
  */
-static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
+static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int extralen)
 {
 	unsigned int len;
 
-	len = seqhilen;
+	len = extralen;
 
 	len += crypto_aead_ivsize(aead);
 
@@ -57,15 +62,16 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
 	return kmalloc(len, GFP_ATOMIC);
 }
 
-static inline __be32 *esp_tmp_seqhi(void *tmp)
+static inline void *esp_tmp_extra(void *tmp)
 {
-	return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32));
+	return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra));
 }
-static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
+
+static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int extralen)
 {
 	return crypto_aead_ivsize(aead) ?
-	       PTR_ALIGN((u8 *)tmp + seqhilen,
-			 crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
+	       PTR_ALIGN((u8 *)tmp + extralen,
+			 crypto_aead_alignmask(aead) + 1) : tmp + extralen;
 }
 
 static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
@@ -99,7 +105,7 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
 {
 	struct ip_esp_hdr *esph = (void *)(skb->data + offset);
 	void *tmp = ESP_SKB_CB(skb)->tmp;
-	__be32 *seqhi = esp_tmp_seqhi(tmp);
+	__be32 *seqhi = esp_tmp_extra(tmp);
 
 	esph->seq_no = esph->spi;
 	esph->spi = *seqhi;
@@ -107,7 +113,11 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
 
 static void esp_output_restore_header(struct sk_buff *skb)
 {
-	esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
+	void *tmp = ESP_SKB_CB(skb)->tmp;
+	struct esp_output_extra *extra = esp_tmp_extra(tmp);
+
+	esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff -
+				sizeof(__be32));
 }
 
 static void esp_output_done_esn(struct crypto_async_request *base, int err)
@@ -121,6 +131,7 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err)
 static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
+	struct esp_output_extra *extra;
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead;
 	struct aead_request *req;
@@ -137,8 +148,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	int tfclen;
 	int nfrags;
 	int assoclen;
-	int seqhilen;
-	__be32 *seqhi;
+	int extralen;
 	__be64 seqno;
 
 	/* skb is pure payload to encrypt */
@@ -166,21 +176,21 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	nfrags = err;
 
 	assoclen = sizeof(*esph);
-	seqhilen = 0;
+	extralen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		seqhilen += sizeof(__be32);
-		assoclen += seqhilen;
+		extralen += sizeof(*extra);
+		assoclen += sizeof(__be32);
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, extralen);
 	if (!tmp) {
 		err = -ENOMEM;
 		goto error;
 	}
 
-	seqhi = esp_tmp_seqhi(tmp);
-	iv = esp_tmp_iv(aead, tmp, seqhilen);
+	extra = esp_tmp_extra(tmp);
+	iv = esp_tmp_iv(aead, tmp, extralen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
 
@@ -247,8 +257,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	 * encryption.
 	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
-		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
-		*seqhi = esph->spi;
+		extra->esphoff = (unsigned char *)esph -
+				 skb_transport_header(skb);
+		esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
+		extra->seqhi = esph->spi;
 		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
 		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
 	}
@@ -445,7 +457,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 		goto out;
 
 	ESP_SKB_CB(skb)->tmp = tmp;
-	seqhi = esp_tmp_seqhi(tmp);
+	seqhi = esp_tmp_extra(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index f2bda9e89c61..6e9ea69e5f75 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -76,6 +76,7 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp,
 {
 	int err = -EAGAIN;
 	struct fib_table *tbl;
+	u32 tb_id;
 
 	switch (rule->action) {
 	case FR_ACT_TO_TBL:
@@ -94,7 +95,8 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp,
 
 	rcu_read_lock();
 
-	tbl = fib_get_table(rule->fr_net, rule->table);
+	tb_id = fib_rule_get_table(rule, arg);
+	tbl = fib_get_table(rule->fr_net, tb_id);
 	if (tbl)
 		err = fib_table_lookup(tbl, &flp->u.ip4,
 				       (struct fib_result *)arg->result,
@@ -180,7 +182,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	if (err)
 		goto errout;
 
-	if (rule->table == RT_TABLE_UNSPEC) {
+	if (rule->table == RT_TABLE_UNSPEC && !rule->l3mdev) {
 		if (rule->action == FR_ACT_TO_TBL) {
 			struct fib_table *table;
 
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 5f9207c039e7..321d57f825ce 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -129,6 +129,36 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 
 	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
 
+	switch (guehdr->version) {
+	case 0: /* Full GUE header present */
+		break;
+
+	case 1: {
+		/* Direct encasulation of IPv4 or IPv6 */
+
+		int prot;
+
+		switch (((struct iphdr *)guehdr)->version) {
+		case 4:
+			prot = IPPROTO_IPIP;
+			break;
+		case 6:
+			prot = IPPROTO_IPV6;
+			break;
+		default:
+			goto drop;
+		}
+
+		if (fou_recv_pull(skb, fou, sizeof(struct udphdr)))
+			goto drop;
+
+		return -prot;
+	}
+
+	default: /* Undefined version */
+		goto drop;
+	}
+
 	optlen = guehdr->hlen << 2;
 	len += optlen;
 
@@ -289,6 +319,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk,
 	int flush = 1;
 	struct fou *fou = fou_from_sock(sk);
 	struct gro_remcsum grc;
+	u8 proto;
 
 	skb_gro_remcsum_init(&grc);
 
@@ -302,6 +333,25 @@ static struct sk_buff **gue_gro_receive(struct sock *sk,
 			goto out;
 	}
 
+	switch (guehdr->version) {
+	case 0:
+		break;
+	case 1:
+		switch (((struct iphdr *)guehdr)->version) {
+		case 4:
+			proto = IPPROTO_IPIP;
+			break;
+		case 6:
+			proto = IPPROTO_IPV6;
+			break;
+		default:
+			goto out;
+		}
+		goto next_proto;
+	default:
+		goto out;
+	}
+
 	optlen = guehdr->hlen << 2;
 	len += optlen;
 
@@ -370,6 +420,10 @@ static struct sk_buff **gue_gro_receive(struct sock *sk,
 		}
 	}
 
+	proto = guehdr->proto_ctype;
+
+next_proto:
+
 	/* We can clear the encap_mark for GUE as we are essentially doing
 	 * one of two possible things.  We are either adding an L4 tunnel
 	 * header to the outer L3 tunnel header, or we are are simply
@@ -383,7 +437,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk,
 
 	rcu_read_lock();
 	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
-	ops = rcu_dereference(offloads[guehdr->proto_ctype]);
+	ops = rcu_dereference(offloads[proto]);
 	if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive))
 		goto out_unlock;
 
@@ -404,13 +458,30 @@ static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 	const struct net_offload **offloads;
 	struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff);
 	const struct net_offload *ops;
-	unsigned int guehlen;
+	unsigned int guehlen = 0;
 	u8 proto;
 	int err = -ENOENT;
 
-	proto = guehdr->proto_ctype;
-
-	guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
+	switch (guehdr->version) {
+	case 0:
+		proto = guehdr->proto_ctype;
+		guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
+		break;
+	case 1:
+		switch (((struct iphdr *)guehdr)->version) {
+		case 4:
+			proto = IPPROTO_IPIP;
+			break;
+		case 6:
+			proto = IPPROTO_IPV6;
+			break;
+		default:
+			return err;
+		}
+		break;
+	default:
+		return err;
+	}
 
 	rcu_read_lock();
 	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 4c39f4fd332a..b798862b6be5 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -62,26 +62,26 @@ EXPORT_SYMBOL_GPL(gre_del_protocol);
 
 /* Fills in tpi and returns header length to be pulled. */
 int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
-		     bool *csum_err, __be16 proto)
+		     bool *csum_err, __be16 proto, int nhs)
 {
 	const struct gre_base_hdr *greh;
 	__be32 *options;
 	int hdr_len;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr))))
+	if (unlikely(!pskb_may_pull(skb, nhs + sizeof(struct gre_base_hdr))))
 		return -EINVAL;
 
-	greh = (struct gre_base_hdr *)skb_transport_header(skb);
+	greh = (struct gre_base_hdr *)(skb->data + nhs);
 	if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING)))
 		return -EINVAL;
 
 	tpi->flags = gre_flags_to_tnl_flags(greh->flags);
 	hdr_len = gre_calc_hlen(tpi->flags);
 
-	if (!pskb_may_pull(skb, hdr_len))
+	if (!pskb_may_pull(skb, nhs + hdr_len))
 		return -EINVAL;
 
-	greh = (struct gre_base_hdr *)skb_transport_header(skb);
+	greh = (struct gre_base_hdr *)(skb->data + nhs);
 	tpi->proto = greh->protocol;
 
 	options = (__be32 *)(greh + 1);
@@ -117,6 +117,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		if ((*(u8 *)options & 0xF0) != 0x40)
 			hdr_len += 4;
 	}
+	tpi->hdr_len = hdr_len;
 	return hdr_len;
 }
 EXPORT_SYMBOL(gre_parse_header);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 25af1243649b..38c2c47fe0e8 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -44,6 +44,7 @@ struct inet_diag_entry {
 	u16 dport;
 	u16 family;
 	u16 userlocks;
+	u32 ifindex;
 };
 
 static DEFINE_MUTEX(inet_diag_table_mutex);
@@ -571,6 +572,14 @@ static int inet_diag_bc_run(const struct nlattr *_bc,
 			yes = 0;
 			break;
 		}
+		case INET_DIAG_BC_DEV_COND: {
+			u32 ifindex;
+
+			ifindex = *((const u32 *)(op + 1));
+			if (ifindex != entry->ifindex)
+				yes = 0;
+			break;
+		}
 		}
 
 		if (yes) {
@@ -613,6 +622,7 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
 	entry_fill_addrs(&entry, sk);
 	entry.sport = inet->inet_num;
 	entry.dport = ntohs(inet->inet_dport);
+	entry.ifindex = sk->sk_bound_dev_if;
 	entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0;
 
 	return inet_diag_bc_run(bc, &entry);
@@ -636,6 +646,17 @@ static int valid_cc(const void *bc, int len, int cc)
 	return 0;
 }
 
+/* data is u32 ifindex */
+static bool valid_devcond(const struct inet_diag_bc_op *op, int len,
+			  int *min_len)
+{
+	/* Check ifindex space. */
+	*min_len += sizeof(u32);
+	if (len < *min_len)
+		return false;
+
+	return true;
+}
 /* Validate an inet_diag_hostcond. */
 static bool valid_hostcond(const struct inet_diag_bc_op *op, int len,
 			   int *min_len)
@@ -700,6 +721,10 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
 			if (!valid_hostcond(bc, len, &min_len))
 				return -EINVAL;
 			break;
+		case INET_DIAG_BC_DEV_COND:
+			if (!valid_devcond(bc, len, &min_len))
+				return -EINVAL;
+			break;
 		case INET_DIAG_BC_S_GE:
 		case INET_DIAG_BC_S_LE:
 		case INET_DIAG_BC_D_GE:
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 4d2025f7ec57..5b1481be0282 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -49,12 +49,6 @@
 #include <net/gre.h>
 #include <net/dst_metadata.h>
 
-#if IS_ENABLED(CONFIG_IPV6)
-#include <net/ipv6.h>
-#include <net/ip6_fib.h>
-#include <net/ip6_route.h>
-#endif
-
 /*
    Problems & solutions
    --------------------
@@ -144,6 +138,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info,
 	const struct iphdr *iph;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	unsigned int data_len = 0;
 	struct ip_tunnel *t;
 
 	switch (type) {
@@ -169,6 +164,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info,
 	case ICMP_TIME_EXCEEDED:
 		if (code != ICMP_EXC_TTL)
 			return;
+		data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
 		break;
 
 	case ICMP_REDIRECT:
@@ -187,6 +183,13 @@ static void ipgre_err(struct sk_buff *skb, u32 info,
 	if (!t)
 		return;
 
+#if IS_ENABLED(CONFIG_IPV6)
+       if (tpi->proto == htons(ETH_P_IPV6) &&
+           !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
+				       type, data_len))
+               return;
+#endif
+
 	if (t->parms.iph.daddr == 0 ||
 	    ipv4_is_multicast(t->parms.iph.daddr))
 		return;
@@ -217,12 +220,14 @@ static void gre_err(struct sk_buff *skb, u32 info)
 	 * by themselves???
 	 */
 
+	const struct iphdr *iph = (struct iphdr *)skb->data;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
 	struct tnl_ptk_info tpi;
 	bool csum_err = false;
 
-	if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP)) < 0) {
+	if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP),
+			     iph->ihl * 4) < 0) {
 		if (!csum_err)		/* ignore csum errors. */
 			return;
 	}
@@ -338,7 +343,7 @@ static int gre_rcv(struct sk_buff *skb)
 	}
 #endif
 
-	hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP));
+	hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), 0);
 	if (hdr_len < 0)
 		goto drop;
 
@@ -841,17 +846,19 @@ out:
 	return ipgre_tunnel_validate(tb, data);
 }
 
-static void ipgre_netlink_parms(struct net_device *dev,
+static int ipgre_netlink_parms(struct net_device *dev,
 				struct nlattr *data[],
 				struct nlattr *tb[],
 				struct ip_tunnel_parm *parms)
 {
+	struct ip_tunnel *t = netdev_priv(dev);
+
 	memset(parms, 0, sizeof(*parms));
 
 	parms->iph.protocol = IPPROTO_GRE;
 
 	if (!data)
-		return;
+		return 0;
 
 	if (data[IFLA_GRE_LINK])
 		parms->link = nla_get_u32(data[IFLA_GRE_LINK]);
@@ -880,16 +887,26 @@ static void ipgre_netlink_parms(struct net_device *dev,
 	if (data[IFLA_GRE_TOS])
 		parms->iph.tos = nla_get_u8(data[IFLA_GRE_TOS]);
 
-	if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC]))
+	if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC])) {
+		if (t->ignore_df)
+			return -EINVAL;
 		parms->iph.frag_off = htons(IP_DF);
+	}
 
 	if (data[IFLA_GRE_COLLECT_METADATA]) {
-		struct ip_tunnel *t = netdev_priv(dev);
-
 		t->collect_md = true;
 		if (dev->type == ARPHRD_IPGRE)
 			dev->type = ARPHRD_NONE;
 	}
+
+	if (data[IFLA_GRE_IGNORE_DF]) {
+		if (nla_get_u8(data[IFLA_GRE_IGNORE_DF])
+		  && (parms->iph.frag_off & htons(IP_DF)))
+			return -EINVAL;
+		t->ignore_df = !!nla_get_u8(data[IFLA_GRE_IGNORE_DF]);
+	}
+
+	return 0;
 }
 
 /* This function returns true when ENCAP attributes are present in the nl msg */
@@ -960,16 +977,19 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev,
 {
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
+	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
 		struct ip_tunnel *t = netdev_priv(dev);
-		int err = ip_tunnel_encap_setup(t, &ipencap);
+		err = ip_tunnel_encap_setup(t, &ipencap);
 
 		if (err < 0)
 			return err;
 	}
 
-	ipgre_netlink_parms(dev, data, tb, &p);
+	err = ipgre_netlink_parms(dev, data, tb, &p);
+	if (err < 0)
+		return err;
 	return ip_tunnel_newlink(dev, tb, &p);
 }
 
@@ -978,16 +998,19 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 {
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
+	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
 		struct ip_tunnel *t = netdev_priv(dev);
-		int err = ip_tunnel_encap_setup(t, &ipencap);
+		err = ip_tunnel_encap_setup(t, &ipencap);
 
 		if (err < 0)
 			return err;
 	}
 
-	ipgre_netlink_parms(dev, data, tb, &p);
+	err = ipgre_netlink_parms(dev, data, tb, &p);
+	if (err < 0)
+		return err;
 	return ip_tunnel_changelink(dev, tb, &p);
 }
 
@@ -1024,6 +1047,8 @@ static size_t ipgre_get_size(const struct net_device *dev)
 		nla_total_size(2) +
 		/* IFLA_GRE_COLLECT_METADATA */
 		nla_total_size(0) +
+		/* IFLA_GRE_IGNORE_DF */
+		nla_total_size(1) +
 		0;
 }
 
@@ -1057,6 +1082,9 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			t->encap.flags))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_GRE_IGNORE_DF, t->ignore_df))
+		goto nla_put_failure;
+
 	if (t->collect_md) {
 		if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA))
 			goto nla_put_failure;
@@ -1084,6 +1112,7 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
 	[IFLA_GRE_ENCAP_SPORT]	= { .type = NLA_U16 },
 	[IFLA_GRE_ENCAP_DPORT]	= { .type = NLA_U16 },
 	[IFLA_GRE_COLLECT_METADATA]	= { .type = NLA_FLAG },
+	[IFLA_GRE_IGNORE_DF]	= { .type = NLA_U8 },
 };
 
 static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
@@ -1121,6 +1150,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 {
 	struct nlattr *tb[IFLA_MAX + 1];
 	struct net_device *dev;
+	LIST_HEAD(list_kill);
 	struct ip_tunnel *t;
 	int err;
 
@@ -1136,8 +1166,10 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	t->collect_md = true;
 
 	err = ipgre_newlink(net, dev, tb, NULL);
-	if (err < 0)
-		goto out;
+	if (err < 0) {
+		free_netdev(dev);
+		return ERR_PTR(err);
+	}
 
 	/* openvswitch users expect packet sizes to be unrestricted,
 	 * so set the largest MTU we can.
@@ -1146,9 +1178,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	if (err)
 		goto out;
 
+	err = rtnl_configure_link(dev, NULL);
+	if (err < 0)
+		goto out;
+
 	return dev;
 out:
-	free_netdev(dev);
+	ip_tunnel_dellink(dev, &list_kill);
+	unregister_netdevice_many(&list_kill);
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(gretap_fb_dev_create);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index d8f5e0a269f5..95649ebd2874 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -682,7 +682,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	df = tnl_params->frag_off;
-	if (skb->protocol == htons(ETH_P_IP))
+	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
 		df |= (inner_iph->frag_off&htons(IP_DF));
 
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 2ed9dd2b5f2f..1d71c40eaaf3 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -127,7 +127,9 @@ __be32 ic_myaddr = NONE;		/* My IP address */
 static __be32 ic_netmask = NONE;	/* Netmask for local subnet */
 __be32 ic_gateway = NONE;	/* Gateway IP address */
 
-__be32 ic_addrservaddr = NONE;	/* IP Address of the IP addresses'server */
+#ifdef IPCONFIG_DYNAMIC
+static __be32 ic_addrservaddr = NONE;	/* IP Address of the IP addresses'server */
+#endif
 
 __be32 ic_servaddr = NONE;	/* Boot server IP address */
 
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 21a38e296fe2..5ad48ec77710 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -891,8 +891,10 @@ static struct mfc_cache *ipmr_cache_alloc(void)
 {
 	struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
 
-	if (c)
+	if (c) {
+		c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 		c->mfc_un.res.minvif = MAXVIFS;
+	}
 	return c;
 }
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5c7ed147449c..032a96d78c99 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2277,6 +2277,38 @@ static inline bool tcp_can_repair_sock(const struct sock *sk)
 		((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED));
 }
 
+static int tcp_repair_set_window(struct tcp_sock *tp, char __user *optbuf, int len)
+{
+	struct tcp_repair_window opt;
+
+	if (!tp->repair)
+		return -EPERM;
+
+	if (len != sizeof(opt))
+		return -EINVAL;
+
+	if (copy_from_user(&opt, optbuf, sizeof(opt)))
+		return -EFAULT;
+
+	if (opt.max_window < opt.snd_wnd)
+		return -EINVAL;
+
+	if (after(opt.snd_wl1, tp->rcv_nxt + opt.rcv_wnd))
+		return -EINVAL;
+
+	if (after(opt.rcv_wup, tp->rcv_nxt))
+		return -EINVAL;
+
+	tp->snd_wl1	= opt.snd_wl1;
+	tp->snd_wnd	= opt.snd_wnd;
+	tp->max_window	= opt.max_window;
+
+	tp->rcv_wnd	= opt.rcv_wnd;
+	tp->rcv_wup	= opt.rcv_wup;
+
+	return 0;
+}
+
 static int tcp_repair_options_est(struct tcp_sock *tp,
 		struct tcp_repair_opt __user *optbuf, unsigned int len)
 {
@@ -2604,6 +2636,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		else
 			tp->tsoffset = val - tcp_time_stamp;
 		break;
+	case TCP_REPAIR_WINDOW:
+		err = tcp_repair_set_window(tp, optval, optlen);
+		break;
 	case TCP_NOTSENT_LOWAT:
 		tp->notsent_lowat = val;
 		sk->sk_write_space(sk);
@@ -2860,6 +2895,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			return -EINVAL;
 		break;
 
+	case TCP_REPAIR_WINDOW: {
+		struct tcp_repair_window opt;
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		if (len != sizeof(opt))
+			return -EINVAL;
+
+		if (!tp->repair)
+			return -EPERM;
+
+		opt.snd_wl1	= tp->snd_wl1;
+		opt.snd_wnd	= tp->snd_wnd;
+		opt.max_window	= tp->max_window;
+		opt.rcv_wnd	= tp->rcv_wnd;
+		opt.rcv_wup	= tp->rcv_wup;
+
+		if (copy_to_user(optval, &opt, len))
+			return -EFAULT;
+		return 0;
+	}
 	case TCP_QUEUE_SEQ:
 		if (tp->repair_queue == TCP_SEND_QUEUE)
 			val = tp->write_seq;
@@ -2969,8 +3026,18 @@ static void __tcp_alloc_md5sig_pool(void)
 		return;
 
 	for_each_possible_cpu(cpu) {
+		void *scratch = per_cpu(tcp_md5sig_pool, cpu).scratch;
 		struct ahash_request *req;
 
+		if (!scratch) {
+			scratch = kmalloc_node(sizeof(union tcp_md5sum_block) +
+					       sizeof(struct tcphdr),
+					       GFP_KERNEL,
+					       cpu_to_node(cpu));
+			if (!scratch)
+				return;
+			per_cpu(tcp_md5sig_pool, cpu).scratch = scratch;
+		}
 		if (per_cpu(tcp_md5sig_pool, cpu).md5_req)
 			continue;
 
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 7e538f71f5fb..10d728b6804c 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -293,7 +293,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
 	 */
 	if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) ||
 	    ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
-		memset(info, 0, sizeof(struct tcp_dctcp_info));
+		memset(&info->dctcp, 0, sizeof(info->dctcp));
 		if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) {
 			info->dctcp.dctcp_enabled = 1;
 			info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
@@ -303,7 +303,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
 		}
 
 		*attr = INET_DIAG_DCTCPINFO;
-		return sizeof(*info);
+		return sizeof(info->dctcp);
 	}
 	return 0;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d6c8f4cd0800..94d4aff97523 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3115,6 +3115,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 	long ca_rtt_us = -1L;
 	struct sk_buff *skb;
 	u32 pkts_acked = 0;
+	u32 last_in_flight = 0;
 	bool rtt_update;
 	int flag = 0;
 
@@ -3154,6 +3155,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			if (!first_ackt.v64)
 				first_ackt = last_ackt;
 
+			last_in_flight = TCP_SKB_CB(skb)->tx.in_flight;
 			reord = min(pkts_acked, reord);
 			if (!after(scb->end_seq, tp->high_seq))
 				flag |= FLAG_ORIG_SACK_ACKED;
@@ -3250,7 +3252,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 
 	if (icsk->icsk_ca_ops->pkts_acked) {
 		struct ack_sample sample = { .pkts_acked = pkts_acked,
-					     .rtt_us = ca_rtt_us };
+					     .rtt_us = ca_rtt_us,
+					     .in_flight = last_in_flight };
 
 		icsk->icsk_ca_ops->pkts_acked(sk, &sample);
 	}
@@ -5159,6 +5162,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 				  const struct tcphdr *th, int syn_inerr)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	bool rst_seq_match = false;
 
 	/* RFC1323: H1. Apply PAWS check first. */
 	if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp &&
@@ -5195,13 +5199,32 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 
 	/* Step 2: check RST bit */
 	if (th->rst) {
-		/* RFC 5961 3.2 :
-		 * If sequence number exactly matches RCV.NXT, then
+		/* RFC 5961 3.2 (extend to match against SACK too if available):
+		 * If seq num matches RCV.NXT or the right-most SACK block,
+		 * then
 		 *     RESET the connection
 		 * else
 		 *     Send a challenge ACK
 		 */
-		if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt)
+		if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
+			rst_seq_match = true;
+		} else if (tcp_is_sack(tp) && tp->rx_opt.num_sacks > 0) {
+			struct tcp_sack_block *sp = &tp->selective_acks[0];
+			int max_sack = sp[0].end_seq;
+			int this_sack;
+
+			for (this_sack = 1; this_sack < tp->rx_opt.num_sacks;
+			     ++this_sack) {
+				max_sack = after(sp[this_sack].end_seq,
+						 max_sack) ?
+					sp[this_sack].end_seq : max_sack;
+			}
+
+			if (TCP_SKB_CB(skb)->seq == max_sack)
+				rst_seq_match = true;
+		}
+
+		if (rst_seq_match)
 			tcp_reset(sk);
 		else
 			tcp_send_challenge_ack(sk, skb);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3708de2a6683..32b048e524d6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1018,27 +1018,28 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
 			      GFP_KERNEL);
 }
 
-static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
-					__be32 daddr, __be32 saddr, int nbytes)
+static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp,
+				   __be32 daddr, __be32 saddr,
+				   const struct tcphdr *th, int nbytes)
 {
 	struct tcp4_pseudohdr *bp;
 	struct scatterlist sg;
+	struct tcphdr *_th;
 
-	bp = &hp->md5_blk.ip4;
-
-	/*
-	 * 1. the TCP pseudo-header (in the order: source IP address,
-	 * destination IP address, zero-padded protocol number, and
-	 * segment length)
-	 */
+	bp = hp->scratch;
 	bp->saddr = saddr;
 	bp->daddr = daddr;
 	bp->pad = 0;
 	bp->protocol = IPPROTO_TCP;
 	bp->len = cpu_to_be16(nbytes);
 
-	sg_init_one(&sg, bp, sizeof(*bp));
-	ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(*bp));
+	_th = (struct tcphdr *)(bp + 1);
+	memcpy(_th, th, sizeof(*th));
+	_th->check = 0;
+
+	sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th));
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL,
+				sizeof(*bp) + sizeof(*th));
 	return crypto_ahash_update(hp->md5_req);
 }
 
@@ -1055,9 +1056,7 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 
 	if (crypto_ahash_init(req))
 		goto clear_hash;
-	if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2))
-		goto clear_hash;
-	if (tcp_md5_hash_header(hp, th))
+	if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2))
 		goto clear_hash;
 	if (tcp_md5_hash_key(hp, key))
 		goto clear_hash;
@@ -1101,9 +1100,7 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
 	if (crypto_ahash_init(req))
 		goto clear_hash;
 
-	if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, skb->len))
-		goto clear_hash;
-	if (tcp_md5_hash_header(hp, th))
+	if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, skb->len))
 		goto clear_hash;
 	if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
 		goto clear_hash;
diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
new file mode 100644
index 000000000000..5de82a8d4d87
--- /dev/null
+++ b/net/ipv4/tcp_nv.c
@@ -0,0 +1,476 @@
+/*
+ * TCP NV: TCP with Congestion Avoidance
+ *
+ * TCP-NV is a successor of TCP-Vegas that has been developed to
+ * deal with the issues that occur in modern networks.
+ * Like TCP-Vegas, TCP-NV supports true congestion avoidance,
+ * the ability to detect congestion before packet losses occur.
+ * When congestion (queue buildup) starts to occur, TCP-NV
+ * predicts what the cwnd size should be for the current
+ * throughput and it reduces the cwnd proportionally to
+ * the difference between the current cwnd and the predicted cwnd.
+ *
+ * NV is only recommeneded for traffic within a data center, and when
+ * all the flows are NV (at least those within the data center). This
+ * is due to the inherent unfairness between flows using losses to
+ * detect congestion (congestion control) and those that use queue
+ * buildup to detect congestion (congestion avoidance).
+ *
+ * Note: High NIC coalescence values may lower the performance of NV
+ * due to the increased noise in RTT values. In particular, we have
+ * seen issues with rx-frames values greater than 8.
+ *
+ * TODO:
+ * 1) Add mechanism to deal with reverse congestion.
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/math64.h>
+#include <net/tcp.h>
+#include <linux/inet_diag.h>
+
+/* TCP NV parameters
+ *
+ * nv_pad		Max number of queued packets allowed in network
+ * nv_pad_buffer	Do not grow cwnd if this closed to nv_pad
+ * nv_reset_period	How often (in) seconds)to reset min_rtt
+ * nv_min_cwnd		Don't decrease cwnd below this if there are no losses
+ * nv_cong_dec_mult	Decrease cwnd by X% (30%) of congestion when detected
+ * nv_ssthresh_factor	On congestion set ssthresh to this * <desired cwnd> / 8
+ * nv_rtt_factor	RTT averaging factor
+ * nv_loss_dec_factor	Decrease cwnd by this (50%) when losses occur
+ * nv_dec_eval_min_calls	Wait this many RTT measurements before dec cwnd
+ * nv_inc_eval_min_calls	Wait this many RTT measurements before inc cwnd
+ * nv_ssthresh_eval_min_calls	Wait this many RTT measurements before stopping
+ *				slow-start due to congestion
+ * nv_stop_rtt_cnt	Only grow cwnd for this many RTTs after non-congestion
+ * nv_rtt_min_cnt	Wait these many RTTs before making congesion decision
+ * nv_cwnd_growth_rate_neg
+ * nv_cwnd_growth_rate_pos
+ *	How quickly to double growth rate (not rate) of cwnd when not
+ *	congested. One value (nv_cwnd_growth_rate_neg) for when
+ *	rate < 1 pkt/RTT (after losses). The other (nv_cwnd_growth_rate_pos)
+ *	otherwise.
+ */
+
+static int nv_pad __read_mostly = 10;
+static int nv_pad_buffer __read_mostly = 2;
+static int nv_reset_period __read_mostly = 5; /* in seconds */
+static int nv_min_cwnd __read_mostly = 2;
+static int nv_cong_dec_mult __read_mostly = 30 * 128 / 100; /* = 30% */
+static int nv_ssthresh_factor __read_mostly = 8; /* = 1 */
+static int nv_rtt_factor __read_mostly = 128; /* = 1/2*old + 1/2*new */
+static int nv_loss_dec_factor __read_mostly = 512; /* => 50% */
+static int nv_cwnd_growth_rate_neg __read_mostly = 8;
+static int nv_cwnd_growth_rate_pos __read_mostly; /* 0 => fixed like Reno */
+static int nv_dec_eval_min_calls __read_mostly = 60;
+static int nv_inc_eval_min_calls __read_mostly = 20;
+static int nv_ssthresh_eval_min_calls __read_mostly = 30;
+static int nv_stop_rtt_cnt __read_mostly = 10;
+static int nv_rtt_min_cnt __read_mostly = 2;
+
+module_param(nv_pad, int, 0644);
+MODULE_PARM_DESC(nv_pad, "max queued packets allowed in network");
+module_param(nv_reset_period, int, 0644);
+MODULE_PARM_DESC(nv_reset_period, "nv_min_rtt reset period (secs)");
+module_param(nv_min_cwnd, int, 0644);
+MODULE_PARM_DESC(nv_min_cwnd, "NV will not decrease cwnd below this value"
+		 " without losses");
+
+/* TCP NV Parameters */
+struct tcpnv {
+	unsigned long nv_min_rtt_reset_jiffies;  /* when to switch to
+						  * nv_min_rtt_new */
+	s8  cwnd_growth_factor;	/* Current cwnd growth factor,
+				 * < 0 => less than 1 packet/RTT */
+	u8  available8;
+	u16 available16;
+	u32 loss_cwnd;	/* cwnd at last loss */
+	u8  nv_allow_cwnd_growth:1, /* whether cwnd can grow */
+		nv_reset:1,	    /* whether to reset values */
+		nv_catchup:1;	    /* whether we are growing because
+				     * of temporary cwnd decrease */
+	u8  nv_eval_call_cnt;	/* call count since last eval */
+	u8  nv_min_cwnd;	/* nv won't make a ca decision if cwnd is
+				 * smaller than this. It may grow to handle
+				 * TSO, LRO and interrupt coalescence because
+				 * with these a small cwnd cannot saturate
+				 * the link. Note that this is different from
+				 * the file local nv_min_cwnd */
+	u8  nv_rtt_cnt;		/* RTTs without making ca decision */;
+	u32 nv_last_rtt;	/* last rtt */
+	u32 nv_min_rtt;		/* active min rtt. Used to determine slope */
+	u32 nv_min_rtt_new;	/* min rtt for future use */
+	u32 nv_rtt_max_rate;	/* max rate seen during current RTT */
+	u32 nv_rtt_start_seq;	/* current RTT ends when packet arrives
+				 * acking beyond nv_rtt_start_seq */
+	u32 nv_last_snd_una;	/* Previous value of tp->snd_una. It is
+				 * used to determine bytes acked since last
+				 * call to bictcp_acked */
+	u32 nv_no_cong_cnt;	/* Consecutive no congestion decisions */
+};
+
+#define NV_INIT_RTT	  U32_MAX
+#define NV_MIN_CWND	  4
+#define NV_MIN_CWND_GROW  2
+#define NV_TSO_CWND_BOUND 80
+
+static inline void tcpnv_reset(struct tcpnv *ca, struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	ca->nv_reset = 0;
+	ca->loss_cwnd = 0;
+	ca->nv_no_cong_cnt = 0;
+	ca->nv_rtt_cnt = 0;
+	ca->nv_last_rtt = 0;
+	ca->nv_rtt_max_rate = 0;
+	ca->nv_rtt_start_seq = tp->snd_una;
+	ca->nv_eval_call_cnt = 0;
+	ca->nv_last_snd_una = tp->snd_una;
+}
+
+static void tcpnv_init(struct sock *sk)
+{
+	struct tcpnv *ca = inet_csk_ca(sk);
+
+	tcpnv_reset(ca, sk);
+
+	ca->nv_allow_cwnd_growth = 1;
+	ca->nv_min_rtt_reset_jiffies = jiffies + 2 * HZ;
+	ca->nv_min_rtt = NV_INIT_RTT;
+	ca->nv_min_rtt_new = NV_INIT_RTT;
+	ca->nv_min_cwnd = NV_MIN_CWND;
+	ca->nv_catchup = 0;
+	ca->cwnd_growth_factor = 0;
+}
+
+static void tcpnv_cong_avoid(struct sock *sk, u32 ack, u32 acked)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct tcpnv *ca = inet_csk_ca(sk);
+	u32 cnt;
+
+	if (!tcp_is_cwnd_limited(sk))
+		return;
+
+	/* Only grow cwnd if NV has not detected congestion */
+	if (!ca->nv_allow_cwnd_growth)
+		return;
+
+	if (tcp_in_slow_start(tp)) {
+		acked = tcp_slow_start(tp, acked);
+		if (!acked)
+			return;
+	}
+
+	if (ca->cwnd_growth_factor < 0) {
+		cnt = tp->snd_cwnd << -ca->cwnd_growth_factor;
+		tcp_cong_avoid_ai(tp, cnt, acked);
+	} else {
+		cnt = max(4U, tp->snd_cwnd >> ca->cwnd_growth_factor);
+		tcp_cong_avoid_ai(tp, cnt, acked);
+	}
+}
+
+static u32 tcpnv_recalc_ssthresh(struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	struct tcpnv *ca = inet_csk_ca(sk);
+
+	ca->loss_cwnd = tp->snd_cwnd;
+	return max((tp->snd_cwnd * nv_loss_dec_factor) >> 10, 2U);
+}
+
+static u32 tcpnv_undo_cwnd(struct sock *sk)
+{
+	struct tcpnv *ca = inet_csk_ca(sk);
+
+	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
+static void tcpnv_state(struct sock *sk, u8 new_state)
+{
+	struct tcpnv *ca = inet_csk_ca(sk);
+
+	if (new_state == TCP_CA_Open && ca->nv_reset) {
+		tcpnv_reset(ca, sk);
+	} else if (new_state == TCP_CA_Loss || new_state == TCP_CA_CWR ||
+		new_state == TCP_CA_Recovery) {
+		ca->nv_reset = 1;
+		ca->nv_allow_cwnd_growth = 0;
+		if (new_state == TCP_CA_Loss) {
+			/* Reset cwnd growth factor to Reno value */
+			if (ca->cwnd_growth_factor > 0)
+				ca->cwnd_growth_factor = 0;
+			/* Decrease growth rate if allowed */
+			if (nv_cwnd_growth_rate_neg > 0 &&
+			    ca->cwnd_growth_factor > -8)
+				ca->cwnd_growth_factor--;
+		}
+	}
+}
+
+/* Do congestion avoidance calculations for TCP-NV
+ */
+static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct tcpnv *ca = inet_csk_ca(sk);
+	unsigned long now = jiffies;
+	s64 rate64 = 0;
+	u32 rate, max_win, cwnd_by_slope;
+	u32 avg_rtt;
+	u32 bytes_acked = 0;
+
+	/* Some calls are for duplicates without timetamps */
+	if (sample->rtt_us < 0)
+		return;
+
+	/* If not in TCP_CA_Open or TCP_CA_Disorder states, skip. */
+	if (icsk->icsk_ca_state != TCP_CA_Open &&
+	    icsk->icsk_ca_state != TCP_CA_Disorder)
+		return;
+
+	/* Stop cwnd growth if we were in catch up mode */
+	if (ca->nv_catchup && tp->snd_cwnd >= nv_min_cwnd) {
+		ca->nv_catchup = 0;
+		ca->nv_allow_cwnd_growth = 0;
+	}
+
+	bytes_acked = tp->snd_una - ca->nv_last_snd_una;
+	ca->nv_last_snd_una = tp->snd_una;
+
+	if (sample->in_flight == 0)
+		return;
+
+	/* Calculate moving average of RTT */
+	if (nv_rtt_factor > 0) {
+		if (ca->nv_last_rtt > 0) {
+			avg_rtt = (((u64)sample->rtt_us) * nv_rtt_factor +
+				   ((u64)ca->nv_last_rtt)
+				   * (256 - nv_rtt_factor)) >> 8;
+		} else {
+			avg_rtt = sample->rtt_us;
+			ca->nv_min_rtt = avg_rtt << 1;
+		}
+		ca->nv_last_rtt = avg_rtt;
+	} else {
+		avg_rtt = sample->rtt_us;
+	}
+
+	/* rate in 100's bits per second */
+	rate64 = ((u64)sample->in_flight) * 8000000;
+	rate = (u32)div64_u64(rate64, (u64)(avg_rtt * 100));
+
+	/* Remember the maximum rate seen during this RTT
+	 * Note: It may be more than one RTT. This function should be
+	 *       called at least nv_dec_eval_min_calls times.
+	 */
+	if (ca->nv_rtt_max_rate < rate)
+		ca->nv_rtt_max_rate = rate;
+
+	/* We have valid information, increment counter */
+	if (ca->nv_eval_call_cnt < 255)
+		ca->nv_eval_call_cnt++;
+
+	/* update min rtt if necessary */
+	if (avg_rtt < ca->nv_min_rtt)
+		ca->nv_min_rtt = avg_rtt;
+
+	/* update future min_rtt if necessary */
+	if (avg_rtt < ca->nv_min_rtt_new)
+		ca->nv_min_rtt_new = avg_rtt;
+
+	/* nv_min_rtt is updated with the minimum (possibley averaged) rtt
+	 * seen in the last sysctl_tcp_nv_reset_period seconds (i.e. a
+	 * warm reset). This new nv_min_rtt will be continued to be updated
+	 * and be used for another sysctl_tcp_nv_reset_period seconds,
+	 * when it will be updated again.
+	 * In practice we introduce some randomness, so the actual period used
+	 * is chosen randomly from the range:
+	 *   [sysctl_tcp_nv_reset_period*3/4, sysctl_tcp_nv_reset_period*5/4)
+	 */
+	if (time_after_eq(now, ca->nv_min_rtt_reset_jiffies)) {
+		unsigned char rand;
+
+		ca->nv_min_rtt = ca->nv_min_rtt_new;
+		ca->nv_min_rtt_new = NV_INIT_RTT;
+		get_random_bytes(&rand, 1);
+		ca->nv_min_rtt_reset_jiffies =
+			now + ((nv_reset_period * (384 + rand) * HZ) >> 9);
+		/* Every so often we decrease ca->nv_min_cwnd in case previous
+		 *  value is no longer accurate.
+		 */
+		ca->nv_min_cwnd = max(ca->nv_min_cwnd / 2, NV_MIN_CWND);
+	}
+
+	/* Once per RTT check if we need to do congestion avoidance */
+	if (before(ca->nv_rtt_start_seq, tp->snd_una)) {
+		ca->nv_rtt_start_seq = tp->snd_nxt;
+		if (ca->nv_rtt_cnt < 0xff)
+			/* Increase counter for RTTs without CA decision */
+			ca->nv_rtt_cnt++;
+
+		/* If this function is only called once within an RTT
+		 * the cwnd is probably too small (in some cases due to
+		 * tso, lro or interrupt coalescence), so we increase
+		 * ca->nv_min_cwnd.
+		 */
+		if (ca->nv_eval_call_cnt == 1 &&
+		    bytes_acked >= (ca->nv_min_cwnd - 1) * tp->mss_cache &&
+		    ca->nv_min_cwnd < (NV_TSO_CWND_BOUND + 1)) {
+			ca->nv_min_cwnd = min(ca->nv_min_cwnd
+					      + NV_MIN_CWND_GROW,
+					      NV_TSO_CWND_BOUND + 1);
+			ca->nv_rtt_start_seq = tp->snd_nxt +
+				ca->nv_min_cwnd * tp->mss_cache;
+			ca->nv_eval_call_cnt = 0;
+			ca->nv_allow_cwnd_growth = 1;
+			return;
+		}
+
+		/* Find the ideal cwnd for current rate from slope
+		 * slope = 80000.0 * mss / nv_min_rtt
+		 * cwnd_by_slope = nv_rtt_max_rate / slope
+		 */
+		cwnd_by_slope = (u32)
+			div64_u64(((u64)ca->nv_rtt_max_rate) * ca->nv_min_rtt,
+				  (u64)(80000 * tp->mss_cache));
+		max_win = cwnd_by_slope + nv_pad;
+
+		/* If cwnd > max_win, decrease cwnd
+		 * if cwnd < max_win, grow cwnd
+		 * else leave the same
+		 */
+		if (tp->snd_cwnd > max_win) {
+			/* there is congestion, check that it is ok
+			 * to make a CA decision
+			 * 1. We should have at least nv_dec_eval_min_calls
+			 *    data points before making a CA  decision
+			 * 2. We only make a congesion decision after
+			 *    nv_rtt_min_cnt RTTs
+			 */
+			if (ca->nv_rtt_cnt < nv_rtt_min_cnt) {
+				return;
+			} else if (tp->snd_ssthresh == TCP_INFINITE_SSTHRESH) {
+				if (ca->nv_eval_call_cnt <
+				    nv_ssthresh_eval_min_calls)
+					return;
+				/* otherwise we will decrease cwnd */
+			} else if (ca->nv_eval_call_cnt <
+				   nv_dec_eval_min_calls) {
+				if (ca->nv_allow_cwnd_growth &&
+				    ca->nv_rtt_cnt > nv_stop_rtt_cnt)
+					ca->nv_allow_cwnd_growth = 0;
+				return;
+			}
+
+			/* We have enough data to determine we are congested */
+			ca->nv_allow_cwnd_growth = 0;
+			tp->snd_ssthresh =
+				(nv_ssthresh_factor * max_win) >> 3;
+			if (tp->snd_cwnd - max_win > 2) {
+				/* gap > 2, we do exponential cwnd decrease */
+				int dec;
+
+				dec = max(2U, ((tp->snd_cwnd - max_win) *
+					       nv_cong_dec_mult) >> 7);
+				tp->snd_cwnd -= dec;
+			} else if (nv_cong_dec_mult > 0) {
+				tp->snd_cwnd = max_win;
+			}
+			if (ca->cwnd_growth_factor > 0)
+				ca->cwnd_growth_factor = 0;
+			ca->nv_no_cong_cnt = 0;
+		} else if (tp->snd_cwnd <= max_win - nv_pad_buffer) {
+			/* There is no congestion, grow cwnd if allowed*/
+			if (ca->nv_eval_call_cnt < nv_inc_eval_min_calls)
+				return;
+
+			ca->nv_allow_cwnd_growth = 1;
+			ca->nv_no_cong_cnt++;
+			if (ca->cwnd_growth_factor < 0 &&
+			    nv_cwnd_growth_rate_neg > 0 &&
+			    ca->nv_no_cong_cnt > nv_cwnd_growth_rate_neg) {
+				ca->cwnd_growth_factor++;
+				ca->nv_no_cong_cnt = 0;
+			} else if (ca->cwnd_growth_factor >= 0 &&
+				   nv_cwnd_growth_rate_pos > 0 &&
+				   ca->nv_no_cong_cnt >
+				   nv_cwnd_growth_rate_pos) {
+				ca->cwnd_growth_factor++;
+				ca->nv_no_cong_cnt = 0;
+			}
+		} else {
+			/* cwnd is in-between, so do nothing */
+			return;
+		}
+
+		/* update state */
+		ca->nv_eval_call_cnt = 0;
+		ca->nv_rtt_cnt = 0;
+		ca->nv_rtt_max_rate = 0;
+
+		/* Don't want to make cwnd < nv_min_cwnd
+		 * (it wasn't before, if it is now is because nv
+		 *  decreased it).
+		 */
+		if (tp->snd_cwnd < nv_min_cwnd)
+			tp->snd_cwnd = nv_min_cwnd;
+	}
+}
+
+/* Extract info for Tcp socket info provided via netlink */
+size_t tcpnv_get_info(struct sock *sk, u32 ext, int *attr,
+		      union tcp_cc_info *info)
+{
+	const struct tcpnv *ca = inet_csk_ca(sk);
+
+	if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
+		info->vegas.tcpv_enabled = 1;
+		info->vegas.tcpv_rttcnt = ca->nv_rtt_cnt;
+		info->vegas.tcpv_rtt = ca->nv_last_rtt;
+		info->vegas.tcpv_minrtt = ca->nv_min_rtt;
+
+		*attr = INET_DIAG_VEGASINFO;
+		return sizeof(struct tcpvegas_info);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tcpnv_get_info);
+
+static struct tcp_congestion_ops tcpnv __read_mostly = {
+	.init		= tcpnv_init,
+	.ssthresh	= tcpnv_recalc_ssthresh,
+	.cong_avoid	= tcpnv_cong_avoid,
+	.set_state	= tcpnv_state,
+	.undo_cwnd	= tcpnv_undo_cwnd,
+	.pkts_acked     = tcpnv_acked,
+	.get_info	= tcpnv_get_info,
+
+	.owner		= THIS_MODULE,
+	.name		= "nv",
+};
+
+static int __init tcpnv_register(void)
+{
+	BUILD_BUG_ON(sizeof(struct tcpnv) > ICSK_CA_PRIV_SIZE);
+
+	return tcp_register_congestion_control(&tcpnv);
+}
+
+static void __exit tcpnv_unregister(void)
+{
+	tcp_unregister_congestion_control(&tcpnv);
+}
+
+module_init(tcpnv_register);
+module_exit(tcpnv_unregister);
+
+MODULE_AUTHOR("Lawrence Brakmo");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("TCP NV");
+MODULE_VERSION("1.0");
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8bd9911fdd16..b26aa870adc0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -911,9 +911,12 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	int err;
 
 	BUG_ON(!skb || !tcp_skb_pcount(skb));
+	tp = tcp_sk(sk);
 
 	if (clone_it) {
 		skb_mstamp_get(&skb->skb_mstamp);
+		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
+			- tp->snd_una;
 
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
@@ -924,7 +927,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	}
 
 	inet = inet_sk(sk);
-	tp = tcp_sk(sk);
 	tcb = TCP_SKB_CB(skb);
 	memset(&opts, 0, sizeof(opts));
 
@@ -2751,7 +2753,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	struct sk_buff *hole = NULL;
-	u32 last_lost;
+	u32 max_segs, last_lost;
 	int mib_idx;
 	int fwd_rexmitting = 0;
 
@@ -2771,6 +2773,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		last_lost = tp->snd_una;
 	}
 
+	max_segs = tcp_tso_autosize(sk, tcp_current_mss(sk));
 	tcp_for_write_queue_from(skb, sk) {
 		__u8 sacked = TCP_SKB_CB(skb)->sacked;
 		int segs;
@@ -2784,6 +2787,10 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		segs = tp->snd_cwnd - tcp_packets_in_flight(tp);
 		if (segs <= 0)
 			return;
+		/* In case tcp_shift_skb_data() have aggregated large skbs,
+		 * we need to make sure not sending too bigs TSO packets
+		 */
+		segs = min_t(int, segs, max_segs);
 
 		if (fwd_rexmitting) {
 begin_fwd:
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d56c0559b477..ca5e8ea29538 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -391,9 +391,9 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum)
 	return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal, hash2_nulladdr);
 }
 
-static inline int compute_score(struct sock *sk, struct net *net,
-				__be32 saddr, unsigned short hnum, __be16 sport,
-				__be32 daddr, __be16 dport, int dif)
+static int compute_score(struct sock *sk, struct net *net,
+			 __be32 saddr, __be16 sport,
+			 __be32 daddr, unsigned short hnum, int dif)
 {
 	int score;
 	struct inet_sock *inet;
@@ -434,52 +434,6 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-/*
- * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num)
- */
-static inline int compute_score2(struct sock *sk, struct net *net,
-				 __be32 saddr, __be16 sport,
-				 __be32 daddr, unsigned int hnum, int dif)
-{
-	int score;
-	struct inet_sock *inet;
-
-	if (!net_eq(sock_net(sk), net) ||
-	    ipv6_only_sock(sk))
-		return -1;
-
-	inet = inet_sk(sk);
-
-	if (inet->inet_rcv_saddr != daddr ||
-	    inet->inet_num != hnum)
-		return -1;
-
-	score = (sk->sk_family == PF_INET) ? 2 : 1;
-
-	if (inet->inet_daddr) {
-		if (inet->inet_daddr != saddr)
-			return -1;
-		score += 4;
-	}
-
-	if (inet->inet_dport) {
-		if (inet->inet_dport != sport)
-			return -1;
-		score += 4;
-	}
-
-	if (sk->sk_bound_dev_if) {
-		if (sk->sk_bound_dev_if != dif)
-			return -1;
-		score += 4;
-	}
-
-	if (sk->sk_incoming_cpu == raw_smp_processor_id())
-		score++;
-
-	return score;
-}
-
 static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
 		       const __u16 lport, const __be32 faddr,
 		       const __be16 fport)
@@ -492,11 +446,11 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
 			      udp_ehash_secret + net_hash_mix(net));
 }
 
-/* called with read_rcu_lock() */
+/* called with rcu_read_lock() */
 static struct sock *udp4_lib_lookup2(struct net *net,
 		__be32 saddr, __be16 sport,
 		__be32 daddr, unsigned int hnum, int dif,
-		struct udp_hslot *hslot2, unsigned int slot2,
+		struct udp_hslot *hslot2,
 		struct sk_buff *skb)
 {
 	struct sock *sk, *result;
@@ -506,7 +460,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 	result = NULL;
 	badness = 0;
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
-		score = compute_score2(sk, net, saddr, sport,
+		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
@@ -554,17 +508,22 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 
 		result = udp4_lib_lookup2(net, saddr, sport,
 					  daddr, hnum, dif,
-					  hslot2, slot2, skb);
+					  hslot2, skb);
 		if (!result) {
+			unsigned int old_slot2 = slot2;
 			hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
 			slot2 = hash2 & udptable->mask;
+			/* avoid searching the same slot again. */
+			if (unlikely(slot2 == old_slot2))
+				return result;
+
 			hslot2 = &udptable->hash2[slot2];
 			if (hslot->count < hslot2->count)
 				goto begin;
 
 			result = udp4_lib_lookup2(net, saddr, sport,
-						  htonl(INADDR_ANY), hnum, dif,
-						  hslot2, slot2, skb);
+						  daddr, hnum, dif,
+						  hslot2, skb);
 		}
 		return result;
 	}
@@ -572,8 +531,8 @@ begin:
 	result = NULL;
 	badness = 0;
 	sk_for_each_rcu(sk, &hslot->head) {
-		score = compute_score(sk, net, saddr, hnum, sport,
-				      daddr, dport, dif);
+		score = compute_score(sk, net, saddr, sport,
+				      daddr, hnum, dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -1618,12 +1577,12 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		}
 	}
 
-	if (rcu_access_pointer(sk->sk_filter)) {
-		if (udp_lib_checksum_complete(skb))
+	if (rcu_access_pointer(sk->sk_filter) &&
+	    udp_lib_checksum_complete(skb))
 			goto csum_error;
-		if (sk_filter(sk, skb))
-			goto drop;
-	}
+
+	if (sk_filter(sk, skb))
+		goto drop;
 
 	udp_csum_pull_header(skb);
 	if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
@@ -1755,8 +1714,11 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 			return err;
 	}
 
-	return skb_checksum_init_zero_check(skb, proto, uh->check,
-					    inet_compute_pseudo);
+	/* Note, we are only interested in != 0 or == 0, thus the
+	 * force to int.
+	 */
+	return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+							 inet_compute_pseudo);
 }
 
 /*
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 47f12c73d959..58bd39fb14b4 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -76,6 +76,67 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 }
 EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
 
+void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
+			     unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct udp_tunnel_info ti;
+
+	if (!dev->netdev_ops->ndo_udp_tunnel_add)
+		return;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_push_rx_port);
+
+/* Notify netdevs that UDP port started listening */
+void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct net *net = sock_net(sk);
+	struct udp_tunnel_info ti;
+	struct net_device *dev;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		if (!dev->netdev_ops->ndo_udp_tunnel_add)
+			continue;
+		dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_notify_add_rx_port);
+
+/* Notify netdevs that UDP port is no more listening */
+void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct net *net = sock_net(sk);
+	struct udp_tunnel_info ti;
+	struct net_device *dev;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		if (!dev->netdev_ops->ndo_udp_tunnel_del)
+			continue;
+		dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_notify_del_rx_port);
+
 void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
 			 __be32 src, __be32 dst, __u8 tos, __u8 ttl,
 			 __be16 df, __be16 src_port, __be16 dst_port,
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 7b0edb37a115..b644a23c3db0 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -295,7 +295,7 @@ static struct ctl_table xfrm4_policy_table[] = {
 	{ }
 };
 
-static int __net_init xfrm4_net_sysctl_init(struct net *net)
+static __net_init int xfrm4_net_sysctl_init(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
@@ -323,7 +323,7 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static void __net_exit xfrm4_net_sysctl_exit(struct net *net)
+static __net_exit void xfrm4_net_sysctl_exit(struct net *net)
 {
 	struct ctl_table *table;
 
@@ -336,12 +336,12 @@ static void __net_exit xfrm4_net_sysctl_exit(struct net *net)
 		kfree(table);
 }
 #else /* CONFIG_SYSCTL */
-static int inline xfrm4_net_sysctl_init(struct net *net)
+static inline int xfrm4_net_sysctl_init(struct net *net)
 {
 	return 0;
 }
 
-static void inline xfrm4_net_sysctl_exit(struct net *net)
+static inline void xfrm4_net_sysctl_exit(struct net *net)
 {
 }
 #endif
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 47f837a58e0a..a1f6b7b31531 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1524,6 +1524,28 @@ out:
 	return hiscore_idx;
 }
 
+static int ipv6_get_saddr_master(struct net *net,
+				 const struct net_device *dst_dev,
+				 const struct net_device *master,
+				 struct ipv6_saddr_dst *dst,
+				 struct ipv6_saddr_score *scores,
+				 int hiscore_idx)
+{
+	struct inet6_dev *idev;
+
+	idev = __in6_dev_get(dst_dev);
+	if (idev)
+		hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev,
+						   scores, hiscore_idx);
+
+	idev = __in6_dev_get(master);
+	if (idev)
+		hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev,
+						   scores, hiscore_idx);
+
+	return hiscore_idx;
+}
+
 int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 		       const struct in6_addr *daddr, unsigned int prefs,
 		       struct in6_addr *saddr)
@@ -1577,13 +1599,39 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 		if (idev)
 			hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx);
 	} else {
+		const struct net_device *master;
+		int master_idx = 0;
+
+		/* if dst_dev exists and is enslaved to an L3 device, then
+		 * prefer addresses from dst_dev and then the master over
+		 * any other enslaved devices in the L3 domain.
+		 */
+		master = l3mdev_master_dev_rcu(dst_dev);
+		if (master) {
+			master_idx = master->ifindex;
+
+			hiscore_idx = ipv6_get_saddr_master(net, dst_dev,
+							    master, &dst,
+							    scores, hiscore_idx);
+
+			if (scores[hiscore_idx].ifa)
+				goto out;
+		}
+
 		for_each_netdev_rcu(net, dev) {
+			/* only consider addresses on devices in the
+			 * same L3 domain
+			 */
+			if (l3mdev_master_ifindex_rcu(dev) != master_idx)
+				continue;
 			idev = __in6_dev_get(dev);
 			if (!idev)
 				continue;
 			hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx);
 		}
 	}
+
+out:
 	rcu_read_unlock();
 
 	hiscore = &scores[hiscore_idx];
@@ -2254,7 +2302,7 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
 		return ERR_PTR(-EACCES);
 
 	/* Add default multicast route */
-	if (!(dev->flags & IFF_LOOPBACK))
+	if (!(dev->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev))
 		addrconf_add_mroute(dev);
 
 	return idev;
@@ -2333,12 +2381,109 @@ static bool is_addr_mode_generate_stable(struct inet6_dev *idev)
 	       idev->addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM;
 }
 
+int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
+				 const struct prefix_info *pinfo,
+				 struct inet6_dev *in6_dev,
+				 const struct in6_addr *addr, int addr_type,
+				 u32 addr_flags, bool sllao, bool tokenized,
+				 __u32 valid_lft, u32 prefered_lft)
+{
+	struct inet6_ifaddr *ifp = ipv6_get_ifaddr(net, addr, dev, 1);
+	int create = 0, update_lft = 0;
+
+	if (!ifp && valid_lft) {
+		int max_addresses = in6_dev->cnf.max_addresses;
+
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+		if (in6_dev->cnf.optimistic_dad &&
+		    !net->ipv6.devconf_all->forwarding && sllao)
+			addr_flags |= IFA_F_OPTIMISTIC;
+#endif
+
+		/* Do not allow to create too much of autoconfigured
+		 * addresses; this would be too easy way to crash kernel.
+		 */
+		if (!max_addresses ||
+		    ipv6_count_addresses(in6_dev) < max_addresses)
+			ifp = ipv6_add_addr(in6_dev, addr, NULL,
+					    pinfo->prefix_len,
+					    addr_type&IPV6_ADDR_SCOPE_MASK,
+					    addr_flags, valid_lft,
+					    prefered_lft);
+
+		if (IS_ERR_OR_NULL(ifp))
+			return -1;
+
+		update_lft = 0;
+		create = 1;
+		spin_lock_bh(&ifp->lock);
+		ifp->flags |= IFA_F_MANAGETEMPADDR;
+		ifp->cstamp = jiffies;
+		ifp->tokenized = tokenized;
+		spin_unlock_bh(&ifp->lock);
+		addrconf_dad_start(ifp);
+	}
+
+	if (ifp) {
+		u32 flags;
+		unsigned long now;
+		u32 stored_lft;
+
+		/* update lifetime (RFC2462 5.5.3 e) */
+		spin_lock_bh(&ifp->lock);
+		now = jiffies;
+		if (ifp->valid_lft > (now - ifp->tstamp) / HZ)
+			stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ;
+		else
+			stored_lft = 0;
+		if (!update_lft && !create && stored_lft) {
+			const u32 minimum_lft = min_t(u32,
+				stored_lft, MIN_VALID_LIFETIME);
+			valid_lft = max(valid_lft, minimum_lft);
+
+			/* RFC4862 Section 5.5.3e:
+			 * "Note that the preferred lifetime of the
+			 *  corresponding address is always reset to
+			 *  the Preferred Lifetime in the received
+			 *  Prefix Information option, regardless of
+			 *  whether the valid lifetime is also reset or
+			 *  ignored."
+			 *
+			 * So we should always update prefered_lft here.
+			 */
+			update_lft = 1;
+		}
+
+		if (update_lft) {
+			ifp->valid_lft = valid_lft;
+			ifp->prefered_lft = prefered_lft;
+			ifp->tstamp = now;
+			flags = ifp->flags;
+			ifp->flags &= ~IFA_F_DEPRECATED;
+			spin_unlock_bh(&ifp->lock);
+
+			if (!(flags&IFA_F_TENTATIVE))
+				ipv6_ifa_notify(0, ifp);
+		} else
+			spin_unlock_bh(&ifp->lock);
+
+		manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft,
+				 create, now);
+
+		in6_ifa_put(ifp);
+		addrconf_verify();
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(addrconf_prefix_rcv_add_addr);
+
 void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 {
 	struct prefix_info *pinfo;
 	__u32 valid_lft;
 	__u32 prefered_lft;
-	int addr_type;
+	int addr_type, err;
 	u32 addr_flags = 0;
 	struct inet6_dev *in6_dev;
 	struct net *net = dev_net(dev);
@@ -2432,10 +2577,8 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 	/* Try to figure out our local address for this prefix */
 
 	if (pinfo->autoconf && in6_dev->cnf.autoconf) {
-		struct inet6_ifaddr *ifp;
 		struct in6_addr addr;
-		int create = 0, update_lft = 0;
-		bool tokenized = false;
+		bool tokenized = false, dev_addr_generated = false;
 
 		if (pinfo->prefix_len == 64) {
 			memcpy(&addr, &pinfo->prefix, 8);
@@ -2453,106 +2596,36 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 				goto ok;
 			} else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) &&
 				   ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) {
-				in6_dev_put(in6_dev);
-				return;
+				goto put;
+			} else {
+				dev_addr_generated = true;
 			}
 			goto ok;
 		}
 		net_dbg_ratelimited("IPv6 addrconf: prefix with wrong length %d\n",
 				    pinfo->prefix_len);
-		in6_dev_put(in6_dev);
-		return;
+		goto put;
 
 ok:
+		err = addrconf_prefix_rcv_add_addr(net, dev, pinfo, in6_dev,
+						   &addr, addr_type,
+						   addr_flags, sllao,
+						   tokenized, valid_lft,
+						   prefered_lft);
+		if (err)
+			goto put;
 
-		ifp = ipv6_get_ifaddr(net, &addr, dev, 1);
-
-		if (!ifp && valid_lft) {
-			int max_addresses = in6_dev->cnf.max_addresses;
-
-#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
-			if (in6_dev->cnf.optimistic_dad &&
-			    !net->ipv6.devconf_all->forwarding && sllao)
-				addr_flags |= IFA_F_OPTIMISTIC;
-#endif
-
-			/* Do not allow to create too much of autoconfigured
-			 * addresses; this would be too easy way to crash kernel.
-			 */
-			if (!max_addresses ||
-			    ipv6_count_addresses(in6_dev) < max_addresses)
-				ifp = ipv6_add_addr(in6_dev, &addr, NULL,
-						    pinfo->prefix_len,
-						    addr_type&IPV6_ADDR_SCOPE_MASK,
-						    addr_flags, valid_lft,
-						    prefered_lft);
-
-			if (IS_ERR_OR_NULL(ifp)) {
-				in6_dev_put(in6_dev);
-				return;
-			}
-
-			update_lft = 0;
-			create = 1;
-			spin_lock_bh(&ifp->lock);
-			ifp->flags |= IFA_F_MANAGETEMPADDR;
-			ifp->cstamp = jiffies;
-			ifp->tokenized = tokenized;
-			spin_unlock_bh(&ifp->lock);
-			addrconf_dad_start(ifp);
-		}
-
-		if (ifp) {
-			u32 flags;
-			unsigned long now;
-			u32 stored_lft;
-
-			/* update lifetime (RFC2462 5.5.3 e) */
-			spin_lock_bh(&ifp->lock);
-			now = jiffies;
-			if (ifp->valid_lft > (now - ifp->tstamp) / HZ)
-				stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ;
-			else
-				stored_lft = 0;
-			if (!update_lft && !create && stored_lft) {
-				const u32 minimum_lft = min_t(u32,
-					stored_lft, MIN_VALID_LIFETIME);
-				valid_lft = max(valid_lft, minimum_lft);
-
-				/* RFC4862 Section 5.5.3e:
-				 * "Note that the preferred lifetime of the
-				 *  corresponding address is always reset to
-				 *  the Preferred Lifetime in the received
-				 *  Prefix Information option, regardless of
-				 *  whether the valid lifetime is also reset or
-				 *  ignored."
-				 *
-				 * So we should always update prefered_lft here.
-				 */
-				update_lft = 1;
-			}
-
-			if (update_lft) {
-				ifp->valid_lft = valid_lft;
-				ifp->prefered_lft = prefered_lft;
-				ifp->tstamp = now;
-				flags = ifp->flags;
-				ifp->flags &= ~IFA_F_DEPRECATED;
-				spin_unlock_bh(&ifp->lock);
-
-				if (!(flags&IFA_F_TENTATIVE))
-					ipv6_ifa_notify(0, ifp);
-			} else
-				spin_unlock_bh(&ifp->lock);
-
-			manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft,
-					 create, now);
-
-			in6_ifa_put(ifp);
-			addrconf_verify();
-		}
+		/* Ignore error case here because previous prefix add addr was
+		 * successful which will be notified.
+		 */
+		ndisc_ops_prefix_rcv_add_addr(net, dev, pinfo, in6_dev, &addr,
+					      addr_type, addr_flags, sllao,
+					      tokenized, valid_lft,
+					      prefered_lft,
+					      dev_addr_generated);
 	}
 	inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo);
+put:
 	in6_dev_put(in6_dev);
 }
 
@@ -2947,8 +3020,8 @@ static void init_loopback(struct net_device *dev)
 	}
 }
 
-static void addrconf_add_linklocal(struct inet6_dev *idev,
-				   const struct in6_addr *addr, u32 flags)
+void addrconf_add_linklocal(struct inet6_dev *idev,
+			    const struct in6_addr *addr, u32 flags)
 {
 	struct inet6_ifaddr *ifp;
 	u32 addr_flags = flags | IFA_F_PERMANENT;
@@ -2967,6 +3040,7 @@ static void addrconf_add_linklocal(struct inet6_dev *idev,
 		in6_ifa_put(ifp);
 	}
 }
+EXPORT_SYMBOL_GPL(addrconf_add_linklocal);
 
 static bool ipv6_reserved_interfaceid(struct in6_addr address)
 {
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index bfa86f040c16..2076c21107d0 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -92,6 +92,12 @@ MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces");
 module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444);
 MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces");
 
+bool ipv6_mod_enabled(void)
+{
+	return disable_ipv6_mod == 0;
+}
+EXPORT_SYMBOL_GPL(ipv6_mod_enabled);
+
 static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
 {
 	const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo);
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index ed33abf57abd..5857c1fc8b67 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -67,6 +67,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 	struct net *net = rule->fr_net;
 	pol_lookup_t lookup = arg->lookup_ptr;
 	int err = 0;
+	u32 tb_id;
 
 	switch (rule->action) {
 	case FR_ACT_TO_TBL:
@@ -86,7 +87,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 		goto discard_pkt;
 	}
 
-	table = fib6_get_table(net, rule->table);
+	tb_id = fib_rule_get_table(rule, arg);
+	table = fib6_get_table(net, tb_id);
 	if (!table) {
 		err = -EAGAIN;
 		goto out;
@@ -199,7 +201,7 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	struct net *net = sock_net(skb->sk);
 	struct fib6_rule *rule6 = (struct fib6_rule *) rule;
 
-	if (rule->action == FR_ACT_TO_TBL) {
+	if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) {
 		if (rule->table == RT6_TABLE_UNSPEC)
 			goto errout;
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 4527285fcaa2..bd59c343d35f 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -98,7 +98,7 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	if (!(type & ICMPV6_INFOMSG_MASK))
 		if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
-			ping_err(skb, offset, info);
+			ping_err(skb, offset, ntohl(info));
 }
 
 static int icmpv6_rcv(struct sk_buff *skb);
@@ -388,7 +388,8 @@ relookup_failed:
 /*
  *	Send an ICMP message in response to a packet in error
  */
-static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
+static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+		       const struct in6_addr *force_saddr)
 {
 	struct net *net = dev_net(skb->dev);
 	struct inet6_dev *idev = NULL;
@@ -475,6 +476,8 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_proto = IPPROTO_ICMPV6;
 	fl6.daddr = hdr->saddr;
+	if (force_saddr)
+		saddr = force_saddr;
 	if (saddr)
 		fl6.saddr = *saddr;
 	fl6.flowi6_mark = mark;
@@ -502,12 +505,14 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
+	ipc6.tclass = np->tclass;
+	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
 	dst = icmpv6_route_lookup(net, skb, sk, &fl6);
 	if (IS_ERR(dst))
 		goto out;
 
 	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
-	ipc6.tclass = np->tclass;
 	ipc6.dontfrag = np->dontfrag;
 	ipc6.opt = NULL;
 
@@ -549,10 +554,75 @@ out:
  */
 void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
 {
-	icmp6_send(skb, ICMPV6_PARAMPROB, code, pos);
+	icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL);
 	kfree_skb(skb);
 }
 
+/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
+ * if sufficient data bytes are available
+ * @nhs is the size of the tunnel header(s) :
+ *  Either an IPv4 header for SIT encap
+ *         an IPv4 header + GRE header for GRE encap
+ */
+int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
+			       unsigned int data_len)
+{
+	struct in6_addr temp_saddr;
+	struct rt6_info *rt;
+	struct sk_buff *skb2;
+	u32 info = 0;
+
+	if (!pskb_may_pull(skb, nhs + sizeof(struct ipv6hdr) + 8))
+		return 1;
+
+	/* RFC 4884 (partial) support for ICMP extensions */
+	if (data_len < 128 || (data_len & 7) || skb->len < data_len)
+		data_len = 0;
+
+	skb2 = data_len ? skb_copy(skb, GFP_ATOMIC) : skb_clone(skb, GFP_ATOMIC);
+
+	if (!skb2)
+		return 1;
+
+	skb_dst_drop(skb2);
+	skb_pull(skb2, nhs);
+	skb_reset_network_header(skb2);
+
+	rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
+
+	if (rt && rt->dst.dev)
+		skb2->dev = rt->dst.dev;
+
+	ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &temp_saddr);
+
+	if (data_len) {
+		/* RFC 4884 (partial) support :
+		 * insert 0 padding at the end, before the extensions
+		 */
+		__skb_push(skb2, nhs);
+		skb_reset_network_header(skb2);
+		memmove(skb2->data, skb2->data + nhs, data_len - nhs);
+		memset(skb2->data + data_len - nhs, 0, nhs);
+		/* RFC 4884 4.5 : Length is measured in 64-bit words,
+		 * and stored in reserved[0]
+		 */
+		info = (data_len/8) << 24;
+	}
+	if (type == ICMP_TIME_EXCEEDED)
+		icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
+			   info, &temp_saddr);
+	else
+		icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH,
+			   info, &temp_saddr);
+	if (rt)
+		ip6_rt_put(rt);
+
+	kfree_skb(skb2);
+
+	return 0;
+}
+EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach);
+
 static void icmpv6_echo_reply(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
@@ -585,7 +655,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	fl6.daddr = ipv6_hdr(skb)->saddr;
 	if (saddr)
 		fl6.saddr = *saddr;
-	fl6.flowi6_oif = l3mdev_fib_oif(skb->dev);
+	fl6.flowi6_oif = skb->dev->ifindex;
 	fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
 	fl6.flowi6_mark = mark;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h
index d08fd2d48a78..e0170f62bc39 100644
--- a/net/ipv6/ila/ila.h
+++ b/net/ipv6/ila/ila.h
@@ -109,7 +109,8 @@ static inline bool ila_csum_neutral_set(struct ila_identifier ident)
 	return !!(ident.csum_neutral);
 }
 
-void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p);
+void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p,
+			     bool set_csum_neutral);
 
 void ila_init_saved_csum(struct ila_params *p);
 
diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c
index 0e94042d1289..ec9efbcdad35 100644
--- a/net/ipv6/ila/ila_common.c
+++ b/net/ipv6/ila/ila_common.c
@@ -34,12 +34,12 @@ static void ila_csum_do_neutral(struct ila_addr *iaddr,
 	if (p->locator_match.v64) {
 		diff = p->csum_diff;
 	} else {
-		diff = compute_csum_diff8((__be32 *)iaddr,
-					  (__be32 *)&p->locator);
+		diff = compute_csum_diff8((__be32 *)&p->locator,
+					  (__be32 *)iaddr);
 	}
 
 	fval = (__force __wsum)(ila_csum_neutral_set(iaddr->ident) ?
-			~CSUM_NEUTRAL_FLAG : CSUM_NEUTRAL_FLAG);
+			CSUM_NEUTRAL_FLAG : ~CSUM_NEUTRAL_FLAG);
 
 	diff = csum_add(diff, fval);
 
@@ -103,7 +103,8 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
 	iaddr->loc = p->locator;
 }
 
-void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p)
+void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p,
+			     bool set_csum_neutral)
 {
 	struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	struct ila_addr *iaddr = ila_a2i(&ip6h->daddr);
@@ -114,7 +115,8 @@ void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p)
 		 * is a locator being translated to a SIR address.
 		 * Perform (receiver) checksum-neutral translation.
 		 */
-		ila_csum_do_neutral(iaddr, p);
+		if (!set_csum_neutral)
+			ila_csum_do_neutral(iaddr, p);
 	} else {
 		switch (p->csum_mode) {
 		case ILA_CSUM_ADJUST_TRANSPORT:
@@ -138,8 +140,8 @@ void ila_init_saved_csum(struct ila_params *p)
 		return;
 
 	p->csum_diff = compute_csum_diff8(
-				(__be32 *)&p->locator_match,
-				(__be32 *)&p->locator);
+				(__be32 *)&p->locator,
+				(__be32 *)&p->locator_match);
 }
 
 static int __init ila_init(void)
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index 1dfb64166d7d..c8314c6b6154 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -26,7 +26,7 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (skb->protocol != htons(ETH_P_IPV6))
 		goto drop;
 
-	ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
+	ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), true);
 
 	return dst->lwtstate->orig_output(net, sk, skb);
 
@@ -42,7 +42,7 @@ static int ila_input(struct sk_buff *skb)
 	if (skb->protocol != htons(ETH_P_IPV6))
 		goto drop;
 
-	ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
+	ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), false);
 
 	return dst->lwtstate->orig_input(skb);
 
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index a90e57229c6c..e6eca5fdf4c9 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -210,14 +210,14 @@ static void ila_free_cb(void *ptr, void *arg)
 	}
 }
 
-static int ila_xlat_addr(struct sk_buff *skb);
+static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral);
 
 static unsigned int
 ila_nf_input(void *priv,
 	     struct sk_buff *skb,
 	     const struct nf_hook_state *state)
 {
-	ila_xlat_addr(skb);
+	ila_xlat_addr(skb, false);
 	return NF_ACCEPT;
 }
 
@@ -597,7 +597,7 @@ static struct pernet_operations ila_net_ops = {
 	.size = sizeof(struct ila_net),
 };
 
-static int ila_xlat_addr(struct sk_buff *skb)
+static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral)
 {
 	struct ila_map *ila;
 	struct ipv6hdr *ip6h = ipv6_hdr(skb);
@@ -616,7 +616,7 @@ static int ila_xlat_addr(struct sk_buff *skb)
 
 	ila = ila_lookup_wildcards(iaddr, skb->dev->ifindex, ilan);
 	if (ila)
-		ila_update_ipv6_locator(skb, &ila->xp.ip);
+		ila_update_ipv6_locator(skb, &ila->xp.ip, set_csum_neutral);
 
 	rcu_read_unlock();
 
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index b2025bf3da4a..c0cbcb259f5a 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -78,9 +78,12 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
 	 * we accept a checksum of zero here. When we find the socket
 	 * for the UDP packet we'll check if that socket allows zero checksum
 	 * for IPv6 (set by socket option).
+	 *
+	 * Note, we are only interested in != 0 or == 0, thus the
+	 * force to int.
 	 */
-	return skb_checksum_init_zero_check(skb, proto, uh->check,
-					   ip6_compute_pseudo);
+	return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+							 ip6_compute_pseudo);
 }
 EXPORT_SYMBOL(udp6_csum_init);
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index f4ac2842d4d9..776d145113e1 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -468,7 +468,7 @@ static int gre_rcv(struct sk_buff *skb)
 	bool csum_err = false;
 	int hdr_len;
 
-	hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IPV6));
+	hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IPV6), 0);
 	if (hdr_len < 0)
 		goto drop;
 
@@ -1256,6 +1256,8 @@ static int ip6gre_tap_init(struct net_device *dev)
 	if (ret)
 		return ret;
 
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+
 	tunnel = netdev_priv(dev);
 
 	ip6gre_tnl_link_config(tunnel, 1);
@@ -1289,6 +1291,7 @@ static void ip6gre_tap_setup(struct net_device *dev)
 
 	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 }
 
 static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 14dacc544c3e..713676f14a0e 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -39,7 +39,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 
 	if (!send)
 		goto out;
-	send(skb, type, code, info);
+	send(skb, type, code, info, NULL);
 out:
 	rcu_read_unlock();
 }
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 94611e450ec9..aacfb4bce153 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -323,6 +323,7 @@ int ip6_input(struct sk_buff *skb)
 		       dev_net(skb->dev), NULL, skb, skb->dev, NULL,
 		       ip6_input_finish);
 }
+EXPORT_SYMBOL_GPL(ip6_input);
 
 int ip6_mc_input(struct sk_buff *skb)
 {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6b2f60a5c1de..1dfc402d9ad1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -910,6 +910,13 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 	int err;
 	int flags = 0;
 
+	if (ipv6_addr_any(&fl6->saddr) && fl6->flowi6_oif &&
+	    (!*dst || !(*dst)->error)) {
+		err = l3mdev_get_saddr6(net, sk, fl6);
+		if (err)
+			goto out_err;
+	}
+
 	/* The correct way to handle this would be to do
 	 * ip6_route_get_saddr, and then ip6_route_output; however,
 	 * the route-specific preferred source forces the
@@ -999,10 +1006,11 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 	return 0;
 
 out_err_release:
-	if (err == -ENETUNREACH)
-		IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
 	dst_release(*dst);
 	*dst = NULL;
+out_err:
+	if (err == -ENETUNREACH)
+		IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
 	return err;
 }
 
@@ -1071,17 +1079,12 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 					 const struct in6_addr *final_dst)
 {
 	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
-	int err;
 
 	dst = ip6_sk_dst_check(sk, dst, fl6);
+	if (!dst)
+		dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
 
-	err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
-	if (err)
-		return ERR_PTR(err);
-	if (final_dst)
-		fl6->daddr = *final_dst;
-
-	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return dst;
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index f2e2013f8346..487ef3bc7bbc 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1074,6 +1074,7 @@ static struct mfc6_cache *ip6mr_cache_alloc(void)
 	struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
 	if (!c)
 		return NULL;
+	c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 	c->mfc_un.res.minvif = MAXMIFS;
 	return c;
 }
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index c245895a3d41..fe65cdc28a45 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -73,15 +73,6 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv6.h>
 
-/* Set to 3 to get tracing... */
-#define ND_DEBUG 1
-
-#define ND_PRINTK(val, level, fmt, ...)				\
-do {								\
-	if (val <= ND_DEBUG)					\
-		net_##level##_ratelimited(fmt, ##__VA_ARGS__);	\
-} while (0)
-
 static u32 ndisc_hash(const void *pkey,
 		      const struct net_device *dev,
 		      __u32 *hash_rnd);
@@ -150,11 +141,10 @@ struct neigh_table nd_tbl = {
 };
 EXPORT_SYMBOL_GPL(nd_tbl);
 
-static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data)
+void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data,
+			      int data_len, int pad)
 {
-	int pad   = ndisc_addr_option_pad(skb->dev->type);
-	int data_len = skb->dev->addr_len;
-	int space = ndisc_opt_addr_space(skb->dev);
+	int space = __ndisc_opt_addr_space(data_len, pad);
 	u8 *opt = skb_put(skb, space);
 
 	opt[0] = type;
@@ -171,6 +161,23 @@ static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data)
 	if (space > 0)
 		memset(opt, 0, space);
 }
+EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option);
+
+static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type,
+					  void *data, u8 icmp6_type)
+{
+	__ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len,
+				 ndisc_addr_option_pad(skb->dev->type));
+	ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type);
+}
+
+static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb,
+						   void *ha,
+						   const u8 *ops_data)
+{
+	ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT);
+	ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data);
+}
 
 static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
 					    struct nd_opt_hdr *end)
@@ -185,24 +192,28 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
 	return cur <= end && cur->nd_opt_type == type ? cur : NULL;
 }
 
-static inline int ndisc_is_useropt(struct nd_opt_hdr *opt)
+static inline int ndisc_is_useropt(const struct net_device *dev,
+				   struct nd_opt_hdr *opt)
 {
 	return opt->nd_opt_type == ND_OPT_RDNSS ||
-		opt->nd_opt_type == ND_OPT_DNSSL;
+		opt->nd_opt_type == ND_OPT_DNSSL ||
+		ndisc_ops_is_useropt(dev, opt->nd_opt_type);
 }
 
-static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur,
+static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev,
+					     struct nd_opt_hdr *cur,
 					     struct nd_opt_hdr *end)
 {
 	if (!cur || !end || cur >= end)
 		return NULL;
 	do {
 		cur = ((void *)cur) + (cur->nd_opt_len << 3);
-	} while (cur < end && !ndisc_is_useropt(cur));
-	return cur <= end && ndisc_is_useropt(cur) ? cur : NULL;
+	} while (cur < end && !ndisc_is_useropt(dev, cur));
+	return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL;
 }
 
-struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
+struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
+					  u8 *opt, int opt_len,
 					  struct ndisc_options *ndopts)
 {
 	struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt;
@@ -217,6 +228,8 @@ struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
 		l = nd_opt->nd_opt_len << 3;
 		if (opt_len < l || l == 0)
 			return NULL;
+		if (ndisc_ops_parse_options(dev, nd_opt, ndopts))
+			goto next_opt;
 		switch (nd_opt->nd_opt_type) {
 		case ND_OPT_SOURCE_LL_ADDR:
 		case ND_OPT_TARGET_LL_ADDR:
@@ -243,7 +256,7 @@ struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
 			break;
 #endif
 		default:
-			if (ndisc_is_useropt(nd_opt)) {
+			if (ndisc_is_useropt(dev, nd_opt)) {
 				ndopts->nd_useropts_end = nd_opt;
 				if (!ndopts->nd_useropts)
 					ndopts->nd_useropts = nd_opt;
@@ -260,6 +273,7 @@ struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
 					  nd_opt->nd_opt_len);
 			}
 		}
+next_opt:
 		opt_len -= l;
 		nd_opt = ((void *)nd_opt) + l;
 	}
@@ -509,7 +523,8 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
 	if (!dev->addr_len)
 		inc_opt = 0;
 	if (inc_opt)
-		optlen += ndisc_opt_addr_space(dev);
+		optlen += ndisc_opt_addr_space(dev,
+					       NDISC_NEIGHBOUR_ADVERTISEMENT);
 
 	skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
 	if (!skb)
@@ -528,8 +543,8 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
 
 	if (inc_opt)
 		ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR,
-				       dev->dev_addr);
-
+				       dev->dev_addr,
+				       NDISC_NEIGHBOUR_ADVERTISEMENT);
 
 	ndisc_send_skb(skb, daddr, src_addr);
 }
@@ -574,7 +589,8 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
 	if (ipv6_addr_any(saddr))
 		inc_opt = false;
 	if (inc_opt)
-		optlen += ndisc_opt_addr_space(dev);
+		optlen += ndisc_opt_addr_space(dev,
+					       NDISC_NEIGHBOUR_SOLICITATION);
 
 	skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
 	if (!skb)
@@ -590,7 +606,8 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
 
 	if (inc_opt)
 		ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
-				       dev->dev_addr);
+				       dev->dev_addr,
+				       NDISC_NEIGHBOUR_SOLICITATION);
 
 	ndisc_send_skb(skb, daddr, saddr);
 }
@@ -626,7 +643,7 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
 	}
 #endif
 	if (send_sllao)
-		optlen += ndisc_opt_addr_space(dev);
+		optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION);
 
 	skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
 	if (!skb)
@@ -641,7 +658,8 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
 
 	if (send_sllao)
 		ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
-				       dev->dev_addr);
+				       dev->dev_addr,
+				       NDISC_ROUTER_SOLICITATION);
 
 	ndisc_send_skb(skb, daddr, saddr);
 }
@@ -702,6 +720,15 @@ static int pndisc_is_router(const void *pkey,
 	return ret;
 }
 
+void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
+		  const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
+		  struct ndisc_options *ndopts)
+{
+	neigh_update(neigh, lladdr, new, flags);
+	/* report ndisc ops about neighbour update */
+	ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts);
+}
+
 static void ndisc_recv_ns(struct sk_buff *skb)
 {
 	struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
@@ -738,7 +765,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
 		return;
 	}
 
-	if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
+	if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) {
 		ND_PRINTK(2, warn, "NS: invalid ND options\n");
 		return;
 	}
@@ -856,9 +883,10 @@ have_ifp:
 	neigh = __neigh_lookup(&nd_tbl, saddr, dev,
 			       !inc || lladdr || !dev->addr_len);
 	if (neigh)
-		neigh_update(neigh, lladdr, NUD_STALE,
+		ndisc_update(dev, neigh, lladdr, NUD_STALE,
 			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
-			     NEIGH_UPDATE_F_OVERRIDE);
+			     NEIGH_UPDATE_F_OVERRIDE,
+			     NDISC_NEIGHBOUR_SOLICITATION, &ndopts);
 	if (neigh || !dev->header_ops) {
 		ndisc_send_na(dev, saddr, &msg->target, !!is_router,
 			      true, (ifp != NULL && inc), inc);
@@ -911,7 +939,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
 	    idev->cnf.drop_unsolicited_na)
 		return;
 
-	if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
+	if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) {
 		ND_PRINTK(2, warn, "NS: invalid ND option\n");
 		return;
 	}
@@ -967,12 +995,13 @@ static void ndisc_recv_na(struct sk_buff *skb)
 			goto out;
 		}
 
-		neigh_update(neigh, lladdr,
+		ndisc_update(dev, neigh, lladdr,
 			     msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE,
 			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
 			     (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)|
 			     NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
-			     (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0));
+			     (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0),
+			     NDISC_NEIGHBOUR_ADVERTISEMENT, &ndopts);
 
 		if ((old_flags & ~neigh->flags) & NTF_ROUTER) {
 			/*
@@ -1017,7 +1046,7 @@ static void ndisc_recv_rs(struct sk_buff *skb)
 		goto out;
 
 	/* Parse ND options */
-	if (!ndisc_parse_options(rs_msg->opt, ndoptlen, &ndopts)) {
+	if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts)) {
 		ND_PRINTK(2, notice, "NS: invalid ND option, ignored\n");
 		goto out;
 	}
@@ -1031,10 +1060,11 @@ static void ndisc_recv_rs(struct sk_buff *skb)
 
 	neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1);
 	if (neigh) {
-		neigh_update(neigh, lladdr, NUD_STALE,
+		ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
 			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
 			     NEIGH_UPDATE_F_OVERRIDE|
-			     NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
+			     NEIGH_UPDATE_F_OVERRIDE_ISROUTER,
+			     NDISC_ROUTER_SOLICITATION, &ndopts);
 		neigh_release(neigh);
 	}
 out:
@@ -1135,7 +1165,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 		return;
 	}
 
-	if (!ndisc_parse_options(opt, optlen, &ndopts)) {
+	if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) {
 		ND_PRINTK(2, warn, "RA: invalid ND options\n");
 		return;
 	}
@@ -1329,11 +1359,12 @@ skip_linkparms:
 				goto out;
 			}
 		}
-		neigh_update(neigh, lladdr, NUD_STALE,
+		ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
 			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
 			     NEIGH_UPDATE_F_OVERRIDE|
 			     NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
-			     NEIGH_UPDATE_F_ISROUTER);
+			     NEIGH_UPDATE_F_ISROUTER,
+			     NDISC_ROUTER_ADVERTISEMENT, &ndopts);
 	}
 
 	if (!ipv6_accept_ra(in6_dev)) {
@@ -1421,7 +1452,8 @@ skip_routeinfo:
 		struct nd_opt_hdr *p;
 		for (p = ndopts.nd_useropts;
 		     p;
-		     p = ndisc_next_useropt(p, ndopts.nd_useropts_end)) {
+		     p = ndisc_next_useropt(skb->dev, p,
+					    ndopts.nd_useropts_end)) {
 			ndisc_ra_useropt(skb, p);
 		}
 	}
@@ -1459,7 +1491,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb)
 		return;
 	}
 
-	if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts))
+	if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts))
 		return;
 
 	if (!ndopts.nd_opts_rh) {
@@ -1504,7 +1536,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
 	struct dst_entry *dst;
 	struct flowi6 fl6;
 	int rd_len;
-	u8 ha_buf[MAX_ADDR_LEN], *ha = NULL;
+	u8 ha_buf[MAX_ADDR_LEN], *ha = NULL,
+	   ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL;
 	int oif = l3mdev_fib_oif(dev);
 	bool ret;
 
@@ -1563,7 +1596,9 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
 			memcpy(ha_buf, neigh->ha, dev->addr_len);
 			read_unlock_bh(&neigh->lock);
 			ha = ha_buf;
-			optlen += ndisc_opt_addr_space(dev);
+			optlen += ndisc_redirect_opt_addr_space(dev, neigh,
+								ops_data_buf,
+								&ops_data);
 		} else
 			read_unlock_bh(&neigh->lock);
 
@@ -1594,7 +1629,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
 	 */
 
 	if (ha)
-		ndisc_fill_addr_option(buff, ND_OPT_TARGET_LL_ADDR, ha);
+		ndisc_fill_redirect_addr_option(buff, ha, ops_data);
 
 	/*
 	 *	build redirect option and copy skb over to the new packet.
diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
index 6989c70ae29f..4a84b5ad9ecb 100644
--- a/net/ipv6/netfilter/nf_dup_ipv6.c
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -33,6 +33,7 @@ static bool nf_dup_ipv6_route(struct net *net, struct sk_buff *skb,
 	fl6.daddr = *gw;
 	fl6.flowlabel = (__force __be32)(((iph->flow_lbl[0] & 0xF) << 16) |
 			(iph->flow_lbl[1] << 8) | iph->flow_lbl[2]);
+	fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst->error) {
 		dst_release(dst);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 3ee3e444a66b..fed40d1ec29b 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -116,6 +116,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
+	ipc6.tclass = np->tclass;
+	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
 	dst = ip6_sk_dst_lookup_flow(sk, &fl6,  daddr);
 	if (IS_ERR(dst))
 		return PTR_ERR(dst);
@@ -140,7 +143,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	pfh.family = AF_INET6;
 
 	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
-	ipc6.tclass = np->tclass;
 	ipc6.dontfrag = np->dontfrag;
 	ipc6.opt = NULL;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 896350df6423..590dd1f7746f 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -878,6 +878,11 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (inet->hdrincl)
 		fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
 
+	if (ipc6.tclass < 0)
+		ipc6.tclass = np->tclass;
+
+	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
@@ -886,9 +891,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (ipc6.hlimit < 0)
 		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
-	if (ipc6.tclass < 0)
-		ipc6.tclass = np->tclass;
-
 	if (ipc6.dontfrag < 0)
 		ipc6.dontfrag = np->dontfrag;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 969913da494f..49817555449e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1042,8 +1042,8 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
 	return pcpu_rt;
 }
 
-static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
-				      struct flowi6 *fl6, int flags)
+struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
+			       int oif, struct flowi6 *fl6, int flags)
 {
 	struct fib6_node *fn, *saved_fn;
 	struct rt6_info *rt;
@@ -1139,6 +1139,7 @@ redo_rt6_select:
 
 	}
 }
+EXPORT_SYMBOL_GPL(ip6_pol_route);
 
 static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
 					    struct flowi6 *fl6, int flags)
@@ -1782,7 +1783,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net,
 	};
 	struct fib6_table *table;
 	struct rt6_info *rt;
-	int flags = 0;
+	int flags = RT6_LOOKUP_F_IFACE;
 
 	table = fib6_get_table(net, cfg->fc_table);
 	if (!table)
@@ -2200,7 +2201,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	 *	first-hop router for the specified ICMP Destination Address.
 	 */
 
-	if (!ndisc_parse_options(msg->opt, optlen, &ndopts)) {
+	if (!ndisc_parse_options(skb->dev, msg->opt, optlen, &ndopts)) {
 		net_dbg_ratelimited("rt6_redirect: invalid ND options\n");
 		return;
 	}
@@ -2235,12 +2236,12 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	 *	We have finally decided to accept it.
 	 */
 
-	neigh_update(neigh, lladdr, NUD_STALE,
+	ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
 		     NEIGH_UPDATE_F_WEAK_OVERRIDE|
 		     NEIGH_UPDATE_F_OVERRIDE|
 		     (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
-				     NEIGH_UPDATE_F_ISROUTER))
-		     );
+				     NEIGH_UPDATE_F_ISROUTER)),
+		     NDISC_REDIRECT, &ndopts);
 
 	nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL);
 	if (!nrt)
@@ -2585,23 +2586,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 	return rt;
 }
 
-int ip6_route_get_saddr(struct net *net,
-			struct rt6_info *rt,
-			const struct in6_addr *daddr,
-			unsigned int prefs,
-			struct in6_addr *saddr)
-{
-	struct inet6_dev *idev =
-		rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
-	int err = 0;
-	if (rt && rt->rt6i_prefsrc.plen)
-		*saddr = rt->rt6i_prefsrc.addr;
-	else
-		err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
-					 daddr, prefs, saddr);
-	return err;
-}
-
 /* remove deleted ip from prefsrc entries */
 struct arg_dev_net_ip {
 	struct net_device *dev;
@@ -3306,6 +3290,8 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 
 	err = -EINVAL;
 	memset(&fl6, 0, sizeof(fl6));
+	rtm = nlmsg_data(nlh);
+	fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
 
 	if (tb[RTA_SRC]) {
 		if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 0a5a255277e5..917a5cd4b8fc 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -479,47 +479,12 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
 	dev_put(dev);
 }
 
-/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
- * if sufficient data bytes are available
- */
-static int ipip6_err_gen_icmpv6_unreach(struct sk_buff *skb)
-{
-	int ihl = ((const struct iphdr *)skb->data)->ihl*4;
-	struct rt6_info *rt;
-	struct sk_buff *skb2;
-
-	if (!pskb_may_pull(skb, ihl + sizeof(struct ipv6hdr) + 8))
-		return 1;
-
-	skb2 = skb_clone(skb, GFP_ATOMIC);
-
-	if (!skb2)
-		return 1;
-
-	skb_dst_drop(skb2);
-	skb_pull(skb2, ihl);
-	skb_reset_network_header(skb2);
-
-	rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
-
-	if (rt && rt->dst.dev)
-		skb2->dev = rt->dst.dev;
-
-	icmpv6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
-
-	if (rt)
-		ip6_rt_put(rt);
-
-	kfree_skb(skb2);
-
-	return 0;
-}
-
 static int ipip6_err(struct sk_buff *skb, u32 info)
 {
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	unsigned int data_len = 0;
 	struct ip_tunnel *t;
 	int err;
 
@@ -544,6 +509,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 	case ICMP_TIME_EXCEEDED:
 		if (code != ICMP_EXC_TTL)
 			return 0;
+		data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
 		break;
 	case ICMP_REDIRECT:
 		break;
@@ -560,22 +526,22 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->parms.link, 0, IPPROTO_IPV6, 0);
+				 t->parms.link, 0, iph->protocol, 0);
 		err = 0;
 		goto out;
 	}
 	if (type == ICMP_REDIRECT) {
 		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
-			      IPPROTO_IPV6, 0);
+			      iph->protocol, 0);
 		err = 0;
 		goto out;
 	}
 
-	if (t->parms.iph.daddr == 0)
+	err = 0;
+	if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
 		goto out;
 
-	err = 0;
-	if (!ipip6_err_gen_icmpv6_unreach(skb))
+	if (t->parms.iph.daddr == 0)
 		goto out;
 
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
@@ -825,9 +791,6 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	u8 protocol = IPPROTO_IPV6;
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
-	if (skb->protocol != htons(ETH_P_IPV6))
-		goto tx_error;
-
 	if (tos == 1)
 		tos = ipv6_get_dsfield(iph6);
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 79e33e02f11a..37cf91323319 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -526,26 +526,33 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval,
 			      AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
 }
 
-static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
-					const struct in6_addr *daddr,
-					const struct in6_addr *saddr, int nbytes)
+static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp,
+				   const struct in6_addr *daddr,
+				   const struct in6_addr *saddr,
+				   const struct tcphdr *th, int nbytes)
 {
 	struct tcp6_pseudohdr *bp;
 	struct scatterlist sg;
+	struct tcphdr *_th;
 
-	bp = &hp->md5_blk.ip6;
+	bp = hp->scratch;
 	/* 1. TCP pseudo-header (RFC2460) */
 	bp->saddr = *saddr;
 	bp->daddr = *daddr;
 	bp->protocol = cpu_to_be32(IPPROTO_TCP);
 	bp->len = cpu_to_be32(nbytes);
 
-	sg_init_one(&sg, bp, sizeof(*bp));
-	ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(*bp));
+	_th = (struct tcphdr *)(bp + 1);
+	memcpy(_th, th, sizeof(*th));
+	_th->check = 0;
+
+	sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th));
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL,
+				sizeof(*bp) + sizeof(*th));
 	return crypto_ahash_update(hp->md5_req);
 }
 
-static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
+static int tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 			       const struct in6_addr *daddr, struct in6_addr *saddr,
 			       const struct tcphdr *th)
 {
@@ -559,9 +566,7 @@ static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
 
 	if (crypto_ahash_init(req))
 		goto clear_hash;
-	if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2))
-		goto clear_hash;
-	if (tcp_md5_hash_header(hp, th))
+	if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2))
 		goto clear_hash;
 	if (tcp_md5_hash_key(hp, key))
 		goto clear_hash;
@@ -606,9 +611,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash,
 	if (crypto_ahash_init(req))
 		goto clear_hash;
 
-	if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, skb->len))
-		goto clear_hash;
-	if (tcp_md5_hash_header(hp, th))
+	if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, skb->len))
 		goto clear_hash;
 	if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
 		goto clear_hash;
@@ -738,7 +741,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq,
 				 u32 ack, u32 win, u32 tsval, u32 tsecr,
 				 int oif, struct tcp_md5sig_key *key, int rst,
-				 u8 tclass, u32 label)
+				 u8 tclass, __be32 label)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 	struct tcphdr *t1;
@@ -911,7 +914,7 @@ out:
 static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq,
 			    u32 ack, u32 win, u32 tsval, u32 tsecr, int oif,
 			    struct tcp_md5sig_key *key, u8 tclass,
-			    u32 label)
+			    __be32 label)
 {
 	tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
 			     tclass, label);
@@ -1721,7 +1724,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	destp = ntohs(inet->inet_dport);
 	srcp  = ntohs(inet->inet_sport);
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 2da1896af934..0a71a312d0d8 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -115,11 +115,10 @@ static void udp_v6_rehash(struct sock *sk)
 	udp_lib_rehash(sk, new_hash);
 }
 
-static inline int compute_score(struct sock *sk, struct net *net,
-				unsigned short hnum,
-				const struct in6_addr *saddr, __be16 sport,
-				const struct in6_addr *daddr, __be16 dport,
-				int dif)
+static int compute_score(struct sock *sk, struct net *net,
+			 const struct in6_addr *saddr, __be16 sport,
+			 const struct in6_addr *daddr, unsigned short hnum,
+			 int dif)
 {
 	int score;
 	struct inet_sock *inet;
@@ -162,54 +161,11 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-static inline int compute_score2(struct sock *sk, struct net *net,
-				 const struct in6_addr *saddr, __be16 sport,
-				 const struct in6_addr *daddr,
-				 unsigned short hnum, int dif)
-{
-	int score;
-	struct inet_sock *inet;
-
-	if (!net_eq(sock_net(sk), net) ||
-	    udp_sk(sk)->udp_port_hash != hnum ||
-	    sk->sk_family != PF_INET6)
-		return -1;
-
-	if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
-		return -1;
-
-	score = 0;
-	inet = inet_sk(sk);
-
-	if (inet->inet_dport) {
-		if (inet->inet_dport != sport)
-			return -1;
-		score++;
-	}
-
-	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
-		if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
-			return -1;
-		score++;
-	}
-
-	if (sk->sk_bound_dev_if) {
-		if (sk->sk_bound_dev_if != dif)
-			return -1;
-		score++;
-	}
-
-	if (sk->sk_incoming_cpu == raw_smp_processor_id())
-		score++;
-
-	return score;
-}
-
-/* called with read_rcu_lock() */
+/* called with rcu_read_lock() */
 static struct sock *udp6_lib_lookup2(struct net *net,
 		const struct in6_addr *saddr, __be16 sport,
 		const struct in6_addr *daddr, unsigned int hnum, int dif,
-		struct udp_hslot *hslot2, unsigned int slot2,
+		struct udp_hslot *hslot2,
 		struct sk_buff *skb)
 {
 	struct sock *sk, *result;
@@ -219,7 +175,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 	result = NULL;
 	badness = -1;
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
-		score = compute_score2(sk, net, saddr, sport,
+		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
@@ -268,17 +224,22 @@ struct sock *__udp6_lib_lookup(struct net *net,
 
 		result = udp6_lib_lookup2(net, saddr, sport,
 					  daddr, hnum, dif,
-					  hslot2, slot2, skb);
+					  hslot2, skb);
 		if (!result) {
+			unsigned int old_slot2 = slot2;
 			hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum);
 			slot2 = hash2 & udptable->mask;
+			/* avoid searching the same slot again. */
+			if (unlikely(slot2 == old_slot2))
+				return result;
+
 			hslot2 = &udptable->hash2[slot2];
 			if (hslot->count < hslot2->count)
 				goto begin;
 
 			result = udp6_lib_lookup2(net, saddr, sport,
-						  &in6addr_any, hnum, dif,
-						  hslot2, slot2, skb);
+						  daddr, hnum, dif,
+						  hslot2, skb);
 		}
 		return result;
 	}
@@ -286,7 +247,7 @@ begin:
 	result = NULL;
 	badness = -1;
 	sk_for_each_rcu(sk, &hslot->head) {
-		score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif);
+		score = compute_score(sk, net, saddr, sport, daddr, hnum, dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -653,12 +614,12 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		}
 	}
 
-	if (rcu_access_pointer(sk->sk_filter)) {
-		if (udp_lib_checksum_complete(skb))
-			goto csum_error;
-		if (sk_filter(sk, skb))
-			goto drop;
-	}
+	if (rcu_access_pointer(sk->sk_filter) &&
+	    udp_lib_checksum_complete(skb))
+		goto csum_error;
+
+	if (sk_filter(sk, skb))
+		goto drop;
 
 	udp_csum_pull_header(skb);
 	if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
@@ -1246,6 +1207,11 @@ do_udp_sendmsg:
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
+	if (ipc6.tclass < 0)
+		ipc6.tclass = np->tclass;
+
+	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
 	dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
@@ -1256,9 +1222,6 @@ do_udp_sendmsg:
 	if (ipc6.hlimit < 0)
 		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
-	if (ipc6.tclass < 0)
-		ipc6.tclass = np->tclass;
-
 	if (msg->msg_flags&MSG_CONFIRM)
 		goto do_confirm;
 back_from_confirm:
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index c074771a10f7..6cc97003e4a9 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -366,12 +366,12 @@ static void __net_exit xfrm6_net_sysctl_exit(struct net *net)
 		kfree(table);
 }
 #else /* CONFIG_SYSCTL */
-static int inline xfrm6_net_sysctl_init(struct net *net)
+static inline int xfrm6_net_sysctl_init(struct net *net)
 {
 	return 0;
 }
 
-static void inline xfrm6_net_sysctl_exit(struct net *net)
+static inline void xfrm6_net_sysctl_exit(struct net *net)
 {
 }
 #endif
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index fc3598a922b0..37d674e6f8a9 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1033,6 +1033,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct iucv_sock *iucv = iucv_sk(sk);
+	size_t headroom, linear;
 	struct sk_buff *skb;
 	struct iucv_message txmsg = {0};
 	struct cmsghdr *cmsg;
@@ -1110,20 +1111,31 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	 * this is fine for SOCK_SEQPACKET (unless we want to support
 	 * segmented records using the MSG_EOR flag), but
 	 * for SOCK_STREAM we might want to improve it in future */
-	if (iucv->transport == AF_IUCV_TRANS_HIPER)
-		skb = sock_alloc_send_skb(sk,
-			len + sizeof(struct af_iucv_trans_hdr) + ETH_HLEN,
-			noblock, &err);
-	else
-		skb = sock_alloc_send_skb(sk, len, noblock, &err);
+	headroom = (iucv->transport == AF_IUCV_TRANS_HIPER)
+		   ? sizeof(struct af_iucv_trans_hdr) + ETH_HLEN : 0;
+	if (headroom + len < PAGE_SIZE) {
+		linear = len;
+	} else {
+		/* In nonlinear "classic" iucv skb,
+		 * reserve space for iucv_array
+		 */
+		if (iucv->transport != AF_IUCV_TRANS_HIPER)
+			headroom += sizeof(struct iucv_array) *
+				    (MAX_SKB_FRAGS + 1);
+		linear = PAGE_SIZE - headroom;
+	}
+	skb = sock_alloc_send_pskb(sk, headroom + linear, len - linear,
+				   noblock, &err, 0);
 	if (!skb)
 		goto out;
-	if (iucv->transport == AF_IUCV_TRANS_HIPER)
-		skb_reserve(skb, sizeof(struct af_iucv_trans_hdr) + ETH_HLEN);
-	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
-		err = -EFAULT;
+	if (headroom)
+		skb_reserve(skb, headroom);
+	skb_put(skb, linear);
+	skb->len = len;
+	skb->data_len = len - linear;
+	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, len);
+	if (err)
 		goto fail;
-	}
 
 	/* wait if outstanding messages for iucv path has reached */
 	timeo = sock_sndtimeo(sk, noblock);
@@ -1148,49 +1160,67 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 			atomic_dec(&iucv->msg_sent);
 			goto fail;
 		}
-		goto release;
-	}
-	skb_queue_tail(&iucv->send_skb_q, skb);
-
-	if (((iucv->path->flags & IUCV_IPRMDATA) & iucv->flags)
-	      && skb->len <= 7) {
-		err = iucv_send_iprm(iucv->path, &txmsg, skb);
+	} else { /* Classic VM IUCV transport */
+		skb_queue_tail(&iucv->send_skb_q, skb);
+
+		if (((iucv->path->flags & IUCV_IPRMDATA) & iucv->flags) &&
+		    skb->len <= 7) {
+			err = iucv_send_iprm(iucv->path, &txmsg, skb);
+
+			/* on success: there is no message_complete callback */
+			/* for an IPRMDATA msg; remove skb from send queue   */
+			if (err == 0) {
+				skb_unlink(skb, &iucv->send_skb_q);
+				kfree_skb(skb);
+			}
 
-		/* on success: there is no message_complete callback
-		 * for an IPRMDATA msg; remove skb from send queue */
-		if (err == 0) {
-			skb_unlink(skb, &iucv->send_skb_q);
-			kfree_skb(skb);
+			/* this error should never happen since the	*/
+			/* IUCV_IPRMDATA path flag is set... sever path */
+			if (err == 0x15) {
+				pr_iucv->path_sever(iucv->path, NULL);
+				skb_unlink(skb, &iucv->send_skb_q);
+				err = -EPIPE;
+				goto fail;
+			}
+		} else if (skb_is_nonlinear(skb)) {
+			struct iucv_array *iba = (struct iucv_array *)skb->head;
+			int i;
+
+			/* skip iucv_array lying in the headroom */
+			iba[0].address = (u32)(addr_t)skb->data;
+			iba[0].length = (u32)skb_headlen(skb);
+			for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+				skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+				iba[i + 1].address =
+					(u32)(addr_t)skb_frag_address(frag);
+				iba[i + 1].length = (u32)skb_frag_size(frag);
+			}
+			err = pr_iucv->message_send(iucv->path, &txmsg,
+						    IUCV_IPBUFLST, 0,
+						    (void *)iba, skb->len);
+		} else { /* non-IPRM Linear skb */
+			err = pr_iucv->message_send(iucv->path, &txmsg,
+					0, 0, (void *)skb->data, skb->len);
 		}
-
-		/* this error should never happen since the
-		 * IUCV_IPRMDATA path flag is set... sever path */
-		if (err == 0x15) {
-			pr_iucv->path_sever(iucv->path, NULL);
+		if (err) {
+			if (err == 3) {
+				user_id[8] = 0;
+				memcpy(user_id, iucv->dst_user_id, 8);
+				appl_id[8] = 0;
+				memcpy(appl_id, iucv->dst_name, 8);
+				pr_err(
+		"Application %s on z/VM guest %s exceeds message limit\n",
+					appl_id, user_id);
+				err = -EAGAIN;
+			} else {
+				err = -EPIPE;
+			}
 			skb_unlink(skb, &iucv->send_skb_q);
-			err = -EPIPE;
 			goto fail;
 		}
-	} else
-		err = pr_iucv->message_send(iucv->path, &txmsg, 0, 0,
-					(void *) skb->data, skb->len);
-	if (err) {
-		if (err == 3) {
-			user_id[8] = 0;
-			memcpy(user_id, iucv->dst_user_id, 8);
-			appl_id[8] = 0;
-			memcpy(appl_id, iucv->dst_name, 8);
-			pr_err("Application %s on z/VM guest %s"
-				" exceeds message limit\n",
-				appl_id, user_id);
-			err = -EAGAIN;
-		} else
-			err = -EPIPE;
-		skb_unlink(skb, &iucv->send_skb_q);
-		goto fail;
 	}
 
-release:
 	release_sock(sk);
 	return len;
 
@@ -1201,42 +1231,32 @@ out:
 	return err;
 }
 
-/* iucv_fragment_skb() - Fragment a single IUCV message into multiple skb's
- *
- * Locking: must be called with message_q.lock held
- */
-static int iucv_fragment_skb(struct sock *sk, struct sk_buff *skb, int len)
+static struct sk_buff *alloc_iucv_recv_skb(unsigned long len)
 {
-	int dataleft, size, copied = 0;
-	struct sk_buff *nskb;
-
-	dataleft = len;
-	while (dataleft) {
-		if (dataleft >= sk->sk_rcvbuf / 4)
-			size = sk->sk_rcvbuf / 4;
-		else
-			size = dataleft;
-
-		nskb = alloc_skb(size, GFP_ATOMIC | GFP_DMA);
-		if (!nskb)
-			return -ENOMEM;
-
-		/* copy target class to control buffer of new skb */
-		IUCV_SKB_CB(nskb)->class = IUCV_SKB_CB(skb)->class;
-
-		/* copy data fragment */
-		memcpy(nskb->data, skb->data + copied, size);
-		copied += size;
-		dataleft -= size;
-
-		skb_reset_transport_header(nskb);
-		skb_reset_network_header(nskb);
-		nskb->len = size;
+	size_t headroom, linear;
+	struct sk_buff *skb;
+	int err;
 
-		skb_queue_tail(&iucv_sk(sk)->backlog_skb_q, nskb);
+	if (len < PAGE_SIZE) {
+		headroom = 0;
+		linear = len;
+	} else {
+		headroom = sizeof(struct iucv_array) * (MAX_SKB_FRAGS + 1);
+		linear = PAGE_SIZE - headroom;
+	}
+	skb = alloc_skb_with_frags(headroom + linear, len - linear,
+				   0, &err, GFP_ATOMIC | GFP_DMA);
+	WARN_ONCE(!skb,
+		  "alloc of recv iucv skb len=%lu failed with errcode=%d\n",
+		  len, err);
+	if (skb) {
+		if (headroom)
+			skb_reserve(skb, headroom);
+		skb_put(skb, linear);
+		skb->len = len;
+		skb->data_len = len - linear;
 	}
-
-	return 0;
+	return skb;
 }
 
 /* iucv_process_message() - Receive a single outstanding IUCV message
@@ -1263,31 +1283,32 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb,
 			skb->len = 0;
 		}
 	} else {
-		rc = pr_iucv->message_receive(path, msg,
+		if (skb_is_nonlinear(skb)) {
+			struct iucv_array *iba = (struct iucv_array *)skb->head;
+			int i;
+
+			iba[0].address = (u32)(addr_t)skb->data;
+			iba[0].length = (u32)skb_headlen(skb);
+			for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+				skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+				iba[i + 1].address =
+					(u32)(addr_t)skb_frag_address(frag);
+				iba[i + 1].length = (u32)skb_frag_size(frag);
+			}
+			rc = pr_iucv->message_receive(path, msg,
+					      IUCV_IPBUFLST,
+					      (void *)iba, len, NULL);
+		} else {
+			rc = pr_iucv->message_receive(path, msg,
 					      msg->flags & IUCV_IPRMDATA,
 					      skb->data, len, NULL);
+		}
 		if (rc) {
 			kfree_skb(skb);
 			return;
 		}
-		/* we need to fragment iucv messages for SOCK_STREAM only;
-		 * for SOCK_SEQPACKET, it is only relevant if we support
-		 * record segmentation using MSG_EOR (see also recvmsg()) */
-		if (sk->sk_type == SOCK_STREAM &&
-		    skb->truesize >= sk->sk_rcvbuf / 4) {
-			rc = iucv_fragment_skb(sk, skb, len);
-			kfree_skb(skb);
-			skb = NULL;
-			if (rc) {
-				pr_iucv->path_sever(path, NULL);
-				return;
-			}
-			skb = skb_dequeue(&iucv_sk(sk)->backlog_skb_q);
-		} else {
-			skb_reset_transport_header(skb);
-			skb_reset_network_header(skb);
-			skb->len = len;
-		}
+		WARN_ON_ONCE(skb->len != len);
 	}
 
 	IUCV_SKB_CB(skb)->offset = 0;
@@ -1306,7 +1327,7 @@ static void iucv_process_message_q(struct sock *sk)
 	struct sock_msg_q *p, *n;
 
 	list_for_each_entry_safe(p, n, &iucv->message_q.list, list) {
-		skb = alloc_skb(iucv_msg_length(&p->msg), GFP_ATOMIC | GFP_DMA);
+		skb = alloc_iucv_recv_skb(iucv_msg_length(&p->msg));
 		if (!skb)
 			break;
 		iucv_process_message(sk, skb, p->path, &p->msg);
@@ -1801,7 +1822,7 @@ static void iucv_callback_rx(struct iucv_path *path, struct iucv_message *msg)
 	if (len > sk->sk_rcvbuf)
 		goto save_message;
 
-	skb = alloc_skb(iucv_msg_length(msg), GFP_ATOMIC | GFP_DMA);
+	skb = alloc_iucv_recv_skb(iucv_msg_length(msg));
 	if (!skb)
 		goto save_message;
 
diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c
index 738008726cc6..fda7f4715c58 100644
--- a/net/kcm/kcmproc.c
+++ b/net/kcm/kcmproc.c
@@ -241,6 +241,7 @@ static const struct file_operations kcm_seq_fops = {
 	.open		= kcm_seq_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
+	.release	= seq_release_net,
 };
 
 static struct kcm_seq_muxinfo kcm_seq_muxinfo = {
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 0b68ba730a06..cb39e05b166c 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1765,18 +1765,12 @@ static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info)
 	if (!csock)
 		return -ENOENT;
 
-	prog = bpf_prog_get(info->bpf_fd);
+	prog = bpf_prog_get_type(info->bpf_fd, BPF_PROG_TYPE_SOCKET_FILTER);
 	if (IS_ERR(prog)) {
 		err = PTR_ERR(prog);
 		goto out;
 	}
 
-	if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) {
-		bpf_prog_put(prog);
-		err = -EINVAL;
-		goto out;
-	}
-
 	err = kcm_attach(sock, csock, prog);
 	if (err) {
 		bpf_prog_put(prog);
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 6edfa9980314..1e40dacaa137 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1581,7 +1581,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
 	tunnel->encap = encap;
 	if (encap == L2TP_ENCAPTYPE_UDP) {
-		struct udp_tunnel_sock_cfg udp_cfg;
+		struct udp_tunnel_sock_cfg udp_cfg = { };
 
 		udp_cfg.sk_user_data = tunnel;
 		udp_cfg.encap_type = UDP_ENCAP_L2TPINUDP;
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index e253c26f31ac..57fc5a46ce06 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -67,7 +67,6 @@ static inline struct l2tp_eth_net *l2tp_eth_pernet(struct net *net)
 	return net_generic(net, l2tp_eth_net_id);
 }
 
-static struct lock_class_key l2tp_eth_tx_busylock;
 static int l2tp_eth_dev_init(struct net_device *dev)
 {
 	struct l2tp_eth *priv = netdev_priv(dev);
@@ -75,7 +74,8 @@ static int l2tp_eth_dev_init(struct net_device *dev)
 	priv->dev = dev;
 	eth_hw_addr_random(dev);
 	eth_broadcast_addr(dev->broadcast);
-	dev->qdisc_tx_busylock = &l2tp_eth_tx_busylock;
+	netdev_lockdep_set_classes(dev);
+
 	return 0;
 }
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 6c54e03fe9c1..ea2ae6664cc8 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -611,6 +611,11 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
+	if (ipc6.tclass < 0)
+		ipc6.tclass = np->tclass;
+
+	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
@@ -620,9 +625,6 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (ipc6.hlimit < 0)
 		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
-	if (ipc6.tclass < 0)
-		ipc6.tclass = np->tclass;
-
 	if (ipc6.dontfrag < 0)
 		ipc6.dontfrag = np->dontfrag;
 
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index 6651a78e100c..c4a1c3e84e12 100644
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/netdevice.h>
+#include <net/fib_rules.h>
 #include <net/l3mdev.h>
 
 /**
@@ -107,7 +108,7 @@ EXPORT_SYMBOL_GPL(l3mdev_fib_table_by_index);
  */
 
 struct dst_entry *l3mdev_get_rt6_dst(struct net *net,
-				     const struct flowi6 *fl6)
+				     struct flowi6 *fl6)
 {
 	struct dst_entry *dst = NULL;
 	struct net_device *dev;
@@ -160,3 +161,64 @@ int l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4)
 	return rc;
 }
 EXPORT_SYMBOL_GPL(l3mdev_get_saddr);
+
+int l3mdev_get_saddr6(struct net *net, const struct sock *sk,
+		      struct flowi6 *fl6)
+{
+	struct net_device *dev;
+	int rc = 0;
+
+	if (fl6->flowi6_oif) {
+		rcu_read_lock();
+
+		dev = dev_get_by_index_rcu(net, fl6->flowi6_oif);
+		if (dev && netif_is_l3_slave(dev))
+			dev = netdev_master_upper_dev_get_rcu(dev);
+
+		if (dev && netif_is_l3_master(dev) &&
+		    dev->l3mdev_ops->l3mdev_get_saddr6)
+			rc = dev->l3mdev_ops->l3mdev_get_saddr6(dev, sk, fl6);
+
+		rcu_read_unlock();
+	}
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(l3mdev_get_saddr6);
+
+/**
+ *	l3mdev_fib_rule_match - Determine if flowi references an
+ *				L3 master device
+ *	@net: network namespace for device index lookup
+ *	@fl:  flow struct
+ */
+
+int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
+			  struct fib_lookup_arg *arg)
+{
+	struct net_device *dev;
+	int rc = 0;
+
+	rcu_read_lock();
+
+	dev = dev_get_by_index_rcu(net, fl->flowi_oif);
+	if (dev && netif_is_l3_master(dev) &&
+	    dev->l3mdev_ops->l3mdev_fib_table) {
+		arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev);
+		rc = 1;
+		goto out;
+	}
+
+	dev = dev_get_by_index_rcu(net, fl->flowi_iif);
+	if (dev && netif_is_l3_master(dev) &&
+	    dev->l3mdev_ops->l3mdev_fib_table) {
+		arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev);
+		rc = 1;
+		goto out;
+	}
+
+out:
+	rcu_read_unlock();
+
+	return rc;
+}
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 42fa81031dfa..5650c46bf91a 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -194,17 +194,21 @@ static void
 ieee80211_agg_stop_txq(struct sta_info *sta, int tid)
 {
 	struct ieee80211_txq *txq = sta->sta.txq[tid];
+	struct ieee80211_sub_if_data *sdata;
+	struct fq *fq;
 	struct txq_info *txqi;
 
 	if (!txq)
 		return;
 
 	txqi = to_txq_info(txq);
+	sdata = vif_to_sdata(txq->vif);
+	fq = &sdata->local->fq;
 
 	/* Lock here to protect against further seqno updates on dequeue */
-	spin_lock_bh(&txqi->queue.lock);
+	spin_lock_bh(&fq->lock);
 	set_bit(IEEE80211_TXQ_STOP, &txqi->flags);
-	spin_unlock_bh(&txqi->queue.lock);
+	spin_unlock_bh(&fq->lock);
 }
 
 static void
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index b251b2f7f8dd..2906c1004e1a 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -10,6 +10,7 @@
 
 #include <linux/debugfs.h>
 #include <linux/rtnetlink.h>
+#include <linux/vmalloc.h>
 #include "ieee80211_i.h"
 #include "driver-ops.h"
 #include "rate.h"
@@ -70,6 +71,177 @@ DEBUGFS_READONLY_FILE(wep_iv, "%#08x",
 DEBUGFS_READONLY_FILE(rate_ctrl_alg, "%s",
 	local->rate_ctrl ? local->rate_ctrl->ops->name : "hw/driver");
 
+struct aqm_info {
+	struct ieee80211_local *local;
+	size_t size;
+	size_t len;
+	unsigned char buf[0];
+};
+
+#define AQM_HDR_LEN 200
+#define AQM_HW_ENTRY_LEN 40
+#define AQM_TXQ_ENTRY_LEN 110
+
+static int aqm_open(struct inode *inode, struct file *file)
+{
+	struct ieee80211_local *local = inode->i_private;
+	struct ieee80211_sub_if_data *sdata;
+	struct sta_info *sta;
+	struct txq_info *txqi;
+	struct fq *fq = &local->fq;
+	struct aqm_info *info = NULL;
+	int len = 0;
+	int i;
+
+	if (!local->ops->wake_tx_queue)
+		return -EOPNOTSUPP;
+
+	len += AQM_HDR_LEN;
+	len += 6 * AQM_HW_ENTRY_LEN;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdata, &local->interfaces, list)
+		len += AQM_TXQ_ENTRY_LEN;
+	list_for_each_entry_rcu(sta, &local->sta_list, list)
+		len += AQM_TXQ_ENTRY_LEN * ARRAY_SIZE(sta->sta.txq);
+	rcu_read_unlock();
+
+	info = vmalloc(len);
+	if (!info)
+		return -ENOMEM;
+
+	spin_lock_bh(&local->fq.lock);
+	rcu_read_lock();
+
+	file->private_data = info;
+	info->local = local;
+	info->size = len;
+	len = 0;
+
+	len += scnprintf(info->buf + len, info->size - len,
+			 "* hw\n"
+			 "access name value\n"
+			 "R fq_flows_cnt %u\n"
+			 "R fq_backlog %u\n"
+			 "R fq_overlimit %u\n"
+			 "R fq_collisions %u\n"
+			 "RW fq_limit %u\n"
+			 "RW fq_quantum %u\n",
+			 fq->flows_cnt,
+			 fq->backlog,
+			 fq->overlimit,
+			 fq->collisions,
+			 fq->limit,
+			 fq->quantum);
+
+	len += scnprintf(info->buf + len,
+			 info->size - len,
+			 "* vif\n"
+			 "ifname addr ac backlog-bytes backlog-packets flows overlimit collisions tx-bytes tx-packets\n");
+
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		txqi = to_txq_info(sdata->vif.txq);
+		len += scnprintf(info->buf + len, info->size - len,
+				 "%s %pM %u %u %u %u %u %u %u %u\n",
+				 sdata->name,
+				 sdata->vif.addr,
+				 txqi->txq.ac,
+				 txqi->tin.backlog_bytes,
+				 txqi->tin.backlog_packets,
+				 txqi->tin.flows,
+				 txqi->tin.overlimit,
+				 txqi->tin.collisions,
+				 txqi->tin.tx_bytes,
+				 txqi->tin.tx_packets);
+	}
+
+	len += scnprintf(info->buf + len,
+			 info->size - len,
+			 "* sta\n"
+			 "ifname addr tid ac backlog-bytes backlog-packets flows overlimit collisions tx-bytes tx-packets\n");
+
+	list_for_each_entry_rcu(sta, &local->sta_list, list) {
+		sdata = sta->sdata;
+		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
+			txqi = to_txq_info(sta->sta.txq[i]);
+			len += scnprintf(info->buf + len, info->size - len,
+					 "%s %pM %d %d %u %u %u %u %u %u %u\n",
+					 sdata->name,
+					 sta->sta.addr,
+					 txqi->txq.tid,
+					 txqi->txq.ac,
+					 txqi->tin.backlog_bytes,
+					 txqi->tin.backlog_packets,
+					 txqi->tin.flows,
+					 txqi->tin.overlimit,
+					 txqi->tin.collisions,
+					 txqi->tin.tx_bytes,
+					 txqi->tin.tx_packets);
+		}
+	}
+
+	info->len = len;
+
+	rcu_read_unlock();
+	spin_unlock_bh(&local->fq.lock);
+
+	return 0;
+}
+
+static int aqm_release(struct inode *inode, struct file *file)
+{
+	vfree(file->private_data);
+	return 0;
+}
+
+static ssize_t aqm_read(struct file *file,
+			char __user *user_buf,
+			size_t count,
+			loff_t *ppos)
+{
+	struct aqm_info *info = file->private_data;
+
+	return simple_read_from_buffer(user_buf, count, ppos,
+				       info->buf, info->len);
+}
+
+static ssize_t aqm_write(struct file *file,
+			 const char __user *user_buf,
+			 size_t count,
+			 loff_t *ppos)
+{
+	struct aqm_info *info = file->private_data;
+	struct ieee80211_local *local = info->local;
+	char buf[100];
+	size_t len;
+
+	if (count > sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(buf, user_buf, count))
+		return -EFAULT;
+
+	buf[sizeof(buf) - 1] = '\0';
+	len = strlen(buf);
+	if (len > 0 && buf[len-1] == '\n')
+		buf[len-1] = 0;
+
+	if (sscanf(buf, "fq_limit %u", &local->fq.limit) == 1)
+		return count;
+	else if (sscanf(buf, "fq_quantum %u", &local->fq.quantum) == 1)
+		return count;
+
+	return -EINVAL;
+}
+
+static const struct file_operations aqm_ops = {
+	.write = aqm_write,
+	.read = aqm_read,
+	.open = aqm_open,
+	.release = aqm_release,
+	.llseek = default_llseek,
+};
+
 #ifdef CONFIG_PM
 static ssize_t reset_write(struct file *file, const char __user *user_buf,
 			   size_t count, loff_t *ppos)
@@ -256,6 +428,7 @@ void debugfs_hw_add(struct ieee80211_local *local)
 	DEBUGFS_ADD(hwflags);
 	DEBUGFS_ADD(user_power);
 	DEBUGFS_ADD(power);
+	DEBUGFS_ADD_MODE(aqm, 0600);
 
 	statsd = debugfs_create_dir("statistics", phyd);
 
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 33dfcbc2bf9c..fd334133ff45 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -328,14 +328,88 @@ STA_OPS(ht_capa);
 static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf,
 				 size_t count, loff_t *ppos)
 {
-	char buf[128], *p = buf;
+	char buf[512], *p = buf;
 	struct sta_info *sta = file->private_data;
 	struct ieee80211_sta_vht_cap *vhtc = &sta->sta.vht_cap;
 
 	p += scnprintf(p, sizeof(buf) + buf - p, "VHT %ssupported\n",
 			vhtc->vht_supported ? "" : "not ");
 	if (vhtc->vht_supported) {
-		p += scnprintf(p, sizeof(buf)+buf-p, "cap: %#.8x\n", vhtc->cap);
+		p += scnprintf(p, sizeof(buf) + buf - p, "cap: %#.8x\n",
+			       vhtc->cap);
+#define PFLAG(a, b)							\
+		do {							\
+			if (vhtc->cap & IEEE80211_VHT_CAP_ ## a)	\
+				p += scnprintf(p, sizeof(buf) + buf - p, \
+					       "\t\t%s\n", b);		\
+		} while (0)
+
+		switch (vhtc->cap & 0x3) {
+		case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\tMAX-MPDU-3895\n");
+			break;
+		case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\tMAX-MPDU-7991\n");
+			break;
+		case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\tMAX-MPDU-11454\n");
+			break;
+		default:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\tMAX-MPDU-UNKNOWN\n");
+		};
+		switch (vhtc->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) {
+		case 0:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\t80Mhz\n");
+			break;
+		case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\t160Mhz\n");
+			break;
+		case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\t80+80Mhz\n");
+			break;
+		default:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\tUNKNOWN-MHZ: 0x%x\n",
+				       (vhtc->cap >> 2) & 0x3);
+		};
+		PFLAG(RXLDPC, "RXLDPC");
+		PFLAG(SHORT_GI_80, "SHORT-GI-80");
+		PFLAG(SHORT_GI_160, "SHORT-GI-160");
+		PFLAG(TXSTBC, "TXSTBC");
+		p += scnprintf(p, sizeof(buf) + buf - p,
+			       "\t\tRXSTBC_%d\n", (vhtc->cap >> 8) & 0x7);
+		PFLAG(SU_BEAMFORMER_CAPABLE, "SU-BEAMFORMER-CAPABLE");
+		PFLAG(SU_BEAMFORMEE_CAPABLE, "SU-BEAMFORMEE-CAPABLE");
+		p += scnprintf(p, sizeof(buf) + buf - p,
+			"\t\tBEAMFORMEE-STS: 0x%x\n",
+			(vhtc->cap & IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK) >>
+			IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT);
+		p += scnprintf(p, sizeof(buf) + buf - p,
+			"\t\tSOUNDING-DIMENSIONS: 0x%x\n",
+			(vhtc->cap & IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK)
+			>> IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT);
+		PFLAG(MU_BEAMFORMER_CAPABLE, "MU-BEAMFORMER-CAPABLE");
+		PFLAG(MU_BEAMFORMEE_CAPABLE, "MU-BEAMFORMEE-CAPABLE");
+		PFLAG(VHT_TXOP_PS, "TXOP-PS");
+		PFLAG(HTC_VHT, "HTC-VHT");
+		p += scnprintf(p, sizeof(buf) + buf - p,
+			"\t\tMPDU-LENGTH-EXPONENT: 0x%x\n",
+			(vhtc->cap & IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK) >>
+			IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT);
+		PFLAG(VHT_LINK_ADAPTATION_VHT_UNSOL_MFB,
+		      "LINK-ADAPTATION-VHT-UNSOL-MFB");
+		p += scnprintf(p, sizeof(buf) + buf - p,
+			"\t\tLINK-ADAPTATION-VHT-MRQ-MFB: 0x%x\n",
+			(vhtc->cap & IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB) >> 26);
+		PFLAG(RX_ANTENNA_PATTERN, "RX-ANTENNA-PATTERN");
+		PFLAG(TX_ANTENNA_PATTERN, "TX-ANTENNA-PATTERN");
 
 		p += scnprintf(p, sizeof(buf)+buf-p, "RX MCS: %.4x\n",
 			       le16_to_cpu(vhtc->vht_mcs.rx_mcs_map));
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 9438c9406687..54edfb6fc1d1 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -30,6 +30,7 @@
 #include <net/ieee80211_radiotap.h>
 #include <net/cfg80211.h>
 #include <net/mac80211.h>
+#include <net/fq.h>
 #include "key.h"
 #include "sta_info.h"
 #include "debug.h"
@@ -805,10 +806,19 @@ enum txq_info_flags {
 	IEEE80211_TXQ_NO_AMSDU,
 };
 
+/**
+ * struct txq_info - per tid queue
+ *
+ * @tin: contains packets split into multiple flows
+ * @def_flow: used as a fallback flow when a packet destined to @tin hashes to
+ *	a fq_flow which is already owned by a different tin
+ * @def_cvars: codel vars for @def_flow
+ */
 struct txq_info {
-	struct sk_buff_head queue;
+	struct fq_tin tin;
+	struct fq_flow def_flow;
+	struct codel_vars def_cvars;
 	unsigned long flags;
-	unsigned long byte_cnt;
 
 	/* keep last! */
 	struct ieee80211_txq txq;
@@ -856,7 +866,7 @@ struct ieee80211_sub_if_data {
 	bool control_port_no_encrypt;
 	int encrypt_headroom;
 
-	atomic_t txqs_len[IEEE80211_NUM_ACS];
+	atomic_t num_tx_queued;
 	struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS];
 	struct mac80211_qos_map __rcu *qos_map;
 
@@ -1099,6 +1109,11 @@ struct ieee80211_local {
 	 * it first anyway so they become a no-op */
 	struct ieee80211_hw hw;
 
+	struct fq fq;
+	struct codel_vars *cvars;
+	struct codel_params cparams;
+	struct codel_stats cstats;
+
 	const struct ieee80211_ops *ops;
 
 	/*
@@ -1931,9 +1946,13 @@ static inline bool ieee80211_can_run_worker(struct ieee80211_local *local)
 	return true;
 }
 
-void ieee80211_init_tx_queue(struct ieee80211_sub_if_data *sdata,
-			     struct sta_info *sta,
-			     struct txq_info *txq, int tid);
+int ieee80211_txq_setup_flows(struct ieee80211_local *local);
+void ieee80211_txq_teardown_flows(struct ieee80211_local *local);
+void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata,
+			struct sta_info *sta,
+			struct txq_info *txq, int tid);
+void ieee80211_txq_purge(struct ieee80211_local *local,
+			 struct txq_info *txqi);
 void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
 			 u16 transaction, u16 auth_alg, u16 status,
 			 const u8 *extra, size_t extra_len, const u8 *bssid,
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index c59af3eb9fa4..b123a9e325b3 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -779,6 +779,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 			      bool going_down)
 {
 	struct ieee80211_local *local = sdata->local;
+	struct fq *fq = &local->fq;
 	unsigned long flags;
 	struct sk_buff *skb, *tmp;
 	u32 hw_reconf_flags = 0;
@@ -977,12 +978,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	if (sdata->vif.txq) {
 		struct txq_info *txqi = to_txq_info(sdata->vif.txq);
 
-		spin_lock_bh(&txqi->queue.lock);
-		ieee80211_purge_tx_queue(&local->hw, &txqi->queue);
-		txqi->byte_cnt = 0;
-		spin_unlock_bh(&txqi->queue.lock);
-
-		atomic_set(&sdata->txqs_len[txqi->txq.ac], 0);
+		spin_lock_bh(&fq->lock);
+		ieee80211_txq_purge(local, txqi);
+		spin_unlock_bh(&fq->lock);
 	}
 
 	if (local->open_count == 0)
@@ -1198,6 +1196,12 @@ static void ieee80211_if_setup(struct net_device *dev)
 	dev->destructor = ieee80211_if_free;
 }
 
+static void ieee80211_if_setup_no_queue(struct net_device *dev)
+{
+	ieee80211_if_setup(dev);
+	dev->priv_flags |= IFF_NO_QUEUE;
+}
+
 static void ieee80211_iface_work(struct work_struct *work)
 {
 	struct ieee80211_sub_if_data *sdata =
@@ -1707,6 +1711,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 	struct net_device *ndev = NULL;
 	struct ieee80211_sub_if_data *sdata = NULL;
 	struct txq_info *txqi;
+	void (*if_setup)(struct net_device *dev);
 	int ret, i;
 	int txqs = 1;
 
@@ -1734,12 +1739,17 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 			txq_size += sizeof(struct txq_info) +
 				    local->hw.txq_data_size;
 
+		if (local->ops->wake_tx_queue)
+			if_setup = ieee80211_if_setup_no_queue;
+		else
+			if_setup = ieee80211_if_setup;
+
 		if (local->hw.queues >= IEEE80211_NUM_ACS)
 			txqs = IEEE80211_NUM_ACS;
 
 		ndev = alloc_netdev_mqs(size + txq_size,
 					name, name_assign_type,
-					ieee80211_if_setup, txqs, 1);
+					if_setup, txqs, 1);
 		if (!ndev)
 			return -ENOMEM;
 		dev_net_set(ndev, wiphy_net(local->hw.wiphy));
@@ -1780,7 +1790,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 
 		if (txq_size) {
 			txqi = netdev_priv(ndev) + size;
-			ieee80211_init_tx_queue(sdata, NULL, txqi, 0);
+			ieee80211_txq_init(sdata, NULL, txqi, 0);
 		}
 
 		sdata->dev = ndev;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 7ee91d6151d1..d00ea9b13f49 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1055,9 +1055,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 
 	local->dynamic_ps_forced_timeout = -1;
 
-	if (!local->hw.txq_ac_max_pending)
-		local->hw.txq_ac_max_pending = 64;
-
 	result = ieee80211_wep_init(local);
 	if (result < 0)
 		wiphy_debug(local->hw.wiphy, "Failed to initialize wep: %d\n",
@@ -1089,6 +1086,10 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 
 	rtnl_unlock();
 
+	result = ieee80211_txq_setup_flows(local);
+	if (result)
+		goto fail_flows;
+
 #ifdef CONFIG_INET
 	local->ifa_notifier.notifier_call = ieee80211_ifa_changed;
 	result = register_inetaddr_notifier(&local->ifa_notifier);
@@ -1114,6 +1115,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 #if defined(CONFIG_INET) || defined(CONFIG_IPV6)
  fail_ifa:
 #endif
+	ieee80211_txq_teardown_flows(local);
+ fail_flows:
 	rtnl_lock();
 	rate_control_deinitialize(local);
 	ieee80211_remove_interfaces(local);
@@ -1172,6 +1175,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw)
 	skb_queue_purge(&local->skb_queue);
 	skb_queue_purge(&local->skb_queue_unreliable);
 	skb_queue_purge(&local->skb_queue_tdls_chsw);
+	ieee80211_txq_teardown_flows(local);
 
 	destroy_workqueue(local->workqueue);
 	wiphy_unregister(local->hw.wiphy);
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 4c6404e1ad6e..6a1603bcdced 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -148,19 +148,26 @@ u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata)
 void mesh_sta_cleanup(struct sta_info *sta)
 {
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	u32 changed;
+	u32 changed = 0;
 
 	/*
 	 * maybe userspace handles peer allocation and peering, but in either
 	 * case the beacon is still generated by the kernel and we might need
 	 * an update.
 	 */
-	changed = mesh_accept_plinks_update(sdata);
+	if (sdata->u.mesh.user_mpm &&
+	    sta->mesh->plink_state == NL80211_PLINK_ESTAB)
+		changed |= mesh_plink_dec_estab_count(sdata);
+	changed |= mesh_accept_plinks_update(sdata);
 	if (!sdata->u.mesh.user_mpm) {
 		changed |= mesh_plink_deactivate(sta);
 		del_timer_sync(&sta->mesh->plink_timer);
 	}
 
+	/* make sure no readers can access nexthop sta from here on */
+	mesh_path_flush_by_nexthop(sta);
+	synchronize_net();
+
 	if (changed)
 		ieee80211_mbss_info_change_notify(sdata, changed);
 }
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 5e65e838992a..9a1eb70cb120 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1268,7 +1268,7 @@ static void sta_ps_start(struct sta_info *sta)
 	for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
 		struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
 
-		if (!skb_queue_len(&txqi->queue))
+		if (!txqi->tin.backlog_packets)
 			set_bit(tid, &sta->txq_buffered_tids);
 		else
 			clear_bit(tid, &sta->txq_buffered_tids);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 5ccfdbd406bd..76b737dcc36f 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -90,6 +90,7 @@ static void __cleanup_single_sta(struct sta_info *sta)
 	struct tid_ampdu_tx *tid_tx;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct ieee80211_local *local = sdata->local;
+	struct fq *fq = &local->fq;
 	struct ps_data *ps;
 
 	if (test_sta_flag(sta, WLAN_STA_PS_STA) ||
@@ -113,11 +114,10 @@ static void __cleanup_single_sta(struct sta_info *sta)
 	if (sta->sta.txq[0]) {
 		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
 			struct txq_info *txqi = to_txq_info(sta->sta.txq[i]);
-			int n = skb_queue_len(&txqi->queue);
 
-			ieee80211_purge_tx_queue(&local->hw, &txqi->queue);
-			atomic_sub(n, &sdata->txqs_len[txqi->txq.ac]);
-			txqi->byte_cnt = 0;
+			spin_lock_bh(&fq->lock);
+			ieee80211_txq_purge(local, txqi);
+			spin_unlock_bh(&fq->lock);
 		}
 	}
 
@@ -368,7 +368,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
 			struct txq_info *txq = txq_data + i * size;
 
-			ieee80211_init_tx_queue(sdata, sta, txq, i);
+			ieee80211_txq_init(sdata, sta, txq, i);
 		}
 	}
 
@@ -1211,7 +1211,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
 			struct txq_info *txqi = to_txq_info(sta->sta.txq[i]);
 
-			if (!skb_queue_len(&txqi->queue))
+			if (!txqi->tin.backlog_packets)
 				continue;
 
 			drv_wake_tx_queue(local, txqi);
@@ -1648,7 +1648,7 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 		for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
 			struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
 
-			if (!(tids & BIT(tid)) || skb_queue_len(&txqi->queue))
+			if (!(tids & BIT(tid)) || txqi->tin.backlog_packets)
 				continue;
 
 			sta_info_recalc_tim(sta);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index c8b8ccc370eb..78b0ef32dddd 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -280,7 +280,7 @@ struct ieee80211_fast_tx {
 	u8 sa_offs, da_offs, pn_offs;
 	u8 band;
 	u8 hdr[30 + 2 + IEEE80211_FAST_XMIT_MAX_IV +
-	       sizeof(rfc1042_header)];
+	       sizeof(rfc1042_header)] __aligned(2);
 
 	struct rcu_head rcu_head;
 };
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 203044379ce0..44ec605a5682 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -24,7 +24,10 @@
 #include <net/ieee80211_radiotap.h>
 #include <net/cfg80211.h>
 #include <net/mac80211.h>
+#include <net/codel.h>
+#include <net/codel_impl.h>
 #include <asm/unaligned.h>
+#include <net/fq_impl.h>
 
 #include "ieee80211_i.h"
 #include "driver-ops.h"
@@ -1236,27 +1239,21 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
 	return TX_CONTINUE;
 }
 
-static void ieee80211_drv_tx(struct ieee80211_local *local,
-			     struct ieee80211_vif *vif,
-			     struct ieee80211_sta *pubsta,
-			     struct sk_buff *skb)
+static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local,
+					  struct ieee80211_vif *vif,
+					  struct ieee80211_sta *pubsta,
+					  struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
-	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_tx_control control = {
-		.sta = pubsta,
-	};
 	struct ieee80211_txq *txq = NULL;
-	struct txq_info *txqi;
-	u8 ac;
 
 	if ((info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) ||
 	    (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE))
-		goto tx_normal;
+		return NULL;
 
 	if (!ieee80211_is_data(hdr->frame_control))
-		goto tx_normal;
+		return NULL;
 
 	if (pubsta) {
 		u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
@@ -1267,51 +1264,230 @@ static void ieee80211_drv_tx(struct ieee80211_local *local,
 	}
 
 	if (!txq)
-		goto tx_normal;
+		return NULL;
 
-	ac = txq->ac;
-	txqi = to_txq_info(txq);
-	atomic_inc(&sdata->txqs_len[ac]);
-	if (atomic_read(&sdata->txqs_len[ac]) >= local->hw.txq_ac_max_pending)
-		netif_stop_subqueue(sdata->dev, ac);
+	return to_txq_info(txq);
+}
 
-	spin_lock_bh(&txqi->queue.lock);
-	txqi->byte_cnt += skb->len;
-	__skb_queue_tail(&txqi->queue, skb);
-	spin_unlock_bh(&txqi->queue.lock);
+static void ieee80211_set_skb_enqueue_time(struct sk_buff *skb)
+{
+	IEEE80211_SKB_CB(skb)->control.enqueue_time = codel_get_time();
+}
 
-	drv_wake_tx_queue(local, txqi);
+static void ieee80211_set_skb_vif(struct sk_buff *skb, struct txq_info *txqi)
+{
+	IEEE80211_SKB_CB(skb)->control.vif = txqi->txq.vif;
+}
 
-	return;
+static u32 codel_skb_len_func(const struct sk_buff *skb)
+{
+	return skb->len;
+}
+
+static codel_time_t codel_skb_time_func(const struct sk_buff *skb)
+{
+	const struct ieee80211_tx_info *info;
 
-tx_normal:
-	drv_tx(local, &control, skb);
+	info = (const struct ieee80211_tx_info *)skb->cb;
+	return info->control.enqueue_time;
+}
+
+static struct sk_buff *codel_dequeue_func(struct codel_vars *cvars,
+					  void *ctx)
+{
+	struct ieee80211_local *local;
+	struct txq_info *txqi;
+	struct fq *fq;
+	struct fq_flow *flow;
+
+	txqi = ctx;
+	local = vif_to_sdata(txqi->txq.vif)->local;
+	fq = &local->fq;
+
+	if (cvars == &txqi->def_cvars)
+		flow = &txqi->def_flow;
+	else
+		flow = &fq->flows[cvars - local->cvars];
+
+	return fq_flow_dequeue(fq, flow);
+}
+
+static void codel_drop_func(struct sk_buff *skb,
+			    void *ctx)
+{
+	struct ieee80211_local *local;
+	struct ieee80211_hw *hw;
+	struct txq_info *txqi;
+
+	txqi = ctx;
+	local = vif_to_sdata(txqi->txq.vif)->local;
+	hw = &local->hw;
+
+	ieee80211_free_txskb(hw, skb);
+}
+
+static struct sk_buff *fq_tin_dequeue_func(struct fq *fq,
+					   struct fq_tin *tin,
+					   struct fq_flow *flow)
+{
+	struct ieee80211_local *local;
+	struct txq_info *txqi;
+	struct codel_vars *cvars;
+	struct codel_params *cparams;
+	struct codel_stats *cstats;
+
+	local = container_of(fq, struct ieee80211_local, fq);
+	txqi = container_of(tin, struct txq_info, tin);
+	cparams = &local->cparams;
+	cstats = &local->cstats;
+
+	if (flow == &txqi->def_flow)
+		cvars = &txqi->def_cvars;
+	else
+		cvars = &local->cvars[flow - fq->flows];
+
+	return codel_dequeue(txqi,
+			     &flow->backlog,
+			     cparams,
+			     cvars,
+			     cstats,
+			     codel_skb_len_func,
+			     codel_skb_time_func,
+			     codel_drop_func,
+			     codel_dequeue_func);
+}
+
+static void fq_skb_free_func(struct fq *fq,
+			     struct fq_tin *tin,
+			     struct fq_flow *flow,
+			     struct sk_buff *skb)
+{
+	struct ieee80211_local *local;
+
+	local = container_of(fq, struct ieee80211_local, fq);
+	ieee80211_free_txskb(&local->hw, skb);
+}
+
+static struct fq_flow *fq_flow_get_default_func(struct fq *fq,
+						struct fq_tin *tin,
+						int idx,
+						struct sk_buff *skb)
+{
+	struct txq_info *txqi;
+
+	txqi = container_of(tin, struct txq_info, tin);
+	return &txqi->def_flow;
+}
+
+static void ieee80211_txq_enqueue(struct ieee80211_local *local,
+				  struct txq_info *txqi,
+				  struct sk_buff *skb)
+{
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin = &txqi->tin;
+
+	ieee80211_set_skb_enqueue_time(skb);
+	fq_tin_enqueue(fq, tin, skb,
+		       fq_skb_free_func,
+		       fq_flow_get_default_func);
+}
+
+void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata,
+			struct sta_info *sta,
+			struct txq_info *txqi, int tid)
+{
+	fq_tin_init(&txqi->tin);
+	fq_flow_init(&txqi->def_flow);
+	codel_vars_init(&txqi->def_cvars);
+
+	txqi->txq.vif = &sdata->vif;
+
+	if (sta) {
+		txqi->txq.sta = &sta->sta;
+		sta->sta.txq[tid] = &txqi->txq;
+		txqi->txq.tid = tid;
+		txqi->txq.ac = ieee802_1d_to_ac[tid & 7];
+	} else {
+		sdata->vif.txq = &txqi->txq;
+		txqi->txq.tid = 0;
+		txqi->txq.ac = IEEE80211_AC_BE;
+	}
+}
+
+void ieee80211_txq_purge(struct ieee80211_local *local,
+			 struct txq_info *txqi)
+{
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin = &txqi->tin;
+
+	fq_tin_reset(fq, tin, fq_skb_free_func);
+}
+
+int ieee80211_txq_setup_flows(struct ieee80211_local *local)
+{
+	struct fq *fq = &local->fq;
+	int ret;
+	int i;
+
+	if (!local->ops->wake_tx_queue)
+		return 0;
+
+	ret = fq_init(fq, 4096);
+	if (ret)
+		return ret;
+
+	codel_params_init(&local->cparams);
+	codel_stats_init(&local->cstats);
+	local->cparams.interval = MS2TIME(100);
+	local->cparams.target = MS2TIME(20);
+	local->cparams.ecn = true;
+
+	local->cvars = kcalloc(fq->flows_cnt, sizeof(local->cvars[0]),
+			       GFP_KERNEL);
+	if (!local->cvars) {
+		fq_reset(fq, fq_skb_free_func);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < fq->flows_cnt; i++)
+		codel_vars_init(&local->cvars[i]);
+
+	return 0;
+}
+
+void ieee80211_txq_teardown_flows(struct ieee80211_local *local)
+{
+	struct fq *fq = &local->fq;
+
+	if (!local->ops->wake_tx_queue)
+		return;
+
+	kfree(local->cvars);
+	local->cvars = NULL;
+
+	fq_reset(fq, fq_skb_free_func);
 }
 
 struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 				     struct ieee80211_txq *txq)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
-	struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif);
 	struct txq_info *txqi = container_of(txq, struct txq_info, txq);
 	struct ieee80211_hdr *hdr;
 	struct sk_buff *skb = NULL;
-	u8 ac = txq->ac;
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin = &txqi->tin;
 
-	spin_lock_bh(&txqi->queue.lock);
+	spin_lock_bh(&fq->lock);
 
 	if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags))
 		goto out;
 
-	skb = __skb_dequeue(&txqi->queue);
+	skb = fq_tin_dequeue(fq, tin, fq_tin_dequeue_func);
 	if (!skb)
 		goto out;
 
-	txqi->byte_cnt -= skb->len;
-
-	atomic_dec(&sdata->txqs_len[ac]);
-	if (__netif_subqueue_stopped(sdata->dev, ac))
-		ieee80211_propagate_queue_wake(local, sdata->vif.hw_queue[ac]);
+	ieee80211_set_skb_vif(skb, txqi);
 
 	hdr = (struct ieee80211_hdr *)skb->data;
 	if (txq->sta && ieee80211_is_data_qos(hdr->frame_control)) {
@@ -1327,7 +1503,7 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 	}
 
 out:
-	spin_unlock_bh(&txqi->queue.lock);
+	spin_unlock_bh(&fq->lock);
 
 	if (skb && skb_has_frag_list(skb) &&
 	    !ieee80211_hw_check(&local->hw, TX_FRAG_LIST))
@@ -1343,7 +1519,10 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local,
 			       struct sk_buff_head *skbs,
 			       bool txpending)
 {
+	struct ieee80211_tx_control control = {};
+	struct fq *fq = &local->fq;
 	struct sk_buff *skb, *tmp;
+	struct txq_info *txqi;
 	unsigned long flags;
 
 	skb_queue_walk_safe(skbs, skb, tmp) {
@@ -1358,6 +1537,21 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local,
 		}
 #endif
 
+		txqi = ieee80211_get_txq(local, vif, sta, skb);
+		if (txqi) {
+			info->control.vif = vif;
+
+			__skb_unlink(skb, skbs);
+
+			spin_lock_bh(&fq->lock);
+			ieee80211_txq_enqueue(local, txqi, skb);
+			spin_unlock_bh(&fq->lock);
+
+			drv_wake_tx_queue(local, txqi);
+
+			continue;
+		}
+
 		spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
 		if (local->queue_stop_reasons[q] ||
 		    (!txpending && !skb_queue_empty(&local->pending[q]))) {
@@ -1400,9 +1594,10 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local,
 		spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 
 		info->control.vif = vif;
+		control.sta = sta;
 
 		__skb_unlink(skb, skbs);
-		ieee80211_drv_tx(local, vif, sta, skb);
+		drv_tx(local, &control, skb);
 	}
 
 	return true;
@@ -2882,6 +3077,9 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 				      struct sk_buff *skb)
 {
 	struct ieee80211_local *local = sdata->local;
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin;
+	struct fq_flow *flow;
 	u8 tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
 	struct ieee80211_txq *txq = sta->sta.txq[tid];
 	struct txq_info *txqi;
@@ -2893,6 +3091,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	__be16 len;
 	void *data;
 	bool ret = false;
+	unsigned int orig_len;
 	int n = 1, nfrags;
 
 	if (!ieee80211_hw_check(&local->hw, TX_AMSDU))
@@ -2909,12 +3108,20 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 		max_amsdu_len = min_t(int, max_amsdu_len,
 				      sta->sta.max_rc_amsdu_len);
 
-	spin_lock_bh(&txqi->queue.lock);
+	spin_lock_bh(&fq->lock);
+
+	/* TODO: Ideally aggregation should be done on dequeue to remain
+	 * responsive to environment changes.
+	 */
 
-	head = skb_peek_tail(&txqi->queue);
+	tin = &txqi->tin;
+	flow = fq_flow_classify(fq, tin, skb, fq_flow_get_default_func);
+	head = skb_peek_tail(&flow->queue);
 	if (!head)
 		goto out;
 
+	orig_len = head->len;
+
 	if (skb->len + head->len > max_amsdu_len)
 		goto out;
 
@@ -2953,8 +3160,13 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	head->data_len += skb->len;
 	*frag_tail = skb;
 
+	flow->backlog += head->len - orig_len;
+	tin->backlog_bytes += head->len - orig_len;
+
+	fq_recalc_backlog(fq, tin, flow);
+
 out:
-	spin_unlock_bh(&txqi->queue.lock);
+	spin_unlock_bh(&fq->lock);
 
 	return ret;
 }
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 905003f75c4d..42bf0b6685e8 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -244,6 +244,9 @@ void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue)
 	struct ieee80211_sub_if_data *sdata;
 	int n_acs = IEEE80211_NUM_ACS;
 
+	if (local->ops->wake_tx_queue)
+		return;
+
 	if (local->hw.queues < IEEE80211_NUM_ACS)
 		n_acs = 1;
 
@@ -260,11 +263,6 @@ void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue)
 		for (ac = 0; ac < n_acs; ac++) {
 			int ac_queue = sdata->vif.hw_queue[ac];
 
-			if (local->ops->wake_tx_queue &&
-			    (atomic_read(&sdata->txqs_len[ac]) >
-			     local->hw.txq_ac_max_pending))
-				continue;
-
 			if (ac_queue == queue ||
 			    (sdata->vif.cab_queue == queue &&
 			     local->queue_stop_reasons[ac_queue] == 0 &&
@@ -352,6 +350,9 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue,
 	if (__test_and_set_bit(reason, &local->queue_stop_reasons[queue]))
 		return;
 
+	if (local->ops->wake_tx_queue)
+		return;
+
 	if (local->hw.queues < IEEE80211_NUM_ACS)
 		n_acs = 1;
 
@@ -3388,25 +3389,6 @@ u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo)
 	return buf;
 }
 
-void ieee80211_init_tx_queue(struct ieee80211_sub_if_data *sdata,
-			     struct sta_info *sta,
-			     struct txq_info *txqi, int tid)
-{
-	skb_queue_head_init(&txqi->queue);
-	txqi->txq.vif = &sdata->vif;
-
-	if (sta) {
-		txqi->txq.sta = &sta->sta;
-		sta->sta.txq[tid] = &txqi->txq;
-		txqi->txq.tid = tid;
-		txqi->txq.ac = ieee802_1d_to_ac[tid & 7];
-	} else {
-		sdata->vif.txq = &txqi->txq;
-		txqi->txq.tid = 0;
-		txqi->txq.ac = IEEE80211_AC_BE;
-	}
-}
-
 void ieee80211_txq_get_depth(struct ieee80211_txq *txq,
 			     unsigned long *frame_cnt,
 			     unsigned long *byte_cnt)
@@ -3414,9 +3396,9 @@ void ieee80211_txq_get_depth(struct ieee80211_txq *txq,
 	struct txq_info *txqi = to_txq_info(txq);
 
 	if (frame_cnt)
-		*frame_cnt = txqi->queue.qlen;
+		*frame_cnt = txqi->tin.backlog_packets;
 
 	if (byte_cnt)
-		*byte_cnt = txqi->byte_cnt;
+		*byte_cnt = txqi->tin.backlog_bytes;
 }
 EXPORT_SYMBOL(ieee80211_txq_get_depth);
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 7a4aa3450dd7..e9beaa58573c 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1009,9 +1009,10 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 	unsigned int flags;
 
 	if (event == NETDEV_REGISTER) {
-		/* For now just support ethernet devices */
-		if ((dev->type == ARPHRD_ETHER) ||
-		    (dev->type == ARPHRD_LOOPBACK)) {
+		/* For now just support Ethernet and IPGRE devices */
+		if (dev->type == ARPHRD_ETHER ||
+		    dev->type == ARPHRD_LOOPBACK ||
+		    dev->type == ARPHRD_IPGRE) {
 			mdev = mpls_add_dev(dev);
 			if (IS_ERR(mdev))
 				return notifier_from_errno(PTR_ERR(mdev));
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 2cb3c626cd43..096a45103f14 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -762,7 +762,7 @@ static int expire_quiescent_template(struct netns_ipvs *ipvs,
  *	If available, return 1, otherwise invalidate this connection
  *	template and return 0.
  */
-int ip_vs_check_template(struct ip_vs_conn *ct)
+int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest)
 {
 	struct ip_vs_dest *dest = ct->dest;
 	struct netns_ipvs *ipvs = ct->ipvs;
@@ -772,7 +772,8 @@ int ip_vs_check_template(struct ip_vs_conn *ct)
 	 */
 	if ((dest == NULL) ||
 	    !(dest->flags & IP_VS_DEST_F_AVAILABLE) ||
-	    expire_quiescent_template(ipvs, dest)) {
+	    expire_quiescent_template(ipvs, dest) ||
+	    (cdest && (dest != cdest))) {
 		IP_VS_DBG_BUF(9, "check_template: dest not available for "
 			      "protocol %s s:%s:%d v:%s:%d "
 			      "-> d:%s:%d\n",
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 1207f20d24e4..2c1b498a7a27 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -321,7 +321,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 
 	/* Check if a template already exists */
 	ct = ip_vs_ct_in_get(&param);
-	if (!ct || !ip_vs_check_template(ct)) {
+	if (!ct || !ip_vs_check_template(ct, NULL)) {
 		struct ip_vs_scheduler *sched;
 
 		/*
@@ -1154,7 +1154,8 @@ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc,
 						  vport, &param) < 0)
 			return NULL;
 		ct = ip_vs_ct_in_get(&param);
-		if (!ct) {
+		/* check if template exists and points to the same dest */
+		if (!ct || !ip_vs_check_template(ct, dest)) {
 			ct = ip_vs_conn_new(&param, dest->af, daddr, dport,
 					    IP_VS_CONN_F_TEMPLATE, dest, 0);
 			if (!ct) {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index e17d5c7faca0..153e33ffeeaa 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1524,6 +1524,8 @@ void nf_conntrack_cleanup_end(void)
 	nf_conntrack_tstamp_fini();
 	nf_conntrack_acct_fini();
 	nf_conntrack_expect_fini();
+
+	kmem_cache_destroy(nf_conntrack_cachep);
 }
 
 /*
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index 883c691ec8d0..19efeba02abb 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -632,6 +632,7 @@ static int __init nf_conntrack_ftp_init(void)
 			if (ret) {
 				pr_err("failed to register helper for pf: %d port: %d\n",
 				       ftp[i][j].tuple.src.l3num, ports[i]);
+				ports_c = i;
 				nf_conntrack_ftp_fini();
 				return ret;
 			}
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 7ba16e9c69fa..3a1a88b9bafa 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -361,9 +361,10 @@ EXPORT_SYMBOL_GPL(nf_ct_helper_log);
 
 int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 {
-	int ret = 0;
-	struct nf_conntrack_helper *cur;
+	struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) };
 	unsigned int h = helper_hash(&me->tuple);
+	struct nf_conntrack_helper *cur;
+	int ret = 0;
 
 	BUG_ON(me->expect_policy == NULL);
 	BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES);
@@ -371,9 +372,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 
 	mutex_lock(&nf_ct_helper_mutex);
 	hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) {
-		if (strncmp(cur->name, me->name, NF_CT_HELPER_NAME_LEN) == 0 &&
-		    cur->tuple.src.l3num == me->tuple.src.l3num &&
-		    cur->tuple.dst.protonum == me->tuple.dst.protonum) {
+		if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple, &mask)) {
 			ret = -EEXIST;
 			goto out;
 		}
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 8b6da2719600..f97ac61d2536 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -271,6 +271,7 @@ static int __init nf_conntrack_irc_init(void)
 		if (ret) {
 			pr_err("failed to register helper for pf: %u port: %u\n",
 			       irc[i].tuple.src.l3num, ports[i]);
+			ports_c = i;
 			nf_conntrack_irc_fini();
 			return ret;
 		}
diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c
index 7523a575f6d1..3fcbaab83b3d 100644
--- a/net/netfilter/nf_conntrack_sane.c
+++ b/net/netfilter/nf_conntrack_sane.c
@@ -223,6 +223,7 @@ static int __init nf_conntrack_sane_init(void)
 			if (ret) {
 				pr_err("failed to register helper for pf: %d port: %d\n",
 				       sane[i][j].tuple.src.l3num, ports[i]);
+				ports_c = i;
 				nf_conntrack_sane_fini();
 				return ret;
 			}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 3e06402739e0..f72ba5587588 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1669,6 +1669,7 @@ static int __init nf_conntrack_sip_init(void)
 			if (ret) {
 				pr_err("failed to register helper for pf: %u port: %u\n",
 				       sip[i][j].tuple.src.l3num, ports[i]);
+				ports_c = i;
 				nf_conntrack_sip_fini();
 				return ret;
 			}
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index a0cc1919f081..2aaa188ee961 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -508,8 +508,6 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 	{ }
 };
 
-#define NET_NF_CONNTRACK_MAX 2089
-
 static struct ctl_table nf_ct_netfilter_table[] = {
 	{
 		.procname	= "nf_conntrack_max",
diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c
index 36f964066461..2e65b5430fba 100644
--- a/net/netfilter/nf_conntrack_tftp.c
+++ b/net/netfilter/nf_conntrack_tftp.c
@@ -142,6 +142,7 @@ static int __init nf_conntrack_tftp_init(void)
 			if (ret) {
 				pr_err("failed to register helper for pf: %u port: %u\n",
 				       tftp[i][j].tuple.src.l3num, ports[i]);
+				ports_c = i;
 				nf_conntrack_tftp_fini();
 				return ret;
 			}
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 5baa8e24e6ac..b19ad20a705c 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -26,23 +26,21 @@
  * Once the queue is registered it must reinject all packets it
  * receives, no matter what.
  */
-static const struct nf_queue_handler __rcu *queue_handler __read_mostly;
 
 /* return EBUSY when somebody else is registered, return EEXIST if the
  * same handler is registered, return 0 in case of success. */
-void nf_register_queue_handler(const struct nf_queue_handler *qh)
+void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh)
 {
 	/* should never happen, we only have one queueing backend in kernel */
-	WARN_ON(rcu_access_pointer(queue_handler));
-	rcu_assign_pointer(queue_handler, qh);
+	WARN_ON(rcu_access_pointer(net->nf.queue_handler));
+	rcu_assign_pointer(net->nf.queue_handler, qh);
 }
 EXPORT_SYMBOL(nf_register_queue_handler);
 
 /* The caller must flush their queue before this */
-void nf_unregister_queue_handler(void)
+void nf_unregister_queue_handler(struct net *net)
 {
-	RCU_INIT_POINTER(queue_handler, NULL);
-	synchronize_rcu();
+	RCU_INIT_POINTER(net->nf.queue_handler, NULL);
 }
 EXPORT_SYMBOL(nf_unregister_queue_handler);
 
@@ -103,7 +101,7 @@ void nf_queue_nf_hook_drop(struct net *net, struct nf_hook_ops *ops)
 	const struct nf_queue_handler *qh;
 
 	rcu_read_lock();
-	qh = rcu_dereference(queue_handler);
+	qh = rcu_dereference(net->nf.queue_handler);
 	if (qh)
 		qh->nf_hook_drop(net, ops);
 	rcu_read_unlock();
@@ -122,9 +120,10 @@ int nf_queue(struct sk_buff *skb,
 	struct nf_queue_entry *entry = NULL;
 	const struct nf_afinfo *afinfo;
 	const struct nf_queue_handler *qh;
+	struct net *net = state->net;
 
 	/* QUEUE == DROP if no one is waiting, to be safe. */
-	qh = rcu_dereference(queue_handler);
+	qh = rcu_dereference(net->nf.queue_handler);
 	if (!qh) {
 		status = -ESRCH;
 		goto err;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 92c9faeb2bf8..18b7f8578ee0 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2646,6 +2646,8 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk,
 	/* Only accept unspec with dump */
 	if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
 		return -EAFNOSUPPORT;
+	if (!nla[NFTA_SET_TABLE])
+		return -EINVAL;
 
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask);
 	if (IS_ERR(set))
@@ -2943,24 +2945,20 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 		 * jumps are already validated for that chain.
 		 */
 		list_for_each_entry(i, &set->bindings, list) {
-			if (binding->flags & NFT_SET_MAP &&
+			if (i->flags & NFT_SET_MAP &&
 			    i->chain == binding->chain)
 				goto bind;
 		}
 
+		iter.genmask	= nft_genmask_next(ctx->net);
 		iter.skip 	= 0;
 		iter.count	= 0;
 		iter.err	= 0;
 		iter.fn		= nf_tables_bind_check_setelem;
 
 		set->ops->walk(ctx, set, &iter);
-		if (iter.err < 0) {
-			/* Destroy anonymous sets if binding fails */
-			if (set->flags & NFT_SET_ANONYMOUS)
-				nf_tables_set_destroy(ctx, set);
-
+		if (iter.err < 0)
 			return iter.err;
-		}
 	}
 bind:
 	binding->chain = ctx->chain;
@@ -3189,12 +3187,13 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	if (nest == NULL)
 		goto nla_put_failure;
 
-	args.cb		= cb;
-	args.skb	= skb;
-	args.iter.skip	= cb->args[0];
-	args.iter.count	= 0;
-	args.iter.err   = 0;
-	args.iter.fn	= nf_tables_dump_setelem;
+	args.cb			= cb;
+	args.skb		= skb;
+	args.iter.genmask	= nft_genmask_cur(ctx.net);
+	args.iter.skip		= cb->args[0];
+	args.iter.count		= 0;
+	args.iter.err		= 0;
+	args.iter.fn		= nf_tables_dump_setelem;
 	set->ops->walk(&ctx, set, &args.iter);
 
 	nla_nest_end(skb, nest);
@@ -4290,6 +4289,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 			    binding->chain != chain)
 				continue;
 
+			iter.genmask	= nft_genmask_next(ctx->net);
 			iter.skip 	= 0;
 			iter.count	= 0;
 			iter.err	= 0;
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index e9f8dffcc244..fb8b5892b5ff 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -143,7 +143,7 @@ next_rule:
 	list_for_each_entry_continue_rcu(rule, &chain->rules, list) {
 
 		/* This rule is not active, skip. */
-		if (unlikely(rule->genmask & (1 << gencursor)))
+		if (unlikely(rule->genmask & gencursor))
 			continue;
 
 		rulenum++;
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index aa93877ab6e2..5d36a0926b4a 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -557,7 +557,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 
 	if (entskb->tstamp.tv64) {
 		struct nfqnl_msg_packet_timestamp ts;
-		struct timespec64 kts = ktime_to_timespec64(skb->tstamp);
+		struct timespec64 kts = ktime_to_timespec64(entskb->tstamp);
 
 		ts.sec = cpu_to_be64(kts.tv_sec);
 		ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC);
@@ -1482,21 +1482,29 @@ static int __net_init nfnl_queue_net_init(struct net *net)
 			 net->nf.proc_netfilter, &nfqnl_file_ops))
 		return -ENOMEM;
 #endif
+	nf_register_queue_handler(net, &nfqh);
 	return 0;
 }
 
 static void __net_exit nfnl_queue_net_exit(struct net *net)
 {
+	nf_unregister_queue_handler(net);
 #ifdef CONFIG_PROC_FS
 	remove_proc_entry("nfnetlink_queue", net->nf.proc_netfilter);
 #endif
 }
 
+static void nfnl_queue_net_exit_batch(struct list_head *net_exit_list)
+{
+	synchronize_rcu();
+}
+
 static struct pernet_operations nfnl_queue_net_ops = {
-	.init	= nfnl_queue_net_init,
-	.exit	= nfnl_queue_net_exit,
-	.id	= &nfnl_queue_net_id,
-	.size	= sizeof(struct nfnl_queue_net),
+	.init		= nfnl_queue_net_init,
+	.exit		= nfnl_queue_net_exit,
+	.exit_batch	= nfnl_queue_net_exit_batch,
+	.id		= &nfnl_queue_net_id,
+	.size		= sizeof(struct nfnl_queue_net),
 };
 
 static int __init nfnetlink_queue_init(void)
@@ -1517,7 +1525,6 @@ static int __init nfnetlink_queue_init(void)
 	}
 
 	register_netdevice_notifier(&nfqnl_dev_notifier);
-	nf_register_queue_handler(&nfqh);
 	return status;
 
 cleanup_netlink_notifier:
@@ -1529,7 +1536,6 @@ out:
 
 static void __exit nfnetlink_queue_fini(void)
 {
-	nf_unregister_queue_handler();
 	unregister_netdevice_notifier(&nfqnl_dev_notifier);
 	nfnetlink_subsys_unregister(&nfqnl_subsys);
 	netlink_unregister_notifier(&nfqnl_rtnl_notifier);
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index d3a507d3f192..ea924816b7b8 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -191,7 +191,6 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
 	struct nft_hash_elem *he;
 	struct rhashtable_iter hti;
 	struct nft_set_elem elem;
-	u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
 	int err;
 
 	err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL);
@@ -220,7 +219,7 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
 			goto cont;
 		if (nft_set_elem_expired(&he->ext))
 			goto cont;
-		if (!nft_set_elem_active(&he->ext, genmask))
+		if (!nft_set_elem_active(&he->ext, iter->genmask))
 			goto cont;
 
 		elem.priv = he;
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 16c50b0dd426..03e5e33b5c39 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -199,13 +199,6 @@ err:
 }
 EXPORT_SYMBOL_GPL(nft_meta_get_eval);
 
-/* don't change or set _LOOPBACK, _USER, etc. */
-static bool pkt_type_ok(u32 p)
-{
-	return p == PACKET_HOST || p == PACKET_BROADCAST ||
-	       p == PACKET_MULTICAST || p == PACKET_OTHERHOST;
-}
-
 void nft_meta_set_eval(const struct nft_expr *expr,
 		       struct nft_regs *regs,
 		       const struct nft_pktinfo *pkt)
@@ -223,7 +216,7 @@ void nft_meta_set_eval(const struct nft_expr *expr,
 		break;
 	case NFT_META_PKTTYPE:
 		if (skb->pkt_type != value &&
-		    pkt_type_ok(value) && pkt_type_ok(skb->pkt_type))
+		    skb_pkt_type_ok(value) && skb_pkt_type_ok(skb->pkt_type))
 			skb->pkt_type = value;
 		break;
 	case NFT_META_NFTRACE:
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index 86fbe5e68d28..c0f638745adc 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -211,7 +211,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 	struct nft_rbtree_elem *rbe;
 	struct nft_set_elem elem;
 	struct rb_node *node;
-	u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
 
 	spin_lock_bh(&nft_rbtree_lock);
 	for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
@@ -219,7 +218,7 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 		if (iter->count < iter->skip)
 			goto cont;
-		if (!nft_set_elem_active(&rbe->ext, genmask))
+		if (!nft_set_elem_active(&rbe->ext, iter->genmask))
 			goto cont;
 
 		elem.priv = rbe;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 8aff34e8737c..fe0e2db632c7 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -612,7 +612,7 @@ int xt_compat_check_entry_offsets(const void *base, const char *elems,
 		return -EINVAL;
 
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
-	    target_offset + sizeof(struct compat_xt_standard_target) != next_offset)
+	    COMPAT_XT_ALIGN(target_offset + sizeof(struct compat_xt_standard_target)) != next_offset)
 		return -EINVAL;
 
 	/* compat_xt_entry match has less strict aligment requirements,
@@ -694,7 +694,7 @@ int xt_check_entry_offsets(const void *base,
 		return -EINVAL;
 
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
-	    target_offset + sizeof(struct xt_standard_target) != next_offset)
+	    XT_ALIGN(target_offset + sizeof(struct xt_standard_target)) != next_offset)
 		return -EINVAL;
 
 	return xt_check_entry_match(elems, base + target_offset,
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 604df6fae6fc..515131f9e021 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -137,7 +137,7 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
 	cfg.est.ewma_log	= info->ewma_log;
 
 	ret = gen_new_estimator(&est->bstats, NULL, &est->rstats,
-				&est->lock, &cfg.opt);
+				&est->lock, NULL, &cfg.opt);
 	if (ret < 0)
 		goto err2;
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index e68ef9ccd703..3cfd6cc60504 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -8,20 +8,6 @@
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
 #define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))
 
-struct netlink_ring {
-	void			**pg_vec;
-	unsigned int		head;
-	unsigned int		frames_per_block;
-	unsigned int		frame_size;
-	unsigned int		frame_max;
-
-	unsigned int		pg_vec_order;
-	unsigned int		pg_vec_pages;
-	unsigned int		pg_vec_len;
-
-	atomic_t		pending;
-};
-
 struct netlink_sock {
 	/* struct sock has to be the first member of netlink_sock */
 	struct sock		sk;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 9a3eb7a0ebf4..1ecbd7715f6d 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -750,6 +750,14 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 
 	if (likely(vport)) {
 		u16 mru = OVS_CB(skb)->mru;
+		u32 cutlen = OVS_CB(skb)->cutlen;
+
+		if (unlikely(cutlen > 0)) {
+			if (skb->len - cutlen > ETH_HLEN)
+				pskb_trim(skb, skb->len - cutlen);
+			else
+				pskb_trim(skb, ETH_HLEN);
+		}
 
 		if (likely(!mru || (skb->len <= mru + ETH_HLEN))) {
 			ovs_vport_send(vport, skb);
@@ -775,7 +783,8 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 
 static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 			    struct sw_flow_key *key, const struct nlattr *attr,
-			    const struct nlattr *actions, int actions_len)
+			    const struct nlattr *actions, int actions_len,
+			    uint32_t cutlen)
 {
 	struct dp_upcall_info upcall;
 	const struct nlattr *a;
@@ -822,7 +831,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 		} /* End of switch. */
 	}
 
-	return ovs_dp_upcall(dp, skb, key, &upcall);
+	return ovs_dp_upcall(dp, skb, key, &upcall, cutlen);
 }
 
 static int sample(struct datapath *dp, struct sk_buff *skb,
@@ -832,6 +841,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 	const struct nlattr *acts_list = NULL;
 	const struct nlattr *a;
 	int rem;
+	u32 cutlen = 0;
 
 	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
 		 a = nla_next(a, &rem)) {
@@ -858,13 +868,24 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 		return 0;
 
 	/* The only known usage of sample action is having a single user-space
+	 * action, or having a truncate action followed by a single user-space
 	 * action. Treat this usage as a special case.
 	 * The output_userspace() should clone the skb to be sent to the
 	 * user space. This skb will be consumed by its caller.
 	 */
+	if (unlikely(nla_type(a) == OVS_ACTION_ATTR_TRUNC)) {
+		struct ovs_action_trunc *trunc = nla_data(a);
+
+		if (skb->len > trunc->max_len)
+			cutlen = skb->len - trunc->max_len;
+
+		a = nla_next(a, &rem);
+	}
+
 	if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
 		   nla_is_last(a, rem)))
-		return output_userspace(dp, skb, key, a, actions, actions_len);
+		return output_userspace(dp, skb, key, a, actions,
+					actions_len, cutlen);
 
 	skb = skb_clone(skb, GFP_ATOMIC);
 	if (!skb)
@@ -1051,6 +1072,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			if (out_skb)
 				do_output(dp, out_skb, prev_port, key);
 
+			OVS_CB(skb)->cutlen = 0;
 			prev_port = -1;
 		}
 
@@ -1059,8 +1081,18 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			prev_port = nla_get_u32(a);
 			break;
 
+		case OVS_ACTION_ATTR_TRUNC: {
+			struct ovs_action_trunc *trunc = nla_data(a);
+
+			if (skb->len > trunc->max_len)
+				OVS_CB(skb)->cutlen = skb->len - trunc->max_len;
+			break;
+		}
+
 		case OVS_ACTION_ATTR_USERSPACE:
-			output_userspace(dp, skb, key, a, attr, len);
+			output_userspace(dp, skb, key, a, attr,
+						     len, OVS_CB(skb)->cutlen);
+			OVS_CB(skb)->cutlen = 0;
 			break;
 
 		case OVS_ACTION_ATTR_HASH:
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 3d5feede962d..b4069a90e375 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -818,12 +818,33 @@ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
 		 */
 		state = OVS_CS_F_TRACKED | OVS_CS_F_NEW | OVS_CS_F_RELATED;
 		__ovs_ct_update_key(key, state, &info->zone, exp->master);
-	} else
-		return __ovs_ct_lookup(net, key, info, skb);
+	} else {
+		struct nf_conn *ct;
+		int err;
+
+		err = __ovs_ct_lookup(net, key, info, skb);
+		if (err)
+			return err;
+
+		ct = (struct nf_conn *)skb->nfct;
+		if (ct)
+			nf_ct_deliver_cached_events(ct);
+	}
 
 	return 0;
 }
 
+static bool labels_nonzero(const struct ovs_key_ct_labels *labels)
+{
+	size_t i;
+
+	for (i = 0; i < sizeof(*labels); i++)
+		if (labels->ct_labels[i])
+			return true;
+
+	return false;
+}
+
 /* Lookup connection and confirm if unconfirmed. */
 static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
 			 const struct ovs_conntrack_info *info,
@@ -834,24 +855,32 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
 	err = __ovs_ct_lookup(net, key, info, skb);
 	if (err)
 		return err;
-	/* This is a no-op if the connection has already been confirmed. */
+
+	/* Apply changes before confirming the connection so that the initial
+	 * conntrack NEW netlink event carries the values given in the CT
+	 * action.
+	 */
+	if (info->mark.mask) {
+		err = ovs_ct_set_mark(skb, key, info->mark.value,
+				      info->mark.mask);
+		if (err)
+			return err;
+	}
+	if (labels_nonzero(&info->labels.mask)) {
+		err = ovs_ct_set_labels(skb, key, &info->labels.value,
+					&info->labels.mask);
+		if (err)
+			return err;
+	}
+	/* This will take care of sending queued events even if the connection
+	 * is already confirmed.
+	 */
 	if (nf_conntrack_confirm(skb) != NF_ACCEPT)
 		return -EINVAL;
 
 	return 0;
 }
 
-static bool labels_nonzero(const struct ovs_key_ct_labels *labels)
-{
-	size_t i;
-
-	for (i = 0; i < sizeof(*labels); i++)
-		if (labels->ct_labels[i])
-			return true;
-
-	return false;
-}
-
 /* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero
  * value if 'skb' is freed.
  */
@@ -876,19 +905,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 		err = ovs_ct_commit(net, key, info, skb);
 	else
 		err = ovs_ct_lookup(net, key, info, skb);
-	if (err)
-		goto err;
 
-	if (info->mark.mask) {
-		err = ovs_ct_set_mark(skb, key, info->mark.value,
-				      info->mark.mask);
-		if (err)
-			goto err;
-	}
-	if (labels_nonzero(&info->labels.mask))
-		err = ovs_ct_set_labels(skb, key, &info->labels.value,
-					&info->labels.mask);
-err:
 	skb_push(skb, nh_ofs);
 	if (err)
 		kfree_skb(skb);
@@ -1145,6 +1162,20 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 		}
 	}
 
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	if (!info->commit && info->mark.mask) {
+		OVS_NLERR(log,
+			  "Setting conntrack mark requires 'commit' flag.");
+		return -EINVAL;
+	}
+#endif
+#ifdef CONFIG_NF_CONNTRACK_LABELS
+	if (!info->commit && labels_nonzero(&info->labels.mask)) {
+		OVS_NLERR(log,
+			  "Setting conntrack labels requires 'commit' flag.");
+		return -EINVAL;
+	}
+#endif
 	if (rem > 0) {
 		OVS_NLERR(log, "Conntrack attr has %d unknown bytes", rem);
 		return -EINVAL;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 856bd8dba676..524c0fd3078e 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -137,10 +137,12 @@ EXPORT_SYMBOL_GPL(lockdep_ovsl_is_held);
 static struct vport *new_vport(const struct vport_parms *);
 static int queue_gso_packets(struct datapath *dp, struct sk_buff *,
 			     const struct sw_flow_key *,
-			     const struct dp_upcall_info *);
+			     const struct dp_upcall_info *,
+			     uint32_t cutlen);
 static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
 				  const struct sw_flow_key *,
-				  const struct dp_upcall_info *);
+				  const struct dp_upcall_info *,
+				  uint32_t cutlen);
 
 /* Must be called with rcu_read_lock. */
 static struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
@@ -275,7 +277,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 		upcall.cmd = OVS_PACKET_CMD_MISS;
 		upcall.portid = ovs_vport_find_upcall_portid(p, skb);
 		upcall.mru = OVS_CB(skb)->mru;
-		error = ovs_dp_upcall(dp, skb, key, &upcall);
+		error = ovs_dp_upcall(dp, skb, key, &upcall, 0);
 		if (unlikely(error))
 			kfree_skb(skb);
 		else
@@ -300,7 +302,8 @@ out:
 
 int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 		  const struct sw_flow_key *key,
-		  const struct dp_upcall_info *upcall_info)
+		  const struct dp_upcall_info *upcall_info,
+		  uint32_t cutlen)
 {
 	struct dp_stats_percpu *stats;
 	int err;
@@ -311,9 +314,9 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 	}
 
 	if (!skb_is_gso(skb))
-		err = queue_userspace_packet(dp, skb, key, upcall_info);
+		err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen);
 	else
-		err = queue_gso_packets(dp, skb, key, upcall_info);
+		err = queue_gso_packets(dp, skb, key, upcall_info, cutlen);
 	if (err)
 		goto err;
 
@@ -331,7 +334,8 @@ err:
 
 static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 			     const struct sw_flow_key *key,
-			     const struct dp_upcall_info *upcall_info)
+			     const struct dp_upcall_info *upcall_info,
+				 uint32_t cutlen)
 {
 	unsigned short gso_type = skb_shinfo(skb)->gso_type;
 	struct sw_flow_key later_key;
@@ -360,7 +364,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 		if (gso_type & SKB_GSO_UDP && skb != segs)
 			key = &later_key;
 
-		err = queue_userspace_packet(dp, skb, key, upcall_info);
+		err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen);
 		if (err)
 			break;
 
@@ -383,7 +387,8 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
 		+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
-		+ nla_total_size(ovs_key_attr_size()); /* OVS_PACKET_ATTR_KEY */
+		+ nla_total_size(ovs_key_attr_size()) /* OVS_PACKET_ATTR_KEY */
+		+ nla_total_size(sizeof(unsigned int)); /* OVS_PACKET_ATTR_LEN */
 
 	/* OVS_PACKET_ATTR_USERDATA */
 	if (upcall_info->userdata)
@@ -416,7 +421,8 @@ static void pad_packet(struct datapath *dp, struct sk_buff *skb)
 
 static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 				  const struct sw_flow_key *key,
-				  const struct dp_upcall_info *upcall_info)
+				  const struct dp_upcall_info *upcall_info,
+				  uint32_t cutlen)
 {
 	struct ovs_header *upcall;
 	struct sk_buff *nskb = NULL;
@@ -461,7 +467,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	else
 		hlen = skb->len;
 
-	len = upcall_msg_size(upcall_info, hlen);
+	len = upcall_msg_size(upcall_info, hlen - cutlen);
 	user_skb = genlmsg_new(len, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;
@@ -509,15 +515,25 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 		pad_packet(dp, user_skb);
 	}
 
+	/* Add OVS_PACKET_ATTR_LEN when packet is truncated */
+	if (cutlen > 0) {
+		if (nla_put_u32(user_skb, OVS_PACKET_ATTR_LEN,
+				skb->len)) {
+			err = -ENOBUFS;
+			goto out;
+		}
+		pad_packet(dp, user_skb);
+	}
+
 	/* Only reserve room for attribute header, packet data is added
 	 * in skb_zerocopy() */
 	if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
 		err = -ENOBUFS;
 		goto out;
 	}
-	nla->nla_len = nla_attr_size(skb->len);
+	nla->nla_len = nla_attr_size(skb->len - cutlen);
 
-	err = skb_zerocopy(user_skb, skb, skb->len, hlen);
+	err = skb_zerocopy(user_skb, skb, skb->len - cutlen, hlen);
 	if (err)
 		goto out;
 
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 427e39a045cf..ab85c1cae255 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -100,11 +100,13 @@ struct datapath {
  * @input_vport: The original vport packet came in on. This value is cached
  * when a packet is received by OVS.
  * @mru: The maximum received fragement size; 0 if the packet is not
+ * @cutlen: The number of bytes from the packet end to be removed.
  * fragmented.
  */
 struct ovs_skb_cb {
 	struct vport		*input_vport;
 	u16			mru;
+	u32			cutlen;
 };
 #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
 
@@ -194,7 +196,8 @@ extern struct genl_family dp_vport_genl_family;
 void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key);
 void ovs_dp_detach_port(struct vport *);
 int ovs_dp_upcall(struct datapath *, struct sk_buff *,
-		  const struct sw_flow_key *, const struct dp_upcall_info *);
+		  const struct sw_flow_key *, const struct dp_upcall_info *,
+		  uint32_t cutlen);
 
 const char *ovs_dp_name(const struct datapath *dp);
 struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 0bb650f4f219..c78a6a1476fb 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2229,6 +2229,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
 			[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash),
 			[OVS_ACTION_ATTR_CT] = (u32)-1,
+			[OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc),
 		};
 		const struct ovs_action_push_vlan *vlan;
 		int type = nla_type(a);
@@ -2255,6 +2256,14 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				return -EINVAL;
 			break;
 
+		case OVS_ACTION_ATTR_TRUNC: {
+			const struct ovs_action_trunc *trunc = nla_data(a);
+
+			if (trunc->max_len < ETH_HLEN)
+				return -EINVAL;
+			break;
+		}
+
 		case OVS_ACTION_ATTR_HASH: {
 			const struct ovs_action_hash *act_hash = nla_data(a);
 
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 31cbc8c5c7db..6b21fd068d87 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -444,6 +444,7 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
 
 	OVS_CB(skb)->input_vport = vport;
 	OVS_CB(skb)->mru = 0;
+	OVS_CB(skb)->cutlen = 0;
 	if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) {
 		u32 mark;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 4040eb92d9c9..48b58957adf4 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -93,6 +93,7 @@
 #include <net/inet_common.h>
 #endif
 #include <linux/bpf.h>
+#include <net/compat.h>
 
 #include "internal.h"
 
@@ -1587,13 +1588,9 @@ static int fanout_set_data_ebpf(struct packet_sock *po, char __user *data,
 	if (copy_from_user(&fd, data, len))
 		return -EFAULT;
 
-	new = bpf_prog_get(fd);
+	new = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER);
 	if (IS_ERR(new))
 		return PTR_ERR(new);
-	if (new->type != BPF_PROG_TYPE_SOCKET_FILTER) {
-		bpf_prog_put(new);
-		return -EINVAL;
-	}
 
 	__fanout_set_data_bpf(po->fanout, new);
 	return 0;
@@ -1978,40 +1975,8 @@ static int __packet_rcv_vnet(const struct sk_buff *skb,
 {
 	*vnet_hdr = (const struct virtio_net_hdr) { 0 };
 
-	if (skb_is_gso(skb)) {
-		struct skb_shared_info *sinfo = skb_shinfo(skb);
-
-		/* This is a hint as to how much should be linear. */
-		vnet_hdr->hdr_len =
-			__cpu_to_virtio16(vio_le(), skb_headlen(skb));
-		vnet_hdr->gso_size =
-			__cpu_to_virtio16(vio_le(), sinfo->gso_size);
-
-		if (sinfo->gso_type & SKB_GSO_TCPV4)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
-		else if (sinfo->gso_type & SKB_GSO_TCPV6)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
-		else if (sinfo->gso_type & SKB_GSO_UDP)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
-		else if (sinfo->gso_type & SKB_GSO_FCOE)
-			return -EINVAL;
-		else
-			BUG();
-
-		if (sinfo->gso_type & SKB_GSO_TCP_ECN)
-			vnet_hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
-	} else
-		vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
-
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		vnet_hdr->csum_start = __cpu_to_virtio16(vio_le(),
-				  skb_checksum_start_offset(skb));
-		vnet_hdr->csum_offset = __cpu_to_virtio16(vio_le(),
-						 skb->csum_offset);
-	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-		vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
-	} /* else everything is zero */
+	if (virtio_net_hdr_from_skb(skb, vnet_hdr, vio_le()))
+		BUG();
 
 	return 0;
 }
@@ -3940,6 +3905,27 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 }
 
 
+#ifdef CONFIG_COMPAT
+static int compat_packet_setsockopt(struct socket *sock, int level, int optname,
+				    char __user *optval, unsigned int optlen)
+{
+	struct packet_sock *po = pkt_sk(sock->sk);
+
+	if (level != SOL_PACKET)
+		return -ENOPROTOOPT;
+
+	if (optname == PACKET_FANOUT_DATA &&
+	    po->fanout && po->fanout->type == PACKET_FANOUT_CBPF) {
+		optval = (char __user *)get_compat_bpf_fprog(optval);
+		if (!optval)
+			return -EFAULT;
+		optlen = sizeof(struct sock_fprog);
+	}
+
+	return packet_setsockopt(sock, level, optname, optval, optlen);
+}
+#endif
+
 static int packet_notifier(struct notifier_block *this,
 			   unsigned long msg, void *ptr)
 {
@@ -4416,6 +4402,9 @@ static const struct proto_ops packet_ops = {
 	.shutdown =	sock_no_shutdown,
 	.setsockopt =	packet_setsockopt,
 	.getsockopt =	packet_getsockopt,
+#ifdef CONFIG_COMPAT
+	.compat_setsockopt = compat_packet_setsockopt,
+#endif
 	.sendmsg =	packet_sendmsg,
 	.recvmsg =	packet_recvmsg,
 	.mmap =		packet_mmap,
diff --git a/net/rds/cong.c b/net/rds/cong.c
index 6641bcf7c185..8398fee7c866 100644
--- a/net/rds/cong.c
+++ b/net/rds/cong.c
@@ -235,7 +235,8 @@ void rds_cong_queue_updates(struct rds_cong_map *map)
 			 *    therefore trigger warnings.
 			 * Defer the xmit to rds_send_worker() instead.
 			 */
-			queue_delayed_work(rds_wq, &conn->c_send_w, 0);
+			queue_delayed_work(rds_wq,
+					   &conn->c_path[0].cp_send_w, 0);
 		}
 	}
 
diff --git a/net/rds/connection.c b/net/rds/connection.c
index e3b118cae81d..19a4fee5f4dd 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -95,14 +95,16 @@ static struct rds_connection *rds_conn_lookup(struct net *net,
  * and receiving over this connection again in the future.  It is up to
  * the transport to have serialized this call with its send and recv.
  */
-static void rds_conn_reset(struct rds_connection *conn)
+static void rds_conn_path_reset(struct rds_conn_path *cp)
 {
+	struct rds_connection *conn = cp->cp_conn;
+
 	rdsdebug("connection %pI4 to %pI4 reset\n",
 	  &conn->c_laddr, &conn->c_faddr);
 
 	rds_stats_inc(s_conn_reset);
-	rds_send_reset(conn);
-	conn->c_flags = 0;
+	rds_send_path_reset(cp);
+	cp->cp_flags = 0;
 
 	/* Do not clear next_rx_seq here, else we cannot distinguish
 	 * retransmitted packets from new packets, and will hand all
@@ -110,6 +112,32 @@ static void rds_conn_reset(struct rds_connection *conn)
 	 * reliability guarantees of RDS. */
 }
 
+static void __rds_conn_path_init(struct rds_connection *conn,
+				 struct rds_conn_path *cp, bool is_outgoing)
+{
+	spin_lock_init(&cp->cp_lock);
+	cp->cp_next_tx_seq = 1;
+	init_waitqueue_head(&cp->cp_waitq);
+	INIT_LIST_HEAD(&cp->cp_send_queue);
+	INIT_LIST_HEAD(&cp->cp_retrans);
+
+	cp->cp_conn = conn;
+	atomic_set(&cp->cp_state, RDS_CONN_DOWN);
+	cp->cp_send_gen = 0;
+	/* cp_outgoing is per-path. So we can only set it here
+	 * for the single-path transports.
+	 */
+	if (!conn->c_trans->t_mp_capable)
+		cp->cp_outgoing = (is_outgoing ? 1 : 0);
+	cp->cp_reconnect_jiffies = 0;
+	INIT_DELAYED_WORK(&cp->cp_send_w, rds_send_worker);
+	INIT_DELAYED_WORK(&cp->cp_recv_w, rds_recv_worker);
+	INIT_DELAYED_WORK(&cp->cp_conn_w, rds_connect_worker);
+	INIT_WORK(&cp->cp_down_w, rds_shutdown_worker);
+	mutex_init(&cp->cp_cm_lock);
+	cp->cp_flags = 0;
+}
+
 /*
  * There is only every one 'conn' for a given pair of addresses in the
  * system at a time.  They contain messages to be retransmitted and so
@@ -153,13 +181,8 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	INIT_HLIST_NODE(&conn->c_hash_node);
 	conn->c_laddr = laddr;
 	conn->c_faddr = faddr;
-	spin_lock_init(&conn->c_lock);
-	conn->c_next_tx_seq = 1;
-	rds_conn_net_set(conn, net);
 
-	init_waitqueue_head(&conn->c_waitq);
-	INIT_LIST_HEAD(&conn->c_send_queue);
-	INIT_LIST_HEAD(&conn->c_retrans);
+	rds_conn_net_set(conn, net);
 
 	ret = rds_cong_get_maps(conn);
 	if (ret) {
@@ -195,17 +218,6 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 		goto out;
 	}
 
-	atomic_set(&conn->c_state, RDS_CONN_DOWN);
-	conn->c_send_gen = 0;
-	conn->c_outgoing = (is_outgoing ? 1 : 0);
-	conn->c_reconnect_jiffies = 0;
-	INIT_DELAYED_WORK(&conn->c_send_w, rds_send_worker);
-	INIT_DELAYED_WORK(&conn->c_recv_w, rds_recv_worker);
-	INIT_DELAYED_WORK(&conn->c_conn_w, rds_connect_worker);
-	INIT_WORK(&conn->c_down_w, rds_shutdown_worker);
-	mutex_init(&conn->c_cm_lock);
-	conn->c_flags = 0;
-
 	rdsdebug("allocated conn %p for %pI4 -> %pI4 over %s %s\n",
 	  conn, &laddr, &faddr,
 	  trans->t_name ? trans->t_name : "[unknown]",
@@ -222,7 +234,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	if (parent) {
 		/* Creating passive conn */
 		if (parent->c_passive) {
-			trans->conn_free(conn->c_transport_data);
+			trans->conn_free(conn->c_path[0].cp_transport_data);
 			kmem_cache_free(rds_conn_slab, conn);
 			conn = parent->c_passive;
 		} else {
@@ -236,10 +248,29 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 
 		found = rds_conn_lookup(net, head, laddr, faddr, trans);
 		if (found) {
-			trans->conn_free(conn->c_transport_data);
+			struct rds_conn_path *cp;
+			int i;
+
+			for (i = 0; i < RDS_MPATH_WORKERS; i++) {
+				cp = &conn->c_path[i];
+				/* The ->conn_alloc invocation may have
+				 * allocated resource for all paths, so all
+				 * of them may have to be freed here.
+				 */
+				if (cp->cp_transport_data)
+					trans->conn_free(cp->cp_transport_data);
+			}
 			kmem_cache_free(rds_conn_slab, conn);
 			conn = found;
 		} else {
+			int i;
+
+			for (i = 0; i < RDS_MPATH_WORKERS; i++) {
+				__rds_conn_path_init(conn, &conn->c_path[i],
+						     is_outgoing);
+				conn->c_path[i].cp_index = i;
+			}
+
 			hlist_add_head_rcu(&conn->c_hash_node, head);
 			rds_cong_add_conn(conn);
 			rds_conn_count++;
@@ -267,10 +298,12 @@ struct rds_connection *rds_conn_create_outgoing(struct net *net,
 }
 EXPORT_SYMBOL_GPL(rds_conn_create_outgoing);
 
-void rds_conn_shutdown(struct rds_connection *conn)
+void rds_conn_shutdown(struct rds_conn_path *cp)
 {
+	struct rds_connection *conn = cp->cp_conn;
+
 	/* shut it down unless it's down already */
-	if (!rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_DOWN)) {
+	if (!rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_DOWN)) {
 		/*
 		 * Quiesce the connection mgmt handlers before we start tearing
 		 * things down. We don't hold the mutex for the entire
@@ -278,35 +311,38 @@ void rds_conn_shutdown(struct rds_connection *conn)
 		 * deadlocking with the CM handler. Instead, the CM event
 		 * handler is supposed to check for state DISCONNECTING
 		 */
-		mutex_lock(&conn->c_cm_lock);
-		if (!rds_conn_transition(conn, RDS_CONN_UP, RDS_CONN_DISCONNECTING)
-		 && !rds_conn_transition(conn, RDS_CONN_ERROR, RDS_CONN_DISCONNECTING)) {
-			rds_conn_error(conn, "shutdown called in state %d\n",
-					atomic_read(&conn->c_state));
-			mutex_unlock(&conn->c_cm_lock);
+		mutex_lock(&cp->cp_cm_lock);
+		if (!rds_conn_path_transition(cp, RDS_CONN_UP,
+					      RDS_CONN_DISCONNECTING) &&
+		    !rds_conn_path_transition(cp, RDS_CONN_ERROR,
+					      RDS_CONN_DISCONNECTING)) {
+			rds_conn_path_error(cp,
+					    "shutdown called in state %d\n",
+					    atomic_read(&cp->cp_state));
+			mutex_unlock(&cp->cp_cm_lock);
 			return;
 		}
-		mutex_unlock(&conn->c_cm_lock);
+		mutex_unlock(&cp->cp_cm_lock);
 
-		wait_event(conn->c_waitq,
-			   !test_bit(RDS_IN_XMIT, &conn->c_flags));
-		wait_event(conn->c_waitq,
-			   !test_bit(RDS_RECV_REFILL, &conn->c_flags));
+		wait_event(cp->cp_waitq,
+			   !test_bit(RDS_IN_XMIT, &cp->cp_flags));
+		wait_event(cp->cp_waitq,
+			   !test_bit(RDS_RECV_REFILL, &cp->cp_flags));
 
-		conn->c_trans->conn_shutdown(conn);
-		rds_conn_reset(conn);
+		conn->c_trans->conn_path_shutdown(cp);
+		rds_conn_path_reset(cp);
 
-		if (!rds_conn_transition(conn, RDS_CONN_DISCONNECTING, RDS_CONN_DOWN)) {
+		if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING,
+					      RDS_CONN_DOWN)) {
 			/* This can happen - eg when we're in the middle of tearing
 			 * down the connection, and someone unloads the rds module.
 			 * Quite reproduceable with loopback connections.
 			 * Mostly harmless.
 			 */
-			rds_conn_error(conn,
-				"%s: failed to transition to state DOWN, "
-				"current state is %d\n",
-				__func__,
-				atomic_read(&conn->c_state));
+			rds_conn_path_error(cp, "%s: failed to transition "
+					    "to state DOWN, current state "
+					    "is %d\n", __func__,
+					    atomic_read(&cp->cp_state));
 			return;
 		}
 	}
@@ -315,18 +351,47 @@ void rds_conn_shutdown(struct rds_connection *conn)
 	 * The passive side of an IB loopback connection is never added
 	 * to the conn hash, so we never trigger a reconnect on this
 	 * conn - the reconnect is always triggered by the active peer. */
-	cancel_delayed_work_sync(&conn->c_conn_w);
+	cancel_delayed_work_sync(&cp->cp_conn_w);
 	rcu_read_lock();
 	if (!hlist_unhashed(&conn->c_hash_node)) {
 		rcu_read_unlock();
-		if (conn->c_trans->t_type != RDS_TRANS_TCP ||
-		    conn->c_outgoing == 1)
-			rds_queue_reconnect(conn);
+		rds_queue_reconnect(cp);
 	} else {
 		rcu_read_unlock();
 	}
 }
 
+/* destroy a single rds_conn_path. rds_conn_destroy() iterates over
+ * all paths using rds_conn_path_destroy()
+ */
+static void rds_conn_path_destroy(struct rds_conn_path *cp)
+{
+	struct rds_message *rm, *rtmp;
+
+	if (!cp->cp_transport_data)
+		return;
+
+	rds_conn_path_drop(cp);
+	flush_work(&cp->cp_down_w);
+
+	/* make sure lingering queued work won't try to ref the conn */
+	cancel_delayed_work_sync(&cp->cp_send_w);
+	cancel_delayed_work_sync(&cp->cp_recv_w);
+
+	/* tear down queued messages */
+	list_for_each_entry_safe(rm, rtmp,
+				 &cp->cp_send_queue,
+				 m_conn_item) {
+		list_del_init(&rm->m_conn_item);
+		BUG_ON(!list_empty(&rm->m_sock_item));
+		rds_message_put(rm);
+	}
+	if (cp->cp_xmit_rm)
+		rds_message_put(cp->cp_xmit_rm);
+
+	cp->cp_conn->c_trans->conn_free(cp->cp_transport_data);
+}
+
 /*
  * Stop and free a connection.
  *
@@ -336,8 +401,9 @@ void rds_conn_shutdown(struct rds_connection *conn)
  */
 void rds_conn_destroy(struct rds_connection *conn)
 {
-	struct rds_message *rm, *rtmp;
 	unsigned long flags;
+	int i;
+	struct rds_conn_path *cp;
 
 	rdsdebug("freeing conn %p for %pI4 -> "
 		 "%pI4\n", conn, &conn->c_laddr,
@@ -350,25 +416,11 @@ void rds_conn_destroy(struct rds_connection *conn)
 	synchronize_rcu();
 
 	/* shut the connection down */
-	rds_conn_drop(conn);
-	flush_work(&conn->c_down_w);
-
-	/* make sure lingering queued work won't try to ref the conn */
-	cancel_delayed_work_sync(&conn->c_send_w);
-	cancel_delayed_work_sync(&conn->c_recv_w);
-
-	/* tear down queued messages */
-	list_for_each_entry_safe(rm, rtmp,
-				 &conn->c_send_queue,
-				 m_conn_item) {
-		list_del_init(&rm->m_conn_item);
-		BUG_ON(!list_empty(&rm->m_sock_item));
-		rds_message_put(rm);
+	for (i = 0; i < RDS_MPATH_WORKERS; i++) {
+		cp = &conn->c_path[i];
+		rds_conn_path_destroy(cp);
+		BUG_ON(!list_empty(&cp->cp_retrans));
 	}
-	if (conn->c_xmit_rm)
-		rds_message_put(conn->c_xmit_rm);
-
-	conn->c_trans->conn_free(conn->c_transport_data);
 
 	/*
 	 * The congestion maps aren't freed up here.  They're
@@ -377,7 +429,6 @@ void rds_conn_destroy(struct rds_connection *conn)
 	 */
 	rds_cong_remove_conn(conn);
 
-	BUG_ON(!list_empty(&conn->c_retrans));
 	kmem_cache_free(rds_conn_slab, conn);
 
 	spin_lock_irqsave(&rds_conn_lock, flags);
@@ -398,6 +449,7 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
 	unsigned int total = 0;
 	unsigned long flags;
 	size_t i;
+	int j;
 
 	len /= sizeof(struct rds_info_message);
 
@@ -406,23 +458,32 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
 	for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash);
 	     i++, head++) {
 		hlist_for_each_entry_rcu(conn, head, c_hash_node) {
-			if (want_send)
-				list = &conn->c_send_queue;
-			else
-				list = &conn->c_retrans;
-
-			spin_lock_irqsave(&conn->c_lock, flags);
-
-			/* XXX too lazy to maintain counts.. */
-			list_for_each_entry(rm, list, m_conn_item) {
-				total++;
-				if (total <= len)
-					rds_inc_info_copy(&rm->m_inc, iter,
-							  conn->c_laddr,
-							  conn->c_faddr, 0);
+			struct rds_conn_path *cp;
+
+			for (j = 0; j < RDS_MPATH_WORKERS; j++) {
+				cp = &conn->c_path[j];
+				if (want_send)
+					list = &cp->cp_send_queue;
+				else
+					list = &cp->cp_retrans;
+
+				spin_lock_irqsave(&cp->cp_lock, flags);
+
+				/* XXX too lazy to maintain counts.. */
+				list_for_each_entry(rm, list, m_conn_item) {
+					total++;
+					if (total <= len)
+						rds_inc_info_copy(&rm->m_inc,
+								  iter,
+								  conn->c_laddr,
+								  conn->c_faddr,
+								  0);
+				}
+
+				spin_unlock_irqrestore(&cp->cp_lock, flags);
+				if (!conn->c_trans->t_mp_capable)
+					break;
 			}
-
-			spin_unlock_irqrestore(&conn->c_lock, flags);
 		}
 	}
 	rcu_read_unlock();
@@ -484,27 +545,72 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len,
 }
 EXPORT_SYMBOL_GPL(rds_for_each_conn_info);
 
-static int rds_conn_info_visitor(struct rds_connection *conn,
-				  void *buffer)
+void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
+			     struct rds_info_iterator *iter,
+			     struct rds_info_lengths *lens,
+			     int (*visitor)(struct rds_conn_path *, void *),
+			     size_t item_len)
+{
+	u64  buffer[(item_len + 7) / 8];
+	struct hlist_head *head;
+	struct rds_connection *conn;
+	size_t i;
+	int j;
+
+	rcu_read_lock();
+
+	lens->nr = 0;
+	lens->each = item_len;
+
+	for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash);
+	     i++, head++) {
+		hlist_for_each_entry_rcu(conn, head, c_hash_node) {
+			struct rds_conn_path *cp;
+
+			for (j = 0; j < RDS_MPATH_WORKERS; j++) {
+				cp = &conn->c_path[j];
+
+				/* XXX no cp_lock usage.. */
+				if (!visitor(cp, buffer))
+					continue;
+				if (!conn->c_trans->t_mp_capable)
+					break;
+			}
+
+			/* We copy as much as we can fit in the buffer,
+			 * but we count all items so that the caller
+			 * can resize the buffer.
+			 */
+			if (len >= item_len) {
+				rds_info_copy(iter, buffer, item_len);
+				len -= item_len;
+			}
+			lens->nr++;
+		}
+	}
+	rcu_read_unlock();
+}
+
+static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 {
 	struct rds_info_connection *cinfo = buffer;
 
-	cinfo->next_tx_seq = conn->c_next_tx_seq;
-	cinfo->next_rx_seq = conn->c_next_rx_seq;
-	cinfo->laddr = conn->c_laddr;
-	cinfo->faddr = conn->c_faddr;
-	strncpy(cinfo->transport, conn->c_trans->t_name,
+	cinfo->next_tx_seq = cp->cp_next_tx_seq;
+	cinfo->next_rx_seq = cp->cp_next_rx_seq;
+	cinfo->laddr = cp->cp_conn->c_laddr;
+	cinfo->faddr = cp->cp_conn->c_faddr;
+	strncpy(cinfo->transport, cp->cp_conn->c_trans->t_name,
 		sizeof(cinfo->transport));
 	cinfo->flags = 0;
 
-	rds_conn_info_set(cinfo->flags, test_bit(RDS_IN_XMIT, &conn->c_flags),
+	rds_conn_info_set(cinfo->flags, test_bit(RDS_IN_XMIT, &cp->cp_flags),
 			  SENDING);
 	/* XXX Future: return the state rather than these funky bits */
 	rds_conn_info_set(cinfo->flags,
-			  atomic_read(&conn->c_state) == RDS_CONN_CONNECTING,
+			  atomic_read(&cp->cp_state) == RDS_CONN_CONNECTING,
 			  CONNECTING);
 	rds_conn_info_set(cinfo->flags,
-			  atomic_read(&conn->c_state) == RDS_CONN_UP,
+			  atomic_read(&cp->cp_state) == RDS_CONN_UP,
 			  CONNECTED);
 	return 1;
 }
@@ -513,7 +619,7 @@ static void rds_conn_info(struct socket *sock, unsigned int len,
 			  struct rds_info_iterator *iter,
 			  struct rds_info_lengths *lens)
 {
-	rds_for_each_conn_info(sock, len, iter, lens,
+	rds_walk_conn_path_info(sock, len, iter, lens,
 				rds_conn_info_visitor,
 				sizeof(struct rds_info_connection));
 }
@@ -553,10 +659,16 @@ void rds_conn_exit(void)
 /*
  * Force a disconnect
  */
+void rds_conn_path_drop(struct rds_conn_path *cp)
+{
+	atomic_set(&cp->cp_state, RDS_CONN_ERROR);
+	queue_work(rds_wq, &cp->cp_down_w);
+}
+EXPORT_SYMBOL_GPL(rds_conn_path_drop);
+
 void rds_conn_drop(struct rds_connection *conn)
 {
-	atomic_set(&conn->c_state, RDS_CONN_ERROR);
-	queue_work(rds_wq, &conn->c_down_w);
+	rds_conn_path_drop(&conn->c_path[0]);
 }
 EXPORT_SYMBOL_GPL(rds_conn_drop);
 
@@ -564,11 +676,17 @@ EXPORT_SYMBOL_GPL(rds_conn_drop);
  * If the connection is down, trigger a connect. We may have scheduled a
  * delayed reconnect however - in this case we should not interfere.
  */
+void rds_conn_path_connect_if_down(struct rds_conn_path *cp)
+{
+	if (rds_conn_path_state(cp) == RDS_CONN_DOWN &&
+	    !test_and_set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags))
+		queue_delayed_work(rds_wq, &cp->cp_conn_w, 0);
+}
+
 void rds_conn_connect_if_down(struct rds_connection *conn)
 {
-	if (rds_conn_state(conn) == RDS_CONN_DOWN &&
-	    !test_and_set_bit(RDS_RECONNECT_PENDING, &conn->c_flags))
-		queue_delayed_work(rds_wq, &conn->c_conn_w, 0);
+	WARN_ON(conn->c_trans->t_mp_capable);
+	rds_conn_path_connect_if_down(&conn->c_path[0]);
 }
 EXPORT_SYMBOL_GPL(rds_conn_connect_if_down);
 
@@ -586,3 +704,15 @@ __rds_conn_error(struct rds_connection *conn, const char *fmt, ...)
 
 	rds_conn_drop(conn);
 }
+
+void
+__rds_conn_path_error(struct rds_conn_path *cp, const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vprintk(fmt, ap);
+	va_end(ap);
+
+	rds_conn_path_drop(cp);
+}
diff --git a/net/rds/ib.c b/net/rds/ib.c
index b5342fddaf98..7eaf887e46f8 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -40,6 +40,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "ib.h"
 #include "ib_mr.h"
@@ -380,15 +381,15 @@ void rds_ib_exit(void)
 
 struct rds_transport rds_ib_transport = {
 	.laddr_check		= rds_ib_laddr_check,
-	.xmit_complete		= rds_ib_xmit_complete,
+	.xmit_path_complete	= rds_ib_xmit_path_complete,
 	.xmit			= rds_ib_xmit,
 	.xmit_rdma		= rds_ib_xmit_rdma,
 	.xmit_atomic		= rds_ib_xmit_atomic,
-	.recv			= rds_ib_recv,
+	.recv_path		= rds_ib_recv_path,
 	.conn_alloc		= rds_ib_conn_alloc,
 	.conn_free		= rds_ib_conn_free,
-	.conn_connect		= rds_ib_conn_connect,
-	.conn_shutdown		= rds_ib_conn_shutdown,
+	.conn_path_connect	= rds_ib_conn_path_connect,
+	.conn_path_shutdown	= rds_ib_conn_path_shutdown,
 	.inc_copy_to_user	= rds_ib_inc_copy_to_user,
 	.inc_free		= rds_ib_inc_free,
 	.cm_initiate_connect	= rds_ib_cm_initiate_connect,
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 627fb79aee65..046f7508c06b 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -328,8 +328,8 @@ extern struct list_head ib_nodev_conns;
 /* ib_cm.c */
 int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp);
 void rds_ib_conn_free(void *arg);
-int rds_ib_conn_connect(struct rds_connection *conn);
-void rds_ib_conn_shutdown(struct rds_connection *conn);
+int rds_ib_conn_path_connect(struct rds_conn_path *cp);
+void rds_ib_conn_path_shutdown(struct rds_conn_path *cp);
 void rds_ib_state_change(struct sock *sk);
 int rds_ib_listen_init(void);
 void rds_ib_listen_stop(void);
@@ -354,7 +354,7 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc);
 /* ib_recv.c */
 int rds_ib_recv_init(void);
 void rds_ib_recv_exit(void);
-int rds_ib_recv(struct rds_connection *conn);
+int rds_ib_recv_path(struct rds_conn_path *conn);
 int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic);
 void rds_ib_recv_free_caches(struct rds_ib_connection *ic);
 void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp);
@@ -384,7 +384,7 @@ u32 rds_ib_ring_completed(struct rds_ib_work_ring *ring, u32 wr_id, u32 oldest);
 extern wait_queue_head_t rds_ib_ring_empty_wait;
 
 /* ib_send.c */
-void rds_ib_xmit_complete(struct rds_connection *conn);
+void rds_ib_xmit_path_complete(struct rds_conn_path *cp);
 int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
 		unsigned int hdr_off, unsigned int sg, unsigned int off);
 void rds_ib_send_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 310cabce2311..5b2ab95afa07 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -36,6 +36,7 @@
 #include <linux/vmalloc.h>
 #include <linux/ratelimit.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "ib.h"
 
@@ -111,7 +112,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
 		}
 	}
 
-	if (conn->c_version < RDS_PROTOCOL(3,1)) {
+	if (conn->c_version < RDS_PROTOCOL(3, 1)) {
 		printk(KERN_NOTICE "RDS/IB: Connection to %pI4 version %u.%u failed,"
 		       " no longer supported\n",
 		       &conn->c_faddr,
@@ -273,7 +274,7 @@ static void rds_ib_tasklet_fn_send(unsigned long data)
 	if (rds_conn_up(conn) &&
 	    (!test_bit(RDS_LL_SEND_FULL, &conn->c_flags) ||
 	    test_bit(0, &conn->c_map_queued)))
-		rds_send_xmit(ic->conn);
+		rds_send_xmit(&ic->conn->c_path[0]);
 }
 
 static void poll_rcq(struct rds_ib_connection *ic, struct ib_cq *cq,
@@ -684,8 +685,9 @@ out:
 	return ret;
 }
 
-int rds_ib_conn_connect(struct rds_connection *conn)
+int rds_ib_conn_path_connect(struct rds_conn_path *cp)
 {
+	struct rds_connection *conn = cp->cp_conn;
 	struct rds_ib_connection *ic = conn->c_transport_data;
 	struct sockaddr_in src, dest;
 	int ret;
@@ -730,8 +732,9 @@ out:
  * so that it can be called at any point during startup.  In fact it
  * can be called multiple times for a given connection.
  */
-void rds_ib_conn_shutdown(struct rds_connection *conn)
+void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
 {
+	struct rds_connection *conn = cp->cp_conn;
 	struct rds_ib_connection *ic = conn->c_transport_data;
 	int err = 0;
 
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index f7164ac1ffc1..977f69886c00 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -35,6 +35,7 @@
 #include <linux/rculist.h>
 #include <linux/llist.h>
 
+#include "rds_single_path.h"
 #include "ib_mr.h"
 
 struct workqueue_struct *rds_ib_mr_wq;
@@ -618,7 +619,7 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev,
 
 int rds_ib_mr_init(void)
 {
-	rds_ib_mr_wq = create_workqueue("rds_mr_flushd");
+	rds_ib_mr_wq = alloc_workqueue("rds_mr_flushd", WQ_MEM_RECLAIM, 0);
 	if (!rds_ib_mr_wq)
 		return -ENOMEM;
 	return 0;
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index abc8cc805e8d..606a11f681d2 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -36,6 +36,7 @@
 #include <linux/dma-mapping.h>
 #include <rdma/rdma_cm.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "ib.h"
 
@@ -1008,8 +1009,9 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic,
 		rds_ib_recv_refill(conn, 0, GFP_NOWAIT);
 }
 
-int rds_ib_recv(struct rds_connection *conn)
+int rds_ib_recv_path(struct rds_conn_path *cp)
 {
+	struct rds_connection *conn = cp->cp_conn;
 	struct rds_ib_connection *ic = conn->c_transport_data;
 	int ret = 0;
 
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index f27d2c82b036..84d90c97332f 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -36,6 +36,7 @@
 #include <linux/dmapool.h>
 #include <linux/ratelimit.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "ib.h"
 
@@ -979,8 +980,9 @@ out:
 	return ret;
 }
 
-void rds_ib_xmit_complete(struct rds_connection *conn)
+void rds_ib_xmit_path_complete(struct rds_conn_path *cp)
 {
+	struct rds_connection *conn = cp->cp_conn;
 	struct rds_ib_connection *ic = conn->c_transport_data;
 
 	/* We may have a pending ACK or window update we were unable
diff --git a/net/rds/loop.c b/net/rds/loop.c
index 6b12b68541ae..f2bf78de5688 100644
--- a/net/rds/loop.c
+++ b/net/rds/loop.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/in.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "loop.h"
 
@@ -95,12 +96,13 @@ out:
  */
 static void rds_loop_inc_free(struct rds_incoming *inc)
 {
-        struct rds_message *rm = container_of(inc, struct rds_message, m_inc);
-        rds_message_put(rm);
+	struct rds_message *rm = container_of(inc, struct rds_message, m_inc);
+
+	rds_message_put(rm);
 }
 
 /* we need to at least give the thread something to succeed */
-static int rds_loop_recv(struct rds_connection *conn)
+static int rds_loop_recv_path(struct rds_conn_path *cp)
 {
 	return 0;
 }
@@ -148,13 +150,13 @@ static void rds_loop_conn_free(void *arg)
 	kfree(lc);
 }
 
-static int rds_loop_conn_connect(struct rds_connection *conn)
+static int rds_loop_conn_path_connect(struct rds_conn_path *cp)
 {
-	rds_connect_complete(conn);
+	rds_connect_complete(cp->cp_conn);
 	return 0;
 }
 
-static void rds_loop_conn_shutdown(struct rds_connection *conn)
+static void rds_loop_conn_path_shutdown(struct rds_conn_path *cp)
 {
 }
 
@@ -183,11 +185,11 @@ void rds_loop_exit(void)
  */
 struct rds_transport rds_loop_transport = {
 	.xmit			= rds_loop_xmit,
-	.recv			= rds_loop_recv,
+	.recv_path		= rds_loop_recv_path,
 	.conn_alloc		= rds_loop_conn_alloc,
 	.conn_free		= rds_loop_conn_free,
-	.conn_connect		= rds_loop_conn_connect,
-	.conn_shutdown		= rds_loop_conn_shutdown,
+	.conn_path_connect	= rds_loop_conn_path_connect,
+	.conn_path_shutdown	= rds_loop_conn_path_shutdown,
 	.inc_copy_to_user	= rds_message_inc_copy_to_user,
 	.inc_free		= rds_loop_inc_free,
 	.t_name			= "loopback",
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 7220bebcf558..345f09059e9f 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -33,6 +33,7 @@
 #include <linux/module.h>
 #include <rdma/rdma_cm.h>
 
+#include "rds_single_path.h"
 #include "rdma_transport.h"
 #include "ib.h"
 
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 80256b08eac0..6ef07bd27227 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -74,6 +74,7 @@ enum {
 	RDS_CONN_CONNECTING,
 	RDS_CONN_DISCONNECTING,
 	RDS_CONN_UP,
+	RDS_CONN_RESETTING,
 	RDS_CONN_ERROR,
 };
 
@@ -83,56 +84,69 @@ enum {
 #define RDS_IN_XMIT		2
 #define RDS_RECV_REFILL		3
 
+/* Max number of multipaths per RDS connection. Must be a power of 2 */
+#define	RDS_MPATH_WORKERS	1
+
+/* Per mpath connection state */
+struct rds_conn_path {
+	struct rds_connection	*cp_conn;
+	struct rds_message	*cp_xmit_rm;
+	unsigned long		cp_xmit_sg;
+	unsigned int		cp_xmit_hdr_off;
+	unsigned int		cp_xmit_data_off;
+	unsigned int		cp_xmit_atomic_sent;
+	unsigned int		cp_xmit_rdma_sent;
+	unsigned int		cp_xmit_data_sent;
+
+	spinlock_t		cp_lock;		/* protect msg queues */
+	u64			cp_next_tx_seq;
+	struct list_head	cp_send_queue;
+	struct list_head	cp_retrans;
+
+	u64			cp_next_rx_seq;
+
+	void			*cp_transport_data;
+
+	atomic_t		cp_state;
+	unsigned long		cp_send_gen;
+	unsigned long		cp_flags;
+	unsigned long		cp_reconnect_jiffies;
+	struct delayed_work	cp_send_w;
+	struct delayed_work	cp_recv_w;
+	struct delayed_work	cp_conn_w;
+	struct work_struct	cp_down_w;
+	struct mutex		cp_cm_lock;	/* protect cp_state & cm */
+	wait_queue_head_t	cp_waitq;
+
+	unsigned int		cp_unacked_packets;
+	unsigned int		cp_unacked_bytes;
+	unsigned int		cp_outgoing:1,
+				cp_pad_to_32:31;
+	unsigned int		cp_index;
+};
+
+/* One rds_connection per RDS address pair */
 struct rds_connection {
 	struct hlist_node	c_hash_node;
 	__be32			c_laddr;
 	__be32			c_faddr;
 	unsigned int		c_loopback:1,
-				c_outgoing:1,
-				c_pad_to_32:30;
+				c_pad_to_32:31;
+	int			c_npaths;
 	struct rds_connection	*c_passive;
+	struct rds_transport	*c_trans;
 
 	struct rds_cong_map	*c_lcong;
 	struct rds_cong_map	*c_fcong;
 
-	struct rds_message	*c_xmit_rm;
-	unsigned long		c_xmit_sg;
-	unsigned int		c_xmit_hdr_off;
-	unsigned int		c_xmit_data_off;
-	unsigned int		c_xmit_atomic_sent;
-	unsigned int		c_xmit_rdma_sent;
-	unsigned int		c_xmit_data_sent;
-
-	spinlock_t		c_lock;		/* protect msg queues */
-	u64			c_next_tx_seq;
-	struct list_head	c_send_queue;
-	struct list_head	c_retrans;
-
-	u64			c_next_rx_seq;
-
-	struct rds_transport	*c_trans;
-	void			*c_transport_data;
-
-	atomic_t		c_state;
-	unsigned long		c_send_gen;
-	unsigned long		c_flags;
-	unsigned long		c_reconnect_jiffies;
-	struct delayed_work	c_send_w;
-	struct delayed_work	c_recv_w;
-	struct delayed_work	c_conn_w;
-	struct work_struct	c_down_w;
-	struct mutex		c_cm_lock;	/* protect conn state & cm */
-	wait_queue_head_t	c_waitq;
+	/* Protocol version */
+	unsigned int		c_version;
+	possible_net_t		c_net;
 
 	struct list_head	c_map_item;
 	unsigned long		c_map_queued;
 
-	unsigned int		c_unacked_packets;
-	unsigned int		c_unacked_bytes;
-
-	/* Protocol version */
-	unsigned int		c_version;
-	possible_net_t		c_net;
+	struct rds_conn_path	c_path[RDS_MPATH_WORKERS];
 };
 
 static inline
@@ -217,6 +231,7 @@ struct rds_incoming {
 	atomic_t		i_refcount;
 	struct list_head	i_item;
 	struct rds_connection	*i_conn;
+	struct rds_conn_path	*i_conn_path;
 	struct rds_header	i_hdr;
 	unsigned long		i_rx_jiffies;
 	__be32			i_saddr;
@@ -432,21 +447,22 @@ struct rds_transport {
 	char			t_name[TRANSNAMSIZ];
 	struct list_head	t_item;
 	struct module		*t_owner;
-	unsigned int		t_prefer_loopback:1;
+	unsigned int		t_prefer_loopback:1,
+				t_mp_capable:1;
 	unsigned int		t_type;
 
 	int (*laddr_check)(struct net *net, __be32 addr);
 	int (*conn_alloc)(struct rds_connection *conn, gfp_t gfp);
 	void (*conn_free)(void *data);
-	int (*conn_connect)(struct rds_connection *conn);
-	void (*conn_shutdown)(struct rds_connection *conn);
-	void (*xmit_prepare)(struct rds_connection *conn);
-	void (*xmit_complete)(struct rds_connection *conn);
+	int (*conn_path_connect)(struct rds_conn_path *cp);
+	void (*conn_path_shutdown)(struct rds_conn_path *conn);
+	void (*xmit_path_prepare)(struct rds_conn_path *cp);
+	void (*xmit_path_complete)(struct rds_conn_path *cp);
 	int (*xmit)(struct rds_connection *conn, struct rds_message *rm,
 		    unsigned int hdr_off, unsigned int sg, unsigned int off);
 	int (*xmit_rdma)(struct rds_connection *conn, struct rm_rdma_op *op);
 	int (*xmit_atomic)(struct rds_connection *conn, struct rm_atomic_op *op);
-	int (*recv)(struct rds_connection *conn);
+	int (*recv_path)(struct rds_conn_path *cp);
 	int (*inc_copy_to_user)(struct rds_incoming *inc, struct iov_iter *to);
 	void (*inc_free)(struct rds_incoming *inc);
 
@@ -635,10 +651,12 @@ struct rds_connection *rds_conn_create(struct net *net,
 struct rds_connection *rds_conn_create_outgoing(struct net *net,
 						__be32 laddr, __be32 faddr,
 			       struct rds_transport *trans, gfp_t gfp);
-void rds_conn_shutdown(struct rds_connection *conn);
+void rds_conn_shutdown(struct rds_conn_path *cpath);
 void rds_conn_destroy(struct rds_connection *conn);
 void rds_conn_drop(struct rds_connection *conn);
+void rds_conn_path_drop(struct rds_conn_path *cpath);
 void rds_conn_connect_if_down(struct rds_connection *conn);
+void rds_conn_path_connect_if_down(struct rds_conn_path *cp);
 void rds_for_each_conn_info(struct socket *sock, unsigned int len,
 			  struct rds_info_iterator *iter,
 			  struct rds_info_lengths *lens,
@@ -649,28 +667,60 @@ void __rds_conn_error(struct rds_connection *conn, const char *, ...);
 #define rds_conn_error(conn, fmt...) \
 	__rds_conn_error(conn, KERN_WARNING "RDS: " fmt)
 
+void __rds_conn_path_error(struct rds_conn_path *cp, const char *, ...);
+#define rds_conn_path_error(cp, fmt...) \
+	__rds_conn_path_error(cp, KERN_WARNING "RDS: " fmt)
+
+static inline int
+rds_conn_path_transition(struct rds_conn_path *cp, int old, int new)
+{
+	return atomic_cmpxchg(&cp->cp_state, old, new) == old;
+}
+
 static inline int
 rds_conn_transition(struct rds_connection *conn, int old, int new)
 {
-	return atomic_cmpxchg(&conn->c_state, old, new) == old;
+	WARN_ON(conn->c_trans->t_mp_capable);
+	return rds_conn_path_transition(&conn->c_path[0], old, new);
+}
+
+static inline int
+rds_conn_path_state(struct rds_conn_path *cp)
+{
+	return atomic_read(&cp->cp_state);
 }
 
 static inline int
 rds_conn_state(struct rds_connection *conn)
 {
-	return atomic_read(&conn->c_state);
+	WARN_ON(conn->c_trans->t_mp_capable);
+	return rds_conn_path_state(&conn->c_path[0]);
+}
+
+static inline int
+rds_conn_path_up(struct rds_conn_path *cp)
+{
+	return atomic_read(&cp->cp_state) == RDS_CONN_UP;
 }
 
 static inline int
 rds_conn_up(struct rds_connection *conn)
 {
-	return atomic_read(&conn->c_state) == RDS_CONN_UP;
+	WARN_ON(conn->c_trans->t_mp_capable);
+	return rds_conn_path_up(&conn->c_path[0]);
+}
+
+static inline int
+rds_conn_path_connecting(struct rds_conn_path *cp)
+{
+	return atomic_read(&cp->cp_state) == RDS_CONN_CONNECTING;
 }
 
 static inline int
 rds_conn_connecting(struct rds_connection *conn)
 {
-	return atomic_read(&conn->c_state) == RDS_CONN_CONNECTING;
+	WARN_ON(conn->c_trans->t_mp_capable);
+	return rds_conn_path_connecting(&conn->c_path[0]);
 }
 
 /* message.c */
@@ -719,6 +769,8 @@ void rds_page_exit(void);
 /* recv.c */
 void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
 		  __be32 saddr);
+void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *conn,
+		       __be32 saddr);
 void rds_inc_put(struct rds_incoming *inc);
 void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
 		       struct rds_incoming *inc, gfp_t gfp);
@@ -732,16 +784,16 @@ void rds_inc_info_copy(struct rds_incoming *inc,
 
 /* send.c */
 int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len);
-void rds_send_reset(struct rds_connection *conn);
-int rds_send_xmit(struct rds_connection *conn);
+void rds_send_path_reset(struct rds_conn_path *conn);
+int rds_send_xmit(struct rds_conn_path *cp);
 struct sockaddr_in;
 void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest);
 typedef int (*is_acked_func)(struct rds_message *rm, uint64_t ack);
 void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
 			 is_acked_func is_acked);
-int rds_send_pong(struct rds_connection *conn, __be16 dport);
-struct rds_message *rds_send_get_message(struct rds_connection *,
-					 struct rm_rdma_op *);
+void rds_send_path_drop_acked(struct rds_conn_path *cp, u64 ack,
+			      is_acked_func is_acked);
+int rds_send_pong(struct rds_conn_path *cp, __be16 dport);
 
 /* rdma.c */
 void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force);
@@ -808,11 +860,12 @@ extern unsigned int  rds_sysctl_trace_level;
 int rds_threads_init(void);
 void rds_threads_exit(void);
 extern struct workqueue_struct *rds_wq;
-void rds_queue_reconnect(struct rds_connection *conn);
+void rds_queue_reconnect(struct rds_conn_path *cp);
 void rds_connect_worker(struct work_struct *);
 void rds_shutdown_worker(struct work_struct *);
 void rds_send_worker(struct work_struct *);
 void rds_recv_worker(struct work_struct *);
+void rds_connect_path_complete(struct rds_conn_path *conn, int curr);
 void rds_connect_complete(struct rds_connection *conn);
 
 /* transport.c */
diff --git a/net/rds/rds_single_path.h b/net/rds/rds_single_path.h
new file mode 100644
index 000000000000..e1241af7c1ad
--- /dev/null
+++ b/net/rds/rds_single_path.h
@@ -0,0 +1,30 @@
+#ifndef _RDS_RDS_SINGLE_H
+#define _RDS_RDS_SINGLE_H
+
+#define	c_xmit_rm		c_path[0].cp_xmit_rm
+#define	c_xmit_sg		c_path[0].cp_xmit_sg
+#define	c_xmit_hdr_off		c_path[0].cp_xmit_hdr_off
+#define	c_xmit_data_off		c_path[0].cp_xmit_data_off
+#define	c_xmit_atomic_sent	c_path[0].cp_xmit_atomic_sent
+#define	c_xmit_rdma_sent	c_path[0].cp_xmit_rdma_sent
+#define	c_xmit_data_sent	c_path[0].cp_xmit_data_sent
+#define	c_lock			c_path[0].cp_lock
+#define c_next_tx_seq		c_path[0].cp_next_tx_seq
+#define c_send_queue		c_path[0].cp_send_queue
+#define c_retrans		c_path[0].cp_retrans
+#define c_next_rx_seq		c_path[0].cp_next_rx_seq
+#define c_transport_data	c_path[0].cp_transport_data
+#define c_state			c_path[0].cp_state
+#define c_send_gen		c_path[0].cp_send_gen
+#define c_flags			c_path[0].cp_flags
+#define c_reconnect_jiffies	c_path[0].cp_reconnect_jiffies
+#define c_send_w		c_path[0].cp_send_w
+#define c_recv_w		c_path[0].cp_recv_w
+#define c_conn_w		c_path[0].cp_conn_w
+#define c_down_w		c_path[0].cp_down_w
+#define c_cm_lock		c_path[0].cp_cm_lock
+#define c_waitq			c_path[0].cp_waitq
+#define c_unacked_packets	c_path[0].cp_unacked_packets
+#define c_unacked_bytes		c_path[0].cp_unacked_bytes
+
+#endif /* _RDS_RDS_SINGLE_H */
diff --git a/net/rds/recv.c b/net/rds/recv.c
index c0be1ecd11c9..fed53a6c2890 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -53,6 +53,20 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
 }
 EXPORT_SYMBOL_GPL(rds_inc_init);
 
+void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *cp,
+		       __be32 saddr)
+{
+	atomic_set(&inc->i_refcount, 1);
+	INIT_LIST_HEAD(&inc->i_item);
+	inc->i_conn = cp->cp_conn;
+	inc->i_conn_path = cp;
+	inc->i_saddr = saddr;
+	inc->i_rdma_cookie = 0;
+	inc->i_rx_tstamp.tv_sec = 0;
+	inc->i_rx_tstamp.tv_usec = 0;
+}
+EXPORT_SYMBOL_GPL(rds_inc_path_init);
+
 static void rds_inc_addref(struct rds_incoming *inc)
 {
 	rdsdebug("addref inc %p ref %d\n", inc, atomic_read(&inc->i_refcount));
@@ -164,13 +178,18 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
 	struct rds_sock *rs = NULL;
 	struct sock *sk;
 	unsigned long flags;
+	struct rds_conn_path *cp;
 
 	inc->i_conn = conn;
 	inc->i_rx_jiffies = jiffies;
+	if (conn->c_trans->t_mp_capable)
+		cp = inc->i_conn_path;
+	else
+		cp = &conn->c_path[0];
 
 	rdsdebug("conn %p next %llu inc %p seq %llu len %u sport %u dport %u "
 		 "flags 0x%x rx_jiffies %lu\n", conn,
-		 (unsigned long long)conn->c_next_rx_seq,
+		 (unsigned long long)cp->cp_next_rx_seq,
 		 inc,
 		 (unsigned long long)be64_to_cpu(inc->i_hdr.h_sequence),
 		 be32_to_cpu(inc->i_hdr.h_len),
@@ -199,16 +218,20 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
 	 * XXX we could spend more on the wire to get more robust failure
 	 * detection, arguably worth it to avoid data corruption.
 	 */
-	if (be64_to_cpu(inc->i_hdr.h_sequence) < conn->c_next_rx_seq &&
+	if (be64_to_cpu(inc->i_hdr.h_sequence) < cp->cp_next_rx_seq &&
 	    (inc->i_hdr.h_flags & RDS_FLAG_RETRANSMITTED)) {
 		rds_stats_inc(s_recv_drop_old_seq);
 		goto out;
 	}
-	conn->c_next_rx_seq = be64_to_cpu(inc->i_hdr.h_sequence) + 1;
+	cp->cp_next_rx_seq = be64_to_cpu(inc->i_hdr.h_sequence) + 1;
 
 	if (rds_sysctl_ping_enable && inc->i_hdr.h_dport == 0) {
+		if (inc->i_hdr.h_sport == 0) {
+			rdsdebug("ignore ping with 0 sport from 0x%x\n", saddr);
+			goto out;
+		}
 		rds_stats_inc(s_recv_ping);
-		rds_send_pong(conn, inc->i_hdr.h_sport);
+		rds_send_pong(cp, inc->i_hdr.h_sport);
 		goto out;
 	}
 
@@ -561,5 +584,7 @@ void rds_inc_info_copy(struct rds_incoming *inc,
 		minfo.fport = inc->i_hdr.h_dport;
 	}
 
+	minfo.flags = 0;
+
 	rds_info_copy(iter, &minfo, sizeof(minfo));
 }
diff --git a/net/rds/send.c b/net/rds/send.c
index c9cdb358ea88..5a9caf1da896 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -62,14 +62,14 @@ static void rds_send_remove_from_sock(struct list_head *messages, int status);
  * Reset the send state.  Callers must ensure that this doesn't race with
  * rds_send_xmit().
  */
-void rds_send_reset(struct rds_connection *conn)
+void rds_send_path_reset(struct rds_conn_path *cp)
 {
 	struct rds_message *rm, *tmp;
 	unsigned long flags;
 
-	if (conn->c_xmit_rm) {
-		rm = conn->c_xmit_rm;
-		conn->c_xmit_rm = NULL;
+	if (cp->cp_xmit_rm) {
+		rm = cp->cp_xmit_rm;
+		cp->cp_xmit_rm = NULL;
 		/* Tell the user the RDMA op is no longer mapped by the
 		 * transport. This isn't entirely true (it's flushed out
 		 * independently) but as the connection is down, there's
@@ -78,36 +78,37 @@ void rds_send_reset(struct rds_connection *conn)
 		rds_message_put(rm);
 	}
 
-	conn->c_xmit_sg = 0;
-	conn->c_xmit_hdr_off = 0;
-	conn->c_xmit_data_off = 0;
-	conn->c_xmit_atomic_sent = 0;
-	conn->c_xmit_rdma_sent = 0;
-	conn->c_xmit_data_sent = 0;
+	cp->cp_xmit_sg = 0;
+	cp->cp_xmit_hdr_off = 0;
+	cp->cp_xmit_data_off = 0;
+	cp->cp_xmit_atomic_sent = 0;
+	cp->cp_xmit_rdma_sent = 0;
+	cp->cp_xmit_data_sent = 0;
 
-	conn->c_map_queued = 0;
+	cp->cp_conn->c_map_queued = 0;
 
-	conn->c_unacked_packets = rds_sysctl_max_unacked_packets;
-	conn->c_unacked_bytes = rds_sysctl_max_unacked_bytes;
+	cp->cp_unacked_packets = rds_sysctl_max_unacked_packets;
+	cp->cp_unacked_bytes = rds_sysctl_max_unacked_bytes;
 
 	/* Mark messages as retransmissions, and move them to the send q */
-	spin_lock_irqsave(&conn->c_lock, flags);
-	list_for_each_entry_safe(rm, tmp, &conn->c_retrans, m_conn_item) {
+	spin_lock_irqsave(&cp->cp_lock, flags);
+	list_for_each_entry_safe(rm, tmp, &cp->cp_retrans, m_conn_item) {
 		set_bit(RDS_MSG_ACK_REQUIRED, &rm->m_flags);
 		set_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags);
 	}
-	list_splice_init(&conn->c_retrans, &conn->c_send_queue);
-	spin_unlock_irqrestore(&conn->c_lock, flags);
+	list_splice_init(&cp->cp_retrans, &cp->cp_send_queue);
+	spin_unlock_irqrestore(&cp->cp_lock, flags);
 }
+EXPORT_SYMBOL_GPL(rds_send_path_reset);
 
-static int acquire_in_xmit(struct rds_connection *conn)
+static int acquire_in_xmit(struct rds_conn_path *cp)
 {
-	return test_and_set_bit(RDS_IN_XMIT, &conn->c_flags) == 0;
+	return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0;
 }
 
-static void release_in_xmit(struct rds_connection *conn)
+static void release_in_xmit(struct rds_conn_path *cp)
 {
-	clear_bit(RDS_IN_XMIT, &conn->c_flags);
+	clear_bit(RDS_IN_XMIT, &cp->cp_flags);
 	smp_mb__after_atomic();
 	/*
 	 * We don't use wait_on_bit()/wake_up_bit() because our waking is in a
@@ -115,8 +116,8 @@ static void release_in_xmit(struct rds_connection *conn)
 	 * the system-wide hashed waitqueue buckets in the fast path only to
 	 * almost never find waiters.
 	 */
-	if (waitqueue_active(&conn->c_waitq))
-		wake_up_all(&conn->c_waitq);
+	if (waitqueue_active(&cp->cp_waitq))
+		wake_up_all(&cp->cp_waitq);
 }
 
 /*
@@ -133,8 +134,9 @@ static void release_in_xmit(struct rds_connection *conn)
  *      - small message latency is higher behind queued large messages
  *      - large message latency isn't starved by intervening small sends
  */
-int rds_send_xmit(struct rds_connection *conn)
+int rds_send_xmit(struct rds_conn_path *cp)
 {
+	struct rds_connection *conn = cp->cp_conn;
 	struct rds_message *rm;
 	unsigned long flags;
 	unsigned int tmp;
@@ -154,7 +156,7 @@ restart:
 	 * avoids blocking the caller and trading per-connection data between
 	 * caches per message.
 	 */
-	if (!acquire_in_xmit(conn)) {
+	if (!acquire_in_xmit(cp)) {
 		rds_stats_inc(s_send_lock_contention);
 		ret = -ENOMEM;
 		goto out;
@@ -168,21 +170,21 @@ restart:
 	 * The acquire_in_xmit() check above ensures that only one
 	 * caller can increment c_send_gen at any time.
 	 */
-	conn->c_send_gen++;
-	send_gen = conn->c_send_gen;
+	cp->cp_send_gen++;
+	send_gen = cp->cp_send_gen;
 
 	/*
 	 * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT,
 	 * we do the opposite to avoid races.
 	 */
-	if (!rds_conn_up(conn)) {
-		release_in_xmit(conn);
+	if (!rds_conn_path_up(cp)) {
+		release_in_xmit(cp);
 		ret = 0;
 		goto out;
 	}
 
-	if (conn->c_trans->xmit_prepare)
-		conn->c_trans->xmit_prepare(conn);
+	if (conn->c_trans->xmit_path_prepare)
+		conn->c_trans->xmit_path_prepare(cp);
 
 	/*
 	 * spin trying to push headers and data down the connection until
@@ -190,7 +192,7 @@ restart:
 	 */
 	while (1) {
 
-		rm = conn->c_xmit_rm;
+		rm = cp->cp_xmit_rm;
 
 		/*
 		 * If between sending messages, we can send a pending congestion
@@ -203,14 +205,16 @@ restart:
 				break;
 			}
 			rm->data.op_active = 1;
+			rm->m_inc.i_conn_path = cp;
+			rm->m_inc.i_conn = cp->cp_conn;
 
-			conn->c_xmit_rm = rm;
+			cp->cp_xmit_rm = rm;
 		}
 
 		/*
 		 * If not already working on one, grab the next message.
 		 *
-		 * c_xmit_rm holds a ref while we're sending this message down
+		 * cp_xmit_rm holds a ref while we're sending this message down
 		 * the connction.  We can use this ref while holding the
 		 * send_sem.. rds_send_reset() is serialized with it.
 		 */
@@ -227,10 +231,10 @@ restart:
 			if (batch_count >= send_batch_count)
 				goto over_batch;
 
-			spin_lock_irqsave(&conn->c_lock, flags);
+			spin_lock_irqsave(&cp->cp_lock, flags);
 
-			if (!list_empty(&conn->c_send_queue)) {
-				rm = list_entry(conn->c_send_queue.next,
+			if (!list_empty(&cp->cp_send_queue)) {
+				rm = list_entry(cp->cp_send_queue.next,
 						struct rds_message,
 						m_conn_item);
 				rds_message_addref(rm);
@@ -239,10 +243,11 @@ restart:
 				 * Move the message from the send queue to the retransmit
 				 * list right away.
 				 */
-				list_move_tail(&rm->m_conn_item, &conn->c_retrans);
+				list_move_tail(&rm->m_conn_item,
+					       &cp->cp_retrans);
 			}
 
-			spin_unlock_irqrestore(&conn->c_lock, flags);
+			spin_unlock_irqrestore(&cp->cp_lock, flags);
 
 			if (!rm)
 				break;
@@ -256,32 +261,34 @@ restart:
 			 */
 			if (rm->rdma.op_active &&
 			    test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags)) {
-				spin_lock_irqsave(&conn->c_lock, flags);
+				spin_lock_irqsave(&cp->cp_lock, flags);
 				if (test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags))
 					list_move(&rm->m_conn_item, &to_be_dropped);
-				spin_unlock_irqrestore(&conn->c_lock, flags);
+				spin_unlock_irqrestore(&cp->cp_lock, flags);
 				continue;
 			}
 
 			/* Require an ACK every once in a while */
 			len = ntohl(rm->m_inc.i_hdr.h_len);
-			if (conn->c_unacked_packets == 0 ||
-			    conn->c_unacked_bytes < len) {
+			if (cp->cp_unacked_packets == 0 ||
+			    cp->cp_unacked_bytes < len) {
 				__set_bit(RDS_MSG_ACK_REQUIRED, &rm->m_flags);
 
-				conn->c_unacked_packets = rds_sysctl_max_unacked_packets;
-				conn->c_unacked_bytes = rds_sysctl_max_unacked_bytes;
+				cp->cp_unacked_packets =
+					rds_sysctl_max_unacked_packets;
+				cp->cp_unacked_bytes =
+					rds_sysctl_max_unacked_bytes;
 				rds_stats_inc(s_send_ack_required);
 			} else {
-				conn->c_unacked_bytes -= len;
-				conn->c_unacked_packets--;
+				cp->cp_unacked_bytes -= len;
+				cp->cp_unacked_packets--;
 			}
 
-			conn->c_xmit_rm = rm;
+			cp->cp_xmit_rm = rm;
 		}
 
 		/* The transport either sends the whole rdma or none of it */
-		if (rm->rdma.op_active && !conn->c_xmit_rdma_sent) {
+		if (rm->rdma.op_active && !cp->cp_xmit_rdma_sent) {
 			rm->m_final_op = &rm->rdma;
 			/* The transport owns the mapped memory for now.
 			 * You can't unmap it while it's on the send queue
@@ -293,11 +300,11 @@ restart:
 				wake_up_interruptible(&rm->m_flush_wait);
 				break;
 			}
-			conn->c_xmit_rdma_sent = 1;
+			cp->cp_xmit_rdma_sent = 1;
 
 		}
 
-		if (rm->atomic.op_active && !conn->c_xmit_atomic_sent) {
+		if (rm->atomic.op_active && !cp->cp_xmit_atomic_sent) {
 			rm->m_final_op = &rm->atomic;
 			/* The transport owns the mapped memory for now.
 			 * You can't unmap it while it's on the send queue
@@ -309,7 +316,7 @@ restart:
 				wake_up_interruptible(&rm->m_flush_wait);
 				break;
 			}
-			conn->c_xmit_atomic_sent = 1;
+			cp->cp_xmit_atomic_sent = 1;
 
 		}
 
@@ -335,41 +342,42 @@ restart:
 				rm->data.op_active = 0;
 		}
 
-		if (rm->data.op_active && !conn->c_xmit_data_sent) {
+		if (rm->data.op_active && !cp->cp_xmit_data_sent) {
 			rm->m_final_op = &rm->data;
+
 			ret = conn->c_trans->xmit(conn, rm,
-						  conn->c_xmit_hdr_off,
-						  conn->c_xmit_sg,
-						  conn->c_xmit_data_off);
+						  cp->cp_xmit_hdr_off,
+						  cp->cp_xmit_sg,
+						  cp->cp_xmit_data_off);
 			if (ret <= 0)
 				break;
 
-			if (conn->c_xmit_hdr_off < sizeof(struct rds_header)) {
+			if (cp->cp_xmit_hdr_off < sizeof(struct rds_header)) {
 				tmp = min_t(int, ret,
 					    sizeof(struct rds_header) -
-					    conn->c_xmit_hdr_off);
-				conn->c_xmit_hdr_off += tmp;
+					    cp->cp_xmit_hdr_off);
+				cp->cp_xmit_hdr_off += tmp;
 				ret -= tmp;
 			}
 
-			sg = &rm->data.op_sg[conn->c_xmit_sg];
+			sg = &rm->data.op_sg[cp->cp_xmit_sg];
 			while (ret) {
 				tmp = min_t(int, ret, sg->length -
-						      conn->c_xmit_data_off);
-				conn->c_xmit_data_off += tmp;
+						      cp->cp_xmit_data_off);
+				cp->cp_xmit_data_off += tmp;
 				ret -= tmp;
-				if (conn->c_xmit_data_off == sg->length) {
-					conn->c_xmit_data_off = 0;
+				if (cp->cp_xmit_data_off == sg->length) {
+					cp->cp_xmit_data_off = 0;
 					sg++;
-					conn->c_xmit_sg++;
-					BUG_ON(ret != 0 &&
-					       conn->c_xmit_sg == rm->data.op_nents);
+					cp->cp_xmit_sg++;
+					BUG_ON(ret != 0 && cp->cp_xmit_sg ==
+					       rm->data.op_nents);
 				}
 			}
 
-			if (conn->c_xmit_hdr_off == sizeof(struct rds_header) &&
-			    (conn->c_xmit_sg == rm->data.op_nents))
-				conn->c_xmit_data_sent = 1;
+			if (cp->cp_xmit_hdr_off == sizeof(struct rds_header) &&
+			    (cp->cp_xmit_sg == rm->data.op_nents))
+				cp->cp_xmit_data_sent = 1;
 		}
 
 		/*
@@ -377,23 +385,23 @@ restart:
 		 * if there is a data op. Thus, if the data is sent (or there was
 		 * none), then we're done with the rm.
 		 */
-		if (!rm->data.op_active || conn->c_xmit_data_sent) {
-			conn->c_xmit_rm = NULL;
-			conn->c_xmit_sg = 0;
-			conn->c_xmit_hdr_off = 0;
-			conn->c_xmit_data_off = 0;
-			conn->c_xmit_rdma_sent = 0;
-			conn->c_xmit_atomic_sent = 0;
-			conn->c_xmit_data_sent = 0;
+		if (!rm->data.op_active || cp->cp_xmit_data_sent) {
+			cp->cp_xmit_rm = NULL;
+			cp->cp_xmit_sg = 0;
+			cp->cp_xmit_hdr_off = 0;
+			cp->cp_xmit_data_off = 0;
+			cp->cp_xmit_rdma_sent = 0;
+			cp->cp_xmit_atomic_sent = 0;
+			cp->cp_xmit_data_sent = 0;
 
 			rds_message_put(rm);
 		}
 	}
 
 over_batch:
-	if (conn->c_trans->xmit_complete)
-		conn->c_trans->xmit_complete(conn);
-	release_in_xmit(conn);
+	if (conn->c_trans->xmit_path_complete)
+		conn->c_trans->xmit_path_complete(cp);
+	release_in_xmit(cp);
 
 	/* Nuke any messages we decided not to retransmit. */
 	if (!list_empty(&to_be_dropped)) {
@@ -421,12 +429,12 @@ over_batch:
 	if (ret == 0) {
 		smp_mb();
 		if ((test_bit(0, &conn->c_map_queued) ||
-		     !list_empty(&conn->c_send_queue)) &&
-		    send_gen == conn->c_send_gen) {
+		     !list_empty(&cp->cp_send_queue)) &&
+		    send_gen == cp->cp_send_gen) {
 			rds_stats_inc(s_send_lock_queue_raced);
 			if (batch_count < send_batch_count)
 				goto restart;
-			queue_delayed_work(rds_wq, &conn->c_send_w, 1);
+			queue_delayed_work(rds_wq, &cp->cp_send_w, 1);
 		}
 	}
 out:
@@ -559,42 +567,6 @@ __rds_send_complete(struct rds_sock *rs, struct rds_message *rm, int status)
 }
 
 /*
- * This is called from the IB send completion when we detect
- * a RDMA operation that failed with remote access error.
- * So speed is not an issue here.
- */
-struct rds_message *rds_send_get_message(struct rds_connection *conn,
-					 struct rm_rdma_op *op)
-{
-	struct rds_message *rm, *tmp, *found = NULL;
-	unsigned long flags;
-
-	spin_lock_irqsave(&conn->c_lock, flags);
-
-	list_for_each_entry_safe(rm, tmp, &conn->c_retrans, m_conn_item) {
-		if (&rm->rdma == op) {
-			atomic_inc(&rm->m_refcount);
-			found = rm;
-			goto out;
-		}
-	}
-
-	list_for_each_entry_safe(rm, tmp, &conn->c_send_queue, m_conn_item) {
-		if (&rm->rdma == op) {
-			atomic_inc(&rm->m_refcount);
-			found = rm;
-			break;
-		}
-	}
-
-out:
-	spin_unlock_irqrestore(&conn->c_lock, flags);
-
-	return found;
-}
-EXPORT_SYMBOL_GPL(rds_send_get_message);
-
-/*
  * This removes messages from the socket's list if they're on it.  The list
  * argument must be private to the caller, we must be able to modify it
  * without locks.  The messages must have a reference held for their
@@ -684,16 +656,16 @@ unlock_and_drop:
  * assigned the m_ack_seq yet - but that's fine as long as tcp_is_acked
  * checks the RDS_MSG_HAS_ACK_SEQ bit.
  */
-void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
-			 is_acked_func is_acked)
+void rds_send_path_drop_acked(struct rds_conn_path *cp, u64 ack,
+			      is_acked_func is_acked)
 {
 	struct rds_message *rm, *tmp;
 	unsigned long flags;
 	LIST_HEAD(list);
 
-	spin_lock_irqsave(&conn->c_lock, flags);
+	spin_lock_irqsave(&cp->cp_lock, flags);
 
-	list_for_each_entry_safe(rm, tmp, &conn->c_retrans, m_conn_item) {
+	list_for_each_entry_safe(rm, tmp, &cp->cp_retrans, m_conn_item) {
 		if (!rds_send_is_acked(rm, ack, is_acked))
 			break;
 
@@ -705,17 +677,26 @@ void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
 	if (!list_empty(&list))
 		smp_mb__after_atomic();
 
-	spin_unlock_irqrestore(&conn->c_lock, flags);
+	spin_unlock_irqrestore(&cp->cp_lock, flags);
 
 	/* now remove the messages from the sock list as needed */
 	rds_send_remove_from_sock(&list, RDS_RDMA_SUCCESS);
 }
+EXPORT_SYMBOL_GPL(rds_send_path_drop_acked);
+
+void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
+			 is_acked_func is_acked)
+{
+	WARN_ON(conn->c_trans->t_mp_capable);
+	rds_send_path_drop_acked(&conn->c_path[0], ack, is_acked);
+}
 EXPORT_SYMBOL_GPL(rds_send_drop_acked);
 
 void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
 {
 	struct rds_message *rm, *tmp;
 	struct rds_connection *conn;
+	struct rds_conn_path *cp;
 	unsigned long flags;
 	LIST_HEAD(list);
 
@@ -744,22 +725,26 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
 	list_for_each_entry(rm, &list, m_sock_item) {
 
 		conn = rm->m_inc.i_conn;
+		if (conn->c_trans->t_mp_capable)
+			cp = rm->m_inc.i_conn_path;
+		else
+			cp = &conn->c_path[0];
 
-		spin_lock_irqsave(&conn->c_lock, flags);
+		spin_lock_irqsave(&cp->cp_lock, flags);
 		/*
 		 * Maybe someone else beat us to removing rm from the conn.
 		 * If we race with their flag update we'll get the lock and
 		 * then really see that the flag has been cleared.
 		 */
 		if (!test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags)) {
-			spin_unlock_irqrestore(&conn->c_lock, flags);
+			spin_unlock_irqrestore(&cp->cp_lock, flags);
 			spin_lock_irqsave(&rm->m_rs_lock, flags);
 			rm->m_rs = NULL;
 			spin_unlock_irqrestore(&rm->m_rs_lock, flags);
 			continue;
 		}
 		list_del_init(&rm->m_conn_item);
-		spin_unlock_irqrestore(&conn->c_lock, flags);
+		spin_unlock_irqrestore(&cp->cp_lock, flags);
 
 		/*
 		 * Couldn't grab m_rs_lock in top loop (lock ordering),
@@ -808,6 +793,7 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
  * message from the flow with RDS_CANCEL_SENT_TO.
  */
 static int rds_send_queue_rm(struct rds_sock *rs, struct rds_connection *conn,
+			     struct rds_conn_path *cp,
 			     struct rds_message *rm, __be16 sport,
 			     __be16 dport, int *queued)
 {
@@ -851,13 +837,14 @@ static int rds_send_queue_rm(struct rds_sock *rs, struct rds_connection *conn,
 		   trying to minimize the time we hold c_lock */
 		rds_message_populate_header(&rm->m_inc.i_hdr, sport, dport, 0);
 		rm->m_inc.i_conn = conn;
+		rm->m_inc.i_conn_path = cp;
 		rds_message_addref(rm);
 
-		spin_lock(&conn->c_lock);
-		rm->m_inc.i_hdr.h_sequence = cpu_to_be64(conn->c_next_tx_seq++);
-		list_add_tail(&rm->m_conn_item, &conn->c_send_queue);
+		spin_lock(&cp->cp_lock);
+		rm->m_inc.i_hdr.h_sequence = cpu_to_be64(cp->cp_next_tx_seq++);
+		list_add_tail(&rm->m_conn_item, &cp->cp_send_queue);
 		set_bit(RDS_MSG_ON_CONN, &rm->m_flags);
-		spin_unlock(&conn->c_lock);
+		spin_unlock(&cp->cp_lock);
 
 		rdsdebug("queued msg %p len %d, rs %p bytes %d seq %llu\n",
 			 rm, len, rs, rs->rs_snd_bytes,
@@ -989,6 +976,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 	int queued = 0, allocated_mr = 0;
 	int nonblock = msg->msg_flags & MSG_DONTWAIT;
 	long timeo = sock_sndtimeo(sk, nonblock);
+	struct rds_conn_path *cpath;
 
 	/* Mirror Linux UDP mirror of BSD error message compatibility */
 	/* XXX: Perhaps MSG_MORE someday */
@@ -1087,15 +1075,16 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 		goto out;
 	}
 
-	rds_conn_connect_if_down(conn);
+	cpath = &conn->c_path[0];
+
+	rds_conn_path_connect_if_down(cpath);
 
 	ret = rds_cong_wait(conn->c_fcong, dport, nonblock, rs);
 	if (ret) {
 		rs->rs_seen_congestion = 1;
 		goto out;
 	}
-
-	while (!rds_send_queue_rm(rs, conn, rm, rs->rs_bound_port,
+	while (!rds_send_queue_rm(rs, conn, cpath, rm, rs->rs_bound_port,
 				  dport, &queued)) {
 		rds_stats_inc(s_send_queue_full);
 
@@ -1105,7 +1094,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 		}
 
 		timeo = wait_event_interruptible_timeout(*sk_sleep(sk),
-					rds_send_queue_rm(rs, conn, rm,
+					rds_send_queue_rm(rs, conn, cpath, rm,
 							  rs->rs_bound_port,
 							  dport,
 							  &queued),
@@ -1126,9 +1115,9 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 	 */
 	rds_stats_inc(s_send_queued);
 
-	ret = rds_send_xmit(conn);
+	ret = rds_send_xmit(cpath);
 	if (ret == -ENOMEM || ret == -EAGAIN)
-		queue_delayed_work(rds_wq, &conn->c_send_w, 1);
+		queue_delayed_work(rds_wq, &cpath->cp_send_w, 1);
 
 	rds_message_put(rm);
 	return payload_len;
@@ -1149,7 +1138,7 @@ out:
  * Reply to a ping packet.
  */
 int
-rds_send_pong(struct rds_connection *conn, __be16 dport)
+rds_send_pong(struct rds_conn_path *cp, __be16 dport)
 {
 	struct rds_message *rm;
 	unsigned long flags;
@@ -1161,31 +1150,32 @@ rds_send_pong(struct rds_connection *conn, __be16 dport)
 		goto out;
 	}
 
-	rm->m_daddr = conn->c_faddr;
+	rm->m_daddr = cp->cp_conn->c_faddr;
 	rm->data.op_active = 1;
 
-	rds_conn_connect_if_down(conn);
+	rds_conn_path_connect_if_down(cp);
 
-	ret = rds_cong_wait(conn->c_fcong, dport, 1, NULL);
+	ret = rds_cong_wait(cp->cp_conn->c_fcong, dport, 1, NULL);
 	if (ret)
 		goto out;
 
-	spin_lock_irqsave(&conn->c_lock, flags);
-	list_add_tail(&rm->m_conn_item, &conn->c_send_queue);
+	spin_lock_irqsave(&cp->cp_lock, flags);
+	list_add_tail(&rm->m_conn_item, &cp->cp_send_queue);
 	set_bit(RDS_MSG_ON_CONN, &rm->m_flags);
 	rds_message_addref(rm);
-	rm->m_inc.i_conn = conn;
+	rm->m_inc.i_conn = cp->cp_conn;
+	rm->m_inc.i_conn_path = cp;
 
 	rds_message_populate_header(&rm->m_inc.i_hdr, 0, dport,
-				    conn->c_next_tx_seq);
-	conn->c_next_tx_seq++;
-	spin_unlock_irqrestore(&conn->c_lock, flags);
+				    cp->cp_next_tx_seq);
+	cp->cp_next_tx_seq++;
+	spin_unlock_irqrestore(&cp->cp_lock, flags);
 
 	rds_stats_inc(s_send_queued);
 	rds_stats_inc(s_send_pong);
 
 	/* schedule the send work on rds_wq */
-	queue_delayed_work(rds_wq, &conn->c_send_w, 1);
+	queue_delayed_work(rds_wq, &cp->cp_send_w, 1);
 
 	rds_message_put(rm);
 	return 0;
diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c
index c173f69e1479..e381bbcd9cc1 100644
--- a/net/rds/sysctl.c
+++ b/net/rds/sysctl.c
@@ -102,7 +102,8 @@ int rds_sysctl_init(void)
 	rds_sysctl_reconnect_min = msecs_to_jiffies(1);
 	rds_sysctl_reconnect_min_jiffies = rds_sysctl_reconnect_min;
 
-	rds_sysctl_reg_table = register_net_sysctl(&init_net,"net/rds", rds_sysctl_rds_table);
+	rds_sysctl_reg_table =
+		register_net_sysctl(&init_net, "net/rds", rds_sysctl_rds_table);
 	if (!rds_sysctl_reg_table)
 		return -ENOMEM;
 	return 0;
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 86187dad1440..d278432f080b 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -38,6 +38,7 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "tcp.h"
 
@@ -56,8 +57,8 @@ static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
 				 void __user *buffer, size_t *lenp,
 				 loff_t *fpos);
 
-int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF;
-int rds_tcp_min_rcvbuf = SOCK_MIN_RCVBUF;
+static int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF;
+static int rds_tcp_min_rcvbuf = SOCK_MIN_RCVBUF;
 
 static struct ctl_table rds_tcp_sysctl_table[] = {
 #define	RDS_TCP_SNDBUF	0
@@ -126,13 +127,86 @@ void rds_tcp_restore_callbacks(struct socket *sock,
 }
 
 /*
- * This is the only path that sets tc->t_sock.  Send and receive trust that
- * it is set.  The RDS_CONN_UP bit protects those paths from being
- * called while it isn't set.
+ * rds_tcp_reset_callbacks() switches the to the new sock and
+ * returns the existing tc->t_sock.
+ *
+ * The only functions that set tc->t_sock are rds_tcp_set_callbacks
+ * and rds_tcp_reset_callbacks.  Send and receive trust that
+ * it is set.  The absence of RDS_CONN_UP bit protects those paths
+ * from being called while it isn't set.
+ */
+void rds_tcp_reset_callbacks(struct socket *sock,
+			     struct rds_conn_path *cp)
+{
+	struct rds_tcp_connection *tc = cp->cp_transport_data;
+	struct socket *osock = tc->t_sock;
+
+	if (!osock)
+		goto newsock;
+
+	/* Need to resolve a duelling SYN between peers.
+	 * We have an outstanding SYN to this peer, which may
+	 * potentially have transitioned to the RDS_CONN_UP state,
+	 * so we must quiesce any send threads before resetting
+	 * cp_transport_data. We quiesce these threads by setting
+	 * cp_state to something other than RDS_CONN_UP, and then
+	 * waiting for any existing threads in rds_send_xmit to
+	 * complete release_in_xmit(). (Subsequent threads entering
+	 * rds_send_xmit() will bail on !rds_conn_up().
+	 *
+	 * However an incoming syn-ack at this point would end up
+	 * marking the conn as RDS_CONN_UP, and would again permit
+	 * rds_send_xmi() threads through, so ideally we would
+	 * synchronize on RDS_CONN_UP after lock_sock(), but cannot
+	 * do that: waiting on !RDS_IN_XMIT after lock_sock() may
+	 * end up deadlocking with tcp_sendmsg(), and the RDS_IN_XMIT
+	 * would not get set. As a result, we set c_state to
+	 * RDS_CONN_RESETTTING, to ensure that rds_tcp_state_change
+	 * cannot mark rds_conn_path_up() in the window before lock_sock()
+	 */
+	atomic_set(&cp->cp_state, RDS_CONN_RESETTING);
+	wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags));
+	lock_sock(osock->sk);
+	/* reset receive side state for rds_tcp_data_recv() for osock  */
+	if (tc->t_tinc) {
+		rds_inc_put(&tc->t_tinc->ti_inc);
+		tc->t_tinc = NULL;
+	}
+	tc->t_tinc_hdr_rem = sizeof(struct rds_header);
+	tc->t_tinc_data_rem = 0;
+	tc->t_sock = NULL;
+
+	write_lock_bh(&osock->sk->sk_callback_lock);
+
+	osock->sk->sk_user_data = NULL;
+	osock->sk->sk_data_ready = tc->t_orig_data_ready;
+	osock->sk->sk_write_space = tc->t_orig_write_space;
+	osock->sk->sk_state_change = tc->t_orig_state_change;
+	write_unlock_bh(&osock->sk->sk_callback_lock);
+	release_sock(osock->sk);
+	sock_release(osock);
+newsock:
+	rds_send_path_reset(cp);
+	lock_sock(sock->sk);
+	write_lock_bh(&sock->sk->sk_callback_lock);
+	tc->t_sock = sock;
+	tc->t_cpath = cp;
+	sock->sk->sk_user_data = cp;
+	sock->sk->sk_data_ready = rds_tcp_data_ready;
+	sock->sk->sk_write_space = rds_tcp_write_space;
+	sock->sk->sk_state_change = rds_tcp_state_change;
+
+	write_unlock_bh(&sock->sk->sk_callback_lock);
+	release_sock(sock->sk);
+}
+
+/* Add tc to rds_tcp_tc_list and set tc->t_sock. See comments
+ * above rds_tcp_reset_callbacks for notes about synchronization
+ * with data path
  */
-void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn)
+void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp)
 {
-	struct rds_tcp_connection *tc = conn->c_transport_data;
+	struct rds_tcp_connection *tc = cp->cp_transport_data;
 
 	rdsdebug("setting sock %p callbacks to tc %p\n", sock, tc);
 	write_lock_bh(&sock->sk->sk_callback_lock);
@@ -148,12 +222,12 @@ void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn)
 		sock->sk->sk_data_ready = sock->sk->sk_user_data;
 
 	tc->t_sock = sock;
-	tc->conn = conn;
+	tc->t_cpath = cp;
 	tc->t_orig_data_ready = sock->sk->sk_data_ready;
 	tc->t_orig_write_space = sock->sk->sk_write_space;
 	tc->t_orig_state_change = sock->sk->sk_state_change;
 
-	sock->sk->sk_user_data = conn;
+	sock->sk->sk_user_data = cp;
 	sock->sk->sk_data_ready = rds_tcp_data_ready;
 	sock->sk->sk_write_space = rds_tcp_write_space;
 	sock->sk->sk_state_change = rds_tcp_state_change;
@@ -211,24 +285,29 @@ static int rds_tcp_laddr_check(struct net *net, __be32 addr)
 static int rds_tcp_conn_alloc(struct rds_connection *conn, gfp_t gfp)
 {
 	struct rds_tcp_connection *tc;
+	int i;
 
-	tc = kmem_cache_alloc(rds_tcp_conn_slab, gfp);
-	if (!tc)
-		return -ENOMEM;
+	for (i = 0; i < RDS_MPATH_WORKERS; i++) {
+		tc = kmem_cache_alloc(rds_tcp_conn_slab, gfp);
+		if (!tc)
+			return -ENOMEM;
 
-	mutex_init(&tc->t_conn_lock);
-	tc->t_sock = NULL;
-	tc->t_tinc = NULL;
-	tc->t_tinc_hdr_rem = sizeof(struct rds_header);
-	tc->t_tinc_data_rem = 0;
+		mutex_init(&tc->t_conn_path_lock);
+		tc->t_sock = NULL;
+		tc->t_tinc = NULL;
+		tc->t_tinc_hdr_rem = sizeof(struct rds_header);
+		tc->t_tinc_data_rem = 0;
 
-	conn->c_transport_data = tc;
+		conn->c_path[i].cp_transport_data = tc;
+		tc->t_cpath = &conn->c_path[i];
 
-	spin_lock_irq(&rds_tcp_conn_lock);
-	list_add_tail(&tc->t_tcp_node, &rds_tcp_conn_list);
-	spin_unlock_irq(&rds_tcp_conn_lock);
+		spin_lock_irq(&rds_tcp_conn_lock);
+		list_add_tail(&tc->t_tcp_node, &rds_tcp_conn_list);
+		spin_unlock_irq(&rds_tcp_conn_lock);
+		rdsdebug("rds_conn_path [%d] tc %p\n", i,
+			 conn->c_path[i].cp_transport_data);
+	}
 
-	rdsdebug("alloced tc %p\n", conn->c_transport_data);
 	return 0;
 }
 
@@ -245,6 +324,17 @@ static void rds_tcp_conn_free(void *arg)
 	kmem_cache_free(rds_tcp_conn_slab, tc);
 }
 
+static bool list_has_conn(struct list_head *list, struct rds_connection *conn)
+{
+	struct rds_tcp_connection *tc, *_tc;
+
+	list_for_each_entry_safe(tc, _tc, list, t_tcp_node) {
+		if (tc->t_cpath->cp_conn == conn)
+			return true;
+	}
+	return false;
+}
+
 static void rds_tcp_destroy_conns(void)
 {
 	struct rds_tcp_connection *tc, *_tc;
@@ -252,29 +342,28 @@ static void rds_tcp_destroy_conns(void)
 
 	/* avoid calling conn_destroy with irqs off */
 	spin_lock_irq(&rds_tcp_conn_lock);
-	list_splice(&rds_tcp_conn_list, &tmp_list);
-	INIT_LIST_HEAD(&rds_tcp_conn_list);
+	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
+		if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn))
+			list_move_tail(&tc->t_tcp_node, &tmp_list);
+	}
 	spin_unlock_irq(&rds_tcp_conn_lock);
 
-	list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node) {
-		if (tc->conn->c_passive)
-			rds_conn_destroy(tc->conn->c_passive);
-		rds_conn_destroy(tc->conn);
-	}
+	list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node)
+		rds_conn_destroy(tc->t_cpath->cp_conn);
 }
 
 static void rds_tcp_exit(void);
 
 struct rds_transport rds_tcp_transport = {
 	.laddr_check		= rds_tcp_laddr_check,
-	.xmit_prepare		= rds_tcp_xmit_prepare,
-	.xmit_complete		= rds_tcp_xmit_complete,
+	.xmit_path_prepare	= rds_tcp_xmit_path_prepare,
+	.xmit_path_complete	= rds_tcp_xmit_path_complete,
 	.xmit			= rds_tcp_xmit,
-	.recv			= rds_tcp_recv,
+	.recv_path		= rds_tcp_recv_path,
 	.conn_alloc		= rds_tcp_conn_alloc,
 	.conn_free		= rds_tcp_conn_free,
-	.conn_connect		= rds_tcp_conn_connect,
-	.conn_shutdown		= rds_tcp_conn_shutdown,
+	.conn_path_connect	= rds_tcp_conn_path_connect,
+	.conn_path_shutdown	= rds_tcp_conn_path_shutdown,
 	.inc_copy_to_user	= rds_tcp_inc_copy_to_user,
 	.inc_free		= rds_tcp_inc_free,
 	.stats_info_copy	= rds_tcp_stats_info_copy,
@@ -416,10 +505,30 @@ static struct pernet_operations rds_tcp_net_ops = {
 	.size = sizeof(struct rds_tcp_net),
 };
 
+/* explicitly send a RST on each socket, thereby releasing any socket refcnts
+ * that may otherwise hold up netns deletion.
+ */
+static void rds_tcp_conn_paths_destroy(struct rds_connection *conn)
+{
+	struct rds_conn_path *cp;
+	struct rds_tcp_connection *tc;
+	int i;
+	struct sock *sk;
+
+	for (i = 0; i < RDS_MPATH_WORKERS; i++) {
+		cp = &conn->c_path[i];
+		tc = cp->cp_transport_data;
+		if (!tc->t_sock)
+			continue;
+		sk = tc->t_sock->sk;
+		sk->sk_prot->disconnect(sk, 0);
+		tcp_done(sk);
+	}
+}
+
 static void rds_tcp_kill_sock(struct net *net)
 {
 	struct rds_tcp_connection *tc, *_tc;
-	struct sock *sk;
 	LIST_HEAD(tmp_list);
 	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
 
@@ -428,20 +537,17 @@ static void rds_tcp_kill_sock(struct net *net)
 	flush_work(&rtn->rds_tcp_accept_w);
 	spin_lock_irq(&rds_tcp_conn_lock);
 	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
-		struct net *c_net = read_pnet(&tc->conn->c_net);
+		struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
 
 		if (net != c_net || !tc->t_sock)
 			continue;
-		list_move_tail(&tc->t_tcp_node, &tmp_list);
+		if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn))
+			list_move_tail(&tc->t_tcp_node, &tmp_list);
 	}
 	spin_unlock_irq(&rds_tcp_conn_lock);
 	list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node) {
-		sk = tc->t_sock->sk;
-		sk->sk_prot->disconnect(sk, 0);
-		tcp_done(sk);
-		if (tc->conn->c_passive)
-			rds_conn_destroy(tc->conn->c_passive);
-		rds_conn_destroy(tc->conn);
+		rds_tcp_conn_paths_destroy(tc->t_cpath->cp_conn);
+		rds_conn_destroy(tc->t_cpath->cp_conn);
 	}
 }
 
@@ -479,12 +585,13 @@ static void rds_tcp_sysctl_reset(struct net *net)
 
 	spin_lock_irq(&rds_tcp_conn_lock);
 	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
-		struct net *c_net = read_pnet(&tc->conn->c_net);
+		struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
 
 		if (net != c_net || !tc->t_sock)
 			continue;
 
-		rds_conn_drop(tc->conn); /* reconnect with new parameters */
+		/* reconnect with new parameters */
+		rds_conn_path_drop(tc->t_cpath);
 	}
 	spin_unlock_irq(&rds_tcp_conn_lock);
 }
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 41c228300525..1c3160faa963 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -11,11 +11,11 @@ struct rds_tcp_incoming {
 struct rds_tcp_connection {
 
 	struct list_head	t_tcp_node;
-	struct rds_connection   *conn;
-	/* t_conn_lock synchronizes the connection establishment between
-	 * rds_tcp_accept_one and rds_tcp_conn_connect
+	struct rds_conn_path	*t_cpath;
+	/* t_conn_path_lock synchronizes the connection establishment between
+	 * rds_tcp_accept_one and rds_tcp_conn_path_connect
 	 */
-	struct mutex		t_conn_lock;
+	struct mutex		t_conn_path_lock;
 	struct socket		*t_sock;
 	void			*t_orig_write_space;
 	void			*t_orig_data_ready;
@@ -49,7 +49,8 @@ struct rds_tcp_statistics {
 /* tcp.c */
 void rds_tcp_tune(struct socket *sock);
 void rds_tcp_nonagle(struct socket *sock);
-void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn);
+void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp);
+void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp);
 void rds_tcp_restore_callbacks(struct socket *sock,
 			       struct rds_tcp_connection *tc);
 u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc);
@@ -59,8 +60,8 @@ extern struct rds_transport rds_tcp_transport;
 void rds_tcp_accept_work(struct sock *sk);
 
 /* tcp_connect.c */
-int rds_tcp_conn_connect(struct rds_connection *conn);
-void rds_tcp_conn_shutdown(struct rds_connection *conn);
+int rds_tcp_conn_path_connect(struct rds_conn_path *cp);
+void rds_tcp_conn_path_shutdown(struct rds_conn_path *conn);
 void rds_tcp_state_change(struct sock *sk);
 
 /* tcp_listen.c */
@@ -74,15 +75,15 @@ int rds_tcp_keepalive(struct socket *sock);
 int rds_tcp_recv_init(void);
 void rds_tcp_recv_exit(void);
 void rds_tcp_data_ready(struct sock *sk);
-int rds_tcp_recv(struct rds_connection *conn);
+int rds_tcp_recv_path(struct rds_conn_path *cp);
 void rds_tcp_inc_free(struct rds_incoming *inc);
 int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to);
 
 /* tcp_send.c */
-void rds_tcp_xmit_prepare(struct rds_connection *conn);
-void rds_tcp_xmit_complete(struct rds_connection *conn);
+void rds_tcp_xmit_path_prepare(struct rds_conn_path *cp);
+void rds_tcp_xmit_path_complete(struct rds_conn_path *cp);
 int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
-	         unsigned int hdr_off, unsigned int sg, unsigned int off);
+		 unsigned int hdr_off, unsigned int sg, unsigned int off);
 void rds_tcp_write_space(struct sock *sk);
 
 /* tcp_stats.c */
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index fb82e0a0bf89..c916715fbe61 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -34,56 +34,58 @@
 #include <linux/in.h>
 #include <net/tcp.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "tcp.h"
 
 void rds_tcp_state_change(struct sock *sk)
 {
 	void (*state_change)(struct sock *sk);
-	struct rds_connection *conn;
+	struct rds_conn_path *cp;
 	struct rds_tcp_connection *tc;
 
 	read_lock_bh(&sk->sk_callback_lock);
-	conn = sk->sk_user_data;
-	if (!conn) {
+	cp = sk->sk_user_data;
+	if (!cp) {
 		state_change = sk->sk_state_change;
 		goto out;
 	}
-	tc = conn->c_transport_data;
+	tc = cp->cp_transport_data;
 	state_change = tc->t_orig_state_change;
 
 	rdsdebug("sock %p state_change to %d\n", tc->t_sock, sk->sk_state);
 
-	switch(sk->sk_state) {
-		/* ignore connecting sockets as they make progress */
-		case TCP_SYN_SENT:
-		case TCP_SYN_RECV:
-			break;
-		case TCP_ESTABLISHED:
-			rds_connect_complete(conn);
-			break;
-		case TCP_CLOSE_WAIT:
-		case TCP_CLOSE:
-			rds_conn_drop(conn);
-		default:
-			break;
+	switch (sk->sk_state) {
+	/* ignore connecting sockets as they make progress */
+	case TCP_SYN_SENT:
+	case TCP_SYN_RECV:
+		break;
+	case TCP_ESTABLISHED:
+		rds_connect_path_complete(cp, RDS_CONN_CONNECTING);
+		break;
+	case TCP_CLOSE_WAIT:
+	case TCP_CLOSE:
+		rds_conn_path_drop(cp);
+	default:
+		break;
 	}
 out:
 	read_unlock_bh(&sk->sk_callback_lock);
 	state_change(sk);
 }
 
-int rds_tcp_conn_connect(struct rds_connection *conn)
+int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
 {
 	struct socket *sock = NULL;
 	struct sockaddr_in src, dest;
 	int ret;
-	struct rds_tcp_connection *tc = conn->c_transport_data;
+	struct rds_connection *conn = cp->cp_conn;
+	struct rds_tcp_connection *tc = cp->cp_transport_data;
 
-	mutex_lock(&tc->t_conn_lock);
+	mutex_lock(&tc->t_conn_path_lock);
 
-	if (rds_conn_up(conn)) {
-		mutex_unlock(&tc->t_conn_lock);
+	if (rds_conn_path_up(cp)) {
+		mutex_unlock(&tc->t_conn_path_lock);
 		return 0;
 	}
 	ret = sock_create_kern(rds_conn_net(conn), PF_INET,
@@ -112,10 +114,11 @@ int rds_tcp_conn_connect(struct rds_connection *conn)
 	 * once we call connect() we can start getting callbacks and they
 	 * own the socket
 	 */
-	rds_tcp_set_callbacks(sock, conn);
+	rds_tcp_set_callbacks(sock, cp);
 	ret = sock->ops->connect(sock, (struct sockaddr *)&dest, sizeof(dest),
 				 O_NONBLOCK);
 
+	cp->cp_outgoing = 1;
 	rdsdebug("connect to address %pI4 returned %d\n", &conn->c_faddr, ret);
 	if (ret == -EINPROGRESS)
 		ret = 0;
@@ -123,11 +126,11 @@ int rds_tcp_conn_connect(struct rds_connection *conn)
 		rds_tcp_keepalive(sock);
 		sock = NULL;
 	} else {
-		rds_tcp_restore_callbacks(sock, conn->c_transport_data);
+		rds_tcp_restore_callbacks(sock, cp->cp_transport_data);
 	}
 
 out:
-	mutex_unlock(&tc->t_conn_lock);
+	mutex_unlock(&tc->t_conn_path_lock);
 	if (sock)
 		sock_release(sock);
 	return ret;
@@ -142,12 +145,13 @@ out:
  * callbacks to those set by TCP.  Our callbacks won't execute again once we
  * hold the sock lock.
  */
-void rds_tcp_conn_shutdown(struct rds_connection *conn)
+void rds_tcp_conn_path_shutdown(struct rds_conn_path *cp)
 {
-	struct rds_tcp_connection *tc = conn->c_transport_data;
+	struct rds_tcp_connection *tc = cp->cp_transport_data;
 	struct socket *sock = tc->t_sock;
 
-	rdsdebug("shutting down conn %p tc %p sock %p\n", conn, tc, sock);
+	rdsdebug("shutting down conn %p tc %p sock %p\n",
+		 cp->cp_conn, tc, sock);
 
 	if (sock) {
 		sock->ops->shutdown(sock, RCV_SHUTDOWN | SEND_SHUTDOWN);
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 4bf4befe5066..ca975a217a49 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -35,6 +35,7 @@
 #include <linux/in.h>
 #include <net/tcp.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "tcp.h"
 
@@ -78,7 +79,7 @@ int rds_tcp_accept_one(struct socket *sock)
 	struct inet_sock *inet;
 	struct rds_tcp_connection *rs_tcp = NULL;
 	int conn_state;
-	struct sock *nsk;
+	struct rds_conn_path *cp;
 
 	if (!sock) /* module unload or netns delete in progress */
 		return -ENETUNREACH;
@@ -120,8 +121,9 @@ int rds_tcp_accept_one(struct socket *sock)
 	 * rds_tcp_state_change() will do that cleanup
 	 */
 	rs_tcp = (struct rds_tcp_connection *)conn->c_transport_data;
+	cp = &conn->c_path[0];
 	rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING);
-	mutex_lock(&rs_tcp->t_conn_lock);
+	mutex_lock(&rs_tcp->t_conn_path_lock);
 	conn_state = rds_conn_state(conn);
 	if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_UP)
 		goto rst_nsk;
@@ -133,33 +135,28 @@ int rds_tcp_accept_one(struct socket *sock)
 		 * c_transport_data.
 		 */
 		if (ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr) ||
-		    !conn->c_outgoing) {
+		    !conn->c_path[0].cp_outgoing) {
 			goto rst_nsk;
 		} else {
-			atomic_set(&conn->c_state, RDS_CONN_CONNECTING);
-			wait_event(conn->c_waitq,
-				   !test_bit(RDS_IN_XMIT, &conn->c_flags));
-			rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp);
-			conn->c_outgoing = 0;
+			rds_tcp_reset_callbacks(new_sock, cp);
+			conn->c_path[0].cp_outgoing = 0;
+			/* rds_connect_path_complete() marks RDS_CONN_UP */
+			rds_connect_path_complete(cp, RDS_CONN_RESETTING);
 		}
+	} else {
+		rds_tcp_set_callbacks(new_sock, cp);
+		rds_connect_path_complete(cp, RDS_CONN_CONNECTING);
 	}
-	rds_tcp_set_callbacks(new_sock, conn);
-	rds_connect_complete(conn); /* marks RDS_CONN_UP */
 	new_sock = NULL;
 	ret = 0;
 	goto out;
 rst_nsk:
 	/* reset the newly returned accept sock and bail */
-	nsk = new_sock->sk;
-	rds_tcp_stats_inc(s_tcp_listen_closed_stale);
-	nsk->sk_user_data = NULL;
-	nsk->sk_prot->disconnect(nsk, 0);
-	tcp_done(nsk);
-	new_sock = NULL;
+	kernel_sock_shutdown(new_sock, SHUT_RDWR);
 	ret = 0;
 out:
 	if (rs_tcp)
-		mutex_unlock(&rs_tcp->t_conn_lock);
+		mutex_unlock(&rs_tcp->t_conn_path_lock);
 	if (new_sock)
 		sock_release(new_sock);
 	return ret;
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index c3196f9d070a..ad4892e97f91 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -147,7 +147,7 @@ static void rds_tcp_cong_recv(struct rds_connection *conn,
 }
 
 struct rds_tcp_desc_arg {
-	struct rds_connection *conn;
+	struct rds_conn_path *conn_path;
 	gfp_t gfp;
 };
 
@@ -155,8 +155,8 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 			     unsigned int offset, size_t len)
 {
 	struct rds_tcp_desc_arg *arg = desc->arg.data;
-	struct rds_connection *conn = arg->conn;
-	struct rds_tcp_connection *tc = conn->c_transport_data;
+	struct rds_conn_path *cp = arg->conn_path;
+	struct rds_tcp_connection *tc = cp->cp_transport_data;
 	struct rds_tcp_incoming *tinc = tc->t_tinc;
 	struct sk_buff *clone;
 	size_t left = len, to_copy;
@@ -171,14 +171,15 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 	while (left) {
 		if (!tinc) {
 			tinc = kmem_cache_alloc(rds_tcp_incoming_slab,
-					        arg->gfp);
+						arg->gfp);
 			if (!tinc) {
 				desc->error = -ENOMEM;
 				goto out;
 			}
 			tc->t_tinc = tinc;
 			rdsdebug("alloced tinc %p\n", tinc);
-			rds_inc_init(&tinc->ti_inc, conn, conn->c_faddr);
+			rds_inc_path_init(&tinc->ti_inc, cp,
+					  cp->cp_conn->c_faddr);
 			/*
 			 * XXX * we might be able to use the __ variants when
 			 * we've already serialized at a higher level.
@@ -228,6 +229,8 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 		}
 
 		if (tc->t_tinc_hdr_rem == 0 && tc->t_tinc_data_rem == 0) {
+			struct rds_connection *conn = cp->cp_conn;
+
 			if (tinc->ti_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP)
 				rds_tcp_cong_recv(conn, tinc);
 			else
@@ -250,15 +253,15 @@ out:
 }
 
 /* the caller has to hold the sock lock */
-static int rds_tcp_read_sock(struct rds_connection *conn, gfp_t gfp)
+static int rds_tcp_read_sock(struct rds_conn_path *cp, gfp_t gfp)
 {
-	struct rds_tcp_connection *tc = conn->c_transport_data;
+	struct rds_tcp_connection *tc = cp->cp_transport_data;
 	struct socket *sock = tc->t_sock;
 	read_descriptor_t desc;
 	struct rds_tcp_desc_arg arg;
 
 	/* It's like glib in the kernel! */
-	arg.conn = conn;
+	arg.conn_path = cp;
 	arg.gfp = gfp;
 	desc.arg.data = &arg;
 	desc.error = 0;
@@ -278,16 +281,17 @@ static int rds_tcp_read_sock(struct rds_connection *conn, gfp_t gfp)
  * if we fail to allocate we're in trouble.. blindly wait some time before
  * trying again to see if the VM can free up something for us.
  */
-int rds_tcp_recv(struct rds_connection *conn)
+int rds_tcp_recv_path(struct rds_conn_path *cp)
 {
-	struct rds_tcp_connection *tc = conn->c_transport_data;
+	struct rds_tcp_connection *tc = cp->cp_transport_data;
 	struct socket *sock = tc->t_sock;
 	int ret = 0;
 
-	rdsdebug("recv worker conn %p tc %p sock %p\n", conn, tc, sock);
+	rdsdebug("recv worker path [%d] tc %p sock %p\n",
+		 cp->cp_index, tc, sock);
 
 	lock_sock(sock->sk);
-	ret = rds_tcp_read_sock(conn, GFP_KERNEL);
+	ret = rds_tcp_read_sock(cp, GFP_KERNEL);
 	release_sock(sock->sk);
 
 	return ret;
@@ -296,24 +300,24 @@ int rds_tcp_recv(struct rds_connection *conn)
 void rds_tcp_data_ready(struct sock *sk)
 {
 	void (*ready)(struct sock *sk);
-	struct rds_connection *conn;
+	struct rds_conn_path *cp;
 	struct rds_tcp_connection *tc;
 
 	rdsdebug("data ready sk %p\n", sk);
 
 	read_lock_bh(&sk->sk_callback_lock);
-	conn = sk->sk_user_data;
-	if (!conn) { /* check for teardown race */
+	cp = sk->sk_user_data;
+	if (!cp) { /* check for teardown race */
 		ready = sk->sk_data_ready;
 		goto out;
 	}
 
-	tc = conn->c_transport_data;
+	tc = cp->cp_transport_data;
 	ready = tc->t_orig_data_ready;
 	rds_tcp_stats_inc(s_tcp_data_ready_calls);
 
-	if (rds_tcp_read_sock(conn, GFP_ATOMIC) == -ENOMEM)
-		queue_delayed_work(rds_wq, &conn->c_recv_w, 0);
+	if (rds_tcp_read_sock(cp, GFP_ATOMIC) == -ENOMEM)
+		queue_delayed_work(rds_wq, &cp->cp_recv_w, 0);
 out:
 	read_unlock_bh(&sk->sk_callback_lock);
 	ready(sk);
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 22d0f2020a79..57e0f5826406 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -34,6 +34,7 @@
 #include <linux/in.h>
 #include <net/tcp.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "tcp.h"
 
@@ -48,16 +49,16 @@ static void rds_tcp_cork(struct socket *sock, int val)
 	set_fs(oldfs);
 }
 
-void rds_tcp_xmit_prepare(struct rds_connection *conn)
+void rds_tcp_xmit_path_prepare(struct rds_conn_path *cp)
 {
-	struct rds_tcp_connection *tc = conn->c_transport_data;
+	struct rds_tcp_connection *tc = cp->cp_transport_data;
 
 	rds_tcp_cork(tc->t_sock, 1);
 }
 
-void rds_tcp_xmit_complete(struct rds_connection *conn)
+void rds_tcp_xmit_path_complete(struct rds_conn_path *cp)
 {
-	struct rds_tcp_connection *tc = conn->c_transport_data;
+	struct rds_tcp_connection *tc = cp->cp_transport_data;
 
 	rds_tcp_cork(tc->t_sock, 0);
 }
@@ -66,19 +67,19 @@ void rds_tcp_xmit_complete(struct rds_connection *conn)
 static int rds_tcp_sendmsg(struct socket *sock, void *data, unsigned int len)
 {
 	struct kvec vec = {
-                .iov_base = data,
-                .iov_len = len,
+		.iov_base = data,
+		.iov_len = len,
+	};
+	struct msghdr msg = {
+		.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL,
 	};
-        struct msghdr msg = {
-                .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL,
-        };
 
 	return kernel_sendmsg(sock, &msg, &vec, 1, vec.iov_len);
 }
 
 /* the core send_sem serializes this with other xmit and shutdown */
 int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
-	         unsigned int hdr_off, unsigned int sg, unsigned int off)
+		 unsigned int hdr_off, unsigned int sg, unsigned int off)
 {
 	struct rds_tcp_connection *tc = conn->c_transport_data;
 	int done = 0;
@@ -177,27 +178,27 @@ static int rds_tcp_is_acked(struct rds_message *rm, uint64_t ack)
 void rds_tcp_write_space(struct sock *sk)
 {
 	void (*write_space)(struct sock *sk);
-	struct rds_connection *conn;
+	struct rds_conn_path *cp;
 	struct rds_tcp_connection *tc;
 
 	read_lock_bh(&sk->sk_callback_lock);
-	conn = sk->sk_user_data;
-	if (!conn) {
+	cp = sk->sk_user_data;
+	if (!cp) {
 		write_space = sk->sk_write_space;
 		goto out;
 	}
 
-	tc = conn->c_transport_data;
+	tc = cp->cp_transport_data;
 	rdsdebug("write_space for tc %p\n", tc);
 	write_space = tc->t_orig_write_space;
 	rds_tcp_stats_inc(s_tcp_write_space_calls);
 
 	rdsdebug("tcp una %u\n", rds_tcp_snd_una(tc));
 	tc->t_last_seen_una = rds_tcp_snd_una(tc);
-	rds_send_drop_acked(conn, rds_tcp_snd_una(tc), rds_tcp_is_acked);
+	rds_send_path_drop_acked(cp, rds_tcp_snd_una(tc), rds_tcp_is_acked);
 
-        if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf)
-		queue_delayed_work(rds_wq, &conn->c_send_w, 0);
+	if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf)
+		queue_delayed_work(rds_wq, &cp->cp_send_w, 0);
 
 out:
 	read_unlock_bh(&sk->sk_callback_lock);
diff --git a/net/rds/threads.c b/net/rds/threads.c
index 454aa6d23327..bc97d67f29cc 100644
--- a/net/rds/threads.c
+++ b/net/rds/threads.c
@@ -71,24 +71,30 @@
 struct workqueue_struct *rds_wq;
 EXPORT_SYMBOL_GPL(rds_wq);
 
-void rds_connect_complete(struct rds_connection *conn)
+void rds_connect_path_complete(struct rds_conn_path *cp, int curr)
 {
-	if (!rds_conn_transition(conn, RDS_CONN_CONNECTING, RDS_CONN_UP)) {
+	if (!rds_conn_path_transition(cp, curr, RDS_CONN_UP)) {
 		printk(KERN_WARNING "%s: Cannot transition to state UP, "
 				"current state is %d\n",
 				__func__,
-				atomic_read(&conn->c_state));
-		rds_conn_drop(conn);
+				atomic_read(&cp->cp_state));
+		rds_conn_path_drop(cp);
 		return;
 	}
 
 	rdsdebug("conn %p for %pI4 to %pI4 complete\n",
-	  conn, &conn->c_laddr, &conn->c_faddr);
+	  cp->cp_conn, &cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr);
 
-	conn->c_reconnect_jiffies = 0;
-	set_bit(0, &conn->c_map_queued);
-	queue_delayed_work(rds_wq, &conn->c_send_w, 0);
-	queue_delayed_work(rds_wq, &conn->c_recv_w, 0);
+	cp->cp_reconnect_jiffies = 0;
+	set_bit(0, &cp->cp_conn->c_map_queued);
+	queue_delayed_work(rds_wq, &cp->cp_send_w, 0);
+	queue_delayed_work(rds_wq, &cp->cp_recv_w, 0);
+}
+EXPORT_SYMBOL_GPL(rds_connect_path_complete);
+
+void rds_connect_complete(struct rds_connection *conn)
+{
+	rds_connect_path_complete(&conn->c_path[0], RDS_CONN_CONNECTING);
 }
 EXPORT_SYMBOL_GPL(rds_connect_complete);
 
@@ -110,70 +116,85 @@ EXPORT_SYMBOL_GPL(rds_connect_complete);
  * We should *always* start with a random backoff; otherwise a broken connection
  * will always take several iterations to be re-established.
  */
-void rds_queue_reconnect(struct rds_connection *conn)
+void rds_queue_reconnect(struct rds_conn_path *cp)
 {
 	unsigned long rand;
+	struct rds_connection *conn = cp->cp_conn;
 
 	rdsdebug("conn %p for %pI4 to %pI4 reconnect jiffies %lu\n",
 	  conn, &conn->c_laddr, &conn->c_faddr,
-	  conn->c_reconnect_jiffies);
+	  cp->cp_reconnect_jiffies);
+
+	/* let peer with smaller addr initiate reconnect, to avoid duels */
+	if (conn->c_trans->t_type == RDS_TRANS_TCP &&
+	    conn->c_laddr > conn->c_faddr)
+		return;
 
-	set_bit(RDS_RECONNECT_PENDING, &conn->c_flags);
-	if (conn->c_reconnect_jiffies == 0) {
-		conn->c_reconnect_jiffies = rds_sysctl_reconnect_min_jiffies;
-		queue_delayed_work(rds_wq, &conn->c_conn_w, 0);
+	set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags);
+	if (cp->cp_reconnect_jiffies == 0) {
+		cp->cp_reconnect_jiffies = rds_sysctl_reconnect_min_jiffies;
+		queue_delayed_work(rds_wq, &cp->cp_conn_w, 0);
 		return;
 	}
 
 	get_random_bytes(&rand, sizeof(rand));
 	rdsdebug("%lu delay %lu ceil conn %p for %pI4 -> %pI4\n",
-		 rand % conn->c_reconnect_jiffies, conn->c_reconnect_jiffies,
+		 rand % cp->cp_reconnect_jiffies, cp->cp_reconnect_jiffies,
 		 conn, &conn->c_laddr, &conn->c_faddr);
-	queue_delayed_work(rds_wq, &conn->c_conn_w,
-			   rand % conn->c_reconnect_jiffies);
+	queue_delayed_work(rds_wq, &cp->cp_conn_w,
+			   rand % cp->cp_reconnect_jiffies);
 
-	conn->c_reconnect_jiffies = min(conn->c_reconnect_jiffies * 2,
+	cp->cp_reconnect_jiffies = min(cp->cp_reconnect_jiffies * 2,
 					rds_sysctl_reconnect_max_jiffies);
 }
 
 void rds_connect_worker(struct work_struct *work)
 {
-	struct rds_connection *conn = container_of(work, struct rds_connection, c_conn_w.work);
+	struct rds_conn_path *cp = container_of(work,
+						struct rds_conn_path,
+						cp_conn_w.work);
+	struct rds_connection *conn = cp->cp_conn;
 	int ret;
 
-	clear_bit(RDS_RECONNECT_PENDING, &conn->c_flags);
-	if (rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING)) {
-		ret = conn->c_trans->conn_connect(conn);
+	clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags);
+	ret = rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING);
+	if (ret) {
+		ret = conn->c_trans->conn_path_connect(cp);
 		rdsdebug("conn %p for %pI4 to %pI4 dispatched, ret %d\n",
 			conn, &conn->c_laddr, &conn->c_faddr, ret);
 
 		if (ret) {
-			if (rds_conn_transition(conn, RDS_CONN_CONNECTING, RDS_CONN_DOWN))
-				rds_queue_reconnect(conn);
+			if (rds_conn_path_transition(cp,
+						     RDS_CONN_CONNECTING,
+						     RDS_CONN_DOWN))
+				rds_queue_reconnect(cp);
 			else
-				rds_conn_error(conn, "RDS: connect failed\n");
+				rds_conn_path_error(cp,
+						    "RDS: connect failed\n");
 		}
 	}
 }
 
 void rds_send_worker(struct work_struct *work)
 {
-	struct rds_connection *conn = container_of(work, struct rds_connection, c_send_w.work);
+	struct rds_conn_path *cp = container_of(work,
+						struct rds_conn_path,
+						cp_send_w.work);
 	int ret;
 
-	if (rds_conn_state(conn) == RDS_CONN_UP) {
-		clear_bit(RDS_LL_SEND_FULL, &conn->c_flags);
-		ret = rds_send_xmit(conn);
+	if (rds_conn_path_state(cp) == RDS_CONN_UP) {
+		clear_bit(RDS_LL_SEND_FULL, &cp->cp_flags);
+		ret = rds_send_xmit(cp);
 		cond_resched();
-		rdsdebug("conn %p ret %d\n", conn, ret);
+		rdsdebug("conn %p ret %d\n", cp->cp_conn, ret);
 		switch (ret) {
 		case -EAGAIN:
 			rds_stats_inc(s_send_immediate_retry);
-			queue_delayed_work(rds_wq, &conn->c_send_w, 0);
+			queue_delayed_work(rds_wq, &cp->cp_send_w, 0);
 			break;
 		case -ENOMEM:
 			rds_stats_inc(s_send_delayed_retry);
-			queue_delayed_work(rds_wq, &conn->c_send_w, 2);
+			queue_delayed_work(rds_wq, &cp->cp_send_w, 2);
 		default:
 			break;
 		}
@@ -182,20 +203,22 @@ void rds_send_worker(struct work_struct *work)
 
 void rds_recv_worker(struct work_struct *work)
 {
-	struct rds_connection *conn = container_of(work, struct rds_connection, c_recv_w.work);
+	struct rds_conn_path *cp = container_of(work,
+						struct rds_conn_path,
+						cp_recv_w.work);
 	int ret;
 
-	if (rds_conn_state(conn) == RDS_CONN_UP) {
-		ret = conn->c_trans->recv(conn);
-		rdsdebug("conn %p ret %d\n", conn, ret);
+	if (rds_conn_path_state(cp) == RDS_CONN_UP) {
+		ret = cp->cp_conn->c_trans->recv_path(cp);
+		rdsdebug("conn %p ret %d\n", cp->cp_conn, ret);
 		switch (ret) {
 		case -EAGAIN:
 			rds_stats_inc(s_recv_immediate_retry);
-			queue_delayed_work(rds_wq, &conn->c_recv_w, 0);
+			queue_delayed_work(rds_wq, &cp->cp_recv_w, 0);
 			break;
 		case -ENOMEM:
 			rds_stats_inc(s_recv_delayed_retry);
-			queue_delayed_work(rds_wq, &conn->c_recv_w, 2);
+			queue_delayed_work(rds_wq, &cp->cp_recv_w, 2);
 		default:
 			break;
 		}
@@ -204,9 +227,11 @@ void rds_recv_worker(struct work_struct *work)
 
 void rds_shutdown_worker(struct work_struct *work)
 {
-	struct rds_connection *conn = container_of(work, struct rds_connection, c_down_w);
+	struct rds_conn_path *cp = container_of(work,
+						struct rds_conn_path,
+						cp_down_w);
 
-	rds_conn_shutdown(conn);
+	rds_conn_shutdown(cp);
 }
 
 void rds_threads_exit(void)
diff --git a/net/rds/transport.c b/net/rds/transport.c
index f3afd1d60d3c..2ffd3e30c643 100644
--- a/net/rds/transport.c
+++ b/net/rds/transport.c
@@ -140,8 +140,7 @@ unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter,
 	rds_info_iter_unmap(iter);
 	down_read(&rds_trans_sem);
 
-	for (i = 0; i < RDS_TRANS_COUNT; i++)
-	{
+	for (i = 0; i < RDS_TRANS_COUNT; i++) {
 		trans = transports[i];
 		if (!trans || !trans->stats_info_copy)
 			continue;
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile
index e05a06ef2254..6522e50fb750 100644
--- a/net/rxrpc/Makefile
+++ b/net/rxrpc/Makefile
@@ -4,25 +4,27 @@
 
 af-rxrpc-y := \
 	af_rxrpc.o \
-	ar-accept.o \
-	ar-ack.o \
-	ar-call.o \
-	ar-connection.o \
-	ar-connevent.o \
-	ar-error.o \
-	ar-input.o \
-	ar-key.o \
-	ar-local.o \
-	ar-output.o \
-	ar-peer.o \
-	ar-recvmsg.o \
-	ar-security.o \
-	ar-skbuff.o \
-	ar-transport.o \
+	call_accept.o \
+	call_event.o \
+	call_object.o \
+	conn_client.o \
+	conn_event.o \
+	conn_object.o \
+	input.o \
 	insecure.o \
-	misc.o
+	key.o \
+	local_event.o \
+	local_object.o \
+	misc.o \
+	output.o \
+	peer_event.o \
+	peer_object.o \
+	recvmsg.o \
+	security.o \
+	skbuff.o \
+	utils.o
 
-af-rxrpc-$(CONFIG_PROC_FS) += ar-proc.o
+af-rxrpc-$(CONFIG_PROC_FS) += proc.o
 af-rxrpc-$(CONFIG_RXKAD) += rxkad.o
 af-rxrpc-$(CONFIG_SYSCTL) += sysctl.o
 
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 7840b8e7da80..5d3e795a7c48 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -33,8 +33,6 @@ unsigned int rxrpc_debug; // = RXRPC_DEBUG_KPROTO;
 module_param_named(debug, rxrpc_debug, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(debug, "RxRPC debugging mask");
 
-static int sysctl_rxrpc_max_qlen __read_mostly = 10;
-
 static struct proto rxrpc_proto;
 static const struct proto_ops rxrpc_rpc_ops;
 
@@ -99,11 +97,13 @@ static int rxrpc_validate_address(struct rxrpc_sock *rx,
 	    srx->transport_len > len)
 		return -EINVAL;
 
-	if (srx->transport.family != rx->proto)
+	if (srx->transport.family != rx->family)
 		return -EAFNOSUPPORT;
 
 	switch (srx->transport.family) {
 	case AF_INET:
+		if (srx->transport_len < sizeof(struct sockaddr_in))
+			return -EINVAL;
 		_debug("INET: %x @ %pI4",
 		       ntohs(srx->transport.sin.sin_port),
 		       &srx->transport.sin.sin_addr);
@@ -139,33 +139,33 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 
 	lock_sock(&rx->sk);
 
-	if (rx->sk.sk_state != RXRPC_UNCONNECTED) {
+	if (rx->sk.sk_state != RXRPC_UNBOUND) {
 		ret = -EINVAL;
 		goto error_unlock;
 	}
 
 	memcpy(&rx->srx, srx, sizeof(rx->srx));
 
-	/* Find or create a local transport endpoint to use */
 	local = rxrpc_lookup_local(&rx->srx);
 	if (IS_ERR(local)) {
 		ret = PTR_ERR(local);
 		goto error_unlock;
 	}
 
-	rx->local = local;
-	if (srx->srx_service) {
+	if (rx->srx.srx_service) {
 		write_lock_bh(&local->services_lock);
 		list_for_each_entry(prx, &local->services, listen_link) {
-			if (prx->srx.srx_service == srx->srx_service)
+			if (prx->srx.srx_service == rx->srx.srx_service)
 				goto service_in_use;
 		}
 
+		rx->local = local;
 		list_add_tail(&rx->listen_link, &local->services);
 		write_unlock_bh(&local->services_lock);
 
 		rx->sk.sk_state = RXRPC_SERVER_BOUND;
 	} else {
+		rx->local = local;
 		rx->sk.sk_state = RXRPC_CLIENT_BOUND;
 	}
 
@@ -174,8 +174,9 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 	return 0;
 
 service_in_use:
-	ret = -EADDRINUSE;
 	write_unlock_bh(&local->services_lock);
+	rxrpc_put_local(local);
+	ret = -EADDRINUSE;
 error_unlock:
 	release_sock(&rx->sk);
 error:
@@ -190,6 +191,7 @@ static int rxrpc_listen(struct socket *sock, int backlog)
 {
 	struct sock *sk = sock->sk;
 	struct rxrpc_sock *rx = rxrpc_sk(sk);
+	unsigned int max;
 	int ret;
 
 	_enter("%p,%d", rx, backlog);
@@ -197,20 +199,24 @@ static int rxrpc_listen(struct socket *sock, int backlog)
 	lock_sock(&rx->sk);
 
 	switch (rx->sk.sk_state) {
-	case RXRPC_UNCONNECTED:
+	case RXRPC_UNBOUND:
 		ret = -EADDRNOTAVAIL;
 		break;
-	case RXRPC_CLIENT_BOUND:
-	case RXRPC_CLIENT_CONNECTED:
-	default:
-		ret = -EBUSY;
-		break;
 	case RXRPC_SERVER_BOUND:
 		ASSERT(rx->local != NULL);
+		max = READ_ONCE(rxrpc_max_backlog);
+		ret = -EINVAL;
+		if (backlog == INT_MAX)
+			backlog = max;
+		else if (backlog < 0 || backlog > max)
+			break;
 		sk->sk_max_ack_backlog = backlog;
 		rx->sk.sk_state = RXRPC_SERVER_LISTENING;
 		ret = 0;
 		break;
+	default:
+		ret = -EBUSY;
+		break;
 	}
 
 	release_sock(&rx->sk);
@@ -218,45 +224,10 @@ static int rxrpc_listen(struct socket *sock, int backlog)
 	return ret;
 }
 
-/*
- * find a transport by address
- */
-static struct rxrpc_transport *rxrpc_name_to_transport(struct socket *sock,
-						       struct sockaddr *addr,
-						       int addr_len, int flags,
-						       gfp_t gfp)
-{
-	struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) addr;
-	struct rxrpc_transport *trans;
-	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
-	struct rxrpc_peer *peer;
-
-	_enter("%p,%p,%d,%d", rx, addr, addr_len, flags);
-
-	ASSERT(rx->local != NULL);
-	ASSERT(rx->sk.sk_state > RXRPC_UNCONNECTED);
-
-	if (rx->srx.transport_type != srx->transport_type)
-		return ERR_PTR(-ESOCKTNOSUPPORT);
-	if (rx->srx.transport.family != srx->transport.family)
-		return ERR_PTR(-EAFNOSUPPORT);
-
-	/* find a remote transport endpoint from the local one */
-	peer = rxrpc_get_peer(srx, gfp);
-	if (IS_ERR(peer))
-		return ERR_CAST(peer);
-
-	/* find a transport */
-	trans = rxrpc_get_transport(rx->local, peer, gfp);
-	rxrpc_put_peer(peer);
-	_leave(" = %p", trans);
-	return trans;
-}
-
 /**
  * rxrpc_kernel_begin_call - Allow a kernel service to begin a call
  * @sock: The socket on which to make the call
- * @srx: The address of the peer to contact (defaults to socket setting)
+ * @srx: The address of the peer to contact
  * @key: The security context to use (defaults to socket setting)
  * @user_call_ID: The ID to use
  *
@@ -273,51 +244,32 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 					   unsigned long user_call_ID,
 					   gfp_t gfp)
 {
-	struct rxrpc_conn_bundle *bundle;
-	struct rxrpc_transport *trans;
+	struct rxrpc_conn_parameters cp;
 	struct rxrpc_call *call;
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+	int ret;
 
 	_enter(",,%x,%lx", key_serial(key), user_call_ID);
 
-	lock_sock(&rx->sk);
+	ret = rxrpc_validate_address(rx, srx, sizeof(*srx));
+	if (ret < 0)
+		return ERR_PTR(ret);
 
-	if (srx) {
-		trans = rxrpc_name_to_transport(sock, (struct sockaddr *) srx,
-						sizeof(*srx), 0, gfp);
-		if (IS_ERR(trans)) {
-			call = ERR_CAST(trans);
-			trans = NULL;
-			goto out_notrans;
-		}
-	} else {
-		trans = rx->trans;
-		if (!trans) {
-			call = ERR_PTR(-ENOTCONN);
-			goto out_notrans;
-		}
-		atomic_inc(&trans->usage);
-	}
+	lock_sock(&rx->sk);
 
-	if (!srx)
-		srx = &rx->srx;
 	if (!key)
 		key = rx->key;
 	if (key && !key->payload.data[0])
 		key = NULL; /* a no-security key */
 
-	bundle = rxrpc_get_bundle(rx, trans, key, srx->srx_service, gfp);
-	if (IS_ERR(bundle)) {
-		call = ERR_CAST(bundle);
-		goto out;
-	}
+	memset(&cp, 0, sizeof(cp));
+	cp.local		= rx->local;
+	cp.key			= key;
+	cp.security_level	= 0;
+	cp.exclusive		= false;
+	cp.service_id		= srx->srx_service;
+	call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, gfp);
 
-	call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID, true,
-				     gfp);
-	rxrpc_put_bundle(trans, bundle);
-out:
-	rxrpc_put_transport(trans);
-out_notrans:
 	release_sock(&rx->sk);
 	_leave(" = %p", call);
 	return call;
@@ -369,11 +321,8 @@ EXPORT_SYMBOL(rxrpc_kernel_intercept_rx_messages);
 static int rxrpc_connect(struct socket *sock, struct sockaddr *addr,
 			 int addr_len, int flags)
 {
-	struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) addr;
-	struct sock *sk = sock->sk;
-	struct rxrpc_transport *trans;
-	struct rxrpc_local *local;
-	struct rxrpc_sock *rx = rxrpc_sk(sk);
+	struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)addr;
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	int ret;
 
 	_enter("%p,%p,%d,%d", rx, addr, addr_len, flags);
@@ -386,45 +335,28 @@ static int rxrpc_connect(struct socket *sock, struct sockaddr *addr,
 
 	lock_sock(&rx->sk);
 
+	ret = -EISCONN;
+	if (test_bit(RXRPC_SOCK_CONNECTED, &rx->flags))
+		goto error;
+
 	switch (rx->sk.sk_state) {
-	case RXRPC_UNCONNECTED:
-		/* find a local transport endpoint if we don't have one already */
-		ASSERTCMP(rx->local, ==, NULL);
-		rx->srx.srx_family = AF_RXRPC;
-		rx->srx.srx_service = 0;
-		rx->srx.transport_type = srx->transport_type;
-		rx->srx.transport_len = sizeof(sa_family_t);
-		rx->srx.transport.family = srx->transport.family;
-		local = rxrpc_lookup_local(&rx->srx);
-		if (IS_ERR(local)) {
-			release_sock(&rx->sk);
-			return PTR_ERR(local);
-		}
-		rx->local = local;
-		rx->sk.sk_state = RXRPC_CLIENT_BOUND;
+	case RXRPC_UNBOUND:
+		rx->sk.sk_state = RXRPC_CLIENT_UNBOUND;
+	case RXRPC_CLIENT_UNBOUND:
 	case RXRPC_CLIENT_BOUND:
 		break;
-	case RXRPC_CLIENT_CONNECTED:
-		release_sock(&rx->sk);
-		return -EISCONN;
 	default:
-		release_sock(&rx->sk);
-		return -EBUSY; /* server sockets can't connect as well */
-	}
-
-	trans = rxrpc_name_to_transport(sock, addr, addr_len, flags,
-					GFP_KERNEL);
-	if (IS_ERR(trans)) {
-		release_sock(&rx->sk);
-		_leave(" = %ld", PTR_ERR(trans));
-		return PTR_ERR(trans);
+		ret = -EBUSY;
+		goto error;
 	}
 
-	rx->trans = trans;
-	rx->sk.sk_state = RXRPC_CLIENT_CONNECTED;
+	rx->connect_srx = *srx;
+	set_bit(RXRPC_SOCK_CONNECTED, &rx->flags);
+	ret = 0;
 
+error:
 	release_sock(&rx->sk);
-	return 0;
+	return ret;
 }
 
 /*
@@ -438,7 +370,7 @@ static int rxrpc_connect(struct socket *sock, struct sockaddr *addr,
  */
 static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 {
-	struct rxrpc_transport *trans;
+	struct rxrpc_local *local;
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	int ret;
 
@@ -455,48 +387,38 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 		}
 	}
 
-	trans = NULL;
 	lock_sock(&rx->sk);
 
-	if (m->msg_name) {
-		ret = -EISCONN;
-		trans = rxrpc_name_to_transport(sock, m->msg_name,
-						m->msg_namelen, 0, GFP_KERNEL);
-		if (IS_ERR(trans)) {
-			ret = PTR_ERR(trans);
-			trans = NULL;
-			goto out;
-		}
-	} else {
-		trans = rx->trans;
-		if (trans)
-			atomic_inc(&trans->usage);
-	}
-
 	switch (rx->sk.sk_state) {
-	case RXRPC_SERVER_LISTENING:
-		if (!m->msg_name) {
-			ret = rxrpc_server_sendmsg(rx, m, len);
-			break;
+	case RXRPC_UNBOUND:
+		local = rxrpc_lookup_local(&rx->srx);
+		if (IS_ERR(local)) {
+			ret = PTR_ERR(local);
+			goto error_unlock;
 		}
-	case RXRPC_SERVER_BOUND:
+
+		rx->local = local;
+		rx->sk.sk_state = RXRPC_CLIENT_UNBOUND;
+		/* Fall through */
+
+	case RXRPC_CLIENT_UNBOUND:
 	case RXRPC_CLIENT_BOUND:
-		if (!m->msg_name) {
-			ret = -ENOTCONN;
-			break;
+		if (!m->msg_name &&
+		    test_bit(RXRPC_SOCK_CONNECTED, &rx->flags)) {
+			m->msg_name = &rx->connect_srx;
+			m->msg_namelen = sizeof(rx->connect_srx);
 		}
-	case RXRPC_CLIENT_CONNECTED:
-		ret = rxrpc_client_sendmsg(rx, trans, m, len);
+	case RXRPC_SERVER_BOUND:
+	case RXRPC_SERVER_LISTENING:
+		ret = rxrpc_do_sendmsg(rx, m, len);
 		break;
 	default:
-		ret = -ENOTCONN;
+		ret = -EINVAL;
 		break;
 	}
 
-out:
+error_unlock:
 	release_sock(&rx->sk);
-	if (trans)
-		rxrpc_put_transport(trans);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -523,9 +445,9 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			if (optlen != 0)
 				goto error;
 			ret = -EISCONN;
-			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
-			set_bit(RXRPC_SOCK_EXCLUSIVE_CONN, &rx->flags);
+			rx->exclusive = true;
 			goto success;
 
 		case RXRPC_SECURITY_KEY:
@@ -533,7 +455,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			if (rx->key)
 				goto error;
 			ret = -EISCONN;
-			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
 			ret = rxrpc_request_key(rx, optval, optlen);
 			goto error;
@@ -543,7 +465,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			if (rx->key)
 				goto error;
 			ret = -EISCONN;
-			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
 			ret = rxrpc_server_keyring(rx, optval, optlen);
 			goto error;
@@ -553,7 +475,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			if (optlen != sizeof(unsigned int))
 				goto error;
 			ret = -EISCONN;
-			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
 			ret = get_user(min_sec_level,
 				       (unsigned int __user *) optval);
@@ -632,13 +554,13 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol,
 		return -ENOMEM;
 
 	sock_init_data(sock, sk);
-	sk->sk_state		= RXRPC_UNCONNECTED;
+	sk->sk_state		= RXRPC_UNBOUND;
 	sk->sk_write_space	= rxrpc_write_space;
-	sk->sk_max_ack_backlog	= sysctl_rxrpc_max_qlen;
+	sk->sk_max_ack_backlog	= 0;
 	sk->sk_destruct		= rxrpc_sock_destructor;
 
 	rx = rxrpc_sk(sk);
-	rx->proto = protocol;
+	rx->family = protocol;
 	rx->calls = RB_ROOT;
 
 	INIT_LIST_HEAD(&rx->listen_link);
@@ -700,24 +622,8 @@ static int rxrpc_release_sock(struct sock *sk)
 	flush_workqueue(rxrpc_workqueue);
 	rxrpc_purge_queue(&sk->sk_receive_queue);
 
-	if (rx->conn) {
-		rxrpc_put_connection(rx->conn);
-		rx->conn = NULL;
-	}
-
-	if (rx->bundle) {
-		rxrpc_put_bundle(rx->trans, rx->bundle);
-		rx->bundle = NULL;
-	}
-	if (rx->trans) {
-		rxrpc_put_transport(rx->trans);
-		rx->trans = NULL;
-	}
-	if (rx->local) {
-		rxrpc_put_local(rx->local);
-		rx->local = NULL;
-	}
-
+	rxrpc_put_local(rx->local);
+	rx->local = NULL;
 	key_put(rx->key);
 	rx->key = NULL;
 	key_put(rx->securities);
@@ -882,14 +788,29 @@ static void __exit af_rxrpc_exit(void)
 	proto_unregister(&rxrpc_proto);
 	rxrpc_destroy_all_calls();
 	rxrpc_destroy_all_connections();
-	rxrpc_destroy_all_transports();
-	rxrpc_destroy_all_peers();
-	rxrpc_destroy_all_locals();
 
 	ASSERTCMP(atomic_read(&rxrpc_n_skbs), ==, 0);
 
+	/* We need to flush the scheduled work twice because the local endpoint
+	 * records involve a work item in their destruction as they can only be
+	 * destroyed from process context.  However, a connection may have a
+	 * work item outstanding - and this will pin the local endpoint record
+	 * until the connection goes away.
+	 *
+	 * Peers don't pin locals and calls pin sockets - which prevents the
+	 * module from being unloaded - so we should only need two flushes.
+	 */
 	_debug("flush scheduled work");
 	flush_workqueue(rxrpc_workqueue);
+	_debug("flush scheduled work 2");
+	flush_workqueue(rxrpc_workqueue);
+	_debug("synchronise RCU");
+	rcu_barrier();
+	_debug("destroy locals");
+	ASSERT(idr_is_empty(&rxrpc_client_conn_ids));
+	idr_destroy(&rxrpc_client_conn_ids);
+	rxrpc_destroy_all_locals();
+
 	remove_proc_entry("rxrpc_conns", init_net.proc_net);
 	remove_proc_entry("rxrpc_calls", init_net.proc_net);
 	destroy_workqueue(rxrpc_workqueue);
diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c
deleted file mode 100644
index d67b1f1b5001..000000000000
--- a/net/rxrpc/ar-connection.c
+++ /dev/null
@@ -1,929 +0,0 @@
-/* RxRPC virtual connection handler
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells ([email protected])
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/net.h>
-#include <linux/skbuff.h>
-#include <linux/crypto.h>
-#include <net/sock.h>
-#include <net/af_rxrpc.h>
-#include "ar-internal.h"
-
-/*
- * Time till a connection expires after last use (in seconds).
- */
-unsigned int rxrpc_connection_expiry = 10 * 60;
-
-static void rxrpc_connection_reaper(struct work_struct *work);
-
-LIST_HEAD(rxrpc_connections);
-DEFINE_RWLOCK(rxrpc_connection_lock);
-static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper);
-
-/*
- * allocate a new client connection bundle
- */
-static struct rxrpc_conn_bundle *rxrpc_alloc_bundle(gfp_t gfp)
-{
-	struct rxrpc_conn_bundle *bundle;
-
-	_enter("");
-
-	bundle = kzalloc(sizeof(struct rxrpc_conn_bundle), gfp);
-	if (bundle) {
-		INIT_LIST_HEAD(&bundle->unused_conns);
-		INIT_LIST_HEAD(&bundle->avail_conns);
-		INIT_LIST_HEAD(&bundle->busy_conns);
-		init_waitqueue_head(&bundle->chanwait);
-		atomic_set(&bundle->usage, 1);
-	}
-
-	_leave(" = %p", bundle);
-	return bundle;
-}
-
-/*
- * compare bundle parameters with what we're looking for
- * - return -ve, 0 or +ve
- */
-static inline
-int rxrpc_cmp_bundle(const struct rxrpc_conn_bundle *bundle,
-		     struct key *key, u16 service_id)
-{
-	return (bundle->service_id - service_id) ?:
-		((unsigned long)bundle->key - (unsigned long)key);
-}
-
-/*
- * get bundle of client connections that a client socket can make use of
- */
-struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx,
-					   struct rxrpc_transport *trans,
-					   struct key *key,
-					   u16 service_id,
-					   gfp_t gfp)
-{
-	struct rxrpc_conn_bundle *bundle, *candidate;
-	struct rb_node *p, *parent, **pp;
-
-	_enter("%p{%x},%x,%hx,",
-	       rx, key_serial(key), trans->debug_id, service_id);
-
-	if (rx->trans == trans && rx->bundle) {
-		atomic_inc(&rx->bundle->usage);
-		return rx->bundle;
-	}
-
-	/* search the extant bundles first for one that matches the specified
-	 * user ID */
-	spin_lock(&trans->client_lock);
-
-	p = trans->bundles.rb_node;
-	while (p) {
-		bundle = rb_entry(p, struct rxrpc_conn_bundle, node);
-
-		if (rxrpc_cmp_bundle(bundle, key, service_id) < 0)
-			p = p->rb_left;
-		else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0)
-			p = p->rb_right;
-		else
-			goto found_extant_bundle;
-	}
-
-	spin_unlock(&trans->client_lock);
-
-	/* not yet present - create a candidate for a new record and then
-	 * redo the search */
-	candidate = rxrpc_alloc_bundle(gfp);
-	if (!candidate) {
-		_leave(" = -ENOMEM");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	candidate->key = key_get(key);
-	candidate->service_id = service_id;
-
-	spin_lock(&trans->client_lock);
-
-	pp = &trans->bundles.rb_node;
-	parent = NULL;
-	while (*pp) {
-		parent = *pp;
-		bundle = rb_entry(parent, struct rxrpc_conn_bundle, node);
-
-		if (rxrpc_cmp_bundle(bundle, key, service_id) < 0)
-			pp = &(*pp)->rb_left;
-		else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0)
-			pp = &(*pp)->rb_right;
-		else
-			goto found_extant_second;
-	}
-
-	/* second search also failed; add the new bundle */
-	bundle = candidate;
-	candidate = NULL;
-
-	rb_link_node(&bundle->node, parent, pp);
-	rb_insert_color(&bundle->node, &trans->bundles);
-	spin_unlock(&trans->client_lock);
-	_net("BUNDLE new on trans %d", trans->debug_id);
-	if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
-		atomic_inc(&bundle->usage);
-		rx->bundle = bundle;
-	}
-	_leave(" = %p [new]", bundle);
-	return bundle;
-
-	/* we found the bundle in the list immediately */
-found_extant_bundle:
-	atomic_inc(&bundle->usage);
-	spin_unlock(&trans->client_lock);
-	_net("BUNDLE old on trans %d", trans->debug_id);
-	if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
-		atomic_inc(&bundle->usage);
-		rx->bundle = bundle;
-	}
-	_leave(" = %p [extant %d]", bundle, atomic_read(&bundle->usage));
-	return bundle;
-
-	/* we found the bundle on the second time through the list */
-found_extant_second:
-	atomic_inc(&bundle->usage);
-	spin_unlock(&trans->client_lock);
-	kfree(candidate);
-	_net("BUNDLE old2 on trans %d", trans->debug_id);
-	if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
-		atomic_inc(&bundle->usage);
-		rx->bundle = bundle;
-	}
-	_leave(" = %p [second %d]", bundle, atomic_read(&bundle->usage));
-	return bundle;
-}
-
-/*
- * release a bundle
- */
-void rxrpc_put_bundle(struct rxrpc_transport *trans,
-		      struct rxrpc_conn_bundle *bundle)
-{
-	_enter("%p,%p{%d}",trans, bundle, atomic_read(&bundle->usage));
-
-	if (atomic_dec_and_lock(&bundle->usage, &trans->client_lock)) {
-		_debug("Destroy bundle");
-		rb_erase(&bundle->node, &trans->bundles);
-		spin_unlock(&trans->client_lock);
-		ASSERT(list_empty(&bundle->unused_conns));
-		ASSERT(list_empty(&bundle->avail_conns));
-		ASSERT(list_empty(&bundle->busy_conns));
-		ASSERTCMP(bundle->num_conns, ==, 0);
-		key_put(bundle->key);
-		kfree(bundle);
-	}
-
-	_leave("");
-}
-
-/*
- * allocate a new connection
- */
-static struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp)
-{
-	struct rxrpc_connection *conn;
-
-	_enter("");
-
-	conn = kzalloc(sizeof(struct rxrpc_connection), gfp);
-	if (conn) {
-		INIT_WORK(&conn->processor, &rxrpc_process_connection);
-		INIT_LIST_HEAD(&conn->bundle_link);
-		conn->calls = RB_ROOT;
-		skb_queue_head_init(&conn->rx_queue);
-		conn->security = &rxrpc_no_security;
-		rwlock_init(&conn->lock);
-		spin_lock_init(&conn->state_lock);
-		atomic_set(&conn->usage, 1);
-		conn->debug_id = atomic_inc_return(&rxrpc_debug_id);
-		conn->avail_calls = RXRPC_MAXCALLS;
-		conn->size_align = 4;
-		conn->header_size = sizeof(struct rxrpc_wire_header);
-	}
-
-	_leave(" = %p{%d}", conn, conn ? conn->debug_id : 0);
-	return conn;
-}
-
-/*
- * assign a connection ID to a connection and add it to the transport's
- * connection lookup tree
- * - called with transport client lock held
- */
-static void rxrpc_assign_connection_id(struct rxrpc_connection *conn)
-{
-	struct rxrpc_connection *xconn;
-	struct rb_node *parent, **p;
-	__be32 epoch;
-	u32 cid;
-
-	_enter("");
-
-	epoch = conn->epoch;
-
-	write_lock_bh(&conn->trans->conn_lock);
-
-	conn->trans->conn_idcounter += RXRPC_CID_INC;
-	if (conn->trans->conn_idcounter < RXRPC_CID_INC)
-		conn->trans->conn_idcounter = RXRPC_CID_INC;
-	cid = conn->trans->conn_idcounter;
-
-attempt_insertion:
-	parent = NULL;
-	p = &conn->trans->client_conns.rb_node;
-
-	while (*p) {
-		parent = *p;
-		xconn = rb_entry(parent, struct rxrpc_connection, node);
-
-		if (epoch < xconn->epoch)
-			p = &(*p)->rb_left;
-		else if (epoch > xconn->epoch)
-			p = &(*p)->rb_right;
-		else if (cid < xconn->cid)
-			p = &(*p)->rb_left;
-		else if (cid > xconn->cid)
-			p = &(*p)->rb_right;
-		else
-			goto id_exists;
-	}
-
-	/* we've found a suitable hole - arrange for this connection to occupy
-	 * it */
-	rb_link_node(&conn->node, parent, p);
-	rb_insert_color(&conn->node, &conn->trans->client_conns);
-
-	conn->cid = cid;
-	write_unlock_bh(&conn->trans->conn_lock);
-	_leave(" [CID %x]", cid);
-	return;
-
-	/* we found a connection with the proposed ID - walk the tree from that
-	 * point looking for the next unused ID */
-id_exists:
-	for (;;) {
-		cid += RXRPC_CID_INC;
-		if (cid < RXRPC_CID_INC) {
-			cid = RXRPC_CID_INC;
-			conn->trans->conn_idcounter = cid;
-			goto attempt_insertion;
-		}
-
-		parent = rb_next(parent);
-		if (!parent)
-			goto attempt_insertion;
-
-		xconn = rb_entry(parent, struct rxrpc_connection, node);
-		if (epoch < xconn->epoch ||
-		    cid < xconn->cid)
-			goto attempt_insertion;
-	}
-}
-
-/*
- * add a call to a connection's call-by-ID tree
- */
-static void rxrpc_add_call_ID_to_conn(struct rxrpc_connection *conn,
-				      struct rxrpc_call *call)
-{
-	struct rxrpc_call *xcall;
-	struct rb_node *parent, **p;
-	__be32 call_id;
-
-	write_lock_bh(&conn->lock);
-
-	call_id = call->call_id;
-	p = &conn->calls.rb_node;
-	parent = NULL;
-	while (*p) {
-		parent = *p;
-		xcall = rb_entry(parent, struct rxrpc_call, conn_node);
-
-		if (call_id < xcall->call_id)
-			p = &(*p)->rb_left;
-		else if (call_id > xcall->call_id)
-			p = &(*p)->rb_right;
-		else
-			BUG();
-	}
-
-	rb_link_node(&call->conn_node, parent, p);
-	rb_insert_color(&call->conn_node, &conn->calls);
-
-	write_unlock_bh(&conn->lock);
-}
-
-/*
- * connect a call on an exclusive connection
- */
-static int rxrpc_connect_exclusive(struct rxrpc_sock *rx,
-				   struct rxrpc_transport *trans,
-				   u16 service_id,
-				   struct rxrpc_call *call,
-				   gfp_t gfp)
-{
-	struct rxrpc_connection *conn;
-	int chan, ret;
-
-	_enter("");
-
-	conn = rx->conn;
-	if (!conn) {
-		/* not yet present - create a candidate for a new connection
-		 * and then redo the check */
-		conn = rxrpc_alloc_connection(gfp);
-		if (!conn) {
-			_leave(" = -ENOMEM");
-			return -ENOMEM;
-		}
-
-		conn->trans = trans;
-		conn->bundle = NULL;
-		conn->service_id = service_id;
-		conn->epoch = rxrpc_epoch;
-		conn->in_clientflag = 0;
-		conn->out_clientflag = RXRPC_CLIENT_INITIATED;
-		conn->cid = 0;
-		conn->state = RXRPC_CONN_CLIENT;
-		conn->avail_calls = RXRPC_MAXCALLS - 1;
-		conn->security_level = rx->min_sec_level;
-		conn->key = key_get(rx->key);
-
-		ret = rxrpc_init_client_conn_security(conn);
-		if (ret < 0) {
-			key_put(conn->key);
-			kfree(conn);
-			_leave(" = %d [key]", ret);
-			return ret;
-		}
-
-		write_lock_bh(&rxrpc_connection_lock);
-		list_add_tail(&conn->link, &rxrpc_connections);
-		write_unlock_bh(&rxrpc_connection_lock);
-
-		spin_lock(&trans->client_lock);
-		atomic_inc(&trans->usage);
-
-		_net("CONNECT EXCL new %d on TRANS %d",
-		     conn->debug_id, conn->trans->debug_id);
-
-		rxrpc_assign_connection_id(conn);
-		rx->conn = conn;
-	} else {
-		spin_lock(&trans->client_lock);
-	}
-
-	/* we've got a connection with a free channel and we can now attach the
-	 * call to it
-	 * - we're holding the transport's client lock
-	 * - we're holding a reference on the connection
-	 */
-	for (chan = 0; chan < RXRPC_MAXCALLS; chan++)
-		if (!conn->channels[chan])
-			goto found_channel;
-	goto no_free_channels;
-
-found_channel:
-	atomic_inc(&conn->usage);
-	conn->channels[chan] = call;
-	call->conn = conn;
-	call->channel = chan;
-	call->cid = conn->cid | chan;
-	call->call_id = ++conn->call_counter;
-
-	_net("CONNECT client on conn %d chan %d as call %x",
-	     conn->debug_id, chan, call->call_id);
-
-	spin_unlock(&trans->client_lock);
-
-	rxrpc_add_call_ID_to_conn(conn, call);
-	_leave(" = 0");
-	return 0;
-
-no_free_channels:
-	spin_unlock(&trans->client_lock);
-	_leave(" = -ENOSR");
-	return -ENOSR;
-}
-
-/*
- * find a connection for a call
- * - called in process context with IRQs enabled
- */
-int rxrpc_connect_call(struct rxrpc_sock *rx,
-		       struct rxrpc_transport *trans,
-		       struct rxrpc_conn_bundle *bundle,
-		       struct rxrpc_call *call,
-		       gfp_t gfp)
-{
-	struct rxrpc_connection *conn, *candidate;
-	int chan, ret;
-
-	DECLARE_WAITQUEUE(myself, current);
-
-	_enter("%p,%lx,", rx, call->user_call_ID);
-
-	if (test_bit(RXRPC_SOCK_EXCLUSIVE_CONN, &rx->flags))
-		return rxrpc_connect_exclusive(rx, trans, bundle->service_id,
-					       call, gfp);
-
-	spin_lock(&trans->client_lock);
-	for (;;) {
-		/* see if the bundle has a call slot available */
-		if (!list_empty(&bundle->avail_conns)) {
-			_debug("avail");
-			conn = list_entry(bundle->avail_conns.next,
-					  struct rxrpc_connection,
-					  bundle_link);
-			if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
-				list_del_init(&conn->bundle_link);
-				bundle->num_conns--;
-				continue;
-			}
-			if (--conn->avail_calls == 0)
-				list_move(&conn->bundle_link,
-					  &bundle->busy_conns);
-			ASSERTCMP(conn->avail_calls, <, RXRPC_MAXCALLS);
-			ASSERT(conn->channels[0] == NULL ||
-			       conn->channels[1] == NULL ||
-			       conn->channels[2] == NULL ||
-			       conn->channels[3] == NULL);
-			atomic_inc(&conn->usage);
-			break;
-		}
-
-		if (!list_empty(&bundle->unused_conns)) {
-			_debug("unused");
-			conn = list_entry(bundle->unused_conns.next,
-					  struct rxrpc_connection,
-					  bundle_link);
-			if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
-				list_del_init(&conn->bundle_link);
-				bundle->num_conns--;
-				continue;
-			}
-			ASSERTCMP(conn->avail_calls, ==, RXRPC_MAXCALLS);
-			conn->avail_calls = RXRPC_MAXCALLS - 1;
-			ASSERT(conn->channels[0] == NULL &&
-			       conn->channels[1] == NULL &&
-			       conn->channels[2] == NULL &&
-			       conn->channels[3] == NULL);
-			atomic_inc(&conn->usage);
-			list_move(&conn->bundle_link, &bundle->avail_conns);
-			break;
-		}
-
-		/* need to allocate a new connection */
-		_debug("get new conn [%d]", bundle->num_conns);
-
-		spin_unlock(&trans->client_lock);
-
-		if (signal_pending(current))
-			goto interrupted;
-
-		if (bundle->num_conns >= 20) {
-			_debug("too many conns");
-
-			if (!gfpflags_allow_blocking(gfp)) {
-				_leave(" = -EAGAIN");
-				return -EAGAIN;
-			}
-
-			add_wait_queue(&bundle->chanwait, &myself);
-			for (;;) {
-				set_current_state(TASK_INTERRUPTIBLE);
-				if (bundle->num_conns < 20 ||
-				    !list_empty(&bundle->unused_conns) ||
-				    !list_empty(&bundle->avail_conns))
-					break;
-				if (signal_pending(current))
-					goto interrupted_dequeue;
-				schedule();
-			}
-			remove_wait_queue(&bundle->chanwait, &myself);
-			__set_current_state(TASK_RUNNING);
-			spin_lock(&trans->client_lock);
-			continue;
-		}
-
-		/* not yet present - create a candidate for a new connection and then
-		 * redo the check */
-		candidate = rxrpc_alloc_connection(gfp);
-		if (!candidate) {
-			_leave(" = -ENOMEM");
-			return -ENOMEM;
-		}
-
-		candidate->trans = trans;
-		candidate->bundle = bundle;
-		candidate->service_id = bundle->service_id;
-		candidate->epoch = rxrpc_epoch;
-		candidate->in_clientflag = 0;
-		candidate->out_clientflag = RXRPC_CLIENT_INITIATED;
-		candidate->cid = 0;
-		candidate->state = RXRPC_CONN_CLIENT;
-		candidate->avail_calls = RXRPC_MAXCALLS;
-		candidate->security_level = rx->min_sec_level;
-		candidate->key = key_get(bundle->key);
-
-		ret = rxrpc_init_client_conn_security(candidate);
-		if (ret < 0) {
-			key_put(candidate->key);
-			kfree(candidate);
-			_leave(" = %d [key]", ret);
-			return ret;
-		}
-
-		write_lock_bh(&rxrpc_connection_lock);
-		list_add_tail(&candidate->link, &rxrpc_connections);
-		write_unlock_bh(&rxrpc_connection_lock);
-
-		spin_lock(&trans->client_lock);
-
-		list_add(&candidate->bundle_link, &bundle->unused_conns);
-		bundle->num_conns++;
-		atomic_inc(&bundle->usage);
-		atomic_inc(&trans->usage);
-
-		_net("CONNECT new %d on TRANS %d",
-		     candidate->debug_id, candidate->trans->debug_id);
-
-		rxrpc_assign_connection_id(candidate);
-		candidate->security->prime_packet_security(candidate);
-
-		/* leave the candidate lurking in zombie mode attached to the
-		 * bundle until we're ready for it */
-		rxrpc_put_connection(candidate);
-		candidate = NULL;
-	}
-
-	/* we've got a connection with a free channel and we can now attach the
-	 * call to it
-	 * - we're holding the transport's client lock
-	 * - we're holding a reference on the connection
-	 * - we're holding a reference on the bundle
-	 */
-	for (chan = 0; chan < RXRPC_MAXCALLS; chan++)
-		if (!conn->channels[chan])
-			goto found_channel;
-	ASSERT(conn->channels[0] == NULL ||
-	       conn->channels[1] == NULL ||
-	       conn->channels[2] == NULL ||
-	       conn->channels[3] == NULL);
-	BUG();
-
-found_channel:
-	conn->channels[chan] = call;
-	call->conn = conn;
-	call->channel = chan;
-	call->cid = conn->cid | chan;
-	call->call_id = ++conn->call_counter;
-
-	_net("CONNECT client on conn %d chan %d as call %x",
-	     conn->debug_id, chan, call->call_id);
-
-	ASSERTCMP(conn->avail_calls, <, RXRPC_MAXCALLS);
-	spin_unlock(&trans->client_lock);
-
-	rxrpc_add_call_ID_to_conn(conn, call);
-
-	_leave(" = 0");
-	return 0;
-
-interrupted_dequeue:
-	remove_wait_queue(&bundle->chanwait, &myself);
-	__set_current_state(TASK_RUNNING);
-interrupted:
-	_leave(" = -ERESTARTSYS");
-	return -ERESTARTSYS;
-}
-
-/*
- * get a record of an incoming connection
- */
-struct rxrpc_connection *
-rxrpc_incoming_connection(struct rxrpc_transport *trans,
-			  struct rxrpc_host_header *hdr)
-{
-	struct rxrpc_connection *conn, *candidate = NULL;
-	struct rb_node *p, **pp;
-	const char *new = "old";
-	__be32 epoch;
-	u32 cid;
-
-	_enter("");
-
-	ASSERT(hdr->flags & RXRPC_CLIENT_INITIATED);
-
-	epoch = hdr->epoch;
-	cid = hdr->cid & RXRPC_CIDMASK;
-
-	/* search the connection list first */
-	read_lock_bh(&trans->conn_lock);
-
-	p = trans->server_conns.rb_node;
-	while (p) {
-		conn = rb_entry(p, struct rxrpc_connection, node);
-
-		_debug("maybe %x", conn->cid);
-
-		if (epoch < conn->epoch)
-			p = p->rb_left;
-		else if (epoch > conn->epoch)
-			p = p->rb_right;
-		else if (cid < conn->cid)
-			p = p->rb_left;
-		else if (cid > conn->cid)
-			p = p->rb_right;
-		else
-			goto found_extant_connection;
-	}
-	read_unlock_bh(&trans->conn_lock);
-
-	/* not yet present - create a candidate for a new record and then
-	 * redo the search */
-	candidate = rxrpc_alloc_connection(GFP_NOIO);
-	if (!candidate) {
-		_leave(" = -ENOMEM");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	candidate->trans = trans;
-	candidate->epoch = hdr->epoch;
-	candidate->cid = hdr->cid & RXRPC_CIDMASK;
-	candidate->service_id = hdr->serviceId;
-	candidate->security_ix = hdr->securityIndex;
-	candidate->in_clientflag = RXRPC_CLIENT_INITIATED;
-	candidate->out_clientflag = 0;
-	candidate->state = RXRPC_CONN_SERVER;
-	if (candidate->service_id)
-		candidate->state = RXRPC_CONN_SERVER_UNSECURED;
-
-	write_lock_bh(&trans->conn_lock);
-
-	pp = &trans->server_conns.rb_node;
-	p = NULL;
-	while (*pp) {
-		p = *pp;
-		conn = rb_entry(p, struct rxrpc_connection, node);
-
-		if (epoch < conn->epoch)
-			pp = &(*pp)->rb_left;
-		else if (epoch > conn->epoch)
-			pp = &(*pp)->rb_right;
-		else if (cid < conn->cid)
-			pp = &(*pp)->rb_left;
-		else if (cid > conn->cid)
-			pp = &(*pp)->rb_right;
-		else
-			goto found_extant_second;
-	}
-
-	/* we can now add the new candidate to the list */
-	conn = candidate;
-	candidate = NULL;
-	rb_link_node(&conn->node, p, pp);
-	rb_insert_color(&conn->node, &trans->server_conns);
-	atomic_inc(&conn->trans->usage);
-
-	write_unlock_bh(&trans->conn_lock);
-
-	write_lock_bh(&rxrpc_connection_lock);
-	list_add_tail(&conn->link, &rxrpc_connections);
-	write_unlock_bh(&rxrpc_connection_lock);
-
-	new = "new";
-
-success:
-	_net("CONNECTION %s %d {%x}", new, conn->debug_id, conn->cid);
-
-	_leave(" = %p {u=%d}", conn, atomic_read(&conn->usage));
-	return conn;
-
-	/* we found the connection in the list immediately */
-found_extant_connection:
-	if (hdr->securityIndex != conn->security_ix) {
-		read_unlock_bh(&trans->conn_lock);
-		goto security_mismatch;
-	}
-	atomic_inc(&conn->usage);
-	read_unlock_bh(&trans->conn_lock);
-	goto success;
-
-	/* we found the connection on the second time through the list */
-found_extant_second:
-	if (hdr->securityIndex != conn->security_ix) {
-		write_unlock_bh(&trans->conn_lock);
-		goto security_mismatch;
-	}
-	atomic_inc(&conn->usage);
-	write_unlock_bh(&trans->conn_lock);
-	kfree(candidate);
-	goto success;
-
-security_mismatch:
-	kfree(candidate);
-	_leave(" = -EKEYREJECTED");
-	return ERR_PTR(-EKEYREJECTED);
-}
-
-/*
- * find a connection based on transport and RxRPC connection ID for an incoming
- * packet
- */
-struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_transport *trans,
-					       struct rxrpc_host_header *hdr)
-{
-	struct rxrpc_connection *conn;
-	struct rb_node *p;
-	u32 epoch, cid;
-
-	_enter(",{%x,%x}", hdr->cid, hdr->flags);
-
-	read_lock_bh(&trans->conn_lock);
-
-	cid = hdr->cid & RXRPC_CIDMASK;
-	epoch = hdr->epoch;
-
-	if (hdr->flags & RXRPC_CLIENT_INITIATED)
-		p = trans->server_conns.rb_node;
-	else
-		p = trans->client_conns.rb_node;
-
-	while (p) {
-		conn = rb_entry(p, struct rxrpc_connection, node);
-
-		_debug("maybe %x", conn->cid);
-
-		if (epoch < conn->epoch)
-			p = p->rb_left;
-		else if (epoch > conn->epoch)
-			p = p->rb_right;
-		else if (cid < conn->cid)
-			p = p->rb_left;
-		else if (cid > conn->cid)
-			p = p->rb_right;
-		else
-			goto found;
-	}
-
-	read_unlock_bh(&trans->conn_lock);
-	_leave(" = NULL");
-	return NULL;
-
-found:
-	atomic_inc(&conn->usage);
-	read_unlock_bh(&trans->conn_lock);
-	_leave(" = %p", conn);
-	return conn;
-}
-
-/*
- * release a virtual connection
- */
-void rxrpc_put_connection(struct rxrpc_connection *conn)
-{
-	_enter("%p{u=%d,d=%d}",
-	       conn, atomic_read(&conn->usage), conn->debug_id);
-
-	ASSERTCMP(atomic_read(&conn->usage), >, 0);
-
-	conn->put_time = ktime_get_seconds();
-	if (atomic_dec_and_test(&conn->usage)) {
-		_debug("zombie");
-		rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0);
-	}
-
-	_leave("");
-}
-
-/*
- * destroy a virtual connection
- */
-static void rxrpc_destroy_connection(struct rxrpc_connection *conn)
-{
-	_enter("%p{%d}", conn, atomic_read(&conn->usage));
-
-	ASSERTCMP(atomic_read(&conn->usage), ==, 0);
-
-	_net("DESTROY CONN %d", conn->debug_id);
-
-	if (conn->bundle)
-		rxrpc_put_bundle(conn->trans, conn->bundle);
-
-	ASSERT(RB_EMPTY_ROOT(&conn->calls));
-	rxrpc_purge_queue(&conn->rx_queue);
-
-	conn->security->clear(conn);
-	key_put(conn->key);
-	key_put(conn->server_key);
-
-	rxrpc_put_transport(conn->trans);
-	kfree(conn);
-	_leave("");
-}
-
-/*
- * reap dead connections
- */
-static void rxrpc_connection_reaper(struct work_struct *work)
-{
-	struct rxrpc_connection *conn, *_p;
-	unsigned long now, earliest, reap_time;
-
-	LIST_HEAD(graveyard);
-
-	_enter("");
-
-	now = ktime_get_seconds();
-	earliest = ULONG_MAX;
-
-	write_lock_bh(&rxrpc_connection_lock);
-	list_for_each_entry_safe(conn, _p, &rxrpc_connections, link) {
-		_debug("reap CONN %d { u=%d,t=%ld }",
-		       conn->debug_id, atomic_read(&conn->usage),
-		       (long) now - (long) conn->put_time);
-
-		if (likely(atomic_read(&conn->usage) > 0))
-			continue;
-
-		spin_lock(&conn->trans->client_lock);
-		write_lock(&conn->trans->conn_lock);
-		reap_time = conn->put_time + rxrpc_connection_expiry;
-
-		if (atomic_read(&conn->usage) > 0) {
-			;
-		} else if (reap_time <= now) {
-			list_move_tail(&conn->link, &graveyard);
-			if (conn->out_clientflag)
-				rb_erase(&conn->node,
-					 &conn->trans->client_conns);
-			else
-				rb_erase(&conn->node,
-					 &conn->trans->server_conns);
-			if (conn->bundle) {
-				list_del_init(&conn->bundle_link);
-				conn->bundle->num_conns--;
-			}
-
-		} else if (reap_time < earliest) {
-			earliest = reap_time;
-		}
-
-		write_unlock(&conn->trans->conn_lock);
-		spin_unlock(&conn->trans->client_lock);
-	}
-	write_unlock_bh(&rxrpc_connection_lock);
-
-	if (earliest != ULONG_MAX) {
-		_debug("reschedule reaper %ld", (long) earliest - now);
-		ASSERTCMP(earliest, >, now);
-		rxrpc_queue_delayed_work(&rxrpc_connection_reap,
-					 (earliest - now) * HZ);
-	}
-
-	/* then destroy all those pulled out */
-	while (!list_empty(&graveyard)) {
-		conn = list_entry(graveyard.next, struct rxrpc_connection,
-				  link);
-		list_del_init(&conn->link);
-
-		ASSERTCMP(atomic_read(&conn->usage), ==, 0);
-		rxrpc_destroy_connection(conn);
-	}
-
-	_leave("");
-}
-
-/*
- * preemptively destroy all the connection records rather than waiting for them
- * to time out
- */
-void __exit rxrpc_destroy_all_connections(void)
-{
-	_enter("");
-
-	rxrpc_connection_expiry = 0;
-	cancel_delayed_work(&rxrpc_connection_reap);
-	rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0);
-
-	_leave("");
-}
diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c
deleted file mode 100644
index 3e82d6f0313c..000000000000
--- a/net/rxrpc/ar-error.c
+++ /dev/null
@@ -1,230 +0,0 @@
-/* Error message handling (ICMP)
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells ([email protected])
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/module.h>
-#include <linux/net.h>
-#include <linux/skbuff.h>
-#include <linux/errqueue.h>
-#include <linux/udp.h>
-#include <linux/in.h>
-#include <linux/in6.h>
-#include <linux/icmp.h>
-#include <net/sock.h>
-#include <net/af_rxrpc.h>
-#include <net/ip.h>
-#include "ar-internal.h"
-
-/*
- * handle an error received on the local endpoint
- */
-void rxrpc_UDP_error_report(struct sock *sk)
-{
-	struct sock_exterr_skb *serr;
-	struct rxrpc_transport *trans;
-	struct rxrpc_local *local = sk->sk_user_data;
-	struct rxrpc_peer *peer;
-	struct sk_buff *skb;
-	__be32 addr;
-	__be16 port;
-
-	_enter("%p{%d}", sk, local->debug_id);
-
-	skb = sock_dequeue_err_skb(sk);
-	if (!skb) {
-		_leave("UDP socket errqueue empty");
-		return;
-	}
-	serr = SKB_EXT_ERR(skb);
-	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
-		_leave("UDP empty message");
-		kfree_skb(skb);
-		return;
-	}
-
-	rxrpc_new_skb(skb);
-
-	addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset);
-	port = serr->port;
-
-	_net("Rx UDP Error from %pI4:%hu", &addr, ntohs(port));
-	_debug("Msg l:%d d:%d", skb->len, skb->data_len);
-
-	peer = rxrpc_find_peer(local, addr, port);
-	if (IS_ERR(peer)) {
-		rxrpc_free_skb(skb);
-		_leave(" [no peer]");
-		return;
-	}
-
-	trans = rxrpc_find_transport(local, peer);
-	if (!trans) {
-		rxrpc_put_peer(peer);
-		rxrpc_free_skb(skb);
-		_leave(" [no trans]");
-		return;
-	}
-
-	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
-	    serr->ee.ee_type == ICMP_DEST_UNREACH &&
-	    serr->ee.ee_code == ICMP_FRAG_NEEDED
-	    ) {
-		u32 mtu = serr->ee.ee_info;
-
-		_net("Rx Received ICMP Fragmentation Needed (%d)", mtu);
-
-		/* wind down the local interface MTU */
-		if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) {
-			peer->if_mtu = mtu;
-			_net("I/F MTU %u", mtu);
-		}
-
-		if (mtu == 0) {
-			/* they didn't give us a size, estimate one */
-			mtu = peer->if_mtu;
-			if (mtu > 1500) {
-				mtu >>= 1;
-				if (mtu < 1500)
-					mtu = 1500;
-			} else {
-				mtu -= 100;
-				if (mtu < peer->hdrsize)
-					mtu = peer->hdrsize + 4;
-			}
-		}
-
-		if (mtu < peer->mtu) {
-			spin_lock_bh(&peer->lock);
-			peer->mtu = mtu;
-			peer->maxdata = peer->mtu - peer->hdrsize;
-			spin_unlock_bh(&peer->lock);
-			_net("Net MTU %u (maxdata %u)",
-			     peer->mtu, peer->maxdata);
-		}
-	}
-
-	rxrpc_put_peer(peer);
-
-	/* pass the transport ref to error_handler to release */
-	skb_queue_tail(&trans->error_queue, skb);
-	rxrpc_queue_work(&trans->error_handler);
-	_leave("");
-}
-
-/*
- * deal with UDP error messages
- */
-void rxrpc_UDP_error_handler(struct work_struct *work)
-{
-	struct sock_extended_err *ee;
-	struct sock_exterr_skb *serr;
-	struct rxrpc_transport *trans =
-		container_of(work, struct rxrpc_transport, error_handler);
-	struct sk_buff *skb;
-	int err;
-
-	_enter("");
-
-	skb = skb_dequeue(&trans->error_queue);
-	if (!skb)
-		return;
-
-	serr = SKB_EXT_ERR(skb);
-	ee = &serr->ee;
-
-	_net("Rx Error o=%d t=%d c=%d e=%d",
-	     ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno);
-
-	err = ee->ee_errno;
-
-	switch (ee->ee_origin) {
-	case SO_EE_ORIGIN_ICMP:
-		switch (ee->ee_type) {
-		case ICMP_DEST_UNREACH:
-			switch (ee->ee_code) {
-			case ICMP_NET_UNREACH:
-				_net("Rx Received ICMP Network Unreachable");
-				break;
-			case ICMP_HOST_UNREACH:
-				_net("Rx Received ICMP Host Unreachable");
-				break;
-			case ICMP_PORT_UNREACH:
-				_net("Rx Received ICMP Port Unreachable");
-				break;
-			case ICMP_NET_UNKNOWN:
-				_net("Rx Received ICMP Unknown Network");
-				break;
-			case ICMP_HOST_UNKNOWN:
-				_net("Rx Received ICMP Unknown Host");
-				break;
-			default:
-				_net("Rx Received ICMP DestUnreach code=%u",
-				     ee->ee_code);
-				break;
-			}
-			break;
-
-		case ICMP_TIME_EXCEEDED:
-			_net("Rx Received ICMP TTL Exceeded");
-			break;
-
-		default:
-			_proto("Rx Received ICMP error { type=%u code=%u }",
-			       ee->ee_type, ee->ee_code);
-			break;
-		}
-		break;
-
-	case SO_EE_ORIGIN_LOCAL:
-		_proto("Rx Received local error { error=%d }",
-		       ee->ee_errno);
-		break;
-
-	case SO_EE_ORIGIN_NONE:
-	case SO_EE_ORIGIN_ICMP6:
-	default:
-		_proto("Rx Received error report { orig=%u }",
-		       ee->ee_origin);
-		break;
-	}
-
-	/* terminate all the affected calls if there's an unrecoverable
-	 * error */
-	if (err) {
-		struct rxrpc_call *call, *_n;
-
-		_debug("ISSUE ERROR %d", err);
-
-		spin_lock_bh(&trans->peer->lock);
-		trans->peer->net_error = err;
-
-		list_for_each_entry_safe(call, _n, &trans->peer->error_targets,
-					 error_link) {
-			write_lock(&call->state_lock);
-			if (call->state != RXRPC_CALL_COMPLETE &&
-			    call->state < RXRPC_CALL_NETWORK_ERROR) {
-				call->state = RXRPC_CALL_NETWORK_ERROR;
-				set_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events);
-				rxrpc_queue_call(call);
-			}
-			write_unlock(&call->state_lock);
-			list_del_init(&call->error_link);
-		}
-
-		spin_unlock_bh(&trans->peer->lock);
-	}
-
-	if (!skb_queue_empty(&trans->error_queue))
-		rxrpc_queue_work(&trans->error_handler);
-
-	rxrpc_free_skb(skb);
-	rxrpc_put_transport(trans);
-	_leave("");
-}
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 18ab5c50ba87..702db72196fb 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -9,7 +9,9 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <linux/atomic.h>
 #include <net/sock.h>
+#include <net/af_rxrpc.h>
 #include <rxrpc/packet.h>
 
 #if 0
@@ -35,13 +37,15 @@ struct rxrpc_crypt {
 #define rxrpc_queue_call(CALL)	rxrpc_queue_work(&(CALL)->processor)
 #define rxrpc_queue_conn(CONN)	rxrpc_queue_work(&(CONN)->processor)
 
+struct rxrpc_connection;
+
 /*
  * sk_state for RxRPC sockets
  */
 enum {
-	RXRPC_UNCONNECTED = 0,
+	RXRPC_UNBOUND = 0,
+	RXRPC_CLIENT_UNBOUND,		/* Unbound socket used as client */
 	RXRPC_CLIENT_BOUND,		/* client local address bound */
-	RXRPC_CLIENT_CONNECTED,		/* client is connected */
 	RXRPC_SERVER_BOUND,		/* server local address bound */
 	RXRPC_SERVER_LISTENING,		/* server listening for connections */
 	RXRPC_CLOSE,			/* socket is being closed */
@@ -55,9 +59,6 @@ struct rxrpc_sock {
 	struct sock		sk;
 	rxrpc_interceptor_t	interceptor;	/* kernel service Rx interceptor function */
 	struct rxrpc_local	*local;		/* local endpoint */
-	struct rxrpc_transport	*trans;		/* transport handler */
-	struct rxrpc_conn_bundle *bundle;	/* virtual connection bundle */
-	struct rxrpc_connection	*conn;		/* exclusive virtual connection */
 	struct list_head	listen_link;	/* link in the local endpoint's listen list */
 	struct list_head	secureq;	/* calls awaiting connection security clearance */
 	struct list_head	acceptq;	/* calls awaiting acceptance */
@@ -65,12 +66,14 @@ struct rxrpc_sock {
 	struct key		*securities;	/* list of server security descriptors */
 	struct rb_root		calls;		/* outstanding calls on this socket */
 	unsigned long		flags;
-#define RXRPC_SOCK_EXCLUSIVE_CONN	1	/* exclusive connection for a client socket */
+#define RXRPC_SOCK_CONNECTED		0	/* connect_srx is set */
 	rwlock_t		call_lock;	/* lock for calls */
 	u32			min_sec_level;	/* minimum security level */
 #define RXRPC_SECURITY_MAX	RXRPC_SECURITY_ENCRYPT
+	bool			exclusive;	/* Exclusive connection for a client socket */
+	sa_family_t		family;		/* Protocol family created with */
 	struct sockaddr_rxrpc	srx;		/* local address */
-	sa_family_t		proto;		/* protocol created with */
+	struct sockaddr_rxrpc	connect_srx;	/* Default client address from connect() */
 };
 
 #define rxrpc_sk(__sk) container_of((__sk), struct rxrpc_sock, sk)
@@ -168,46 +171,52 @@ struct rxrpc_security {
 };
 
 /*
- * RxRPC local transport endpoint definition
- * - matched by local port, address and protocol type
+ * RxRPC local transport endpoint description
+ * - owned by a single AF_RXRPC socket
+ * - pointed to by transport socket struct sk_user_data
  */
 struct rxrpc_local {
+	struct rcu_head		rcu;
+	atomic_t		usage;
+	struct list_head	link;
 	struct socket		*socket;	/* my UDP socket */
-	struct work_struct	destroyer;	/* endpoint destroyer */
-	struct work_struct	acceptor;	/* incoming call processor */
-	struct work_struct	rejecter;	/* packet reject writer */
-	struct work_struct	event_processor; /* endpoint event processor */
+	struct work_struct	processor;
 	struct list_head	services;	/* services listening on this endpoint */
-	struct list_head	link;		/* link in endpoint list */
 	struct rw_semaphore	defrag_sem;	/* control re-enablement of IP DF bit */
 	struct sk_buff_head	accept_queue;	/* incoming calls awaiting acceptance */
 	struct sk_buff_head	reject_queue;	/* packets awaiting rejection */
 	struct sk_buff_head	event_queue;	/* endpoint event packets awaiting processing */
+	struct rb_root		client_conns;	/* Client connections by socket params */
+	spinlock_t		client_conns_lock; /* Lock for client_conns */
 	spinlock_t		lock;		/* access lock */
 	rwlock_t		services_lock;	/* lock for services list */
-	atomic_t		usage;
 	int			debug_id;	/* debug ID for printks */
-	volatile char		error_rcvd;	/* T if received ICMP error outstanding */
+	bool			dead;
 	struct sockaddr_rxrpc	srx;		/* local address */
 };
 
 /*
  * RxRPC remote transport endpoint definition
- * - matched by remote port, address and protocol type
- * - holds the connection ID counter for connections between the two endpoints
+ * - matched by local endpoint, remote port, address and protocol type
  */
 struct rxrpc_peer {
-	struct work_struct	destroyer;	/* peer destroyer */
-	struct list_head	link;		/* link in master peer list */
-	struct list_head	error_targets;	/* targets for net error distribution */
-	spinlock_t		lock;		/* access lock */
+	struct rcu_head		rcu;		/* This must be first */
 	atomic_t		usage;
+	unsigned long		hash_key;
+	struct hlist_node	hash_link;
+	struct rxrpc_local	*local;
+	struct hlist_head	error_targets;	/* targets for net error distribution */
+	struct work_struct	error_distributor;
+	struct rb_root		service_conns;	/* Service connections */
+	rwlock_t		conn_lock;
+	spinlock_t		lock;		/* access lock */
 	unsigned int		if_mtu;		/* interface MTU for this peer */
 	unsigned int		mtu;		/* network MTU for this peer */
 	unsigned int		maxdata;	/* data size (MTU - hdrsize) */
 	unsigned short		hdrsize;	/* header size (IP + UDP + RxRPC) */
 	int			debug_id;	/* debug ID for printks */
-	int			net_error;	/* network error distributed */
+	int			error_report;	/* Net (+0) or local (+1000000) to distribute */
+#define RXRPC_LOCAL_ERROR_OFFSET 1000000
 	struct sockaddr_rxrpc	srx;		/* remote address */
 
 	/* calculated RTT cache */
@@ -219,68 +228,63 @@ struct rxrpc_peer {
 };
 
 /*
- * RxRPC point-to-point transport / connection manager definition
- * - handles a bundle of connections between two endpoints
- * - matched by { local, peer }
- */
-struct rxrpc_transport {
-	struct rxrpc_local	*local;		/* local transport endpoint */
-	struct rxrpc_peer	*peer;		/* remote transport endpoint */
-	struct work_struct	error_handler;	/* network error distributor */
-	struct rb_root		bundles;	/* client connection bundles on this transport */
-	struct rb_root		client_conns;	/* client connections on this transport */
-	struct rb_root		server_conns;	/* server connections on this transport */
-	struct list_head	link;		/* link in master session list */
-	struct sk_buff_head	error_queue;	/* error packets awaiting processing */
-	unsigned long		put_time;	/* time at which to reap */
-	spinlock_t		client_lock;	/* client connection allocation lock */
-	rwlock_t		conn_lock;	/* lock for active/dead connections */
-	atomic_t		usage;
-	int			debug_id;	/* debug ID for printks */
-	unsigned int		conn_idcounter;	/* connection ID counter (client) */
+ * Keys for matching a connection.
+ */
+struct rxrpc_conn_proto {
+	unsigned long		hash_key;
+	struct rxrpc_local	*local;		/* Representation of local endpoint */
+	u32			epoch;		/* epoch of this connection */
+	u32			cid;		/* connection ID */
+	u8			in_clientflag;	/* RXRPC_CLIENT_INITIATED if we are server */
+	u8			addr_size;	/* Size of the address */
+	sa_family_t		family;		/* Transport protocol */
+	__be16			port;		/* Peer UDP/UDP6 port */
+	union {					/* Peer address */
+		struct in_addr	ipv4_addr;
+		struct in6_addr	ipv6_addr;
+		u32		raw_addr[0];
+	};
 };
 
-/*
- * RxRPC client connection bundle
- * - matched by { transport, service_id, key }
- */
-struct rxrpc_conn_bundle {
-	struct rb_node		node;		/* node in transport's lookup tree */
-	struct list_head	unused_conns;	/* unused connections in this bundle */
-	struct list_head	avail_conns;	/* available connections in this bundle */
-	struct list_head	busy_conns;	/* busy connections in this bundle */
-	struct key		*key;		/* security for this bundle */
-	wait_queue_head_t	chanwait;	/* wait for channel to become available */
-	atomic_t		usage;
-	int			debug_id;	/* debug ID for printks */
-	unsigned short		num_conns;	/* number of connections in this bundle */
-	u16			service_id;	/* Service ID for this bundle */
-	u8			security_ix;	/* security type */
+struct rxrpc_conn_parameters {
+	struct rxrpc_local	*local;		/* Representation of local endpoint */
+	struct rxrpc_peer	*peer;		/* Remote endpoint */
+	struct key		*key;		/* Security details */
+	bool			exclusive;	/* T if conn is exclusive */
+	u16			service_id;	/* Service ID for this connection */
+	u32			security_level;	/* Security level selected */
 };
 
 /*
  * RxRPC connection definition
- * - matched by { transport, service_id, conn_id, direction, key }
+ * - matched by { local, peer, epoch, conn_id, direction }
  * - each connection can only handle four simultaneous calls
  */
 struct rxrpc_connection {
-	struct rxrpc_transport	*trans;		/* transport session */
-	struct rxrpc_conn_bundle *bundle;	/* connection bundle (client) */
+	struct rxrpc_conn_proto	proto;
+	struct rxrpc_conn_parameters params;
+
+	spinlock_t		channel_lock;
+	struct rxrpc_call	*channels[RXRPC_MAXCALLS]; /* active calls */
+	wait_queue_head_t	channel_wq;	/* queue to wait for channel to become available */
+
 	struct work_struct	processor;	/* connection event processor */
-	struct rb_node		node;		/* node in transport's lookup tree */
+	union {
+		struct rb_node	client_node;	/* Node in local->client_conns */
+		struct rb_node	service_node;	/* Node in peer->service_conns */
+	};
 	struct list_head	link;		/* link in master connection list */
-	struct list_head	bundle_link;	/* link in bundle */
 	struct rb_root		calls;		/* calls on this connection */
 	struct sk_buff_head	rx_queue;	/* received conn-level packets */
-	struct rxrpc_call	*channels[RXRPC_MAXCALLS]; /* channels (active calls) */
 	const struct rxrpc_security *security;	/* applied security module */
-	struct key		*key;		/* security for this connection (client) */
 	struct key		*server_key;	/* security for this service */
 	struct crypto_skcipher	*cipher;	/* encryption handle */
 	struct rxrpc_crypt	csum_iv;	/* packet checksum base */
+	unsigned long		flags;
+#define RXRPC_CONN_HAS_IDR	0		/* - Has a client conn ID assigned */
 	unsigned long		events;
 #define RXRPC_CONN_CHALLENGE	0		/* send challenge packet */
-	unsigned long		put_time;	/* time at which to reap */
+	unsigned long		put_time;	/* Time at which last put */
 	rwlock_t		lock;		/* access lock */
 	spinlock_t		state_lock;	/* state-change lock */
 	atomic_t		usage;
@@ -301,17 +305,12 @@ struct rxrpc_connection {
 	unsigned int		call_counter;	/* call ID counter */
 	atomic_t		serial;		/* packet serial number counter */
 	atomic_t		hi_serial;	/* highest serial number received */
-	u8			avail_calls;	/* number of calls available */
+	atomic_t		avail_chans;	/* number of channels available */
 	u8			size_align;	/* data size alignment (for security) */
 	u8			header_size;	/* rxrpc + security header size */
 	u8			security_size;	/* security header size */
-	u32			security_level;	/* security level negotiated */
 	u32			security_nonce;	/* response re-use preventer */
-	u32			epoch;		/* epoch of this connection */
-	u32			cid;		/* connection ID */
-	u16			service_id;	/* service ID for this connection */
 	u8			security_ix;	/* security type */
-	u8			in_clientflag;	/* RXRPC_CLIENT_INITIATED if we are server */
 	u8			out_clientflag;	/* RXRPC_CLIENT_INITIATED if we are client */
 };
 
@@ -357,6 +356,8 @@ enum rxrpc_call_event {
  * The states that a call can be in.
  */
 enum rxrpc_call_state {
+	RXRPC_CALL_UNINITIALISED,
+	RXRPC_CALL_CLIENT_AWAIT_CONN,	/* - client waiting for connection to become available */
 	RXRPC_CALL_CLIENT_SEND_REQUEST,	/* - client sending request phase */
 	RXRPC_CALL_CLIENT_AWAIT_REPLY,	/* - client awaiting reply */
 	RXRPC_CALL_CLIENT_RECV_REPLY,	/* - client receiving reply phase */
@@ -390,7 +391,7 @@ struct rxrpc_call {
 	struct work_struct	destroyer;	/* call destroyer */
 	struct work_struct	processor;	/* packet processor and ACK generator */
 	struct list_head	link;		/* link in master call list */
-	struct list_head	error_link;	/* link in error distribution list */
+	struct hlist_node	error_link;	/* link in error distribution list */
 	struct list_head	accept_link;	/* calls awaiting acceptance */
 	struct rb_node		sock_node;	/* node in socket call tree */
 	struct rb_node		conn_node;	/* node in connection call tree */
@@ -408,7 +409,8 @@ struct rxrpc_call {
 	atomic_t		sequence;	/* Tx data packet sequence counter */
 	u32			local_abort;	/* local abort code */
 	u32			remote_abort;	/* remote abort code */
-	int			error;		/* local error incurred */
+	int			error_report;	/* Network error (ICMP/local transport) */
+	int			error;		/* Local error incurred */
 	enum rxrpc_call_state	state : 8;	/* current state of call */
 	int			debug_id;	/* debug ID for printks */
 	u8			channel;	/* connection channel occupied by this call */
@@ -444,7 +446,7 @@ struct rxrpc_call {
 	unsigned long		hash_key;	/* Full hash key */
 	u8			in_clientflag;	/* Copy of conn->in_clientflag for hashing */
 	struct rxrpc_local	*local;		/* Local endpoint. Used for hashing. */
-	sa_family_t		proto;		/* Frame protocol */
+	sa_family_t		family;		/* Frame protocol */
 	u32			call_id;	/* call ID on connection  */
 	u32			cid;		/* connection ID plus channel index */
 	u32			epoch;		/* epoch of this connection */
@@ -478,21 +480,21 @@ extern atomic_t rxrpc_debug_id;
 extern struct workqueue_struct *rxrpc_workqueue;
 
 /*
- * ar-accept.c
+ * call_accept.c
  */
-void rxrpc_accept_incoming_calls(struct work_struct *);
+void rxrpc_accept_incoming_calls(struct rxrpc_local *);
 struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long);
 int rxrpc_reject_call(struct rxrpc_sock *);
 
 /*
- * ar-ack.c
+ * call_event.c
  */
 void __rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool);
 void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool);
 void rxrpc_process_call(struct work_struct *);
 
 /*
- * ar-call.c
+ * call_object.c
  */
 extern unsigned int rxrpc_max_call_lifetime;
 extern unsigned int rxrpc_dead_call_expiry;
@@ -502,70 +504,82 @@ extern rwlock_t rxrpc_call_lock;
 
 struct rxrpc_call *rxrpc_find_call_hash(struct rxrpc_host_header *,
 					void *, sa_family_t, const void *);
-struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *,
-					 struct rxrpc_transport *,
-					 struct rxrpc_conn_bundle *,
-					 unsigned long, int, gfp_t);
+struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long);
+struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *,
+					 struct rxrpc_conn_parameters *,
+					 struct sockaddr_rxrpc *,
+					 unsigned long, gfp_t);
 struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *,
 				       struct rxrpc_connection *,
-				       struct rxrpc_host_header *);
-struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *, unsigned long);
+				       struct sk_buff *);
 void rxrpc_release_call(struct rxrpc_call *);
 void rxrpc_release_calls_on_socket(struct rxrpc_sock *);
 void __rxrpc_put_call(struct rxrpc_call *);
 void __exit rxrpc_destroy_all_calls(void);
 
 /*
- * ar-connection.c
+ * conn_client.c
  */
-extern unsigned int rxrpc_connection_expiry;
-extern struct list_head rxrpc_connections;
-extern rwlock_t rxrpc_connection_lock;
+extern struct idr rxrpc_client_conn_ids;
 
-struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *,
-					   struct rxrpc_transport *,
-					   struct key *, u16, gfp_t);
-void rxrpc_put_bundle(struct rxrpc_transport *, struct rxrpc_conn_bundle *);
-int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_transport *,
-		       struct rxrpc_conn_bundle *, struct rxrpc_call *, gfp_t);
-void rxrpc_put_connection(struct rxrpc_connection *);
-void __exit rxrpc_destroy_all_connections(void);
-struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_transport *,
-					       struct rxrpc_host_header *);
-extern struct rxrpc_connection *
-rxrpc_incoming_connection(struct rxrpc_transport *, struct rxrpc_host_header *);
+int rxrpc_get_client_connection_id(struct rxrpc_connection *, gfp_t);
+void rxrpc_put_client_connection_id(struct rxrpc_connection *);
 
 /*
- * ar-connevent.c
+ * conn_event.c
  */
 void rxrpc_process_connection(struct work_struct *);
 void rxrpc_reject_packet(struct rxrpc_local *, struct sk_buff *);
-void rxrpc_reject_packets(struct work_struct *);
+void rxrpc_reject_packets(struct rxrpc_local *);
 
 /*
- * ar-error.c
+ * conn_object.c
  */
-void rxrpc_UDP_error_report(struct sock *);
-void rxrpc_UDP_error_handler(struct work_struct *);
+extern unsigned int rxrpc_connection_expiry;
+extern struct list_head rxrpc_connections;
+extern rwlock_t rxrpc_connection_lock;
+
+int rxrpc_connect_call(struct rxrpc_call *, struct rxrpc_conn_parameters *,
+		       struct sockaddr_rxrpc *, gfp_t);
+struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_local *,
+					       struct rxrpc_peer *,
+					       struct sk_buff *);
+void rxrpc_disconnect_call(struct rxrpc_call *);
+void rxrpc_put_connection(struct rxrpc_connection *);
+void __exit rxrpc_destroy_all_connections(void);
+struct rxrpc_connection *rxrpc_incoming_connection(struct rxrpc_local *,
+						   struct rxrpc_peer *,
+						   struct sk_buff *);
+
+static inline bool rxrpc_conn_is_client(const struct rxrpc_connection *conn)
+{
+	return conn->out_clientflag;
+}
+
+static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn)
+{
+	return conn->proto.in_clientflag;
+}
+
+static inline void rxrpc_get_connection(struct rxrpc_connection *conn)
+{
+	atomic_inc(&conn->usage);
+}
 
 /*
- * ar-input.c
+ * input.c
  */
 void rxrpc_data_ready(struct sock *);
 int rxrpc_queue_rcv_skb(struct rxrpc_call *, struct sk_buff *, bool, bool);
 void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *);
 
 /*
- * ar-local.c
+ * insecure.c
  */
-extern rwlock_t rxrpc_local_lock;
-
-struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *);
-void rxrpc_put_local(struct rxrpc_local *);
-void __exit rxrpc_destroy_all_locals(void);
+extern const struct rxrpc_security rxrpc_no_security;
 
 /*
- * ar-key.c
+ * key.c
  */
 extern struct key_type key_type_rxrpc;
 extern struct key_type key_type_rxrpc_s;
@@ -576,80 +590,103 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t,
 			      u32);
 
 /*
- * ar-output.c
+ * local_event.c
  */
-extern unsigned int rxrpc_resend_timeout;
-
-int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *);
-int rxrpc_client_sendmsg(struct rxrpc_sock *, struct rxrpc_transport *,
-			 struct msghdr *, size_t);
-int rxrpc_server_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
+extern void rxrpc_process_local_events(struct rxrpc_local *);
 
 /*
- * ar-peer.c
+ * local_object.c
  */
-struct rxrpc_peer *rxrpc_get_peer(struct sockaddr_rxrpc *, gfp_t);
-void rxrpc_put_peer(struct rxrpc_peer *);
-struct rxrpc_peer *rxrpc_find_peer(struct rxrpc_local *, __be32, __be16);
-void __exit rxrpc_destroy_all_peers(void);
+struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *);
+void __rxrpc_put_local(struct rxrpc_local *);
+void __exit rxrpc_destroy_all_locals(void);
 
-/*
- * ar-proc.c
- */
-extern const char *const rxrpc_call_states[];
-extern const struct file_operations rxrpc_call_seq_fops;
-extern const struct file_operations rxrpc_connection_seq_fops;
+static inline void rxrpc_get_local(struct rxrpc_local *local)
+{
+	atomic_inc(&local->usage);
+}
+
+static inline
+struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
+{
+	return atomic_inc_not_zero(&local->usage) ? local : NULL;
+}
+
+static inline void rxrpc_put_local(struct rxrpc_local *local)
+{
+	if (local && atomic_dec_and_test(&local->usage))
+		__rxrpc_put_local(local);
+}
 
 /*
- * ar-recvmsg.c
+ * misc.c
  */
-void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *);
-int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
+extern unsigned int rxrpc_max_backlog __read_mostly;
+extern unsigned int rxrpc_requested_ack_delay;
+extern unsigned int rxrpc_soft_ack_delay;
+extern unsigned int rxrpc_idle_ack_delay;
+extern unsigned int rxrpc_rx_window_size;
+extern unsigned int rxrpc_rx_mtu;
+extern unsigned int rxrpc_rx_jumbo_max;
+
+extern const char *const rxrpc_pkts[];
+extern const s8 rxrpc_ack_priority[];
+
+extern const char *rxrpc_acks(u8 reason);
 
 /*
- * ar-security.c
+ * output.c
  */
-int __init rxrpc_init_security(void);
-void rxrpc_exit_security(void);
-int rxrpc_init_client_conn_security(struct rxrpc_connection *);
-int rxrpc_init_server_conn_security(struct rxrpc_connection *);
+extern unsigned int rxrpc_resend_timeout;
+
+int rxrpc_send_data_packet(struct rxrpc_connection *, struct sk_buff *);
+int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
 
 /*
- * ar-skbuff.c
+ * peer_event.c
  */
-void rxrpc_packet_destructor(struct sk_buff *);
+void rxrpc_error_report(struct sock *);
+void rxrpc_peer_error_distributor(struct work_struct *);
 
 /*
- * ar-transport.c
+ * peer_object.c
  */
-extern unsigned int rxrpc_transport_expiry;
+struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *,
+					 const struct sockaddr_rxrpc *);
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *,
+				     struct sockaddr_rxrpc *, gfp_t);
+struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t);
+
+static inline void rxrpc_get_peer(struct rxrpc_peer *peer)
+{
+	atomic_inc(&peer->usage);
+}
+
+static inline
+struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
+{
+	return atomic_inc_not_zero(&peer->usage) ? peer : NULL;
+}
 
-struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *,
-					    struct rxrpc_peer *, gfp_t);
-void rxrpc_put_transport(struct rxrpc_transport *);
-void __exit rxrpc_destroy_all_transports(void);
-struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *,
-					     struct rxrpc_peer *);
+extern void __rxrpc_put_peer(struct rxrpc_peer *peer);
+static inline void rxrpc_put_peer(struct rxrpc_peer *peer)
+{
+	if (peer && atomic_dec_and_test(&peer->usage))
+		__rxrpc_put_peer(peer);
+}
 
 /*
- * insecure.c
+ * proc.c
  */
-extern const struct rxrpc_security rxrpc_no_security;
+extern const char *const rxrpc_call_states[];
+extern const struct file_operations rxrpc_call_seq_fops;
+extern const struct file_operations rxrpc_connection_seq_fops;
 
 /*
- * misc.c
+ * recvmsg.c
  */
-extern unsigned int rxrpc_requested_ack_delay;
-extern unsigned int rxrpc_soft_ack_delay;
-extern unsigned int rxrpc_idle_ack_delay;
-extern unsigned int rxrpc_rx_window_size;
-extern unsigned int rxrpc_rx_mtu;
-extern unsigned int rxrpc_rx_jumbo_max;
-
-extern const char *const rxrpc_pkts[];
-extern const s8 rxrpc_ack_priority[];
-
-extern const char *rxrpc_acks(u8 reason);
+void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *);
+int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
 
 /*
  * rxkad.c
@@ -659,6 +696,19 @@ extern const struct rxrpc_security rxkad;
 #endif
 
 /*
+ * security.c
+ */
+int __init rxrpc_init_security(void);
+void rxrpc_exit_security(void);
+int rxrpc_init_client_conn_security(struct rxrpc_connection *);
+int rxrpc_init_server_conn_security(struct rxrpc_connection *);
+
+/*
+ * skbuff.c
+ */
+void rxrpc_packet_destructor(struct sk_buff *);
+
+/*
  * sysctl.c
  */
 #ifdef CONFIG_SYSCTL
@@ -670,6 +720,12 @@ static inline void rxrpc_sysctl_exit(void) {}
 #endif
 
 /*
+ * utils.c
+ */
+void rxrpc_get_addr_from_skb(struct rxrpc_local *, const struct sk_buff *,
+			     struct sockaddr_rxrpc *);
+
+/*
  * debug tracing
  */
 extern unsigned int rxrpc_debug;
@@ -838,15 +894,6 @@ static inline void rxrpc_purge_queue(struct sk_buff_head *list)
 		rxrpc_free_skb(skb);
 }
 
-static inline void __rxrpc_get_local(struct rxrpc_local *local, const char *f)
-{
-	CHECK_SLAB_OKAY(&local->usage);
-	if (atomic_inc_return(&local->usage) == 1)
-		printk("resurrected (%s)\n", f);
-}
-
-#define rxrpc_get_local(LOCAL) __rxrpc_get_local((LOCAL), __func__)
-
 #define rxrpc_get_call(CALL)				\
 do {							\
 	CHECK_SLAB_OKAY(&(CALL)->usage);		\
diff --git a/net/rxrpc/ar-local.c b/net/rxrpc/ar-local.c
deleted file mode 100644
index 701c42b7050e..000000000000
--- a/net/rxrpc/ar-local.c
+++ /dev/null
@@ -1,417 +0,0 @@
-/* AF_RXRPC local endpoint management
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells ([email protected])
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/net.h>
-#include <linux/skbuff.h>
-#include <linux/slab.h>
-#include <linux/udp.h>
-#include <linux/ip.h>
-#include <net/sock.h>
-#include <net/af_rxrpc.h>
-#include <generated/utsrelease.h>
-#include "ar-internal.h"
-
-static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC";
-
-static LIST_HEAD(rxrpc_locals);
-DEFINE_RWLOCK(rxrpc_local_lock);
-static DECLARE_RWSEM(rxrpc_local_sem);
-static DECLARE_WAIT_QUEUE_HEAD(rxrpc_local_wq);
-
-static void rxrpc_destroy_local(struct work_struct *work);
-static void rxrpc_process_local_events(struct work_struct *work);
-
-/*
- * allocate a new local
- */
-static
-struct rxrpc_local *rxrpc_alloc_local(struct sockaddr_rxrpc *srx)
-{
-	struct rxrpc_local *local;
-
-	local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
-	if (local) {
-		INIT_WORK(&local->destroyer, &rxrpc_destroy_local);
-		INIT_WORK(&local->acceptor, &rxrpc_accept_incoming_calls);
-		INIT_WORK(&local->rejecter, &rxrpc_reject_packets);
-		INIT_WORK(&local->event_processor, &rxrpc_process_local_events);
-		INIT_LIST_HEAD(&local->services);
-		INIT_LIST_HEAD(&local->link);
-		init_rwsem(&local->defrag_sem);
-		skb_queue_head_init(&local->accept_queue);
-		skb_queue_head_init(&local->reject_queue);
-		skb_queue_head_init(&local->event_queue);
-		spin_lock_init(&local->lock);
-		rwlock_init(&local->services_lock);
-		atomic_set(&local->usage, 1);
-		local->debug_id = atomic_inc_return(&rxrpc_debug_id);
-		memcpy(&local->srx, srx, sizeof(*srx));
-	}
-
-	_leave(" = %p", local);
-	return local;
-}
-
-/*
- * create the local socket
- * - must be called with rxrpc_local_sem writelocked
- */
-static int rxrpc_create_local(struct rxrpc_local *local)
-{
-	struct sock *sock;
-	int ret, opt;
-
-	_enter("%p{%d}", local, local->srx.transport_type);
-
-	/* create a socket to represent the local endpoint */
-	ret = sock_create_kern(&init_net, PF_INET, local->srx.transport_type,
-			       IPPROTO_UDP, &local->socket);
-	if (ret < 0) {
-		_leave(" = %d [socket]", ret);
-		return ret;
-	}
-
-	/* if a local address was supplied then bind it */
-	if (local->srx.transport_len > sizeof(sa_family_t)) {
-		_debug("bind");
-		ret = kernel_bind(local->socket,
-				  (struct sockaddr *) &local->srx.transport,
-				  local->srx.transport_len);
-		if (ret < 0) {
-			_debug("bind failed");
-			goto error;
-		}
-	}
-
-	/* we want to receive ICMP errors */
-	opt = 1;
-	ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
-				(char *) &opt, sizeof(opt));
-	if (ret < 0) {
-		_debug("setsockopt failed");
-		goto error;
-	}
-
-	/* we want to set the don't fragment bit */
-	opt = IP_PMTUDISC_DO;
-	ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
-				(char *) &opt, sizeof(opt));
-	if (ret < 0) {
-		_debug("setsockopt failed");
-		goto error;
-	}
-
-	write_lock_bh(&rxrpc_local_lock);
-	list_add(&local->link, &rxrpc_locals);
-	write_unlock_bh(&rxrpc_local_lock);
-
-	/* set the socket up */
-	sock = local->socket->sk;
-	sock->sk_user_data	= local;
-	sock->sk_data_ready	= rxrpc_data_ready;
-	sock->sk_error_report	= rxrpc_UDP_error_report;
-	_leave(" = 0");
-	return 0;
-
-error:
-	kernel_sock_shutdown(local->socket, SHUT_RDWR);
-	local->socket->sk->sk_user_data = NULL;
-	sock_release(local->socket);
-	local->socket = NULL;
-
-	_leave(" = %d", ret);
-	return ret;
-}
-
-/*
- * create a new local endpoint using the specified UDP address
- */
-struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *srx)
-{
-	struct rxrpc_local *local;
-	int ret;
-
-	_enter("{%d,%u,%pI4+%hu}",
-	       srx->transport_type,
-	       srx->transport.family,
-	       &srx->transport.sin.sin_addr,
-	       ntohs(srx->transport.sin.sin_port));
-
-	down_write(&rxrpc_local_sem);
-
-	/* see if we have a suitable local local endpoint already */
-	read_lock_bh(&rxrpc_local_lock);
-
-	list_for_each_entry(local, &rxrpc_locals, link) {
-		_debug("CMP {%d,%u,%pI4+%hu}",
-		       local->srx.transport_type,
-		       local->srx.transport.family,
-		       &local->srx.transport.sin.sin_addr,
-		       ntohs(local->srx.transport.sin.sin_port));
-
-		if (local->srx.transport_type != srx->transport_type ||
-		    local->srx.transport.family != srx->transport.family)
-			continue;
-
-		switch (srx->transport.family) {
-		case AF_INET:
-			if (local->srx.transport.sin.sin_port !=
-			    srx->transport.sin.sin_port)
-				continue;
-			if (memcmp(&local->srx.transport.sin.sin_addr,
-				   &srx->transport.sin.sin_addr,
-				   sizeof(struct in_addr)) != 0)
-				continue;
-			goto found_local;
-
-		default:
-			BUG();
-		}
-	}
-
-	read_unlock_bh(&rxrpc_local_lock);
-
-	/* we didn't find one, so we need to create one */
-	local = rxrpc_alloc_local(srx);
-	if (!local) {
-		up_write(&rxrpc_local_sem);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	ret = rxrpc_create_local(local);
-	if (ret < 0) {
-		up_write(&rxrpc_local_sem);
-		kfree(local);
-		_leave(" = %d", ret);
-		return ERR_PTR(ret);
-	}
-
-	up_write(&rxrpc_local_sem);
-
-	_net("LOCAL new %d {%d,%u,%pI4+%hu}",
-	     local->debug_id,
-	     local->srx.transport_type,
-	     local->srx.transport.family,
-	     &local->srx.transport.sin.sin_addr,
-	     ntohs(local->srx.transport.sin.sin_port));
-
-	_leave(" = %p [new]", local);
-	return local;
-
-found_local:
-	rxrpc_get_local(local);
-	read_unlock_bh(&rxrpc_local_lock);
-	up_write(&rxrpc_local_sem);
-
-	_net("LOCAL old %d {%d,%u,%pI4+%hu}",
-	     local->debug_id,
-	     local->srx.transport_type,
-	     local->srx.transport.family,
-	     &local->srx.transport.sin.sin_addr,
-	     ntohs(local->srx.transport.sin.sin_port));
-
-	_leave(" = %p [reuse]", local);
-	return local;
-}
-
-/*
- * release a local endpoint
- */
-void rxrpc_put_local(struct rxrpc_local *local)
-{
-	_enter("%p{u=%d}", local, atomic_read(&local->usage));
-
-	ASSERTCMP(atomic_read(&local->usage), >, 0);
-
-	/* to prevent a race, the decrement and the dequeue must be effectively
-	 * atomic */
-	write_lock_bh(&rxrpc_local_lock);
-	if (unlikely(atomic_dec_and_test(&local->usage))) {
-		_debug("destroy local");
-		rxrpc_queue_work(&local->destroyer);
-	}
-	write_unlock_bh(&rxrpc_local_lock);
-	_leave("");
-}
-
-/*
- * destroy a local endpoint
- */
-static void rxrpc_destroy_local(struct work_struct *work)
-{
-	struct rxrpc_local *local =
-		container_of(work, struct rxrpc_local, destroyer);
-
-	_enter("%p{%d}", local, atomic_read(&local->usage));
-
-	down_write(&rxrpc_local_sem);
-
-	write_lock_bh(&rxrpc_local_lock);
-	if (atomic_read(&local->usage) > 0) {
-		write_unlock_bh(&rxrpc_local_lock);
-		up_read(&rxrpc_local_sem);
-		_leave(" [resurrected]");
-		return;
-	}
-
-	list_del(&local->link);
-	local->socket->sk->sk_user_data = NULL;
-	write_unlock_bh(&rxrpc_local_lock);
-
-	downgrade_write(&rxrpc_local_sem);
-
-	ASSERT(list_empty(&local->services));
-	ASSERT(!work_pending(&local->acceptor));
-	ASSERT(!work_pending(&local->rejecter));
-	ASSERT(!work_pending(&local->event_processor));
-
-	/* finish cleaning up the local descriptor */
-	rxrpc_purge_queue(&local->accept_queue);
-	rxrpc_purge_queue(&local->reject_queue);
-	rxrpc_purge_queue(&local->event_queue);
-	kernel_sock_shutdown(local->socket, SHUT_RDWR);
-	sock_release(local->socket);
-
-	up_read(&rxrpc_local_sem);
-
-	_net("DESTROY LOCAL %d", local->debug_id);
-	kfree(local);
-
-	if (list_empty(&rxrpc_locals))
-		wake_up_all(&rxrpc_local_wq);
-
-	_leave("");
-}
-
-/*
- * preemptively destroy all local local endpoint rather than waiting for
- * them to be destroyed
- */
-void __exit rxrpc_destroy_all_locals(void)
-{
-	DECLARE_WAITQUEUE(myself,current);
-
-	_enter("");
-
-	/* we simply have to wait for them to go away */
-	if (!list_empty(&rxrpc_locals)) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		add_wait_queue(&rxrpc_local_wq, &myself);
-
-		while (!list_empty(&rxrpc_locals)) {
-			schedule();
-			set_current_state(TASK_UNINTERRUPTIBLE);
-		}
-
-		remove_wait_queue(&rxrpc_local_wq, &myself);
-		set_current_state(TASK_RUNNING);
-	}
-
-	_leave("");
-}
-
-/*
- * Reply to a version request
- */
-static void rxrpc_send_version_request(struct rxrpc_local *local,
-				       struct rxrpc_host_header *hdr,
-				       struct sk_buff *skb)
-{
-	struct rxrpc_wire_header whdr;
-	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-	struct sockaddr_in sin;
-	struct msghdr msg;
-	struct kvec iov[2];
-	size_t len;
-	int ret;
-
-	_enter("");
-
-	sin.sin_family = AF_INET;
-	sin.sin_port = udp_hdr(skb)->source;
-	sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
-
-	msg.msg_name	= &sin;
-	msg.msg_namelen	= sizeof(sin);
-	msg.msg_control	= NULL;
-	msg.msg_controllen = 0;
-	msg.msg_flags	= 0;
-
-	whdr.epoch	= htonl(sp->hdr.epoch);
-	whdr.cid	= htonl(sp->hdr.cid);
-	whdr.callNumber	= htonl(sp->hdr.callNumber);
-	whdr.seq	= 0;
-	whdr.serial	= 0;
-	whdr.type	= RXRPC_PACKET_TYPE_VERSION;
-	whdr.flags	= RXRPC_LAST_PACKET | (~hdr->flags & RXRPC_CLIENT_INITIATED);
-	whdr.userStatus	= 0;
-	whdr.securityIndex = 0;
-	whdr._rsvd	= 0;
-	whdr.serviceId	= htons(sp->hdr.serviceId);
-
-	iov[0].iov_base	= &whdr;
-	iov[0].iov_len	= sizeof(whdr);
-	iov[1].iov_base	= (char *)rxrpc_version_string;
-	iov[1].iov_len	= sizeof(rxrpc_version_string);
-
-	len = iov[0].iov_len + iov[1].iov_len;
-
-	_proto("Tx VERSION (reply)");
-
-	ret = kernel_sendmsg(local->socket, &msg, iov, 2, len);
-	if (ret < 0)
-		_debug("sendmsg failed: %d", ret);
-
-	_leave("");
-}
-
-/*
- * Process event packets targetted at a local endpoint.
- */
-static void rxrpc_process_local_events(struct work_struct *work)
-{
-	struct rxrpc_local *local = container_of(work, struct rxrpc_local, event_processor);
-	struct sk_buff *skb;
-	char v;
-
-	_enter("");
-
-	atomic_inc(&local->usage);
-	
-	while ((skb = skb_dequeue(&local->event_queue))) {
-		struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-
-		_debug("{%d},{%u}", local->debug_id, sp->hdr.type);
-
-		switch (sp->hdr.type) {
-		case RXRPC_PACKET_TYPE_VERSION:
-			if (skb_copy_bits(skb, 0, &v, 1) < 0)
-				return;
-			_proto("Rx VERSION { %02x }", v);
-			if (v == 0)
-				rxrpc_send_version_request(local, &sp->hdr, skb);
-			break;
-
-		default:
-			/* Just ignore anything we don't understand */
-			break;
-		}
-
-		rxrpc_put_local(local);
-		rxrpc_free_skb(skb);
-	}
-
-	rxrpc_put_local(local);
-	_leave("");
-}
diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c
deleted file mode 100644
index 0b54cda3d8e5..000000000000
--- a/net/rxrpc/ar-peer.c
+++ /dev/null
@@ -1,305 +0,0 @@
-/* RxRPC remote transport endpoint management
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells ([email protected])
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/net.h>
-#include <linux/skbuff.h>
-#include <linux/udp.h>
-#include <linux/in.h>
-#include <linux/in6.h>
-#include <linux/icmp.h>
-#include <linux/slab.h>
-#include <net/sock.h>
-#include <net/af_rxrpc.h>
-#include <net/ip.h>
-#include <net/route.h>
-#include "ar-internal.h"
-
-static LIST_HEAD(rxrpc_peers);
-static DEFINE_RWLOCK(rxrpc_peer_lock);
-static DECLARE_WAIT_QUEUE_HEAD(rxrpc_peer_wq);
-
-static void rxrpc_destroy_peer(struct work_struct *work);
-
-/*
- * assess the MTU size for the network interface through which this peer is
- * reached
- */
-static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
-{
-	struct rtable *rt;
-	struct flowi4 fl4;
-
-	peer->if_mtu = 1500;
-
-	rt = ip_route_output_ports(&init_net, &fl4, NULL,
-				   peer->srx.transport.sin.sin_addr.s_addr, 0,
-				   htons(7000), htons(7001),
-				   IPPROTO_UDP, 0, 0);
-	if (IS_ERR(rt)) {
-		_leave(" [route err %ld]", PTR_ERR(rt));
-		return;
-	}
-
-	peer->if_mtu = dst_mtu(&rt->dst);
-	dst_release(&rt->dst);
-
-	_leave(" [if_mtu %u]", peer->if_mtu);
-}
-
-/*
- * allocate a new peer
- */
-static struct rxrpc_peer *rxrpc_alloc_peer(struct sockaddr_rxrpc *srx,
-					   gfp_t gfp)
-{
-	struct rxrpc_peer *peer;
-
-	_enter("");
-
-	peer = kzalloc(sizeof(struct rxrpc_peer), gfp);
-	if (peer) {
-		INIT_WORK(&peer->destroyer, &rxrpc_destroy_peer);
-		INIT_LIST_HEAD(&peer->link);
-		INIT_LIST_HEAD(&peer->error_targets);
-		spin_lock_init(&peer->lock);
-		atomic_set(&peer->usage, 1);
-		peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
-		memcpy(&peer->srx, srx, sizeof(*srx));
-
-		rxrpc_assess_MTU_size(peer);
-		peer->mtu = peer->if_mtu;
-
-		if (srx->transport.family == AF_INET) {
-			peer->hdrsize = sizeof(struct iphdr);
-			switch (srx->transport_type) {
-			case SOCK_DGRAM:
-				peer->hdrsize += sizeof(struct udphdr);
-				break;
-			default:
-				BUG();
-				break;
-			}
-		} else {
-			BUG();
-		}
-
-		peer->hdrsize += sizeof(struct rxrpc_wire_header);
-		peer->maxdata = peer->mtu - peer->hdrsize;
-	}
-
-	_leave(" = %p", peer);
-	return peer;
-}
-
-/*
- * obtain a remote transport endpoint for the specified address
- */
-struct rxrpc_peer *rxrpc_get_peer(struct sockaddr_rxrpc *srx, gfp_t gfp)
-{
-	struct rxrpc_peer *peer, *candidate;
-	const char *new = "old";
-	int usage;
-
-	_enter("{%d,%d,%pI4+%hu}",
-	       srx->transport_type,
-	       srx->transport_len,
-	       &srx->transport.sin.sin_addr,
-	       ntohs(srx->transport.sin.sin_port));
-
-	/* search the peer list first */
-	read_lock_bh(&rxrpc_peer_lock);
-	list_for_each_entry(peer, &rxrpc_peers, link) {
-		_debug("check PEER %d { u=%d t=%d l=%d }",
-		       peer->debug_id,
-		       atomic_read(&peer->usage),
-		       peer->srx.transport_type,
-		       peer->srx.transport_len);
-
-		if (atomic_read(&peer->usage) > 0 &&
-		    peer->srx.transport_type == srx->transport_type &&
-		    peer->srx.transport_len == srx->transport_len &&
-		    memcmp(&peer->srx.transport,
-			   &srx->transport,
-			   srx->transport_len) == 0)
-			goto found_extant_peer;
-	}
-	read_unlock_bh(&rxrpc_peer_lock);
-
-	/* not yet present - create a candidate for a new record and then
-	 * redo the search */
-	candidate = rxrpc_alloc_peer(srx, gfp);
-	if (!candidate) {
-		_leave(" = -ENOMEM");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	write_lock_bh(&rxrpc_peer_lock);
-
-	list_for_each_entry(peer, &rxrpc_peers, link) {
-		if (atomic_read(&peer->usage) > 0 &&
-		    peer->srx.transport_type == srx->transport_type &&
-		    peer->srx.transport_len == srx->transport_len &&
-		    memcmp(&peer->srx.transport,
-			   &srx->transport,
-			   srx->transport_len) == 0)
-			goto found_extant_second;
-	}
-
-	/* we can now add the new candidate to the list */
-	peer = candidate;
-	candidate = NULL;
-	usage = atomic_read(&peer->usage);
-
-	list_add_tail(&peer->link, &rxrpc_peers);
-	write_unlock_bh(&rxrpc_peer_lock);
-	new = "new";
-
-success:
-	_net("PEER %s %d {%d,%u,%pI4+%hu}",
-	     new,
-	     peer->debug_id,
-	     peer->srx.transport_type,
-	     peer->srx.transport.family,
-	     &peer->srx.transport.sin.sin_addr,
-	     ntohs(peer->srx.transport.sin.sin_port));
-
-	_leave(" = %p {u=%d}", peer, usage);
-	return peer;
-
-	/* we found the peer in the list immediately */
-found_extant_peer:
-	usage = atomic_inc_return(&peer->usage);
-	read_unlock_bh(&rxrpc_peer_lock);
-	goto success;
-
-	/* we found the peer on the second time through the list */
-found_extant_second:
-	usage = atomic_inc_return(&peer->usage);
-	write_unlock_bh(&rxrpc_peer_lock);
-	kfree(candidate);
-	goto success;
-}
-
-/*
- * find the peer associated with a packet
- */
-struct rxrpc_peer *rxrpc_find_peer(struct rxrpc_local *local,
-				   __be32 addr, __be16 port)
-{
-	struct rxrpc_peer *peer;
-
-	_enter("");
-
-	/* search the peer list */
-	read_lock_bh(&rxrpc_peer_lock);
-
-	if (local->srx.transport.family == AF_INET &&
-	    local->srx.transport_type == SOCK_DGRAM
-	    ) {
-		list_for_each_entry(peer, &rxrpc_peers, link) {
-			if (atomic_read(&peer->usage) > 0 &&
-			    peer->srx.transport_type == SOCK_DGRAM &&
-			    peer->srx.transport.family == AF_INET &&
-			    peer->srx.transport.sin.sin_port == port &&
-			    peer->srx.transport.sin.sin_addr.s_addr == addr)
-				goto found_UDP_peer;
-		}
-
-		goto new_UDP_peer;
-	}
-
-	read_unlock_bh(&rxrpc_peer_lock);
-	_leave(" = -EAFNOSUPPORT");
-	return ERR_PTR(-EAFNOSUPPORT);
-
-found_UDP_peer:
-	_net("Rx UDP DGRAM from peer %d", peer->debug_id);
-	atomic_inc(&peer->usage);
-	read_unlock_bh(&rxrpc_peer_lock);
-	_leave(" = %p", peer);
-	return peer;
-
-new_UDP_peer:
-	_net("Rx UDP DGRAM from NEW peer");
-	read_unlock_bh(&rxrpc_peer_lock);
-	_leave(" = -EBUSY [new]");
-	return ERR_PTR(-EBUSY);
-}
-
-/*
- * release a remote transport endpoint
- */
-void rxrpc_put_peer(struct rxrpc_peer *peer)
-{
-	_enter("%p{u=%d}", peer, atomic_read(&peer->usage));
-
-	ASSERTCMP(atomic_read(&peer->usage), >, 0);
-
-	if (likely(!atomic_dec_and_test(&peer->usage))) {
-		_leave(" [in use]");
-		return;
-	}
-
-	rxrpc_queue_work(&peer->destroyer);
-	_leave("");
-}
-
-/*
- * destroy a remote transport endpoint
- */
-static void rxrpc_destroy_peer(struct work_struct *work)
-{
-	struct rxrpc_peer *peer =
-		container_of(work, struct rxrpc_peer, destroyer);
-
-	_enter("%p{%d}", peer, atomic_read(&peer->usage));
-
-	write_lock_bh(&rxrpc_peer_lock);
-	list_del(&peer->link);
-	write_unlock_bh(&rxrpc_peer_lock);
-
-	_net("DESTROY PEER %d", peer->debug_id);
-	kfree(peer);
-
-	if (list_empty(&rxrpc_peers))
-		wake_up_all(&rxrpc_peer_wq);
-	_leave("");
-}
-
-/*
- * preemptively destroy all the peer records from a transport endpoint rather
- * than waiting for them to time out
- */
-void __exit rxrpc_destroy_all_peers(void)
-{
-	DECLARE_WAITQUEUE(myself,current);
-
-	_enter("");
-
-	/* we simply have to wait for them to go away */
-	if (!list_empty(&rxrpc_peers)) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		add_wait_queue(&rxrpc_peer_wq, &myself);
-
-		while (!list_empty(&rxrpc_peers)) {
-			schedule();
-			set_current_state(TASK_UNINTERRUPTIBLE);
-		}
-
-		remove_wait_queue(&rxrpc_peer_wq, &myself);
-		set_current_state(TASK_RUNNING);
-	}
-
-	_leave("");
-}
diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/ar-transport.c
deleted file mode 100644
index a1b65183b07d..000000000000
--- a/net/rxrpc/ar-transport.c
+++ /dev/null
@@ -1,286 +0,0 @@
-/* RxRPC point-to-point transport session management
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells ([email protected])
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/net.h>
-#include <linux/skbuff.h>
-#include <linux/slab.h>
-#include <net/sock.h>
-#include <net/af_rxrpc.h>
-#include "ar-internal.h"
-
-/*
- * Time after last use at which transport record is cleaned up.
- */
-unsigned int rxrpc_transport_expiry = 3600 * 24;
-
-static void rxrpc_transport_reaper(struct work_struct *work);
-
-static LIST_HEAD(rxrpc_transports);
-static DEFINE_RWLOCK(rxrpc_transport_lock);
-static DECLARE_DELAYED_WORK(rxrpc_transport_reap, rxrpc_transport_reaper);
-
-/*
- * allocate a new transport session manager
- */
-static struct rxrpc_transport *rxrpc_alloc_transport(struct rxrpc_local *local,
-						     struct rxrpc_peer *peer,
-						     gfp_t gfp)
-{
-	struct rxrpc_transport *trans;
-
-	_enter("");
-
-	trans = kzalloc(sizeof(struct rxrpc_transport), gfp);
-	if (trans) {
-		trans->local = local;
-		trans->peer = peer;
-		INIT_LIST_HEAD(&trans->link);
-		trans->bundles = RB_ROOT;
-		trans->client_conns = RB_ROOT;
-		trans->server_conns = RB_ROOT;
-		skb_queue_head_init(&trans->error_queue);
-		spin_lock_init(&trans->client_lock);
-		rwlock_init(&trans->conn_lock);
-		atomic_set(&trans->usage, 1);
-		trans->conn_idcounter = peer->srx.srx_service << 16;
-		trans->debug_id = atomic_inc_return(&rxrpc_debug_id);
-
-		if (peer->srx.transport.family == AF_INET) {
-			switch (peer->srx.transport_type) {
-			case SOCK_DGRAM:
-				INIT_WORK(&trans->error_handler,
-					  rxrpc_UDP_error_handler);
-				break;
-			default:
-				BUG();
-				break;
-			}
-		} else {
-			BUG();
-		}
-	}
-
-	_leave(" = %p", trans);
-	return trans;
-}
-
-/*
- * obtain a transport session for the nominated endpoints
- */
-struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *local,
-					    struct rxrpc_peer *peer,
-					    gfp_t gfp)
-{
-	struct rxrpc_transport *trans, *candidate;
-	const char *new = "old";
-	int usage;
-
-	_enter("{%pI4+%hu},{%pI4+%hu},",
-	       &local->srx.transport.sin.sin_addr,
-	       ntohs(local->srx.transport.sin.sin_port),
-	       &peer->srx.transport.sin.sin_addr,
-	       ntohs(peer->srx.transport.sin.sin_port));
-
-	/* search the transport list first */
-	read_lock_bh(&rxrpc_transport_lock);
-	list_for_each_entry(trans, &rxrpc_transports, link) {
-		if (trans->local == local && trans->peer == peer)
-			goto found_extant_transport;
-	}
-	read_unlock_bh(&rxrpc_transport_lock);
-
-	/* not yet present - create a candidate for a new record and then
-	 * redo the search */
-	candidate = rxrpc_alloc_transport(local, peer, gfp);
-	if (!candidate) {
-		_leave(" = -ENOMEM");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	write_lock_bh(&rxrpc_transport_lock);
-
-	list_for_each_entry(trans, &rxrpc_transports, link) {
-		if (trans->local == local && trans->peer == peer)
-			goto found_extant_second;
-	}
-
-	/* we can now add the new candidate to the list */
-	trans = candidate;
-	candidate = NULL;
-	usage = atomic_read(&trans->usage);
-
-	rxrpc_get_local(trans->local);
-	atomic_inc(&trans->peer->usage);
-	list_add_tail(&trans->link, &rxrpc_transports);
-	write_unlock_bh(&rxrpc_transport_lock);
-	new = "new";
-
-success:
-	_net("TRANSPORT %s %d local %d -> peer %d",
-	     new,
-	     trans->debug_id,
-	     trans->local->debug_id,
-	     trans->peer->debug_id);
-
-	_leave(" = %p {u=%d}", trans, usage);
-	return trans;
-
-	/* we found the transport in the list immediately */
-found_extant_transport:
-	usage = atomic_inc_return(&trans->usage);
-	read_unlock_bh(&rxrpc_transport_lock);
-	goto success;
-
-	/* we found the transport on the second time through the list */
-found_extant_second:
-	usage = atomic_inc_return(&trans->usage);
-	write_unlock_bh(&rxrpc_transport_lock);
-	kfree(candidate);
-	goto success;
-}
-
-/*
- * find the transport connecting two endpoints
- */
-struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *local,
-					     struct rxrpc_peer *peer)
-{
-	struct rxrpc_transport *trans;
-
-	_enter("{%pI4+%hu},{%pI4+%hu},",
-	       &local->srx.transport.sin.sin_addr,
-	       ntohs(local->srx.transport.sin.sin_port),
-	       &peer->srx.transport.sin.sin_addr,
-	       ntohs(peer->srx.transport.sin.sin_port));
-
-	/* search the transport list */
-	read_lock_bh(&rxrpc_transport_lock);
-
-	list_for_each_entry(trans, &rxrpc_transports, link) {
-		if (trans->local == local && trans->peer == peer)
-			goto found_extant_transport;
-	}
-
-	read_unlock_bh(&rxrpc_transport_lock);
-	_leave(" = NULL");
-	return NULL;
-
-found_extant_transport:
-	atomic_inc(&trans->usage);
-	read_unlock_bh(&rxrpc_transport_lock);
-	_leave(" = %p", trans);
-	return trans;
-}
-
-/*
- * release a transport session
- */
-void rxrpc_put_transport(struct rxrpc_transport *trans)
-{
-	_enter("%p{u=%d}", trans, atomic_read(&trans->usage));
-
-	ASSERTCMP(atomic_read(&trans->usage), >, 0);
-
-	trans->put_time = ktime_get_seconds();
-	if (unlikely(atomic_dec_and_test(&trans->usage))) {
-		_debug("zombie");
-		/* let the reaper determine the timeout to avoid a race with
-		 * overextending the timeout if the reaper is running at the
-		 * same time */
-		rxrpc_queue_delayed_work(&rxrpc_transport_reap, 0);
-	}
-	_leave("");
-}
-
-/*
- * clean up a transport session
- */
-static void rxrpc_cleanup_transport(struct rxrpc_transport *trans)
-{
-	_net("DESTROY TRANS %d", trans->debug_id);
-
-	rxrpc_purge_queue(&trans->error_queue);
-
-	rxrpc_put_local(trans->local);
-	rxrpc_put_peer(trans->peer);
-	kfree(trans);
-}
-
-/*
- * reap dead transports that have passed their expiry date
- */
-static void rxrpc_transport_reaper(struct work_struct *work)
-{
-	struct rxrpc_transport *trans, *_p;
-	unsigned long now, earliest, reap_time;
-
-	LIST_HEAD(graveyard);
-
-	_enter("");
-
-	now = ktime_get_seconds();
-	earliest = ULONG_MAX;
-
-	/* extract all the transports that have been dead too long */
-	write_lock_bh(&rxrpc_transport_lock);
-	list_for_each_entry_safe(trans, _p, &rxrpc_transports, link) {
-		_debug("reap TRANS %d { u=%d t=%ld }",
-		       trans->debug_id, atomic_read(&trans->usage),
-		       (long) now - (long) trans->put_time);
-
-		if (likely(atomic_read(&trans->usage) > 0))
-			continue;
-
-		reap_time = trans->put_time + rxrpc_transport_expiry;
-		if (reap_time <= now)
-			list_move_tail(&trans->link, &graveyard);
-		else if (reap_time < earliest)
-			earliest = reap_time;
-	}
-	write_unlock_bh(&rxrpc_transport_lock);
-
-	if (earliest != ULONG_MAX) {
-		_debug("reschedule reaper %ld", (long) earliest - now);
-		ASSERTCMP(earliest, >, now);
-		rxrpc_queue_delayed_work(&rxrpc_transport_reap,
-					 (earliest - now) * HZ);
-	}
-
-	/* then destroy all those pulled out */
-	while (!list_empty(&graveyard)) {
-		trans = list_entry(graveyard.next, struct rxrpc_transport,
-				   link);
-		list_del_init(&trans->link);
-
-		ASSERTCMP(atomic_read(&trans->usage), ==, 0);
-		rxrpc_cleanup_transport(trans);
-	}
-
-	_leave("");
-}
-
-/*
- * preemptively destroy all the transport session records rather than waiting
- * for them to time out
- */
-void __exit rxrpc_destroy_all_transports(void)
-{
-	_enter("");
-
-	rxrpc_transport_expiry = 0;
-	cancel_delayed_work(&rxrpc_transport_reap);
-	rxrpc_queue_delayed_work(&rxrpc_transport_reap, 0);
-
-	_leave("");
-}
diff --git a/net/rxrpc/ar-accept.c b/net/rxrpc/call_accept.c
index eea5f4a5d8b1..202e053a3c6d 100644
--- a/net/rxrpc/ar-accept.c
+++ b/net/rxrpc/call_accept.c
@@ -74,7 +74,6 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local,
 				      struct sockaddr_rxrpc *srx)
 {
 	struct rxrpc_connection *conn;
-	struct rxrpc_transport *trans;
 	struct rxrpc_skb_priv *sp, *nsp;
 	struct rxrpc_peer *peer;
 	struct rxrpc_call *call;
@@ -95,30 +94,22 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local,
 	rxrpc_new_skb(notification);
 	notification->mark = RXRPC_SKB_MARK_NEW_CALL;
 
-	peer = rxrpc_get_peer(srx, GFP_NOIO);
-	if (IS_ERR(peer)) {
+	peer = rxrpc_lookup_peer(local, srx, GFP_NOIO);
+	if (!peer) {
 		_debug("no peer");
 		ret = -EBUSY;
 		goto error;
 	}
 
-	trans = rxrpc_get_transport(local, peer, GFP_NOIO);
+	conn = rxrpc_incoming_connection(local, peer, skb);
 	rxrpc_put_peer(peer);
-	if (IS_ERR(trans)) {
-		_debug("no trans");
-		ret = -EBUSY;
-		goto error;
-	}
-
-	conn = rxrpc_incoming_connection(trans, &sp->hdr);
-	rxrpc_put_transport(trans);
 	if (IS_ERR(conn)) {
 		_debug("no conn");
 		ret = PTR_ERR(conn);
 		goto error;
 	}
 
-	call = rxrpc_incoming_call(rx, conn, &sp->hdr);
+	call = rxrpc_incoming_call(rx, conn, skb);
 	rxrpc_put_connection(conn);
 	if (IS_ERR(call)) {
 		_debug("no call");
@@ -141,7 +132,7 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local,
 			_debug("await conn sec");
 			list_add_tail(&call->accept_link, &rx->secureq);
 			call->conn->state = RXRPC_CONN_SERVER_CHALLENGING;
-			atomic_inc(&call->conn->usage);
+			rxrpc_get_connection(call->conn);
 			set_bit(RXRPC_CONN_CHALLENGE, &call->conn->events);
 			rxrpc_queue_conn(call->conn);
 		} else {
@@ -202,10 +193,8 @@ error_nofree:
  * accept incoming calls that need peer, transport and/or connection setting up
  * - the packets we get are all incoming client DATA packets that have seq == 1
  */
-void rxrpc_accept_incoming_calls(struct work_struct *work)
+void rxrpc_accept_incoming_calls(struct rxrpc_local *local)
 {
-	struct rxrpc_local *local =
-		container_of(work, struct rxrpc_local, acceptor);
 	struct rxrpc_skb_priv *sp;
 	struct sockaddr_rxrpc srx;
 	struct rxrpc_sock *rx;
@@ -215,21 +204,8 @@ void rxrpc_accept_incoming_calls(struct work_struct *work)
 
 	_enter("%d", local->debug_id);
 
-	read_lock_bh(&rxrpc_local_lock);
-	if (atomic_read(&local->usage) > 0)
-		rxrpc_get_local(local);
-	else
-		local = NULL;
-	read_unlock_bh(&rxrpc_local_lock);
-	if (!local) {
-		_leave(" [local dead]");
-		return;
-	}
-
-process_next_packet:
 	skb = skb_dequeue(&local->accept_queue);
 	if (!skb) {
-		rxrpc_put_local(local);
 		_leave("\n");
 		return;
 	}
@@ -292,7 +268,7 @@ found_service:
 	case -ECONNRESET: /* old calls are ignored */
 	case -ECONNABORTED: /* aborted calls are reaborted or ignored */
 	case 0:
-		goto process_next_packet;
+		return;
 	case -ECONNREFUSED:
 		goto invalid_service;
 	case -EBUSY:
@@ -308,18 +284,18 @@ backlog_full:
 busy:
 	rxrpc_busy(local, &srx, &whdr);
 	rxrpc_free_skb(skb);
-	goto process_next_packet;
+	return;
 
 invalid_service:
 	skb->priority = RX_INVALID_OPERATION;
 	rxrpc_reject_packet(local, skb);
-	goto process_next_packet;
+	return;
 
 	/* can't change connection security type mid-flow */
 security_mismatch:
 	skb->priority = RX_PROTOCOL_ERROR;
 	rxrpc_reject_packet(local, skb);
-	goto process_next_packet;
+	return;
 }
 
 /*
diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/call_event.c
index 18381783c2b1..0ba84295f913 100644
--- a/net/rxrpc/ar-ack.c
+++ b/net/rxrpc/call_event.c
@@ -187,7 +187,7 @@ static void rxrpc_resend(struct rxrpc_call *call)
 
 			_proto("Tx DATA %%%u { #%d }",
 			       sp->hdr.serial, sp->hdr.seq);
-			if (rxrpc_send_packet(call->conn->trans, txb) < 0) {
+			if (rxrpc_send_data_packet(call->conn, txb) < 0) {
 				stop = true;
 				sp->resend_at = jiffies + 3;
 			} else {
@@ -545,7 +545,7 @@ static void rxrpc_extract_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
 
 	mtu = min(ntohl(ackinfo.rxMTU), ntohl(ackinfo.maxMTU));
 
-	peer = call->conn->trans->peer;
+	peer = call->conn->params.peer;
 	if (mtu < peer->maxdata) {
 		spin_lock_bh(&peer->lock);
 		peer->maxdata = mtu;
@@ -836,13 +836,13 @@ void rxrpc_process_call(struct work_struct *work)
 
 	/* there's a good chance we're going to have to send a message, so set
 	 * one up in advance */
-	msg.msg_name	= &call->conn->trans->peer->srx.transport;
-	msg.msg_namelen	= call->conn->trans->peer->srx.transport_len;
+	msg.msg_name	= &call->conn->params.peer->srx.transport;
+	msg.msg_namelen	= call->conn->params.peer->srx.transport_len;
 	msg.msg_control	= NULL;
 	msg.msg_controllen = 0;
 	msg.msg_flags	= 0;
 
-	whdr.epoch	= htonl(call->conn->epoch);
+	whdr.epoch	= htonl(call->conn->proto.epoch);
 	whdr.cid	= htonl(call->cid);
 	whdr.callNumber	= htonl(call->call_id);
 	whdr.seq	= 0;
@@ -864,17 +864,24 @@ void rxrpc_process_call(struct work_struct *work)
 	}
 
 	if (test_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events)) {
+		enum rxrpc_skb_mark mark;
 		int error;
 
 		clear_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events);
 		clear_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events);
 		clear_bit(RXRPC_CALL_EV_ABORT, &call->events);
 
-		error = call->conn->trans->peer->net_error;
-		_debug("post net error %d", error);
+		error = call->error_report;
+		if (error < RXRPC_LOCAL_ERROR_OFFSET) {
+			mark = RXRPC_SKB_MARK_NET_ERROR;
+			_debug("post net error %d", error);
+		} else {
+			mark = RXRPC_SKB_MARK_LOCAL_ERROR;
+			error -= RXRPC_LOCAL_ERROR_OFFSET;
+			_debug("post net local error %d", error);
+		}
 
-		if (rxrpc_post_message(call, RXRPC_SKB_MARK_NET_ERROR,
-				       error, true) < 0)
+		if (rxrpc_post_message(call, mark, error, true) < 0)
 			goto no_mem;
 		clear_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events);
 		goto kill_ACKs;
@@ -1144,8 +1151,8 @@ send_ACK_with_skew:
 	ack.maxSkew = htons(atomic_read(&call->conn->hi_serial) -
 			    ntohl(ack.serial));
 send_ACK:
-	mtu = call->conn->trans->peer->if_mtu;
-	mtu -= call->conn->trans->peer->hdrsize;
+	mtu = call->conn->params.peer->if_mtu;
+	mtu -= call->conn->params.peer->hdrsize;
 	ackinfo.maxMTU	= htonl(mtu);
 	ackinfo.rwind	= htonl(rxrpc_rx_window_size);
 
@@ -1199,7 +1206,7 @@ send_message_2:
 		len += iov[1].iov_len;
 	}
 
-	ret = kernel_sendmsg(call->conn->trans->local->socket,
+	ret = kernel_sendmsg(call->conn->params.local->socket,
 			     &msg, iov, ioc, len);
 	if (ret < 0) {
 		_debug("sendmsg failed: %d", ret);
@@ -1257,7 +1264,7 @@ maybe_reschedule:
 	if (call->state >= RXRPC_CALL_COMPLETE &&
 	    !list_empty(&call->accept_link)) {
 		_debug("X unlinking once-pending call %p { e=%lx f=%lx c=%x }",
-		       call, call->events, call->flags, call->conn->cid);
+		       call, call->events, call->flags, call->conn->proto.cid);
 
 		read_lock_bh(&call->state_lock);
 		if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) &&
@@ -1275,7 +1282,7 @@ error:
 	 * this means there's a race between clearing the flag and setting the
 	 * work pending bit and the work item being processed again */
 	if (call->events && !work_pending(&call->processor)) {
-		_debug("jumpstart %x", call->conn->cid);
+		_debug("jumpstart %x", call->conn->proto.cid);
 		rxrpc_queue_call(call);
 	}
 
diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/call_object.c
index 1fbaae1cba5f..ad933daae13b 100644
--- a/net/rxrpc/ar-call.c
+++ b/net/rxrpc/call_object.c
@@ -31,6 +31,8 @@ unsigned int rxrpc_max_call_lifetime = 60 * HZ;
 unsigned int rxrpc_dead_call_expiry = 2 * HZ;
 
 const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = {
+	[RXRPC_CALL_UNINITIALISED]		= "Uninit",
+	[RXRPC_CALL_CLIENT_AWAIT_CONN]		= "ClWtConn",
 	[RXRPC_CALL_CLIENT_SEND_REQUEST]	= "ClSndReq",
 	[RXRPC_CALL_CLIENT_AWAIT_REPLY]		= "ClAwtRpl",
 	[RXRPC_CALL_CLIENT_RECV_REPLY]		= "ClRcvRpl",
@@ -71,7 +73,7 @@ static unsigned long rxrpc_call_hashfunc(
 	u32		call_id,
 	u32		epoch,
 	u16		service_id,
-	sa_family_t	proto,
+	sa_family_t	family,
 	void		*localptr,
 	unsigned int	addr_size,
 	const u8	*peer_addr)
@@ -92,7 +94,7 @@ static unsigned long rxrpc_call_hashfunc(
 	key += (cid & RXRPC_CIDMASK) >> RXRPC_CIDSHIFT;
 	key += cid & RXRPC_CHANNELMASK;
 	key += in_clientflag;
-	key += proto;
+	key += family;
 	/* Step through the peer address in 16-bit portions for speed */
 	for (i = 0, p = (const u16 *)peer_addr; i < addr_size >> 1; i++, p++)
 		key += *p;
@@ -109,7 +111,7 @@ static void rxrpc_call_hash_add(struct rxrpc_call *call)
 	unsigned int addr_size = 0;
 
 	_enter("");
-	switch (call->proto) {
+	switch (call->family) {
 	case AF_INET:
 		addr_size = sizeof(call->peer_ip.ipv4_addr);
 		break;
@@ -121,8 +123,8 @@ static void rxrpc_call_hash_add(struct rxrpc_call *call)
 	}
 	key = rxrpc_call_hashfunc(call->in_clientflag, call->cid,
 				  call->call_id, call->epoch,
-				  call->service_id, call->proto,
-				  call->conn->trans->local, addr_size,
+				  call->service_id, call->family,
+				  call->conn->params.local, addr_size,
 				  call->peer_ip.ipv6_addr);
 	/* Store the full key in the call */
 	call->hash_key = key;
@@ -151,7 +153,7 @@ static void rxrpc_call_hash_del(struct rxrpc_call *call)
 struct rxrpc_call *rxrpc_find_call_hash(
 	struct rxrpc_host_header *hdr,
 	void		*localptr,
-	sa_family_t	proto,
+	sa_family_t	family,
 	const void	*peer_addr)
 {
 	unsigned long key;
@@ -161,7 +163,7 @@ struct rxrpc_call *rxrpc_find_call_hash(
 	u8 in_clientflag = hdr->flags & RXRPC_CLIENT_INITIATED;
 
 	_enter("");
-	switch (proto) {
+	switch (family) {
 	case AF_INET:
 		addr_size = sizeof(call->peer_ip.ipv4_addr);
 		break;
@@ -174,7 +176,7 @@ struct rxrpc_call *rxrpc_find_call_hash(
 
 	key = rxrpc_call_hashfunc(in_clientflag, hdr->cid, hdr->callNumber,
 				  hdr->epoch, hdr->serviceId,
-				  proto, localptr, addr_size,
+				  family, localptr, addr_size,
 				  peer_addr);
 	hash_for_each_possible_rcu(rxrpc_call_hash, call, hash_node, key) {
 		if (call->hash_key == key &&
@@ -182,7 +184,7 @@ struct rxrpc_call *rxrpc_find_call_hash(
 		    call->cid == hdr->cid &&
 		    call->in_clientflag == in_clientflag &&
 		    call->service_id == hdr->serviceId &&
-		    call->proto == proto &&
+		    call->family == family &&
 		    call->local == localptr &&
 		    memcmp(call->peer_ip.ipv6_addr, peer_addr,
 			   addr_size) == 0 &&
@@ -196,6 +198,43 @@ struct rxrpc_call *rxrpc_find_call_hash(
 }
 
 /*
+ * find an extant server call
+ * - called in process context with IRQs enabled
+ */
+struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *rx,
+					      unsigned long user_call_ID)
+{
+	struct rxrpc_call *call;
+	struct rb_node *p;
+
+	_enter("%p,%lx", rx, user_call_ID);
+
+	read_lock(&rx->call_lock);
+
+	p = rx->calls.rb_node;
+	while (p) {
+		call = rb_entry(p, struct rxrpc_call, sock_node);
+
+		if (user_call_ID < call->user_call_ID)
+			p = p->rb_left;
+		else if (user_call_ID > call->user_call_ID)
+			p = p->rb_right;
+		else
+			goto found_extant_call;
+	}
+
+	read_unlock(&rx->call_lock);
+	_leave(" = NULL");
+	return NULL;
+
+found_extant_call:
+	rxrpc_get_call(call);
+	read_unlock(&rx->call_lock);
+	_leave(" = %p [%d]", call, atomic_read(&call->usage));
+	return call;
+}
+
+/*
  * allocate a new call
  */
 static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp)
@@ -224,6 +263,7 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp)
 		    (unsigned long) call);
 	INIT_WORK(&call->destroyer, &rxrpc_destroy_call);
 	INIT_WORK(&call->processor, &rxrpc_process_call);
+	INIT_LIST_HEAD(&call->link);
 	INIT_LIST_HEAD(&call->accept_link);
 	skb_queue_head_init(&call->rx_queue);
 	skb_queue_head_init(&call->rx_oos_queue);
@@ -232,7 +272,6 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp)
 	rwlock_init(&call->state_lock);
 	atomic_set(&call->usage, 1);
 	call->debug_id = atomic_inc_return(&rxrpc_debug_id);
-	call->state = RXRPC_CALL_CLIENT_SEND_REQUEST;
 
 	memset(&call->sock_node, 0xed, sizeof(call->sock_node));
 
@@ -245,117 +284,104 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp)
 }
 
 /*
- * allocate a new client call and attempt to get a connection slot for it
+ * Allocate a new client call.
  */
-static struct rxrpc_call *rxrpc_alloc_client_call(
-	struct rxrpc_sock *rx,
-	struct rxrpc_transport *trans,
-	struct rxrpc_conn_bundle *bundle,
-	gfp_t gfp)
+static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
+						  struct sockaddr_rxrpc *srx,
+						  gfp_t gfp)
 {
 	struct rxrpc_call *call;
-	int ret;
 
 	_enter("");
 
-	ASSERT(rx != NULL);
-	ASSERT(trans != NULL);
-	ASSERT(bundle != NULL);
+	ASSERT(rx->local != NULL);
 
 	call = rxrpc_alloc_call(gfp);
 	if (!call)
 		return ERR_PTR(-ENOMEM);
+	call->state = RXRPC_CALL_CLIENT_AWAIT_CONN;
 
 	sock_hold(&rx->sk);
 	call->socket = rx;
 	call->rx_data_post = 1;
 
-	ret = rxrpc_connect_call(rx, trans, bundle, call, gfp);
-	if (ret < 0) {
-		kmem_cache_free(rxrpc_call_jar, call);
-		return ERR_PTR(ret);
-	}
-
 	/* Record copies of information for hashtable lookup */
-	call->proto = rx->proto;
-	call->local = trans->local;
-	switch (call->proto) {
+	call->family = rx->family;
+	call->local = rx->local;
+	switch (call->family) {
 	case AF_INET:
-		call->peer_ip.ipv4_addr =
-			trans->peer->srx.transport.sin.sin_addr.s_addr;
+		call->peer_ip.ipv4_addr = srx->transport.sin.sin_addr.s_addr;
 		break;
 	case AF_INET6:
 		memcpy(call->peer_ip.ipv6_addr,
-		       trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8,
+		       srx->transport.sin6.sin6_addr.in6_u.u6_addr8,
 		       sizeof(call->peer_ip.ipv6_addr));
 		break;
 	}
-	call->epoch = call->conn->epoch;
-	call->service_id = call->conn->service_id;
-	call->in_clientflag = call->conn->in_clientflag;
+
+	call->service_id = srx->srx_service;
+	call->in_clientflag = 0;
+
+	_leave(" = %p", call);
+	return call;
+}
+
+/*
+ * Begin client call.
+ */
+static int rxrpc_begin_client_call(struct rxrpc_call *call,
+				   struct rxrpc_conn_parameters *cp,
+				   struct sockaddr_rxrpc *srx,
+				   gfp_t gfp)
+{
+	int ret;
+
+	/* Set up or get a connection record and set the protocol parameters,
+	 * including channel number and call ID.
+	 */
+	ret = rxrpc_connect_call(call, cp, srx, gfp);
+	if (ret < 0)
+		return ret;
+
+	call->state = RXRPC_CALL_CLIENT_SEND_REQUEST;
+
 	/* Add the new call to the hashtable */
 	rxrpc_call_hash_add(call);
 
-	spin_lock(&call->conn->trans->peer->lock);
-	list_add(&call->error_link, &call->conn->trans->peer->error_targets);
-	spin_unlock(&call->conn->trans->peer->lock);
+	spin_lock(&call->conn->params.peer->lock);
+	hlist_add_head(&call->error_link, &call->conn->params.peer->error_targets);
+	spin_unlock(&call->conn->params.peer->lock);
 
 	call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime;
 	add_timer(&call->lifetimer);
-
-	_leave(" = %p", call);
-	return call;
+	return 0;
 }
 
 /*
  * set up a call for the given data
  * - called in process context with IRQs enabled
  */
-struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx,
-					 struct rxrpc_transport *trans,
-					 struct rxrpc_conn_bundle *bundle,
+struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
+					 struct rxrpc_conn_parameters *cp,
+					 struct sockaddr_rxrpc *srx,
 					 unsigned long user_call_ID,
-					 int create,
 					 gfp_t gfp)
 {
-	struct rxrpc_call *call, *candidate;
-	struct rb_node *p, *parent, **pp;
-
-	_enter("%p,%d,%d,%lx,%d",
-	       rx, trans ? trans->debug_id : -1, bundle ? bundle->debug_id : -1,
-	       user_call_ID, create);
-
-	/* search the extant calls first for one that matches the specified
-	 * user ID */
-	read_lock(&rx->call_lock);
-
-	p = rx->calls.rb_node;
-	while (p) {
-		call = rb_entry(p, struct rxrpc_call, sock_node);
-
-		if (user_call_ID < call->user_call_ID)
-			p = p->rb_left;
-		else if (user_call_ID > call->user_call_ID)
-			p = p->rb_right;
-		else
-			goto found_extant_call;
-	}
-
-	read_unlock(&rx->call_lock);
+	struct rxrpc_call *call, *xcall;
+	struct rb_node *parent, **pp;
+	int ret;
 
-	if (!create || !trans)
-		return ERR_PTR(-EBADSLT);
+	_enter("%p,%lx", rx, user_call_ID);
 
-	/* not yet present - create a candidate for a new record and then
-	 * redo the search */
-	candidate = rxrpc_alloc_client_call(rx, trans, bundle, gfp);
-	if (IS_ERR(candidate)) {
-		_leave(" = %ld", PTR_ERR(candidate));
-		return candidate;
+	call = rxrpc_alloc_client_call(rx, srx, gfp);
+	if (IS_ERR(call)) {
+		_leave(" = %ld", PTR_ERR(call));
+		return call;
 	}
 
-	candidate->user_call_ID = user_call_ID;
-	__set_bit(RXRPC_CALL_HAS_USERID, &candidate->flags);
+	/* Publish the call, even though it is incompletely set up as yet */
+	call->user_call_ID = user_call_ID;
+	__set_bit(RXRPC_CALL_HAS_USERID, &call->flags);
 
 	write_lock(&rx->call_lock);
 
@@ -363,19 +389,16 @@ struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx,
 	parent = NULL;
 	while (*pp) {
 		parent = *pp;
-		call = rb_entry(parent, struct rxrpc_call, sock_node);
+		xcall = rb_entry(parent, struct rxrpc_call, sock_node);
 
-		if (user_call_ID < call->user_call_ID)
+		if (user_call_ID < xcall->user_call_ID)
 			pp = &(*pp)->rb_left;
-		else if (user_call_ID > call->user_call_ID)
+		else if (user_call_ID > xcall->user_call_ID)
 			pp = &(*pp)->rb_right;
 		else
-			goto found_extant_second;
+			goto found_user_ID_now_present;
 	}
 
-	/* second search also failed; add the new call */
-	call = candidate;
-	candidate = NULL;
 	rxrpc_get_call(call);
 
 	rb_link_node(&call->sock_node, parent, pp);
@@ -386,25 +409,39 @@ struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx,
 	list_add_tail(&call->link, &rxrpc_calls);
 	write_unlock_bh(&rxrpc_call_lock);
 
+	ret = rxrpc_begin_client_call(call, cp, srx, gfp);
+	if (ret < 0)
+		goto error;
+
 	_net("CALL new %d on CONN %d", call->debug_id, call->conn->debug_id);
 
 	_leave(" = %p [new]", call);
 	return call;
 
-	/* we found the call in the list immediately */
-found_extant_call:
-	rxrpc_get_call(call);
-	read_unlock(&rx->call_lock);
-	_leave(" = %p [extant %d]", call, atomic_read(&call->usage));
-	return call;
+error:
+	write_lock(&rx->call_lock);
+	rb_erase(&call->sock_node, &rx->calls);
+	write_unlock(&rx->call_lock);
+	rxrpc_put_call(call);
 
-	/* we found the call on the second time through the list */
-found_extant_second:
-	rxrpc_get_call(call);
+	write_lock_bh(&rxrpc_call_lock);
+	list_del(&call->link);
+	write_unlock_bh(&rxrpc_call_lock);
+
+	rxrpc_put_call(call);
+	_leave(" = %d", ret);
+	return ERR_PTR(ret);
+
+	/* We unexpectedly found the user ID in the list after taking
+	 * the call_lock.  This shouldn't happen unless the user races
+	 * with itself and tries to add the same user ID twice at the
+	 * same time in different threads.
+	 */
+found_user_ID_now_present:
 	write_unlock(&rx->call_lock);
-	rxrpc_put_call(candidate);
-	_leave(" = %p [second %d]", call, atomic_read(&call->usage));
-	return call;
+	rxrpc_put_call(call);
+	_leave(" = -EEXIST [%p]", call);
+	return ERR_PTR(-EEXIST);
 }
 
 /*
@@ -413,8 +450,9 @@ found_extant_second:
  */
 struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx,
 				       struct rxrpc_connection *conn,
-				       struct rxrpc_host_header *hdr)
+				       struct sk_buff *skb)
 {
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_call *call, *candidate;
 	struct rb_node **p, *parent;
 	u32 call_id;
@@ -427,13 +465,13 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx,
 	if (!candidate)
 		return ERR_PTR(-EBUSY);
 
-	candidate->socket = rx;
-	candidate->conn = conn;
-	candidate->cid = hdr->cid;
-	candidate->call_id = hdr->callNumber;
-	candidate->channel = hdr->cid & RXRPC_CHANNELMASK;
-	candidate->rx_data_post = 0;
-	candidate->state = RXRPC_CALL_SERVER_ACCEPTING;
+	candidate->socket	= rx;
+	candidate->conn		= conn;
+	candidate->cid		= sp->hdr.cid;
+	candidate->call_id	= sp->hdr.callNumber;
+	candidate->channel	= sp->hdr.cid & RXRPC_CHANNELMASK;
+	candidate->rx_data_post	= 0;
+	candidate->state	= RXRPC_CALL_SERVER_ACCEPTING;
 	if (conn->security_ix > 0)
 		candidate->state = RXRPC_CALL_SERVER_SECURING;
 
@@ -442,7 +480,7 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx,
 	/* set the channel for this call */
 	call = conn->channels[candidate->channel];
 	_debug("channel[%u] is %p", candidate->channel, call);
-	if (call && call->call_id == hdr->callNumber) {
+	if (call && call->call_id == sp->hdr.callNumber) {
 		/* already set; must've been a duplicate packet */
 		_debug("extant call [%d]", call->state);
 		ASSERTCMP(call->conn, ==, conn);
@@ -480,7 +518,7 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx,
 
 	/* check the call number isn't duplicate */
 	_debug("check dup");
-	call_id = hdr->callNumber;
+	call_id = sp->hdr.callNumber;
 	p = &conn->calls.rb_node;
 	parent = NULL;
 	while (*p) {
@@ -506,36 +544,36 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx,
 	rb_insert_color(&call->conn_node, &conn->calls);
 	conn->channels[call->channel] = call;
 	sock_hold(&rx->sk);
-	atomic_inc(&conn->usage);
+	rxrpc_get_connection(conn);
 	write_unlock_bh(&conn->lock);
 
-	spin_lock(&conn->trans->peer->lock);
-	list_add(&call->error_link, &conn->trans->peer->error_targets);
-	spin_unlock(&conn->trans->peer->lock);
+	spin_lock(&conn->params.peer->lock);
+	hlist_add_head(&call->error_link, &conn->params.peer->error_targets);
+	spin_unlock(&conn->params.peer->lock);
 
 	write_lock_bh(&rxrpc_call_lock);
 	list_add_tail(&call->link, &rxrpc_calls);
 	write_unlock_bh(&rxrpc_call_lock);
 
 	/* Record copies of information for hashtable lookup */
-	call->proto = rx->proto;
-	call->local = conn->trans->local;
-	switch (call->proto) {
+	call->family = rx->family;
+	call->local = conn->params.local;
+	switch (call->family) {
 	case AF_INET:
 		call->peer_ip.ipv4_addr =
-			conn->trans->peer->srx.transport.sin.sin_addr.s_addr;
+			conn->params.peer->srx.transport.sin.sin_addr.s_addr;
 		break;
 	case AF_INET6:
 		memcpy(call->peer_ip.ipv6_addr,
-		       conn->trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8,
+		       conn->params.peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8,
 		       sizeof(call->peer_ip.ipv6_addr));
 		break;
 	default:
 		break;
 	}
-	call->epoch = conn->epoch;
-	call->service_id = conn->service_id;
-	call->in_clientflag = conn->in_clientflag;
+	call->epoch = conn->proto.epoch;
+	call->service_id = conn->params.service_id;
+	call->in_clientflag = conn->proto.in_clientflag;
 	/* Add the new call to the hashtable */
 	rxrpc_call_hash_add(call);
 
@@ -566,46 +604,6 @@ old_call:
 }
 
 /*
- * find an extant server call
- * - called in process context with IRQs enabled
- */
-struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *rx,
-					  unsigned long user_call_ID)
-{
-	struct rxrpc_call *call;
-	struct rb_node *p;
-
-	_enter("%p,%lx", rx, user_call_ID);
-
-	/* search the extant calls for one that matches the specified user
-	 * ID */
-	read_lock(&rx->call_lock);
-
-	p = rx->calls.rb_node;
-	while (p) {
-		call = rb_entry(p, struct rxrpc_call, sock_node);
-
-		if (user_call_ID < call->user_call_ID)
-			p = p->rb_left;
-		else if (user_call_ID > call->user_call_ID)
-			p = p->rb_right;
-		else
-			goto found_extant_call;
-	}
-
-	read_unlock(&rx->call_lock);
-	_leave(" = NULL");
-	return NULL;
-
-	/* we found the call in the list immediately */
-found_extant_call:
-	rxrpc_get_call(call);
-	read_unlock(&rx->call_lock);
-	_leave(" = %p [%d]", call, atomic_read(&call->usage));
-	return call;
-}
-
-/*
  * detach a call from a socket and set up for release
  */
 void rxrpc_release_call(struct rxrpc_call *call)
@@ -643,40 +641,13 @@ void rxrpc_release_call(struct rxrpc_call *call)
 	write_unlock_bh(&rx->call_lock);
 
 	/* free up the channel for reuse */
-	spin_lock(&conn->trans->client_lock);
+	spin_lock(&conn->channel_lock);
 	write_lock_bh(&conn->lock);
 	write_lock(&call->state_lock);
 
-	if (conn->channels[call->channel] == call)
-		conn->channels[call->channel] = NULL;
-
-	if (conn->out_clientflag && conn->bundle) {
-		conn->avail_calls++;
-		switch (conn->avail_calls) {
-		case 1:
-			list_move_tail(&conn->bundle_link,
-				       &conn->bundle->avail_conns);
-		case 2 ... RXRPC_MAXCALLS - 1:
-			ASSERT(conn->channels[0] == NULL ||
-			       conn->channels[1] == NULL ||
-			       conn->channels[2] == NULL ||
-			       conn->channels[3] == NULL);
-			break;
-		case RXRPC_MAXCALLS:
-			list_move_tail(&conn->bundle_link,
-				       &conn->bundle->unused_conns);
-			ASSERT(conn->channels[0] == NULL &&
-			       conn->channels[1] == NULL &&
-			       conn->channels[2] == NULL &&
-			       conn->channels[3] == NULL);
-			break;
-		default:
-			pr_err("conn->avail_calls=%d\n", conn->avail_calls);
-			BUG();
-		}
-	}
+	rxrpc_disconnect_call(call);
 
-	spin_unlock(&conn->trans->client_lock);
+	spin_unlock(&conn->channel_lock);
 
 	if (call->state < RXRPC_CALL_COMPLETE &&
 	    call->state != RXRPC_CALL_CLIENT_FINAL_ACK) {
@@ -845,9 +816,9 @@ static void rxrpc_cleanup_call(struct rxrpc_call *call)
 	}
 
 	if (call->conn) {
-		spin_lock(&call->conn->trans->peer->lock);
-		list_del(&call->error_link);
-		spin_unlock(&call->conn->trans->peer->lock);
+		spin_lock(&call->conn->params.peer->lock);
+		hlist_del_init(&call->error_link);
+		spin_unlock(&call->conn->params.peer->lock);
 
 		write_lock_bh(&call->conn->lock);
 		rb_erase(&call->conn_node, &call->conn->calls);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
new file mode 100644
index 000000000000..82488d6adb83
--- /dev/null
+++ b/net/rxrpc/conn_client.c
@@ -0,0 +1,94 @@
+/* Client connection-specific management code.
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells ([email protected])
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#include <linux/idr.h>
+#include <linux/timer.h>
+#include "ar-internal.h"
+
+/*
+ * We use machine-unique IDs for our client connections.
+ */
+DEFINE_IDR(rxrpc_client_conn_ids);
+static DEFINE_SPINLOCK(rxrpc_conn_id_lock);
+
+/*
+ * Get a connection ID and epoch for a client connection from the global pool.
+ * The connection struct pointer is then recorded in the idr radix tree.  The
+ * epoch is changed if this wraps.
+ *
+ * TODO: The IDR tree gets very expensive on memory if the connection IDs are
+ * widely scattered throughout the number space, so we shall need to retire
+ * connections that have, say, an ID more than four times the maximum number of
+ * client conns away from the current allocation point to try and keep the IDs
+ * concentrated.  We will also need to retire connections from an old epoch.
+ */
+int rxrpc_get_client_connection_id(struct rxrpc_connection *conn, gfp_t gfp)
+{
+	u32 epoch;
+	int id;
+
+	_enter("");
+
+	idr_preload(gfp);
+	spin_lock(&rxrpc_conn_id_lock);
+
+	epoch = rxrpc_epoch;
+
+	/* We could use idr_alloc_cyclic() here, but we really need to know
+	 * when the thing wraps so that we can advance the epoch.
+	 */
+	if (rxrpc_client_conn_ids.cur == 0)
+		rxrpc_client_conn_ids.cur = 1;
+	id = idr_alloc(&rxrpc_client_conn_ids, conn,
+		       rxrpc_client_conn_ids.cur, 0x40000000, GFP_NOWAIT);
+	if (id < 0) {
+		if (id != -ENOSPC)
+			goto error;
+		id = idr_alloc(&rxrpc_client_conn_ids, conn,
+			       1, 0x40000000, GFP_NOWAIT);
+		if (id < 0)
+			goto error;
+		epoch++;
+		rxrpc_epoch = epoch;
+	}
+	rxrpc_client_conn_ids.cur = id + 1;
+
+	spin_unlock(&rxrpc_conn_id_lock);
+	idr_preload_end();
+
+	conn->proto.epoch = epoch;
+	conn->proto.cid = id << RXRPC_CIDSHIFT;
+	set_bit(RXRPC_CONN_HAS_IDR, &conn->flags);
+	_leave(" [CID %x:%x]", epoch, conn->proto.cid);
+	return 0;
+
+error:
+	spin_unlock(&rxrpc_conn_id_lock);
+	idr_preload_end();
+	_leave(" = %d", id);
+	return id;
+}
+
+/*
+ * Release a connection ID for a client connection from the global pool.
+ */
+void rxrpc_put_client_connection_id(struct rxrpc_connection *conn)
+{
+	if (test_bit(RXRPC_CONN_HAS_IDR, &conn->flags)) {
+		spin_lock(&rxrpc_conn_id_lock);
+		idr_remove(&rxrpc_client_conn_ids,
+			   conn->proto.cid >> RXRPC_CIDSHIFT);
+		spin_unlock(&rxrpc_conn_id_lock);
+	}
+}
diff --git a/net/rxrpc/ar-connevent.c b/net/rxrpc/conn_event.c
index 8bdd692d4862..bf6971555eac 100644
--- a/net/rxrpc/ar-connevent.c
+++ b/net/rxrpc/conn_event.c
@@ -88,14 +88,14 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 
 	rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, abort_code);
 
-	msg.msg_name	= &conn->trans->peer->srx.transport;
-	msg.msg_namelen	= conn->trans->peer->srx.transport_len;
+	msg.msg_name	= &conn->params.peer->srx.transport;
+	msg.msg_namelen	= conn->params.peer->srx.transport_len;
 	msg.msg_control	= NULL;
 	msg.msg_controllen = 0;
 	msg.msg_flags	= 0;
 
-	whdr.epoch	= htonl(conn->epoch);
-	whdr.cid	= htonl(conn->cid);
+	whdr.epoch	= htonl(conn->proto.epoch);
+	whdr.cid	= htonl(conn->proto.cid);
 	whdr.callNumber	= 0;
 	whdr.seq	= 0;
 	whdr.type	= RXRPC_PACKET_TYPE_ABORT;
@@ -103,7 +103,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 	whdr.userStatus	= 0;
 	whdr.securityIndex = conn->security_ix;
 	whdr._rsvd	= 0;
-	whdr.serviceId	= htons(conn->service_id);
+	whdr.serviceId	= htons(conn->params.service_id);
 
 	word		= htonl(conn->local_abort);
 
@@ -118,7 +118,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 	whdr.serial = htonl(serial);
 	_proto("Tx CONN ABORT %%%u { %d }", serial, conn->local_abort);
 
-	ret = kernel_sendmsg(conn->trans->local->socket, &msg, iov, 2, len);
+	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
 	if (ret < 0) {
 		_debug("sendmsg failed: %d", ret);
 		return -EAGAIN;
@@ -220,7 +220,7 @@ static void rxrpc_secure_connection(struct rxrpc_connection *conn)
 
 	ASSERT(conn->security_ix != 0);
 
-	if (!conn->key) {
+	if (!conn->params.key) {
 		_debug("set up security");
 		ret = rxrpc_init_server_conn_security(conn);
 		switch (ret) {
@@ -263,7 +263,7 @@ void rxrpc_process_connection(struct work_struct *work)
 
 	_enter("{%d}", conn->debug_id);
 
-	atomic_inc(&conn->usage);
+	rxrpc_get_connection(conn);
 
 	if (test_and_clear_bit(RXRPC_CONN_CHALLENGE, &conn->events)) {
 		rxrpc_secure_connection(conn);
@@ -314,19 +314,14 @@ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb)
 {
 	CHECK_SLAB_OKAY(&local->usage);
 
-	if (!atomic_inc_not_zero(&local->usage)) {
-		printk("resurrected on reject\n");
-		BUG();
-	}
-
 	skb_queue_tail(&local->reject_queue, skb);
-	rxrpc_queue_work(&local->rejecter);
+	rxrpc_queue_work(&local->processor);
 }
 
 /*
  * reject packets through the local endpoint
  */
-void rxrpc_reject_packets(struct work_struct *work)
+void rxrpc_reject_packets(struct rxrpc_local *local)
 {
 	union {
 		struct sockaddr sa;
@@ -334,16 +329,12 @@ void rxrpc_reject_packets(struct work_struct *work)
 	} sa;
 	struct rxrpc_skb_priv *sp;
 	struct rxrpc_wire_header whdr;
-	struct rxrpc_local *local;
 	struct sk_buff *skb;
 	struct msghdr msg;
 	struct kvec iov[2];
 	size_t size;
 	__be32 code;
 
-	local = container_of(work, struct rxrpc_local, rejecter);
-	rxrpc_get_local(local);
-
 	_enter("%d", local->debug_id);
 
 	iov[0].iov_base = &whdr;
@@ -395,9 +386,7 @@ void rxrpc_reject_packets(struct work_struct *work)
 		}
 
 		rxrpc_free_skb(skb);
-		rxrpc_put_local(local);
 	}
 
-	rxrpc_put_local(local);
 	_leave("");
 }
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
new file mode 100644
index 000000000000..4bfad7cf96cb
--- /dev/null
+++ b/net/rxrpc/conn_object.c
@@ -0,0 +1,686 @@
+/* RxRPC virtual connection handler
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells ([email protected])
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/crypto.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+/*
+ * Time till a connection expires after last use (in seconds).
+ */
+unsigned int rxrpc_connection_expiry = 10 * 60;
+
+static void rxrpc_connection_reaper(struct work_struct *work);
+
+LIST_HEAD(rxrpc_connections);
+DEFINE_RWLOCK(rxrpc_connection_lock);
+static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper);
+
+/*
+ * allocate a new connection
+ */
+static struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp)
+{
+	struct rxrpc_connection *conn;
+
+	_enter("");
+
+	conn = kzalloc(sizeof(struct rxrpc_connection), gfp);
+	if (conn) {
+		spin_lock_init(&conn->channel_lock);
+		init_waitqueue_head(&conn->channel_wq);
+		INIT_WORK(&conn->processor, &rxrpc_process_connection);
+		INIT_LIST_HEAD(&conn->link);
+		conn->calls = RB_ROOT;
+		skb_queue_head_init(&conn->rx_queue);
+		conn->security = &rxrpc_no_security;
+		rwlock_init(&conn->lock);
+		spin_lock_init(&conn->state_lock);
+		atomic_set(&conn->usage, 1);
+		conn->debug_id = atomic_inc_return(&rxrpc_debug_id);
+		atomic_set(&conn->avail_chans, RXRPC_MAXCALLS);
+		conn->size_align = 4;
+		conn->header_size = sizeof(struct rxrpc_wire_header);
+	}
+
+	_leave(" = %p{%d}", conn, conn ? conn->debug_id : 0);
+	return conn;
+}
+
+/*
+ * add a call to a connection's call-by-ID tree
+ */
+static void rxrpc_add_call_ID_to_conn(struct rxrpc_connection *conn,
+				      struct rxrpc_call *call)
+{
+	struct rxrpc_call *xcall;
+	struct rb_node *parent, **p;
+	__be32 call_id;
+
+	write_lock_bh(&conn->lock);
+
+	call_id = call->call_id;
+	p = &conn->calls.rb_node;
+	parent = NULL;
+	while (*p) {
+		parent = *p;
+		xcall = rb_entry(parent, struct rxrpc_call, conn_node);
+
+		if (call_id < xcall->call_id)
+			p = &(*p)->rb_left;
+		else if (call_id > xcall->call_id)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&call->conn_node, parent, p);
+	rb_insert_color(&call->conn_node, &conn->calls);
+
+	write_unlock_bh(&conn->lock);
+}
+
+/*
+ * Allocate a client connection.  The caller must take care to clear any
+ * padding bytes in *cp.
+ */
+static struct rxrpc_connection *
+rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp)
+{
+	struct rxrpc_connection *conn;
+	int ret;
+
+	_enter("");
+
+	conn = rxrpc_alloc_connection(gfp);
+	if (!conn) {
+		_leave(" = -ENOMEM");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	conn->params		= *cp;
+	conn->proto.local	= cp->local;
+	conn->proto.epoch	= rxrpc_epoch;
+	conn->proto.cid		= 0;
+	conn->proto.in_clientflag = 0;
+	conn->proto.family	= cp->peer->srx.transport.family;
+	conn->out_clientflag	= RXRPC_CLIENT_INITIATED;
+	conn->state		= RXRPC_CONN_CLIENT;
+
+	switch (conn->proto.family) {
+	case AF_INET:
+		conn->proto.addr_size = sizeof(conn->proto.ipv4_addr);
+		conn->proto.ipv4_addr = cp->peer->srx.transport.sin.sin_addr;
+		conn->proto.port = cp->peer->srx.transport.sin.sin_port;
+		break;
+	}
+
+	ret = rxrpc_get_client_connection_id(conn, gfp);
+	if (ret < 0)
+		goto error_0;
+
+	ret = rxrpc_init_client_conn_security(conn);
+	if (ret < 0)
+		goto error_1;
+
+	conn->security->prime_packet_security(conn);
+
+	write_lock(&rxrpc_connection_lock);
+	list_add_tail(&conn->link, &rxrpc_connections);
+	write_unlock(&rxrpc_connection_lock);
+
+	/* We steal the caller's peer ref. */
+	cp->peer = NULL;
+	rxrpc_get_local(conn->params.local);
+	key_get(conn->params.key);
+
+	_leave(" = %p", conn);
+	return conn;
+
+error_1:
+	rxrpc_put_client_connection_id(conn);
+error_0:
+	kfree(conn);
+	_leave(" = %d", ret);
+	return ERR_PTR(ret);
+}
+
+/*
+ * find a connection for a call
+ * - called in process context with IRQs enabled
+ */
+int rxrpc_connect_call(struct rxrpc_call *call,
+		       struct rxrpc_conn_parameters *cp,
+		       struct sockaddr_rxrpc *srx,
+		       gfp_t gfp)
+{
+	struct rxrpc_connection *conn, *candidate = NULL;
+	struct rxrpc_local *local = cp->local;
+	struct rb_node *p, **pp, *parent;
+	long diff;
+	int chan;
+
+	DECLARE_WAITQUEUE(myself, current);
+
+	_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
+
+	cp->peer = rxrpc_lookup_peer(cp->local, srx, gfp);
+	if (!cp->peer)
+		return -ENOMEM;
+
+	if (!cp->exclusive) {
+		/* Search for a existing client connection unless this is going
+		 * to be a connection that's used exclusively for a single call.
+		 */
+		_debug("search 1");
+		spin_lock(&local->client_conns_lock);
+		p = local->client_conns.rb_node;
+		while (p) {
+			conn = rb_entry(p, struct rxrpc_connection, client_node);
+
+#define cmp(X) ((long)conn->params.X - (long)cp->X)
+			diff = (cmp(peer) ?:
+				cmp(key) ?:
+				cmp(security_level));
+			if (diff < 0)
+				p = p->rb_left;
+			else if (diff > 0)
+				p = p->rb_right;
+			else
+				goto found_extant_conn;
+		}
+		spin_unlock(&local->client_conns_lock);
+	}
+
+	/* We didn't find a connection or we want an exclusive one. */
+	_debug("get new conn");
+	candidate = rxrpc_alloc_client_connection(cp, gfp);
+	if (!candidate) {
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	if (cp->exclusive) {
+		/* Assign the call on an exclusive connection to channel 0 and
+		 * don't add the connection to the endpoint's shareable conn
+		 * lookup tree.
+		 */
+		_debug("exclusive chan 0");
+		conn = candidate;
+		atomic_set(&conn->avail_chans, RXRPC_MAXCALLS - 1);
+		spin_lock(&conn->channel_lock);
+		chan = 0;
+		goto found_channel;
+	}
+
+	/* We need to redo the search before attempting to add a new connection
+	 * lest we race with someone else adding a conflicting instance.
+	 */
+	_debug("search 2");
+	spin_lock(&local->client_conns_lock);
+
+	pp = &local->client_conns.rb_node;
+	parent = NULL;
+	while (*pp) {
+		parent = *pp;
+		conn = rb_entry(parent, struct rxrpc_connection, client_node);
+
+		diff = (cmp(peer) ?:
+			cmp(key) ?:
+			cmp(security_level));
+		if (diff < 0)
+			pp = &(*pp)->rb_left;
+		else if (diff > 0)
+			pp = &(*pp)->rb_right;
+		else
+			goto found_extant_conn;
+	}
+
+	/* The second search also failed; simply add the new connection with
+	 * the new call in channel 0.  Note that we need to take the channel
+	 * lock before dropping the client conn lock.
+	 */
+	_debug("new conn");
+	conn = candidate;
+	candidate = NULL;
+
+	rb_link_node(&conn->client_node, parent, pp);
+	rb_insert_color(&conn->client_node, &local->client_conns);
+
+	atomic_set(&conn->avail_chans, RXRPC_MAXCALLS - 1);
+	spin_lock(&conn->channel_lock);
+	spin_unlock(&local->client_conns_lock);
+	chan = 0;
+
+found_channel:
+	_debug("found chan");
+	call->conn	= conn;
+	call->channel	= chan;
+	call->epoch	= conn->proto.epoch;
+	call->cid	= conn->proto.cid | chan;
+	call->call_id	= ++conn->call_counter;
+	rcu_assign_pointer(conn->channels[chan], call);
+
+	_net("CONNECT call %d on conn %d", call->debug_id, conn->debug_id);
+
+	rxrpc_add_call_ID_to_conn(conn, call);
+	spin_unlock(&conn->channel_lock);
+	rxrpc_put_peer(cp->peer);
+	cp->peer = NULL;
+	_leave(" = %p {u=%d}", conn, atomic_read(&conn->usage));
+	return 0;
+
+	/* We found a suitable connection already in existence.  Discard any
+	 * candidate we may have allocated, and try to get a channel on this
+	 * one.
+	 */
+found_extant_conn:
+	_debug("found conn");
+	rxrpc_get_connection(conn);
+	spin_unlock(&local->client_conns_lock);
+
+	rxrpc_put_connection(candidate);
+
+	if (!atomic_add_unless(&conn->avail_chans, -1, 0)) {
+		if (!gfpflags_allow_blocking(gfp)) {
+			rxrpc_put_connection(conn);
+			_leave(" = -EAGAIN");
+			return -EAGAIN;
+		}
+
+		add_wait_queue(&conn->channel_wq, &myself);
+		for (;;) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			if (atomic_add_unless(&conn->avail_chans, -1, 0))
+				break;
+			if (signal_pending(current))
+				goto interrupted;
+			schedule();
+		}
+		remove_wait_queue(&conn->channel_wq, &myself);
+		__set_current_state(TASK_RUNNING);
+	}
+
+	/* The connection allegedly now has a free channel and we can now
+	 * attach the call to it.
+	 */
+	spin_lock(&conn->channel_lock);
+
+	for (chan = 0; chan < RXRPC_MAXCALLS; chan++)
+		if (!conn->channels[chan])
+			goto found_channel;
+	BUG();
+
+interrupted:
+	remove_wait_queue(&conn->channel_wq, &myself);
+	__set_current_state(TASK_RUNNING);
+	rxrpc_put_connection(conn);
+	rxrpc_put_peer(cp->peer);
+	cp->peer = NULL;
+	_leave(" = -ERESTARTSYS");
+	return -ERESTARTSYS;
+}
+
+/*
+ * get a record of an incoming connection
+ */
+struct rxrpc_connection *rxrpc_incoming_connection(struct rxrpc_local *local,
+						   struct rxrpc_peer *peer,
+						   struct sk_buff *skb)
+{
+	struct rxrpc_connection *conn, *candidate = NULL;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rb_node *p, **pp;
+	const char *new = "old";
+	__be32 epoch;
+	u32 cid;
+
+	_enter("");
+
+	ASSERT(sp->hdr.flags & RXRPC_CLIENT_INITIATED);
+
+	epoch = sp->hdr.epoch;
+	cid = sp->hdr.cid & RXRPC_CIDMASK;
+
+	/* search the connection list first */
+	read_lock_bh(&peer->conn_lock);
+
+	p = peer->service_conns.rb_node;
+	while (p) {
+		conn = rb_entry(p, struct rxrpc_connection, service_node);
+
+		_debug("maybe %x", conn->proto.cid);
+
+		if (epoch < conn->proto.epoch)
+			p = p->rb_left;
+		else if (epoch > conn->proto.epoch)
+			p = p->rb_right;
+		else if (cid < conn->proto.cid)
+			p = p->rb_left;
+		else if (cid > conn->proto.cid)
+			p = p->rb_right;
+		else
+			goto found_extant_connection;
+	}
+	read_unlock_bh(&peer->conn_lock);
+
+	/* not yet present - create a candidate for a new record and then
+	 * redo the search */
+	candidate = rxrpc_alloc_connection(GFP_NOIO);
+	if (!candidate) {
+		_leave(" = -ENOMEM");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	candidate->proto.local		= local;
+	candidate->proto.epoch		= sp->hdr.epoch;
+	candidate->proto.cid		= sp->hdr.cid & RXRPC_CIDMASK;
+	candidate->proto.in_clientflag	= RXRPC_CLIENT_INITIATED;
+	candidate->params.local		= local;
+	candidate->params.peer		= peer;
+	candidate->params.service_id	= sp->hdr.serviceId;
+	candidate->security_ix		= sp->hdr.securityIndex;
+	candidate->out_clientflag	= 0;
+	candidate->state		= RXRPC_CONN_SERVER;
+	if (candidate->params.service_id)
+		candidate->state	= RXRPC_CONN_SERVER_UNSECURED;
+
+	write_lock_bh(&peer->conn_lock);
+
+	pp = &peer->service_conns.rb_node;
+	p = NULL;
+	while (*pp) {
+		p = *pp;
+		conn = rb_entry(p, struct rxrpc_connection, service_node);
+
+		if (epoch < conn->proto.epoch)
+			pp = &(*pp)->rb_left;
+		else if (epoch > conn->proto.epoch)
+			pp = &(*pp)->rb_right;
+		else if (cid < conn->proto.cid)
+			pp = &(*pp)->rb_left;
+		else if (cid > conn->proto.cid)
+			pp = &(*pp)->rb_right;
+		else
+			goto found_extant_second;
+	}
+
+	/* we can now add the new candidate to the list */
+	conn = candidate;
+	candidate = NULL;
+	rb_link_node(&conn->service_node, p, pp);
+	rb_insert_color(&conn->service_node, &peer->service_conns);
+	rxrpc_get_peer(peer);
+	rxrpc_get_local(local);
+
+	write_unlock_bh(&peer->conn_lock);
+
+	write_lock(&rxrpc_connection_lock);
+	list_add_tail(&conn->link, &rxrpc_connections);
+	write_unlock(&rxrpc_connection_lock);
+
+	new = "new";
+
+success:
+	_net("CONNECTION %s %d {%x}", new, conn->debug_id, conn->proto.cid);
+
+	_leave(" = %p {u=%d}", conn, atomic_read(&conn->usage));
+	return conn;
+
+	/* we found the connection in the list immediately */
+found_extant_connection:
+	if (sp->hdr.securityIndex != conn->security_ix) {
+		read_unlock_bh(&peer->conn_lock);
+		goto security_mismatch;
+	}
+	rxrpc_get_connection(conn);
+	read_unlock_bh(&peer->conn_lock);
+	goto success;
+
+	/* we found the connection on the second time through the list */
+found_extant_second:
+	if (sp->hdr.securityIndex != conn->security_ix) {
+		write_unlock_bh(&peer->conn_lock);
+		goto security_mismatch;
+	}
+	rxrpc_get_connection(conn);
+	write_unlock_bh(&peer->conn_lock);
+	kfree(candidate);
+	goto success;
+
+security_mismatch:
+	kfree(candidate);
+	_leave(" = -EKEYREJECTED");
+	return ERR_PTR(-EKEYREJECTED);
+}
+
+/*
+ * find a connection based on transport and RxRPC connection ID for an incoming
+ * packet
+ */
+struct rxrpc_connection *rxrpc_find_connection(struct rxrpc_local *local,
+					       struct rxrpc_peer *peer,
+					       struct sk_buff *skb)
+{
+	struct rxrpc_connection *conn;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rb_node *p;
+	u32 epoch, cid;
+
+	_enter(",{%x,%x}", sp->hdr.cid, sp->hdr.flags);
+
+	read_lock_bh(&peer->conn_lock);
+
+	cid	= sp->hdr.cid & RXRPC_CIDMASK;
+	epoch	= sp->hdr.epoch;
+
+	if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) {
+		p = peer->service_conns.rb_node;
+		while (p) {
+			conn = rb_entry(p, struct rxrpc_connection, service_node);
+
+			_debug("maybe %x", conn->proto.cid);
+
+			if (epoch < conn->proto.epoch)
+				p = p->rb_left;
+			else if (epoch > conn->proto.epoch)
+				p = p->rb_right;
+			else if (cid < conn->proto.cid)
+				p = p->rb_left;
+			else if (cid > conn->proto.cid)
+				p = p->rb_right;
+			else
+				goto found;
+		}
+	} else {
+		conn = idr_find(&rxrpc_client_conn_ids, cid >> RXRPC_CIDSHIFT);
+		if (conn && conn->proto.epoch == epoch)
+			goto found;
+	}
+
+	read_unlock_bh(&peer->conn_lock);
+	_leave(" = NULL");
+	return NULL;
+
+found:
+	rxrpc_get_connection(conn);
+	read_unlock_bh(&peer->conn_lock);
+	_leave(" = %p", conn);
+	return conn;
+}
+
+/*
+ * Disconnect a call and clear any channel it occupies when that call
+ * terminates.
+ */
+void rxrpc_disconnect_call(struct rxrpc_call *call)
+{
+	struct rxrpc_connection *conn = call->conn;
+	unsigned chan = call->channel;
+
+	_enter("%d,%d", conn->debug_id, call->channel);
+
+	if (conn->channels[chan] == call) {
+		rcu_assign_pointer(conn->channels[chan], NULL);
+		atomic_inc(&conn->avail_chans);
+		wake_up(&conn->channel_wq);
+	}
+}
+
+/*
+ * release a virtual connection
+ */
+void rxrpc_put_connection(struct rxrpc_connection *conn)
+{
+	if (!conn)
+		return;
+
+	_enter("%p{u=%d,d=%d}",
+	       conn, atomic_read(&conn->usage), conn->debug_id);
+
+	ASSERTCMP(atomic_read(&conn->usage), >, 0);
+
+	conn->put_time = ktime_get_seconds();
+	if (atomic_dec_and_test(&conn->usage)) {
+		_debug("zombie");
+		rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0);
+	}
+
+	_leave("");
+}
+
+/*
+ * destroy a virtual connection
+ */
+static void rxrpc_destroy_connection(struct rxrpc_connection *conn)
+{
+	_enter("%p{%d}", conn, atomic_read(&conn->usage));
+
+	ASSERTCMP(atomic_read(&conn->usage), ==, 0);
+
+	_net("DESTROY CONN %d", conn->debug_id);
+
+	ASSERT(RB_EMPTY_ROOT(&conn->calls));
+	rxrpc_purge_queue(&conn->rx_queue);
+
+	conn->security->clear(conn);
+	key_put(conn->params.key);
+	key_put(conn->server_key);
+	rxrpc_put_peer(conn->params.peer);
+	rxrpc_put_local(conn->params.local);
+
+	kfree(conn);
+	_leave("");
+}
+
+/*
+ * reap dead connections
+ */
+static void rxrpc_connection_reaper(struct work_struct *work)
+{
+	struct rxrpc_connection *conn, *_p;
+	struct rxrpc_peer *peer;
+	unsigned long now, earliest, reap_time;
+
+	LIST_HEAD(graveyard);
+
+	_enter("");
+
+	now = ktime_get_seconds();
+	earliest = ULONG_MAX;
+
+	write_lock(&rxrpc_connection_lock);
+	list_for_each_entry_safe(conn, _p, &rxrpc_connections, link) {
+		_debug("reap CONN %d { u=%d,t=%ld }",
+		       conn->debug_id, atomic_read(&conn->usage),
+		       (long) now - (long) conn->put_time);
+
+		if (likely(atomic_read(&conn->usage) > 0))
+			continue;
+
+		if (rxrpc_conn_is_client(conn)) {
+			struct rxrpc_local *local = conn->params.local;
+			spin_lock(&local->client_conns_lock);
+			reap_time = conn->put_time + rxrpc_connection_expiry;
+
+			if (atomic_read(&conn->usage) > 0) {
+				;
+			} else if (reap_time <= now) {
+				list_move_tail(&conn->link, &graveyard);
+				rxrpc_put_client_connection_id(conn);
+				rb_erase(&conn->client_node,
+					 &local->client_conns);
+			} else if (reap_time < earliest) {
+				earliest = reap_time;
+			}
+
+			spin_unlock(&local->client_conns_lock);
+		} else {
+			peer = conn->params.peer;
+			write_lock_bh(&peer->conn_lock);
+			reap_time = conn->put_time + rxrpc_connection_expiry;
+
+			if (atomic_read(&conn->usage) > 0) {
+				;
+			} else if (reap_time <= now) {
+				list_move_tail(&conn->link, &graveyard);
+				rb_erase(&conn->service_node,
+					 &peer->service_conns);
+			} else if (reap_time < earliest) {
+				earliest = reap_time;
+			}
+
+			write_unlock_bh(&peer->conn_lock);
+		}
+	}
+	write_unlock(&rxrpc_connection_lock);
+
+	if (earliest != ULONG_MAX) {
+		_debug("reschedule reaper %ld", (long) earliest - now);
+		ASSERTCMP(earliest, >, now);
+		rxrpc_queue_delayed_work(&rxrpc_connection_reap,
+					 (earliest - now) * HZ);
+	}
+
+	/* then destroy all those pulled out */
+	while (!list_empty(&graveyard)) {
+		conn = list_entry(graveyard.next, struct rxrpc_connection,
+				  link);
+		list_del_init(&conn->link);
+
+		ASSERTCMP(atomic_read(&conn->usage), ==, 0);
+		rxrpc_destroy_connection(conn);
+	}
+
+	_leave("");
+}
+
+/*
+ * preemptively destroy all the connection records rather than waiting for them
+ * to time out
+ */
+void __exit rxrpc_destroy_all_connections(void)
+{
+	_enter("");
+
+	rxrpc_connection_expiry = 0;
+	cancel_delayed_work(&rxrpc_connection_reap);
+	rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0);
+
+	_leave("");
+}
diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/input.c
index d7c2a0bc839e..f4bd57b77b93 100644
--- a/net/rxrpc/ar-input.c
+++ b/net/rxrpc/input.c
@@ -360,7 +360,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb)
 	case RXRPC_PACKET_TYPE_BUSY:
 		_proto("Rx BUSY %%%u", sp->hdr.serial);
 
-		if (call->conn->out_clientflag)
+		if (rxrpc_conn_is_service(call->conn))
 			goto protocol_error;
 
 		write_lock_bh(&call->state_lock);
@@ -533,7 +533,7 @@ static void rxrpc_post_packet_to_call(struct rxrpc_call *call,
 	case RXRPC_CALL_COMPLETE:
 	case RXRPC_CALL_CLIENT_FINAL_ACK:
 		/* complete server call */
-		if (call->conn->in_clientflag)
+		if (rxrpc_conn_is_service(call->conn))
 			goto dead_call;
 		/* resend last packet of a completed call */
 		_debug("final ack again");
@@ -560,7 +560,7 @@ static void rxrpc_post_packet_to_call(struct rxrpc_call *call,
 dead_call:
 	if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) {
 		skb->priority = RX_CALL_DEAD;
-		rxrpc_reject_packet(call->conn->trans->local, skb);
+		rxrpc_reject_packet(call->conn->params.local, skb);
 		goto unlock;
 	}
 free_unlock:
@@ -580,7 +580,7 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn,
 {
 	_enter("%p,%p", conn, skb);
 
-	atomic_inc(&conn->usage);
+	rxrpc_get_connection(conn);
 	skb_queue_tail(&conn->rx_queue, skb);
 	rxrpc_queue_conn(conn);
 }
@@ -594,9 +594,8 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local,
 {
 	_enter("%p,%p", local, skb);
 
-	atomic_inc(&local->usage);
 	skb_queue_tail(&local->event_queue, skb);
-	rxrpc_queue_work(&local->event_processor);
+	rxrpc_queue_work(&local->processor);
 }
 
 /*
@@ -629,29 +628,27 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
 }
 
 static struct rxrpc_connection *rxrpc_conn_from_local(struct rxrpc_local *local,
-					       struct sk_buff *skb,
-					       struct rxrpc_skb_priv *sp)
+						      struct sk_buff *skb)
 {
 	struct rxrpc_peer *peer;
-	struct rxrpc_transport *trans;
 	struct rxrpc_connection *conn;
+	struct sockaddr_rxrpc srx;
 
-	peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr,
-				udp_hdr(skb)->source);
-	if (IS_ERR(peer))
-		goto cant_find_conn;
-
-	trans = rxrpc_find_transport(local, peer);
-	rxrpc_put_peer(peer);
-	if (!trans)
-		goto cant_find_conn;
+	rxrpc_get_addr_from_skb(local, skb, &srx);
+	rcu_read_lock();
+	peer = rxrpc_lookup_peer_rcu(local, &srx);
+	if (!peer)
+		goto cant_find_peer;
 
-	conn = rxrpc_find_connection(trans, &sp->hdr);
-	rxrpc_put_transport(trans);
+	conn = rxrpc_find_connection(local, peer, skb);
+	rcu_read_unlock();
 	if (!conn)
 		goto cant_find_conn;
 
 	return conn;
+
+cant_find_peer:
+	rcu_read_unlock();
 cant_find_conn:
 	return NULL;
 }
@@ -659,11 +656,15 @@ cant_find_conn:
 /*
  * handle data received on the local endpoint
  * - may be called in interrupt context
+ *
+ * The socket is locked by the caller and this prevents the socket from being
+ * shut down and the local endpoint from going away, thus sk_user_data will not
+ * be cleared until this function returns.
  */
 void rxrpc_data_ready(struct sock *sk)
 {
 	struct rxrpc_skb_priv *sp;
-	struct rxrpc_local *local;
+	struct rxrpc_local *local = sk->sk_user_data;
 	struct sk_buff *skb;
 	int ret;
 
@@ -671,21 +672,8 @@ void rxrpc_data_ready(struct sock *sk)
 
 	ASSERT(!irqs_disabled());
 
-	read_lock_bh(&rxrpc_local_lock);
-	local = sk->sk_user_data;
-	if (local && atomic_read(&local->usage) > 0)
-		rxrpc_get_local(local);
-	else
-		local = NULL;
-	read_unlock_bh(&rxrpc_local_lock);
-	if (!local) {
-		_leave(" [local dead]");
-		return;
-	}
-
 	skb = skb_recv_datagram(sk, 0, 1, &ret);
 	if (!skb) {
-		rxrpc_put_local(local);
 		if (ret == -EAGAIN)
 			return;
 		_debug("UDP socket error %d", ret);
@@ -699,7 +687,6 @@ void rxrpc_data_ready(struct sock *sk)
 	/* we'll probably need to checksum it (didn't call sock_recvmsg) */
 	if (skb_checksum_complete(skb)) {
 		rxrpc_free_skb(skb);
-		rxrpc_put_local(local);
 		__UDP_INC_STATS(&init_net, UDP_MIB_INERRORS, 0);
 		_leave(" [CSUM failed]");
 		return;
@@ -734,7 +721,7 @@ void rxrpc_data_ready(struct sock *sk)
 		rxrpc_post_packet_to_local(local, skb);
 		goto out;
 	}
-	
+
 	if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
 	    (sp->hdr.callNumber == 0 || sp->hdr.seq == 0))
 		goto bad_message;
@@ -745,7 +732,7 @@ void rxrpc_data_ready(struct sock *sk)
 		 * old-fashioned way doesn't really hurt */
 		struct rxrpc_connection *conn;
 
-		conn = rxrpc_conn_from_local(local, skb, sp);
+		conn = rxrpc_conn_from_local(local, skb);
 		if (!conn)
 			goto cant_route_call;
 
@@ -764,7 +751,6 @@ void rxrpc_data_ready(struct sock *sk)
 	}
 
 out:
-	rxrpc_put_local(local);
 	return;
 
 cant_route_call:
@@ -774,8 +760,7 @@ cant_route_call:
 		if (sp->hdr.seq == 1) {
 			_debug("first packet");
 			skb_queue_tail(&local->accept_queue, skb);
-			rxrpc_queue_work(&local->acceptor);
-			rxrpc_put_local(local);
+			rxrpc_queue_work(&local->processor);
 			_leave(" [incoming]");
 			return;
 		}
@@ -788,13 +773,11 @@ cant_route_call:
 		_debug("reject type %d",sp->hdr.type);
 		rxrpc_reject_packet(local, skb);
 	}
-	rxrpc_put_local(local);
 	_leave(" [no call]");
 	return;
 
 bad_message:
 	skb->priority = RX_PROTOCOL_ERROR;
 	rxrpc_reject_packet(local, skb);
-	rxrpc_put_local(local);
 	_leave(" [badmsg]");
 }
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/key.c
index 4ad56fafe3a7..18c737a61d80 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/key.c
@@ -987,7 +987,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *conn,
 	if (ret < 0)
 		goto error;
 
-	conn->key = key;
+	conn->params.key = key;
 	_leave(" = 0 [%d]", key_serial(key));
 	return 0;
 
diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c
new file mode 100644
index 000000000000..31a3f86ef2f6
--- /dev/null
+++ b/net/rxrpc/local_event.c
@@ -0,0 +1,116 @@
+/* AF_RXRPC local endpoint management
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells ([email protected])
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/udp.h>
+#include <linux/ip.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <generated/utsrelease.h>
+#include "ar-internal.h"
+
+static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC";
+
+/*
+ * Reply to a version request
+ */
+static void rxrpc_send_version_request(struct rxrpc_local *local,
+				       struct rxrpc_host_header *hdr,
+				       struct sk_buff *skb)
+{
+	struct rxrpc_wire_header whdr;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct sockaddr_in sin;
+	struct msghdr msg;
+	struct kvec iov[2];
+	size_t len;
+	int ret;
+
+	_enter("");
+
+	sin.sin_family = AF_INET;
+	sin.sin_port = udp_hdr(skb)->source;
+	sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
+
+	msg.msg_name	= &sin;
+	msg.msg_namelen	= sizeof(sin);
+	msg.msg_control	= NULL;
+	msg.msg_controllen = 0;
+	msg.msg_flags	= 0;
+
+	whdr.epoch	= htonl(sp->hdr.epoch);
+	whdr.cid	= htonl(sp->hdr.cid);
+	whdr.callNumber	= htonl(sp->hdr.callNumber);
+	whdr.seq	= 0;
+	whdr.serial	= 0;
+	whdr.type	= RXRPC_PACKET_TYPE_VERSION;
+	whdr.flags	= RXRPC_LAST_PACKET | (~hdr->flags & RXRPC_CLIENT_INITIATED);
+	whdr.userStatus	= 0;
+	whdr.securityIndex = 0;
+	whdr._rsvd	= 0;
+	whdr.serviceId	= htons(sp->hdr.serviceId);
+
+	iov[0].iov_base	= &whdr;
+	iov[0].iov_len	= sizeof(whdr);
+	iov[1].iov_base	= (char *)rxrpc_version_string;
+	iov[1].iov_len	= sizeof(rxrpc_version_string);
+
+	len = iov[0].iov_len + iov[1].iov_len;
+
+	_proto("Tx VERSION (reply)");
+
+	ret = kernel_sendmsg(local->socket, &msg, iov, 2, len);
+	if (ret < 0)
+		_debug("sendmsg failed: %d", ret);
+
+	_leave("");
+}
+
+/*
+ * Process event packets targetted at a local endpoint.
+ */
+void rxrpc_process_local_events(struct rxrpc_local *local)
+{
+	struct sk_buff *skb;
+	char v;
+
+	_enter("");
+
+	skb = skb_dequeue(&local->event_queue);
+	if (skb) {
+		struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+		_debug("{%d},{%u}", local->debug_id, sp->hdr.type);
+
+		switch (sp->hdr.type) {
+		case RXRPC_PACKET_TYPE_VERSION:
+			if (skb_copy_bits(skb, 0, &v, 1) < 0)
+				return;
+			_proto("Rx VERSION { %02x }", v);
+			if (v == 0)
+				rxrpc_send_version_request(local, &sp->hdr, skb);
+			break;
+
+		default:
+			/* Just ignore anything we don't understand */
+			break;
+		}
+
+		rxrpc_free_skb(skb);
+	}
+
+	_leave("");
+}
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
new file mode 100644
index 000000000000..3ab7764f7cd8
--- /dev/null
+++ b/net/rxrpc/local_object.c
@@ -0,0 +1,387 @@
+/* Local endpoint object management
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells ([email protected])
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/udp.h>
+#include <linux/ip.h>
+#include <linux/hashtable.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+static void rxrpc_local_processor(struct work_struct *);
+static void rxrpc_local_rcu(struct rcu_head *);
+
+static DEFINE_MUTEX(rxrpc_local_mutex);
+static LIST_HEAD(rxrpc_local_endpoints);
+
+/*
+ * Compare a local to an address.  Return -ve, 0 or +ve to indicate less than,
+ * same or greater than.
+ *
+ * We explicitly don't compare the RxRPC service ID as we want to reject
+ * conflicting uses by differing services.  Further, we don't want to share
+ * addresses with different options (IPv6), so we don't compare those bits
+ * either.
+ */
+static long rxrpc_local_cmp_key(const struct rxrpc_local *local,
+				const struct sockaddr_rxrpc *srx)
+{
+	long diff;
+
+	diff = ((local->srx.transport_type - srx->transport_type) ?:
+		(local->srx.transport_len - srx->transport_len) ?:
+		(local->srx.transport.family - srx->transport.family));
+	if (diff != 0)
+		return diff;
+
+	switch (srx->transport.family) {
+	case AF_INET:
+		/* If the choice of UDP port is left up to the transport, then
+		 * the endpoint record doesn't match.
+		 */
+		return ((u16 __force)local->srx.transport.sin.sin_port -
+			(u16 __force)srx->transport.sin.sin_port) ?:
+			memcmp(&local->srx.transport.sin.sin_addr,
+			       &srx->transport.sin.sin_addr,
+			       sizeof(struct in_addr));
+	default:
+		BUG();
+	}
+}
+
+/*
+ * Allocate a new local endpoint.
+ */
+static struct rxrpc_local *rxrpc_alloc_local(const struct sockaddr_rxrpc *srx)
+{
+	struct rxrpc_local *local;
+
+	local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
+	if (local) {
+		atomic_set(&local->usage, 1);
+		INIT_LIST_HEAD(&local->link);
+		INIT_WORK(&local->processor, rxrpc_local_processor);
+		INIT_LIST_HEAD(&local->services);
+		init_rwsem(&local->defrag_sem);
+		skb_queue_head_init(&local->accept_queue);
+		skb_queue_head_init(&local->reject_queue);
+		skb_queue_head_init(&local->event_queue);
+		local->client_conns = RB_ROOT;
+		spin_lock_init(&local->client_conns_lock);
+		spin_lock_init(&local->lock);
+		rwlock_init(&local->services_lock);
+		local->debug_id = atomic_inc_return(&rxrpc_debug_id);
+		memcpy(&local->srx, srx, sizeof(*srx));
+	}
+
+	_leave(" = %p", local);
+	return local;
+}
+
+/*
+ * create the local socket
+ * - must be called with rxrpc_local_mutex locked
+ */
+static int rxrpc_open_socket(struct rxrpc_local *local)
+{
+	struct sock *sock;
+	int ret, opt;
+
+	_enter("%p{%d}", local, local->srx.transport_type);
+
+	/* create a socket to represent the local endpoint */
+	ret = sock_create_kern(&init_net, PF_INET, local->srx.transport_type,
+			       IPPROTO_UDP, &local->socket);
+	if (ret < 0) {
+		_leave(" = %d [socket]", ret);
+		return ret;
+	}
+
+	/* if a local address was supplied then bind it */
+	if (local->srx.transport_len > sizeof(sa_family_t)) {
+		_debug("bind");
+		ret = kernel_bind(local->socket,
+				  (struct sockaddr *)&local->srx.transport,
+				  local->srx.transport_len);
+		if (ret < 0) {
+			_debug("bind failed %d", ret);
+			goto error;
+		}
+	}
+
+	/* we want to receive ICMP errors */
+	opt = 1;
+	ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
+				(char *) &opt, sizeof(opt));
+	if (ret < 0) {
+		_debug("setsockopt failed");
+		goto error;
+	}
+
+	/* we want to set the don't fragment bit */
+	opt = IP_PMTUDISC_DO;
+	ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
+				(char *) &opt, sizeof(opt));
+	if (ret < 0) {
+		_debug("setsockopt failed");
+		goto error;
+	}
+
+	/* set the socket up */
+	sock = local->socket->sk;
+	sock->sk_user_data	= local;
+	sock->sk_data_ready	= rxrpc_data_ready;
+	sock->sk_error_report	= rxrpc_error_report;
+	_leave(" = 0");
+	return 0;
+
+error:
+	kernel_sock_shutdown(local->socket, SHUT_RDWR);
+	local->socket->sk->sk_user_data = NULL;
+	sock_release(local->socket);
+	local->socket = NULL;
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Look up or create a new local endpoint using the specified local address.
+ */
+struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *srx)
+{
+	struct rxrpc_local *local;
+	struct list_head *cursor;
+	const char *age;
+	long diff;
+	int ret;
+
+	if (srx->transport.family == AF_INET) {
+		_enter("{%d,%u,%pI4+%hu}",
+		       srx->transport_type,
+		       srx->transport.family,
+		       &srx->transport.sin.sin_addr,
+		       ntohs(srx->transport.sin.sin_port));
+	} else {
+		_enter("{%d,%u}",
+		       srx->transport_type,
+		       srx->transport.family);
+		return ERR_PTR(-EAFNOSUPPORT);
+	}
+
+	mutex_lock(&rxrpc_local_mutex);
+
+	for (cursor = rxrpc_local_endpoints.next;
+	     cursor != &rxrpc_local_endpoints;
+	     cursor = cursor->next) {
+		local = list_entry(cursor, struct rxrpc_local, link);
+
+		diff = rxrpc_local_cmp_key(local, srx);
+		if (diff < 0)
+			continue;
+		if (diff > 0)
+			break;
+
+		/* Services aren't allowed to share transport sockets, so
+		 * reject that here.  It is possible that the object is dying -
+		 * but it may also still have the local transport address that
+		 * we want bound.
+		 */
+		if (srx->srx_service) {
+			local = NULL;
+			goto addr_in_use;
+		}
+
+		/* Found a match.  We replace a dying object.  Attempting to
+		 * bind the transport socket may still fail if we're attempting
+		 * to use a local address that the dying object is still using.
+		 */
+		if (!rxrpc_get_local_maybe(local)) {
+			cursor = cursor->next;
+			list_del_init(&local->link);
+			break;
+		}
+
+		age = "old";
+		goto found;
+	}
+
+	local = rxrpc_alloc_local(srx);
+	if (!local)
+		goto nomem;
+
+	ret = rxrpc_open_socket(local);
+	if (ret < 0)
+		goto sock_error;
+
+	list_add_tail(&local->link, cursor);
+	age = "new";
+
+found:
+	mutex_unlock(&rxrpc_local_mutex);
+
+	_net("LOCAL %s %d {%d,%u,%pI4+%hu}",
+	     age,
+	     local->debug_id,
+	     local->srx.transport_type,
+	     local->srx.transport.family,
+	     &local->srx.transport.sin.sin_addr,
+	     ntohs(local->srx.transport.sin.sin_port));
+
+	_leave(" = %p", local);
+	return local;
+
+nomem:
+	ret = -ENOMEM;
+sock_error:
+	mutex_unlock(&rxrpc_local_mutex);
+	kfree(local);
+	_leave(" = %d", ret);
+	return ERR_PTR(ret);
+
+addr_in_use:
+	mutex_unlock(&rxrpc_local_mutex);
+	_leave(" = -EADDRINUSE");
+	return ERR_PTR(-EADDRINUSE);
+}
+
+/*
+ * A local endpoint reached its end of life.
+ */
+void __rxrpc_put_local(struct rxrpc_local *local)
+{
+	_enter("%d", local->debug_id);
+	rxrpc_queue_work(&local->processor);
+}
+
+/*
+ * Destroy a local endpoint's socket and then hand the record to RCU to dispose
+ * of.
+ *
+ * Closing the socket cannot be done from bottom half context or RCU callback
+ * context because it might sleep.
+ */
+static void rxrpc_local_destroyer(struct rxrpc_local *local)
+{
+	struct socket *socket = local->socket;
+
+	_enter("%d", local->debug_id);
+
+	/* We can get a race between an incoming call packet queueing the
+	 * processor again and the work processor starting the destruction
+	 * process which will shut down the UDP socket.
+	 */
+	if (local->dead) {
+		_leave(" [already dead]");
+		return;
+	}
+	local->dead = true;
+
+	mutex_lock(&rxrpc_local_mutex);
+	list_del_init(&local->link);
+	mutex_unlock(&rxrpc_local_mutex);
+
+	ASSERT(RB_EMPTY_ROOT(&local->client_conns));
+	ASSERT(list_empty(&local->services));
+
+	if (socket) {
+		local->socket = NULL;
+		kernel_sock_shutdown(socket, SHUT_RDWR);
+		socket->sk->sk_user_data = NULL;
+		sock_release(socket);
+	}
+
+	/* At this point, there should be no more packets coming in to the
+	 * local endpoint.
+	 */
+	rxrpc_purge_queue(&local->accept_queue);
+	rxrpc_purge_queue(&local->reject_queue);
+	rxrpc_purge_queue(&local->event_queue);
+
+	_debug("rcu local %d", local->debug_id);
+	call_rcu(&local->rcu, rxrpc_local_rcu);
+}
+
+/*
+ * Process events on an endpoint
+ */
+static void rxrpc_local_processor(struct work_struct *work)
+{
+	struct rxrpc_local *local =
+		container_of(work, struct rxrpc_local, processor);
+	bool again;
+
+	_enter("%d", local->debug_id);
+
+	do {
+		again = false;
+		if (atomic_read(&local->usage) == 0)
+			return rxrpc_local_destroyer(local);
+
+		if (!skb_queue_empty(&local->accept_queue)) {
+			rxrpc_accept_incoming_calls(local);
+			again = true;
+		}
+
+		if (!skb_queue_empty(&local->reject_queue)) {
+			rxrpc_reject_packets(local);
+			again = true;
+		}
+
+		if (!skb_queue_empty(&local->event_queue)) {
+			rxrpc_process_local_events(local);
+			again = true;
+		}
+	} while (again);
+}
+
+/*
+ * Destroy a local endpoint after the RCU grace period expires.
+ */
+static void rxrpc_local_rcu(struct rcu_head *rcu)
+{
+	struct rxrpc_local *local = container_of(rcu, struct rxrpc_local, rcu);
+
+	_enter("%d", local->debug_id);
+
+	ASSERT(!work_pending(&local->processor));
+
+	_net("DESTROY LOCAL %d", local->debug_id);
+	kfree(local);
+	_leave("");
+}
+
+/*
+ * Verify the local endpoint list is empty by this point.
+ */
+void __exit rxrpc_destroy_all_locals(void)
+{
+	struct rxrpc_local *local;
+
+	_enter("");
+
+	if (list_empty(&rxrpc_local_endpoints))
+		return;
+
+	mutex_lock(&rxrpc_local_mutex);
+	list_for_each_entry(local, &rxrpc_local_endpoints, link) {
+		pr_err("AF_RXRPC: Leaked local %p {%d}\n",
+		       local, atomic_read(&local->usage));
+	}
+	mutex_unlock(&rxrpc_local_mutex);
+	BUG();
+}
diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c
index 1afe9876e79f..bdc5e42fe600 100644
--- a/net/rxrpc/misc.c
+++ b/net/rxrpc/misc.c
@@ -15,6 +15,12 @@
 #include "ar-internal.h"
 
 /*
+ * The maximum listening backlog queue size that may be set on a socket by
+ * listen().
+ */
+unsigned int rxrpc_max_backlog __read_mostly = 10;
+
+/*
  * How long to wait before scheduling ACK generation after seeing a
  * packet with RXRPC_REQUEST_ACK set (in jiffies).
  */
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/output.c
index ea619535f0ed..f4bda06b7d2d 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/output.c
@@ -32,13 +32,14 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 /*
  * extract control messages from the sendmsg() control buffer
  */
-static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg,
+static int rxrpc_sendmsg_cmsg(struct msghdr *msg,
 			      unsigned long *user_call_ID,
 			      enum rxrpc_command *command,
 			      u32 *abort_code,
-			      bool server)
+			      bool *_exclusive)
 {
 	struct cmsghdr *cmsg;
+	bool got_user_ID = false;
 	int len;
 
 	*command = RXRPC_CMD_SEND_DATA;
@@ -70,6 +71,7 @@ static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 					CMSG_DATA(cmsg);
 			}
 			_debug("User Call ID %lx", *user_call_ID);
+			got_user_ID = true;
 			break;
 
 		case RXRPC_ABORT:
@@ -90,15 +92,20 @@ static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 			*command = RXRPC_CMD_ACCEPT;
 			if (len != 0)
 				return -EINVAL;
-			if (!server)
-				return -EISCONN;
 			break;
 
+		case RXRPC_EXCLUSIVE_CALL:
+			*_exclusive = true;
+			if (len != 0)
+				return -EINVAL;
+			break;
 		default:
 			return -EINVAL;
 		}
 	}
 
+	if (!got_user_ID)
+		return -EINVAL;
 	_leave(" = 0");
 	return 0;
 }
@@ -126,55 +133,78 @@ static void rxrpc_send_abort(struct rxrpc_call *call, u32 abort_code)
 }
 
 /*
+ * Create a new client call for sendmsg().
+ */
+static struct rxrpc_call *
+rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
+				  unsigned long user_call_ID, bool exclusive)
+{
+	struct rxrpc_conn_parameters cp;
+	struct rxrpc_call *call;
+	struct key *key;
+
+	DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx, msg->msg_name);
+
+	_enter("");
+
+	if (!msg->msg_name)
+		return ERR_PTR(-EDESTADDRREQ);
+
+	key = rx->key;
+	if (key && !rx->key->payload.data[0])
+		key = NULL;
+
+	memset(&cp, 0, sizeof(cp));
+	cp.local		= rx->local;
+	cp.key			= rx->key;
+	cp.security_level	= rx->min_sec_level;
+	cp.exclusive		= rx->exclusive | exclusive;
+	cp.service_id		= srx->srx_service;
+	call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, GFP_KERNEL);
+
+	_leave(" = %p\n", call);
+	return call;
+}
+
+/*
  * send a message forming part of a client call through an RxRPC socket
  * - caller holds the socket locked
  * - the socket may be either a client socket or a server socket
  */
-int rxrpc_client_sendmsg(struct rxrpc_sock *rx, struct rxrpc_transport *trans,
-			 struct msghdr *msg, size_t len)
+int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 {
-	struct rxrpc_conn_bundle *bundle;
 	enum rxrpc_command cmd;
 	struct rxrpc_call *call;
 	unsigned long user_call_ID = 0;
-	struct key *key;
-	u16 service_id;
+	bool exclusive = false;
 	u32 abort_code = 0;
 	int ret;
 
 	_enter("");
 
-	ASSERT(trans != NULL);
-
-	ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code,
-				 false);
+	ret = rxrpc_sendmsg_cmsg(msg, &user_call_ID, &cmd, &abort_code,
+				 &exclusive);
 	if (ret < 0)
 		return ret;
 
-	bundle = NULL;
-	if (trans) {
-		service_id = rx->srx.srx_service;
-		if (msg->msg_name) {
-			DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx,
-					 msg->msg_name);
-			service_id = srx->srx_service;
-		}
-		key = rx->key;
-		if (key && !rx->key->payload.data[0])
-			key = NULL;
-		bundle = rxrpc_get_bundle(rx, trans, key, service_id,
-					  GFP_KERNEL);
-		if (IS_ERR(bundle))
-			return PTR_ERR(bundle);
+	if (cmd == RXRPC_CMD_ACCEPT) {
+		if (rx->sk.sk_state != RXRPC_SERVER_LISTENING)
+			return -EINVAL;
+		call = rxrpc_accept_call(rx, user_call_ID);
+		if (IS_ERR(call))
+			return PTR_ERR(call);
+		rxrpc_put_call(call);
+		return 0;
 	}
 
-	call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID,
-				     abort_code == 0, GFP_KERNEL);
-	if (trans)
-		rxrpc_put_bundle(trans, bundle);
-	if (IS_ERR(call)) {
-		_leave(" = %ld", PTR_ERR(call));
-		return PTR_ERR(call);
+	call = rxrpc_find_call_by_user_ID(rx, user_call_ID);
+	if (!call) {
+		if (cmd != RXRPC_CMD_SEND_DATA)
+			return -EBADSLT;
+		call = rxrpc_new_client_call_for_sendmsg(rx, msg, user_call_ID,
+							 exclusive);
+		if (IS_ERR(call))
+			return PTR_ERR(call);
 	}
 
 	_debug("CALL %d USR %lx ST %d on CONN %p",
@@ -182,14 +212,21 @@ int rxrpc_client_sendmsg(struct rxrpc_sock *rx, struct rxrpc_transport *trans,
 
 	if (call->state >= RXRPC_CALL_COMPLETE) {
 		/* it's too late for this call */
-		ret = -ESHUTDOWN;
+		ret = -ECONNRESET;
 	} else if (cmd == RXRPC_CMD_SEND_ABORT) {
 		rxrpc_send_abort(call, abort_code);
+		ret = 0;
 	} else if (cmd != RXRPC_CMD_SEND_DATA) {
 		ret = -EINVAL;
-	} else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
+	} else if (!call->in_clientflag &&
+		   call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
 		/* request phase complete for this client call */
 		ret = -EPROTO;
+	} else if (call->in_clientflag &&
+		   call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+		   call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
+		/* Reply phase not begun or not complete for service call. */
+		ret = -EPROTO;
 	} else {
 		ret = rxrpc_send_data(rx, call, msg, len);
 	}
@@ -268,70 +305,9 @@ void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code)
 EXPORT_SYMBOL(rxrpc_kernel_abort_call);
 
 /*
- * send a message through a server socket
- * - caller holds the socket locked
- */
-int rxrpc_server_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
-{
-	enum rxrpc_command cmd;
-	struct rxrpc_call *call;
-	unsigned long user_call_ID = 0;
-	u32 abort_code = 0;
-	int ret;
-
-	_enter("");
-
-	ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code,
-				 true);
-	if (ret < 0)
-		return ret;
-
-	if (cmd == RXRPC_CMD_ACCEPT) {
-		call = rxrpc_accept_call(rx, user_call_ID);
-		if (IS_ERR(call))
-			return PTR_ERR(call);
-		rxrpc_put_call(call);
-		return 0;
-	}
-
-	call = rxrpc_find_server_call(rx, user_call_ID);
-	if (!call)
-		return -EBADSLT;
-	if (call->state >= RXRPC_CALL_COMPLETE) {
-		ret = -ESHUTDOWN;
-		goto out;
-	}
-
-	switch (cmd) {
-	case RXRPC_CMD_SEND_DATA:
-		if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
-		    call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
-		    call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
-			/* Tx phase not yet begun for this call */
-			ret = -EPROTO;
-			break;
-		}
-
-		ret = rxrpc_send_data(rx, call, msg, len);
-		break;
-
-	case RXRPC_CMD_SEND_ABORT:
-		rxrpc_send_abort(call, abort_code);
-		break;
-	default:
-		BUG();
-	}
-
-	out:
-	rxrpc_put_call(call);
-	_leave(" = %d", ret);
-	return ret;
-}
-
-/*
  * send a packet through the transport endpoint
  */
-int rxrpc_send_packet(struct rxrpc_transport *trans, struct sk_buff *skb)
+int rxrpc_send_data_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
 {
 	struct kvec iov[1];
 	struct msghdr msg;
@@ -342,30 +318,30 @@ int rxrpc_send_packet(struct rxrpc_transport *trans, struct sk_buff *skb)
 	iov[0].iov_base = skb->head;
 	iov[0].iov_len = skb->len;
 
-	msg.msg_name = &trans->peer->srx.transport.sin;
-	msg.msg_namelen = sizeof(trans->peer->srx.transport.sin);
+	msg.msg_name = &conn->params.peer->srx.transport;
+	msg.msg_namelen = conn->params.peer->srx.transport_len;
 	msg.msg_control = NULL;
 	msg.msg_controllen = 0;
 	msg.msg_flags = 0;
 
 	/* send the packet with the don't fragment bit set if we currently
 	 * think it's small enough */
-	if (skb->len - sizeof(struct rxrpc_wire_header) < trans->peer->maxdata) {
-		down_read(&trans->local->defrag_sem);
+	if (skb->len - sizeof(struct rxrpc_wire_header) < conn->params.peer->maxdata) {
+		down_read(&conn->params.local->defrag_sem);
 		/* send the packet by UDP
 		 * - returns -EMSGSIZE if UDP would have to fragment the packet
 		 *   to go out of the interface
 		 *   - in which case, we'll have processed the ICMP error
 		 *     message and update the peer record
 		 */
-		ret = kernel_sendmsg(trans->local->socket, &msg, iov, 1,
+		ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 1,
 				     iov[0].iov_len);
 
-		up_read(&trans->local->defrag_sem);
+		up_read(&conn->params.local->defrag_sem);
 		if (ret == -EMSGSIZE)
 			goto send_fragmentable;
 
-		_leave(" = %d [%u]", ret, trans->peer->maxdata);
+		_leave(" = %d [%u]", ret, conn->params.peer->maxdata);
 		return ret;
 	}
 
@@ -373,21 +349,28 @@ send_fragmentable:
 	/* attempt to send this message with fragmentation enabled */
 	_debug("send fragment");
 
-	down_write(&trans->local->defrag_sem);
-	opt = IP_PMTUDISC_DONT;
-	ret = kernel_setsockopt(trans->local->socket, SOL_IP, IP_MTU_DISCOVER,
-				(char *) &opt, sizeof(opt));
-	if (ret == 0) {
-		ret = kernel_sendmsg(trans->local->socket, &msg, iov, 1,
-				     iov[0].iov_len);
-
-		opt = IP_PMTUDISC_DO;
-		kernel_setsockopt(trans->local->socket, SOL_IP,
-				  IP_MTU_DISCOVER, (char *) &opt, sizeof(opt));
+	down_write(&conn->params.local->defrag_sem);
+
+	switch (conn->params.local->srx.transport.family) {
+	case AF_INET:
+		opt = IP_PMTUDISC_DONT;
+		ret = kernel_setsockopt(conn->params.local->socket,
+					SOL_IP, IP_MTU_DISCOVER,
+					(char *)&opt, sizeof(opt));
+		if (ret == 0) {
+			ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 1,
+					     iov[0].iov_len);
+
+			opt = IP_PMTUDISC_DO;
+			kernel_setsockopt(conn->params.local->socket, SOL_IP,
+					  IP_MTU_DISCOVER,
+					  (char *)&opt, sizeof(opt));
+		}
+		break;
 	}
 
-	up_write(&trans->local->defrag_sem);
-	_leave(" = %d [frag %u]", ret, trans->peer->maxdata);
+	up_write(&conn->params.local->defrag_sem);
+	_leave(" = %d [frag %u]", ret, conn->params.peer->maxdata);
 	return ret;
 }
 
@@ -499,7 +482,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	if (try_to_del_timer_sync(&call->ack_timer) >= 0) {
 		/* the packet may be freed by rxrpc_process_call() before this
 		 * returns */
-		ret = rxrpc_send_packet(call->conn->trans, skb);
+		ret = rxrpc_send_data_packet(call->conn, skb);
 		_net("sent skb %p", skb);
 	} else {
 		_debug("failed to delete ACK timer");
@@ -585,7 +568,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 					goto maybe_error;
 			}
 
-			max = call->conn->trans->peer->maxdata;
+			max = call->conn->params.peer->maxdata;
 			max -= call->conn->security_size;
 			max &= ~(call->conn->size_align - 1UL);
 
@@ -676,7 +659,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 
 			seq = atomic_inc_return(&call->sequence);
 
-			sp->hdr.epoch	= conn->epoch;
+			sp->hdr.epoch	= conn->proto.epoch;
 			sp->hdr.cid	= call->cid;
 			sp->hdr.callNumber = call->call_id;
 			sp->hdr.seq	= seq;
@@ -719,7 +702,9 @@ out:
 call_aborted:
 	rxrpc_free_skb(skb);
 	if (call->state == RXRPC_CALL_NETWORK_ERROR)
-		ret = call->conn->trans->peer->net_error;
+		ret = call->error_report < RXRPC_LOCAL_ERROR_OFFSET ?
+			call->error_report :
+			call->error_report - RXRPC_LOCAL_ERROR_OFFSET;
 	else
 		ret = -ECONNABORTED;
 	_leave(" = %d", ret);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
new file mode 100644
index 000000000000..8940674b5e08
--- /dev/null
+++ b/net/rxrpc/peer_event.c
@@ -0,0 +1,281 @@
+/* Peer event handling, typically ICMP messages.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells ([email protected])
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/errqueue.h>
+#include <linux/udp.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/icmp.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <net/ip.h>
+#include "ar-internal.h"
+
+static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
+
+/*
+ * Find the peer associated with an ICMP packet.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
+						     const struct sk_buff *skb)
+{
+	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+	struct sockaddr_rxrpc srx;
+
+	_enter("");
+
+	memset(&srx, 0, sizeof(srx));
+	srx.transport_type = local->srx.transport_type;
+	srx.transport.family = local->srx.transport.family;
+
+	/* Can we see an ICMP4 packet on an ICMP6 listening socket?  and vice
+	 * versa?
+	 */
+	switch (srx.transport.family) {
+	case AF_INET:
+		srx.transport.sin.sin_port = serr->port;
+		srx.transport_len = sizeof(struct sockaddr_in);
+		switch (serr->ee.ee_origin) {
+		case SO_EE_ORIGIN_ICMP:
+			_net("Rx ICMP");
+			memcpy(&srx.transport.sin.sin_addr,
+			       skb_network_header(skb) + serr->addr_offset,
+			       sizeof(struct in_addr));
+			break;
+		case SO_EE_ORIGIN_ICMP6:
+			_net("Rx ICMP6 on v4 sock");
+			memcpy(&srx.transport.sin.sin_addr,
+			       skb_network_header(skb) + serr->addr_offset + 12,
+			       sizeof(struct in_addr));
+			break;
+		default:
+			memcpy(&srx.transport.sin.sin_addr, &ip_hdr(skb)->saddr,
+			       sizeof(struct in_addr));
+			break;
+		}
+		break;
+
+	default:
+		BUG();
+	}
+
+	return rxrpc_lookup_peer_rcu(local, &srx);
+}
+
+/*
+ * Handle an MTU/fragmentation problem.
+ */
+static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr)
+{
+	u32 mtu = serr->ee.ee_info;
+
+	_net("Rx ICMP Fragmentation Needed (%d)", mtu);
+
+	/* wind down the local interface MTU */
+	if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) {
+		peer->if_mtu = mtu;
+		_net("I/F MTU %u", mtu);
+	}
+
+	if (mtu == 0) {
+		/* they didn't give us a size, estimate one */
+		mtu = peer->if_mtu;
+		if (mtu > 1500) {
+			mtu >>= 1;
+			if (mtu < 1500)
+				mtu = 1500;
+		} else {
+			mtu -= 100;
+			if (mtu < peer->hdrsize)
+				mtu = peer->hdrsize + 4;
+		}
+	}
+
+	if (mtu < peer->mtu) {
+		spin_lock_bh(&peer->lock);
+		peer->mtu = mtu;
+		peer->maxdata = peer->mtu - peer->hdrsize;
+		spin_unlock_bh(&peer->lock);
+		_net("Net MTU %u (maxdata %u)",
+		     peer->mtu, peer->maxdata);
+	}
+}
+
+/*
+ * Handle an error received on the local endpoint.
+ */
+void rxrpc_error_report(struct sock *sk)
+{
+	struct sock_exterr_skb *serr;
+	struct rxrpc_local *local = sk->sk_user_data;
+	struct rxrpc_peer *peer;
+	struct sk_buff *skb;
+
+	_enter("%p{%d}", sk, local->debug_id);
+
+	skb = sock_dequeue_err_skb(sk);
+	if (!skb) {
+		_leave("UDP socket errqueue empty");
+		return;
+	}
+	serr = SKB_EXT_ERR(skb);
+	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
+		_leave("UDP empty message");
+		kfree_skb(skb);
+		return;
+	}
+
+	rxrpc_new_skb(skb);
+
+	rcu_read_lock();
+	peer = rxrpc_lookup_peer_icmp_rcu(local, skb);
+	if (peer && !rxrpc_get_peer_maybe(peer))
+		peer = NULL;
+	if (!peer) {
+		rcu_read_unlock();
+		rxrpc_free_skb(skb);
+		_leave(" [no peer]");
+		return;
+	}
+
+	if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
+	     serr->ee.ee_type == ICMP_DEST_UNREACH &&
+	     serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
+		rxrpc_adjust_mtu(peer, serr);
+		rcu_read_unlock();
+		rxrpc_free_skb(skb);
+		rxrpc_put_peer(peer);
+		_leave(" [MTU update]");
+		return;
+	}
+
+	rxrpc_store_error(peer, serr);
+	rcu_read_unlock();
+	rxrpc_free_skb(skb);
+
+	/* The ref we obtained is passed off to the work item */
+	rxrpc_queue_work(&peer->error_distributor);
+	_leave("");
+}
+
+/*
+ * Map an error report to error codes on the peer record.
+ */
+static void rxrpc_store_error(struct rxrpc_peer *peer,
+			      struct sock_exterr_skb *serr)
+{
+	struct sock_extended_err *ee;
+	int err;
+
+	_enter("");
+
+	ee = &serr->ee;
+
+	_net("Rx Error o=%d t=%d c=%d e=%d",
+	     ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno);
+
+	err = ee->ee_errno;
+
+	switch (ee->ee_origin) {
+	case SO_EE_ORIGIN_ICMP:
+		switch (ee->ee_type) {
+		case ICMP_DEST_UNREACH:
+			switch (ee->ee_code) {
+			case ICMP_NET_UNREACH:
+				_net("Rx Received ICMP Network Unreachable");
+				break;
+			case ICMP_HOST_UNREACH:
+				_net("Rx Received ICMP Host Unreachable");
+				break;
+			case ICMP_PORT_UNREACH:
+				_net("Rx Received ICMP Port Unreachable");
+				break;
+			case ICMP_NET_UNKNOWN:
+				_net("Rx Received ICMP Unknown Network");
+				break;
+			case ICMP_HOST_UNKNOWN:
+				_net("Rx Received ICMP Unknown Host");
+				break;
+			default:
+				_net("Rx Received ICMP DestUnreach code=%u",
+				     ee->ee_code);
+				break;
+			}
+			break;
+
+		case ICMP_TIME_EXCEEDED:
+			_net("Rx Received ICMP TTL Exceeded");
+			break;
+
+		default:
+			_proto("Rx Received ICMP error { type=%u code=%u }",
+			       ee->ee_type, ee->ee_code);
+			break;
+		}
+		break;
+
+	case SO_EE_ORIGIN_NONE:
+	case SO_EE_ORIGIN_LOCAL:
+		_proto("Rx Received local error { error=%d }", err);
+		err += RXRPC_LOCAL_ERROR_OFFSET;
+		break;
+
+	case SO_EE_ORIGIN_ICMP6:
+	default:
+		_proto("Rx Received error report { orig=%u }", ee->ee_origin);
+		break;
+	}
+
+	peer->error_report = err;
+}
+
+/*
+ * Distribute an error that occurred on a peer
+ */
+void rxrpc_peer_error_distributor(struct work_struct *work)
+{
+	struct rxrpc_peer *peer =
+		container_of(work, struct rxrpc_peer, error_distributor);
+	struct rxrpc_call *call;
+	int error_report;
+
+	_enter("");
+
+	error_report = READ_ONCE(peer->error_report);
+
+	_debug("ISSUE ERROR %d", error_report);
+
+	spin_lock_bh(&peer->lock);
+
+	while (!hlist_empty(&peer->error_targets)) {
+		call = hlist_entry(peer->error_targets.first,
+				   struct rxrpc_call, error_link);
+		hlist_del_init(&call->error_link);
+
+		write_lock(&call->state_lock);
+		if (call->state != RXRPC_CALL_COMPLETE &&
+		    call->state < RXRPC_CALL_NETWORK_ERROR) {
+			call->error_report = error_report;
+			call->state = RXRPC_CALL_NETWORK_ERROR;
+			set_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events);
+			rxrpc_queue_call(call);
+		}
+		write_unlock(&call->state_lock);
+	}
+
+	spin_unlock_bh(&peer->lock);
+
+	rxrpc_put_peer(peer);
+	_leave("");
+}
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
new file mode 100644
index 000000000000..01d4930a11f7
--- /dev/null
+++ b/net/rxrpc/peer_object.c
@@ -0,0 +1,315 @@
+/* RxRPC remote transport endpoint record management
+ *
+ * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells ([email protected])
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/udp.h>
+#include <linux/in.h>
+#include <linux/slab.h>
+#include <linux/hashtable.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include "ar-internal.h"
+
+static DEFINE_HASHTABLE(rxrpc_peer_hash, 10);
+static DEFINE_SPINLOCK(rxrpc_peer_hash_lock);
+
+/*
+ * Hash a peer key.
+ */
+static unsigned long rxrpc_peer_hash_key(struct rxrpc_local *local,
+					 const struct sockaddr_rxrpc *srx)
+{
+	const u16 *p;
+	unsigned int i, size;
+	unsigned long hash_key;
+
+	_enter("");
+
+	hash_key = (unsigned long)local / __alignof__(*local);
+	hash_key += srx->transport_type;
+	hash_key += srx->transport_len;
+	hash_key += srx->transport.family;
+
+	switch (srx->transport.family) {
+	case AF_INET:
+		hash_key += (u16 __force)srx->transport.sin.sin_port;
+		size = sizeof(srx->transport.sin.sin_addr);
+		p = (u16 *)&srx->transport.sin.sin_addr;
+		break;
+	default:
+		WARN(1, "AF_RXRPC: Unsupported transport address family\n");
+		return 0;
+	}
+
+	/* Step through the peer address in 16-bit portions for speed */
+	for (i = 0; i < size; i += sizeof(*p), p++)
+		hash_key += *p;
+
+	_leave(" 0x%lx", hash_key);
+	return hash_key;
+}
+
+/*
+ * Compare a peer to a key.  Return -ve, 0 or +ve to indicate less than, same
+ * or greater than.
+ *
+ * Unfortunately, the primitives in linux/hashtable.h don't allow for sorted
+ * buckets and mid-bucket insertion, so we don't make full use of this
+ * information at this point.
+ */
+static long rxrpc_peer_cmp_key(const struct rxrpc_peer *peer,
+			       struct rxrpc_local *local,
+			       const struct sockaddr_rxrpc *srx,
+			       unsigned long hash_key)
+{
+	long diff;
+
+	diff = ((peer->hash_key - hash_key) ?:
+		((unsigned long)peer->local - (unsigned long)local) ?:
+		(peer->srx.transport_type - srx->transport_type) ?:
+		(peer->srx.transport_len - srx->transport_len) ?:
+		(peer->srx.transport.family - srx->transport.family));
+	if (diff != 0)
+		return diff;
+
+	switch (srx->transport.family) {
+	case AF_INET:
+		return ((u16 __force)peer->srx.transport.sin.sin_port -
+			(u16 __force)srx->transport.sin.sin_port) ?:
+			memcmp(&peer->srx.transport.sin.sin_addr,
+			       &srx->transport.sin.sin_addr,
+			       sizeof(struct in_addr));
+	default:
+		BUG();
+	}
+}
+
+/*
+ * Look up a remote transport endpoint for the specified address using RCU.
+ */
+static struct rxrpc_peer *__rxrpc_lookup_peer_rcu(
+	struct rxrpc_local *local,
+	const struct sockaddr_rxrpc *srx,
+	unsigned long hash_key)
+{
+	struct rxrpc_peer *peer;
+
+	hash_for_each_possible_rcu(rxrpc_peer_hash, peer, hash_link, hash_key) {
+		if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) {
+			if (atomic_read(&peer->usage) == 0)
+				return NULL;
+			return peer;
+		}
+	}
+
+	return NULL;
+}
+
+/*
+ * Look up a remote transport endpoint for the specified address using RCU.
+ */
+struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local,
+					 const struct sockaddr_rxrpc *srx)
+{
+	struct rxrpc_peer *peer;
+	unsigned long hash_key = rxrpc_peer_hash_key(local, srx);
+
+	peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
+	if (peer) {
+		switch (srx->transport.family) {
+		case AF_INET:
+			_net("PEER %d {%d,%u,%pI4+%hu}",
+			     peer->debug_id,
+			     peer->srx.transport_type,
+			     peer->srx.transport.family,
+			     &peer->srx.transport.sin.sin_addr,
+			     ntohs(peer->srx.transport.sin.sin_port));
+			break;
+		}
+
+		_leave(" = %p {u=%d}", peer, atomic_read(&peer->usage));
+	}
+	return peer;
+}
+
+/*
+ * assess the MTU size for the network interface through which this peer is
+ * reached
+ */
+static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
+{
+	struct rtable *rt;
+	struct flowi4 fl4;
+
+	peer->if_mtu = 1500;
+
+	rt = ip_route_output_ports(&init_net, &fl4, NULL,
+				   peer->srx.transport.sin.sin_addr.s_addr, 0,
+				   htons(7000), htons(7001),
+				   IPPROTO_UDP, 0, 0);
+	if (IS_ERR(rt)) {
+		_leave(" [route err %ld]", PTR_ERR(rt));
+		return;
+	}
+
+	peer->if_mtu = dst_mtu(&rt->dst);
+	dst_release(&rt->dst);
+
+	_leave(" [if_mtu %u]", peer->if_mtu);
+}
+
+/*
+ * Allocate a peer.
+ */
+struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
+{
+	struct rxrpc_peer *peer;
+
+	_enter("");
+
+	peer = kzalloc(sizeof(struct rxrpc_peer), gfp);
+	if (peer) {
+		atomic_set(&peer->usage, 1);
+		peer->local = local;
+		INIT_HLIST_HEAD(&peer->error_targets);
+		INIT_WORK(&peer->error_distributor,
+			  &rxrpc_peer_error_distributor);
+		peer->service_conns = RB_ROOT;
+		rwlock_init(&peer->conn_lock);
+		spin_lock_init(&peer->lock);
+		peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
+	}
+
+	_leave(" = %p", peer);
+	return peer;
+}
+
+/*
+ * Set up a new peer.
+ */
+static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
+					    struct sockaddr_rxrpc *srx,
+					    unsigned long hash_key,
+					    gfp_t gfp)
+{
+	struct rxrpc_peer *peer;
+
+	_enter("");
+
+	peer = rxrpc_alloc_peer(local, gfp);
+	if (peer) {
+		peer->hash_key = hash_key;
+		memcpy(&peer->srx, srx, sizeof(*srx));
+
+		rxrpc_assess_MTU_size(peer);
+		peer->mtu = peer->if_mtu;
+
+		if (srx->transport.family == AF_INET) {
+			peer->hdrsize = sizeof(struct iphdr);
+			switch (srx->transport_type) {
+			case SOCK_DGRAM:
+				peer->hdrsize += sizeof(struct udphdr);
+				break;
+			default:
+				BUG();
+				break;
+			}
+		} else {
+			BUG();
+		}
+
+		peer->hdrsize += sizeof(struct rxrpc_wire_header);
+		peer->maxdata = peer->mtu - peer->hdrsize;
+	}
+
+	_leave(" = %p", peer);
+	return peer;
+}
+
+/*
+ * obtain a remote transport endpoint for the specified address
+ */
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
+				     struct sockaddr_rxrpc *srx, gfp_t gfp)
+{
+	struct rxrpc_peer *peer, *candidate;
+	unsigned long hash_key = rxrpc_peer_hash_key(local, srx);
+
+	_enter("{%d,%d,%pI4+%hu}",
+	       srx->transport_type,
+	       srx->transport_len,
+	       &srx->transport.sin.sin_addr,
+	       ntohs(srx->transport.sin.sin_port));
+
+	/* search the peer list first */
+	rcu_read_lock();
+	peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
+	if (peer && !rxrpc_get_peer_maybe(peer))
+		peer = NULL;
+	rcu_read_unlock();
+
+	if (!peer) {
+		/* The peer is not yet present in hash - create a candidate
+		 * for a new record and then redo the search.
+		 */
+		candidate = rxrpc_create_peer(local, srx, hash_key, gfp);
+		if (!candidate) {
+			_leave(" = NULL [nomem]");
+			return NULL;
+		}
+
+		spin_lock(&rxrpc_peer_hash_lock);
+
+		/* Need to check that we aren't racing with someone else */
+		peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
+		if (peer && !rxrpc_get_peer_maybe(peer))
+			peer = NULL;
+		if (!peer)
+			hash_add_rcu(rxrpc_peer_hash,
+				     &candidate->hash_link, hash_key);
+
+		spin_unlock(&rxrpc_peer_hash_lock);
+
+		if (peer)
+			kfree(candidate);
+		else
+			peer = candidate;
+	}
+
+	_net("PEER %d {%d,%pI4+%hu}",
+	     peer->debug_id,
+	     peer->srx.transport_type,
+	     &peer->srx.transport.sin.sin_addr,
+	     ntohs(peer->srx.transport.sin.sin_port));
+
+	_leave(" = %p {u=%d}", peer, atomic_read(&peer->usage));
+	return peer;
+}
+
+/*
+ * Discard a ref on a remote peer record.
+ */
+void __rxrpc_put_peer(struct rxrpc_peer *peer)
+{
+	ASSERT(hlist_empty(&peer->error_targets));
+
+	spin_lock(&rxrpc_peer_hash_lock);
+	hash_del_rcu(&peer->hash_link);
+	spin_unlock(&rxrpc_peer_hash_lock);
+
+	kfree_rcu(peer, rcu);
+}
diff --git a/net/rxrpc/ar-proc.c b/net/rxrpc/proc.c
index 225163bc658d..500cdcdc843c 100644
--- a/net/rxrpc/ar-proc.c
+++ b/net/rxrpc/proc.c
@@ -46,7 +46,7 @@ static void rxrpc_call_seq_stop(struct seq_file *seq, void *v)
 
 static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 {
-	struct rxrpc_transport *trans;
+	struct rxrpc_connection *conn;
 	struct rxrpc_call *call;
 	char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1];
 
@@ -59,25 +59,28 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 	}
 
 	call = list_entry(v, struct rxrpc_call, link);
-	trans = call->conn->trans;
 
 	sprintf(lbuff, "%pI4:%u",
-		&trans->local->srx.transport.sin.sin_addr,
-		ntohs(trans->local->srx.transport.sin.sin_port));
+		&call->local->srx.transport.sin.sin_addr,
+		ntohs(call->local->srx.transport.sin.sin_port));
 
-	sprintf(rbuff, "%pI4:%u",
-		&trans->peer->srx.transport.sin.sin_addr,
-		ntohs(trans->peer->srx.transport.sin.sin_port));
+	conn = call->conn;
+	if (conn)
+		sprintf(rbuff, "%pI4:%u",
+			&conn->params.peer->srx.transport.sin.sin_addr,
+			ntohs(conn->params.peer->srx.transport.sin.sin_port));
+	else
+		strcpy(rbuff, "no_connection");
 
 	seq_printf(seq,
 		   "UDP   %-22.22s %-22.22s %4x %08x %08x %s %3u"
 		   " %-8.8s %08x %lx\n",
 		   lbuff,
 		   rbuff,
-		   call->conn->service_id,
+		   call->service_id,
 		   call->cid,
 		   call->call_id,
-		   call->conn->in_clientflag ? "Svc" : "Clt",
+		   call->in_clientflag ? "Svc" : "Clt",
 		   atomic_read(&call->usage),
 		   rxrpc_call_states[call->state],
 		   call->remote_abort ?: call->local_abort,
@@ -129,7 +132,6 @@ static void rxrpc_connection_seq_stop(struct seq_file *seq, void *v)
 static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
 {
 	struct rxrpc_connection *conn;
-	struct rxrpc_transport *trans;
 	char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1];
 
 	if (v == &rxrpc_connections) {
@@ -142,28 +144,27 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
 	}
 
 	conn = list_entry(v, struct rxrpc_connection, link);
-	trans = conn->trans;
 
 	sprintf(lbuff, "%pI4:%u",
-		&trans->local->srx.transport.sin.sin_addr,
-		ntohs(trans->local->srx.transport.sin.sin_port));
+		&conn->params.local->srx.transport.sin.sin_addr,
+		ntohs(conn->params.local->srx.transport.sin.sin_port));
 
 	sprintf(rbuff, "%pI4:%u",
-		&trans->peer->srx.transport.sin.sin_addr,
-		ntohs(trans->peer->srx.transport.sin.sin_port));
+		&conn->params.peer->srx.transport.sin.sin_addr,
+		ntohs(conn->params.peer->srx.transport.sin.sin_port));
 
 	seq_printf(seq,
 		   "UDP   %-22.22s %-22.22s %4x %08x %08x %s %3u"
 		   " %s %08x %08x %08x\n",
 		   lbuff,
 		   rbuff,
-		   conn->service_id,
-		   conn->cid,
+		   conn->params.service_id,
+		   conn->proto.cid,
 		   conn->call_counter,
-		   conn->in_clientflag ? "Svc" : "Clt",
+		   rxrpc_conn_is_service(conn) ? "Svc" : "Clt",
 		   atomic_read(&conn->usage),
 		   rxrpc_conn_states[conn->state],
-		   key_serial(conn->key),
+		   key_serial(conn->params.key),
 		   atomic_read(&conn->serial),
 		   atomic_read(&conn->hi_serial));
 
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/recvmsg.c
index 59706b9f2f7a..a3fa2ed85d63 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -147,9 +147,9 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		if (!continue_call) {
 			if (msg->msg_name) {
 				size_t len =
-					sizeof(call->conn->trans->peer->srx);
+					sizeof(call->conn->params.peer->srx);
 				memcpy(msg->msg_name,
-				       &call->conn->trans->peer->srx, len);
+				       &call->conn->params.peer->srx, len);
 				msg->msg_namelen = len;
 			}
 			sock_recv_timestamp(msg, &rx->sk, skb);
@@ -205,7 +205,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		/* we transferred the whole data packet */
 		if (sp->hdr.flags & RXRPC_LAST_PACKET) {
 			_debug("last");
-			if (call->conn->out_clientflag) {
+			if (rxrpc_conn_is_client(call->conn)) {
 				 /* last byte of reply received */
 				ret = copied;
 				goto terminal_message;
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index d4da538b3d3c..23c05ec6fa28 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -58,9 +58,9 @@ static int rxkad_init_connection_security(struct rxrpc_connection *conn)
 	struct rxrpc_key_token *token;
 	int ret;
 
-	_enter("{%d},{%x}", conn->debug_id, key_serial(conn->key));
+	_enter("{%d},{%x}", conn->debug_id, key_serial(conn->params.key));
 
-	token = conn->key->payload.data[0];
+	token = conn->params.key->payload.data[0];
 	conn->security_ix = token->security_index;
 
 	ci = crypto_alloc_skcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC);
@@ -74,7 +74,7 @@ static int rxkad_init_connection_security(struct rxrpc_connection *conn)
 				   sizeof(token->kad->session_key)) < 0)
 		BUG();
 
-	switch (conn->security_level) {
+	switch (conn->params.security_level) {
 	case RXRPC_SECURITY_PLAIN:
 		break;
 	case RXRPC_SECURITY_AUTH:
@@ -115,14 +115,14 @@ static void rxkad_prime_packet_security(struct rxrpc_connection *conn)
 
 	_enter("");
 
-	if (!conn->key)
+	if (!conn->params.key)
 		return;
 
-	token = conn->key->payload.data[0];
+	token = conn->params.key->payload.data[0];
 	memcpy(&iv, token->kad->session_key, sizeof(iv));
 
-	tmpbuf.x[0] = htonl(conn->epoch);
-	tmpbuf.x[1] = htonl(conn->cid);
+	tmpbuf.x[0] = htonl(conn->proto.epoch);
+	tmpbuf.x[1] = htonl(conn->proto.cid);
 	tmpbuf.x[2] = 0;
 	tmpbuf.x[3] = htonl(conn->security_ix);
 
@@ -220,7 +220,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call,
 	rxkhdr.checksum = 0;
 
 	/* encrypt from the session key */
-	token = call->conn->key->payload.data[0];
+	token = call->conn->params.key->payload.data[0];
 	memcpy(&iv, token->kad->session_key, sizeof(iv));
 
 	sg_init_one(&sg[0], sechdr, sizeof(rxkhdr));
@@ -277,13 +277,13 @@ static int rxkad_secure_packet(const struct rxrpc_call *call,
 	sp = rxrpc_skb(skb);
 
 	_enter("{%d{%x}},{#%u},%zu,",
-	       call->debug_id, key_serial(call->conn->key), sp->hdr.seq,
-	       data_size);
+	       call->debug_id, key_serial(call->conn->params.key),
+	       sp->hdr.seq, data_size);
 
 	if (!call->conn->cipher)
 		return 0;
 
-	ret = key_validate(call->conn->key);
+	ret = key_validate(call->conn->params.key);
 	if (ret < 0)
 		return ret;
 
@@ -312,7 +312,7 @@ static int rxkad_secure_packet(const struct rxrpc_call *call,
 		y = 1; /* zero checksums are not permitted */
 	sp->hdr.cksum = y;
 
-	switch (call->conn->security_level) {
+	switch (call->conn->params.security_level) {
 	case RXRPC_SECURITY_PLAIN:
 		ret = 0;
 		break;
@@ -446,7 +446,7 @@ static int rxkad_verify_packet_encrypt(const struct rxrpc_call *call,
 	skb_to_sgvec(skb, sg, 0, skb->len);
 
 	/* decrypt from the session key */
-	token = call->conn->key->payload.data[0];
+	token = call->conn->params.key->payload.data[0];
 	memcpy(&iv, token->kad->session_key, sizeof(iv));
 
 	skcipher_request_set_tfm(req, call->conn->cipher);
@@ -516,7 +516,7 @@ static int rxkad_verify_packet(const struct rxrpc_call *call,
 	sp = rxrpc_skb(skb);
 
 	_enter("{%d{%x}},{#%u}",
-	       call->debug_id, key_serial(call->conn->key), sp->hdr.seq);
+	       call->debug_id, key_serial(call->conn->params.key), sp->hdr.seq);
 
 	if (!call->conn->cipher)
 		return 0;
@@ -557,7 +557,7 @@ static int rxkad_verify_packet(const struct rxrpc_call *call,
 		return -EPROTO;
 	}
 
-	switch (call->conn->security_level) {
+	switch (call->conn->params.security_level) {
 	case RXRPC_SECURITY_PLAIN:
 		ret = 0;
 		break;
@@ -589,9 +589,9 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 	u32 serial;
 	int ret;
 
-	_enter("{%d,%x}", conn->debug_id, key_serial(conn->key));
+	_enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key));
 
-	ret = key_validate(conn->key);
+	ret = key_validate(conn->params.key);
 	if (ret < 0)
 		return ret;
 
@@ -602,14 +602,14 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 	challenge.min_level	= htonl(0);
 	challenge.__padding	= 0;
 
-	msg.msg_name	= &conn->trans->peer->srx.transport.sin;
-	msg.msg_namelen	= sizeof(conn->trans->peer->srx.transport.sin);
+	msg.msg_name	= &conn->params.peer->srx.transport.sin;
+	msg.msg_namelen	= sizeof(conn->params.peer->srx.transport.sin);
 	msg.msg_control	= NULL;
 	msg.msg_controllen = 0;
 	msg.msg_flags	= 0;
 
-	whdr.epoch	= htonl(conn->epoch);
-	whdr.cid	= htonl(conn->cid);
+	whdr.epoch	= htonl(conn->proto.epoch);
+	whdr.cid	= htonl(conn->proto.cid);
 	whdr.callNumber	= 0;
 	whdr.seq	= 0;
 	whdr.type	= RXRPC_PACKET_TYPE_CHALLENGE;
@@ -617,7 +617,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 	whdr.userStatus	= 0;
 	whdr.securityIndex = conn->security_ix;
 	whdr._rsvd	= 0;
-	whdr.serviceId	= htons(conn->service_id);
+	whdr.serviceId	= htons(conn->params.service_id);
 
 	iov[0].iov_base	= &whdr;
 	iov[0].iov_len	= sizeof(whdr);
@@ -630,7 +630,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 	whdr.serial = htonl(serial);
 	_proto("Tx CHALLENGE %%%u", serial);
 
-	ret = kernel_sendmsg(conn->trans->local->socket, &msg, iov, 2, len);
+	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
 	if (ret < 0) {
 		_debug("sendmsg failed: %d", ret);
 		return -EAGAIN;
@@ -657,8 +657,8 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 
 	_enter("");
 
-	msg.msg_name	= &conn->trans->peer->srx.transport.sin;
-	msg.msg_namelen	= sizeof(conn->trans->peer->srx.transport.sin);
+	msg.msg_name	= &conn->params.peer->srx.transport.sin;
+	msg.msg_namelen	= sizeof(conn->params.peer->srx.transport.sin);
 	msg.msg_control	= NULL;
 	msg.msg_controllen = 0;
 	msg.msg_flags	= 0;
@@ -684,7 +684,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 	whdr.serial = htonl(serial);
 	_proto("Tx RESPONSE %%%u", serial);
 
-	ret = kernel_sendmsg(conn->trans->local->socket, &msg, iov, 3, len);
+	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len);
 	if (ret < 0) {
 		_debug("sendmsg failed: %d", ret);
 		return -EAGAIN;
@@ -771,14 +771,14 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
 	u32 version, nonce, min_level, abort_code;
 	int ret;
 
-	_enter("{%d,%x}", conn->debug_id, key_serial(conn->key));
+	_enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key));
 
-	if (!conn->key) {
+	if (!conn->params.key) {
 		_leave(" = -EPROTO [no key]");
 		return -EPROTO;
 	}
 
-	ret = key_validate(conn->key);
+	ret = key_validate(conn->params.key);
 	if (ret < 0) {
 		*_abort_code = RXKADEXPIRED;
 		return ret;
@@ -801,20 +801,20 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
 		goto protocol_error;
 
 	abort_code = RXKADLEVELFAIL;
-	if (conn->security_level < min_level)
+	if (conn->params.security_level < min_level)
 		goto protocol_error;
 
-	token = conn->key->payload.data[0];
+	token = conn->params.key->payload.data[0];
 
 	/* build the response packet */
 	memset(&resp, 0, sizeof(resp));
 
 	resp.version			= htonl(RXKAD_VERSION);
-	resp.encrypted.epoch		= htonl(conn->epoch);
-	resp.encrypted.cid		= htonl(conn->cid);
+	resp.encrypted.epoch		= htonl(conn->proto.epoch);
+	resp.encrypted.cid		= htonl(conn->proto.cid);
 	resp.encrypted.securityIndex	= htonl(conn->security_ix);
 	resp.encrypted.inc_nonce	= htonl(nonce + 1);
-	resp.encrypted.level		= htonl(conn->security_level);
+	resp.encrypted.level		= htonl(conn->params.security_level);
 	resp.kvno			= htonl(token->kad->kvno);
 	resp.ticket_len			= htonl(token->kad->ticket_len);
 
@@ -1096,9 +1096,9 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	rxkad_decrypt_response(conn, &response, &session_key);
 
 	abort_code = RXKADSEALEDINCON;
-	if (ntohl(response.encrypted.epoch) != conn->epoch)
+	if (ntohl(response.encrypted.epoch) != conn->proto.epoch)
 		goto protocol_error_free;
-	if (ntohl(response.encrypted.cid) != conn->cid)
+	if (ntohl(response.encrypted.cid) != conn->proto.cid)
 		goto protocol_error_free;
 	if (ntohl(response.encrypted.securityIndex) != conn->security_ix)
 		goto protocol_error_free;
@@ -1122,7 +1122,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	level = ntohl(response.encrypted.level);
 	if (level > RXRPC_SECURITY_ENCRYPT)
 		goto protocol_error_free;
-	conn->security_level = level;
+	conn->params.security_level = level;
 
 	/* create a key to hold the security data and expiration time - after
 	 * this the connection security can be handled in exactly the same way
@@ -1164,9 +1164,7 @@ static int rxkad_init(void)
 	/* pin the cipher we need so that the crypto layer doesn't invoke
 	 * keventd to go get it */
 	rxkad_ci = crypto_alloc_skcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(rxkad_ci))
-		return PTR_ERR(rxkad_ci);
-	return 0;
+	return PTR_ERR_OR_ZERO(rxkad_ci);
 }
 
 /*
diff --git a/net/rxrpc/ar-security.c b/net/rxrpc/security.c
index d223253b22fa..814d285ff802 100644
--- a/net/rxrpc/ar-security.c
+++ b/net/rxrpc/security.c
@@ -76,7 +76,7 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn)
 {
 	const struct rxrpc_security *sec;
 	struct rxrpc_key_token *token;
-	struct key *key = conn->key;
+	struct key *key = conn->params.key;
 	int ret;
 
 	_enter("{%d},{%x}", conn->debug_id, key_serial(key));
@@ -113,7 +113,7 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn)
 int rxrpc_init_server_conn_security(struct rxrpc_connection *conn)
 {
 	const struct rxrpc_security *sec;
-	struct rxrpc_local *local = conn->trans->local;
+	struct rxrpc_local *local = conn->params.local;
 	struct rxrpc_sock *rx;
 	struct key *key;
 	key_ref_t kref;
@@ -121,7 +121,7 @@ int rxrpc_init_server_conn_security(struct rxrpc_connection *conn)
 
 	_enter("");
 
-	sprintf(kdesc, "%u:%u", conn->service_id, conn->security_ix);
+	sprintf(kdesc, "%u:%u", conn->params.service_id, conn->security_ix);
 
 	sec = rxrpc_security_lookup(conn->security_ix);
 	if (!sec) {
@@ -132,7 +132,7 @@ int rxrpc_init_server_conn_security(struct rxrpc_connection *conn)
 	/* find the service */
 	read_lock_bh(&local->services_lock);
 	list_for_each_entry(rx, &local->services, listen_link) {
-		if (rx->srx.srx_service == conn->service_id)
+		if (rx->srx.srx_service == conn->params.service_id)
 			goto found_service;
 	}
 
diff --git a/net/rxrpc/ar-skbuff.c b/net/rxrpc/skbuff.c
index eee0cfd9ac8c..eee0cfd9ac8c 100644
--- a/net/rxrpc/ar-skbuff.c
+++ b/net/rxrpc/skbuff.c
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index d20ed575acf4..03ad08774d4e 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -18,6 +18,7 @@ static struct ctl_table_header *rxrpc_sysctl_reg_table;
 static const unsigned int zero = 0;
 static const unsigned int one = 1;
 static const unsigned int four = 4;
+static const unsigned int thirtytwo = 32;
 static const unsigned int n_65535 = 65535;
 static const unsigned int n_max_acks = RXRPC_MAXACKS;
 
@@ -89,16 +90,17 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= (void *)&one,
 	},
+
+	/* Non-time values */
 	{
-		.procname	= "transport_expiry",
-		.data		= &rxrpc_transport_expiry,
+		.procname	= "max_backlog",
+		.data		= &rxrpc_max_backlog,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= (void *)&one,
+		.extra1		= (void *)&four,
+		.extra2		= (void *)&thirtytwo,
 	},
-
-	/* Non-time values */
 	{
 		.procname	= "rx_window_size",
 		.data		= &rxrpc_rx_window_size,
diff --git a/net/rxrpc/utils.c b/net/rxrpc/utils.c
new file mode 100644
index 000000000000..f28122a15a24
--- /dev/null
+++ b/net/rxrpc/utils.c
@@ -0,0 +1,41 @@
+/* Utility routines
+ *
+ * Copyright (C) 2015 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells ([email protected])
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include "ar-internal.h"
+
+/*
+ * Set up an RxRPC address from a socket buffer.
+ */
+void rxrpc_get_addr_from_skb(struct rxrpc_local *local,
+			     const struct sk_buff *skb,
+			     struct sockaddr_rxrpc *srx)
+{
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport.family = local->srx.transport.family;
+
+	/* Can we see an ipv4 UDP packet on an ipv6 UDP socket?  and vice
+	 * versa?
+	 */
+	switch (srx->transport.family) {
+	case AF_INET:
+		srx->transport.sin.sin_port = udp_hdr(skb)->source;
+		srx->transport_len = sizeof(struct sockaddr_in);
+		memcpy(&srx->transport.sin.sin_addr, &ip_hdr(skb)->saddr,
+		       sizeof(struct in_addr));
+		break;
+
+	default:
+		BUG();
+	}
+}
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 336774a535c3..47ec2305f920 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -224,8 +224,8 @@ int tcf_hash_search(struct tc_action_net *tn, struct tc_action *a, u32 index)
 }
 EXPORT_SYMBOL(tcf_hash_search);
 
-int tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a,
-		   int bind)
+bool tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a,
+		    int bind)
 {
 	struct tcf_hashinfo *hinfo = tn->hinfo;
 	struct tcf_common *p = NULL;
@@ -235,9 +235,9 @@ int tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a,
 		p->tcfc_refcnt++;
 		a->priv = p;
 		a->hinfo = hinfo;
-		return 1;
+		return true;
 	}
-	return 0;
+	return false;
 }
 EXPORT_SYMBOL(tcf_hash_check);
 
@@ -283,10 +283,11 @@ err2:
 	p->tcfc_index = index ? index : tcf_hash_new_index(tn);
 	p->tcfc_tm.install = jiffies;
 	p->tcfc_tm.lastuse = jiffies;
+	p->tcfc_tm.firstuse = 0;
 	if (est) {
 		err = gen_new_estimator(&p->tcfc_bstats, p->cpu_bstats,
 					&p->tcfc_rate_est,
-					&p->tcfc_lock, est);
+					&p->tcfc_lock, NULL, est);
 		if (err) {
 			free_percpu(p->cpu_qstats);
 			goto err2;
@@ -503,8 +504,8 @@ nla_put_failure:
 }
 EXPORT_SYMBOL(tcf_action_dump_1);
 
-int
-tcf_action_dump(struct sk_buff *skb, struct list_head *actions, int bind, int ref)
+int tcf_action_dump(struct sk_buff *skb, struct list_head *actions,
+		    int bind, int ref)
 {
 	struct tc_action *a;
 	int err = -EINVAL;
@@ -670,7 +671,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
 	if (err < 0)
 		goto errout;
 
-	if (gnet_stats_copy_basic(&d, p->cpu_bstats, &p->tcfc_bstats) < 0 ||
+	if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfc_bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &p->tcfc_bstats,
 				     &p->tcfc_rate_est) < 0 ||
 	    gnet_stats_copy_queue(&d, p->cpu_qstats,
@@ -687,9 +688,9 @@ errout:
 	return -1;
 }
 
-static int
-tca_get_fill(struct sk_buff *skb, struct list_head *actions, u32 portid, u32 seq,
-	     u16 flags, int event, int bind, int ref)
+static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
+			u32 portid, u32 seq, u16 flags, int event, int bind,
+			int ref)
 {
 	struct tcamsg *t;
 	struct nlmsghdr *nlh;
@@ -730,7 +731,8 @@ act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n,
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
-	if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, 0, 0) <= 0) {
+	if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event,
+			 0, 0) <= 0) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
@@ -838,7 +840,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 	if (a.ops == NULL) /*some idjot trying to flush unknown action */
 		goto err_out;
 
-	nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0);
+	nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION,
+			sizeof(*t), 0);
 	if (!nlh)
 		goto out_module_put;
 	t = nlmsg_data(nlh);
@@ -1001,7 +1004,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n)
 	u32 portid = skb ? NETLINK_CB(skb).portid : 0;
 	int ret = 0, ovr = 0;
 
-	if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETACTION) &&
+	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL);
@@ -1118,7 +1122,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
 		nla_nest_end(skb, nest);
 		ret = skb->len;
 	} else
-		nla_nest_cancel(skb, nest);
+		nlmsg_trim(skb, b);
 
 	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
 	if (NETLINK_CB(cb->skb).portid && ret)
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index c7123e01c2ca..ef74bffa6101 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -154,10 +154,7 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
 	if (ret)
 		goto nla_put_failure;
 
-	tm.install = jiffies_to_clock_t(jiffies - prog->tcf_tm.install);
-	tm.lastuse = jiffies_to_clock_t(jiffies - prog->tcf_tm.lastuse);
-	tm.expires = jiffies_to_clock_t(prog->tcf_tm.expires);
-
+	tcf_tm_dump(&tm, &prog->tcf_tm);
 	if (nla_put_64bit(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm,
 			  TCA_ACT_BPF_PAD))
 		goto nla_put_failure;
@@ -172,7 +169,8 @@ nla_put_failure:
 static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = {
 	[TCA_ACT_BPF_PARMS]	= { .len = sizeof(struct tc_act_bpf) },
 	[TCA_ACT_BPF_FD]	= { .type = NLA_U32 },
-	[TCA_ACT_BPF_NAME]	= { .type = NLA_NUL_STRING, .len = ACT_BPF_NAME_LEN },
+	[TCA_ACT_BPF_NAME]	= { .type = NLA_NUL_STRING,
+				    .len = ACT_BPF_NAME_LEN },
 	[TCA_ACT_BPF_OPS_LEN]	= { .type = NLA_U16 },
 	[TCA_ACT_BPF_OPS]	= { .type = NLA_BINARY,
 				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
@@ -225,15 +223,10 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
 
 	bpf_fd = nla_get_u32(tb[TCA_ACT_BPF_FD]);
 
-	fp = bpf_prog_get(bpf_fd);
+	fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_ACT);
 	if (IS_ERR(fp))
 		return PTR_ERR(fp);
 
-	if (fp->type != BPF_PROG_TYPE_SCHED_ACT) {
-		bpf_prog_put(fp);
-		return -EINVAL;
-	}
-
 	if (tb[TCA_ACT_BPF_NAME]) {
 		name = kmemdup(nla_data(tb[TCA_ACT_BPF_NAME]),
 			       nla_len(tb[TCA_ACT_BPF_NAME]),
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 2ba700c765e0..35a5270f289d 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -44,7 +44,7 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a,
 	int proto;
 
 	spin_lock(&ca->tcf_lock);
-	ca->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&ca->tcf_tm);
 	bstats_update(&ca->tcf_bstats, skb);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
@@ -160,9 +160,7 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a,
 	if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
-	t.install = jiffies_to_clock_t(jiffies - ci->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - ci->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(ci->tcf_tm.expires);
+	tcf_tm_dump(&t, &ci->tcf_tm);
 	if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t,
 			  TCA_CONNMARK_PAD))
 		goto nla_put_failure;
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 28e934ed038a..dcd9ababd351 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -501,7 +501,7 @@ static int tcf_csum(struct sk_buff *skb,
 	u32 update_flags;
 
 	spin_lock(&p->tcf_lock);
-	p->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&p->tcf_tm);
 	bstats_update(&p->tcf_bstats, skb);
 	action = p->tcf_action;
 	update_flags = p->update_flags;
@@ -546,9 +546,8 @@ static int tcf_csum_dump(struct sk_buff *skb,
 
 	if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(p->tcf_tm.expires);
+
+	tcf_tm_dump(&t, &p->tcf_tm);
 	if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_PAD))
 		goto nla_put_failure;
 
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index ec5cc8435238..19058a7f3e5c 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -162,7 +162,8 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 	tm->lastuse = lastuse;
 }
 
-static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
+static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a,
+			 int bind, int ref)
 {
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_gact *gact = a->priv;
@@ -188,9 +189,7 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int
 			goto nla_put_failure;
 	}
 #endif
-	t.install = jiffies_to_clock_t(jiffies - gact->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - gact->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(gact->tcf_tm.expires);
+	tcf_tm_dump(&t, &gact->tcf_tm);
 	if (nla_put_64bit(skb, TCA_GACT_TM, sizeof(t), &t, TCA_GACT_PAD))
 		goto nla_put_failure;
 	return skb->len;
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 658046dfe02d..845ab5119c05 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -106,9 +106,9 @@ int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi)
 }
 EXPORT_SYMBOL_GPL(ife_get_meta_u16);
 
-int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval)
+int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp)
 {
-	mi->metaval = kmemdup(metaval, sizeof(u32), GFP_KERNEL);
+	mi->metaval = kmemdup(metaval, sizeof(u32), gfp);
 	if (!mi->metaval)
 		return -ENOMEM;
 
@@ -116,9 +116,9 @@ int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval)
 }
 EXPORT_SYMBOL_GPL(ife_alloc_meta_u32);
 
-int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval)
+int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp)
 {
-	mi->metaval = kmemdup(metaval, sizeof(u16), GFP_KERNEL);
+	mi->metaval = kmemdup(metaval, sizeof(u16), gfp);
 	if (!mi->metaval)
 		return -ENOMEM;
 
@@ -240,10 +240,10 @@ static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len)
 }
 
 /* called when adding new meta information
- * under ife->tcf_lock
+ * under ife->tcf_lock for existing action
 */
 static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
-				void *val, int len)
+				void *val, int len, bool exists)
 {
 	struct tcf_meta_ops *ops = find_ife_oplist(metaid);
 	int ret = 0;
@@ -251,11 +251,13 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
 	if (!ops) {
 		ret = -ENOENT;
 #ifdef CONFIG_MODULES
-		spin_unlock_bh(&ife->tcf_lock);
+		if (exists)
+			spin_unlock_bh(&ife->tcf_lock);
 		rtnl_unlock();
 		request_module("ifemeta%u", metaid);
 		rtnl_lock();
-		spin_lock_bh(&ife->tcf_lock);
+		if (exists)
+			spin_lock_bh(&ife->tcf_lock);
 		ops = find_ife_oplist(metaid);
 #endif
 	}
@@ -272,10 +274,10 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
 }
 
 /* called when adding new meta information
- * under ife->tcf_lock
+ * under ife->tcf_lock for existing action
 */
 static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
-			int len)
+			int len, bool atomic)
 {
 	struct tcf_meta_info *mi = NULL;
 	struct tcf_meta_ops *ops = find_ife_oplist(metaid);
@@ -284,7 +286,7 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
 	if (!ops)
 		return -ENOENT;
 
-	mi = kzalloc(sizeof(*mi), GFP_KERNEL);
+	mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL);
 	if (!mi) {
 		/*put back what find_ife_oplist took */
 		module_put(ops->owner);
@@ -294,7 +296,7 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
 	mi->metaid = metaid;
 	mi->ops = ops;
 	if (len > 0) {
-		ret = ops->alloc(mi, metaval);
+		ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL);
 		if (ret != 0) {
 			kfree(mi);
 			module_put(ops->owner);
@@ -313,11 +315,13 @@ static int use_all_metadata(struct tcf_ife_info *ife)
 	int rc = 0;
 	int installed = 0;
 
+	read_lock(&ife_mod_lock);
 	list_for_each_entry(o, &ifeoplist, list) {
-		rc = add_metainfo(ife, o->metaid, NULL, 0);
+		rc = add_metainfo(ife, o->metaid, NULL, 0, true);
 		if (rc == 0)
 			installed += 1;
 	}
+	read_unlock(&ife_mod_lock);
 
 	if (installed)
 		return 0;
@@ -385,8 +389,9 @@ static void tcf_ife_cleanup(struct tc_action *a, int bind)
 	spin_unlock_bh(&ife->tcf_lock);
 }
 
-/* under ife->tcf_lock */
-static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb)
+/* under ife->tcf_lock for existing action */
+static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
+			     bool exists)
 {
 	int len = 0;
 	int rc = 0;
@@ -398,11 +403,11 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb)
 			val = nla_data(tb[i]);
 			len = nla_len(tb[i]);
 
-			rc = load_metaops_and_vet(ife, i, val, len);
+			rc = load_metaops_and_vet(ife, i, val, len, exists);
 			if (rc != 0)
 				return rc;
 
-			rc = add_metainfo(ife, i, val, len);
+			rc = add_metainfo(ife, i, val, len, exists);
 			if (rc)
 				return rc;
 		}
@@ -423,7 +428,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	u16 ife_type = 0;
 	u8 *daddr = NULL;
 	u8 *saddr = NULL;
-	int ret = 0, exists = 0;
+	bool exists = false;
+	int ret = 0;
 	int err;
 
 	err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy);
@@ -474,7 +480,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 			saddr = nla_data(tb[TCA_IFE_SMAC]);
 	}
 
-	spin_lock_bh(&ife->tcf_lock);
+	if (exists)
+		spin_lock_bh(&ife->tcf_lock);
 	ife->tcf_action = parm->action;
 
 	if (parm->flags & IFE_ENCODE) {
@@ -504,11 +511,12 @@ metadata_parse_err:
 			if (ret == ACT_P_CREATED)
 				_tcf_ife_cleanup(a, bind);
 
-			spin_unlock_bh(&ife->tcf_lock);
+			if (exists)
+				spin_unlock_bh(&ife->tcf_lock);
 			return err;
 		}
 
-		err = populate_metalist(ife, tb2);
+		err = populate_metalist(ife, tb2, exists);
 		if (err)
 			goto metadata_parse_err;
 
@@ -523,12 +531,14 @@ metadata_parse_err:
 			if (ret == ACT_P_CREATED)
 				_tcf_ife_cleanup(a, bind);
 
-			spin_unlock_bh(&ife->tcf_lock);
+			if (exists)
+				spin_unlock_bh(&ife->tcf_lock);
 			return err;
 		}
 	}
 
-	spin_unlock_bh(&ife->tcf_lock);
+	if (exists)
+		spin_unlock_bh(&ife->tcf_lock);
 
 	if (ret == ACT_P_CREATED)
 		tcf_hash_insert(tn, a);
@@ -553,9 +563,7 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	if (nla_put(skb, TCA_IFE_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
-	t.install = jiffies_to_clock_t(jiffies - ife->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - ife->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(ife->tcf_tm.expires);
+	tcf_tm_dump(&t, &ife->tcf_tm);
 	if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD))
 		goto nla_put_failure;
 
@@ -623,7 +631,7 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 
 	spin_lock(&ife->tcf_lock);
 	bstats_update(&ife->tcf_bstats, skb);
-	ife->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&ife->tcf_tm);
 	spin_unlock(&ife->tcf_lock);
 
 	ifehdrln = ntohs(ifehdrln);
@@ -711,7 +719,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
 
 	spin_lock(&ife->tcf_lock);
 	bstats_update(&ife->tcf_bstats, skb);
-	ife->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&ife->tcf_tm);
 
 	if (!metalen) {		/* no metadata to send */
 		/* abuse overlimits to count when we allow packet
@@ -802,7 +810,7 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a,
 	pr_info_ratelimited("unknown failure(policy neither de/encode\n");
 	spin_lock(&ife->tcf_lock);
 	bstats_update(&ife->tcf_bstats, skb);
-	ife->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&ife->tcf_tm);
 	ife->tcf_qstats.drops++;
 	spin_unlock(&ife->tcf_lock);
 
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 9f002ada7074..b8c50600697a 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -34,7 +34,8 @@ static int ipt_net_id;
 
 static int xt_net_id;
 
-static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook)
+static int ipt_init_target(struct xt_entry_target *t, char *table,
+			   unsigned int hook)
 {
 	struct xt_tgchk_param par;
 	struct xt_target *target;
@@ -96,7 +97,8 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla,
 	struct tcf_ipt *ipt;
 	struct xt_entry_target *td, *t;
 	char *tname;
-	int ret = 0, err, exists = 0;
+	bool exists = false;
+	int ret = 0, err;
 	u32 hook = 0;
 	u32 index = 0;
 
@@ -121,10 +123,13 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla,
 	}
 
 	td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]);
-	if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size)
+	if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) {
+		if (exists)
+			tcf_hash_release(a, bind);
 		return -EINVAL;
+	}
 
-	if (!tcf_hash_check(tn, index, a, bind)) {
+	if (!exists) {
 		ret = tcf_hash_create(tn, index, est, a, sizeof(*ipt), bind,
 				      false);
 		if (ret)
@@ -212,7 +217,7 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
 
 	spin_lock(&ipt->tcf_lock);
 
-	ipt->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&ipt->tcf_tm);
 	bstats_update(&ipt->tcf_bstats, skb);
 
 	/* yes, we have to worry about both in and out dev
@@ -242,7 +247,7 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
 	default:
 		net_notice_ratelimited("tc filter: Bogus netfilter code %d assume ACCEPT\n",
 				       ret);
-		result = TC_POLICE_OK;
+		result = TC_ACT_OK;
 		break;
 	}
 	spin_unlock(&ipt->tcf_lock);
@@ -250,7 +255,8 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
 
 }
 
-static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
+static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind,
+			int ref)
 {
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_ipt *ipt = a->priv;
@@ -277,11 +283,11 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int
 	    nla_put(skb, TCA_IPT_CNT, sizeof(struct tc_cnt), &c) ||
 	    nla_put_string(skb, TCA_IPT_TABLE, ipt->tcfi_tname))
 		goto nla_put_failure;
-	tm.install = jiffies_to_clock_t(jiffies - ipt->tcf_tm.install);
-	tm.lastuse = jiffies_to_clock_t(jiffies - ipt->tcf_tm.lastuse);
-	tm.expires = jiffies_to_clock_t(ipt->tcf_tm.expires);
+
+	tcf_tm_dump(&tm, &ipt->tcf_tm);
 	if (nla_put_64bit(skb, TCA_IPT_TM, sizeof(tm), &tm, TCA_IPT_PAD))
 		goto nla_put_failure;
+
 	kfree(t);
 	return skb->len;
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 128942bc9e42..5b135d357e1e 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -62,7 +62,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	struct tc_mirred *parm;
 	struct tcf_mirred *m;
 	struct net_device *dev;
-	int ret, ok_push = 0, exists = 0;
+	int ret, ok_push = 0;
+	bool exists = false;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -157,7 +158,6 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 	u32 at;
 
 	tcf_lastuse_update(&m->tcf_tm);
-
 	bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
 
 	rcu_read_lock();
@@ -219,9 +219,8 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, i
 
 	if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - m->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - m->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(m->tcf_tm.expires);
+
+	tcf_tm_dump(&t, &m->tcf_tm);
 	if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD))
 		goto nla_put_failure;
 	return skb->len;
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index c0a879f940de..06ccb03f25da 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -103,7 +103,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
 
 	spin_lock(&p->tcf_lock);
 
-	p->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&p->tcf_tm);
 	old_addr = p->old_addr;
 	new_addr = p->new_addr;
 	mask = p->mask;
@@ -264,9 +264,8 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a,
 
 	if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(p->tcf_tm.expires);
+
+	tcf_tm_dump(&t, &p->tcf_tm);
 	if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD))
 		goto nla_put_failure;
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index c6e18f230af6..82d3c1479029 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -121,7 +121,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 
 	spin_lock(&p->tcf_lock);
 
-	p->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&p->tcf_tm);
 
 	if (p->tcfp_nkeys > 0) {
 		struct tc_pedit_key *tkey = p->tcfp_keys;
@@ -200,11 +200,11 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
 
 	if (nla_put(skb, TCA_PEDIT_PARMS, s, opt))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(p->tcf_tm.expires);
+
+	tcf_tm_dump(&t, &p->tcf_tm);
 	if (nla_put_64bit(skb, TCA_PEDIT_TM, sizeof(t), &t, TCA_PEDIT_PAD))
 		goto nla_put_failure;
+
 	kfree(opt);
 	return skb->len;
 
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index b884dae692a1..1e8ede3955f4 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -38,7 +38,7 @@ struct tcf_police {
 	bool			peak_present;
 };
 #define to_police(pc)	\
-	container_of(pc, struct tcf_police, common)
+	container_of(pc->priv, struct tcf_police, common)
 
 #define POL_TAB_MASK     15
 
@@ -115,18 +115,16 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
 	[TCA_POLICE_RESULT]	= { .type = NLA_U32 },
 };
 
-static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
-				 struct nlattr *est, struct tc_action *a,
-				 int ovr, int bind)
+static int tcf_act_police_init(struct net *net, struct nlattr *nla,
+			       struct nlattr *est, struct tc_action *a,
+			       int ovr, int bind)
 {
-	unsigned int h;
 	int ret = 0, err;
 	struct nlattr *tb[TCA_POLICE_MAX + 1];
 	struct tc_police *parm;
 	struct tcf_police *police;
 	struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL;
 	struct tc_action_net *tn = net_generic(net, police_net_id);
-	struct tcf_hashinfo *hinfo = tn->hinfo;
 	int size;
 
 	if (nla == NULL)
@@ -145,7 +143,7 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
 
 	if (parm->index) {
 		if (tcf_hash_search(tn, a, parm->index)) {
-			police = to_police(a->priv);
+			police = to_police(a);
 			if (bind) {
 				police->tcf_bindcnt += 1;
 				police->tcf_refcnt += 1;
@@ -156,16 +154,15 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
 			/* not replacing */
 			return -EEXIST;
 		}
+	} else {
+		ret = tcf_hash_create(tn, parm->index, NULL, a,
+				      sizeof(*police), bind, false);
+		if (ret)
+			return ret;
+		ret = ACT_P_CREATED;
 	}
 
-	police = kzalloc(sizeof(*police), GFP_KERNEL);
-	if (police == NULL)
-		return -ENOMEM;
-	ret = ACT_P_CREATED;
-	police->tcf_refcnt = 1;
-	spin_lock_init(&police->tcf_lock);
-	if (bind)
-		police->tcf_bindcnt = 1;
+	police = to_police(a);
 override:
 	if (parm->rate.rate) {
 		err = -ENOMEM;
@@ -185,7 +182,8 @@ override:
 	if (est) {
 		err = gen_replace_estimator(&police->tcf_bstats, NULL,
 					    &police->tcf_rate_est,
-					    &police->tcf_lock, est);
+					    &police->tcf_lock,
+					    NULL, est);
 		if (err)
 			goto failure_unlock;
 	} else if (tb[TCA_POLICE_AVRATE] &&
@@ -237,16 +235,8 @@ override:
 		return ret;
 
 	police->tcfp_t_c = ktime_get_ns();
-	police->tcf_index = parm->index ? parm->index :
-		tcf_hash_new_index(tn);
-	police->tcf_tm.install = jiffies;
-	police->tcf_tm.lastuse = jiffies;
-	h = tcf_hash(police->tcf_index, POL_TAB_MASK);
-	spin_lock_bh(&hinfo->lock);
-	hlist_add_head(&police->tcf_head, &hinfo->htab[h]);
-	spin_unlock_bh(&hinfo->lock);
+	tcf_hash_insert(tn, a);
 
-	a->priv = police;
 	return ret;
 
 failure_unlock:
@@ -255,7 +245,7 @@ failure:
 	qdisc_put_rtab(P_tab);
 	qdisc_put_rtab(R_tab);
 	if (ret == ACT_P_CREATED)
-		kfree(police);
+		tcf_hash_cleanup(a, est);
 	return err;
 }
 
@@ -347,6 +337,7 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 
 	t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install);
 	t.lastuse = jiffies_to_clock_t(jiffies - police->tcf_tm.lastuse);
+	t.firstuse = jiffies_to_clock_t(jiffies - police->tcf_tm.firstuse);
 	t.expires = jiffies_to_clock_t(police->tcf_tm.expires);
 	if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD))
 		goto nla_put_failure;
@@ -375,7 +366,7 @@ static struct tc_action_ops act_police_ops = {
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_act_police,
 	.dump		=	tcf_act_police_dump,
-	.init		=	tcf_act_police_locate,
+	.init		=	tcf_act_police_init,
 	.walk		=	tcf_act_police_walker,
 	.lookup		=	tcf_police_search,
 };
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index e42f8daca147..318328d34d12 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -35,7 +35,7 @@ static int tcf_simp(struct sk_buff *skb, const struct tc_action *a,
 	struct tcf_defact *d = a->priv;
 
 	spin_lock(&d->tcf_lock);
-	d->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&d->tcf_tm);
 	bstats_update(&d->tcf_bstats, skb);
 
 	/* print policy string followed by _ then packet count
@@ -86,8 +86,9 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	struct nlattr *tb[TCA_DEF_MAX + 1];
 	struct tc_defact *parm;
 	struct tcf_defact *d;
+	bool exists = false;
+	int ret = 0, err;
 	char *defdata;
-	int ret = 0, err, exists = 0;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -158,9 +159,8 @@ static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a,
 	if (nla_put(skb, TCA_DEF_PARMS, sizeof(opt), &opt) ||
 	    nla_put_string(skb, TCA_DEF_DATA, d->tcfd_defdata))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - d->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(d->tcf_tm.expires);
+
+	tcf_tm_dump(&t, &d->tcf_tm);
 	if (nla_put_64bit(skb, TCA_DEF_TM, sizeof(t), &t, TCA_DEF_PAD))
 		goto nla_put_failure;
 	return skb->len;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index e928802966bc..8e573c0f8742 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -37,7 +37,7 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
 	struct tcf_skbedit *d = a->priv;
 
 	spin_lock(&d->tcf_lock);
-	d->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&d->tcf_tm);
 	bstats_update(&d->tcf_bstats, skb);
 
 	if (d->flags & SKBEDIT_F_PRIORITY)
@@ -47,6 +47,8 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
 		skb_set_queue_mapping(skb, d->queue_mapping);
 	if (d->flags & SKBEDIT_F_MARK)
 		skb->mark = d->mark;
+	if (d->flags & SKBEDIT_F_PTYPE)
+		skb->pkt_type = d->ptype;
 
 	spin_unlock(&d->tcf_lock);
 	return d->tcf_action;
@@ -57,6 +59,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
 	[TCA_SKBEDIT_PRIORITY]		= { .len = sizeof(u32) },
 	[TCA_SKBEDIT_QUEUE_MAPPING]	= { .len = sizeof(u16) },
 	[TCA_SKBEDIT_MARK]		= { .len = sizeof(u32) },
+	[TCA_SKBEDIT_PTYPE]		= { .len = sizeof(u16) },
 };
 
 static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
@@ -68,8 +71,9 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	struct tc_skbedit *parm;
 	struct tcf_skbedit *d;
 	u32 flags = 0, *priority = NULL, *mark = NULL;
-	u16 *queue_mapping = NULL;
-	int ret = 0, err, exists = 0;
+	u16 *queue_mapping = NULL, *ptype = NULL;
+	bool exists = false;
+	int ret = 0, err;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -91,6 +95,13 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]);
 	}
 
+	if (tb[TCA_SKBEDIT_PTYPE] != NULL) {
+		ptype = nla_data(tb[TCA_SKBEDIT_PTYPE]);
+		if (!skb_pkt_type_ok(*ptype))
+			return -EINVAL;
+		flags |= SKBEDIT_F_PTYPE;
+	}
+
 	if (tb[TCA_SKBEDIT_MARK] != NULL) {
 		flags |= SKBEDIT_F_MARK;
 		mark = nla_data(tb[TCA_SKBEDIT_MARK]);
@@ -131,6 +142,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		d->queue_mapping = *queue_mapping;
 	if (flags & SKBEDIT_F_MARK)
 		d->mark = *mark;
+	if (flags & SKBEDIT_F_PTYPE)
+		d->ptype = *ptype;
 
 	d->tcf_action = parm->action;
 
@@ -157,20 +170,19 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
 	if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 	if ((d->flags & SKBEDIT_F_PRIORITY) &&
-	    nla_put(skb, TCA_SKBEDIT_PRIORITY, sizeof(d->priority),
-		    &d->priority))
+	    nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, d->priority))
 		goto nla_put_failure;
 	if ((d->flags & SKBEDIT_F_QUEUE_MAPPING) &&
-	    nla_put(skb, TCA_SKBEDIT_QUEUE_MAPPING,
-		    sizeof(d->queue_mapping), &d->queue_mapping))
+	    nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, d->queue_mapping))
 		goto nla_put_failure;
 	if ((d->flags & SKBEDIT_F_MARK) &&
-	    nla_put(skb, TCA_SKBEDIT_MARK, sizeof(d->mark),
-		    &d->mark))
+	    nla_put_u32(skb, TCA_SKBEDIT_MARK, d->mark))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - d->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(d->tcf_tm.expires);
+	if ((d->flags & SKBEDIT_F_PTYPE) &&
+	    nla_put_u16(skb, TCA_SKBEDIT_PTYPE, d->ptype))
+		goto nla_put_failure;
+
+	tcf_tm_dump(&t, &d->tcf_tm);
 	if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD))
 		goto nla_put_failure;
 	return skb->len;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index ac4adc812c12..db9b7ed570ba 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -31,7 +31,7 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
 	int err;
 
 	spin_lock(&v->tcf_lock);
-	v->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&v->tcf_tm);
 	bstats_update(&v->tcf_bstats, skb);
 	action = v->tcf_action;
 
@@ -77,8 +77,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	int action;
 	__be16 push_vid = 0;
 	__be16 push_proto = 0;
-	int ret = 0, exists = 0;
-	int err;
+	bool exists = false;
+	int ret = 0, err;
 
 	if (!nla)
 		return -EINVAL;
@@ -179,12 +179,11 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
 
 	if (v->tcfv_action == TCA_VLAN_ACT_PUSH &&
 	    (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) ||
-	     nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, v->tcfv_push_proto)))
+	     nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL,
+			  v->tcfv_push_proto)))
 		goto nla_put_failure;
 
-	t.install = jiffies_to_clock_t(jiffies - v->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - v->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(v->tcf_tm.expires);
+	tcf_tm_dump(&t, &v->tcf_tm);
 	if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD))
 		goto nla_put_failure;
 	return skb->len;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a75864d93142..843a716a4303 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -103,6 +103,17 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 			  struct nlmsghdr *n, struct tcf_proto *tp,
 			  unsigned long fh, int event);
 
+static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
+				 struct nlmsghdr *n,
+				 struct tcf_proto __rcu **chain, int event)
+{
+	struct tcf_proto __rcu **it_chain;
+	struct tcf_proto *tp;
+
+	for (it_chain = chain; (tp = rtnl_dereference(*it_chain)) != NULL;
+	     it_chain = &tp->next)
+		tfilter_notify(net, oskb, n, tp, 0, event);
+}
 
 /* Select new prio value from the range, managed by kernel. */
 
@@ -156,11 +167,23 @@ replay:
 	cl = 0;
 
 	if (prio == 0) {
-		/* If no priority is given, user wants we allocated it. */
-		if (n->nlmsg_type != RTM_NEWTFILTER ||
-		    !(n->nlmsg_flags & NLM_F_CREATE))
+		switch (n->nlmsg_type) {
+		case RTM_DELTFILTER:
+			if (protocol || t->tcm_handle || tca[TCA_KIND])
+				return -ENOENT;
+			break;
+		case RTM_NEWTFILTER:
+			/* If no priority is provided by the user,
+			 * we allocate one.
+			 */
+			if (n->nlmsg_flags & NLM_F_CREATE) {
+				prio = TC_H_MAKE(0x80000000U, 0U);
+				break;
+			}
+			/* fall-through */
+		default:
 			return -ENOENT;
-		prio = TC_H_MAKE(0x80000000U, 0U);
+		}
 	}
 
 	/* Find head of filter chain. */
@@ -200,6 +223,12 @@ replay:
 	err = -EINVAL;
 	if (chain == NULL)
 		goto errout;
+	if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) {
+		tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER);
+		tcf_destroy_chain(chain);
+		err = 0;
+		goto errout;
+	}
 
 	/* Check the chain for existence of proto-tcf with this priority */
 	for (back = chain;
@@ -351,8 +380,9 @@ errout:
 	return err;
 }
 
-static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp,
-			 unsigned long fh, u32 portid, u32 seq, u16 flags, int event)
+static int tcf_fill_node(struct net *net, struct sk_buff *skb,
+			 struct tcf_proto *tp, unsigned long fh, u32 portid,
+			 u32 seq, u16 flags, int event)
 {
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
@@ -474,9 +504,11 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		    TC_H_MIN(tcm->tcm_info) != tp->protocol)
 			continue;
 		if (t > s_t)
-			memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0]));
+			memset(&cb->args[1], 0,
+			       sizeof(cb->args)-sizeof(cb->args[0]));
 		if (cb->args[1] == 0) {
-			if (tcf_fill_node(net, skb, tp, 0, NETLINK_CB(cb->skb).portid,
+			if (tcf_fill_node(net, skb, tp, 0,
+					  NETLINK_CB(cb->skb).portid,
 					  cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					  RTM_NEWTFILTER) <= 0)
 				break;
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 7b342c779da7..c3002c2c68bb 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -272,15 +272,10 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog,
 
 	bpf_fd = nla_get_u32(tb[TCA_BPF_FD]);
 
-	fp = bpf_prog_get(bpf_fd);
+	fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_CLS);
 	if (IS_ERR(fp))
 		return PTR_ERR(fp);
 
-	if (fp->type != BPF_PROG_TYPE_SCHED_CLS) {
-		bpf_prog_put(fp);
-		return -EINVAL;
-	}
-
 	if (tb[TCA_BPF_NAME]) {
 		name = kmemdup(nla_data(tb[TCA_BPF_NAME]),
 			       nla_len(tb[TCA_BPF_NAME]),
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 730aacafc22d..5060801a2f6d 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -66,6 +66,7 @@ struct cls_fl_filter {
 	struct fl_flow_key key;
 	struct list_head list;
 	u32 handle;
+	u32 flags;
 	struct rcu_head	rcu;
 };
 
@@ -123,6 +124,9 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	struct fl_flow_key skb_key;
 	struct fl_flow_key skb_mkey;
 
+	if (!atomic_read(&head->ht.nelems))
+		return -1;
+
 	fl_clear_masked_range(&skb_key, &head->mask);
 	skb_key.indev_ifindex = skb->skb_iif;
 	/* skb_flow_dissect() does not set n_proto in case an unknown protocol,
@@ -136,7 +140,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	f = rhashtable_lookup_fast(&head->ht,
 				   fl_key_get_start(&skb_mkey, &head->mask),
 				   head->ht_params);
-	if (f) {
+	if (f && !tc_skip_sw(f->flags)) {
 		*res = f->res;
 		return tcf_exts_exec(skb, &f->exts, res);
 	}
@@ -171,7 +175,7 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, unsigned long cookie)
 	struct tc_cls_flower_offload offload = {0};
 	struct tc_to_netdev tc;
 
-	if (!tc_should_offload(dev, 0))
+	if (!tc_should_offload(dev, tp, 0))
 		return;
 
 	offload.command = TC_CLSFLOWER_DESTROY;
@@ -183,19 +187,20 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, unsigned long cookie)
 	dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
 }
 
-static void fl_hw_replace_filter(struct tcf_proto *tp,
-				 struct flow_dissector *dissector,
-				 struct fl_flow_key *mask,
-				 struct fl_flow_key *key,
-				 struct tcf_exts *actions,
-				 unsigned long cookie, u32 flags)
+static int fl_hw_replace_filter(struct tcf_proto *tp,
+				struct flow_dissector *dissector,
+				struct fl_flow_key *mask,
+				struct fl_flow_key *key,
+				struct tcf_exts *actions,
+				unsigned long cookie, u32 flags)
 {
 	struct net_device *dev = tp->q->dev_queue->dev;
 	struct tc_cls_flower_offload offload = {0};
 	struct tc_to_netdev tc;
+	int err;
 
-	if (!tc_should_offload(dev, flags))
-		return;
+	if (!tc_should_offload(dev, tp, flags))
+		return tc_skip_sw(flags) ? -EINVAL : 0;
 
 	offload.command = TC_CLSFLOWER_REPLACE;
 	offload.cookie = cookie;
@@ -207,7 +212,12 @@ static void fl_hw_replace_filter(struct tcf_proto *tp,
 	tc.type = TC_SETUP_CLSFLOWER;
 	tc.cls_flower = &offload;
 
-	dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
+	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
+
+	if (tc_skip_sw(flags))
+		return err;
+
+	return 0;
 }
 
 static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
@@ -216,7 +226,7 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
 	struct tc_cls_flower_offload offload = {0};
 	struct tc_to_netdev tc;
 
-	if (!tc_should_offload(dev, 0))
+	if (!tc_should_offload(dev, tp, 0))
 		return;
 
 	offload.command = TC_CLSFLOWER_STATS;
@@ -524,7 +534,6 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	struct cls_fl_filter *fnew;
 	struct nlattr *tb[TCA_FLOWER_MAX + 1];
 	struct fl_flow_mask mask = {};
-	u32 flags = 0;
 	int err;
 
 	if (!tca[TCA_OPTIONS])
@@ -552,8 +561,14 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	}
 	fnew->handle = handle;
 
-	if (tb[TCA_FLOWER_FLAGS])
-		flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]);
+	if (tb[TCA_FLOWER_FLAGS]) {
+		fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]);
+
+		if (!tc_flags_valid(fnew->flags)) {
+			err = -EINVAL;
+			goto errout;
+		}
+	}
 
 	err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr);
 	if (err)
@@ -563,19 +578,23 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	if (err)
 		goto errout;
 
-	err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
-				     head->ht_params);
+	if (!tc_skip_sw(fnew->flags)) {
+		err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
+					     head->ht_params);
+		if (err)
+			goto errout;
+	}
+
+	err = fl_hw_replace_filter(tp,
+				   &head->dissector,
+				   &mask.key,
+				   &fnew->key,
+				   &fnew->exts,
+				   (unsigned long)fnew,
+				   fnew->flags);
 	if (err)
 		goto errout;
 
-	fl_hw_replace_filter(tp,
-			     &head->dissector,
-			     &mask.key,
-			     &fnew->key,
-			     &fnew->exts,
-			     (unsigned long)fnew,
-			     flags);
-
 	if (fold) {
 		rhashtable_remove_fast(&head->ht, &fold->ht_node,
 				       head->ht_params);
@@ -734,6 +753,8 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 				  sizeof(key->tp.dst))))
 		goto nla_put_failure;
 
+	nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags);
+
 	if (tcf_exts_dump(skb, &f->exts))
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 079b43b3c5d2..ffe593efe930 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -440,7 +440,7 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle)
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;
 
-	if (tc_should_offload(dev, 0)) {
+	if (tc_should_offload(dev, tp, 0)) {
 		offload.cls_u32->command = TC_CLSU32_DELETE_KNODE;
 		offload.cls_u32->knode.handle = handle;
 		dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
@@ -457,20 +457,21 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp,
 	struct tc_to_netdev offload;
 	int err;
 
+	if (!tc_should_offload(dev, tp, flags))
+		return tc_skip_sw(flags) ? -EINVAL : 0;
+
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;
 
-	if (tc_should_offload(dev, flags)) {
-		offload.cls_u32->command = TC_CLSU32_NEW_HNODE;
-		offload.cls_u32->hnode.divisor = h->divisor;
-		offload.cls_u32->hnode.handle = h->handle;
-		offload.cls_u32->hnode.prio = h->prio;
+	offload.cls_u32->command = TC_CLSU32_NEW_HNODE;
+	offload.cls_u32->hnode.divisor = h->divisor;
+	offload.cls_u32->hnode.handle = h->handle;
+	offload.cls_u32->hnode.prio = h->prio;
 
-		err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
-						    tp->protocol, &offload);
-		if (tc_skip_sw(flags))
-			return err;
-	}
+	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
+					    tp->protocol, &offload);
+	if (tc_skip_sw(flags))
+		return err;
 
 	return 0;
 }
@@ -484,7 +485,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h)
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;
 
-	if (tc_should_offload(dev, 0)) {
+	if (tc_should_offload(dev, tp, 0)) {
 		offload.cls_u32->command = TC_CLSU32_DELETE_HNODE;
 		offload.cls_u32->hnode.divisor = h->divisor;
 		offload.cls_u32->hnode.handle = h->handle;
@@ -507,27 +508,28 @@ static int u32_replace_hw_knode(struct tcf_proto *tp,
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;
 
-	if (tc_should_offload(dev, flags)) {
-		offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE;
-		offload.cls_u32->knode.handle = n->handle;
-		offload.cls_u32->knode.fshift = n->fshift;
+	if (!tc_should_offload(dev, tp, flags))
+		return tc_skip_sw(flags) ? -EINVAL : 0;
+
+	offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE;
+	offload.cls_u32->knode.handle = n->handle;
+	offload.cls_u32->knode.fshift = n->fshift;
 #ifdef CONFIG_CLS_U32_MARK
-		offload.cls_u32->knode.val = n->val;
-		offload.cls_u32->knode.mask = n->mask;
+	offload.cls_u32->knode.val = n->val;
+	offload.cls_u32->knode.mask = n->mask;
 #else
-		offload.cls_u32->knode.val = 0;
-		offload.cls_u32->knode.mask = 0;
+	offload.cls_u32->knode.val = 0;
+	offload.cls_u32->knode.mask = 0;
 #endif
-		offload.cls_u32->knode.sel = &n->sel;
-		offload.cls_u32->knode.exts = &n->exts;
-		if (n->ht_down)
-			offload.cls_u32->knode.link_handle = n->ht_down->handle;
-
-		err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
-						    tp->protocol, &offload);
-		if (tc_skip_sw(flags))
-			return err;
-	}
+	offload.cls_u32->knode.sel = &n->sel;
+	offload.cls_u32->knode.exts = &n->exts;
+	if (n->ht_down)
+		offload.cls_u32->knode.link_handle = n->ht_down->handle;
+
+	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
+					    tp->protocol, &offload);
+	if (tc_skip_sw(flags))
+		return err;
 
 	return 0;
 }
@@ -863,7 +865,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	if (tb[TCA_U32_FLAGS]) {
 		flags = nla_get_u32(tb[TCA_U32_FLAGS]);
 		if (!tc_flags_valid(flags))
-			return err;
+			return -EINVAL;
 	}
 
 	n = (struct tc_u_knode *)*arg;
@@ -921,11 +923,17 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		ht->divisor = divisor;
 		ht->handle = handle;
 		ht->prio = tp->prio;
+
+		err = u32_replace_hw_hnode(tp, ht, flags);
+		if (err) {
+			kfree(ht);
+			return err;
+		}
+
 		RCU_INIT_POINTER(ht->next, tp_c->hlist);
 		rcu_assign_pointer(tp_c->hlist, ht);
 		*arg = (unsigned long)ht;
 
-		u32_replace_hw_hnode(tp, ht, flags);
 		return 0;
 	}
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index ddf047df5361..12ebde845523 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -95,8 +95,6 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb,
      Expected action: do not backoff, but wait until queue will clear.
    NET_XMIT_CN	 	- probably this packet enqueued, but another one dropped.
      Expected action: backoff or ignore
-   NET_XMIT_POLICED	- dropped by police.
-     Expected action: backoff or error to real-time apps.
 
    Auxiliary routines:
 
@@ -583,7 +581,6 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
 						 timer);
 
 	rcu_read_lock();
-	qdisc_unthrottled(wd->qdisc);
 	__netif_schedule(qdisc_root(wd->qdisc));
 	rcu_read_unlock();
 
@@ -598,15 +595,12 @@ void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
 }
 EXPORT_SYMBOL(qdisc_watchdog_init);
 
-void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool throttle)
+void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires)
 {
 	if (test_bit(__QDISC_STATE_DEACTIVATED,
 		     &qdisc_root_sleeping(wd->qdisc)->state))
 		return;
 
-	if (throttle)
-		qdisc_throttled(wd->qdisc);
-
 	if (wd->last_expires == expires)
 		return;
 
@@ -620,7 +614,6 @@ EXPORT_SYMBOL(qdisc_watchdog_schedule_ns);
 void qdisc_watchdog_cancel(struct qdisc_watchdog *wd)
 {
 	hrtimer_cancel(&wd->timer);
-	qdisc_unthrottled(wd->qdisc);
 }
 EXPORT_SYMBOL(qdisc_watchdog_cancel);
 
@@ -982,7 +975,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 			rcu_assign_pointer(sch->stab, stab);
 		}
 		if (tca[TCA_RATE]) {
-			spinlock_t *root_lock;
+			seqcount_t *running;
 
 			err = -EOPNOTSUPP;
 			if (sch->flags & TCQ_F_MQROOT)
@@ -991,14 +984,15 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 			if ((sch->parent != TC_H_ROOT) &&
 			    !(sch->flags & TCQ_F_INGRESS) &&
 			    (!p || !(p->flags & TCQ_F_MQROOT)))
-				root_lock = qdisc_root_sleeping_lock(sch);
+				running = qdisc_root_sleeping_running(sch);
 			else
-				root_lock = qdisc_lock(sch);
+				running = &sch->running;
 
 			err = gen_new_estimator(&sch->bstats,
 						sch->cpu_bstats,
 						&sch->rate_est,
-						root_lock,
+						NULL,
+						running,
 						tca[TCA_RATE]);
 			if (err)
 				goto err_out4;
@@ -1061,7 +1055,8 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca)
 		gen_replace_estimator(&sch->bstats,
 				      sch->cpu_bstats,
 				      &sch->rate_est,
-				      qdisc_root_sleeping_lock(sch),
+				      NULL,
+				      qdisc_root_sleeping_running(sch),
 				      tca[TCA_RATE]);
 	}
 out:
@@ -1369,8 +1364,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 		goto nla_put_failure;
 
 	if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS,
-					 qdisc_root_sleeping_lock(q), &d,
-					 TCA_PAD) < 0)
+					 NULL, &d, TCA_PAD) < 0)
 		goto nla_put_failure;
 
 	if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0)
@@ -1381,7 +1375,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 		cpu_qstats = q->cpu_qstats;
 	}
 
-	if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(q),
+				  &d, cpu_bstats, &q->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 ||
 	    gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0)
 		goto nla_put_failure;
@@ -1684,8 +1679,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q,
 		goto nla_put_failure;
 
 	if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS,
-					 qdisc_root_sleeping_lock(q), &d,
-					 TCA_PAD) < 0)
+					 NULL, &d, TCA_PAD) < 0)
 		goto nla_put_failure;
 
 	if (cl_ops->dump_stats && cl_ops->dump_stats(q, cl, &d) < 0)
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 1911af3ca7c0..481e4f12aeb4 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -357,16 +357,17 @@ static struct tcf_proto __rcu **atm_tc_find_tcf(struct Qdisc *sch,
 
 /* --------------------------- Qdisc operations ---------------------------- */
 
-static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			  struct sk_buff **to_free)
 {
 	struct atm_qdisc_data *p = qdisc_priv(sch);
 	struct atm_flow_data *flow;
 	struct tcf_result res;
 	int result;
-	int ret = NET_XMIT_POLICED;
+	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 
 	pr_debug("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p);
-	result = TC_POLICE_OK;	/* be nice to gcc */
+	result = TC_ACT_OK;	/* be nice to gcc */
 	flow = NULL;
 	if (TC_H_MAJ(skb->priority) != sch->handle ||
 	    !(flow = (struct atm_flow_data *)atm_tc_get(sch, skb->priority))) {
@@ -398,12 +399,12 @@ done:
 		switch (result) {
 		case TC_ACT_QUEUED:
 		case TC_ACT_STOLEN:
-			kfree_skb(skb);
+			__qdisc_drop(skb, to_free);
 			return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
 		case TC_ACT_SHOT:
-			kfree_skb(skb);
+			__qdisc_drop(skb, to_free);
 			goto drop;
-		case TC_POLICE_RECLASSIFY:
+		case TC_ACT_RECLASSIFY:
 			if (flow->excess)
 				flow = flow->excess;
 			else
@@ -413,7 +414,7 @@ done:
 #endif
 	}
 
-	ret = qdisc_enqueue(skb, flow->q);
+	ret = qdisc_enqueue(skb, flow->q, to_free);
 	if (ret != NET_XMIT_SUCCESS) {
 drop: __maybe_unused
 		if (net_xmit_drop_count(ret)) {
@@ -519,20 +520,6 @@ static struct sk_buff *atm_tc_peek(struct Qdisc *sch)
 	return p->link.q->ops->peek(p->link.q);
 }
 
-static unsigned int atm_tc_drop(struct Qdisc *sch)
-{
-	struct atm_qdisc_data *p = qdisc_priv(sch);
-	struct atm_flow_data *flow;
-	unsigned int len;
-
-	pr_debug("atm_tc_drop(sch %p,[qdisc %p])\n", sch, p);
-	list_for_each_entry(flow, &p->flows, list) {
-		if (flow->q->ops->drop && (len = flow->q->ops->drop(flow->q)))
-			return len;
-	}
-	return 0;
-}
-
 static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct atm_qdisc_data *p = qdisc_priv(sch);
@@ -637,7 +624,8 @@ atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 {
 	struct atm_flow_data *flow = (struct atm_flow_data *)arg;
 
-	if (gnet_stats_copy_basic(d, NULL, &flow->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &flow->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0)
 		return -1;
 
@@ -671,7 +659,6 @@ static struct Qdisc_ops atm_qdisc_ops __read_mostly = {
 	.enqueue	= atm_tc_enqueue,
 	.dequeue	= atm_tc_dequeue,
 	.peek		= atm_tc_peek,
-	.drop		= atm_tc_drop,
 	.init		= atm_tc_init,
 	.reset		= atm_tc_reset,
 	.destroy	= atm_tc_destroy,
diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c
index 3fee70d9814f..c98a61e980ba 100644
--- a/net/sched/sch_blackhole.c
+++ b/net/sched/sch_blackhole.c
@@ -17,9 +17,10 @@
 #include <linux/skbuff.h>
 #include <net/pkt_sched.h>
 
-static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			     struct sk_buff **to_free)
 {
-	qdisc_drop(skb, sch);
+	qdisc_drop(skb, sch, to_free);
 	return NET_XMIT_SUCCESS;
 }
 
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index baafddf229ce..beb554aa8cfb 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -80,10 +80,6 @@ struct cbq_class {
 	unsigned char		priority;	/* class priority */
 	unsigned char		priority2;	/* priority to be used after overlimit */
 	unsigned char		ewma_log;	/* time constant for idle time calculation */
-	unsigned char		ovl_strategy;
-#ifdef CONFIG_NET_CLS_ACT
-	unsigned char		police;
-#endif
 
 	u32			defmap;
 
@@ -94,10 +90,6 @@ struct cbq_class {
 	u32			avpkt;
 	struct qdisc_rate_table	*R_tab;
 
-	/* Overlimit strategy parameters */
-	void			(*overlimit)(struct cbq_class *cl);
-	psched_tdiff_t		penalty;
-
 	/* General scheduler (WRR) parameters */
 	long			allot;
 	long			quantum;	/* Allotment per WRR round */
@@ -353,7 +345,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl)
 {
 	int toplevel = q->toplevel;
 
-	if (toplevel > cl->level && !(qdisc_is_throttled(cl->q))) {
+	if (toplevel > cl->level) {
 		psched_time_t now = psched_get_time();
 
 		do {
@@ -366,7 +358,8 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl)
 }
 
 static int
-cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+	    struct sk_buff **to_free)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	int uninitialized_var(ret);
@@ -378,14 +371,11 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (cl == NULL) {
 		if (ret & __NET_XMIT_BYPASS)
 			qdisc_qstats_drop(sch);
-		kfree_skb(skb);
+		__qdisc_drop(skb, to_free);
 		return ret;
 	}
 
-#ifdef CONFIG_NET_CLS_ACT
-	cl->q->__parent = sch;
-#endif
-	ret = qdisc_enqueue(skb, cl->q);
+	ret = qdisc_enqueue(skb, cl->q, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->q.qlen++;
 		cbq_mark_toplevel(q, cl);
@@ -402,11 +392,8 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	return ret;
 }
 
-/* Overlimit actions */
-
-/* TC_CBQ_OVL_CLASSIC: (default) penalize leaf class by adding offtime */
-
-static void cbq_ovl_classic(struct cbq_class *cl)
+/* Overlimit action: penalize leaf class by adding offtime */
+static void cbq_overlimit(struct cbq_class *cl)
 {
 	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
 	psched_tdiff_t delay = cl->undertime - q->now;
@@ -456,99 +443,6 @@ static void cbq_ovl_classic(struct cbq_class *cl)
 	}
 }
 
-/* TC_CBQ_OVL_RCLASSIC: penalize by offtime classes in hierarchy, when
- * they go overlimit
- */
-
-static void cbq_ovl_rclassic(struct cbq_class *cl)
-{
-	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
-	struct cbq_class *this = cl;
-
-	do {
-		if (cl->level > q->toplevel) {
-			cl = NULL;
-			break;
-		}
-	} while ((cl = cl->borrow) != NULL);
-
-	if (cl == NULL)
-		cl = this;
-	cbq_ovl_classic(cl);
-}
-
-/* TC_CBQ_OVL_DELAY: delay until it will go to underlimit */
-
-static void cbq_ovl_delay(struct cbq_class *cl)
-{
-	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
-	psched_tdiff_t delay = cl->undertime - q->now;
-
-	if (test_bit(__QDISC_STATE_DEACTIVATED,
-		     &qdisc_root_sleeping(cl->qdisc)->state))
-		return;
-
-	if (!cl->delayed) {
-		psched_time_t sched = q->now;
-		ktime_t expires;
-
-		delay += cl->offtime;
-		if (cl->avgidle < 0)
-			delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log);
-		if (cl->avgidle < cl->minidle)
-			cl->avgidle = cl->minidle;
-		cl->undertime = q->now + delay;
-
-		if (delay > 0) {
-			sched += delay + cl->penalty;
-			cl->penalized = sched;
-			cl->cpriority = TC_CBQ_MAXPRIO;
-			q->pmask |= (1<<TC_CBQ_MAXPRIO);
-
-			expires = ns_to_ktime(PSCHED_TICKS2NS(sched));
-			if (hrtimer_try_to_cancel(&q->delay_timer) &&
-			    ktime_to_ns(ktime_sub(
-					hrtimer_get_expires(&q->delay_timer),
-					expires)) > 0)
-				hrtimer_set_expires(&q->delay_timer, expires);
-			hrtimer_restart(&q->delay_timer);
-			cl->delayed = 1;
-			cl->xstats.overactions++;
-			return;
-		}
-		delay = 1;
-	}
-	if (q->wd_expires == 0 || q->wd_expires > delay)
-		q->wd_expires = delay;
-}
-
-/* TC_CBQ_OVL_LOWPRIO: penalize class by lowering its priority band */
-
-static void cbq_ovl_lowprio(struct cbq_class *cl)
-{
-	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
-
-	cl->penalized = q->now + cl->penalty;
-
-	if (cl->cpriority != cl->priority2) {
-		cl->cpriority = cl->priority2;
-		q->pmask |= (1<<cl->cpriority);
-		cl->xstats.overactions++;
-	}
-	cbq_ovl_classic(cl);
-}
-
-/* TC_CBQ_OVL_DROP: penalize class by dropping */
-
-static void cbq_ovl_drop(struct cbq_class *cl)
-{
-	if (cl->q->ops->drop)
-		if (cl->q->ops->drop(cl->q))
-			cl->qdisc->q.qlen--;
-	cl->xstats.overactions++;
-	cbq_ovl_classic(cl);
-}
-
 static psched_tdiff_t cbq_undelay_prio(struct cbq_sched_data *q, int prio,
 				       psched_time_t now)
 {
@@ -620,45 +514,10 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer)
 		hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS_PINNED);
 	}
 
-	qdisc_unthrottled(sch);
 	__netif_schedule(qdisc_root(sch));
 	return HRTIMER_NORESTART;
 }
 
-#ifdef CONFIG_NET_CLS_ACT
-static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child)
-{
-	struct Qdisc *sch = child->__parent;
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	struct cbq_class *cl = q->rx_class;
-
-	q->rx_class = NULL;
-
-	if (cl && (cl = cbq_reclassify(skb, cl)) != NULL) {
-		int ret;
-
-		cbq_mark_toplevel(q, cl);
-
-		q->rx_class = cl;
-		cl->q->__parent = sch;
-
-		ret = qdisc_enqueue(skb, cl->q);
-		if (ret == NET_XMIT_SUCCESS) {
-			sch->q.qlen++;
-			if (!cl->next_alive)
-				cbq_activate_class(cl);
-			return 0;
-		}
-		if (net_xmit_drop_count(ret))
-			qdisc_qstats_drop(sch);
-		return 0;
-	}
-
-	qdisc_qstats_drop(sch);
-	return -1;
-}
-#endif
-
 /*
  * It is mission critical procedure.
  *
@@ -807,7 +666,7 @@ cbq_under_limit(struct cbq_class *cl)
 		cl = cl->borrow;
 		if (!cl) {
 			this_cl->qstats.overlimits++;
-			this_cl->overlimit(this_cl);
+			cbq_overlimit(this_cl);
 			return NULL;
 		}
 		if (cl->level > q->toplevel)
@@ -960,7 +819,6 @@ cbq_dequeue(struct Qdisc *sch)
 		if (skb) {
 			qdisc_bstats_update(sch, skb);
 			sch->q.qlen--;
-			qdisc_unthrottled(sch);
 			return skb;
 		}
 
@@ -1166,31 +1024,6 @@ static void cbq_link_class(struct cbq_class *this)
 	}
 }
 
-static unsigned int cbq_drop(struct Qdisc *sch)
-{
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	struct cbq_class *cl, *cl_head;
-	int prio;
-	unsigned int len;
-
-	for (prio = TC_CBQ_MAXPRIO; prio >= 0; prio--) {
-		cl_head = q->active[prio];
-		if (!cl_head)
-			continue;
-
-		cl = cl_head;
-		do {
-			if (cl->q->ops->drop && (len = cl->q->ops->drop(cl->q))) {
-				sch->q.qlen--;
-				if (!cl->q->q.qlen)
-					cbq_deactivate_class(cl);
-				return len;
-			}
-		} while ((cl = cl->next_alive) != cl_head);
-	}
-	return 0;
-}
-
 static void
 cbq_reset(struct Qdisc *sch)
 {
@@ -1280,50 +1113,6 @@ static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr)
 	return 0;
 }
 
-static int cbq_set_overlimit(struct cbq_class *cl, struct tc_cbq_ovl *ovl)
-{
-	switch (ovl->strategy) {
-	case TC_CBQ_OVL_CLASSIC:
-		cl->overlimit = cbq_ovl_classic;
-		break;
-	case TC_CBQ_OVL_DELAY:
-		cl->overlimit = cbq_ovl_delay;
-		break;
-	case TC_CBQ_OVL_LOWPRIO:
-		if (ovl->priority2 - 1 >= TC_CBQ_MAXPRIO ||
-		    ovl->priority2 - 1 <= cl->priority)
-			return -EINVAL;
-		cl->priority2 = ovl->priority2 - 1;
-		cl->overlimit = cbq_ovl_lowprio;
-		break;
-	case TC_CBQ_OVL_DROP:
-		cl->overlimit = cbq_ovl_drop;
-		break;
-	case TC_CBQ_OVL_RCLASSIC:
-		cl->overlimit = cbq_ovl_rclassic;
-		break;
-	default:
-		return -EINVAL;
-	}
-	cl->penalty = ovl->penalty;
-	return 0;
-}
-
-#ifdef CONFIG_NET_CLS_ACT
-static int cbq_set_police(struct cbq_class *cl, struct tc_cbq_police *p)
-{
-	cl->police = p->police;
-
-	if (cl->q->handle) {
-		if (p->police == TC_POLICE_RECLASSIFY)
-			cl->q->reshape_fail = cbq_reshape_fail;
-		else
-			cl->q->reshape_fail = NULL;
-	}
-	return 0;
-}
-#endif
-
 static int cbq_set_fopt(struct cbq_class *cl, struct tc_cbq_fopt *fopt)
 {
 	cbq_change_defmap(cl, fopt->split, fopt->defmap, fopt->defchange);
@@ -1375,8 +1164,6 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt)
 	q->link.priority = TC_CBQ_MAXPRIO - 1;
 	q->link.priority2 = TC_CBQ_MAXPRIO - 1;
 	q->link.cpriority = TC_CBQ_MAXPRIO - 1;
-	q->link.ovl_strategy = TC_CBQ_OVL_CLASSIC;
-	q->link.overlimit = cbq_ovl_classic;
 	q->link.allot = psched_mtu(qdisc_dev(sch));
 	q->link.quantum = q->link.allot;
 	q->link.weight = q->link.R_tab->rate.rate;
@@ -1463,24 +1250,6 @@ nla_put_failure:
 	return -1;
 }
 
-static int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl)
-{
-	unsigned char *b = skb_tail_pointer(skb);
-	struct tc_cbq_ovl opt;
-
-	opt.strategy = cl->ovl_strategy;
-	opt.priority2 = cl->priority2 + 1;
-	opt.pad = 0;
-	opt.penalty = cl->penalty;
-	if (nla_put(skb, TCA_CBQ_OVL_STRATEGY, sizeof(opt), &opt))
-		goto nla_put_failure;
-	return skb->len;
-
-nla_put_failure:
-	nlmsg_trim(skb, b);
-	return -1;
-}
-
 static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl)
 {
 	unsigned char *b = skb_tail_pointer(skb);
@@ -1500,36 +1269,11 @@ nla_put_failure:
 	return -1;
 }
 
-#ifdef CONFIG_NET_CLS_ACT
-static int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl)
-{
-	unsigned char *b = skb_tail_pointer(skb);
-	struct tc_cbq_police opt;
-
-	if (cl->police) {
-		opt.police = cl->police;
-		opt.__res1 = 0;
-		opt.__res2 = 0;
-		if (nla_put(skb, TCA_CBQ_POLICE, sizeof(opt), &opt))
-			goto nla_put_failure;
-	}
-	return skb->len;
-
-nla_put_failure:
-	nlmsg_trim(skb, b);
-	return -1;
-}
-#endif
-
 static int cbq_dump_attr(struct sk_buff *skb, struct cbq_class *cl)
 {
 	if (cbq_dump_lss(skb, cl) < 0 ||
 	    cbq_dump_rate(skb, cl) < 0 ||
 	    cbq_dump_wrr(skb, cl) < 0 ||
-	    cbq_dump_ovl(skb, cl) < 0 ||
-#ifdef CONFIG_NET_CLS_ACT
-	    cbq_dump_police(skb, cl) < 0 ||
-#endif
 	    cbq_dump_fopt(skb, cl) < 0)
 		return -1;
 	return 0;
@@ -1600,7 +1344,8 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	if (cl->undertime != PSCHED_PASTPERFECT)
 		cl->xstats.undertime = cl->undertime - q->now;
 
-	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->q->q.qlen) < 0)
 		return -1;
@@ -1618,11 +1363,6 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 					&pfifo_qdisc_ops, cl->common.classid);
 		if (new == NULL)
 			return -ENOBUFS;
-	} else {
-#ifdef CONFIG_NET_CLS_ACT
-		if (cl->police == TC_POLICE_RECLASSIFY)
-			new->reshape_fail = cbq_reshape_fail;
-#endif
 	}
 
 	*old = qdisc_replace(sch, new, &cl->q);
@@ -1735,6 +1475,9 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 	if (err < 0)
 		return err;
 
+	if (tb[TCA_CBQ_OVL_STRATEGY] || tb[TCA_CBQ_POLICE])
+		return -EOPNOTSUPP;
+
 	if (cl) {
 		/* Check parent */
 		if (parentid) {
@@ -1755,7 +1498,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 		if (tca[TCA_RATE]) {
 			err = gen_replace_estimator(&cl->bstats, NULL,
 						    &cl->rate_est,
-						    qdisc_root_sleeping_lock(sch),
+						    NULL,
+						    qdisc_root_sleeping_running(sch),
 						    tca[TCA_RATE]);
 			if (err) {
 				qdisc_put_rtab(rtab);
@@ -1782,14 +1526,6 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 			cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT]));
 		}
 
-		if (tb[TCA_CBQ_OVL_STRATEGY])
-			cbq_set_overlimit(cl, nla_data(tb[TCA_CBQ_OVL_STRATEGY]));
-
-#ifdef CONFIG_NET_CLS_ACT
-		if (tb[TCA_CBQ_POLICE])
-			cbq_set_police(cl, nla_data(tb[TCA_CBQ_POLICE]));
-#endif
-
 		if (tb[TCA_CBQ_FOPT])
 			cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT]));
 
@@ -1848,7 +1584,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 
 	if (tca[TCA_RATE]) {
 		err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
-					qdisc_root_sleeping_lock(sch),
+					NULL,
+					qdisc_root_sleeping_running(sch),
 					tca[TCA_RATE]);
 		if (err) {
 			kfree(cl);
@@ -1884,13 +1621,6 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 		cl->maxidle = q->link.maxidle;
 	if (cl->avpkt == 0)
 		cl->avpkt = q->link.avpkt;
-	cl->overlimit = cbq_ovl_classic;
-	if (tb[TCA_CBQ_OVL_STRATEGY])
-		cbq_set_overlimit(cl, nla_data(tb[TCA_CBQ_OVL_STRATEGY]));
-#ifdef CONFIG_NET_CLS_ACT
-	if (tb[TCA_CBQ_POLICE])
-		cbq_set_police(cl, nla_data(tb[TCA_CBQ_POLICE]));
-#endif
 	if (tb[TCA_CBQ_FOPT])
 		cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT]));
 	sch_tree_unlock(sch);
@@ -2035,7 +1765,6 @@ static struct Qdisc_ops cbq_qdisc_ops __read_mostly = {
 	.enqueue	=	cbq_enqueue,
 	.dequeue	=	cbq_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	cbq_drop,
 	.init		=	cbq_init,
 	.reset		=	cbq_reset,
 	.destroy	=	cbq_destroy,
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 0a08c860eee4..3b6d5bd69101 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -115,7 +115,8 @@ static void choke_zap_tail_holes(struct choke_sched_data *q)
 }
 
 /* Drop packet from queue array by creating a "hole" */
-static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
+static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx,
+			      struct sk_buff **to_free)
 {
 	struct choke_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb = q->tab[idx];
@@ -129,7 +130,7 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
 
 	qdisc_qstats_backlog_dec(sch, skb);
 	qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
-	qdisc_drop(skb, sch);
+	qdisc_drop(skb, sch, to_free);
 	--sch->q.qlen;
 }
 
@@ -261,7 +262,8 @@ static bool choke_match_random(const struct choke_sched_data *q,
 	return choke_match_flow(oskb, nskb);
 }
 
-static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			 struct sk_buff **to_free)
 {
 	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	struct choke_sched_data *q = qdisc_priv(sch);
@@ -288,7 +290,7 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		/* Draw a packet at random from queue and compare flow */
 		if (choke_match_random(q, skb, &idx)) {
 			q->stats.matched++;
-			choke_drop_by_idx(sch, idx);
+			choke_drop_by_idx(sch, idx, to_free);
 			goto congestion_drop;
 		}
 
@@ -331,16 +333,16 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	}
 
 	q->stats.pdrop++;
-	return qdisc_drop(skb, sch);
+	return qdisc_drop(skb, sch, to_free);
 
 congestion_drop:
-	qdisc_drop(skb, sch);
+	qdisc_drop(skb, sch, to_free);
 	return NET_XMIT_CN;
 
 other_drop:
 	if (ret & __NET_XMIT_BYPASS)
 		qdisc_qstats_drop(sch);
-	kfree_skb(skb);
+	__qdisc_drop(skb, to_free);
 	return ret;
 }
 
@@ -365,22 +367,6 @@ static struct sk_buff *choke_dequeue(struct Qdisc *sch)
 	return skb;
 }
 
-static unsigned int choke_drop(struct Qdisc *sch)
-{
-	struct choke_sched_data *q = qdisc_priv(sch);
-	unsigned int len;
-
-	len = qdisc_queue_drop(sch);
-	if (len > 0)
-		q->stats.other++;
-	else {
-		if (!red_is_idling(&q->vars))
-			red_start_of_idle_period(&q->vars);
-	}
-
-	return len;
-}
-
 static void choke_reset(struct Qdisc *sch)
 {
 	struct choke_sched_data *q = qdisc_priv(sch);
@@ -391,11 +377,11 @@ static void choke_reset(struct Qdisc *sch)
 		q->head = (q->head + 1) & q->tab_mask;
 		if (!skb)
 			continue;
-		qdisc_qstats_backlog_dec(sch, skb);
-		--sch->q.qlen;
-		qdisc_drop(skb, sch);
+		rtnl_qdisc_drop(skb, sch);
 	}
 
+	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
 	memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
 	q->head = q->tail = 0;
 	red_restart(&q->vars);
@@ -471,7 +457,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 				dropped += qdisc_pkt_len(skb);
 				qdisc_qstats_backlog_dec(sch, skb);
 				--sch->q.qlen;
-				qdisc_drop(skb, sch);
+				rtnl_qdisc_drop(skb, sch);
 			}
 			qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
 			q->head = 0;
@@ -569,7 +555,6 @@ static struct Qdisc_ops choke_qdisc_ops __read_mostly = {
 	.enqueue	=	choke_enqueue,
 	.dequeue	=	choke_dequeue,
 	.peek		=	choke_peek_head,
-	.drop		=	choke_drop,
 	.init		=	choke_init,
 	.destroy	=	choke_destroy,
 	.reset		=	choke_reset,
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index dddf3bb65a32..4002df3c7d9f 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -82,7 +82,8 @@ static void drop_func(struct sk_buff *skb, void *ctx)
 {
 	struct Qdisc *sch = ctx;
 
-	qdisc_drop(skb, sch);
+	kfree_skb(skb);
+	qdisc_qstats_drop(sch);
 }
 
 static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
@@ -107,7 +108,8 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 	return skb;
 }
 
-static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			       struct sk_buff **to_free)
 {
 	struct codel_sched_data *q;
 
@@ -117,7 +119,7 @@ static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	}
 	q = qdisc_priv(sch);
 	q->drop_overlimit++;
-	return qdisc_drop(skb, sch);
+	return qdisc_drop(skb, sch, to_free);
 }
 
 static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = {
@@ -174,7 +176,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 
 		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
-		qdisc_drop(skb, sch);
+		rtnl_qdisc_drop(skb, sch);
 	}
 	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index a63e879e8975..8af5c59eef84 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -91,7 +91,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		if (tca[TCA_RATE]) {
 			err = gen_replace_estimator(&cl->bstats, NULL,
 						    &cl->rate_est,
-						    qdisc_root_sleeping_lock(sch),
+						    NULL,
+						    qdisc_root_sleeping_running(sch),
 						    tca[TCA_RATE]);
 			if (err)
 				return err;
@@ -119,7 +120,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 
 	if (tca[TCA_RATE]) {
 		err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
-					    qdisc_root_sleeping_lock(sch),
+					    NULL,
+					    qdisc_root_sleeping_running(sch),
 					    tca[TCA_RATE]);
 		if (err) {
 			qdisc_destroy(cl->qdisc);
@@ -279,7 +281,8 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	if (qlen)
 		xstats.deficit = cl->deficit;
 
-	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &cl->qdisc->qstats, qlen) < 0)
 		return -1;
@@ -347,7 +350,8 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
 	return NULL;
 }
 
-static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
 {
 	struct drr_sched *q = qdisc_priv(sch);
 	struct drr_class *cl;
@@ -357,11 +361,11 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (cl == NULL) {
 		if (err & __NET_XMIT_BYPASS)
 			qdisc_qstats_drop(sch);
-		kfree_skb(skb);
+		__qdisc_drop(skb, to_free);
 		return err;
 	}
 
-	err = qdisc_enqueue(skb, cl->qdisc);
+	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
@@ -375,6 +379,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		cl->deficit = cl->quantum;
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 	return err;
 }
@@ -407,6 +412,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch)
 
 			bstats_update(&cl->bstats, skb);
 			qdisc_bstats_update(sch, skb);
+			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
 			return skb;
 		}
@@ -418,26 +424,6 @@ out:
 	return NULL;
 }
 
-static unsigned int drr_drop(struct Qdisc *sch)
-{
-	struct drr_sched *q = qdisc_priv(sch);
-	struct drr_class *cl;
-	unsigned int len;
-
-	list_for_each_entry(cl, &q->active, alist) {
-		if (cl->qdisc->ops->drop) {
-			len = cl->qdisc->ops->drop(cl->qdisc);
-			if (len > 0) {
-				sch->q.qlen--;
-				if (cl->qdisc->q.qlen == 0)
-					list_del(&cl->alist);
-				return len;
-			}
-		}
-	}
-	return 0;
-}
-
 static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct drr_sched *q = qdisc_priv(sch);
@@ -463,6 +449,7 @@ static void drr_reset_qdisc(struct Qdisc *sch)
 			qdisc_reset(cl->qdisc);
 		}
 	}
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 
@@ -506,7 +493,6 @@ static struct Qdisc_ops drr_qdisc_ops __read_mostly = {
 	.enqueue	= drr_enqueue,
 	.dequeue	= drr_dequeue,
 	.peek		= qdisc_peek_dequeued,
-	.drop		= drr_drop,
 	.init		= drr_init_qdisc,
 	.reset		= drr_reset_qdisc,
 	.destroy	= drr_destroy_qdisc,
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 34b4ddaca27c..1308bbf460f7 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -191,7 +191,8 @@ static inline struct tcf_proto __rcu **dsmark_find_tcf(struct Qdisc *sch,
 
 /* --------------------------- Qdisc operations ---------------------------- */
 
-static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			  struct sk_buff **to_free)
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 	int err;
@@ -234,7 +235,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 #ifdef CONFIG_NET_CLS_ACT
 		case TC_ACT_QUEUED:
 		case TC_ACT_STOLEN:
-			kfree_skb(skb);
+			__qdisc_drop(skb, to_free);
 			return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
 
 		case TC_ACT_SHOT:
@@ -251,7 +252,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		}
 	}
 
-	err = qdisc_enqueue(skb, p->q);
+	err = qdisc_enqueue(skb, p->q, to_free);
 	if (err != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(err))
 			qdisc_qstats_drop(sch);
@@ -264,7 +265,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	return NET_XMIT_SUCCESS;
 
 drop:
-	qdisc_drop(skb, sch);
+	qdisc_drop(skb, sch, to_free);
 	return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 }
 
@@ -320,23 +321,6 @@ static struct sk_buff *dsmark_peek(struct Qdisc *sch)
 	return p->q->ops->peek(p->q);
 }
 
-static unsigned int dsmark_drop(struct Qdisc *sch)
-{
-	struct dsmark_qdisc_data *p = qdisc_priv(sch);
-	unsigned int len;
-
-	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
-
-	if (p->q->ops->drop == NULL)
-		return 0;
-
-	len = p->q->ops->drop(p->q);
-	if (len)
-		sch->q.qlen--;
-
-	return len;
-}
-
 static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
@@ -489,7 +473,6 @@ static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = {
 	.enqueue	=	dsmark_enqueue,
 	.dequeue	=	dsmark_dequeue,
 	.peek		=	dsmark_peek,
-	.drop		=	dsmark_drop,
 	.init		=	dsmark_init,
 	.reset		=	dsmark_reset,
 	.destroy	=	dsmark_destroy,
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 2177eac0a61e..baeed6a78d28 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -19,32 +19,39 @@
 
 /* 1 band FIFO pseudo-"scheduler" */
 
-static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			 struct sk_buff **to_free)
 {
 	if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
-	return qdisc_reshape_fail(skb, sch);
+	return qdisc_drop(skb, sch, to_free);
 }
 
-static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			 struct sk_buff **to_free)
 {
 	if (likely(skb_queue_len(&sch->q) < sch->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
-	return qdisc_reshape_fail(skb, sch);
+	return qdisc_drop(skb, sch, to_free);
 }
 
-static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			      struct sk_buff **to_free)
 {
+	unsigned int prev_backlog;
+
 	if (likely(skb_queue_len(&sch->q) < sch->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
+	prev_backlog = sch->qstats.backlog;
 	/* queue full, remove one skb to fulfill the limit */
-	__qdisc_queue_drop_head(sch, &sch->q);
+	__qdisc_queue_drop_head(sch, &sch->q, to_free);
 	qdisc_qstats_drop(sch);
 	qdisc_enqueue_tail(skb, sch);
 
+	qdisc_tree_reduce_backlog(sch, 0, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_CN;
 }
 
@@ -99,7 +106,6 @@ struct Qdisc_ops pfifo_qdisc_ops __read_mostly = {
 	.enqueue	=	pfifo_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
-	.drop		=	qdisc_queue_drop,
 	.init		=	fifo_init,
 	.reset		=	qdisc_reset_queue,
 	.change		=	fifo_init,
@@ -114,7 +120,6 @@ struct Qdisc_ops bfifo_qdisc_ops __read_mostly = {
 	.enqueue	=	bfifo_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
-	.drop		=	qdisc_queue_drop,
 	.init		=	fifo_init,
 	.reset		=	qdisc_reset_queue,
 	.change		=	fifo_init,
@@ -129,7 +134,6 @@ struct Qdisc_ops pfifo_head_drop_qdisc_ops __read_mostly = {
 	.enqueue	=	pfifo_tail_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
-	.drop		=	qdisc_queue_drop_head,
 	.init		=	fifo_init,
 	.reset		=	qdisc_reset_queue,
 	.change		=	fifo_init,
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 3c6a47d66a04..e5458b99e09c 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -368,18 +368,19 @@ static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb)
 	}
 }
 
-static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		      struct sk_buff **to_free)
 {
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct fq_flow *f;
 
 	if (unlikely(sch->q.qlen >= sch->limit))
-		return qdisc_drop(skb, sch);
+		return qdisc_drop(skb, sch, to_free);
 
 	f = fq_classify(skb, q);
 	if (unlikely(f->qlen >= q->flow_plimit && f != &q->internal)) {
 		q->stat_flows_plimit++;
-		return qdisc_drop(skb, sch);
+		return qdisc_drop(skb, sch, to_free);
 	}
 
 	f->qlen++;
@@ -445,8 +446,7 @@ begin:
 		if (!head->first) {
 			if (q->time_next_delayed_flow != ~0ULL)
 				qdisc_watchdog_schedule_ns(&q->watchdog,
-							   q->time_next_delayed_flow,
-							   false);
+							   q->time_next_delayed_flow);
 			return NULL;
 		}
 	}
@@ -515,17 +515,25 @@ out:
 	return skb;
 }
 
+static void fq_flow_purge(struct fq_flow *flow)
+{
+	rtnl_kfree_skbs(flow->head, flow->tail);
+	flow->head = NULL;
+	flow->qlen = 0;
+}
+
 static void fq_reset(struct Qdisc *sch)
 {
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct rb_root *root;
-	struct sk_buff *skb;
 	struct rb_node *p;
 	struct fq_flow *f;
 	unsigned int idx;
 
-	while ((skb = fq_dequeue_head(sch, &q->internal)) != NULL)
-		kfree_skb(skb);
+	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
+
+	fq_flow_purge(&q->internal);
 
 	if (!q->fq_root)
 		return;
@@ -536,8 +544,7 @@ static void fq_reset(struct Qdisc *sch)
 			f = container_of(p, struct fq_flow, fq_node);
 			rb_erase(p, root);
 
-			while ((skb = fq_dequeue_head(sch, f)) != NULL)
-				kfree_skb(skb);
+			fq_flow_purge(f);
 
 			kmem_cache_free(fq_flow_cachep, f);
 		}
@@ -738,7 +745,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 		if (!skb)
 			break;
 		drop_len += qdisc_pkt_len(skb);
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 		drop_count++;
 	}
 	qdisc_tree_reduce_backlog(sch, drop_count, drop_len);
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 6883a8971562..a5ea0e9b6be4 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -139,7 +139,8 @@ static inline void flow_queue_add(struct fq_codel_flow *flow,
 	skb->next = NULL;
 }
 
-static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets)
+static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets,
+				  struct sk_buff **to_free)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
@@ -171,8 +172,8 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets)
 	do {
 		skb = dequeue_head(flow);
 		len += qdisc_pkt_len(skb);
-		mem += skb->truesize;
-		kfree_skb(skb);
+		mem += get_codel_cb(skb)->mem_usage;
+		__qdisc_drop(skb, to_free);
 	} while (++i < max_packets && len < threshold);
 
 	flow->dropped += i;
@@ -184,28 +185,21 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets)
 	return idx;
 }
 
-static unsigned int fq_codel_qdisc_drop(struct Qdisc *sch)
-{
-	unsigned int prev_backlog;
-
-	prev_backlog = sch->qstats.backlog;
-	fq_codel_drop(sch, 1U);
-	return prev_backlog - sch->qstats.backlog;
-}
-
-static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			    struct sk_buff **to_free)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 	unsigned int idx, prev_backlog, prev_qlen;
 	struct fq_codel_flow *flow;
 	int uninitialized_var(ret);
+	unsigned int pkt_len;
 	bool memory_limited;
 
 	idx = fq_codel_classify(skb, sch, &ret);
 	if (idx == 0) {
 		if (ret & __NET_XMIT_BYPASS)
 			qdisc_qstats_drop(sch);
-		kfree_skb(skb);
+		__qdisc_drop(skb, to_free);
 		return ret;
 	}
 	idx--;
@@ -222,7 +216,8 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		flow->deficit = q->quantum;
 		flow->dropped = 0;
 	}
-	q->memory_usage += skb->truesize;
+	get_codel_cb(skb)->mem_usage = skb->truesize;
+	q->memory_usage += get_codel_cb(skb)->mem_usage;
 	memory_limited = q->memory_usage > q->memory_limit;
 	if (++sch->q.qlen <= sch->limit && !memory_limited)
 		return NET_XMIT_SUCCESS;
@@ -230,21 +225,32 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	prev_backlog = sch->qstats.backlog;
 	prev_qlen = sch->q.qlen;
 
+	/* save this packet length as it might be dropped by fq_codel_drop() */
+	pkt_len = qdisc_pkt_len(skb);
 	/* fq_codel_drop() is quite expensive, as it performs a linear search
 	 * in q->backlogs[] to find a fat flow.
 	 * So instead of dropping a single packet, drop half of its backlog
 	 * with a 64 packets limit to not add a too big cpu spike here.
 	 */
-	ret = fq_codel_drop(sch, q->drop_batch_size);
+	ret = fq_codel_drop(sch, q->drop_batch_size, to_free);
 
-	q->drop_overlimit += prev_qlen - sch->q.qlen;
+	prev_qlen -= sch->q.qlen;
+	prev_backlog -= sch->qstats.backlog;
+	q->drop_overlimit += prev_qlen;
 	if (memory_limited)
-		q->drop_overmemory += prev_qlen - sch->q.qlen;
-	/* As we dropped packet(s), better let upper stack know this */
-	qdisc_tree_reduce_backlog(sch, prev_qlen - sch->q.qlen,
-				  prev_backlog - sch->qstats.backlog);
+		q->drop_overmemory += prev_qlen;
 
-	return ret == idx ? NET_XMIT_CN : NET_XMIT_SUCCESS;
+	/* As we dropped packet(s), better let upper stack know this.
+	 * If we dropped a packet for this flow, return NET_XMIT_CN,
+	 * but in this case, our parents wont increase their backlogs.
+	 */
+	if (ret == idx) {
+		qdisc_tree_reduce_backlog(sch, prev_qlen - 1,
+					  prev_backlog - pkt_len);
+		return NET_XMIT_CN;
+	}
+	qdisc_tree_reduce_backlog(sch, prev_qlen, prev_backlog);
+	return NET_XMIT_SUCCESS;
 }
 
 /* This is the specific function called from codel_dequeue()
@@ -262,7 +268,7 @@ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx)
 	if (flow->head) {
 		skb = dequeue_head(flow);
 		q->backlogs[flow - q->flows] -= qdisc_pkt_len(skb);
-		q->memory_usage -= skb->truesize;
+		q->memory_usage -= get_codel_cb(skb)->mem_usage;
 		sch->q.qlen--;
 		sch->qstats.backlog -= qdisc_pkt_len(skb);
 	}
@@ -273,7 +279,8 @@ static void drop_func(struct sk_buff *skb, void *ctx)
 {
 	struct Qdisc *sch = ctx;
 
-	qdisc_drop(skb, sch);
+	kfree_skb(skb);
+	qdisc_qstats_drop(sch);
 }
 
 static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
@@ -333,6 +340,12 @@ begin:
 	return skb;
 }
 
+static void fq_codel_flow_purge(struct fq_codel_flow *flow)
+{
+	rtnl_kfree_skbs(flow->head, flow->tail);
+	flow->head = NULL;
+}
+
 static void fq_codel_reset(struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
@@ -343,18 +356,13 @@ static void fq_codel_reset(struct Qdisc *sch)
 	for (i = 0; i < q->flows_cnt; i++) {
 		struct fq_codel_flow *flow = q->flows + i;
 
-		while (flow->head) {
-			struct sk_buff *skb = dequeue_head(flow);
-
-			qdisc_qstats_backlog_dec(sch, skb);
-			kfree_skb(skb);
-		}
-
+		fq_codel_flow_purge(flow);
 		INIT_LIST_HEAD(&flow->flowchain);
 		codel_vars_init(&flow->cvars);
 	}
 	memset(q->backlogs, 0, q->flows_cnt * sizeof(u32));
 	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
 	q->memory_usage = 0;
 }
 
@@ -430,7 +438,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
 		struct sk_buff *skb = fq_codel_dequeue(sch);
 
 		q->cstats.drop_len += qdisc_pkt_len(skb);
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 		q->cstats.drop_count++;
 	}
 	qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len);
@@ -566,11 +574,13 @@ static int fq_codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 	st.qdisc_stats.memory_usage  = q->memory_usage;
 	st.qdisc_stats.drop_overmemory = q->drop_overmemory;
 
+	sch_tree_lock(sch);
 	list_for_each(pos, &q->new_flows)
 		st.qdisc_stats.new_flows_len++;
 
 	list_for_each(pos, &q->old_flows)
 		st.qdisc_stats.old_flows_len++;
+	sch_tree_unlock(sch);
 
 	return gnet_stats_copy_app(d, &st, sizeof(st));
 }
@@ -624,7 +634,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	if (idx < q->flows_cnt) {
 		const struct fq_codel_flow *flow = &q->flows[idx];
-		const struct sk_buff *skb = flow->head;
+		const struct sk_buff *skb;
 
 		memset(&xstats, 0, sizeof(xstats));
 		xstats.type = TCA_FQ_CODEL_XSTATS_CLASS;
@@ -642,14 +652,19 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 				codel_time_to_us(delta) :
 				-codel_time_to_us(-delta);
 		}
-		while (skb) {
-			qs.qlen++;
-			skb = skb->next;
+		if (flow->head) {
+			sch_tree_lock(sch);
+			skb = flow->head;
+			while (skb) {
+				qs.qlen++;
+				skb = skb->next;
+			}
+			sch_tree_unlock(sch);
 		}
 		qs.backlog = q->backlogs[idx];
 		qs.drops = flow->dropped;
 	}
-	if (gnet_stats_copy_queue(d, NULL, &qs, 0) < 0)
+	if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0)
 		return -1;
 	if (idx < q->flows_cnt)
 		return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
@@ -697,7 +712,6 @@ static struct Qdisc_ops fq_codel_qdisc_ops __read_mostly = {
 	.enqueue	=	fq_codel_enqueue,
 	.dequeue	=	fq_codel_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	fq_codel_qdisc_drop,
 	.init		=	fq_codel_init,
 	.reset		=	fq_codel_reset,
 	.destroy	=	fq_codel_destroy,
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 269dd71b3828..e95b67cd5718 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -49,6 +49,7 @@ static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 {
 	q->gso_skb = skb;
 	q->qstats.requeues++;
+	qdisc_qstats_backlog_inc(q, skb);
 	q->q.qlen++;	/* it's still part of the queue */
 	__netif_schedule(q);
 
@@ -76,6 +77,34 @@ static void try_bulk_dequeue_skb(struct Qdisc *q,
 	skb->next = NULL;
 }
 
+/* This variant of try_bulk_dequeue_skb() makes sure
+ * all skbs in the chain are for the same txq
+ */
+static void try_bulk_dequeue_skb_slow(struct Qdisc *q,
+				      struct sk_buff *skb,
+				      int *packets)
+{
+	int mapping = skb_get_queue_mapping(skb);
+	struct sk_buff *nskb;
+	int cnt = 0;
+
+	do {
+		nskb = q->dequeue(q);
+		if (!nskb)
+			break;
+		if (unlikely(skb_get_queue_mapping(nskb) != mapping)) {
+			q->skb_bad_txq = nskb;
+			qdisc_qstats_backlog_inc(q, nskb);
+			q->q.qlen++;
+			break;
+		}
+		skb->next = nskb;
+		skb = nskb;
+	} while (++cnt < 8);
+	(*packets) += cnt;
+	skb->next = NULL;
+}
+
 /* Note that dequeue_skb can possibly return a SKB list (via skb->next).
  * A requeued skb (via q->gso_skb) can also be a SKB list.
  */
@@ -86,31 +115,48 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 	const struct netdev_queue *txq = q->dev_queue;
 
 	*packets = 1;
-	*validate = true;
 	if (unlikely(skb)) {
+		/* skb in gso_skb were already validated */
+		*validate = false;
 		/* check the reason of requeuing without tx lock first */
 		txq = skb_get_tx_queue(txq->dev, skb);
 		if (!netif_xmit_frozen_or_stopped(txq)) {
 			q->gso_skb = NULL;
+			qdisc_qstats_backlog_dec(q, skb);
 			q->q.qlen--;
 		} else
 			skb = NULL;
-		/* skb in gso_skb were already validated */
-		*validate = false;
-	} else {
-		if (!(q->flags & TCQ_F_ONETXQUEUE) ||
-		    !netif_xmit_frozen_or_stopped(txq)) {
-			skb = q->dequeue(q);
-			if (skb && qdisc_may_bulk(q))
-				try_bulk_dequeue_skb(q, skb, txq, packets);
+		return skb;
+	}
+	*validate = true;
+	skb = q->skb_bad_txq;
+	if (unlikely(skb)) {
+		/* check the reason of requeuing without tx lock first */
+		txq = skb_get_tx_queue(txq->dev, skb);
+		if (!netif_xmit_frozen_or_stopped(txq)) {
+			q->skb_bad_txq = NULL;
+			qdisc_qstats_backlog_dec(q, skb);
+			q->q.qlen--;
+			goto bulk;
 		}
+		return NULL;
+	}
+	if (!(q->flags & TCQ_F_ONETXQUEUE) ||
+	    !netif_xmit_frozen_or_stopped(txq))
+		skb = q->dequeue(q);
+	if (skb) {
+bulk:
+		if (qdisc_may_bulk(q))
+			try_bulk_dequeue_skb(q, skb, txq, packets);
+		else
+			try_bulk_dequeue_skb_slow(q, skb, packets);
 	}
 	return skb;
 }
 
 /*
  * Transmit possibly several skbs, and handle the return status as
- * required. Holding the __QDISC___STATE_RUNNING bit guarantees that
+ * required. Owning running seqcount bit guarantees that
  * only one CPU can execute this function.
  *
  * Returns to the caller:
@@ -163,7 +209,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 /*
  * NOTE: Called under qdisc_lock(q) with locally disabled BH.
  *
- * __QDISC___STATE_RUNNING guarantees only one CPU can process
+ * running seqcount guarantees only one CPU can process
  * this qdisc at a time. qdisc_lock(q) serializes queue accesses for
  * this queue.
  *
@@ -346,9 +392,10 @@ EXPORT_SYMBOL(netif_carrier_off);
    cheaper.
  */
 
-static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc)
+static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
+			struct sk_buff **to_free)
 {
-	kfree_skb(skb);
+	__qdisc_drop(skb, to_free);
 	return NET_XMIT_CN;
 }
 
@@ -379,6 +426,7 @@ struct Qdisc noop_qdisc = {
 	.list		=	LIST_HEAD_INIT(noop_qdisc.list),
 	.q.lock		=	__SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
 	.dev_queue	=	&noop_netdev_queue,
+	.running	=	SEQCNT_ZERO(noop_qdisc.running),
 	.busylock	=	__SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
 };
 EXPORT_SYMBOL(noop_qdisc);
@@ -436,7 +484,8 @@ static inline struct sk_buff_head *band2list(struct pfifo_fast_priv *priv,
 	return priv->q + band;
 }
 
-static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc)
+static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
+			      struct sk_buff **to_free)
 {
 	if (skb_queue_len(&qdisc->q) < qdisc_dev(qdisc)->tx_queue_len) {
 		int band = prio2band[skb->priority & TC_PRIO_MAX];
@@ -448,7 +497,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc)
 		return __qdisc_enqueue_tail(skb, qdisc, list);
 	}
 
-	return qdisc_drop(skb, qdisc);
+	return qdisc_drop(skb, qdisc, to_free);
 }
 
 static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
@@ -490,7 +539,7 @@ static void pfifo_fast_reset(struct Qdisc *qdisc)
 	struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
 
 	for (prio = 0; prio < PFIFO_FAST_BANDS; prio++)
-		__qdisc_reset_queue(qdisc, band2list(priv, prio));
+		__qdisc_reset_queue(band2list(priv, prio));
 
 	priv->bitmap = 0;
 	qdisc->qstats.backlog = 0;
@@ -537,6 +586,7 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = {
 EXPORT_SYMBOL(pfifo_fast_ops);
 
 static struct lock_class_key qdisc_tx_busylock;
+static struct lock_class_key qdisc_running_key;
 
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops)
@@ -570,6 +620,10 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	lockdep_set_class(&sch->busylock,
 			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
 
+	seqcount_init(&sch->running);
+	lockdep_set_class(&sch->running,
+			  dev->qdisc_running_key ?: &qdisc_running_key);
+
 	sch->ops = ops;
 	sch->enqueue = ops->enqueue;
 	sch->dequeue = ops->dequeue;
@@ -614,11 +668,14 @@ void qdisc_reset(struct Qdisc *qdisc)
 	if (ops->reset)
 		ops->reset(qdisc);
 
+	kfree_skb(qdisc->skb_bad_txq);
+	qdisc->skb_bad_txq = NULL;
+
 	if (qdisc->gso_skb) {
 		kfree_skb_list(qdisc->gso_skb);
 		qdisc->gso_skb = NULL;
-		qdisc->q.qlen = 0;
 	}
+	qdisc->q.qlen = 0;
 }
 EXPORT_SYMBOL(qdisc_reset);
 
@@ -657,6 +714,7 @@ void qdisc_destroy(struct Qdisc *qdisc)
 	dev_put(qdisc_dev(qdisc));
 
 	kfree_skb_list(qdisc->gso_skb);
+	kfree_skb(qdisc->skb_bad_txq);
 	/*
 	 * gen_estimator est_timer() might access qdisc->q.lock,
 	 * wait a RCU grace period before freeing qdisc.
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 80105109f756..c78a093c551a 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -149,7 +149,8 @@ static inline int gred_use_harddrop(struct gred_sched *t)
 	return t->red_flags & TC_RED_HARDDROP;
 }
 
-static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			struct sk_buff **to_free)
 {
 	struct gred_sched_data *q = NULL;
 	struct gred_sched *t = qdisc_priv(sch);
@@ -237,10 +238,10 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	q->stats.pdrop++;
 drop:
-	return qdisc_drop(skb, sch);
+	return qdisc_drop(skb, sch, to_free);
 
 congestion_drop:
-	qdisc_drop(skb, sch);
+	qdisc_drop(skb, sch, to_free);
 	return NET_XMIT_CN;
 }
 
@@ -276,40 +277,6 @@ static struct sk_buff *gred_dequeue(struct Qdisc *sch)
 	return NULL;
 }
 
-static unsigned int gred_drop(struct Qdisc *sch)
-{
-	struct sk_buff *skb;
-	struct gred_sched *t = qdisc_priv(sch);
-
-	skb = qdisc_dequeue_tail(sch);
-	if (skb) {
-		unsigned int len = qdisc_pkt_len(skb);
-		struct gred_sched_data *q;
-		u16 dp = tc_index_to_dp(skb);
-
-		if (dp >= t->DPs || (q = t->tab[dp]) == NULL) {
-			net_warn_ratelimited("GRED: Unable to relocate VQ 0x%x while dropping, screwing up backlog\n",
-					     tc_index_to_dp(skb));
-		} else {
-			q->backlog -= len;
-			q->stats.other++;
-
-			if (gred_wred_mode(t)) {
-				if (!sch->qstats.backlog)
-					red_start_of_idle_period(&t->wred_set);
-			} else {
-				if (!q->backlog)
-					red_start_of_idle_period(&q->vars);
-			}
-		}
-
-		qdisc_drop(skb, sch);
-		return len;
-	}
-
-	return 0;
-}
-
 static void gred_reset(struct Qdisc *sch)
 {
 	int i;
@@ -623,7 +590,6 @@ static struct Qdisc_ops gred_qdisc_ops __read_mostly = {
 	.enqueue	=	gred_enqueue,
 	.dequeue	=	gred_dequeue,
 	.peek		=	qdisc_peek_head,
-	.drop		=	gred_drop,
 	.init		=	gred_init,
 	.reset		=	gred_reset,
 	.destroy	=	gred_destroy,
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index d783d7cc3348..dff92ea772fe 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -130,7 +130,6 @@ struct hfsc_class {
 	struct rb_node vt_node;		/* parent's vt_tree member */
 	struct rb_root cf_tree;		/* active children sorted by cl_f */
 	struct rb_node cf_node;		/* parent's cf_heap member */
-	struct list_head dlist;		/* drop list member */
 
 	u64	cl_total;		/* total work in bytes */
 	u64	cl_cumul;		/* cumulative work in bytes done by
@@ -177,8 +176,6 @@ struct hfsc_sched {
 	struct hfsc_class root;			/* root class */
 	struct Qdisc_class_hash clhash;		/* class hash */
 	struct rb_root eligible;		/* eligible tree */
-	struct list_head droplist;		/* active leaf class list (for
-						   dropping) */
 	struct qdisc_watchdog watchdog;		/* watchdog timer */
 };
 
@@ -781,6 +778,20 @@ update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time)
 		else
 			go_passive = 0;
 
+		/* update vt */
+		cl->cl_vt = rtsc_y2x(&cl->cl_virtual, cl->cl_total)
+			    - cl->cl_vtoff + cl->cl_vtadj;
+
+		/*
+		 * if vt of the class is smaller than cvtmin,
+		 * the class was skipped in the past due to non-fit.
+		 * if so, we need to adjust vtadj.
+		 */
+		if (cl->cl_vt < cl->cl_parent->cl_cvtmin) {
+			cl->cl_vtadj += cl->cl_parent->cl_cvtmin - cl->cl_vt;
+			cl->cl_vt = cl->cl_parent->cl_cvtmin;
+		}
+
 		if (go_passive) {
 			/* no more active child, going passive */
 
@@ -797,25 +808,10 @@ update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time)
 			continue;
 		}
 
-		/*
-		 * update vt and f
-		 */
-		cl->cl_vt = rtsc_y2x(&cl->cl_virtual, cl->cl_total)
-			    - cl->cl_vtoff + cl->cl_vtadj;
-
-		/*
-		 * if vt of the class is smaller than cvtmin,
-		 * the class was skipped in the past due to non-fit.
-		 * if so, we need to adjust vtadj.
-		 */
-		if (cl->cl_vt < cl->cl_parent->cl_cvtmin) {
-			cl->cl_vtadj += cl->cl_parent->cl_cvtmin - cl->cl_vt;
-			cl->cl_vt = cl->cl_parent->cl_cvtmin;
-		}
-
 		/* update the vt tree */
 		vttree_update(cl);
 
+		/* update f */
 		if (cl->cl_flags & HFSC_USC) {
 			cl->cl_myf = cl->cl_myfadj + rtsc_y2x(&cl->cl_ulimit,
 							      cl->cl_total);
@@ -858,7 +854,6 @@ set_active(struct hfsc_class *cl, unsigned int len)
 	if (cl->cl_flags & HFSC_FSC)
 		init_vf(cl, len);
 
-	list_add_tail(&cl->dlist, &cl->sched->droplist);
 }
 
 static void
@@ -867,8 +862,6 @@ set_passive(struct hfsc_class *cl)
 	if (cl->cl_flags & HFSC_RSC)
 		eltree_remove(cl);
 
-	list_del(&cl->dlist);
-
 	/*
 	 * vttree is now handled in update_vf() so that update_vf(cl, 0, 0)
 	 * needs to be called explicitly to remove a class from vttree.
@@ -882,7 +875,7 @@ qdisc_peek_len(struct Qdisc *sch)
 	unsigned int len;
 
 	skb = sch->ops->peek(sch);
-	if (skb == NULL) {
+	if (unlikely(skb == NULL)) {
 		qdisc_warn_nonwc("qdisc_peek_len", sch);
 		return 0;
 	}
@@ -947,7 +940,7 @@ static void
 hfsc_change_fsc(struct hfsc_class *cl, struct tc_service_curve *fsc)
 {
 	sc2isc(fsc, &cl->cl_fsc);
-	rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total);
+	rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vtoff + cl->cl_vt, cl->cl_total);
 	cl->cl_flags |= HFSC_FSC;
 }
 
@@ -1015,11 +1008,10 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		cur_time = psched_get_time();
 
 		if (tca[TCA_RATE]) {
-			spinlock_t *lock = qdisc_root_sleeping_lock(sch);
-
 			err = gen_replace_estimator(&cl->bstats, NULL,
 						    &cl->rate_est,
-						    lock,
+						    NULL,
+						    qdisc_root_sleeping_running(sch),
 						    tca[TCA_RATE]);
 			if (err)
 				return err;
@@ -1068,7 +1060,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 
 	if (tca[TCA_RATE]) {
 		err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
-					qdisc_root_sleeping_lock(sch),
+					NULL,
+					qdisc_root_sleeping_running(sch),
 					tca[TCA_RATE]);
 		if (err) {
 			kfree(cl);
@@ -1373,7 +1366,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	xstats.work    = cl->cl_total;
 	xstats.rtwork  = cl->cl_cumul;
 
-	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->qdisc->q.qlen) < 0)
 		return -1;
@@ -1443,7 +1436,6 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 	if (err < 0)
 		return err;
 	q->eligible = RB_ROOT;
-	INIT_LIST_HEAD(&q->droplist);
 
 	q->root.cl_common.classid = sch->handle;
 	q->root.refcnt  = 1;
@@ -1527,8 +1519,8 @@ hfsc_reset_qdisc(struct Qdisc *sch)
 			hfsc_reset_class(cl);
 	}
 	q->eligible = RB_ROOT;
-	INIT_LIST_HEAD(&q->droplist);
 	qdisc_watchdog_cancel(&q->watchdog);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 
@@ -1559,14 +1551,6 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb)
 	struct hfsc_sched *q = qdisc_priv(sch);
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tc_hfsc_qopt qopt;
-	struct hfsc_class *cl;
-	unsigned int i;
-
-	sch->qstats.backlog = 0;
-	for (i = 0; i < q->clhash.hashsize; i++) {
-		hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode)
-			sch->qstats.backlog += cl->qdisc->qstats.backlog;
-	}
 
 	qopt.defcls = q->defcls;
 	if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt))
@@ -1579,7 +1563,7 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb)
 }
 
 static int
-hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 {
 	struct hfsc_class *cl;
 	int uninitialized_var(err);
@@ -1588,11 +1572,11 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (cl == NULL) {
 		if (err & __NET_XMIT_BYPASS)
 			qdisc_qstats_drop(sch);
-		kfree_skb(skb);
+		__qdisc_drop(skb, to_free);
 		return err;
 	}
 
-	err = qdisc_enqueue(skb, cl->qdisc);
+	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
@@ -1601,9 +1585,19 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return err;
 	}
 
-	if (cl->qdisc->q.qlen == 1)
+	if (cl->qdisc->q.qlen == 1) {
 		set_active(cl, qdisc_pkt_len(skb));
+		/*
+		 * If this is the first packet, isolate the head so an eventual
+		 * head drop before the first dequeue operation has no chance
+		 * to invalidate the deadline.
+		 */
+		if (cl->cl_flags & HFSC_RSC)
+			cl->qdisc->ops->peek(cl->qdisc);
 
+	}
+
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
@@ -1670,38 +1664,13 @@ hfsc_dequeue(struct Qdisc *sch)
 		set_passive(cl);
 	}
 
-	qdisc_unthrottled(sch);
 	qdisc_bstats_update(sch, skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	sch->q.qlen--;
 
 	return skb;
 }
 
-static unsigned int
-hfsc_drop(struct Qdisc *sch)
-{
-	struct hfsc_sched *q = qdisc_priv(sch);
-	struct hfsc_class *cl;
-	unsigned int len;
-
-	list_for_each_entry(cl, &q->droplist, dlist) {
-		if (cl->qdisc->ops->drop != NULL &&
-		    (len = cl->qdisc->ops->drop(cl->qdisc)) > 0) {
-			if (cl->qdisc->q.qlen == 0) {
-				update_vf(cl, 0, 0);
-				set_passive(cl);
-			} else {
-				list_move_tail(&cl->dlist, &q->droplist);
-			}
-			cl->qstats.drops++;
-			qdisc_qstats_drop(sch);
-			sch->q.qlen--;
-			return len;
-		}
-	}
-	return 0;
-}
-
 static const struct Qdisc_class_ops hfsc_class_ops = {
 	.change		= hfsc_change_class,
 	.delete		= hfsc_delete_class,
@@ -1728,7 +1697,6 @@ static struct Qdisc_ops hfsc_qdisc_ops __read_mostly = {
 	.enqueue	= hfsc_enqueue,
 	.dequeue	= hfsc_dequeue,
 	.peek		= qdisc_peek_dequeued,
-	.drop		= hfsc_drop,
 	.cl_ops		= &hfsc_class_ops,
 	.priv_size	= sizeof(struct hfsc_sched),
 	.owner		= THIS_MODULE
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 13d6f83ec491..e3d0458af17b 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -345,7 +345,7 @@ static void bucket_add(struct wdrr_bucket *bucket, struct sk_buff *skb)
 	skb->next = NULL;
 }
 
-static unsigned int hhf_drop(struct Qdisc *sch)
+static unsigned int hhf_drop(struct Qdisc *sch, struct sk_buff **to_free)
 {
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	struct wdrr_bucket *bucket;
@@ -359,25 +359,16 @@ static unsigned int hhf_drop(struct Qdisc *sch)
 		struct sk_buff *skb = dequeue_head(bucket);
 
 		sch->q.qlen--;
-		qdisc_qstats_drop(sch);
 		qdisc_qstats_backlog_dec(sch, skb);
-		kfree_skb(skb);
+		qdisc_drop(skb, sch, to_free);
 	}
 
 	/* Return id of the bucket from which the packet was dropped. */
 	return bucket - q->buckets;
 }
 
-static unsigned int hhf_qdisc_drop(struct Qdisc *sch)
-{
-	unsigned int prev_backlog;
-
-	prev_backlog = sch->qstats.backlog;
-	hhf_drop(sch);
-	return prev_backlog - sch->qstats.backlog;
-}
-
-static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
 {
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	enum wdrr_bucket_idx idx;
@@ -415,7 +406,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	/* Return Congestion Notification only if we dropped a packet from this
 	 * bucket.
 	 */
-	if (hhf_drop(sch) == idx)
+	if (hhf_drop(sch, to_free) == idx)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this. */
@@ -473,7 +464,7 @@ static void hhf_reset(struct Qdisc *sch)
 	struct sk_buff *skb;
 
 	while ((skb = hhf_dequeue(sch)) != NULL)
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 }
 
 static void *hhf_zalloc(size_t sz)
@@ -583,7 +574,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = hhf_dequeue(sch);
 
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 	}
 	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen,
 				  prev_backlog - sch->qstats.backlog);
@@ -709,7 +700,6 @@ static struct Qdisc_ops hhf_qdisc_ops __read_mostly = {
 	.enqueue	=	hhf_enqueue,
 	.dequeue	=	hhf_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	hhf_qdisc_drop,
 	.init		=	hhf_init,
 	.reset		=	hhf_reset,
 	.destroy	=	hhf_destroy,
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index d4b4218af6b1..91982d9784b3 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -117,7 +117,6 @@ struct htb_class {
 	 * Written often fields
 	 */
 	struct gnet_stats_basic_packed bstats;
-	struct gnet_stats_queue	qstats;
 	struct tc_htb_xstats	xstats;	/* our special stats */
 
 	/* token bucket parameters */
@@ -140,6 +139,8 @@ struct htb_class {
 	enum htb_cmode		cmode;		/* current mode of the class */
 	struct rb_node		pq_node;	/* node for event queue */
 	struct rb_node		node[TC_HTB_NUMPRIO];	/* node for self or feed tree */
+
+	unsigned int drops ____cacheline_aligned_in_smp;
 };
 
 struct htb_level {
@@ -569,7 +570,8 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl)
 	list_del_init(&cl->un.leaf.drop_list);
 }
 
-static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
 {
 	int uninitialized_var(ret);
 	struct htb_sched *q = qdisc_priv(sch);
@@ -581,19 +583,20 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 			__skb_queue_tail(&q->direct_queue, skb);
 			q->direct_pkts++;
 		} else {
-			return qdisc_drop(skb, sch);
+			return qdisc_drop(skb, sch, to_free);
 		}
 #ifdef CONFIG_NET_CLS_ACT
 	} else if (!cl) {
 		if (ret & __NET_XMIT_BYPASS)
 			qdisc_qstats_drop(sch);
-		kfree_skb(skb);
+		__qdisc_drop(skb, to_free);
 		return ret;
 #endif
-	} else if ((ret = qdisc_enqueue(skb, cl->un.leaf.q)) != NET_XMIT_SUCCESS) {
+	} else if ((ret = qdisc_enqueue(skb, cl->un.leaf.q,
+					to_free)) != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(ret)) {
 			qdisc_qstats_drop(sch);
-			cl->qstats.drops++;
+			cl->drops++;
 		}
 		return ret;
 	} else {
@@ -889,7 +892,6 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 	if (skb != NULL) {
 ok:
 		qdisc_bstats_update(sch, skb);
-		qdisc_unthrottled(sch);
 		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 		return skb;
@@ -929,38 +931,13 @@ ok:
 	}
 	qdisc_qstats_overlimit(sch);
 	if (likely(next_event > q->now))
-		qdisc_watchdog_schedule_ns(&q->watchdog, next_event, true);
+		qdisc_watchdog_schedule_ns(&q->watchdog, next_event);
 	else
 		schedule_work(&q->work);
 fin:
 	return skb;
 }
 
-/* try to drop from each class (by prio) until one succeed */
-static unsigned int htb_drop(struct Qdisc *sch)
-{
-	struct htb_sched *q = qdisc_priv(sch);
-	int prio;
-
-	for (prio = TC_HTB_NUMPRIO - 1; prio >= 0; prio--) {
-		struct list_head *p;
-		list_for_each(p, q->drops + prio) {
-			struct htb_class *cl = list_entry(p, struct htb_class,
-							  un.leaf.drop_list);
-			unsigned int len;
-			if (cl->un.leaf.q->ops->drop &&
-			    (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) {
-				sch->qstats.backlog -= len;
-				sch->q.qlen--;
-				if (!cl->un.leaf.q->q.qlen)
-					htb_deactivate(q, cl);
-				return len;
-			}
-		}
-	}
-	return 0;
-}
-
 /* reset all classes */
 /* always caled under BH & queue lock */
 static void htb_reset(struct Qdisc *sch)
@@ -983,7 +960,7 @@ static void htb_reset(struct Qdisc *sch)
 		}
 	}
 	qdisc_watchdog_cancel(&q->watchdog);
-	__skb_queue_purge(&q->direct_queue);
+	__qdisc_reset_queue(&q->direct_queue);
 	sch->q.qlen = 0;
 	sch->qstats.backlog = 0;
 	memset(q->hlevel, 0, sizeof(q->hlevel));
@@ -1007,7 +984,9 @@ static void htb_work_func(struct work_struct *work)
 	struct htb_sched *q = container_of(work, struct htb_sched, work);
 	struct Qdisc *sch = q->watchdog.qdisc;
 
+	rcu_read_lock();
 	__netif_schedule(qdisc_root(sch));
+	rcu_read_unlock();
 }
 
 static int htb_init(struct Qdisc *sch, struct nlattr *opt)
@@ -1134,16 +1113,22 @@ static int
 htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
 {
 	struct htb_class *cl = (struct htb_class *)arg;
+	struct gnet_stats_queue qs = {
+		.drops = cl->drops,
+	};
 	__u32 qlen = 0;
 
-	if (!cl->level && cl->un.leaf.q)
+	if (!cl->level && cl->un.leaf.q) {
 		qlen = cl->un.leaf.q->q.qlen;
+		qs.backlog = cl->un.leaf.q->qstats.backlog;
+	}
 	cl->xstats.tokens = PSCHED_NS2TICKS(cl->tokens);
 	cl->xstats.ctokens = PSCHED_NS2TICKS(cl->ctokens);
 
-	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, NULL, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL, &qs, qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats));
@@ -1256,7 +1241,7 @@ static void htb_destroy(struct Qdisc *sch)
 			htb_destroy_class(sch, cl);
 	}
 	qdisc_class_hash_destroy(&q->clhash);
-	__skb_queue_purge(&q->direct_queue);
+	__qdisc_reset_queue(&q->direct_queue);
 }
 
 static int htb_delete(struct Qdisc *sch, unsigned long arg)
@@ -1395,7 +1380,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		if (htb_rate_est || tca[TCA_RATE]) {
 			err = gen_new_estimator(&cl->bstats, NULL,
 						&cl->rate_est,
-						qdisc_root_sleeping_lock(sch),
+						NULL,
+						qdisc_root_sleeping_running(sch),
 						tca[TCA_RATE] ? : &est.nla);
 			if (err) {
 				kfree(cl);
@@ -1457,11 +1443,10 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			parent->children++;
 	} else {
 		if (tca[TCA_RATE]) {
-			spinlock_t *lock = qdisc_root_sleeping_lock(sch);
-
 			err = gen_replace_estimator(&cl->bstats, NULL,
 						    &cl->rate_est,
-						    lock,
+						    NULL,
+						    qdisc_root_sleeping_running(sch),
 						    tca[TCA_RATE]);
 			if (err)
 				return err;
@@ -1599,7 +1584,6 @@ static struct Qdisc_ops htb_qdisc_ops __read_mostly = {
 	.enqueue	=	htb_enqueue,
 	.dequeue	=	htb_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	htb_drop,
 	.init		=	htb_init,
 	.reset		=	htb_reset,
 	.destroy	=	htb_destroy,
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 10adbc617905..8fe6999b642a 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -27,6 +27,11 @@ static unsigned long ingress_get(struct Qdisc *sch, u32 classid)
 	return TC_H_MIN(classid) + 1;
 }
 
+static bool ingress_cl_offload(u32 classid)
+{
+	return true;
+}
+
 static unsigned long ingress_bind_filter(struct Qdisc *sch,
 					 unsigned long parent, u32 classid)
 {
@@ -86,6 +91,7 @@ static const struct Qdisc_class_ops ingress_class_ops = {
 	.put		=	ingress_put,
 	.walk		=	ingress_walk,
 	.tcf_chain	=	ingress_find_tcf,
+	.tcf_cl_offload	=	ingress_cl_offload,
 	.bind_tcf	=	ingress_bind_filter,
 	.unbind_tcf	=	ingress_put,
 };
@@ -110,6 +116,11 @@ static unsigned long clsact_get(struct Qdisc *sch, u32 classid)
 	}
 }
 
+static bool clsact_cl_offload(u32 classid)
+{
+	return TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS);
+}
+
 static unsigned long clsact_bind_filter(struct Qdisc *sch,
 					unsigned long parent, u32 classid)
 {
@@ -158,6 +169,7 @@ static const struct Qdisc_class_ops clsact_class_ops = {
 	.put		=	ingress_put,
 	.walk		=	ingress_walk,
 	.tcf_chain	=	clsact_find_tcf,
+	.tcf_cl_offload	=	clsact_cl_offload,
 	.bind_tcf	=	clsact_bind_filter,
 	.unbind_tcf	=	ingress_put,
 };
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 56a77b878eb3..b9439827c172 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -199,7 +199,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
 
 	sch = dev_queue->qdisc_sleeping;
-	if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
+	if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0)
 		return -1;
 	return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index b8002ce3d010..549c66359924 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -342,7 +342,8 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		 * hold here is the look on dev_queue->qdisc_sleeping
 		 * also acquired below.
 		 */
-		spin_unlock_bh(d->lock);
+		if (d->lock)
+			spin_unlock_bh(d->lock);
 
 		for (i = tc.offset; i < tc.offset + tc.count; i++) {
 			struct netdev_queue *q = netdev_get_tx_queue(dev, i);
@@ -359,15 +360,17 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 			spin_unlock_bh(qdisc_lock(qdisc));
 		}
 		/* Reclaim root sleeping lock before completing stats */
-		spin_lock_bh(d->lock);
-		if (gnet_stats_copy_basic(d, NULL, &bstats) < 0 ||
+		if (d->lock)
+			spin_lock_bh(d->lock);
+		if (gnet_stats_copy_basic(NULL, d, NULL, &bstats) < 0 ||
 		    gnet_stats_copy_queue(d, NULL, &qstats, qlen) < 0)
 			return -1;
 	} else {
 		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
 
 		sch = dev_queue->qdisc_sleeping;
-		if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
+		if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+					  d, NULL, &sch->bstats) < 0 ||
 		    gnet_stats_copy_queue(d, NULL,
 					  &sch->qstats, sch->q.qlen) < 0)
 			return -1;
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index bcdd54bb101c..9ffbb025b37e 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -65,7 +65,8 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 }
 
 static int
-multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+	       struct sk_buff **to_free)
 {
 	struct Qdisc *qdisc;
 	int ret;
@@ -76,12 +77,12 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 		if (ret & __NET_XMIT_BYPASS)
 			qdisc_qstats_drop(sch);
-		kfree_skb(skb);
+		__qdisc_drop(skb, to_free);
 		return ret;
 	}
 #endif
 
-	ret = qdisc_enqueue(skb, qdisc);
+	ret = qdisc_enqueue(skb, qdisc, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->q.qlen++;
 		return NET_XMIT_SUCCESS;
@@ -151,27 +152,6 @@ static struct sk_buff *multiq_peek(struct Qdisc *sch)
 
 }
 
-static unsigned int multiq_drop(struct Qdisc *sch)
-{
-	struct multiq_sched_data *q = qdisc_priv(sch);
-	int band;
-	unsigned int len;
-	struct Qdisc *qdisc;
-
-	for (band = q->bands - 1; band >= 0; band--) {
-		qdisc = q->queues[band];
-		if (qdisc->ops->drop) {
-			len = qdisc->ops->drop(qdisc);
-			if (len != 0) {
-				sch->q.qlen--;
-				return len;
-			}
-		}
-	}
-	return 0;
-}
-
-
 static void
 multiq_reset(struct Qdisc *sch)
 {
@@ -356,7 +336,8 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	struct Qdisc *cl_q;
 
 	cl_q = q->queues[cl - 1];
-	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl_q->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0)
 		return -1;
 
@@ -415,7 +396,6 @@ static struct Qdisc_ops multiq_qdisc_ops __read_mostly = {
 	.enqueue	=	multiq_enqueue,
 	.dequeue	=	multiq_dequeue,
 	.peek		=	multiq_peek,
-	.drop		=	multiq_drop,
 	.init		=	multiq_init,
 	.reset		=	multiq_reset,
 	.destroy	=	multiq_destroy,
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 205bed00dd34..aaaf02175338 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -368,9 +368,7 @@ static void tfifo_reset(struct Qdisc *sch)
 		struct sk_buff *skb = netem_rb_to_skb(p);
 
 		rb_erase(p, &q->t_root);
-		skb->next = NULL;
-		skb->prev = NULL;
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 	}
 }
 
@@ -399,7 +397,8 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
  * when we statistically choose to corrupt one, we instead segment it, returning
  * the first packet to be corrupted, and re-enqueue the remaining frames
  */
-static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch)
+static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch,
+				     struct sk_buff **to_free)
 {
 	struct sk_buff *segs;
 	netdev_features_t features = netif_skb_features(skb);
@@ -407,7 +406,7 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch)
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
 
 	if (IS_ERR_OR_NULL(segs)) {
-		qdisc_reshape_fail(skb, sch);
+		qdisc_drop(skb, sch, to_free);
 		return NULL;
 	}
 	consume_skb(skb);
@@ -420,7 +419,8 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch)
  * 	NET_XMIT_DROP: queue length didn't change.
  *      NET_XMIT_SUCCESS: one skb was queued.
  */
-static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			 struct sk_buff **to_free)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 	/* We don't fill cb now as skb_unshare() may invalidate it */
@@ -445,7 +445,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	}
 	if (count == 0) {
 		qdisc_qstats_drop(sch);
-		kfree_skb(skb);
+		__qdisc_drop(skb, to_free);
 		return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	}
 
@@ -465,7 +465,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
 
 		q->duplicate = 0;
-		rootq->enqueue(skb2, rootq);
+		rootq->enqueue(skb2, rootq, to_free);
 		q->duplicate = dupsave;
 	}
 
@@ -477,7 +477,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	 */
 	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
 		if (skb_is_gso(skb)) {
-			segs = netem_segment(skb, sch);
+			segs = netem_segment(skb, sch, to_free);
 			if (!segs)
 				return NET_XMIT_DROP;
 		} else {
@@ -487,10 +487,14 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		skb = segs;
 		segs = segs->next;
 
-		if (!(skb = skb_unshare(skb, GFP_ATOMIC)) ||
-		    (skb->ip_summed == CHECKSUM_PARTIAL &&
-		     skb_checksum_help(skb))) {
-			rc = qdisc_drop(skb, sch);
+		skb = skb_unshare(skb, GFP_ATOMIC);
+		if (unlikely(!skb)) {
+			qdisc_qstats_drop(sch);
+			goto finish_segs;
+		}
+		if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		    skb_checksum_help(skb)) {
+			qdisc_drop(skb, sch, to_free);
 			goto finish_segs;
 		}
 
@@ -499,7 +503,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	}
 
 	if (unlikely(skb_queue_len(&sch->q) >= sch->limit))
-		return qdisc_reshape_fail(skb, sch);
+		return qdisc_drop(skb, sch, to_free);
 
 	qdisc_qstats_backlog_inc(sch, skb);
 
@@ -559,7 +563,7 @@ finish_segs:
 			segs->next = NULL;
 			qdisc_skb_cb(segs)->pkt_len = segs->len;
 			last_len = segs->len;
-			rc = qdisc_enqueue(segs, sch);
+			rc = qdisc_enqueue(segs, sch, to_free);
 			if (rc != NET_XMIT_SUCCESS) {
 				if (net_xmit_drop_count(rc))
 					qdisc_qstats_drop(sch);
@@ -576,50 +580,17 @@ finish_segs:
 	return NET_XMIT_SUCCESS;
 }
 
-static unsigned int netem_drop(struct Qdisc *sch)
-{
-	struct netem_sched_data *q = qdisc_priv(sch);
-	unsigned int len;
-
-	len = qdisc_queue_drop(sch);
-
-	if (!len) {
-		struct rb_node *p = rb_first(&q->t_root);
-
-		if (p) {
-			struct sk_buff *skb = netem_rb_to_skb(p);
-
-			rb_erase(p, &q->t_root);
-			sch->q.qlen--;
-			skb->next = NULL;
-			skb->prev = NULL;
-			qdisc_qstats_backlog_dec(sch, skb);
-			kfree_skb(skb);
-		}
-	}
-	if (!len && q->qdisc && q->qdisc->ops->drop)
-	    len = q->qdisc->ops->drop(q->qdisc);
-	if (len)
-		qdisc_qstats_drop(sch);
-
-	return len;
-}
-
 static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
 	struct rb_node *p;
 
-	if (qdisc_is_throttled(sch))
-		return NULL;
-
 tfifo_dequeue:
 	skb = __skb_dequeue(&sch->q);
 	if (skb) {
 		qdisc_qstats_backlog_dec(sch, skb);
 deliver:
-		qdisc_unthrottled(sch);
 		qdisc_bstats_update(sch, skb);
 		return skb;
 	}
@@ -650,14 +621,17 @@ deliver:
 #endif
 
 			if (q->qdisc) {
-				int err = qdisc_enqueue(skb, q->qdisc);
-
-				if (unlikely(err != NET_XMIT_SUCCESS)) {
-					if (net_xmit_drop_count(err)) {
-						qdisc_qstats_drop(sch);
-						qdisc_tree_reduce_backlog(sch, 1,
-									  qdisc_pkt_len(skb));
-					}
+				unsigned int pkt_len = qdisc_pkt_len(skb);
+				struct sk_buff *to_free = NULL;
+				int err;
+
+				err = qdisc_enqueue(skb, q->qdisc, &to_free);
+				kfree_skb_list(to_free);
+				if (err != NET_XMIT_SUCCESS &&
+				    net_xmit_drop_count(err)) {
+					qdisc_qstats_drop(sch);
+					qdisc_tree_reduce_backlog(sch, 1,
+								  pkt_len);
 				}
 				goto tfifo_dequeue;
 			}
@@ -1143,7 +1117,6 @@ static struct Qdisc_ops netem_qdisc_ops __read_mostly = {
 	.enqueue	=	netem_enqueue,
 	.dequeue	=	netem_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	netem_drop,
 	.init		=	netem_init,
 	.reset		=	netem_reset,
 	.destroy	=	netem_destroy,
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index 71ae3b9629f9..a570b0bb254c 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -134,7 +134,8 @@ static bool drop_early(struct Qdisc *sch, u32 packet_size)
 	return false;
 }
 
-static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			     struct sk_buff **to_free)
 {
 	struct pie_sched_data *q = qdisc_priv(sch);
 	bool enqueue = false;
@@ -166,7 +167,7 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 out:
 	q->stats.dropped++;
-	return qdisc_drop(skb, sch);
+	return qdisc_drop(skb, sch, to_free);
 }
 
 static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = {
@@ -234,7 +235,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 
 		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
-		qdisc_drop(skb, sch);
+		rtnl_qdisc_drop(skb, sch);
 	}
 	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c
index 5abfe44678d4..1c6cbab3e7b9 100644
--- a/net/sched/sch_plug.c
+++ b/net/sched/sch_plug.c
@@ -64,6 +64,8 @@ struct plug_sched_data {
 	 */
 	bool unplug_indefinite;
 
+	bool throttled;
+
 	/* Queue Limit in bytes */
 	u32 limit;
 
@@ -86,7 +88,8 @@ struct plug_sched_data {
 	u32 pkts_to_release;
 };
 
-static int plug_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int plug_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			struct sk_buff **to_free)
 {
 	struct plug_sched_data *q = qdisc_priv(sch);
 
@@ -96,14 +99,14 @@ static int plug_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return qdisc_enqueue_tail(skb, sch);
 	}
 
-	return qdisc_reshape_fail(skb, sch);
+	return qdisc_drop(skb, sch, to_free);
 }
 
 static struct sk_buff *plug_dequeue(struct Qdisc *sch)
 {
 	struct plug_sched_data *q = qdisc_priv(sch);
 
-	if (qdisc_is_throttled(sch))
+	if (q->throttled)
 		return NULL;
 
 	if (!q->unplug_indefinite) {
@@ -111,7 +114,7 @@ static struct sk_buff *plug_dequeue(struct Qdisc *sch)
 			/* No more packets to dequeue. Block the queue
 			 * and wait for the next release command.
 			 */
-			qdisc_throttled(sch);
+			q->throttled = true;
 			return NULL;
 		}
 		q->pkts_to_release--;
@@ -141,7 +144,7 @@ static int plug_init(struct Qdisc *sch, struct nlattr *opt)
 		q->limit = ctl->limit;
 	}
 
-	qdisc_throttled(sch);
+	q->throttled = true;
 	return 0;
 }
 
@@ -173,7 +176,7 @@ static int plug_change(struct Qdisc *sch, struct nlattr *opt)
 		q->pkts_last_epoch = q->pkts_current_epoch;
 		q->pkts_current_epoch = 0;
 		if (q->unplug_indefinite)
-			qdisc_throttled(sch);
+			q->throttled = true;
 		q->unplug_indefinite = false;
 		break;
 	case TCQ_PLUG_RELEASE_ONE:
@@ -182,7 +185,7 @@ static int plug_change(struct Qdisc *sch, struct nlattr *opt)
 		 */
 		q->pkts_to_release += q->pkts_last_epoch;
 		q->pkts_last_epoch = 0;
-		qdisc_unthrottled(sch);
+		q->throttled = false;
 		netif_schedule_queue(sch->dev_queue);
 		break;
 	case TCQ_PLUG_RELEASE_INDEFINITE:
@@ -190,7 +193,7 @@ static int plug_change(struct Qdisc *sch, struct nlattr *opt)
 		q->pkts_to_release = 0;
 		q->pkts_last_epoch = 0;
 		q->pkts_current_epoch = 0;
-		qdisc_unthrottled(sch);
+		q->throttled = false;
 		netif_schedule_queue(sch->dev_queue);
 		break;
 	case TCQ_PLUG_LIMIT:
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index fee1b15506b2..8f575899adfa 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -67,7 +67,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 }
 
 static int
-prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 {
 	struct Qdisc *qdisc;
 	int ret;
@@ -83,8 +83,9 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	}
 #endif
 
-	ret = qdisc_enqueue(skb, qdisc);
+	ret = qdisc_enqueue(skb, qdisc, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
+		qdisc_qstats_backlog_inc(sch, skb);
 		sch->q.qlen++;
 		return NET_XMIT_SUCCESS;
 	}
@@ -117,6 +118,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc *sch)
 		struct sk_buff *skb = qdisc_dequeue_peeked(qdisc);
 		if (skb) {
 			qdisc_bstats_update(sch, skb);
+			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
 			return skb;
 		}
@@ -125,24 +127,6 @@ static struct sk_buff *prio_dequeue(struct Qdisc *sch)
 
 }
 
-static unsigned int prio_drop(struct Qdisc *sch)
-{
-	struct prio_sched_data *q = qdisc_priv(sch);
-	int prio;
-	unsigned int len;
-	struct Qdisc *qdisc;
-
-	for (prio = q->bands-1; prio >= 0; prio--) {
-		qdisc = q->queues[prio];
-		if (qdisc->ops->drop && (len = qdisc->ops->drop(qdisc)) != 0) {
-			sch->q.qlen--;
-			return len;
-		}
-	}
-	return 0;
-}
-
-
 static void
 prio_reset(struct Qdisc *sch)
 {
@@ -151,6 +135,7 @@ prio_reset(struct Qdisc *sch)
 
 	for (prio = 0; prio < q->bands; prio++)
 		qdisc_reset(q->queues[prio]);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 
@@ -168,8 +153,9 @@ prio_destroy(struct Qdisc *sch)
 static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *queues[TCQ_PRIO_BANDS];
+	int oldbands = q->bands, i;
 	struct tc_prio_qopt *qopt;
-	int i;
 
 	if (nla_len(opt) < sizeof(*qopt))
 		return -EINVAL;
@@ -183,62 +169,42 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 			return -EINVAL;
 	}
 
+	/* Before commit, make sure we can allocate all new qdiscs */
+	for (i = oldbands; i < qopt->bands; i++) {
+		queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+					      TC_H_MAKE(sch->handle, i + 1));
+		if (!queues[i]) {
+			while (i > oldbands)
+				qdisc_destroy(queues[--i]);
+			return -ENOMEM;
+		}
+	}
+
 	sch_tree_lock(sch);
 	q->bands = qopt->bands;
 	memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
 
-	for (i = q->bands; i < TCQ_PRIO_BANDS; i++) {
+	for (i = q->bands; i < oldbands; i++) {
 		struct Qdisc *child = q->queues[i];
-		q->queues[i] = &noop_qdisc;
-		if (child != &noop_qdisc) {
-			qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog);
-			qdisc_destroy(child);
-		}
-	}
-	sch_tree_unlock(sch);
 
-	for (i = 0; i < q->bands; i++) {
-		if (q->queues[i] == &noop_qdisc) {
-			struct Qdisc *child, *old;
-
-			child = qdisc_create_dflt(sch->dev_queue,
-						  &pfifo_qdisc_ops,
-						  TC_H_MAKE(sch->handle, i + 1));
-			if (child) {
-				sch_tree_lock(sch);
-				old = q->queues[i];
-				q->queues[i] = child;
-
-				if (old != &noop_qdisc) {
-					qdisc_tree_reduce_backlog(old,
-								  old->q.qlen,
-								  old->qstats.backlog);
-					qdisc_destroy(old);
-				}
-				sch_tree_unlock(sch);
-			}
-		}
+		qdisc_tree_reduce_backlog(child, child->q.qlen,
+					  child->qstats.backlog);
+		qdisc_destroy(child);
 	}
+
+	for (i = oldbands; i < q->bands; i++)
+		q->queues[i] = queues[i];
+
+	sch_tree_unlock(sch);
 	return 0;
 }
 
 static int prio_init(struct Qdisc *sch, struct nlattr *opt)
 {
-	struct prio_sched_data *q = qdisc_priv(sch);
-	int i;
-
-	for (i = 0; i < TCQ_PRIO_BANDS; i++)
-		q->queues[i] = &noop_qdisc;
-
-	if (opt == NULL) {
+	if (!opt)
 		return -EINVAL;
-	} else {
-		int err;
 
-		if ((err = prio_tune(sch, opt)) != 0)
-			return err;
-	}
-	return 0;
+	return prio_tune(sch, opt);
 }
 
 static int prio_dump(struct Qdisc *sch, struct sk_buff *skb)
@@ -319,7 +285,8 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	struct Qdisc *cl_q;
 
 	cl_q = q->queues[cl - 1];
-	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl_q->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0)
 		return -1;
 
@@ -378,7 +345,6 @@ static struct Qdisc_ops prio_qdisc_ops __read_mostly = {
 	.enqueue	=	prio_enqueue,
 	.dequeue	=	prio_dequeue,
 	.peek		=	prio_peek,
-	.drop		=	prio_drop,
 	.init		=	prio_init,
 	.reset		=	prio_reset,
 	.destroy	=	prio_destroy,
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 8d2d8d953432..f27ffee106f6 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -460,7 +460,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		if (tca[TCA_RATE]) {
 			err = gen_replace_estimator(&cl->bstats, NULL,
 						    &cl->rate_est,
-						    qdisc_root_sleeping_lock(sch),
+						    NULL,
+						    qdisc_root_sleeping_running(sch),
 						    tca[TCA_RATE]);
 			if (err)
 				return err;
@@ -486,7 +487,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	if (tca[TCA_RATE]) {
 		err = gen_new_estimator(&cl->bstats, NULL,
 					&cl->rate_est,
-					qdisc_root_sleeping_lock(sch),
+					NULL,
+					qdisc_root_sleeping_running(sch),
 					tca[TCA_RATE]);
 		if (err)
 			goto destroy_class;
@@ -663,7 +665,8 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	xstats.weight = cl->agg->class_weight;
 	xstats.lmax = cl->agg->lmax;
 
-	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, NULL,
 				  &cl->qdisc->qstats, cl->qdisc->q.qlen) < 0)
@@ -1214,7 +1217,8 @@ static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q)
 	return agg;
 }
 
-static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl;
@@ -1235,11 +1239,13 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 			 cl->agg->lmax, qdisc_pkt_len(skb), cl->common.classid);
 		err = qfq_change_agg(sch, cl, cl->agg->class_weight,
 				     qdisc_pkt_len(skb));
-		if (err)
-			return err;
+		if (err) {
+			cl->qstats.drops++;
+			return qdisc_drop(skb, sch, to_free);
+		}
 	}
 
-	err = qdisc_enqueue(skb, cl->qdisc);
+	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		pr_debug("qfq_enqueue: enqueue failed %d\n", err);
 		if (net_xmit_drop_count(err)) {
@@ -1420,52 +1426,6 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg)
 		qfq_deactivate_class(q, cl);
 }
 
-static unsigned int qfq_drop_from_slot(struct qfq_sched *q,
-				       struct hlist_head *slot)
-{
-	struct qfq_aggregate *agg;
-	struct qfq_class *cl;
-	unsigned int len;
-
-	hlist_for_each_entry(agg, slot, next) {
-		list_for_each_entry(cl, &agg->active, alist) {
-
-			if (!cl->qdisc->ops->drop)
-				continue;
-
-			len = cl->qdisc->ops->drop(cl->qdisc);
-			if (len > 0) {
-				if (cl->qdisc->q.qlen == 0)
-					qfq_deactivate_class(q, cl);
-
-				return len;
-			}
-		}
-	}
-	return 0;
-}
-
-static unsigned int qfq_drop(struct Qdisc *sch)
-{
-	struct qfq_sched *q = qdisc_priv(sch);
-	struct qfq_group *grp;
-	unsigned int i, j, len;
-
-	for (i = 0; i <= QFQ_MAX_INDEX; i++) {
-		grp = &q->groups[i];
-		for (j = 0; j < QFQ_MAX_SLOTS; j++) {
-			len = qfq_drop_from_slot(q, &grp->slots[j]);
-			if (len > 0) {
-				sch->q.qlen--;
-				return len;
-			}
-		}
-
-	}
-
-	return 0;
-}
-
 static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
@@ -1560,7 +1520,6 @@ static struct Qdisc_ops qfq_qdisc_ops __read_mostly = {
 	.enqueue	= qfq_enqueue,
 	.dequeue	= qfq_dequeue,
 	.peek		= qdisc_peek_dequeued,
-	.drop		= qfq_drop,
 	.init		= qfq_init_qdisc,
 	.reset		= qfq_reset_qdisc,
 	.destroy	= qfq_destroy_qdisc,
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 8c0508c0e287..249b2a18acbd 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -56,7 +56,8 @@ static inline int red_use_harddrop(struct red_sched_data *q)
 	return q->flags & TC_RED_HARDDROP;
 }
 
-static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
 	struct Qdisc *child = q->qdisc;
@@ -95,8 +96,9 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		break;
 	}
 
-	ret = qdisc_enqueue(skb, child);
+	ret = qdisc_enqueue(skb, child, to_free);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
+		qdisc_qstats_backlog_inc(sch, skb);
 		sch->q.qlen++;
 	} else if (net_xmit_drop_count(ret)) {
 		q->stats.pdrop++;
@@ -105,7 +107,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	return ret;
 
 congestion_drop:
-	qdisc_drop(skb, sch);
+	qdisc_drop(skb, sch, to_free);
 	return NET_XMIT_CN;
 }
 
@@ -118,6 +120,7 @@ static struct sk_buff *red_dequeue(struct Qdisc *sch)
 	skb = child->dequeue(child);
 	if (skb) {
 		qdisc_bstats_update(sch, skb);
+		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 	} else {
 		if (!red_is_idling(&q->vars))
@@ -134,30 +137,12 @@ static struct sk_buff *red_peek(struct Qdisc *sch)
 	return child->ops->peek(child);
 }
 
-static unsigned int red_drop(struct Qdisc *sch)
-{
-	struct red_sched_data *q = qdisc_priv(sch);
-	struct Qdisc *child = q->qdisc;
-	unsigned int len;
-
-	if (child->ops->drop && (len = child->ops->drop(child)) > 0) {
-		q->stats.other++;
-		qdisc_qstats_drop(sch);
-		sch->q.qlen--;
-		return len;
-	}
-
-	if (!red_is_idling(&q->vars))
-		red_start_of_idle_period(&q->vars);
-
-	return 0;
-}
-
 static void red_reset(struct Qdisc *sch)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
 
 	qdisc_reset(q->qdisc);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 	red_restart(&q->vars);
 }
@@ -361,7 +346,6 @@ static struct Qdisc_ops red_qdisc_ops __read_mostly = {
 	.enqueue	=	red_enqueue,
 	.dequeue	=	red_dequeue,
 	.peek		=	red_peek,
-	.drop		=	red_drop,
 	.init		=	red_init,
 	.reset		=	red_reset,
 	.destroy	=	red_destroy,
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index c69611640fa5..add3cc7d37ec 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -275,7 +275,8 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl,
 	return false;
 }
 
-static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
 {
 
 	struct sfb_sched_data *q = qdisc_priv(sch);
@@ -397,7 +398,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	}
 
 enqueue:
-	ret = qdisc_enqueue(skb, child);
+	ret = qdisc_enqueue(skb, child, to_free);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
 		sch->q.qlen++;
 		increment_qlen(skb, q);
@@ -408,7 +409,7 @@ enqueue:
 	return ret;
 
 drop:
-	qdisc_drop(skb, sch);
+	qdisc_drop(skb, sch, to_free);
 	return NET_XMIT_CN;
 other_drop:
 	if (ret & __NET_XMIT_BYPASS)
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 498f0a2cb47f..7f195ed4d568 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -343,7 +343,7 @@ static int sfq_headdrop(const struct sfq_sched_data *q)
 }
 
 static int
-sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	unsigned int hash, dropped;
@@ -367,7 +367,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (x == SFQ_EMPTY_SLOT) {
 		x = q->dep[0].next; /* get a free slot */
 		if (x >= SFQ_MAX_FLOWS)
-			return qdisc_drop(skb, sch);
+			return qdisc_drop(skb, sch, to_free);
 		q->ht[hash] = x;
 		slot = &q->slots[x];
 		slot->hash = hash;
@@ -424,14 +424,14 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (slot->qlen >= q->maxdepth) {
 congestion_drop:
 		if (!sfq_headdrop(q))
-			return qdisc_drop(skb, sch);
+			return qdisc_drop(skb, sch, to_free);
 
 		/* We know we have at least one packet in queue */
 		head = slot_dequeue_head(slot);
 		delta = qdisc_pkt_len(head) - qdisc_pkt_len(skb);
 		sch->qstats.backlog -= delta;
 		slot->backlog -= delta;
-		qdisc_drop(head, sch);
+		qdisc_drop(head, sch, to_free);
 
 		slot_queue_add(slot, skb);
 		return NET_XMIT_CN;
@@ -520,7 +520,7 @@ sfq_reset(struct Qdisc *sch)
 	struct sk_buff *skb;
 
 	while ((skb = sfq_dequeue(sch)) != NULL)
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 }
 
 /*
@@ -896,7 +896,6 @@ static struct Qdisc_ops sfq_qdisc_ops __read_mostly = {
 	.enqueue	=	sfq_enqueue,
 	.dequeue	=	sfq_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	sfq_drop,
 	.init		=	sfq_init,
 	.reset		=	sfq_reset,
 	.destroy	=	sfq_destroy,
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 83b90b584fae..303355c449ab 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -155,7 +155,8 @@ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb)
 /* GSO packet is too big, segment it so that tbf can transmit
  * each segment in time
  */
-static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
+static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *segs, *nskb;
@@ -166,7 +167,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
 
 	if (IS_ERR_OR_NULL(segs))
-		return qdisc_reshape_fail(skb, sch);
+		return qdisc_drop(skb, sch, to_free);
 
 	nb = 0;
 	while (segs) {
@@ -174,7 +175,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 		segs->next = NULL;
 		qdisc_skb_cb(segs)->pkt_len = segs->len;
 		len += segs->len;
-		ret = qdisc_enqueue(segs, q->qdisc);
+		ret = qdisc_enqueue(segs, q->qdisc, to_free);
 		if (ret != NET_XMIT_SUCCESS) {
 			if (net_xmit_drop_count(ret))
 				qdisc_qstats_drop(sch);
@@ -190,39 +191,29 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
 }
 
-static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	int ret;
 
 	if (qdisc_pkt_len(skb) > q->max_size) {
 		if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size)
-			return tbf_segment(skb, sch);
-		return qdisc_reshape_fail(skb, sch);
+			return tbf_segment(skb, sch, to_free);
+		return qdisc_drop(skb, sch, to_free);
 	}
-	ret = qdisc_enqueue(skb, q->qdisc);
+	ret = qdisc_enqueue(skb, q->qdisc, to_free);
 	if (ret != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(ret))
 			qdisc_qstats_drop(sch);
 		return ret;
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 	return NET_XMIT_SUCCESS;
 }
 
-static unsigned int tbf_drop(struct Qdisc *sch)
-{
-	struct tbf_sched_data *q = qdisc_priv(sch);
-	unsigned int len = 0;
-
-	if (q->qdisc->ops->drop && (len = q->qdisc->ops->drop(q->qdisc)) != 0) {
-		sch->q.qlen--;
-		qdisc_qstats_drop(sch);
-	}
-	return len;
-}
-
 static bool tbf_peak_present(const struct tbf_sched_data *q)
 {
 	return q->peak.rate_bytes_ps;
@@ -263,15 +254,14 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
 			q->t_c = now;
 			q->tokens = toks;
 			q->ptokens = ptoks;
+			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
-			qdisc_unthrottled(sch);
 			qdisc_bstats_update(sch, skb);
 			return skb;
 		}
 
 		qdisc_watchdog_schedule_ns(&q->watchdog,
-					   now + max_t(long, -toks, -ptoks),
-					   true);
+					   now + max_t(long, -toks, -ptoks));
 
 		/* Maybe we have a shorter packet in the queue,
 		   which can be sent now. It sounds cool,
@@ -294,6 +284,7 @@ static void tbf_reset(struct Qdisc *sch)
 	struct tbf_sched_data *q = qdisc_priv(sch);
 
 	qdisc_reset(q->qdisc);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 	q->t_c = ktime_get_ns();
 	q->tokens = q->buffer;
@@ -555,7 +546,6 @@ static struct Qdisc_ops tbf_qdisc_ops __read_mostly = {
 	.enqueue	=	tbf_enqueue,
 	.dequeue	=	tbf_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	tbf_drop,
 	.init		=	tbf_init,
 	.reset		=	tbf_reset,
 	.destroy	=	tbf_destroy,
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index e02687185a59..2cd9b4478b92 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -77,7 +77,7 @@ struct teql_sched_data {
 /* "teql*" qdisc routines */
 
 static int
-teql_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+teql_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 {
 	struct net_device *dev = qdisc_dev(sch);
 	struct teql_sched_data *q = qdisc_priv(sch);
@@ -87,7 +87,7 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_SUCCESS;
 	}
 
-	return qdisc_drop(skb, sch);
+	return qdisc_drop(skb, sch, to_free);
 }
 
 static struct sk_buff *
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 40022ee885d7..3b56ae55aba3 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1479,7 +1479,8 @@ static __init int sctp_init(void)
 		INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain);
 	}
 
-	if (sctp_transport_hashtable_init())
+	status = sctp_transport_hashtable_init();
+	if (status)
 		goto err_thash_alloc;
 
 	pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize,
diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c
index 1ce724b87618..f69edcf219e5 100644
--- a/net/sctp/sctp_diag.c
+++ b/net/sctp/sctp_diag.c
@@ -3,12 +3,6 @@
 #include <linux/sock_diag.h>
 #include <net/sctp/sctp.h>
 
-extern void inet_diag_msg_common_fill(struct inet_diag_msg *r,
-				      struct sock *sk);
-extern int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
-				    struct inet_diag_msg *r, int ext,
-				    struct user_namespace *user_ns);
-
 static void sctp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 			       void *info);
 
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index aa3712259368..12d45193357c 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -806,8 +806,10 @@ static void sctp_cmd_new_state(sctp_cmd_seq_t *cmds,
 
 		/* Set the RCV_SHUTDOWN flag when a SHUTDOWN is received. */
 		if (sctp_state(asoc, SHUTDOWN_RECEIVED) &&
-		    sctp_sstate(sk, ESTABLISHED))
+		    sctp_sstate(sk, ESTABLISHED)) {
+			sk->sk_state = SCTP_SS_CLOSING;
 			sk->sk_shutdown |= RCV_SHUTDOWN;
+		}
 	}
 
 	if (sctp_state(asoc, COOKIE_WAIT)) {
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 712fb2339baa..cdabbd8219b1 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4195,6 +4195,7 @@ static void sctp_shutdown(struct sock *sk, int how)
 		return;
 
 	if (how & SEND_SHUTDOWN) {
+		sk->sk_state = SCTP_SS_CLOSING;
 		ep = sctp_sk(sk)->ep;
 		if (!list_empty(&ep->asocs)) {
 			asoc = list_entry(ep->asocs.next,
@@ -7566,10 +7567,13 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	/* If the association on the newsk is already closed before accept()
 	 * is called, set RCV_SHUTDOWN flag.
 	 */
-	if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP))
+	if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP)) {
+		newsk->sk_state = SCTP_SS_CLOSED;
 		newsk->sk_shutdown |= RCV_SHUTDOWN;
+	} else {
+		newsk->sk_state = SCTP_SS_ESTABLISHED;
+	}
 
-	newsk->sk_state = SCTP_SS_ESTABLISHED;
 	release_sock(newsk);
 }
 
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 06b4df9faaa1..2808d550d273 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -446,16 +446,27 @@ out_no_rpciod:
 	return ERR_PTR(err);
 }
 
-struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
+static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 					struct rpc_xprt *xprt)
 {
 	struct rpc_clnt *clnt = NULL;
 	struct rpc_xprt_switch *xps;
 
-	xps = xprt_switch_alloc(xprt, GFP_KERNEL);
-	if (xps == NULL)
-		return ERR_PTR(-ENOMEM);
-
+	if (args->bc_xprt && args->bc_xprt->xpt_bc_xps) {
+		WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+		xps = args->bc_xprt->xpt_bc_xps;
+		xprt_switch_get(xps);
+	} else {
+		xps = xprt_switch_alloc(xprt, GFP_KERNEL);
+		if (xps == NULL) {
+			xprt_put(xprt);
+			return ERR_PTR(-ENOMEM);
+		}
+		if (xprt->bc_xprt) {
+			xprt_switch_get(xps);
+			xprt->bc_xprt->xpt_bc_xps = xps;
+		}
+	}
 	clnt = rpc_new_client(args, xps, xprt, NULL);
 	if (IS_ERR(clnt))
 		return clnt;
@@ -483,7 +494,6 @@ struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 
 	return clnt;
 }
-EXPORT_SYMBOL_GPL(rpc_create_xprt);
 
 /**
  * rpc_create - create an RPC client and transport with one call
@@ -509,6 +519,15 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 	};
 	char servername[48];
 
+	if (args->bc_xprt) {
+		WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+		xprt = args->bc_xprt->xpt_bc_xprt;
+		if (xprt) {
+			xprt_get(xprt);
+			return rpc_create_xprt(args, xprt);
+		}
+	}
+
 	if (args->flags & RPC_CLNT_CREATE_INFINITE_SLOTS)
 		xprtargs.flags |= XPRT_CREATE_INFINITE_SLOTS;
 	if (args->flags & RPC_CLNT_CREATE_NO_IDLE_TIMEOUT)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index f5572e31d518..4f01f63102ee 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -136,6 +136,8 @@ static void svc_xprt_free(struct kref *kref)
 	/* See comment on corresponding get in xs_setup_bc_tcp(): */
 	if (xprt->xpt_bc_xprt)
 		xprt_put(xprt->xpt_bc_xprt);
+	if (xprt->xpt_bc_xps)
+		xprt_switch_put(xprt->xpt_bc_xps);
 	xprt->xpt_ops->xpo_free(xprt);
 	module_put(owner);
 }
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 2d3e0c42361e..7e2b2fa189c3 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -3057,6 +3057,7 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 		return xprt;
 
 	args->bc_xprt->xpt_bc_xprt = NULL;
+	args->bc_xprt->xpt_bc_xps = NULL;
 	xprt_put(xprt);
 	ret = ERR_PTR(-EINVAL);
 out_err:
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index 57e460be4692..31b9f9c52974 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -6,7 +6,7 @@ obj-$(CONFIG_TIPC) := tipc.o
 
 tipc-y	+= addr.o bcast.o bearer.o \
 	   core.o link.o discover.o msg.o  \
-	   name_distr.o  subscr.o name_table.o net.o  \
+	   name_distr.o  subscr.o monitor.o name_table.o net.o  \
 	   netlink.o netlink_compat.o node.o socket.o eth_media.o \
 	   server.o socket.o
 
diff --git a/net/tipc/addr.h b/net/tipc/addr.h
index 93f7c983be33..64f4004a6fac 100644
--- a/net/tipc/addr.h
+++ b/net/tipc/addr.h
@@ -73,4 +73,5 @@ int tipc_addr_node_valid(u32 addr);
 int tipc_in_scope(u32 domain, u32 addr);
 int tipc_addr_scope(u32 domain);
 char *tipc_addr_string_fill(char *string, u32 addr);
+
 #endif
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 6f11c62bc8f9..8584cc48654c 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/bearer.c: TIPC bearer code
  *
- * Copyright (c) 1996-2006, 2013-2014, Ericsson AB
+ * Copyright (c) 1996-2006, 2013-2016, Ericsson AB
  * Copyright (c) 2004-2006, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -39,6 +39,7 @@
 #include "bearer.h"
 #include "link.h"
 #include "discover.h"
+#include "monitor.h"
 #include "bcast.h"
 #include "netlink.h"
 
@@ -313,6 +314,10 @@ restart:
 	rcu_assign_pointer(tn->bearer_list[bearer_id], b);
 	if (skb)
 		tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr);
+
+	if (tipc_mon_create(net, bearer_id))
+		return -ENOMEM;
+
 	pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n",
 		name,
 		tipc_addr_string_fill(addr_string, disc_domain), priority);
@@ -348,6 +353,7 @@ static void bearer_disable(struct net *net, struct tipc_bearer *b)
 		tipc_disc_delete(b->link_req);
 	RCU_INIT_POINTER(tn->bearer_list[bearer_id], NULL);
 	kfree_rcu(b, rcu);
+	tipc_mon_delete(net, bearer_id);
 }
 
 int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
@@ -405,7 +411,7 @@ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb,
 		return 0;
 
 	/* Send RESET message even if bearer is detached from device */
-	tipc_ptr = rtnl_dereference(dev->tipc_ptr);
+	tipc_ptr = rcu_dereference_rtnl(dev->tipc_ptr);
 	if (unlikely(!tipc_ptr && !msg_is_reset(buf_msg(skb))))
 		goto drop;
 
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index f686e41b5abb..0d337c7b6fad 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/bearer.h: Include file for TIPC bearer code
  *
- * Copyright (c) 1996-2006, 2013-2014, Ericsson AB
+ * Copyright (c) 1996-2006, 2013-2016, Ericsson AB
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
diff --git a/net/tipc/core.c b/net/tipc/core.c
index fe1b062c4f18..236b043a4156 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -57,6 +57,7 @@ static int __net_init tipc_init_net(struct net *net)
 
 	tn->net_id = 4711;
 	tn->own_addr = 0;
+	tn->mon_threshold = TIPC_DEF_MON_THRESHOLD;
 	get_random_bytes(&tn->random, sizeof(int));
 	INIT_LIST_HEAD(&tn->node_list);
 	spin_lock_init(&tn->node_list_lock);
diff --git a/net/tipc/core.h b/net/tipc/core.h
index eff58dc53aa1..a1845fb27d80 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -66,11 +66,13 @@ struct tipc_bc_base;
 struct tipc_link;
 struct tipc_name_table;
 struct tipc_server;
+struct tipc_monitor;
 
 #define TIPC_MOD_VER "2.0.0"
 
-#define NODE_HTABLE_SIZE   512
-#define MAX_BEARERS	   3
+#define NODE_HTABLE_SIZE       512
+#define MAX_BEARERS	         3
+#define TIPC_DEF_MON_THRESHOLD  32
 
 extern int tipc_net_id __read_mostly;
 extern int sysctl_tipc_rmem[3] __read_mostly;
@@ -88,6 +90,10 @@ struct tipc_net {
 	u32 num_nodes;
 	u32 num_links;
 
+	/* Neighbor monitoring list */
+	struct tipc_monitor *monitors[MAX_BEARERS];
+	int mon_threshold;
+
 	/* Bearer list */
 	struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1];
 
@@ -126,6 +132,11 @@ static inline struct list_head *tipc_nodes(struct net *net)
 	return &tipc_net(net)->node_list;
 }
 
+static inline unsigned int tipc_hashfn(u32 addr)
+{
+	return addr & (NODE_HTABLE_SIZE - 1);
+}
+
 static inline u16 mod(u16 x)
 {
 	return x & 0xffffu;
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index ad9d477cc242..6b109a808d4c 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -135,9 +135,12 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb,
 	u16 caps = msg_node_capabilities(hdr);
 	bool respond = false;
 	bool dupl_addr = false;
+	int err;
 
-	bearer->media->msg2addr(bearer, &maddr, msg_media_addr(hdr));
+	err = bearer->media->msg2addr(bearer, &maddr, msg_media_addr(hdr));
 	kfree_skb(skb);
+	if (err)
+		return;
 
 	/* Ensure message from node is valid and communication is permitted */
 	if (net_id != tn->net_id)
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 7059c94f33c5..c1df33f878b2 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -42,6 +42,7 @@
 #include "name_distr.h"
 #include "discover.h"
 #include "netlink.h"
+#include "monitor.h"
 
 #include <linux/pkt_sched.h>
 
@@ -87,7 +88,6 @@ struct tipc_stats {
  * @peer_bearer_id: bearer id used by link's peer endpoint
  * @bearer_id: local bearer id used by link
  * @tolerance: minimum link continuity loss needed to reset link [in ms]
- * @keepalive_intv: link keepalive timer interval
  * @abort_limit: # of unacknowledged continuity probes needed to reset link
  * @state: current state of link FSM
  * @peer_caps: bitmap describing capabilities of peer node
@@ -96,6 +96,7 @@ struct tipc_stats {
  * @pmsg: convenience pointer to "proto_msg" field
  * @priority: current link priority
  * @net_plane: current link network plane ('A' through 'H')
+ * @mon_state: cookie with information needed by link monitor
  * @backlog_limit: backlog queue congestion thresholds (indexed by importance)
  * @exp_msg_count: # of tunnelled messages expected during link changeover
  * @reset_rcv_checkpt: seq # of last acknowledged message at time of link reset
@@ -131,7 +132,6 @@ struct tipc_link {
 	u32 peer_bearer_id;
 	u32 bearer_id;
 	u32 tolerance;
-	unsigned long keepalive_intv;
 	u32 abort_limit;
 	u32 state;
 	u16 peer_caps;
@@ -140,6 +140,7 @@ struct tipc_link {
 	char if_name[TIPC_MAX_IF_NAME];
 	u32 priority;
 	char net_plane;
+	struct tipc_mon_state mon_state;
 	u16 rst_cnt;
 
 	/* Failover/synch */
@@ -704,24 +705,32 @@ static void link_profile_stats(struct tipc_link *l)
  */
 int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
 {
-	int mtyp, rc = 0;
+	int mtyp = 0;
+	int rc = 0;
 	bool state = false;
 	bool probe = false;
 	bool setup = false;
 	u16 bc_snt = l->bc_sndlink->snd_nxt - 1;
 	u16 bc_acked = l->bc_rcvlink->acked;
-
-	link_profile_stats(l);
+	struct tipc_mon_state *mstate = &l->mon_state;
 
 	switch (l->state) {
 	case LINK_ESTABLISHED:
 	case LINK_SYNCHING:
-		if (l->silent_intv_cnt > l->abort_limit)
-			return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
 		mtyp = STATE_MSG;
+		link_profile_stats(l);
+		tipc_mon_get_state(l->net, l->addr, mstate, l->bearer_id);
+		if (mstate->reset || (l->silent_intv_cnt > l->abort_limit))
+			return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
 		state = bc_acked != bc_snt;
-		probe = l->silent_intv_cnt;
-		l->silent_intv_cnt++;
+		state |= l->bc_rcvlink->rcv_unacked;
+		state |= l->rcv_unacked;
+		state |= !skb_queue_empty(&l->transmq);
+		state |= !skb_queue_empty(&l->deferdq);
+		probe = mstate->probing;
+		probe |= l->silent_intv_cnt;
+		if (probe || mstate->monitoring)
+			l->silent_intv_cnt++;
 		break;
 	case LINK_RESET:
 		setup = l->rst_cnt++ <= 4;
@@ -832,6 +841,7 @@ void tipc_link_reset(struct tipc_link *l)
 	l->stats.recv_info = 0;
 	l->stale_count = 0;
 	l->bc_peer_is_up = false;
+	memset(&l->mon_state, 0, sizeof(l->mon_state));
 	tipc_link_reset_stats(l);
 }
 
@@ -1240,6 +1250,9 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 	struct tipc_msg *hdr;
 	struct sk_buff_head *dfq = &l->deferdq;
 	bool node_up = link_is_up(l->bc_rcvlink);
+	struct tipc_mon_state *mstate = &l->mon_state;
+	int dlen = 0;
+	void *data;
 
 	/* Don't send protocol message during reset or link failover */
 	if (tipc_link_is_blocked(l))
@@ -1252,12 +1265,13 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 		rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt;
 
 	skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE,
-			      TIPC_MAX_IF_NAME, l->addr,
+			      tipc_max_domain_size, l->addr,
 			      tipc_own_addr(l->net), 0, 0, 0);
 	if (!skb)
 		return;
 
 	hdr = buf_msg(skb);
+	data = msg_data(hdr);
 	msg_set_session(hdr, l->session);
 	msg_set_bearer_id(hdr, l->bearer_id);
 	msg_set_net_plane(hdr, l->net_plane);
@@ -1273,14 +1287,18 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 
 	if (mtyp == STATE_MSG) {
 		msg_set_seq_gap(hdr, rcvgap);
-		msg_set_size(hdr, INT_H_SIZE);
 		msg_set_probe(hdr, probe);
+		tipc_mon_prep(l->net, data, &dlen, mstate, l->bearer_id);
+		msg_set_size(hdr, INT_H_SIZE + dlen);
+		skb_trim(skb, INT_H_SIZE + dlen);
 		l->stats.sent_states++;
 		l->rcv_unacked = 0;
 	} else {
 		/* RESET_MSG or ACTIVATE_MSG */
 		msg_set_max_pkt(hdr, l->advertised_mtu);
-		strcpy(msg_data(hdr), l->if_name);
+		strcpy(data, l->if_name);
+		msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME);
+		skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME);
 	}
 	if (probe)
 		l->stats.sent_probes++;
@@ -1373,7 +1391,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 	u16 peers_tol = msg_link_tolerance(hdr);
 	u16 peers_prio = msg_linkprio(hdr);
 	u16 rcv_nxt = l->rcv_nxt;
+	u16 dlen = msg_data_sz(hdr);
 	int mtyp = msg_type(hdr);
+	void *data;
 	char *if_name;
 	int rc = 0;
 
@@ -1383,6 +1403,10 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 	if (tipc_own_addr(l->net) > msg_prevnode(hdr))
 		l->net_plane = msg_net_plane(hdr);
 
+	skb_linearize(skb);
+	hdr = buf_msg(skb);
+	data = msg_data(hdr);
+
 	switch (mtyp) {
 	case RESET_MSG:
 
@@ -1393,8 +1417,6 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 		/* fall thru' */
 
 	case ACTIVATE_MSG:
-		skb_linearize(skb);
-		hdr = buf_msg(skb);
 
 		/* Complete own link name with peer's interface name */
 		if_name =  strrchr(l->name, ':') + 1;
@@ -1402,7 +1424,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 			break;
 		if (msg_data_sz(hdr) < TIPC_MAX_IF_NAME)
 			break;
-		strncpy(if_name, msg_data(hdr),	TIPC_MAX_IF_NAME);
+		strncpy(if_name, data, TIPC_MAX_IF_NAME);
 
 		/* Update own tolerance if peer indicates a non-zero value */
 		if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL))
@@ -1450,6 +1472,8 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 				rc = TIPC_LINK_UP_EVT;
 			break;
 		}
+		tipc_mon_rcv(l->net, data, dlen, l->addr,
+			     &l->mon_state, l->bearer_id);
 
 		/* Send NACK if peer has sent pkts we haven't received yet */
 		if (more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l))
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
new file mode 100644
index 000000000000..0d489e81fcca
--- /dev/null
+++ b/net/tipc/monitor.c
@@ -0,0 +1,651 @@
+/*
+ * net/tipc/monitor.c
+ *
+ * Copyright (c) 2016, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "core.h"
+#include "addr.h"
+#include "monitor.h"
+
+#define MAX_MON_DOMAIN       64
+#define MON_TIMEOUT          120000
+#define MAX_PEER_DOWN_EVENTS 4
+
+/* struct tipc_mon_domain: domain record to be transferred between peers
+ * @len: actual size of domain record
+ * @gen: current generation of sender's domain
+ * @ack_gen: most recent generation of self's domain acked by peer
+ * @member_cnt: number of domain member nodes described in this record
+ * @up_map: bit map indicating which of the members the sender considers up
+ * @members: identity of the domain members
+ */
+struct tipc_mon_domain {
+	u16 len;
+	u16 gen;
+	u16 ack_gen;
+	u16 member_cnt;
+	u64 up_map;
+	u32 members[MAX_MON_DOMAIN];
+};
+
+/* struct tipc_peer: state of a peer node and its domain
+ * @addr: tipc node identity of peer
+ * @head_map: shows which other nodes currently consider peer 'up'
+ * @domain: most recent domain record from peer
+ * @hash: position in hashed lookup list
+ * @list: position in linked list, in circular ascending order by 'addr'
+ * @applied: number of reported domain members applied on this monitor list
+ * @is_up: peer is up as seen from this node
+ * @is_head: peer is assigned domain head as seen from this node
+ * @is_local: peer is in local domain and should be continuously monitored
+ * @down_cnt: - numbers of other peers which have reported this on lost
+ */
+struct tipc_peer {
+	u32 addr;
+	struct tipc_mon_domain *domain;
+	struct hlist_node hash;
+	struct list_head list;
+	u8 applied;
+	u8 down_cnt;
+	bool is_up;
+	bool is_head;
+	bool is_local;
+};
+
+struct tipc_monitor {
+	struct hlist_head peers[NODE_HTABLE_SIZE];
+	int peer_cnt;
+	struct tipc_peer *self;
+	rwlock_t lock;
+	struct tipc_mon_domain cache;
+	u16 list_gen;
+	u16 dom_gen;
+	struct net *net;
+	struct timer_list timer;
+	unsigned long timer_intv;
+};
+
+static struct tipc_monitor *tipc_monitor(struct net *net, int bearer_id)
+{
+	return tipc_net(net)->monitors[bearer_id];
+}
+
+const int tipc_max_domain_size = sizeof(struct tipc_mon_domain);
+
+/* dom_rec_len(): actual length of domain record for transport
+ */
+static int dom_rec_len(struct tipc_mon_domain *dom, u16 mcnt)
+{
+	return ((void *)&dom->members - (void *)dom) + (mcnt * sizeof(u32));
+}
+
+/* dom_size() : calculate size of own domain based on number of peers
+ */
+static int dom_size(int peers)
+{
+	int i = 0;
+
+	while ((i * i) < peers)
+		i++;
+	return i < MAX_MON_DOMAIN ? i : MAX_MON_DOMAIN;
+}
+
+static void map_set(u64 *up_map, int i, unsigned int v)
+{
+	*up_map &= ~(1ULL << i);
+	*up_map |= ((u64)v << i);
+}
+
+static int map_get(u64 up_map, int i)
+{
+	return (up_map & (1 << i)) >> i;
+}
+
+static struct tipc_peer *peer_prev(struct tipc_peer *peer)
+{
+	return list_last_entry(&peer->list, struct tipc_peer, list);
+}
+
+static struct tipc_peer *peer_nxt(struct tipc_peer *peer)
+{
+	return list_first_entry(&peer->list, struct tipc_peer, list);
+}
+
+static struct tipc_peer *peer_head(struct tipc_peer *peer)
+{
+	while (!peer->is_head)
+		peer = peer_prev(peer);
+	return peer;
+}
+
+static struct tipc_peer *get_peer(struct tipc_monitor *mon, u32 addr)
+{
+	struct tipc_peer *peer;
+	unsigned int thash = tipc_hashfn(addr);
+
+	hlist_for_each_entry(peer, &mon->peers[thash], hash) {
+		if (peer->addr == addr)
+			return peer;
+	}
+	return NULL;
+}
+
+static struct tipc_peer *get_self(struct net *net, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+
+	return mon->self;
+}
+
+static inline bool tipc_mon_is_active(struct net *net, struct tipc_monitor *mon)
+{
+	struct tipc_net *tn = tipc_net(net);
+
+	return mon->peer_cnt > tn->mon_threshold;
+}
+
+/* mon_identify_lost_members() : - identify amd mark potentially lost members
+ */
+static void mon_identify_lost_members(struct tipc_peer *peer,
+				      struct tipc_mon_domain *dom_bef,
+				      int applied_bef)
+{
+	struct tipc_peer *member = peer;
+	struct tipc_mon_domain *dom_aft = peer->domain;
+	int applied_aft = peer->applied;
+	int i;
+
+	for (i = 0; i < applied_bef; i++) {
+		member = peer_nxt(member);
+
+		/* Do nothing if self or peer already see member as down */
+		if (!member->is_up || !map_get(dom_bef->up_map, i))
+			continue;
+
+		/* Loss of local node must be detected by active probing */
+		if (member->is_local)
+			continue;
+
+		/* Start probing if member was removed from applied domain */
+		if (!applied_aft || (applied_aft < i)) {
+			member->down_cnt = 1;
+			continue;
+		}
+
+		/* Member loss is confirmed if it is still in applied domain */
+		if (!map_get(dom_aft->up_map, i))
+			member->down_cnt++;
+	}
+}
+
+/* mon_apply_domain() : match a peer's domain record against monitor list
+ */
+static void mon_apply_domain(struct tipc_monitor *mon,
+			     struct tipc_peer *peer)
+{
+	struct tipc_mon_domain *dom = peer->domain;
+	struct tipc_peer *member;
+	u32 addr;
+	int i;
+
+	if (!dom || !peer->is_up)
+		return;
+
+	/* Scan across domain members and match against monitor list */
+	peer->applied = 0;
+	member = peer_nxt(peer);
+	for (i = 0; i < dom->member_cnt; i++) {
+		addr = dom->members[i];
+		if (addr != member->addr)
+			return;
+		peer->applied++;
+		member = peer_nxt(member);
+	}
+}
+
+/* mon_update_local_domain() : update after peer addition/removal/up/down
+ */
+static void mon_update_local_domain(struct tipc_monitor *mon)
+{
+	struct tipc_peer *self = mon->self;
+	struct tipc_mon_domain *cache = &mon->cache;
+	struct tipc_mon_domain *dom = self->domain;
+	struct tipc_peer *peer = self;
+	u64 prev_up_map = dom->up_map;
+	u16 member_cnt, i;
+	bool diff;
+
+	/* Update local domain size based on current size of cluster */
+	member_cnt = dom_size(mon->peer_cnt) - 1;
+	self->applied = member_cnt;
+
+	/* Update native and cached outgoing local domain records */
+	dom->len = dom_rec_len(dom, member_cnt);
+	diff = dom->member_cnt != member_cnt;
+	dom->member_cnt = member_cnt;
+	for (i = 0; i < member_cnt; i++) {
+		peer = peer_nxt(peer);
+		diff |= dom->members[i] != peer->addr;
+		dom->members[i] = peer->addr;
+		map_set(&dom->up_map, i, peer->is_up);
+		cache->members[i] = htonl(peer->addr);
+	}
+	diff |= dom->up_map != prev_up_map;
+	if (!diff)
+		return;
+	dom->gen = ++mon->dom_gen;
+	cache->len = htons(dom->len);
+	cache->gen = htons(dom->gen);
+	cache->member_cnt = htons(member_cnt);
+	cache->up_map = cpu_to_be64(dom->up_map);
+	mon_apply_domain(mon, self);
+}
+
+/* mon_update_neighbors() : update preceding neighbors of added/removed peer
+ */
+static void mon_update_neighbors(struct tipc_monitor *mon,
+				 struct tipc_peer *peer)
+{
+	int dz, i;
+
+	dz = dom_size(mon->peer_cnt);
+	for (i = 0; i < dz; i++) {
+		mon_apply_domain(mon, peer);
+		peer = peer_prev(peer);
+	}
+}
+
+/* mon_assign_roles() : reassign peer roles after a network change
+ * The monitor list is consistent at this stage; i.e., each peer is monitoring
+ * a set of domain members as matched between domain record and the monitor list
+ */
+static void mon_assign_roles(struct tipc_monitor *mon, struct tipc_peer *head)
+{
+	struct tipc_peer *peer = peer_nxt(head);
+	struct tipc_peer *self = mon->self;
+	int i = 0;
+
+	for (; peer != self; peer = peer_nxt(peer)) {
+		peer->is_local = false;
+
+		/* Update domain member */
+		if (i++ < head->applied) {
+			peer->is_head = false;
+			if (head == self)
+				peer->is_local = true;
+			continue;
+		}
+		/* Assign next domain head */
+		if (!peer->is_up)
+			continue;
+		if (peer->is_head)
+			break;
+		head = peer;
+		head->is_head = true;
+		i = 0;
+	}
+	mon->list_gen++;
+}
+
+void tipc_mon_remove_peer(struct net *net, u32 addr, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self = get_self(net, bearer_id);
+	struct tipc_peer *peer, *prev, *head;
+
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer)
+		goto exit;
+	prev = peer_prev(peer);
+	list_del(&peer->list);
+	hlist_del(&peer->hash);
+	kfree(peer->domain);
+	kfree(peer);
+	mon->peer_cnt--;
+	head = peer_head(prev);
+	if (head == self)
+		mon_update_local_domain(mon);
+	mon_update_neighbors(mon, prev);
+
+	/* Revert to full-mesh monitoring if we reach threshold */
+	if (!tipc_mon_is_active(net, mon)) {
+		list_for_each_entry(peer, &self->list, list) {
+			kfree(peer->domain);
+			peer->domain = NULL;
+			peer->applied = 0;
+		}
+	}
+	mon_assign_roles(mon, head);
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+static bool tipc_mon_add_peer(struct tipc_monitor *mon, u32 addr,
+			      struct tipc_peer **peer)
+{
+	struct tipc_peer *self = mon->self;
+	struct tipc_peer *cur, *prev, *p;
+
+	p = kzalloc(sizeof(*p), GFP_ATOMIC);
+	*peer = p;
+	if (!p)
+		return false;
+	p->addr = addr;
+
+	/* Add new peer to lookup list */
+	INIT_LIST_HEAD(&p->list);
+	hlist_add_head(&p->hash, &mon->peers[tipc_hashfn(addr)]);
+
+	/* Sort new peer into iterator list, in ascending circular order */
+	prev = self;
+	list_for_each_entry(cur, &self->list, list) {
+		if ((addr > prev->addr) && (addr < cur->addr))
+			break;
+		if (((addr < cur->addr) || (addr > prev->addr)) &&
+		    (prev->addr > cur->addr))
+			break;
+		prev = cur;
+	}
+	list_add_tail(&p->list, &cur->list);
+	mon->peer_cnt++;
+	mon_update_neighbors(mon, p);
+	return true;
+}
+
+void tipc_mon_peer_up(struct net *net, u32 addr, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self = get_self(net, bearer_id);
+	struct tipc_peer *peer, *head;
+
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer && !tipc_mon_add_peer(mon, addr, &peer))
+		goto exit;
+	peer->is_up = true;
+	head = peer_head(peer);
+	if (head == self)
+		mon_update_local_domain(mon);
+	mon_assign_roles(mon, head);
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+void tipc_mon_peer_down(struct net *net, u32 addr, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self = get_self(net, bearer_id);
+	struct tipc_peer *peer, *head;
+	struct tipc_mon_domain *dom;
+	int applied;
+
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer) {
+		pr_warn("Mon: unknown link %x/%u DOWN\n", addr, bearer_id);
+		goto exit;
+	}
+	applied = peer->applied;
+	peer->applied = 0;
+	dom = peer->domain;
+	peer->domain = NULL;
+	if (peer->is_head)
+		mon_identify_lost_members(peer, dom, applied);
+	kfree(dom);
+	peer->is_up = false;
+	peer->is_head = false;
+	peer->is_local = false;
+	peer->down_cnt = 0;
+	head = peer_head(peer);
+	if (head == self)
+		mon_update_local_domain(mon);
+	mon_assign_roles(mon, head);
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+/* tipc_mon_rcv - process monitor domain event message
+ */
+void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr,
+		  struct tipc_mon_state *state, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_mon_domain *arrv_dom = data;
+	struct tipc_mon_domain dom_bef;
+	struct tipc_mon_domain *dom;
+	struct tipc_peer *peer;
+	u16 new_member_cnt = ntohs(arrv_dom->member_cnt);
+	int new_dlen = dom_rec_len(arrv_dom, new_member_cnt);
+	u16 new_gen = ntohs(arrv_dom->gen);
+	u16 acked_gen = ntohs(arrv_dom->ack_gen);
+	bool probing = state->probing;
+	int i, applied_bef;
+
+	state->probing = false;
+	if (!dlen)
+		return;
+
+	/* Sanity check received domain record */
+	if ((dlen < new_dlen) || ntohs(arrv_dom->len) != new_dlen) {
+		pr_warn_ratelimited("Received illegal domain record\n");
+		return;
+	}
+
+	/* Synch generation numbers with peer if link just came up */
+	if (!state->synched) {
+		state->peer_gen = new_gen - 1;
+		state->acked_gen = acked_gen;
+		state->synched = true;
+	}
+
+	if (more(acked_gen, state->acked_gen))
+		state->acked_gen = acked_gen;
+
+	/* Drop duplicate unless we are waiting for a probe response */
+	if (!more(new_gen, state->peer_gen) && !probing)
+		return;
+
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer || !peer->is_up)
+		goto exit;
+
+	/* Peer is confirmed, stop any ongoing probing */
+	peer->down_cnt = 0;
+
+	/* Task is done for duplicate record */
+	if (!more(new_gen, state->peer_gen))
+		goto exit;
+
+	state->peer_gen = new_gen;
+
+	/* Cache current domain record for later use */
+	dom_bef.member_cnt = 0;
+	dom = peer->domain;
+	if (dom)
+		memcpy(&dom_bef, dom, dom->len);
+
+	/* Transform and store received domain record */
+	if (!dom || (dom->len < new_dlen)) {
+		kfree(dom);
+		dom = kmalloc(new_dlen, GFP_ATOMIC);
+		peer->domain = dom;
+		if (!dom)
+			goto exit;
+	}
+	dom->len = new_dlen;
+	dom->gen = new_gen;
+	dom->member_cnt = new_member_cnt;
+	dom->up_map = be64_to_cpu(arrv_dom->up_map);
+	for (i = 0; i < new_member_cnt; i++)
+		dom->members[i] = ntohl(arrv_dom->members[i]);
+
+	/* Update peers affected by this domain record */
+	applied_bef = peer->applied;
+	mon_apply_domain(mon, peer);
+	mon_identify_lost_members(peer, &dom_bef, applied_bef);
+	mon_assign_roles(mon, peer_head(peer));
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+void tipc_mon_prep(struct net *net, void *data, int *dlen,
+		   struct tipc_mon_state *state, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_mon_domain *dom = data;
+	u16 gen = mon->dom_gen;
+	u16 len;
+
+	if (!tipc_mon_is_active(net, mon))
+		return;
+
+	/* Send only a dummy record with ack if peer has acked our last sent */
+	if (likely(state->acked_gen == gen)) {
+		len = dom_rec_len(dom, 0);
+		*dlen = len;
+		dom->len = htons(len);
+		dom->gen = htons(gen);
+		dom->ack_gen = htons(state->peer_gen);
+		dom->member_cnt = 0;
+		return;
+	}
+	/* Send the full record */
+	read_lock_bh(&mon->lock);
+	len = ntohs(mon->cache.len);
+	*dlen = len;
+	memcpy(data, &mon->cache, len);
+	read_unlock_bh(&mon->lock);
+	dom->ack_gen = htons(state->peer_gen);
+}
+
+void tipc_mon_get_state(struct net *net, u32 addr,
+			struct tipc_mon_state *state,
+			int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *peer;
+
+	/* Used cached state if table has not changed */
+	if (!state->probing &&
+	    (state->list_gen == mon->list_gen) &&
+	    (state->acked_gen == mon->dom_gen))
+		return;
+
+	read_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (peer) {
+		state->probing = state->acked_gen != mon->dom_gen;
+		state->probing |= peer->down_cnt;
+		state->reset |= peer->down_cnt >= MAX_PEER_DOWN_EVENTS;
+		state->monitoring = peer->is_local;
+		state->monitoring |= peer->is_head;
+		state->list_gen = mon->list_gen;
+	}
+	read_unlock_bh(&mon->lock);
+}
+
+static void mon_timeout(unsigned long m)
+{
+	struct tipc_monitor *mon = (void *)m;
+	struct tipc_peer *self;
+	int best_member_cnt = dom_size(mon->peer_cnt) - 1;
+
+	write_lock_bh(&mon->lock);
+	self = mon->self;
+	if (self && (best_member_cnt != self->applied)) {
+		mon_update_local_domain(mon);
+		mon_assign_roles(mon, self);
+	}
+	write_unlock_bh(&mon->lock);
+	mod_timer(&mon->timer, jiffies + mon->timer_intv);
+}
+
+int tipc_mon_create(struct net *net, int bearer_id)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct tipc_monitor *mon;
+	struct tipc_peer *self;
+	struct tipc_mon_domain *dom;
+
+	if (tn->monitors[bearer_id])
+		return 0;
+
+	mon = kzalloc(sizeof(*mon), GFP_ATOMIC);
+	self = kzalloc(sizeof(*self), GFP_ATOMIC);
+	dom = kzalloc(sizeof(*dom), GFP_ATOMIC);
+	if (!mon || !self || !dom) {
+		kfree(mon);
+		kfree(self);
+		kfree(dom);
+		return -ENOMEM;
+	}
+	tn->monitors[bearer_id] = mon;
+	rwlock_init(&mon->lock);
+	mon->net = net;
+	mon->peer_cnt = 1;
+	mon->self = self;
+	self->domain = dom;
+	self->addr = tipc_own_addr(net);
+	self->is_up = true;
+	self->is_head = true;
+	INIT_LIST_HEAD(&self->list);
+	setup_timer(&mon->timer, mon_timeout, (unsigned long)mon);
+	mon->timer_intv = msecs_to_jiffies(MON_TIMEOUT + (tn->random & 0xffff));
+	mod_timer(&mon->timer, jiffies + mon->timer_intv);
+	return 0;
+}
+
+void tipc_mon_delete(struct net *net, int bearer_id)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self = get_self(net, bearer_id);
+	struct tipc_peer *peer, *tmp;
+
+	write_lock_bh(&mon->lock);
+	tn->monitors[bearer_id] = NULL;
+	list_for_each_entry_safe(peer, tmp, &self->list, list) {
+		list_del(&peer->list);
+		hlist_del(&peer->hash);
+		kfree(peer->domain);
+		kfree(peer);
+	}
+	mon->self = NULL;
+	write_unlock_bh(&mon->lock);
+	del_timer_sync(&mon->timer);
+	kfree(self->domain);
+	kfree(self);
+	kfree(mon);
+}
diff --git a/net/tipc/monitor.h b/net/tipc/monitor.h
new file mode 100644
index 000000000000..598459cbed5d
--- /dev/null
+++ b/net/tipc/monitor.h
@@ -0,0 +1,73 @@
+/*
+ * net/tipc/monitor.h
+ *
+ * Copyright (c) 2015, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_MONITOR_H
+#define _TIPC_MONITOR_H
+
+/* struct tipc_mon_state: link instance's cache of monitor list and domain state
+ * @list_gen: current generation of this node's monitor list
+ * @gen: current generation of this node's local domain
+ * @peer_gen: most recent domain generation received from peer
+ * @acked_gen: most recent generation of self's domain acked by peer
+ * @monitoring: this peer endpoint should continuously monitored
+ * @probing: peer endpoint should be temporarily probed for potential loss
+ * @synched: domain record's generation has been synched with peer after reset
+ */
+struct tipc_mon_state {
+	u16 list_gen;
+	u16 peer_gen;
+	u16 acked_gen;
+	bool monitoring :1;
+	bool probing    :1;
+	bool reset      :1;
+	bool synched    :1;
+};
+
+int tipc_mon_create(struct net *net, int bearer_id);
+void tipc_mon_delete(struct net *net, int bearer_id);
+
+void tipc_mon_peer_up(struct net *net, u32 addr, int bearer_id);
+void tipc_mon_peer_down(struct net *net, u32 addr, int bearer_id);
+void tipc_mon_prep(struct net *net, void *data, int *dlen,
+		   struct tipc_mon_state *state, int bearer_id);
+void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr,
+		  struct tipc_mon_state *state, int bearer_id);
+void tipc_mon_get_state(struct net *net, u32 addr,
+			struct tipc_mon_state *state,
+			int bearer_id);
+void tipc_mon_remove_peer(struct net *net, u32 addr, int bearer_id);
+
+extern const int tipc_max_domain_size;
+#endif
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 8740930f0787..17201aa8423d 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -41,6 +41,8 @@
 #include "name_table.h"
 
 #define MAX_FORWARD_SIZE 1024
+#define BUF_HEADROOM (LL_MAX_HEADER + 48)
+#define BUF_TAILROOM 16
 
 static unsigned int align(unsigned int i)
 {
@@ -505,6 +507,10 @@ bool tipc_msg_reverse(u32 own_node,  struct sk_buff **skb, int err)
 		msg_set_hdr_sz(hdr, BASIC_H_SIZE);
 	}
 
+	if (skb_cloned(_skb) &&
+	    pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_KERNEL))
+		goto exit;
+
 	/* Now reverse the concerned fields */
 	msg_set_errcode(hdr, err);
 	msg_set_origport(hdr, msg_destport(&ohdr));
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 024da8af91f0..7cf52fb39bee 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -94,17 +94,6 @@ struct plist;
 
 #define TIPC_MEDIA_INFO_OFFSET	5
 
-/**
- * TIPC message buffer code
- *
- * TIPC message buffer headroom reserves space for the worst-case
- * link-level device header (in case the message is sent off-node).
- *
- * Note: Headroom should be a multiple of 4 to ensure the TIPC header fields
- *       are word aligned for quicker access
- */
-#define BUF_HEADROOM (LL_MAX_HEADER + 48)
-
 struct tipc_skb_cb {
 	void *handle;
 	struct sk_buff *tail;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index f795b1dd0ccd..3ad9fab1985f 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -604,7 +604,8 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
 
 	link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
 	link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
-	strcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]));
+	nla_strlcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]),
+		    TIPC_MAX_LINK_NAME);
 
 	return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
 			    &link_info, sizeof(link_info));
diff --git a/net/tipc/node.c b/net/tipc/node.c
index e01e2c71b5a1..a3fc0a3f4077 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -40,6 +40,7 @@
 #include "name_distr.h"
 #include "socket.h"
 #include "bcast.h"
+#include "monitor.h"
 #include "discover.h"
 #include "netlink.h"
 
@@ -205,17 +206,6 @@ u16 tipc_node_get_capabilities(struct net *net, u32 addr)
 	return caps;
 }
 
-/*
- * A trivial power-of-two bitmask technique is used for speed, since this
- * operation is done for every incoming TIPC packet. The number of hash table
- * entries has been chosen so that no hash chain exceeds 8 nodes and will
- * usually be much smaller (typically only a single node).
- */
-static unsigned int tipc_hashfn(u32 addr)
-{
-	return addr & (NODE_HTABLE_SIZE - 1);
-}
-
 static void tipc_node_kref_release(struct kref *kref)
 {
 	struct tipc_node *n = container_of(kref, struct tipc_node, kref);
@@ -279,6 +269,7 @@ static void tipc_node_write_unlock(struct tipc_node *n)
 	u32 addr = 0;
 	u32 flags = n->action_flags;
 	u32 link_id = 0;
+	u32 bearer_id;
 	struct list_head *publ_list;
 
 	if (likely(!flags)) {
@@ -288,6 +279,7 @@ static void tipc_node_write_unlock(struct tipc_node *n)
 
 	addr = n->addr;
 	link_id = n->link_id;
+	bearer_id = link_id & 0xffff;
 	publ_list = &n->publ_list;
 
 	n->action_flags &= ~(TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP |
@@ -301,13 +293,16 @@ static void tipc_node_write_unlock(struct tipc_node *n)
 	if (flags & TIPC_NOTIFY_NODE_UP)
 		tipc_named_node_up(net, addr);
 
-	if (flags & TIPC_NOTIFY_LINK_UP)
+	if (flags & TIPC_NOTIFY_LINK_UP) {
+		tipc_mon_peer_up(net, addr, bearer_id);
 		tipc_nametbl_publish(net, TIPC_LINK_STATE, addr, addr,
 				     TIPC_NODE_SCOPE, link_id, addr);
-
-	if (flags & TIPC_NOTIFY_LINK_DOWN)
+	}
+	if (flags & TIPC_NOTIFY_LINK_DOWN) {
+		tipc_mon_peer_down(net, addr, bearer_id);
 		tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr,
 				      link_id, addr);
+	}
 }
 
 struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities)
@@ -378,14 +373,13 @@ static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l)
 {
 	unsigned long tol = tipc_link_tolerance(l);
 	unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4;
-	unsigned long keepalive_intv = msecs_to_jiffies(intv);
 
 	/* Link with lowest tolerance determines timer interval */
-	if (keepalive_intv < n->keepalive_intv)
-		n->keepalive_intv = keepalive_intv;
+	if (intv < n->keepalive_intv)
+		n->keepalive_intv = intv;
 
-	/* Ensure link's abort limit corresponds to current interval */
-	tipc_link_set_abort_limit(l, tol / jiffies_to_msecs(n->keepalive_intv));
+	/* Ensure link's abort limit corresponds to current tolerance */
+	tipc_link_set_abort_limit(l, tol / n->keepalive_intv);
 }
 
 static void tipc_node_delete(struct tipc_node *node)
@@ -526,7 +520,7 @@ static void tipc_node_timeout(unsigned long data)
 		if (rc & TIPC_LINK_DOWN_EVT)
 			tipc_node_link_down(n, bearer_id, false);
 	}
-	mod_timer(&n->timer, jiffies + n->keepalive_intv);
+	mod_timer(&n->timer, jiffies + msecs_to_jiffies(n->keepalive_intv));
 }
 
 /**
@@ -692,6 +686,7 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
 	struct tipc_link *l = le->link;
 	struct tipc_media_addr *maddr;
 	struct sk_buff_head xmitq;
+	int old_bearer_id = bearer_id;
 
 	if (!l)
 		return;
@@ -711,6 +706,8 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
 		tipc_link_fsm_evt(l, LINK_RESET_EVT);
 	}
 	tipc_node_write_unlock(n);
+	if (delete)
+		tipc_mon_remove_peer(n->net, n->addr, old_bearer_id);
 	tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr);
 	tipc_sk_rcv(n->net, &le->inputq);
 }
@@ -735,6 +732,7 @@ void tipc_node_check_dest(struct net *net, u32 onode,
 	bool accept_addr = false;
 	bool reset = true;
 	char *if_name;
+	unsigned long intv;
 
 	*dupl_addr = false;
 	*respond = false;
@@ -840,9 +838,11 @@ void tipc_node_check_dest(struct net *net, u32 onode,
 		le->link = l;
 		n->link_cnt++;
 		tipc_node_calculate_timer(n, l);
-		if (n->link_cnt == 1)
-			if (!mod_timer(&n->timer, jiffies + n->keepalive_intv))
+		if (n->link_cnt == 1) {
+			intv = jiffies + msecs_to_jiffies(n->keepalive_intv);
+			if (!mod_timer(&n->timer, intv))
 				tipc_node_get(n);
+		}
 	}
 	memcpy(&le->maddr, maddr, sizeof(*maddr));
 exit:
@@ -950,7 +950,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt)
 			state = SELF_UP_PEER_UP;
 			break;
 		case SELF_LOST_CONTACT_EVT:
-			state = SELF_DOWN_PEER_LEAVING;
+			state = SELF_DOWN_PEER_DOWN;
 			break;
 		case SELF_ESTABL_CONTACT_EVT:
 		case PEER_LOST_CONTACT_EVT:
@@ -969,7 +969,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt)
 			state = SELF_UP_PEER_UP;
 			break;
 		case PEER_LOST_CONTACT_EVT:
-			state = SELF_LEAVING_PEER_DOWN;
+			state = SELF_DOWN_PEER_DOWN;
 			break;
 		case SELF_LOST_CONTACT_EVT:
 		case PEER_ESTABL_CONTACT_EVT:
diff --git a/net/tipc/server.c b/net/tipc/server.c
index 272d20a795d5..215849ce453d 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -418,13 +418,12 @@ static struct outqueue_entry *tipc_alloc_entry(void *data, int len)
 	if (!entry)
 		return NULL;
 
-	buf = kmalloc(len, GFP_ATOMIC);
+	buf = kmemdup(data, len, GFP_ATOMIC);
 	if (!buf) {
 		kfree(entry);
 		return NULL;
 	}
 
-	memcpy(buf, data, len);
 	entry->iov.iov_base = buf;
 	entry->iov.iov_len = len;
 
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 88bfcd707064..c49b8df438cb 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -796,9 +796,11 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
  * @tsk: receiving socket
  * @skb: pointer to message buffer.
  */
-static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb)
+static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
+			      struct sk_buff_head *xmitq)
 {
 	struct sock *sk = &tsk->sk;
+	u32 onode = tsk_own_node(tsk);
 	struct tipc_msg *hdr = buf_msg(skb);
 	int mtyp = msg_type(hdr);
 	bool conn_cong;
@@ -811,7 +813,8 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb)
 
 	if (mtyp == CONN_PROBE) {
 		msg_set_type(hdr, CONN_PROBE_REPLY);
-		tipc_sk_respond(sk, skb, TIPC_OK);
+		if (tipc_msg_reverse(onode, &skb, TIPC_OK))
+			__skb_queue_tail(xmitq, skb);
 		return;
 	} else if (mtyp == CONN_ACK) {
 		conn_cong = tsk_conn_cong(tsk);
@@ -1686,7 +1689,8 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
  *
  * Returns true if message was added to socket receive queue, otherwise false
  */
-static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
+static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
+		       struct sk_buff_head *xmitq)
 {
 	struct socket *sock = sk->sk_socket;
 	struct tipc_sock *tsk = tipc_sk(sk);
@@ -1696,7 +1700,7 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
 	int usr = msg_user(hdr);
 
 	if (unlikely(msg_user(hdr) == CONN_MANAGER)) {
-		tipc_sk_proto_rcv(tsk, skb);
+		tipc_sk_proto_rcv(tsk, skb, xmitq);
 		return false;
 	}
 
@@ -1739,7 +1743,8 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
 	return true;
 
 reject:
-	tipc_sk_respond(sk, skb, err);
+	if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err))
+		__skb_queue_tail(xmitq, skb);
 	return false;
 }
 
@@ -1755,9 +1760,24 @@ reject:
 static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
 	unsigned int truesize = skb->truesize;
+	struct sk_buff_head xmitq;
+	u32 dnode, selector;
 
-	if (likely(filter_rcv(sk, skb)))
+	__skb_queue_head_init(&xmitq);
+
+	if (likely(filter_rcv(sk, skb, &xmitq))) {
 		atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt);
+		return 0;
+	}
+
+	if (skb_queue_empty(&xmitq))
+		return 0;
+
+	/* Send response/rejected message */
+	skb = __skb_dequeue(&xmitq);
+	dnode = msg_destnode(buf_msg(skb));
+	selector = msg_origport(buf_msg(skb));
+	tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
 	return 0;
 }
 
@@ -1771,12 +1791,13 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb)
  * Caller must hold socket lock
  */
 static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
-			    u32 dport)
+			    u32 dport, struct sk_buff_head *xmitq)
 {
+	unsigned long time_limit = jiffies + 2;
+	struct sk_buff *skb;
 	unsigned int lim;
 	atomic_t *dcnt;
-	struct sk_buff *skb;
-	unsigned long time_limit = jiffies + 2;
+	u32 onode;
 
 	while (skb_queue_len(inputq)) {
 		if (unlikely(time_after_eq(jiffies, time_limit)))
@@ -1788,7 +1809,7 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
 
 		/* Add message directly to receive queue if possible */
 		if (!sock_owned_by_user(sk)) {
-			filter_rcv(sk, skb);
+			filter_rcv(sk, skb, xmitq);
 			continue;
 		}
 
@@ -1801,7 +1822,9 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
 			continue;
 
 		/* Overload => reject message back to sender */
-		tipc_sk_respond(sk, skb, TIPC_ERR_OVERLOAD);
+		onode = tipc_own_addr(sock_net(sk));
+		if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD))
+			__skb_queue_tail(xmitq, skb);
 		break;
 	}
 }
@@ -1814,12 +1837,14 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
  */
 void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
 {
+	struct sk_buff_head xmitq;
 	u32 dnode, dport = 0;
 	int err;
 	struct tipc_sock *tsk;
 	struct sock *sk;
 	struct sk_buff *skb;
 
+	__skb_queue_head_init(&xmitq);
 	while (skb_queue_len(inputq)) {
 		dport = tipc_skb_peek_port(inputq, dport);
 		tsk = tipc_sk_lookup(net, dport);
@@ -1827,9 +1852,14 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
 		if (likely(tsk)) {
 			sk = &tsk->sk;
 			if (likely(spin_trylock_bh(&sk->sk_lock.slock))) {
-				tipc_sk_enqueue(inputq, sk, dport);
+				tipc_sk_enqueue(inputq, sk, dport, &xmitq);
 				spin_unlock_bh(&sk->sk_lock.slock);
 			}
+			/* Send pending response/rejected messages, if any */
+			while ((skb = __skb_dequeue(&xmitq))) {
+				dnode = msg_destnode(buf_msg(skb));
+				tipc_node_xmit_skb(net, skb, dnode, dport);
+			}
 			sock_put(sk);
 			continue;
 		}
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index c9cf2be3674a..b016c011970b 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -63,7 +63,7 @@
  */
 struct udp_media_addr {
 	__be16	proto;
-	__be16	udp_port;
+	__be16	port;
 	union {
 		struct in_addr ipv4;
 		struct in6_addr ipv6;
@@ -108,9 +108,9 @@ static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size)
 	struct udp_media_addr *ua = (struct udp_media_addr *)&a->value;
 
 	if (ntohs(ua->proto) == ETH_P_IP)
-		snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->udp_port));
+		snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->port));
 	else if (ntohs(ua->proto) == ETH_P_IPV6)
-		snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->udp_port));
+		snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->port));
 	else
 		pr_err("Invalid UDP media address\n");
 	return 0;
@@ -178,8 +178,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
 		skb->dev = rt->dst.dev;
 		ttl = ip4_dst_hoplimit(&rt->dst);
 		udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, src->ipv4.s_addr,
-				    dst->ipv4.s_addr, 0, ttl, 0, src->udp_port,
-				    dst->udp_port, false, true);
+				    dst->ipv4.s_addr, 0, ttl, 0, src->port,
+				    dst->port, false, true);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
 		struct dst_entry *ndst;
@@ -196,8 +196,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
 		ttl = ip6_dst_hoplimit(ndst);
 		err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb,
 					   ndst->dev, &src->ipv6,
-					   &dst->ipv6, 0, ttl, 0, src->udp_port,
-					   dst->udp_port, false);
+					   &dst->ipv6, 0, ttl, 0, src->port,
+					   dst->port, false);
 #endif
 	}
 	return err;
@@ -292,12 +292,12 @@ err:
 
 		ip4 = (struct sockaddr_in *)&sa_local;
 		local->proto = htons(ETH_P_IP);
-		local->udp_port = ip4->sin_port;
+		local->port = ip4->sin_port;
 		local->ipv4.s_addr = ip4->sin_addr.s_addr;
 
 		ip4 = (struct sockaddr_in *)&sa_remote;
 		remote->proto = htons(ETH_P_IP);
-		remote->udp_port = ip4->sin_port;
+		remote->port = ip4->sin_port;
 		remote->ipv4.s_addr = ip4->sin_addr.s_addr;
 		return 0;
 
@@ -312,13 +312,13 @@ err:
 			return -EINVAL;
 
 		local->proto = htons(ETH_P_IPV6);
-		local->udp_port = ip6->sin6_port;
+		local->port = ip6->sin6_port;
 		memcpy(&local->ipv6, &ip6->sin6_addr, sizeof(struct in6_addr));
 		ub->ifindex = ip6->sin6_scope_id;
 
 		ip6 = (struct sockaddr_in6 *)&sa_remote;
 		remote->proto = htons(ETH_P_IPV6);
-		remote->udp_port = ip6->sin6_port;
+		remote->port = ip6->sin6_port;
 		memcpy(&remote->ipv6, &ip6->sin6_addr, sizeof(struct in6_addr));
 		return 0;
 #endif
@@ -386,7 +386,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 		err = -EAFNOSUPPORT;
 		goto err;
 	}
-	udp_conf.local_udp_port = local.udp_port;
+	udp_conf.local_udp_port = local.port;
 	err = udp_sock_create(net, &udp_conf, &ub->ubsock);
 	if (err)
 		goto err;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 80aa6a3e6817..735362c26c8e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -315,7 +315,7 @@ static struct sock *unix_find_socket_byinode(struct inode *i)
 		    &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) {
 		struct dentry *dentry = unix_sk(s)->path.dentry;
 
-		if (dentry && d_backing_inode(dentry) == i) {
+		if (dentry && d_real_inode(dentry) == i) {
 			sock_hold(s);
 			goto found;
 		}
@@ -911,7 +911,7 @@ static struct sock *unix_find_other(struct net *net,
 		err = kern_path(sunname->sun_path, LOOKUP_FOLLOW, &path);
 		if (err)
 			goto fail;
-		inode = d_backing_inode(path.dentry);
+		inode = d_real_inode(path.dentry);
 		err = inode_permission(inode, MAY_WRITE);
 		if (err)
 			goto put_fail;
@@ -1048,7 +1048,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 			goto out_up;
 		}
 		addr->hash = UNIX_HASH_SIZE;
-		hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
+		hash = d_real_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
 		spin_lock(&unix_table_lock);
 		u->path = u_path;
 		list = &unix_socket_table[hash];
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index b5f1221f48d4..b96ac918e0ba 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -61,6 +61,14 @@
  * function will also cleanup rejected sockets, those that reach the connected
  * state but leave it before they have been accepted.
  *
+ * - Lock ordering for pending or accept queue sockets is:
+ *
+ *     lock_sock(listener);
+ *     lock_sock_nested(pending, SINGLE_DEPTH_NESTING);
+ *
+ * Using explicit nested locking keeps lockdep happy since normally only one
+ * lock of a given class may be taken at a time.
+ *
  * - Sockets created by user action will be cleaned up when the user process
  * calls close(2), causing our release implementation to be called. Our release
  * implementation will perform some cleanup then drop the last reference so our
@@ -443,7 +451,7 @@ void vsock_pending_work(struct work_struct *work)
 	cleanup = true;
 
 	lock_sock(listener);
-	lock_sock(sk);
+	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 
 	if (vsock_is_pending(sk)) {
 		vsock_remove_pending(listener, sk);
@@ -1292,7 +1300,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags)
 	if (connected) {
 		listener->sk_ack_backlog--;
 
-		lock_sock(connected);
+		lock_sock_nested(connected, SINGLE_DEPTH_NESTING);
 		vconnected = vsock_sk(connected);
 
 		/* If the listener socket has received an error, then we should
diff --git a/net/wireless/core.c b/net/wireless/core.c
index d25c82bc1bbe..39d9abd309ea 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -363,8 +363,6 @@ struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv,
 	WARN_ON(ops->remain_on_channel && !ops->cancel_remain_on_channel);
 	WARN_ON(ops->tdls_channel_switch && !ops->tdls_cancel_channel_switch);
 	WARN_ON(ops->add_tx_ts && !ops->del_tx_ts);
-	WARN_ON(ops->set_tx_power && !ops->get_tx_power);
-	WARN_ON(ops->set_antenna && !ops->get_antenna);
 
 	alloc_size = sizeof(*rdev) + sizeof_priv;
 
@@ -750,6 +748,36 @@ int wiphy_register(struct wiphy *wiphy)
 		nl80211_send_reg_change_event(&request);
 	}
 
+	/* Check that nobody globally advertises any capabilities they do not
+	 * advertise on all possible interface types.
+	 */
+	if (wiphy->extended_capabilities_len &&
+	    wiphy->num_iftype_ext_capab &&
+	    wiphy->iftype_ext_capab) {
+		u8 supported_on_all, j;
+		const struct wiphy_iftype_ext_capab *capab;
+
+		capab = wiphy->iftype_ext_capab;
+		for (j = 0; j < wiphy->extended_capabilities_len; j++) {
+			if (capab[0].extended_capabilities_len > j)
+				supported_on_all =
+					capab[0].extended_capabilities[j];
+			else
+				supported_on_all = 0x00;
+			for (i = 1; i < wiphy->num_iftype_ext_capab; i++) {
+				if (j >= capab[i].extended_capabilities_len) {
+					supported_on_all = 0x00;
+					break;
+				}
+				supported_on_all &=
+					capab[i].extended_capabilities[j];
+			}
+			if (WARN_ON(wiphy->extended_capabilities[j] &
+				    ~supported_on_all))
+				break;
+		}
+	}
+
 	rdev->wiphy.registered = true;
 	rtnl_unlock();
 
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 025b7a5d508b..a4d547f99f8d 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -214,7 +214,7 @@ struct cfg80211_event {
 			size_t req_ie_len;
 			size_t resp_ie_len;
 			struct cfg80211_bss *bss;
-			u16 status;
+			int status; /* -1 = failed; 0..65535 = status code */
 		} cr;
 		struct {
 			const u8 *req_ie;
@@ -374,7 +374,7 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev,
 void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			       const u8 *req_ie, size_t req_ie_len,
 			       const u8 *resp_ie, size_t resp_ie_len,
-			       u16 status, bool wextev,
+			       int status, bool wextev,
 			       struct cfg80211_bss *bss);
 void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 			     size_t ie_len, u16 reason, bool from_ap);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d7599014055d..c503e96bfd5a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -167,6 +167,7 @@ __cfg80211_rdev_from_attrs(struct net *netns, struct nlattr **attrs)
 
 	if (attrs[NL80211_ATTR_IFINDEX]) {
 		int ifindex = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]);
+
 		netdev = __dev_get_by_index(netns, ifindex);
 		if (netdev) {
 			if (netdev->ieee80211_ptr)
@@ -731,6 +732,7 @@ static int nl80211_parse_key_new(struct nlattr *key, struct key_parse *k)
 
 	if (tb[NL80211_KEY_DEFAULT_TYPES]) {
 		struct nlattr *kdt[NUM_NL80211_KEY_DEFAULT_TYPES];
+
 		err = nla_parse_nested(kdt, NUM_NL80211_KEY_DEFAULT_TYPES - 1,
 				       tb[NL80211_KEY_DEFAULT_TYPES],
 				       nl80211_key_default_policy);
@@ -1264,7 +1266,7 @@ nl80211_send_mgmt_stypes(struct sk_buff *msg,
 struct nl80211_dump_wiphy_state {
 	s64 filter_wiphy;
 	long start;
-	long split_start, band_start, chan_start;
+	long split_start, band_start, chan_start, capa_start;
 	bool split;
 };
 
@@ -1382,6 +1384,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		    rdev->ops->get_antenna) {
 			u32 tx_ant = 0, rx_ant = 0;
 			int res;
+
 			res = rdev_get_antenna(rdev, &tx_ant, &rx_ant);
 			if (!res) {
 				if (nla_put_u32(msg,
@@ -1761,6 +1764,47 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			nla_nest_end(msg, nested);
 		}
 
+		state->split_start++;
+		break;
+	case 13:
+		if (rdev->wiphy.num_iftype_ext_capab &&
+		    rdev->wiphy.iftype_ext_capab) {
+			struct nlattr *nested_ext_capab, *nested;
+
+			nested = nla_nest_start(msg,
+						NL80211_ATTR_IFTYPE_EXT_CAPA);
+			if (!nested)
+				goto nla_put_failure;
+
+			for (i = state->capa_start;
+			     i < rdev->wiphy.num_iftype_ext_capab; i++) {
+				const struct wiphy_iftype_ext_capab *capab;
+
+				capab = &rdev->wiphy.iftype_ext_capab[i];
+
+				nested_ext_capab = nla_nest_start(msg, i);
+				if (!nested_ext_capab ||
+				    nla_put_u32(msg, NL80211_ATTR_IFTYPE,
+						capab->iftype) ||
+				    nla_put(msg, NL80211_ATTR_EXT_CAPA,
+					    capab->extended_capabilities_len,
+					    capab->extended_capabilities) ||
+				    nla_put(msg, NL80211_ATTR_EXT_CAPA_MASK,
+					    capab->extended_capabilities_len,
+					    capab->extended_capabilities_mask))
+					goto nla_put_failure;
+
+				nla_nest_end(msg, nested_ext_capab);
+				if (state->split)
+					break;
+			}
+			nla_nest_end(msg, nested);
+			if (i < rdev->wiphy.num_iftype_ext_capab) {
+				state->capa_start = i + 1;
+				break;
+			}
+		}
+
 		/* done */
 		state->split_start = 0;
 		break;
@@ -2116,7 +2160,6 @@ static int nl80211_set_wds_peer(struct sk_buff *skb, struct genl_info *info)
 	return rdev_set_wds_peer(rdev, dev, bssid);
 }
 
-
 static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev;
@@ -2251,6 +2294,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX] &&
 	    info->attrs[NL80211_ATTR_WIPHY_ANTENNA_RX]) {
 		u32 tx_ant, rx_ant;
+
 		if ((!rdev->wiphy.available_antennas_tx &&
 		     !rdev->wiphy.available_antennas_rx) ||
 		    !rdev->ops->set_antenna)
@@ -2919,6 +2963,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info)
 	pairwise = !!mac_addr;
 	if (info->attrs[NL80211_ATTR_KEY_TYPE]) {
 		u32 kt = nla_get_u32(info->attrs[NL80211_ATTR_KEY_TYPE]);
+
 		if (kt >= NUM_NL80211_KEYTYPES)
 			return -EINVAL;
 		if (kt != NL80211_KEYTYPE_GROUP &&
@@ -3962,7 +4007,6 @@ static int nl80211_dump_station(struct sk_buff *skb,
 		sta_idx++;
 	}
 
-
  out:
 	cb->args[2] = sta_idx;
 	err = skb->len;
@@ -4763,7 +4807,6 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 		path_idx++;
 	}
 
-
  out:
 	cb->args[2] = path_idx;
 	err = skb->len;
@@ -5053,7 +5096,6 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info)
 	enum nl80211_user_reg_hint_type user_reg_hint_type;
 	u32 owner_nlportid;
 
-
 	/*
 	 * You should only get this when cfg80211 hasn't yet initialized
 	 * completely when built-in to the kernel right between the time
@@ -5262,7 +5304,6 @@ do {									    \
 	}								    \
 } while (0)
 
-
 	if (!info->attrs[NL80211_ATTR_MESH_CONFIG])
 		return -EINVAL;
 	if (nla_parse_nested(tb, NL80211_MESHCONF_ATTR_MAX,
@@ -5409,7 +5450,6 @@ static int nl80211_parse_mesh_setup(struct genl_info *info,
 		 IEEE80211_PATH_METRIC_VENDOR :
 		 IEEE80211_PATH_METRIC_AIRTIME;
 
-
 	if (tb[NL80211_MESH_SETUP_IE]) {
 		struct nlattr *ieattr =
 			tb[NL80211_MESH_SETUP_IE];
@@ -5796,10 +5836,8 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	r = set_regdom(rd, REGD_SOURCE_CRDA);
-	/* set_regdom took ownership */
-	rd = NULL;
-
+	/* set_regdom takes ownership of rd */
+	return set_regdom(rd, REGD_SOURCE_CRDA);
  bad_reg:
 	kfree(rd);
 	return r;
@@ -6033,6 +6071,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 		/* all channels */
 		for (band = 0; band < NUM_NL80211_BANDS; band++) {
 			int j;
+
 			if (!wiphy->bands[band])
 				continue;
 			for (j = 0; j < wiphy->bands[band]->n_channels; j++) {
@@ -6442,6 +6481,7 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 		/* all channels */
 		for (band = 0; band < NUM_NL80211_BANDS; band++) {
 			int j;
+
 			if (!wiphy->bands[band])
 				continue;
 			for (j = 0; j < wiphy->bands[band]->n_channels; j++) {
@@ -6511,7 +6551,7 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 				       nla_data(ssid), nla_len(ssid));
 				request->match_sets[i].ssid.ssid_len =
 					nla_len(ssid);
-				/* special attribute - old implemenation w/a */
+				/* special attribute - old implementation w/a */
 				request->match_sets[i].rssi_thold =
 					default_match_rssi;
 				rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI];
@@ -7204,6 +7244,7 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info)
 	if (key.idx >= 0) {
 		int i;
 		bool ok = false;
+
 		for (i = 0; i < rdev->wiphy.n_cipher_suites; i++) {
 			if (key.p.cipher == rdev->wiphy.cipher_suites[i]) {
 				ok = true;
@@ -7282,6 +7323,7 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
 
 	if (info->attrs[NL80211_ATTR_CONTROL_PORT_ETHERTYPE]) {
 		u16 proto;
+
 		proto = nla_get_u16(
 			info->attrs[NL80211_ATTR_CONTROL_PORT_ETHERTYPE]);
 		settings->control_port_ethertype = cpu_to_be16(proto);
@@ -8435,6 +8477,7 @@ static u32 rateset_to_mask(struct ieee80211_supported_band *sband,
 	for (i = 0; i < rates_len; i++) {
 		int rate = (rates[i] & 0x7f) * 5;
 		int ridx;
+
 		for (ridx = 0; ridx < sband->n_bitrates; ridx++) {
 			struct ieee80211_rate *srate =
 				&sband->bitrates[ridx];
@@ -8743,7 +8786,6 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 		if (params.wait < NL80211_MIN_REMAIN_ON_CHANNEL_TIME ||
 		    params.wait > rdev->wiphy.max_remain_on_channel_duration)
 			return -EINVAL;
-
 	}
 
 	params.offchan = info->attrs[NL80211_ATTR_OFFCHANNEL_TX_OK];
@@ -10590,7 +10632,6 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(cfg80211_vendor_cmd_reply);
 
-
 static int nl80211_set_qos_map(struct sk_buff *skb,
 			       struct genl_info *info)
 {
@@ -10945,7 +10986,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_WIPHY,
 		.doit = nl80211_set_wiphy,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_RTNL,
 	},
 	{
@@ -10961,7 +11002,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_INTERFACE,
 		.doit = nl80211_set_interface,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -10969,7 +11010,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_NEW_INTERFACE,
 		.doit = nl80211_new_interface,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -10977,7 +11018,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_DEL_INTERFACE,
 		.doit = nl80211_del_interface,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -10985,7 +11026,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_GET_KEY,
 		.doit = nl80211_get_key,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -10993,7 +11034,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_KEY,
 		.doit = nl80211_set_key,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
 				  NL80211_FLAG_CLEAR_SKB,
@@ -11002,7 +11043,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_NEW_KEY,
 		.doit = nl80211_new_key,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
 				  NL80211_FLAG_CLEAR_SKB,
@@ -11011,14 +11052,14 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_DEL_KEY,
 		.doit = nl80211_del_key,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_SET_BEACON,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_set_beacon,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -11026,7 +11067,7 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_START_AP,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_start_ap,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -11034,7 +11075,7 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_STOP_AP,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_stop_ap,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -11051,7 +11092,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_STATION,
 		.doit = nl80211_set_station,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11059,7 +11100,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_NEW_STATION,
 		.doit = nl80211_new_station,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11067,7 +11108,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_DEL_STATION,
 		.doit = nl80211_del_station,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11076,7 +11117,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.doit = nl80211_get_mpath,
 		.dumpit = nl80211_dump_mpath,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11085,7 +11126,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.doit = nl80211_get_mpp,
 		.dumpit = nl80211_dump_mpp,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11093,7 +11134,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_MPATH,
 		.doit = nl80211_set_mpath,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11101,7 +11142,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_NEW_MPATH,
 		.doit = nl80211_new_mpath,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11109,7 +11150,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_DEL_MPATH,
 		.doit = nl80211_del_mpath,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11117,7 +11158,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_BSS,
 		.doit = nl80211_set_bss,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11156,7 +11197,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_MESH_CONFIG,
 		.doit = nl80211_update_mesh_config,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11164,7 +11205,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_TRIGGER_SCAN,
 		.doit = nl80211_trigger_scan,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11172,7 +11213,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_ABORT_SCAN,
 		.doit = nl80211_abort_scan,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11185,7 +11226,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_START_SCHED_SCAN,
 		.doit = nl80211_start_sched_scan,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11193,7 +11234,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_STOP_SCHED_SCAN,
 		.doit = nl80211_stop_sched_scan,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11201,7 +11242,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_AUTHENTICATE,
 		.doit = nl80211_authenticate,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
 				  NL80211_FLAG_CLEAR_SKB,
@@ -11210,7 +11251,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_ASSOCIATE,
 		.doit = nl80211_associate,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11218,7 +11259,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_DEAUTHENTICATE,
 		.doit = nl80211_deauthenticate,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11226,7 +11267,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_DISASSOCIATE,
 		.doit = nl80211_disassociate,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11234,7 +11275,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_JOIN_IBSS,
 		.doit = nl80211_join_ibss,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11242,7 +11283,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_LEAVE_IBSS,
 		.doit = nl80211_leave_ibss,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11252,7 +11293,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.doit = nl80211_testmode_do,
 		.dumpit = nl80211_testmode_dump,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11261,7 +11302,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_CONNECT,
 		.doit = nl80211_connect,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11269,7 +11310,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_DISCONNECT,
 		.doit = nl80211_disconnect,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11277,7 +11318,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_WIPHY_NETNS,
 		.doit = nl80211_wiphy_netns,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11290,7 +11331,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_PMKSA,
 		.doit = nl80211_setdel_pmksa,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11298,7 +11339,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_DEL_PMKSA,
 		.doit = nl80211_setdel_pmksa,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11306,7 +11347,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_FLUSH_PMKSA,
 		.doit = nl80211_flush_pmksa,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11314,7 +11355,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_REMAIN_ON_CHANNEL,
 		.doit = nl80211_remain_on_channel,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11322,7 +11363,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL,
 		.doit = nl80211_cancel_remain_on_channel,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11330,7 +11371,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_TX_BITRATE_MASK,
 		.doit = nl80211_set_tx_bitrate_mask,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11338,7 +11379,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_REGISTER_FRAME,
 		.doit = nl80211_register_mgmt,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11346,7 +11387,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_FRAME,
 		.doit = nl80211_tx_mgmt,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11354,7 +11395,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_FRAME_WAIT_CANCEL,
 		.doit = nl80211_tx_mgmt_cancel_wait,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11362,7 +11403,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_POWER_SAVE,
 		.doit = nl80211_set_power_save,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11378,7 +11419,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_CQM,
 		.doit = nl80211_set_cqm,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11386,7 +11427,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_CHANNEL,
 		.doit = nl80211_set_channel,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11394,7 +11435,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_WDS_PEER,
 		.doit = nl80211_set_wds_peer,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11402,7 +11443,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_JOIN_MESH,
 		.doit = nl80211_join_mesh,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11410,7 +11451,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_LEAVE_MESH,
 		.doit = nl80211_leave_mesh,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11418,7 +11459,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_JOIN_OCB,
 		.doit = nl80211_join_ocb,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11426,7 +11467,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_LEAVE_OCB,
 		.doit = nl80211_leave_ocb,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11443,7 +11484,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_WOWLAN,
 		.doit = nl80211_set_wowlan,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11452,7 +11493,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_REKEY_OFFLOAD,
 		.doit = nl80211_set_rekey_data,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
 				  NL80211_FLAG_CLEAR_SKB,
@@ -11461,7 +11502,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_TDLS_MGMT,
 		.doit = nl80211_tdls_mgmt,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11469,7 +11510,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_TDLS_OPER,
 		.doit = nl80211_tdls_oper,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11477,7 +11518,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_UNEXPECTED_FRAME,
 		.doit = nl80211_register_unexpected_frame,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11485,7 +11526,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_PROBE_CLIENT,
 		.doit = nl80211_probe_client,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11493,7 +11534,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_REGISTER_BEACONS,
 		.doit = nl80211_register_beacons,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11501,7 +11542,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_NOACK_MAP,
 		.doit = nl80211_set_noack_map,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11509,7 +11550,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_START_P2P_DEVICE,
 		.doit = nl80211_start_p2p_device,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11517,7 +11558,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_STOP_P2P_DEVICE,
 		.doit = nl80211_stop_p2p_device,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11525,7 +11566,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_MCAST_RATE,
 		.doit = nl80211_set_mcast_rate,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11533,7 +11574,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_MAC_ACL,
 		.doit = nl80211_set_mac_acl,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11541,7 +11582,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_RADAR_DETECT,
 		.doit = nl80211_start_radar_detection,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11554,7 +11595,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_UPDATE_FT_IES,
 		.doit = nl80211_update_ft_ies,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11562,7 +11603,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_CRIT_PROTOCOL_START,
 		.doit = nl80211_crit_protocol_start,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11570,7 +11611,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_CRIT_PROTOCOL_STOP,
 		.doit = nl80211_crit_protocol_stop,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11585,7 +11626,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_COALESCE,
 		.doit = nl80211_set_coalesce,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11593,7 +11634,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_CHANNEL_SWITCH,
 		.doit = nl80211_channel_switch,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11602,7 +11643,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.doit = nl80211_vendor_cmd,
 		.dumpit = nl80211_vendor_cmd_dump,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11610,7 +11651,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_SET_QOS_MAP,
 		.doit = nl80211_set_qos_map,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11618,7 +11659,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_ADD_TX_TS,
 		.doit = nl80211_add_tx_ts,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11626,7 +11667,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_DEL_TX_TS,
 		.doit = nl80211_del_tx_ts,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11634,7 +11675,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_TDLS_CHANNEL_SWITCH,
 		.doit = nl80211_tdls_channel_switch,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11642,7 +11683,7 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_TDLS_CANCEL_CHANNEL_SWITCH,
 		.doit = nl80211_tdls_cancel_channel_switch,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -12092,7 +12133,7 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev,
 				 struct net_device *netdev, const u8 *bssid,
 				 const u8 *req_ie, size_t req_ie_len,
 				 const u8 *resp_ie, size_t resp_ie_len,
-				 u16 status, gfp_t gfp)
+				 int status, gfp_t gfp)
 {
 	struct sk_buff *msg;
 	void *hdr;
@@ -12110,7 +12151,10 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev,
 	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) ||
 	    (bssid && nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) ||
-	    nla_put_u16(msg, NL80211_ATTR_STATUS_CODE, status) ||
+	    nla_put_u16(msg, NL80211_ATTR_STATUS_CODE,
+			status < 0 ? WLAN_STATUS_UNSPECIFIED_FAILURE :
+			status) ||
+	    (status < 0 && nla_put_flag(msg, NL80211_ATTR_TIMED_OUT)) ||
 	    (req_ie &&
 	     nla_put(msg, NL80211_ATTR_REQ_IE, req_ie_len, req_ie)) ||
 	    (resp_ie &&
@@ -12126,7 +12170,6 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev,
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	nlmsg_free(msg);
-
 }
 
 void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
@@ -12165,7 +12208,6 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	nlmsg_free(msg);
-
 }
 
 void nl80211_send_disconnected(struct cfg80211_registered_device *rdev,
@@ -12203,7 +12245,6 @@ void nl80211_send_disconnected(struct cfg80211_registered_device *rdev,
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	nlmsg_free(msg);
-
 }
 
 void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev,
@@ -13545,7 +13586,6 @@ void cfg80211_crit_proto_stopped(struct wireless_dev *wdev, gfp_t gfp)
 	if (hdr)
 		genlmsg_cancel(msg, hdr);
 	nlmsg_free(msg);
-
 }
 EXPORT_SYMBOL(cfg80211_crit_proto_stopped);
 
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index 84d4edf1d545..a63f402b10b7 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -55,7 +55,7 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev,
 				 struct net_device *netdev, const u8 *bssid,
 				 const u8 *req_ie, size_t req_ie_len,
 				 const u8 *resp_ie, size_t resp_ie_len,
-				 u16 status, gfp_t gfp);
+				 int status, gfp_t gfp);
 void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
 			 struct net_device *netdev, const u8 *bssid,
 			 const u8 *req_ie, size_t req_ie_len,
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 584fdc347221..add6824c44fd 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -244,9 +244,7 @@ void cfg80211_conn_work(struct work_struct *work)
 		if (cfg80211_conn_do_work(wdev)) {
 			__cfg80211_connect_result(
 					wdev->netdev, bssid,
-					NULL, 0, NULL, 0,
-					WLAN_STATUS_UNSPECIFIED_FAILURE,
-					false, NULL);
+					NULL, 0, NULL, 0, -1, false, NULL);
 		}
 		wdev_unlock(wdev);
 	}
@@ -648,7 +646,7 @@ static DECLARE_WORK(cfg80211_disconnect_work, disconnect_work);
 void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			       const u8 *req_ie, size_t req_ie_len,
 			       const u8 *resp_ie, size_t resp_ie_len,
-			       u16 status, bool wextev,
+			       int status, bool wextev,
 			       struct cfg80211_bss *bss)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
@@ -757,7 +755,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid,
 			  struct cfg80211_bss *bss, const u8 *req_ie,
 			  size_t req_ie_len, const u8 *resp_ie,
-			  size_t resp_ie_len, u16 status, gfp_t gfp)
+			  size_t resp_ie_len, int status, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 4e809e978b7d..2443ee30ba5b 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -509,7 +509,7 @@ static int __ieee80211_data_to_8023(struct sk_buff *skb, struct ethhdr *ehdr,
 		 * replace EtherType */
 		hdrlen += ETH_ALEN + 2;
 	else
-		tmp.h_proto = htons(skb->len);
+		tmp.h_proto = htons(skb->len - hdrlen);
 
 	pskb_pull(skb, hdrlen);
 
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index 6250b1cfcde5..dbb2738e356a 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -958,8 +958,29 @@ static int wireless_process_ioctl(struct net *net, struct ifreq *ifr,
 			return private(dev, iwr, cmd, info, handler);
 	}
 	/* Old driver API : call driver ioctl handler */
-	if (dev->netdev_ops->ndo_do_ioctl)
-		return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd);
+	if (dev->netdev_ops->ndo_do_ioctl) {
+#ifdef CONFIG_COMPAT
+		if (info->flags & IW_REQUEST_FLAG_COMPAT) {
+			int ret = 0;
+			struct iwreq iwr_lcl;
+			struct compat_iw_point *iwp_compat = (void *) &iwr->u.data;
+
+			memcpy(&iwr_lcl, iwr, sizeof(struct iwreq));
+			iwr_lcl.u.data.pointer = compat_ptr(iwp_compat->pointer);
+			iwr_lcl.u.data.length = iwp_compat->length;
+			iwr_lcl.u.data.flags = iwp_compat->flags;
+
+			ret = dev->netdev_ops->ndo_do_ioctl(dev, (void *) &iwr_lcl, cmd);
+
+			iwp_compat->pointer = ptr_to_compat(iwr_lcl.u.data.pointer);
+			iwp_compat->length = iwr_lcl.u.data.length;
+			iwp_compat->flags = iwr_lcl.u.data.flags;
+
+			return ret;
+		} else
+#endif
+			return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd);
+	}
 	return -EOPNOTSUPP;
 }
 
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 0bf2478cb7df..a98b780e974c 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -20,6 +20,7 @@ hostprogs-y += offwaketime
 hostprogs-y += spintest
 hostprogs-y += map_perf_test
 hostprogs-y += test_overhead
+hostprogs-y += test_cgrp2_array_pin
 
 test_verifier-objs := test_verifier.o libbpf.o
 test_maps-objs := test_maps.o libbpf.o
@@ -40,6 +41,7 @@ offwaketime-objs := bpf_load.o libbpf.o offwaketime_user.o
 spintest-objs := bpf_load.o libbpf.o spintest_user.o
 map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o
 test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o
+test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -61,6 +63,7 @@ always += map_perf_test_kern.o
 always += test_overhead_tp_kern.o
 always += test_overhead_kprobe_kern.o
 always += parse_varlen.o parse_simple.o parse_ldabs.o
+always += test_cgrp2_tc_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index 7904a2a493de..84e3fd919a06 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -70,6 +70,8 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag
 	(void *) BPF_FUNC_l3_csum_replace;
 static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
 	(void *) BPF_FUNC_l4_csum_replace;
+static int (*bpf_skb_in_cgroup)(void *ctx, void *map, int index) =
+	(void *) BPF_FUNC_skb_in_cgroup;
 
 #if defined(__x86_64__)
 
diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c
index 29a276d766fc..8a4085c2d117 100644
--- a/samples/bpf/sockex2_user.c
+++ b/samples/bpf/sockex2_user.c
@@ -5,6 +5,7 @@
 #include "bpf_load.h"
 #include <unistd.h>
 #include <arpa/inet.h>
+#include <sys/resource.h>
 
 struct pair {
 	__u64 packets;
@@ -13,11 +14,13 @@ struct pair {
 
 int main(int ac, char **argv)
 {
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	char filename[256];
 	FILE *f;
 	int i, sock;
 
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	setrlimit(RLIMIT_MEMLOCK, &r);
 
 	if (load_bpf_file(filename)) {
 		printf("%s", bpf_log_buf);
diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c
index 2617772d060d..d4184ab5f3ac 100644
--- a/samples/bpf/sockex3_user.c
+++ b/samples/bpf/sockex3_user.c
@@ -5,6 +5,7 @@
 #include "bpf_load.h"
 #include <unistd.h>
 #include <arpa/inet.h>
+#include <sys/resource.h>
 
 struct flow_keys {
 	__be32 src;
@@ -23,11 +24,13 @@ struct pair {
 
 int main(int argc, char **argv)
 {
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	char filename[256];
 	FILE *f;
 	int i, sock;
 
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	setrlimit(RLIMIT_MEMLOCK, &r);
 
 	if (load_bpf_file(filename)) {
 		printf("%s", bpf_log_buf);
diff --git a/samples/bpf/test_cgrp2_array_pin.c b/samples/bpf/test_cgrp2_array_pin.c
new file mode 100644
index 000000000000..70e86f7be69d
--- /dev/null
+++ b/samples/bpf/test_cgrp2_array_pin.c
@@ -0,0 +1,109 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/unistd.h>
+#include <linux/bpf.h>
+
+#include <stdio.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <fcntl.h>
+
+#include "libbpf.h"
+
+static void usage(void)
+{
+	printf("Usage: test_cgrp2_array_pin [...]\n");
+	printf("       -F <file>   File to pin an BPF cgroup array\n");
+	printf("       -U <file>   Update an already pinned BPF cgroup array\n");
+	printf("       -v <value>  Full path of the cgroup2\n");
+	printf("       -h          Display this help\n");
+}
+
+int main(int argc, char **argv)
+{
+	const char *pinned_file = NULL, *cg2 = NULL;
+	int create_array = 1;
+	int array_key = 0;
+	int array_fd = -1;
+	int cg2_fd = -1;
+	int ret = -1;
+	int opt;
+
+	while ((opt = getopt(argc, argv, "F:U:v:")) != -1) {
+		switch (opt) {
+		/* General args */
+		case 'F':
+			pinned_file = optarg;
+			break;
+		case 'U':
+			pinned_file = optarg;
+			create_array = 0;
+			break;
+		case 'v':
+			cg2 = optarg;
+			break;
+		default:
+			usage();
+			goto out;
+		}
+	}
+
+	if (!cg2 || !pinned_file) {
+		usage();
+		goto out;
+	}
+
+	cg2_fd = open(cg2, O_RDONLY);
+	if (cg2_fd < 0) {
+		fprintf(stderr, "open(%s,...): %s(%d)\n",
+			cg2, strerror(errno), errno);
+		goto out;
+	}
+
+	if (create_array) {
+		array_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_ARRAY,
+					  sizeof(uint32_t), sizeof(uint32_t),
+					  1, 0);
+		if (array_fd < 0) {
+			fprintf(stderr,
+				"bpf_create_map(BPF_MAP_TYPE_CGROUP_ARRAY,...): %s(%d)\n",
+				strerror(errno), errno);
+			goto out;
+		}
+	} else {
+		array_fd = bpf_obj_get(pinned_file);
+		if (array_fd < 0) {
+			fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n",
+				pinned_file, strerror(errno), errno);
+			goto out;
+		}
+	}
+
+	ret = bpf_update_elem(array_fd, &array_key, &cg2_fd, 0);
+	if (ret) {
+		perror("bpf_update_elem");
+		goto out;
+	}
+
+	if (create_array) {
+		ret = bpf_obj_pin(array_fd, pinned_file);
+		if (ret) {
+			fprintf(stderr, "bpf_obj_pin(..., %s): %s(%d)\n",
+				pinned_file, strerror(errno), errno);
+			goto out;
+		}
+	}
+
+out:
+	if (array_fd != -1)
+		close(array_fd);
+	if (cg2_fd != -1)
+		close(cg2_fd);
+	return ret;
+}
diff --git a/samples/bpf/test_cgrp2_tc.sh b/samples/bpf/test_cgrp2_tc.sh
new file mode 100755
index 000000000000..0b119eeaf85c
--- /dev/null
+++ b/samples/bpf/test_cgrp2_tc.sh
@@ -0,0 +1,184 @@
+#!/bin/bash
+
+MY_DIR=$(dirname $0)
+# Details on the bpf prog
+BPF_CGRP2_ARRAY_NAME='test_cgrp2_array_pin'
+BPF_PROG="$MY_DIR/test_cgrp2_tc_kern.o"
+BPF_SECTION='filter'
+
+[ -z "$TC" ] && TC='tc'
+[ -z "$IP" ] && IP='ip'
+
+# Names of the veth interface, net namespace...etc.
+HOST_IFC='ve'
+NS_IFC='vens'
+NS='ns'
+
+find_mnt() {
+    cat /proc/mounts | \
+	awk '{ if ($3 == "'$1'" && mnt == "") { mnt = $2 }} END { print mnt }'
+}
+
+# Init cgroup2 vars
+init_cgrp2_vars() {
+    CGRP2_ROOT=$(find_mnt cgroup2)
+    if [ -z "$CGRP2_ROOT" ]
+    then
+	CGRP2_ROOT='/mnt/cgroup2'
+	MOUNT_CGRP2="yes"
+    fi
+    CGRP2_TC="$CGRP2_ROOT/tc"
+    CGRP2_TC_LEAF="$CGRP2_TC/leaf"
+}
+
+# Init bpf fs vars
+init_bpf_fs_vars() {
+    local bpf_fs_root=$(find_mnt bpf)
+    [ -n "$bpf_fs_root" ] || return -1
+    BPF_FS_TC_SHARE="$bpf_fs_root/tc/globals"
+}
+
+setup_cgrp2() {
+    case $1 in
+	start)
+	    if [ "$MOUNT_CGRP2" == 'yes' ]
+	    then
+		[ -d $CGRP2_ROOT ] || mkdir -p $CGRP2_ROOT
+		mount -t cgroup2 none $CGRP2_ROOT || return $?
+	    fi
+	    mkdir -p $CGRP2_TC_LEAF
+	    ;;
+	*)
+	    rmdir $CGRP2_TC_LEAF && rmdir $CGRP2_TC
+	    [ "$MOUNT_CGRP2" == 'yes' ] && umount $CGRP2_ROOT
+	    ;;
+    esac
+}
+
+setup_bpf_cgrp2_array() {
+    local bpf_cgrp2_array="$BPF_FS_TC_SHARE/$BPF_CGRP2_ARRAY_NAME"
+    case $1 in
+	start)
+	    $MY_DIR/test_cgrp2_array_pin -U $bpf_cgrp2_array -v $CGRP2_TC
+	    ;;
+	*)
+	    [ -d "$BPF_FS_TC_SHARE" ] && rm -f $bpf_cgrp2_array
+	    ;;
+    esac
+}
+
+setup_net() {
+    case $1 in
+	start)
+	    $IP link add $HOST_IFC type veth peer name $NS_IFC || return $?
+	    $IP link set dev $HOST_IFC up || return $?
+	    sysctl -q net.ipv6.conf.$HOST_IFC.accept_dad=0
+
+	    $IP netns add ns || return $?
+	    $IP link set dev $NS_IFC netns ns || return $?
+	    $IP -n $NS link set dev $NS_IFC up || return $?
+	    $IP netns exec $NS sysctl -q net.ipv6.conf.$NS_IFC.accept_dad=0
+	    $TC qdisc add dev $HOST_IFC clsact || return $?
+	    $TC filter add dev $HOST_IFC egress bpf da obj $BPF_PROG sec $BPF_SECTION || return $?
+	    ;;
+	*)
+	    $IP netns del $NS
+	    $IP link del $HOST_IFC
+	    ;;
+    esac
+}
+
+run_in_cgrp() {
+    # Fork another bash and move it under the specified cgroup.
+    # It makes the cgroup cleanup easier at the end of the test.
+    cmd='echo $$ > '
+    cmd="$cmd $1/cgroup.procs; exec $2"
+    bash -c "$cmd"
+}
+
+do_test() {
+    run_in_cgrp $CGRP2_TC_LEAF "ping -6 -c3 ff02::1%$HOST_IFC >& /dev/null"
+    local dropped=$($TC -s qdisc show dev $HOST_IFC | tail -3 | \
+			   awk '/drop/{print substr($7, 0, index($7, ",")-1)}')
+    if [[ $dropped -eq 0 ]]
+    then
+	echo "FAIL"
+	return 1
+    else
+	echo "Successfully filtered $dropped packets"
+	return 0
+    fi
+}
+
+do_exit() {
+    if [ "$DEBUG" == "yes" ] && [ "$MODE" != 'cleanuponly' ]
+    then
+	echo "------ DEBUG ------"
+	echo "mount: "; mount | egrep '(cgroup2|bpf)'; echo
+	echo "$CGRP2_TC_LEAF: "; ls -l $CGRP2_TC_LEAF; echo
+	if [ -d "$BPF_FS_TC_SHARE" ]
+	then
+	    echo "$BPF_FS_TC_SHARE: "; ls -l $BPF_FS_TC_SHARE; echo
+	fi
+	echo "Host net:"
+	$IP netns
+	$IP link show dev $HOST_IFC
+	$IP -6 a show dev $HOST_IFC
+	$TC -s qdisc show dev $HOST_IFC
+	echo
+	echo "$NS net:"
+	$IP -n $NS link show dev $NS_IFC
+	$IP -n $NS -6 link show dev $NS_IFC
+	echo "------ DEBUG ------"
+	echo
+    fi
+
+    if [ "$MODE" != 'nocleanup' ]
+    then
+	setup_net stop
+	setup_bpf_cgrp2_array stop
+	setup_cgrp2 stop
+    fi
+}
+
+init_cgrp2_vars
+init_bpf_fs_vars
+
+while [[ $# -ge 1 ]]
+do
+    a="$1"
+    case $a in
+	debug)
+	    DEBUG='yes'
+	    shift 1
+	    ;;
+	cleanup-only)
+	    MODE='cleanuponly'
+	    shift 1
+	    ;;
+	no-cleanup)
+	    MODE='nocleanup'
+	    shift 1
+	    ;;
+	*)
+	    echo "test_cgrp2_tc [debug] [cleanup-only | no-cleanup]"
+	    echo "  debug: Print cgrp and network setup details at the end of the test"
+	    echo "  cleanup-only: Try to cleanup things from last test.  No test will be run"
+	    echo "  no-cleanup: Run the test but don't do cleanup at the end"
+	    echo "[Note: If no arg is given, it will run the test and do cleanup at the end]"
+	    echo
+	    exit -1
+	    ;;
+    esac
+done
+
+trap do_exit 0
+
+[ "$MODE" == 'cleanuponly' ] && exit
+
+setup_cgrp2 start || exit $?
+setup_net start || exit $?
+init_bpf_fs_vars || exit $?
+setup_bpf_cgrp2_array start || exit $?
+do_test
+echo
diff --git a/samples/bpf/test_cgrp2_tc_kern.c b/samples/bpf/test_cgrp2_tc_kern.c
new file mode 100644
index 000000000000..2732c37c8d5b
--- /dev/null
+++ b/samples/bpf/test_cgrp2_tc_kern.c
@@ -0,0 +1,69 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/in6.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/pkt_cls.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+/* copy of 'struct ethhdr' without __packed */
+struct eth_hdr {
+	unsigned char   h_dest[ETH_ALEN];
+	unsigned char   h_source[ETH_ALEN];
+	unsigned short  h_proto;
+};
+
+#define PIN_GLOBAL_NS		2
+struct bpf_elf_map {
+	__u32 type;
+	__u32 size_key;
+	__u32 size_value;
+	__u32 max_elem;
+	__u32 flags;
+	__u32 id;
+	__u32 pinning;
+};
+
+struct bpf_elf_map SEC("maps") test_cgrp2_array_pin = {
+	.type		= BPF_MAP_TYPE_CGROUP_ARRAY,
+	.size_key	= sizeof(uint32_t),
+	.size_value	= sizeof(uint32_t),
+	.pinning	= PIN_GLOBAL_NS,
+	.max_elem	= 1,
+};
+
+SEC("filter")
+int handle_egress(struct __sk_buff *skb)
+{
+	void *data = (void *)(long)skb->data;
+	struct eth_hdr *eth = data;
+	struct ipv6hdr *ip6h = data + sizeof(*eth);
+	void *data_end = (void *)(long)skb->data_end;
+	char dont_care_msg[] = "dont care %04x %d\n";
+	char pass_msg[] = "pass\n";
+	char reject_msg[] = "reject\n";
+
+	/* single length check */
+	if (data + sizeof(*eth) + sizeof(*ip6h) > data_end)
+		return TC_ACT_OK;
+
+	if (eth->h_proto != htons(ETH_P_IPV6) ||
+	    ip6h->nexthdr != IPPROTO_ICMPV6) {
+		bpf_trace_printk(dont_care_msg, sizeof(dont_care_msg),
+				 eth->h_proto, ip6h->nexthdr);
+		return TC_ACT_OK;
+	} else if (bpf_skb_in_cgroup(skb, &test_cgrp2_array_pin, 0) != 1) {
+		bpf_trace_printk(pass_msg, sizeof(pass_msg));
+		return TC_ACT_OK;
+	} else {
+		bpf_trace_printk(reject_msg, sizeof(reject_msg));
+		return TC_ACT_SHOT;
+	}
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/pktgen/pktgen_bench_xmit_mode_queue_xmit.sh b/samples/pktgen/pktgen_bench_xmit_mode_queue_xmit.sh
new file mode 100755
index 000000000000..4e4e92b2515e
--- /dev/null
+++ b/samples/pktgen/pktgen_bench_xmit_mode_queue_xmit.sh
@@ -0,0 +1,66 @@
+#!/bin/bash
+#
+# Benchmark script:
+#  - developed for benchmarking egress qdisc path, derived (more
+#    like cut'n'pasted) from ingress benchmark script.
+#
+# Script for injecting packets into egress qdisc path of the stack
+# with pktgen "xmit_mode queue_xmit".
+#
+basedir=`dirname $0`
+source ${basedir}/functions.sh
+root_check_run_with_sudo "$@"
+
+# Parameter parsing via include
+source ${basedir}/parameters.sh
+[ -z "$DEST_IP" ] && DEST_IP="198.18.0.42"
+[ -z "$DST_MAC" ] && DST_MAC="90:e2:ba:ff:ff:ff"
+
+# Burst greater than 1 are invalid for queue_xmit mode
+if [[ -n "$BURST" ]]; then
+    err 1 "Bursting not supported for this mode"
+fi
+
+# Base Config
+DELAY="0"        # Zero means max speed
+COUNT="10000000" # Zero means indefinitely
+
+# General cleanup everything since last run
+pg_ctrl "reset"
+
+# Threads are specified with parameter -t value in $THREADS
+for ((thread = 0; thread < $THREADS; thread++)); do
+    # The device name is extended with @name, using thread number to
+    # make then unique, but any name will do.
+    dev=${DEV}@${thread}
+
+    # Add remove all other devices and add_device $dev to thread
+    pg_thread $thread "rem_device_all"
+    pg_thread $thread "add_device" $dev
+
+    # Base config of dev
+    pg_set $dev "flag QUEUE_MAP_CPU"
+    pg_set $dev "count $COUNT"
+    pg_set $dev "pkt_size $PKT_SIZE"
+    pg_set $dev "delay $DELAY"
+    pg_set $dev "flag NO_TIMESTAMP"
+
+    # Destination
+    pg_set $dev "dst_mac $DST_MAC"
+    pg_set $dev "dst $DEST_IP"
+
+    # Inject packet into TX qdisc egress path of stack
+    pg_set $dev "xmit_mode queue_xmit"
+done
+
+# start_run
+echo "Running... ctrl^C to stop" >&2
+pg_ctrl "start"
+echo "Done" >&2
+
+# Print results
+for ((thread = 0; thread < $THREADS; thread++)); do
+    dev=${DEV}@${thread}
+    echo "Device: $dev"
+    cat /proc/net/pktgen/$dev | grep -A2 "Result:"
+done
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 6750595bd7b8..4904ced676d4 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2454,6 +2454,7 @@ sub process {
 
 # Check for git id commit length and improperly formed commit descriptions
 		if ($in_commit_log && !$commit_log_possible_stack_dump &&
+		    $line !~ /^\s*(?:Link|Patchwork|http|BugLink):/i &&
 		    ($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i ||
 		     ($line =~ /\b[0-9a-f]{12,40}\b/i &&
 		      $line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i &&
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index a9155077feef..fec75786f75b 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -384,7 +384,7 @@ static void do_of_entry_multi(void *symval, struct module *mod)
 	len = sprintf(alias, "of:N%sT%s", (*name)[0] ? *name : "*",
 		      (*type)[0] ? *type : "*");
 
-	if (compatible[0])
+	if ((*compatible)[0])
 		sprintf(&alias[len], "%sC%s", (*type)[0] ? "*" : "",
 			*compatible);
 
diff --git a/security/keys/compat.c b/security/keys/compat.c
index c8783b3b628c..36c80bf5b89c 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -134,7 +134,7 @@ COMPAT_SYSCALL_DEFINE5(keyctl, u32, option,
 
 	case KEYCTL_DH_COMPUTE:
 		return keyctl_dh_compute(compat_ptr(arg2), compat_ptr(arg3),
-					 arg4);
+					 arg4, compat_ptr(arg5));
 
 	default:
 		return -EOPNOTSUPP;
diff --git a/security/keys/dh.c b/security/keys/dh.c
index 880505a4b9f1..531ed2ec132f 100644
--- a/security/keys/dh.c
+++ b/security/keys/dh.c
@@ -78,7 +78,8 @@ error:
 }
 
 long keyctl_dh_compute(struct keyctl_dh_params __user *params,
-		       char __user *buffer, size_t buflen)
+		       char __user *buffer, size_t buflen,
+		       void __user *reserved)
 {
 	long ret;
 	MPI base, private, prime, result;
@@ -97,6 +98,11 @@ long keyctl_dh_compute(struct keyctl_dh_params __user *params,
 		goto out;
 	}
 
+	if (reserved) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	keylen = mpi_from_key(pcopy.prime, buflen, &prime);
 	if (keylen < 0 || !prime) {
 		/* buflen == 0 may be used to query the required buffer size,
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 8ec7a528365d..a705a7d92ad7 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -260,10 +260,11 @@ static inline long keyctl_get_persistent(uid_t uid, key_serial_t destring)
 
 #ifdef CONFIG_KEY_DH_OPERATIONS
 extern long keyctl_dh_compute(struct keyctl_dh_params __user *, char __user *,
-			      size_t);
+			      size_t, void __user *);
 #else
 static inline long keyctl_dh_compute(struct keyctl_dh_params __user *params,
-				     char __user *buffer, size_t buflen)
+				     char __user *buffer, size_t buflen,
+				     void __user *reserved)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/security/keys/key.c b/security/keys/key.c
index bd5a272f28a6..346fbf201c22 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -597,7 +597,7 @@ int key_reject_and_link(struct key *key,
 
 	mutex_unlock(&key_construction_mutex);
 
-	if (keyring)
+	if (keyring && link_ret == 0)
 		__key_link_end(keyring, &key->index_key, edit);
 
 	/* wake up anyone waiting for a key to be constructed */
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 3b135a0af344..d580ad06b792 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1688,8 +1688,8 @@ SYSCALL_DEFINE5(keyctl, int, option, unsigned long, arg2, unsigned long, arg3,
 
 	case KEYCTL_DH_COMPUTE:
 		return keyctl_dh_compute((struct keyctl_dh_params __user *) arg2,
-					 (char __user *) arg3,
-					 (size_t) arg4);
+					 (char __user *) arg3, (size_t) arg4,
+					 (void __user *) arg5);
 
 	default:
 		return -EOPNOTSUPP;
diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index c0f8f613f1f1..172dacd925f5 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -420,6 +420,7 @@ static int dummy_hrtimer_stop(struct snd_pcm_substream *substream)
 
 static inline void dummy_hrtimer_sync(struct dummy_hrtimer_pcm *dpcm)
 {
+	hrtimer_cancel(&dpcm->timer);
 	tasklet_kill(&dpcm->tasklet);
 }
 
diff --git a/sound/hda/hdac_regmap.c b/sound/hda/hdac_regmap.c
index 87041ddd29cb..47a358fab132 100644
--- a/sound/hda/hdac_regmap.c
+++ b/sound/hda/hdac_regmap.c
@@ -444,7 +444,7 @@ int snd_hdac_regmap_write_raw(struct hdac_device *codec, unsigned int reg,
 	err = reg_raw_write(codec, reg, val);
 	if (err == -EAGAIN) {
 		err = snd_hdac_power_up_pm(codec);
-		if (!err)
+		if (err >= 0)
 			err = reg_raw_write(codec, reg, val);
 		snd_hdac_power_down_pm(codec);
 	}
@@ -470,7 +470,7 @@ static int __snd_hdac_regmap_read_raw(struct hdac_device *codec,
 	err = reg_raw_read(codec, reg, val, uncached);
 	if (err == -EAGAIN) {
 		err = snd_hdac_power_up_pm(codec);
-		if (!err)
+		if (err >= 0)
 			err = reg_raw_read(codec, reg, val, uncached);
 		snd_hdac_power_down_pm(codec);
 	}
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 9a0d1445ca5c..94089fc71884 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -365,8 +365,11 @@ enum {
 
 #define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170)
 #define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70)
+#define IS_KBL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa171)
+#define IS_KBL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d71)
 #define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
-#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci))
+#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) || \
+			IS_KBL(pci) || IS_KBL_LP(pci)
 
 static char *driver_short_names[] = {
 	[AZX_DRIVER_ICH] = "HDA Intel",
@@ -2181,6 +2184,12 @@ static const struct pci_device_id azx_ids[] = {
 	/* Sunrise Point-LP */
 	{ PCI_DEVICE(0x8086, 0x9d70),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
+	/* Kabylake */
+	{ PCI_DEVICE(0x8086, 0xa171),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
+	/* Kabylake-LP */
+	{ PCI_DEVICE(0x8086, 0x9d71),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
 	/* Broxton-P(Apollolake) */
 	{ PCI_DEVICE(0x8086, 0x5a98),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_BROXTON },
diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c
index 17fd81736d3d..0621920f7617 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -115,20 +115,20 @@ static int substream_free_pages(struct azx *chip,
 /*
  * Register access ops. Tegra HDA register access is DWORD only.
  */
-static void hda_tegra_writel(u32 value, u32 *addr)
+static void hda_tegra_writel(u32 value, u32 __iomem *addr)
 {
 	writel(value, addr);
 }
 
-static u32 hda_tegra_readl(u32 *addr)
+static u32 hda_tegra_readl(u32 __iomem *addr)
 {
 	return readl(addr);
 }
 
-static void hda_tegra_writew(u16 value, u16 *addr)
+static void hda_tegra_writew(u16 value, u16 __iomem  *addr)
 {
 	unsigned int shift = ((unsigned long)(addr) & 0x3) << 3;
-	void *dword_addr = (void *)((unsigned long)(addr) & ~0x3);
+	void __iomem *dword_addr = (void __iomem *)((unsigned long)(addr) & ~0x3);
 	u32 v;
 
 	v = readl(dword_addr);
@@ -137,20 +137,20 @@ static void hda_tegra_writew(u16 value, u16 *addr)
 	writel(v, dword_addr);
 }
 
-static u16 hda_tegra_readw(u16 *addr)
+static u16 hda_tegra_readw(u16 __iomem *addr)
 {
 	unsigned int shift = ((unsigned long)(addr) & 0x3) << 3;
-	void *dword_addr = (void *)((unsigned long)(addr) & ~0x3);
+	void __iomem *dword_addr = (void __iomem *)((unsigned long)(addr) & ~0x3);
 	u32 v;
 
 	v = readl(dword_addr);
 	return (v >> shift) & 0xffff;
 }
 
-static void hda_tegra_writeb(u8 value, u8 *addr)
+static void hda_tegra_writeb(u8 value, u8 __iomem *addr)
 {
 	unsigned int shift = ((unsigned long)(addr) & 0x3) << 3;
-	void *dword_addr = (void *)((unsigned long)(addr) & ~0x3);
+	void __iomem *dword_addr = (void __iomem *)((unsigned long)(addr) & ~0x3);
 	u32 v;
 
 	v = readl(dword_addr);
@@ -159,10 +159,10 @@ static void hda_tegra_writeb(u8 value, u8 *addr)
 	writel(v, dword_addr);
 }
 
-static u8 hda_tegra_readb(u8 *addr)
+static u8 hda_tegra_readb(u8 __iomem *addr)
 {
 	unsigned int shift = ((unsigned long)(addr) & 0x3) << 3;
-	void *dword_addr = (void *)((unsigned long)(addr) & ~0x3);
+	void __iomem *dword_addr = (void __iomem *)((unsigned long)(addr) & ~0x3);
 	u32 v;
 
 	v = readl(dword_addr);
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index d53c25e7a1c1..900bfbc3368c 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -346,6 +346,9 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0234:
 	case 0x10ec0274:
 	case 0x10ec0294:
+	case 0x10ec0700:
+	case 0x10ec0701:
+	case 0x10ec0703:
 		alc_update_coef_idx(codec, 0x10, 1<<15, 0);
 		break;
 	case 0x10ec0662:
@@ -2655,6 +2658,7 @@ enum {
 	ALC269_TYPE_ALC256,
 	ALC269_TYPE_ALC225,
 	ALC269_TYPE_ALC294,
+	ALC269_TYPE_ALC700,
 };
 
 /*
@@ -2686,6 +2690,7 @@ static int alc269_parse_auto_config(struct hda_codec *codec)
 	case ALC269_TYPE_ALC256:
 	case ALC269_TYPE_ALC225:
 	case ALC269_TYPE_ALC294:
+	case ALC269_TYPE_ALC700:
 		ssids = alc269_ssids;
 		break;
 	default:
@@ -3618,13 +3623,20 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 static void alc_headset_mode_unplugged(struct hda_codec *codec)
 {
 	static struct coef_fw coef0255[] = {
-		WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */
 		WRITE_COEF(0x45, 0xd089), /* UAJ function set to menual mode */
 		UPDATE_COEFEX(0x57, 0x05, 1<<14, 0), /* Direct Drive HP Amp control(Set to verb control)*/
 		WRITE_COEF(0x06, 0x6104), /* Set MIC2 Vref gate with HP */
 		WRITE_COEFEX(0x57, 0x03, 0x8aa6), /* Direct Drive HP Amp control */
 		{}
 	};
+	static struct coef_fw coef0255_1[] = {
+		WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */
+		{}
+	};
+	static struct coef_fw coef0256[] = {
+		WRITE_COEF(0x1b, 0x0c4b), /* LDO and MISC control */
+		{}
+	};
 	static struct coef_fw coef0233[] = {
 		WRITE_COEF(0x1b, 0x0c0b),
 		WRITE_COEF(0x45, 0xc429),
@@ -3677,7 +3689,11 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 
 	switch (codec->core.vendor_id) {
 	case 0x10ec0255:
+		alc_process_coef_fw(codec, coef0255_1);
+		alc_process_coef_fw(codec, coef0255);
+		break;
 	case 0x10ec0256:
+		alc_process_coef_fw(codec, coef0256);
 		alc_process_coef_fw(codec, coef0255);
 		break;
 	case 0x10ec0233:
@@ -3896,6 +3912,12 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
 		{}
 	};
+	static struct coef_fw coef0256[] = {
+		WRITE_COEF(0x45, 0xd489), /* Set to CTIA type */
+		WRITE_COEF(0x1b, 0x0c6b),
+		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
+		{}
+	};
 	static struct coef_fw coef0233[] = {
 		WRITE_COEF(0x45, 0xd429),
 		WRITE_COEF(0x1b, 0x0c2b),
@@ -3936,9 +3958,11 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 
 	switch (codec->core.vendor_id) {
 	case 0x10ec0255:
-	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
 		break;
+	case 0x10ec0256:
+		alc_process_coef_fw(codec, coef0256);
+		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
 		alc_process_coef_fw(codec, coef0233);
@@ -3978,6 +4002,12 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
 		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
 		{}
 	};
+	static struct coef_fw coef0256[] = {
+		WRITE_COEF(0x45, 0xe489), /* Set to OMTP Type */
+		WRITE_COEF(0x1b, 0x0c6b),
+		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
+		{}
+	};
 	static struct coef_fw coef0233[] = {
 		WRITE_COEF(0x45, 0xe429),
 		WRITE_COEF(0x1b, 0x0c2b),
@@ -4018,9 +4048,11 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
 
 	switch (codec->core.vendor_id) {
 	case 0x10ec0255:
-	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
 		break;
+	case 0x10ec0256:
+		alc_process_coef_fw(codec, coef0256);
+		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
 		alc_process_coef_fw(codec, coef0233);
@@ -4266,7 +4298,7 @@ static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec,
 static void alc255_set_default_jack_type(struct hda_codec *codec)
 {
 	/* Set to iphone type */
-	static struct coef_fw fw[] = {
+	static struct coef_fw alc255fw[] = {
 		WRITE_COEF(0x1b, 0x880b),
 		WRITE_COEF(0x45, 0xd089),
 		WRITE_COEF(0x1b, 0x080b),
@@ -4274,7 +4306,22 @@ static void alc255_set_default_jack_type(struct hda_codec *codec)
 		WRITE_COEF(0x1b, 0x0c0b),
 		{}
 	};
-	alc_process_coef_fw(codec, fw);
+	static struct coef_fw alc256fw[] = {
+		WRITE_COEF(0x1b, 0x884b),
+		WRITE_COEF(0x45, 0xd089),
+		WRITE_COEF(0x1b, 0x084b),
+		WRITE_COEF(0x46, 0x0004),
+		WRITE_COEF(0x1b, 0x0c4b),
+		{}
+	};
+	switch (codec->core.vendor_id) {
+	case 0x10ec0255:
+		alc_process_coef_fw(codec, alc255fw);
+		break;
+	case 0x10ec0256:
+		alc_process_coef_fw(codec, alc256fw);
+		break;
+	}
 	msleep(30);
 }
 
@@ -5587,6 +5634,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x2218, "Thinkpad X1 Carbon 2nd", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK),
+	SND_PCI_QUIRK(0x17aa, 0x2231, "Thinkpad T560", ALC292_FIXUP_TPT460),
 	SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460),
 	SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
@@ -5602,6 +5650,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x504a, "ThinkPad X260", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x504b, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE),
+	SND_PCI_QUIRK(0x17aa, 0x5050, "Thinkpad T560p", ALC292_FIXUP_TPT460),
+	SND_PCI_QUIRK(0x17aa, 0x5053, "Thinkpad T460", ALC292_FIXUP_TPT460),
 	SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
 	SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
@@ -5775,11 +5825,19 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60180},
 		{0x14, 0x90170130},
 		{0x21, 0x02211040}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell Inspiron 5565", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60180},
+		{0x14, 0x90170120},
+		{0x21, 0x02211030}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60160},
 		{0x14, 0x90170120},
 		{0x21, 0x02211030}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60170},
+		{0x14, 0x90170120},
+		{0x21, 0x02211030}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC256_STANDARD_PINS),
 	SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4,
 		{0x12, 0x90a60130},
@@ -6053,6 +6111,14 @@ static int patch_alc269(struct hda_codec *codec)
 	case 0x10ec0294:
 		spec->codec_variant = ALC269_TYPE_ALC294;
 		break;
+	case 0x10ec0700:
+	case 0x10ec0701:
+	case 0x10ec0703:
+		spec->codec_variant = ALC269_TYPE_ALC700;
+		spec->gen.mixer_nid = 0; /* ALC700 does not have any loopback mixer path */
+		alc_update_coef_idx(codec, 0x4a, 0, 1 << 15); /* Combo jack auto trigger control */
+		break;
+
 	}
 
 	if (snd_hda_codec_read(codec, 0x51, 0, AC_VERB_PARAMETERS, 0) == 0x10ec5505) {
@@ -7008,6 +7074,9 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0670, "ALC670", patch_alc662),
 	HDA_CODEC_ENTRY(0x10ec0671, "ALC671", patch_alc662),
 	HDA_CODEC_ENTRY(0x10ec0680, "ALC680", patch_alc680),
+	HDA_CODEC_ENTRY(0x10ec0700, "ALC700", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0701, "ALC701", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0703, "ALC703", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0867, "ALC891", patch_alc882),
 	HDA_CODEC_ENTRY(0x10ec0880, "ALC880", patch_alc880),
 	HDA_CODEC_ENTRY(0x10ec0882, "ALC882", patch_alc882),
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index bbf69d248ec5..9f53020c3269 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -204,6 +204,44 @@ static unsigned long long adjust_signedness(unsigned long long value_int, int si
 	return (value_int & value_mask) | ~value_mask;
 }
 
+static int string_set_value(struct bt_ctf_field *field, const char *string)
+{
+	char *buffer = NULL;
+	size_t len = strlen(string), i, p;
+	int err;
+
+	for (i = p = 0; i < len; i++, p++) {
+		if (isprint(string[i])) {
+			if (!buffer)
+				continue;
+			buffer[p] = string[i];
+		} else {
+			char numstr[5];
+
+			snprintf(numstr, sizeof(numstr), "\\x%02x",
+				 (unsigned int)(string[i]) & 0xff);
+
+			if (!buffer) {
+				buffer = zalloc(i + (len - i) * 4 + 2);
+				if (!buffer) {
+					pr_err("failed to set unprintable string '%s'\n", string);
+					return bt_ctf_field_string_set_value(field, "UNPRINTABLE-STRING");
+				}
+				if (i > 0)
+					strncpy(buffer, string, i);
+			}
+			strncat(buffer + p, numstr, 4);
+			p += 3;
+		}
+	}
+
+	if (!buffer)
+		return bt_ctf_field_string_set_value(field, string);
+	err = bt_ctf_field_string_set_value(field, buffer);
+	free(buffer);
+	return err;
+}
+
 static int add_tracepoint_field_value(struct ctf_writer *cw,
 				      struct bt_ctf_event_class *event_class,
 				      struct bt_ctf_event *event,
@@ -270,8 +308,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		}
 
 		if (flags & FIELD_IS_STRING)
-			ret = bt_ctf_field_string_set_value(field,
-					data + offset + i * len);
+			ret = string_set_value(field, data + offset + i * len);
 		else {
 			unsigned long long value_int;
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index f6fcc6832949..9b141f12329e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -673,6 +673,8 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	int err;
 	union perf_event *event;
 
+	if (symbol_conf.kptr_restrict)
+		return -1;
 	if (map == NULL)
 		return -1;
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 20f9cb32b703..54c4ff2b1cee 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1933,17 +1933,17 @@ int setup_intlist(struct intlist **list, const char *list_str,
 static bool symbol__read_kptr_restrict(void)
 {
 	bool value = false;
+	FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
 
-	if (geteuid() != 0) {
-		FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
-		if (fp != NULL) {
-			char line[8];
+	if (fp != NULL) {
+		char line[8];
 
-			if (fgets(line, sizeof(line), fp) != NULL)
-				value = atoi(line) != 0;
+		if (fgets(line, sizeof(line), fp) != NULL)
+			value = (geteuid() != 0) ?
+					(atoi(line) != 0) :
+					(atoi(line) == 2);
 
-			fclose(fp);
-		}
+		fclose(fp);
 	}
 
 	return value;
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
index c2b61c4fda11..0bf5085281f3 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
@@ -23,15 +23,14 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
-FEATURE=`grep hist events/sched/sched_process_fork/trigger`
-if [ -z "$FEATURE" ]; then
+if [ ! -f events/sched/sched_process_fork/hist ]; then
     echo "hist trigger is not supported"
     exit_unsupported
 fi
 
+reset_tracer
+do_reset
+
 echo "Test histogram with execname modifier"
 
 echo 'hist:keys=common_pid.execname' > events/sched/sched_process_fork/trigger
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
index b2902d42a537..a00184cd9c95 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
@@ -23,15 +23,14 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
-FEATURE=`grep hist events/sched/sched_process_fork/trigger`
-if [ -z "$FEATURE" ]; then
+if [ ! -f events/sched/sched_process_fork/hist ]; then
     echo "hist trigger is not supported"
     exit_unsupported
 fi
 
+reset_tracer
+do_reset
+
 echo "Test histogram basic tigger"
 
 echo 'hist:keys=parent_pid:vals=child_pid' > events/sched/sched_process_fork/trigger
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
index 03c4a46561fc..3478b00ead57 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
@@ -23,15 +23,14 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
-FEATURE=`grep hist events/sched/sched_process_fork/trigger`
-if [ -z "$FEATURE" ]; then
+if [ ! -f events/sched/sched_process_fork/hist ]; then
     echo "hist trigger is not supported"
     exit_unsupported
 fi
 
+reset_tracer
+do_reset
+
 reset_trigger
 
 echo "Test histogram multiple tiggers"
diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c
index 96ba386b1b7b..4a8217448f20 100644
--- a/tools/testing/selftests/net/reuseport_bpf.c
+++ b/tools/testing/selftests/net/reuseport_bpf.c
@@ -111,9 +111,9 @@ static void attach_ebpf(int fd, uint16_t mod)
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
 	attr.insn_cnt = ARRAY_SIZE(prog);
-	attr.insns = (uint64_t)prog;
-	attr.license = (uint64_t)bpf_license;
-	attr.log_buf = (uint64_t)bpf_log_buf;
+	attr.insns = (unsigned long) &prog;
+	attr.license = (unsigned long) &bpf_license;
+	attr.log_buf = (unsigned long) &bpf_log_buf;
 	attr.log_size = sizeof(bpf_log_buf);
 	attr.log_level = 1;
 	attr.kern_version = 0;
@@ -351,8 +351,8 @@ static void test_filter_no_reuseport(const struct test_params p)
 	memset(&eprog, 0, sizeof(eprog));
 	eprog.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
 	eprog.insn_cnt = ARRAY_SIZE(ecode);
-	eprog.insns = (uint64_t)ecode;
-	eprog.license = (uint64_t)bpf_license;
+	eprog.insns = (unsigned long) &ecode;
+	eprog.license = (unsigned long) &bpf_license;
 	eprog.kern_version = 0;
 
 	memset(&cprog, 0, sizeof(cprog));
diff --git a/tools/testing/selftests/vm/compaction_test.c b/tools/testing/selftests/vm/compaction_test.c
index 932ff577ffc0..00c4f65d12da 100644
--- a/tools/testing/selftests/vm/compaction_test.c
+++ b/tools/testing/selftests/vm/compaction_test.c
@@ -136,7 +136,7 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
 	printf("No of huge pages allocated = %d\n",
 	       (atoi(nr_hugepages)));
 
-	if (write(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages))
+	if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages))
 	    != strlen(initial_nr_hugepages)) {
 		perror("Failed to write to /proc/sys/vm/nr_hugepages\n");
 		goto close_fd;
diff --git a/tools/virtio/ringtest/Makefile b/tools/virtio/ringtest/Makefile
index 6ba745529833..877a8a4721b6 100644
--- a/tools/virtio/ringtest/Makefile
+++ b/tools/virtio/ringtest/Makefile
@@ -1,6 +1,6 @@
 all:
 
-all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder
+all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder ptr_ring noring
 
 CFLAGS += -Wall
 CFLAGS += -pthread -O2 -ggdb
@@ -8,6 +8,7 @@ LDFLAGS += -pthread -O2 -ggdb
 
 main.o: main.c main.h
 ring.o: ring.c main.h
+ptr_ring.o: ptr_ring.c main.h ../../../include/linux/ptr_ring.h
 virtio_ring_0_9.o: virtio_ring_0_9.c main.h
 virtio_ring_poll.o: virtio_ring_poll.c virtio_ring_0_9.c main.h
 virtio_ring_inorder.o: virtio_ring_inorder.c virtio_ring_0_9.c main.h
@@ -15,11 +16,15 @@ ring: ring.o main.o
 virtio_ring_0_9: virtio_ring_0_9.o main.o
 virtio_ring_poll: virtio_ring_poll.o main.o
 virtio_ring_inorder: virtio_ring_inorder.o main.o
+ptr_ring: ptr_ring.o main.o
+noring: noring.o main.o
 clean:
 	-rm main.o
 	-rm ring.o ring
 	-rm virtio_ring_0_9.o virtio_ring_0_9
 	-rm virtio_ring_poll.o virtio_ring_poll
 	-rm virtio_ring_inorder.o virtio_ring_inorder
+	-rm ptr_ring.o ptr_ring
+	-rm noring.o noring
 
 .PHONY: all clean
diff --git a/tools/virtio/ringtest/README b/tools/virtio/ringtest/README
index 34e94c46104f..d83707a336c9 100644
--- a/tools/virtio/ringtest/README
+++ b/tools/virtio/ringtest/README
@@ -1,2 +1,6 @@
 Partial implementation of various ring layouts, useful to tune virtio design.
 Uses shared memory heavily.
+
+Typical use:
+
+# sh run-on-all.sh perf stat -r 10 --log-fd 1 -- ./ring
diff --git a/tools/virtio/ringtest/noring.c b/tools/virtio/ringtest/noring.c
new file mode 100644
index 000000000000..eda2f4824130
--- /dev/null
+++ b/tools/virtio/ringtest/noring.c
@@ -0,0 +1,69 @@
+#define _GNU_SOURCE
+#include "main.h"
+#include <assert.h>
+
+/* stub implementation: useful for measuring overhead */
+void alloc_ring(void)
+{
+}
+
+/* guest side */
+int add_inbuf(unsigned len, void *buf, void *datap)
+{
+	return 0;
+}
+
+/*
+ * skb_array API provides no way for producer to find out whether a given
+ * buffer was consumed.  Our tests merely require that a successful get_buf
+ * implies that add_inbuf succeed in the past, and that add_inbuf will succeed,
+ * fake it accordingly.
+ */
+void *get_buf(unsigned *lenp, void **bufp)
+{
+	return "Buffer";
+}
+
+void poll_used(void)
+{
+}
+
+void disable_call()
+{
+	assert(0);
+}
+
+bool enable_call()
+{
+	assert(0);
+}
+
+void kick_available(void)
+{
+	assert(0);
+}
+
+/* host side */
+void disable_kick()
+{
+	assert(0);
+}
+
+bool enable_kick()
+{
+	assert(0);
+}
+
+void poll_avail(void)
+{
+}
+
+bool use_buf(unsigned *lenp, void **bufp)
+{
+	return true;
+}
+
+void call_used(void)
+{
+	assert(0);
+}
diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c
new file mode 100644
index 000000000000..68e4f9f0da3a
--- /dev/null
+++ b/tools/virtio/ringtest/ptr_ring.c
@@ -0,0 +1,197 @@
+#define _GNU_SOURCE
+#include "main.h"
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <pthread.h>
+#include <malloc.h>
+#include <assert.h>
+#include <errno.h>
+#include <limits.h>
+
+#define SMP_CACHE_BYTES 64
+#define cache_line_size() SMP_CACHE_BYTES
+#define ____cacheline_aligned_in_smp __attribute__ ((aligned (SMP_CACHE_BYTES)))
+#define unlikely(x)    (__builtin_expect(!!(x), 0))
+#define ALIGN(x, a) (((x) + (a) - 1) / (a) * (a))
+typedef pthread_spinlock_t  spinlock_t;
+
+typedef int gfp_t;
+static void *kmalloc(unsigned size, gfp_t gfp)
+{
+	return memalign(64, size);
+}
+
+static void *kzalloc(unsigned size, gfp_t gfp)
+{
+	void *p = memalign(64, size);
+	if (!p)
+		return p;
+	memset(p, 0, size);
+
+	return p;
+}
+
+static void kfree(void *p)
+{
+	if (p)
+		free(p);
+}
+
+static void spin_lock_init(spinlock_t *lock)
+{
+	int r = pthread_spin_init(lock, 0);
+	assert(!r);
+}
+
+static void spin_lock(spinlock_t *lock)
+{
+	int ret = pthread_spin_lock(lock);
+	assert(!ret);
+}
+
+static void spin_unlock(spinlock_t *lock)
+{
+	int ret = pthread_spin_unlock(lock);
+	assert(!ret);
+}
+
+static void spin_lock_bh(spinlock_t *lock)
+{
+	spin_lock(lock);
+}
+
+static void spin_unlock_bh(spinlock_t *lock)
+{
+	spin_unlock(lock);
+}
+
+static void spin_lock_irq(spinlock_t *lock)
+{
+	spin_lock(lock);
+}
+
+static void spin_unlock_irq(spinlock_t *lock)
+{
+	spin_unlock(lock);
+}
+
+static void spin_lock_irqsave(spinlock_t *lock, unsigned long f)
+{
+	spin_lock(lock);
+}
+
+static void spin_unlock_irqrestore(spinlock_t *lock, unsigned long f)
+{
+	spin_unlock(lock);
+}
+
+#include "../../../include/linux/ptr_ring.h"
+
+static unsigned long long headcnt, tailcnt;
+static struct ptr_ring array ____cacheline_aligned_in_smp;
+
+/* implemented by ring */
+void alloc_ring(void)
+{
+	int ret = ptr_ring_init(&array, ring_size, 0);
+	assert(!ret);
+}
+
+/* guest side */
+int add_inbuf(unsigned len, void *buf, void *datap)
+{
+	int ret;
+
+	ret = __ptr_ring_produce(&array, buf);
+	if (ret >= 0) {
+		ret = 0;
+		headcnt++;
+	}
+
+	return ret;
+}
+
+/*
+ * ptr_ring API provides no way for producer to find out whether a given
+ * buffer was consumed.  Our tests merely require that a successful get_buf
+ * implies that add_inbuf succeed in the past, and that add_inbuf will succeed,
+ * fake it accordingly.
+ */
+void *get_buf(unsigned *lenp, void **bufp)
+{
+	void *datap;
+
+	if (tailcnt == headcnt || __ptr_ring_full(&array))
+		datap = NULL;
+	else {
+		datap = "Buffer\n";
+		++tailcnt;
+	}
+
+	return datap;
+}
+
+void poll_used(void)
+{
+	void *b;
+
+	do {
+		if (tailcnt == headcnt || __ptr_ring_full(&array)) {
+			b = NULL;
+			barrier();
+		} else {
+			b = "Buffer\n";
+		}
+	} while (!b);
+}
+
+void disable_call()
+{
+	assert(0);
+}
+
+bool enable_call()
+{
+	assert(0);
+}
+
+void kick_available(void)
+{
+	assert(0);
+}
+
+/* host side */
+void disable_kick()
+{
+	assert(0);
+}
+
+bool enable_kick()
+{
+	assert(0);
+}
+
+void poll_avail(void)
+{
+	void *b;
+
+	do {
+		barrier();
+		b = __ptr_ring_peek(&array);
+	} while (!b);
+}
+
+bool use_buf(unsigned *lenp, void **bufp)
+{
+	void *ptr;
+
+	ptr = __ptr_ring_consume(&array);
+
+	return ptr;
+}
+
+void call_used(void)
+{
+	assert(0);
+}
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 52b0f71ffa8d..2e69ca812b4c 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -3,10 +3,10 @@
 #use last CPU for host. Why not the first?
 #many devices tend to use cpu0 by default so
 #it tends to be busier
-HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
+HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
 
 #run command on all cpus
-for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
+for cpu in $(seq 0 $HOST_AFFINITY)
 do
 	#Don't run guest and host on same CPU
 	#It actually works ok if using signalling
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 1889163f2f05..7cf6e1769903 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -492,7 +492,7 @@ static void slab_stats(struct slabinfo *s)
 			s->deactivate_to_head + s->deactivate_to_tail + s->deactivate_bypass;
 
 	if (total) {
-		printf("\nSlab Deactivation             Ocurrences  %%\n");
+		printf("\nSlab Deactivation             Occurrences %%\n");
 		printf("-------------------------------------------------\n");
 		printf("Slab full                     %7lu  %3lu%%\n",
 			s->deactivate_full, (s->deactivate_full * 100) / total);
diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c
index a3f12b3b277b..3a3a699b7489 100644
--- a/virt/kvm/arm/hyp/vgic-v2-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v2-sr.c
@@ -100,12 +100,11 @@ static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)
 		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
 			continue;
 
-		if (cpu_if->vgic_elrsr & (1UL << i)) {
+		if (cpu_if->vgic_elrsr & (1UL << i))
 			cpu_if->vgic_lr[i] &= ~GICH_LR_STATE;
-			continue;
-		}
+		else
+			cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
 
-		cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
 		writel_relaxed(0, base + GICH_LR0 + (i * 4));
 	}
 }
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index 059595ec3da0..9f6fab74dce7 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -191,10 +191,8 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 	 * other thread sync back the IRQ.
 	 */
 	while (irq->vcpu && /* IRQ may have state in an LR somewhere */
-	       irq->vcpu->cpu != -1) { /* VCPU thread is running */
-		BUG_ON(irq->intid < VGIC_NR_PRIVATE_IRQS);
+	       irq->vcpu->cpu != -1) /* VCPU thread is running */
 		cond_resched_lock(&irq->irq_lock);
-	}
 
 	irq->active = new_active_state;
 	if (new_active_state)
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index 8ad42c217770..e31405ee5515 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -112,11 +112,15 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 			}
 		}
 
-		/* Clear soft pending state when level IRQs have been acked */
-		if (irq->config == VGIC_CONFIG_LEVEL &&
-		    !(val & GICH_LR_PENDING_BIT)) {
-			irq->soft_pending = false;
-			irq->pending = irq->line_level;
+		/*
+		 * Clear soft pending state when level irqs have been acked.
+		 * Always regenerate the pending state.
+		 */
+		if (irq->config == VGIC_CONFIG_LEVEL) {
+			if (!(val & GICH_LR_PENDING_BIT))
+				irq->soft_pending = false;
+
+			irq->pending = irq->line_level || irq->soft_pending;
 		}
 
 		spin_unlock(&irq->irq_lock);
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 336a46115937..346b4ad12b49 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -101,11 +101,15 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 			}
 		}
 
-		/* Clear soft pending state when level irqs have been acked */
-		if (irq->config == VGIC_CONFIG_LEVEL &&
-		    !(val & ICH_LR_PENDING_BIT)) {
-			irq->soft_pending = false;
-			irq->pending = irq->line_level;
+		/*
+		 * Clear soft pending state when level irqs have been acked.
+		 * Always regenerate the pending state.
+		 */
+		if (irq->config == VGIC_CONFIG_LEVEL) {
+			if (!(val & ICH_LR_PENDING_BIT))
+				irq->soft_pending = false;
+
+			irq->pending = irq->line_level || irq->soft_pending;
 		}
 
 		spin_unlock(&irq->irq_lock);
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index fe84e1a95dd5..8db197bb6c7a 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -40,7 +40,7 @@ int kvm_irq_map_gsi(struct kvm *kvm,
 
 	irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
 					lockdep_is_held(&kvm->irq_lock));
-	if (gsi < irq_rt->nr_rt_entries) {
+	if (irq_rt && gsi < irq_rt->nr_rt_entries) {
 		hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
 			entries[n] = *e;
 			++n;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 37af23052470..48bd520fc702 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2935,25 +2935,27 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_SET_GSI_ROUTING: {
 		struct kvm_irq_routing routing;
 		struct kvm_irq_routing __user *urouting;
-		struct kvm_irq_routing_entry *entries;
+		struct kvm_irq_routing_entry *entries = NULL;
 
 		r = -EFAULT;
 		if (copy_from_user(&routing, argp, sizeof(routing)))
 			goto out;
 		r = -EINVAL;
-		if (routing.nr >= KVM_MAX_IRQ_ROUTES)
+		if (routing.nr > KVM_MAX_IRQ_ROUTES)
 			goto out;
 		if (routing.flags)
 			goto out;
-		r = -ENOMEM;
-		entries = vmalloc(routing.nr * sizeof(*entries));
-		if (!entries)
-			goto out;
-		r = -EFAULT;
-		urouting = argp;
-		if (copy_from_user(entries, urouting->entries,
-				   routing.nr * sizeof(*entries)))
-			goto out_free_irq_routing;
+		if (routing.nr) {
+			r = -ENOMEM;
+			entries = vmalloc(routing.nr * sizeof(*entries));
+			if (!entries)
+				goto out;
+			r = -EFAULT;
+			urouting = argp;
+			if (copy_from_user(entries, urouting->entries,
+					   routing.nr * sizeof(*entries)))
+				goto out_free_irq_routing;
+		}
 		r = kvm_set_irq_routing(kvm, entries, routing.nr,
 					routing.flags);
 out_free_irq_routing: