diff options
785 files changed, 13420 insertions, 4619 deletions
diff --git a/Documentation/device-mapper/snapshot.txt b/Documentation/device-mapper/snapshot.txt index 0d5bc46dc167..ad6949bff2e3 100644 --- a/Documentation/device-mapper/snapshot.txt +++ b/Documentation/device-mapper/snapshot.txt @@ -41,9 +41,13 @@ useless and be disabled, returning errors. So it is important to monitor the amount of free space and expand the <COW device> before it fills up. <persistent?> is P (Persistent) or N (Not persistent - will not survive -after reboot). -The difference is that for transient snapshots less metadata must be -saved on disk - they can be kept in memory by the kernel. +after reboot). O (Overflow) can be added as a persistent store option +to allow userspace to advertise its support for seeing "Overflow" in the +snapshot status. So supported store types are "P", "PO" and "N". + +The difference between persistent and transient is with transient +snapshots less metadata must be saved on disk - they can be kept in +memory by the kernel. * snapshot-merge <origin> <COW device> <persistent> <chunksize> diff --git a/Documentation/devicetree/bindings/input/cypress,cyapa.txt b/Documentation/devicetree/bindings/input/cypress,cyapa.txt index 635a3b036630..8d91ba9ff2fd 100644 --- a/Documentation/devicetree/bindings/input/cypress,cyapa.txt +++ b/Documentation/devicetree/bindings/input/cypress,cyapa.txt @@ -25,7 +25,7 @@ Example: /* Cypress Gen3 touchpad */ touchpad@67 { compatible = "cypress,cyapa"; - reg = <0x24>; + reg = <0x67>; interrupt-parent = <&gpio>; interrupts = <2 IRQ_TYPE_EDGE_FALLING>; /* GPIO 2 */ wakeup-source; diff --git a/Documentation/devicetree/bindings/spi/sh-msiof.txt b/Documentation/devicetree/bindings/spi/sh-msiof.txt index 8f771441be60..705075da2f10 100644 --- a/Documentation/devicetree/bindings/spi/sh-msiof.txt +++ b/Documentation/devicetree/bindings/spi/sh-msiof.txt @@ -51,7 +51,7 @@ Optional properties, deprecated for soctype-specific bindings: - renesas,tx-fifo-size : Overrides the default tx fifo size given in words (default is 64) - renesas,rx-fifo-size : Overrides the default rx fifo size given in words - (default is 64, or 256 on R-Car Gen2) + (default is 64) Pinctrl properties might be needed, too. See Documentation/devicetree/bindings/pinctrl/renesas,*. diff --git a/Documentation/devicetree/bindings/usb/renesas_usbhs.txt b/Documentation/devicetree/bindings/usb/renesas_usbhs.txt index 64a4ca6cf96f..7d48f63db44e 100644 --- a/Documentation/devicetree/bindings/usb/renesas_usbhs.txt +++ b/Documentation/devicetree/bindings/usb/renesas_usbhs.txt @@ -5,6 +5,7 @@ Required properties: - "renesas,usbhs-r8a7790" - "renesas,usbhs-r8a7791" - "renesas,usbhs-r8a7794" + - "renesas,usbhs-r8a7795" - reg: Base address and length of the register for the USBHS - interrupts: Interrupt specifier for the USBHS - clocks: A list of phandle + clock specifier pairs diff --git a/Documentation/filesystems/nfs/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt index 2d66ed688125..bb5ab6de5924 100644 --- a/Documentation/filesystems/nfs/nfsroot.txt +++ b/Documentation/filesystems/nfs/nfsroot.txt @@ -157,6 +157,9 @@ ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>: both: use both BOOTP and RARP but not DHCP (old option kept for backwards compatibility) + if dhcp is used, the client identifier can be used by following + format "ip=dhcp,client-id-type,client-id-value" + Default: any <dns0-ip> IP address of first nameserver. diff --git a/Documentation/input/multi-touch-protocol.txt b/Documentation/input/multi-touch-protocol.txt index b85d000faeb4..c51f1146f3bd 100644 --- a/Documentation/input/multi-touch-protocol.txt +++ b/Documentation/input/multi-touch-protocol.txt @@ -361,7 +361,7 @@ For win8 devices with both T and C coordinates, the position mapping is ABS_MT_POSITION_X := T_X ABS_MT_POSITION_Y := T_Y ABS_MT_TOOL_X := C_X - ABS_MT_TOOL_X := C_Y + ABS_MT_TOOL_Y := C_Y Unfortunately, there is not enough information to specify both the touching ellipse and the tool ellipse, so one has to resort to approximations. One diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 99838259e2e6..85752c81c5ec 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -384,6 +384,14 @@ tcp_mem - vector of 3 INTEGERs: min, pressure, max Defaults are calculated at boot time from amount of available memory. +tcp_min_rtt_wlen - INTEGER + The window length of the windowed min filter to track the minimum RTT. + A shorter window lets a flow more quickly pick up new (higher) + minimum RTT when it is moved to a longer path (e.g., due to traffic + engineering). A longer window makes the filter more resistant to RTT + inflations such as transient congestion. The unit is seconds. + Default: 300 + tcp_moderate_rcvbuf - BOOLEAN If set, TCP performs receive buffer auto-tuning, attempting to automatically size the buffer (no greater than tcp_rmem[2]) to @@ -425,6 +433,15 @@ tcp_orphan_retries - INTEGER you should think about lowering this value, such sockets may consume significant resources. Cf. tcp_max_orphans. +tcp_recovery - INTEGER + This value is a bitmap to enable various experimental loss recovery + features. + + RACK: 0x1 enables the RACK loss detection for fast detection of lost + retransmissions and tail drops. + + Default: 0x1 + tcp_reordering - INTEGER Initial reordering level of packets in a TCP stream. TCP stack can then dynamically adjust flow reordering level @@ -884,8 +901,8 @@ icmp_ignore_bogus_error_responses - BOOLEAN icmp_errors_use_inbound_ifaddr - BOOLEAN - If zero, icmp error messages except redirects are sent with the primary - address of the exiting interface. + If zero, icmp error messages are sent with the primary address of + the exiting interface. If non-zero, the message will be sent with the primary address of the interface that received the packet that caused the icmp error. @@ -897,23 +914,8 @@ icmp_errors_use_inbound_ifaddr - BOOLEAN then the primary address of the first non-loopback interface that has one will be used regardless of this setting. - The source address selection of icmp redirect messages is controlled by - icmp_errors_use_inbound_ifaddr. Default: 0 -icmp_redirects_use_orig_daddr - BOOLEAN - - If zero, icmp redirect messages are sent using the address specified for - other icmp errors by icmp_errors_use_inbound_ifaddr. - - If non-zero, the message will be sent with the destination address of - the packet that caused the icmp redirect. - This behaviour is the preferred one on VRRP routers (see RFC 5798 - section 8.1.1). - - Default: 0 - - igmp_max_memberships - INTEGER Change the maximum number of multicast groups we can subscribe to. Default: 20 diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt index 031ef4a63485..d52aa10cfe91 100644 --- a/Documentation/networking/vrf.txt +++ b/Documentation/networking/vrf.txt @@ -90,7 +90,304 @@ or to specify the output device using cmsg and IP_PKTINFO. Limitations ----------- -VRF device currently only works for IPv4. Support for IPv6 is under development. - Index of original ingress interface is not available via cmsg. Will address soon. + +################################################################################ + +Using iproute2 for VRFs +======================= +VRF devices do *not* have to start with 'vrf-'. That is a convention used here +for emphasis of the device type, similar to use of 'br' in bridge names. + +1. Create a VRF + + To instantiate a VRF device and associate it with a table: + $ ip link add dev NAME type vrf table ID + + Remember to add the ip rules as well: + $ ip ru add oif NAME table 10 + $ ip ru add iif NAME table 10 + $ ip -6 ru add oif NAME table 10 + $ ip -6 ru add iif NAME table 10 + + Without the rules route lookups are not directed to the table. + + For example: + $ ip link add dev vrf-blue type vrf table 10 + $ ip ru add pref 200 oif vrf-blue table 10 + $ ip ru add pref 200 iif vrf-blue table 10 + $ ip -6 ru add pref 200 oif vrf-blue table 10 + $ ip -6 ru add pref 200 iif vrf-blue table 10 + + +2. List VRFs + + To list VRFs that have been created: + $ ip [-d] link show type vrf + NOTE: The -d option is needed to show the table id + + For example: + $ ip -d link show type vrf + 11: vrf-mgmt: <NOARP,MASTER,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether 72:b3:ba:91:e2:24 brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 1 addrgenmode eui64 + 12: vrf-red: <NOARP,MASTER,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether b6:6f:6e:f6:da:73 brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 10 addrgenmode eui64 + 13: vrf-blue: <NOARP,MASTER,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether 36:62:e8:7d:bb:8c brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 66 addrgenmode eui64 + 14: vrf-green: <NOARP,MASTER,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether e6:28:b8:63:70:bb brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 81 addrgenmode eui64 + + + Or in brief output: + + $ ip -br link show type vrf + vrf-mgmt UP 72:b3:ba:91:e2:24 <NOARP,MASTER,UP,LOWER_UP> + vrf-red UP b6:6f:6e:f6:da:73 <NOARP,MASTER,UP,LOWER_UP> + vrf-blue UP 36:62:e8:7d:bb:8c <NOARP,MASTER,UP,LOWER_UP> + vrf-green UP e6:28:b8:63:70:bb <NOARP,MASTER,UP,LOWER_UP> + + +3. Assign a Network Interface to a VRF + + Network interfaces are assigned to a VRF by enslaving the netdevice to a + VRF device: + $ ip link set dev NAME master VRF-NAME + + On enslavement connected and local routes are automatically moved to the + table associated with the VRF device. + + For example: + $ ip link set dev eth0 master vrf-mgmt + + +4. Show Devices Assigned to a VRF + + To show devices that have been assigned to a specific VRF add the master + option to the ip command: + $ ip link show master VRF-NAME + + For example: + $ ip link show master vrf-red + 3: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master vrf-red state UP mode DEFAULT group default qlen 1000 + link/ether 02:00:00:00:02:02 brd ff:ff:ff:ff:ff:ff + 4: eth2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master vrf-red state UP mode DEFAULT group default qlen 1000 + link/ether 02:00:00:00:02:03 brd ff:ff:ff:ff:ff:ff + 7: eth5: <BROADCAST,MULTICAST> mtu 1500 qdisc noop master vrf-red state DOWN mode DEFAULT group default qlen 1000 + link/ether 02:00:00:00:02:06 brd ff:ff:ff:ff:ff:ff + + + Or using the brief output: + $ ip -br link show master vrf-red + eth1 UP 02:00:00:00:02:02 <BROADCAST,MULTICAST,UP,LOWER_UP> + eth2 UP 02:00:00:00:02:03 <BROADCAST,MULTICAST,UP,LOWER_UP> + eth5 DOWN 02:00:00:00:02:06 <BROADCAST,MULTICAST> + + +5. Show Neighbor Entries for a VRF + + To list neighbor entries associated with devices enslaved to a VRF device + add the master option to the ip command: + $ ip [-6] neigh show master VRF-NAME + + For example: + $ ip neigh show master vrf-red + 10.2.1.254 dev eth1 lladdr a6:d9:c7:4f:06:23 REACHABLE + 10.2.2.254 dev eth2 lladdr 5e:54:01:6a:ee:80 REACHABLE + + $ ip -6 neigh show master vrf-red + 2002:1::64 dev eth1 lladdr a6:d9:c7:4f:06:23 REACHABLE + + +6. Show Addresses for a VRF + + To show addresses for interfaces associated with a VRF add the master + option to the ip command: + $ ip addr show master VRF-NAME + + For example: + $ ip addr show master vrf-red + 3: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master vrf-red state UP group default qlen 1000 + link/ether 02:00:00:00:02:02 brd ff:ff:ff:ff:ff:ff + inet 10.2.1.2/24 brd 10.2.1.255 scope global eth1 + valid_lft forever preferred_lft forever + inet6 2002:1::2/120 scope global + valid_lft forever preferred_lft forever + inet6 fe80::ff:fe00:202/64 scope link + valid_lft forever preferred_lft forever + 4: eth2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master vrf-red state UP group default qlen 1000 + link/ether 02:00:00:00:02:03 brd ff:ff:ff:ff:ff:ff + inet 10.2.2.2/24 brd 10.2.2.255 scope global eth2 + valid_lft forever preferred_lft forever + inet6 2002:2::2/120 scope global + valid_lft forever preferred_lft forever + inet6 fe80::ff:fe00:203/64 scope link + valid_lft forever preferred_lft forever + 7: eth5: <BROADCAST,MULTICAST> mtu 1500 qdisc noop master vrf-red state DOWN group default qlen 1000 + link/ether 02:00:00:00:02:06 brd ff:ff:ff:ff:ff:ff + + Or in brief format: + $ ip -br addr show master vrf-red + eth1 UP 10.2.1.2/24 2002:1::2/120 fe80::ff:fe00:202/64 + eth2 UP 10.2.2.2/24 2002:2::2/120 fe80::ff:fe00:203/64 + eth5 DOWN + + +7. Show Routes for a VRF + + To show routes for a VRF use the ip command to display the table associated + with the VRF device: + $ ip [-6] route show table ID + + For example: + $ ip route show table vrf-red + prohibit default + broadcast 10.2.1.0 dev eth1 proto kernel scope link src 10.2.1.2 + 10.2.1.0/24 dev eth1 proto kernel scope link src 10.2.1.2 + local 10.2.1.2 dev eth1 proto kernel scope host src 10.2.1.2 + broadcast 10.2.1.255 dev eth1 proto kernel scope link src 10.2.1.2 + broadcast 10.2.2.0 dev eth2 proto kernel scope link src 10.2.2.2 + 10.2.2.0/24 dev eth2 proto kernel scope link src 10.2.2.2 + local 10.2.2.2 dev eth2 proto kernel scope host src 10.2.2.2 + broadcast 10.2.2.255 dev eth2 proto kernel scope link src 10.2.2.2 + + $ ip -6 route show table vrf-red + local 2002:1:: dev lo proto none metric 0 pref medium + local 2002:1::2 dev lo proto none metric 0 pref medium + 2002:1::/120 dev eth1 proto kernel metric 256 pref medium + local 2002:2:: dev lo proto none metric 0 pref medium + local 2002:2::2 dev lo proto none metric 0 pref medium + 2002:2::/120 dev eth2 proto kernel metric 256 pref medium + local fe80:: dev lo proto none metric 0 pref medium + local fe80:: dev lo proto none metric 0 pref medium + local fe80::ff:fe00:202 dev lo proto none metric 0 pref medium + local fe80::ff:fe00:203 dev lo proto none metric 0 pref medium + fe80::/64 dev eth1 proto kernel metric 256 pref medium + fe80::/64 dev eth2 proto kernel metric 256 pref medium + ff00::/8 dev vrf-red metric 256 pref medium + ff00::/8 dev eth1 metric 256 pref medium + ff00::/8 dev eth2 metric 256 pref medium + + +8. Route Lookup for a VRF + + A test route lookup can be done for a VRF by adding the oif option to ip: + $ ip [-6] route get oif VRF-NAME ADDRESS + + For example: + $ ip route get 10.2.1.40 oif vrf-red + 10.2.1.40 dev eth1 table vrf-red src 10.2.1.2 + cache + + $ ip -6 route get 2002:1::32 oif vrf-red + 2002:1::32 from :: dev eth1 table vrf-red proto kernel src 2002:1::2 metric 256 pref medium + + +9. Removing Network Interface from a VRF + + Network interfaces are removed from a VRF by breaking the enslavement to + the VRF device: + $ ip link set dev NAME nomaster + + Connected routes are moved back to the default table and local entries are + moved to the local table. + + For example: + $ ip link set dev eth0 nomaster + +-------------------------------------------------------------------------------- + +Commands used in this example: + +cat >> /etc/iproute2/rt_tables <<EOF +1 vrf-mgmt +10 vrf-red +66 vrf-blue +81 vrf-green +EOF + +function vrf_create +{ + VRF=$1 + TBID=$2 + # create VRF device + ip link add vrf-${VRF} type vrf table ${TBID} + + # add rules that direct lookups to vrf table + ip ru add pref 200 oif vrf-${VRF} table ${TBID} + ip ru add pref 200 iif vrf-${VRF} table ${TBID} + ip -6 ru add pref 200 oif vrf-${VRF} table ${TBID} + ip -6 ru add pref 200 iif vrf-${VRF} table ${TBID} + + if [ "${VRF}" != "mgmt" ]; then + ip route add table ${TBID} prohibit default + fi + ip link set dev vrf-${VRF} up + ip link set dev vrf-${VRF} state up +} + +vrf_create mgmt 1 +ip link set dev eth0 master vrf-mgmt + +vrf_create red 10 +ip link set dev eth1 master vrf-red +ip link set dev eth2 master vrf-red +ip link set dev eth5 master vrf-red + +vrf_create blue 66 +ip link set dev eth3 master vrf-blue + +vrf_create green 81 +ip link set dev eth4 master vrf-green + + +Interface addresses from /etc/network/interfaces: +auto eth0 +iface eth0 inet static + address 10.0.0.2 + netmask 255.255.255.0 + gateway 10.0.0.254 + +iface eth0 inet6 static + address 2000:1::2 + netmask 120 + +auto eth1 +iface eth1 inet static + address 10.2.1.2 + netmask 255.255.255.0 + +iface eth1 inet6 static + address 2002:1::2 + netmask 120 + +auto eth2 +iface eth2 inet static + address 10.2.2.2 + netmask 255.255.255.0 + +iface eth2 inet6 static + address 2002:2::2 + netmask 120 + +auto eth3 +iface eth3 inet static + address 10.2.3.2 + netmask 255.255.255.0 + +iface eth3 inet6 static + address 2002:3::2 + netmask 120 + +auto eth4 +iface eth4 inet static + address 10.2.4.2 + netmask 255.255.255.0 + +iface eth4 inet6 static + address 2002:4::2 + netmask 120 diff --git a/MAINTAINERS b/MAINTAINERS index 9bf8683defd9..fb8603e2a3f3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3591,6 +3591,13 @@ F: drivers/gpu/drm/i915/ F: include/drm/i915* F: include/uapi/drm/i915* +DRM DRIVERS FOR ATMEL HLCDC +M: Boris Brezillon <[email protected]> +S: Supported +F: drivers/gpu/drm/atmel-hlcdc/ +F: Documentation/devicetree/bindings/drm/atmel/ + DRM DRIVERS FOR EXYNOS M: Inki Dae <[email protected]> M: Joonyoung Shim <[email protected]> @@ -3619,6 +3626,14 @@ S: Maintained F: drivers/gpu/drm/imx/ F: Documentation/devicetree/bindings/drm/imx/ +DRM DRIVERS FOR GMA500 (Poulsbo, Moorestown and derivative chipsets) +M: Patrik Jakobsson <[email protected]> +T: git git://github.com/patjak/drm-gma500 +S: Maintained +F: drivers/gpu/drm/gma500 +F: include/drm/gma500* + DRM DRIVERS FOR NVIDIA TEGRA M: Thierry Reding <[email protected]> M: Terje Bergström <[email protected]> @@ -4003,7 +4018,7 @@ S: Maintained F: sound/usb/misc/ua101.c EXTENSIBLE FIRMWARE INTERFACE (EFI) -M: Matt Fleming <[email protected]> +M: Matt Fleming <[email protected]> T: git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git S: Maintained @@ -4018,7 +4033,7 @@ F: include/linux/efi*.h EFI VARIABLE FILESYSTEM M: Matthew Garrett <[email protected]> M: Jeremy Kerr <[email protected]> -M: Matt Fleming <[email protected]> +M: Matt Fleming <[email protected]> T: git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git S: Maintained @@ -6785,7 +6800,6 @@ F: drivers/scsi/megaraid/ MELLANOX ETHERNET DRIVER (mlx4_en) M: Amir Vadai <[email protected]> -M: Ido Shamay <[email protected]> S: Supported W: http://www.mellanox.com @@ -9108,6 +9122,15 @@ S: Supported F: Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt F: drivers/net/ethernet/synopsys/dwc_eth_qos.c +SYNOPSYS DESIGNWARE I2C DRIVER +M: Andy Shevchenko <[email protected]> +M: Jarkko Nikula <[email protected]> +M: Mika Westerberg <[email protected]> +S: Maintained +F: drivers/i2c/busses/i2c-designware-* +F: include/linux/platform_data/i2c-designware.h + SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER M: Seungwon Jeon <[email protected]> M: Jaehoon Chung <[email protected]> @@ -9921,7 +9944,6 @@ S: Maintained F: drivers/staging/lustre STAGING - NVIDIA COMPLIANT EMBEDDED CONTROLLER INTERFACE (nvec) -M: Julian Andres Klode <[email protected]> M: Marc Dietrich <[email protected]> L: [email protected] (moderated for non-subscribers) @@ -11384,15 +11406,6 @@ W: http://oops.ghostprotocols.net:81/blog S: Maintained F: drivers/net/wireless/wl3501* -WM97XX TOUCHSCREEN DRIVERS -M: Mark Brown <[email protected]> -M: Liam Girdwood <[email protected]> -W: https://github.com/CirrusLogic/linux-drivers/wiki -S: Supported -F: drivers/input/touchscreen/*wm97* -F: include/linux/wm97xx.h - WOLFSON MICROELECTRONICS DRIVERS T: git https://github.com/CirrusLogic/linux-drivers.git @@ -1,8 +1,8 @@ VERSION = 4 PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = -rc3 -NAME = Hurr durr I'ma sheep +EXTRAVERSION = -rc6 +NAME = Blurry Fish Butt # *DOCUMENTATION* # To see a list of typical targets execute "make help" diff --git a/arch/alpha/include/asm/word-at-a-time.h b/arch/alpha/include/asm/word-at-a-time.h index 6b340d0f1521..902e6ab00a06 100644 --- a/arch/alpha/include/asm/word-at-a-time.h +++ b/arch/alpha/include/asm/word-at-a-time.h @@ -52,4 +52,6 @@ static inline unsigned long find_zero(unsigned long bits) #endif } +#define zero_bytemask(mask) ((2ul << (find_zero(mask) * 8)) - 1) + #endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index 7611b10a2d23..0b10ef2a4372 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -48,4 +48,5 @@ generic-y += types.h generic-y += ucontext.h generic-y += user.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 233159d2eaab..bb8fa023d574 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -578,7 +578,7 @@ dtb-$(CONFIG_MACH_SUN4I) += \ sun4i-a10-hackberry.dtb \ sun4i-a10-hyundai-a7hd.dtb \ sun4i-a10-inet97fv2.dtb \ - sun4i-a10-itead-iteaduino-plus.dts \ + sun4i-a10-itead-iteaduino-plus.dtb \ sun4i-a10-jesurun-q5.dtb \ sun4i-a10-marsboard.dtb \ sun4i-a10-mini-xplus.dtb \ diff --git a/arch/arm/boot/dts/exynos4412.dtsi b/arch/arm/boot/dts/exynos4412.dtsi index ca0e3c15977f..294cfe40388d 100644 --- a/arch/arm/boot/dts/exynos4412.dtsi +++ b/arch/arm/boot/dts/exynos4412.dtsi @@ -98,6 +98,7 @@ opp-hz = /bits/ 64 <800000000>; opp-microvolt = <1000000>; clock-latency-ns = <200000>; + opp-suspend; }; opp07 { opp-hz = /bits/ 64 <900000000>; diff --git a/arch/arm/boot/dts/exynos5250-smdk5250.dts b/arch/arm/boot/dts/exynos5250-smdk5250.dts index 15aea760c1da..c625e71217aa 100644 --- a/arch/arm/boot/dts/exynos5250-smdk5250.dts +++ b/arch/arm/boot/dts/exynos5250-smdk5250.dts @@ -197,6 +197,7 @@ regulator-name = "P1.8V_LDO_OUT10"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-always-on; }; ldo11_reg: LDO11 { diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi index df9aee92ecf4..1b3d6c769a3c 100644 --- a/arch/arm/boot/dts/exynos5420.dtsi +++ b/arch/arm/boot/dts/exynos5420.dtsi @@ -1117,7 +1117,7 @@ interrupt-parent = <&combiner>; interrupts = <3 0>; clock-names = "sysmmu", "master"; - clocks = <&clock CLK_SMMU_FIMD1M0>, <&clock CLK_FIMD1>; + clocks = <&clock CLK_SMMU_FIMD1M1>, <&clock CLK_FIMD1>; power-domains = <&disp_pd>; #iommu-cells = <0>; }; diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi index 79ffdfe712aa..3b43e57845ae 100644 --- a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi +++ b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi @@ -472,7 +472,6 @@ */ pinctrl-0 = <&pwm0_out &pwm1_out &pwm2_out &pwm3_out>; pinctrl-names = "default"; - samsung,pwm-outputs = <0>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx53-qsrb.dts b/arch/arm/boot/dts/imx53-qsrb.dts index 66e47de5e826..96d7eede412e 100644 --- a/arch/arm/boot/dts/imx53-qsrb.dts +++ b/arch/arm/boot/dts/imx53-qsrb.dts @@ -36,7 +36,7 @@ pinctrl-0 = <&pinctrl_pmic>; reg = <0x08>; interrupt-parent = <&gpio5>; - interrupts = <23 0x8>; + interrupts = <23 IRQ_TYPE_LEVEL_HIGH>; regulators { sw1_reg: sw1a { regulator-name = "SW1"; diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi index c3e3ca9362fb..cd170376eaca 100644 --- a/arch/arm/boot/dts/imx53.dtsi +++ b/arch/arm/boot/dts/imx53.dtsi @@ -15,6 +15,7 @@ #include <dt-bindings/clock/imx5-clock.h> #include <dt-bindings/gpio/gpio.h> #include <dt-bindings/input/input.h> +#include <dt-bindings/interrupt-controller/irq.h> / { aliases { diff --git a/arch/arm/boot/dts/imx6qdl-rex.dtsi b/arch/arm/boot/dts/imx6qdl-rex.dtsi index 3373fd958e95..a50356243888 100644 --- a/arch/arm/boot/dts/imx6qdl-rex.dtsi +++ b/arch/arm/boot/dts/imx6qdl-rex.dtsi @@ -35,7 +35,6 @@ compatible = "regulator-fixed"; reg = <1>; pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_usbh1>; regulator-name = "usbh1_vbus"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; @@ -47,7 +46,6 @@ compatible = "regulator-fixed"; reg = <2>; pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_usbotg>; regulator-name = "usb_otg_vbus"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi index a0b2a79cbfbd..4624d0f2a754 100644 --- a/arch/arm/boot/dts/r8a7790.dtsi +++ b/arch/arm/boot/dts/r8a7790.dtsi @@ -1627,6 +1627,7 @@ "mix.0", "mix.1", "dvc.0", "dvc.1", "clk_a", "clk_b", "clk_c", "clk_i"; + power-domains = <&cpg_clocks>; status = "disabled"; diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi index 831525dd39a6..1666c8a6b143 100644 --- a/arch/arm/boot/dts/r8a7791.dtsi +++ b/arch/arm/boot/dts/r8a7791.dtsi @@ -1677,6 +1677,7 @@ "mix.0", "mix.1", "dvc.0", "dvc.1", "clk_a", "clk_b", "clk_c", "clk_i"; + power-domains = <&cpg_clocks>; status = "disabled"; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 2bebaa286f9a..391230c3dc93 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -107,7 +107,7 @@ 720000 1200000 528000 1100000 312000 1000000 - 144000 900000 + 144000 1000000 >; #cooling-cells = <2>; cooling-min-level = <0>; diff --git a/arch/arm/mach-exynos/mcpm-exynos.c b/arch/arm/mach-exynos/mcpm-exynos.c index 9bdf54795f05..56978199c479 100644 --- a/arch/arm/mach-exynos/mcpm-exynos.c +++ b/arch/arm/mach-exynos/mcpm-exynos.c @@ -20,6 +20,7 @@ #include <asm/cputype.h> #include <asm/cp15.h> #include <asm/mcpm.h> +#include <asm/smp_plat.h> #include "regs-pmu.h" #include "common.h" @@ -70,7 +71,31 @@ static int exynos_cpu_powerup(unsigned int cpu, unsigned int cluster) cluster >= EXYNOS5420_NR_CLUSTERS) return -EINVAL; - exynos_cpu_power_up(cpunr); + if (!exynos_cpu_power_state(cpunr)) { + exynos_cpu_power_up(cpunr); + + /* + * This assumes the cluster number of the big cores(Cortex A15) + * is 0 and the Little cores(Cortex A7) is 1. + * When the system was booted from the Little core, + * they should be reset during power up cpu. + */ + if (cluster && + cluster == MPIDR_AFFINITY_LEVEL(cpu_logical_map(0), 1)) { + /* + * Before we reset the Little cores, we should wait + * the SPARE2 register is set to 1 because the init + * codes of the iROM will set the register after + * initialization. + */ + while (!pmu_raw_readl(S5P_PMU_SPARE2)) + udelay(10); + + pmu_raw_writel(EXYNOS5420_KFC_CORE_RESET(cpu), + EXYNOS_SWRESET); + } + } + return 0; } diff --git a/arch/arm/mach-exynos/regs-pmu.h b/arch/arm/mach-exynos/regs-pmu.h index b7614333d296..fba9068ed260 100644 --- a/arch/arm/mach-exynos/regs-pmu.h +++ b/arch/arm/mach-exynos/regs-pmu.h @@ -513,6 +513,12 @@ static inline unsigned int exynos_pmu_cpunr(unsigned int mpidr) #define SPREAD_ENABLE 0xF #define SPREAD_USE_STANDWFI 0xF +#define EXYNOS5420_KFC_CORE_RESET0 BIT(8) +#define EXYNOS5420_KFC_ETM_RESET0 BIT(20) + +#define EXYNOS5420_KFC_CORE_RESET(_nr) \ + ((EXYNOS5420_KFC_CORE_RESET0 | EXYNOS5420_KFC_ETM_RESET0) << (_nr)) + #define EXYNOS5420_BB_CON1 0x0784 #define EXYNOS5420_BB_SEL_EN BIT(31) #define EXYNOS5420_BB_PMOS_EN BIT(7) diff --git a/arch/arm/mach-gemini/board-nas4220b.c b/arch/arm/mach-gemini/board-nas4220b.c index ca8a25bb3521..18b12796acf9 100644 --- a/arch/arm/mach-gemini/board-nas4220b.c +++ b/arch/arm/mach-gemini/board-nas4220b.c @@ -18,7 +18,6 @@ #include <linux/leds.h> #include <linux/input.h> #include <linux/gpio_keys.h> -#include <linux/mdio-gpio.h> #include <linux/io.h> #include <asm/setup.h> diff --git a/arch/arm/mach-gemini/board-wbd111.c b/arch/arm/mach-gemini/board-wbd111.c index 418188cd1712..14c56f3f0ec2 100644 --- a/arch/arm/mach-gemini/board-wbd111.c +++ b/arch/arm/mach-gemini/board-wbd111.c @@ -15,7 +15,6 @@ #include <linux/input.h> #include <linux/skbuff.h> #include <linux/gpio_keys.h> -#include <linux/mdio-gpio.h> #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> #include <asm/mach-types.h> diff --git a/arch/arm/mach-gemini/board-wbd222.c b/arch/arm/mach-gemini/board-wbd222.c index 266b265090cd..6070282ce243 100644 --- a/arch/arm/mach-gemini/board-wbd222.c +++ b/arch/arm/mach-gemini/board-wbd222.c @@ -15,7 +15,6 @@ #include <linux/input.h> #include <linux/skbuff.h> #include <linux/gpio_keys.h> -#include <linux/mdio-gpio.h> #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> #include <asm/mach-types.h> diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 6be415111eec..2f4b14cfddb4 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -626,6 +626,7 @@ load_common: case BPF_LD | BPF_B | BPF_IND: load_order = 0; load_ind: + update_on_xread(ctx); OP_IMM3(ARM_ADD, r_off, r_X, k, ctx); goto load_common; case BPF_LDX | BPF_IMM: diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index f9914d7c1bb0..d10b5d483022 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -42,7 +42,7 @@ endif CHECKFLAGS += -D__aarch64__ ifeq ($(CONFIG_ARM64_ERRATUM_843419), y) -CFLAGS_MODULE += -mcmodel=large +KBUILD_CFLAGS_MODULE += -mcmodel=large endif # Default value diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b0329be95cb1..26b066690593 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -79,7 +79,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) #define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) -#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) +#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) #define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) #define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) #define PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) @@ -496,7 +496,7 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | - PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK; + PTE_PROT_NONE | PTE_VALID | PTE_WRITE; /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) pte = pte_mkdirty(pte); diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 3bc498c250dc..41e58fe3c041 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 388 +#define __NR_compat_syscalls 390 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index cef934a90f17..5b925b761a2a 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -797,3 +797,12 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create) __SYSCALL(__NR_bpf, sys_bpf) #define __NR_execveat 387 __SYSCALL(__NR_execveat, compat_sys_execveat) +#define __NR_userfaultfd 388 +__SYSCALL(__NR_userfaultfd, sys_userfaultfd) +#define __NR_membarrier 389 +__SYSCALL(__NR_membarrier, sys_membarrier) + +/* + * Please add new compat syscalls above this comment and update + * __NR_compat_syscalls in asm/unistd.h. + */ diff --git a/arch/arm64/include/uapi/asm/signal.h b/arch/arm64/include/uapi/asm/signal.h index 8d1e7236431b..991bf5db2ca1 100644 --- a/arch/arm64/include/uapi/asm/signal.h +++ b/arch/arm64/include/uapi/asm/signal.h @@ -19,6 +19,9 @@ /* Required for AArch32 compatibility. */ #define SA_RESTORER 0x04000000 +#define MINSIGSTKSZ 5120 +#define SIGSTKSZ 16384 + #include <asm-generic/signal.h> #endif diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index cebf78661a55..253021ef2769 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -201,7 +201,7 @@ void unregister_step_hook(struct step_hook *hook) } /* - * Call registered single step handers + * Call registered single step handlers * There is no Syndrome info to check for determining the handler. * So we call all the registered handlers, until the right handler is * found which returns zero. @@ -271,20 +271,21 @@ static int single_step_handler(unsigned long addr, unsigned int esr, * Use reader/writer locks instead of plain spinlock. */ static LIST_HEAD(break_hook); -static DEFINE_RWLOCK(break_hook_lock); +static DEFINE_SPINLOCK(break_hook_lock); void register_break_hook(struct break_hook *hook) { - write_lock(&break_hook_lock); - list_add(&hook->node, &break_hook); - write_unlock(&break_hook_lock); + spin_lock(&break_hook_lock); + list_add_rcu(&hook->node, &break_hook); + spin_unlock(&break_hook_lock); } void unregister_break_hook(struct break_hook *hook) { - write_lock(&break_hook_lock); - list_del(&hook->node); - write_unlock(&break_hook_lock); + spin_lock(&break_hook_lock); + list_del_rcu(&hook->node); + spin_unlock(&break_hook_lock); + synchronize_rcu(); } static int call_break_hook(struct pt_regs *regs, unsigned int esr) @@ -292,11 +293,11 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) struct break_hook *hook; int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL; - read_lock(&break_hook_lock); - list_for_each_entry(hook, &break_hook, node) + rcu_read_lock(); + list_for_each_entry_rcu(hook, &break_hook, node) if ((esr & hook->esr_mask) == hook->esr_val) fn = hook->fn; - read_unlock(&break_hook_lock); + rcu_read_unlock(); return fn ? fn(regs, esr) : DBG_HOOK_ERROR; } diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index e8ca6eaedd02..13671a9cf016 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -258,7 +258,8 @@ static bool __init efi_virtmap_init(void) */ if (!is_normal_ram(md)) prot = __pgprot(PROT_DEVICE_nGnRE); - else if (md->type == EFI_RUNTIME_SERVICES_CODE) + else if (md->type == EFI_RUNTIME_SERVICES_CODE || + !PAGE_ALIGNED(md->phys_addr)) prot = PAGE_KERNEL_EXEC; else prot = PAGE_KERNEL; diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 08cafc518b9a..0f03a8fe2314 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -178,6 +178,24 @@ ENTRY(ftrace_stub) ENDPROC(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* save return value regs*/ + .macro save_return_regs + sub sp, sp, #64 + stp x0, x1, [sp] + stp x2, x3, [sp, #16] + stp x4, x5, [sp, #32] + stp x6, x7, [sp, #48] + .endm + + /* restore return value regs*/ + .macro restore_return_regs + ldp x0, x1, [sp] + ldp x2, x3, [sp, #16] + ldp x4, x5, [sp, #32] + ldp x6, x7, [sp, #48] + add sp, sp, #64 + .endm + /* * void ftrace_graph_caller(void) * @@ -204,11 +222,11 @@ ENDPROC(ftrace_graph_caller) * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled. */ ENTRY(return_to_handler) - str x0, [sp, #-16]! + save_return_regs mov x0, x29 // parent's fp bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp); mov x30, x0 // restore the original return address - ldr x0, [sp], #16 + restore_return_regs ret END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index f341866aa810..c08b9ad6f429 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -85,7 +85,7 @@ bool aarch64_insn_is_branch_imm(u32 insn) aarch64_insn_is_bcond(insn)); } -static DEFINE_SPINLOCK(patch_lock); +static DEFINE_RAW_SPINLOCK(patch_lock); static void __kprobes *patch_map(void *addr, int fixmap) { @@ -131,13 +131,13 @@ static int __kprobes __aarch64_insn_write(void *addr, u32 insn) unsigned long flags = 0; int ret; - spin_lock_irqsave(&patch_lock, flags); + raw_spin_lock_irqsave(&patch_lock, flags); waddr = patch_map(addr, FIX_TEXT_POKE0); ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE); patch_unmap(FIX_TEXT_POKE0); - spin_unlock_irqrestore(&patch_lock, flags); + raw_spin_unlock_irqrestore(&patch_lock, flags); return ret; } diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 6bab21f84a9f..232247945b1c 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -364,6 +364,8 @@ static void __init relocate_initrd(void) to_free = ram_end - orig_start; size = orig_end - orig_start; + if (!size) + return; /* initrd needs to be relocated completely inside linear mapping */ new_start = memblock_find_in_range(0, PFN_PHYS(max_pfn), diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index aba9ead1384c..9fadf6d7039b 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -287,6 +287,7 @@ retry: * starvation. */ mm_flags &= ~FAULT_FLAG_ALLOW_RETRY; + mm_flags |= FAULT_FLAG_TRIED; goto retry; } } diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild index f61f2dd67464..241b9b9729d8 100644 --- a/arch/avr32/include/asm/Kbuild +++ b/arch/avr32/include/asm/Kbuild @@ -20,4 +20,5 @@ generic-y += sections.h generic-y += topology.h generic-y += trace_clock.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild index 61cd1e786a14..91d49c0a3118 100644 --- a/arch/blackfin/include/asm/Kbuild +++ b/arch/blackfin/include/asm/Kbuild @@ -46,4 +46,5 @@ generic-y += types.h generic-y += ucontext.h generic-y += unaligned.h generic-y += user.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index f17c4dc6050c..945544ec603e 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -59,4 +59,5 @@ generic-y += types.h generic-y += ucontext.h generic-y += user.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild index b7f68192d15b..1778805f6380 100644 --- a/arch/cris/include/asm/Kbuild +++ b/arch/cris/include/asm/Kbuild @@ -43,4 +43,5 @@ generic-y += topology.h generic-y += trace_clock.h generic-y += types.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild index 8e47b832cc76..1fa084cf1a43 100644 --- a/arch/frv/include/asm/Kbuild +++ b/arch/frv/include/asm/Kbuild @@ -7,3 +7,4 @@ generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += preempt.h generic-y += trace_clock.h +generic-y += word-at-a-time.h diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index 70e6ae1e7006..373cb23301e3 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -73,4 +73,5 @@ generic-y += uaccess.h generic-y += ucontext.h generic-y += unaligned.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index daee37bd0999..db8ddabc6bd2 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -58,4 +58,5 @@ generic-y += types.h generic-y += ucontext.h generic-y += unaligned.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild index 9de3ba12f6b9..502a91d8dbbd 100644 --- a/arch/ia64/include/asm/Kbuild +++ b/arch/ia64/include/asm/Kbuild @@ -8,3 +8,4 @@ generic-y += mm-arch-hooks.h generic-y += preempt.h generic-y += trace_clock.h generic-y += vtime.h +generic-y += word-at-a-time.h diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild index e0eb704ca1fa..fd104bd221ce 100644 --- a/arch/m32r/include/asm/Kbuild +++ b/arch/m32r/include/asm/Kbuild @@ -9,3 +9,4 @@ generic-y += module.h generic-y += preempt.h generic-y += sections.h generic-y += trace_clock.h +generic-y += word-at-a-time.h diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 0b6b40d37b95..5b4ec541ba7c 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -57,7 +58,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -67,10 +67,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -179,6 +181,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -206,6 +209,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -271,6 +275,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -370,6 +375,7 @@ CONFIG_ZORRO8390=y # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m @@ -537,6 +543,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index eeb3a8991fc4..6e5198e2c124 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -55,7 +56,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -65,10 +65,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -177,6 +179,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -204,6 +207,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -269,6 +273,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -344,6 +349,7 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m @@ -495,6 +501,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 3a7006654ce9..f75600b0ca23 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -55,7 +56,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -65,10 +65,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -177,6 +179,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -204,6 +207,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -269,6 +273,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -355,6 +360,7 @@ CONFIG_NE2000=y # CONFIG_NET_VENDOR_SEEQ is not set CONFIG_SMC91X=y # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m @@ -517,6 +523,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 0586b323a673..a42d91c389a6 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -53,7 +54,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -63,10 +63,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -175,6 +177,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -202,6 +205,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -267,6 +271,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -343,6 +348,7 @@ CONFIG_BVME6000_NET=y # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m @@ -488,6 +494,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index ad1dbce07aa4..77f4a11083e9 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -55,7 +56,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -65,10 +65,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -177,6 +179,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -204,6 +207,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -269,6 +273,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -345,6 +350,7 @@ CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m @@ -497,6 +503,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index b44acacaecf4..5a329f77329b 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -54,7 +55,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -64,10 +64,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -176,6 +178,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -203,6 +206,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -271,6 +275,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -364,6 +369,7 @@ CONFIG_MAC8390=y # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m @@ -519,6 +525,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 8afca3753db1..83c80d2030ec 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -64,7 +65,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -74,10 +74,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -186,6 +188,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -213,6 +216,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -281,6 +285,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -410,6 +415,7 @@ CONFIG_ZORRO8390=y # CONFIG_NET_VENDOR_SEEQ is not set CONFIG_SMC91X=y # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PLIP=m @@ -599,6 +605,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index ef00875994d9..6cb42c3bf5a2 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -52,7 +53,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -62,10 +62,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -174,6 +176,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -201,6 +204,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -266,6 +270,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -343,6 +348,7 @@ CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m @@ -488,6 +494,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 387c2bd90ff1..c7508c30330c 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -53,7 +54,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -63,10 +63,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -175,6 +177,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -202,6 +205,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -267,6 +271,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -343,6 +348,7 @@ CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m @@ -488,6 +494,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 35355c1bc714..64b71664a303 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -53,7 +54,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -63,10 +63,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -175,6 +177,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -202,6 +205,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -267,6 +271,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -354,6 +359,7 @@ CONFIG_NE2000=y # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PLIP=m @@ -510,6 +516,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 8442d267b877..9a4cab78a2ea 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -50,7 +51,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -60,10 +60,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -172,6 +174,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -199,6 +202,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -264,6 +268,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -341,6 +346,7 @@ CONFIG_SUN3_82586=y # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_SUN is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m @@ -489,6 +495,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_MANAGER=y diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 0e1b542e1555..1a2eaac13dbd 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -10,6 +10,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -50,7 +51,6 @@ CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_GENEVE_CORE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -60,10 +60,12 @@ CONFIG_INET_XFRM_MODE_BEET=m # CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m +CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_ILA=m CONFIG_IPV6_VTI=m CONFIG_IPV6_GRE=m CONFIG_NETFILTER=y @@ -172,6 +174,7 @@ CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_DUP_IPV4=m CONFIG_NF_TABLES_ARP=m CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_NAT_IPV4=m @@ -199,6 +202,7 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_DUP_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m CONFIG_NFT_REDIR_IPV6=m @@ -264,6 +268,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -341,6 +346,7 @@ CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m @@ -489,6 +495,7 @@ CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_RSA=m diff --git a/arch/m68k/include/asm/linkage.h b/arch/m68k/include/asm/linkage.h index 5a822bb790f7..066e74f666ae 100644 --- a/arch/m68k/include/asm/linkage.h +++ b/arch/m68k/include/asm/linkage.h @@ -4,4 +4,34 @@ #define __ALIGN .align 4 #define __ALIGN_STR ".align 4" +/* + * Make sure the compiler doesn't do anything stupid with the + * arguments on the stack - they are owned by the *caller*, not + * the callee. This just fools gcc into not spilling into them, + * and keeps it from doing tailcall recursion and/or using the + * stack slots for temporaries, since they are live and "used" + * all the way to the end of the function. + */ +#define asmlinkage_protect(n, ret, args...) \ + __asmlinkage_protect##n(ret, ##args) +#define __asmlinkage_protect_n(ret, args...) \ + __asm__ __volatile__ ("" : "=r" (ret) : "0" (ret), ##args) +#define __asmlinkage_protect0(ret) \ + __asmlinkage_protect_n(ret) +#define __asmlinkage_protect1(ret, arg1) \ + __asmlinkage_protect_n(ret, "m" (arg1)) +#define __asmlinkage_protect2(ret, arg1, arg2) \ + __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2)) +#define __asmlinkage_protect3(ret, arg1, arg2, arg3) \ + __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3)) +#define __asmlinkage_protect4(ret, arg1, arg2, arg3, arg4) \ + __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ + "m" (arg4)) +#define __asmlinkage_protect5(ret, arg1, arg2, arg3, arg4, arg5) \ + __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ + "m" (arg4), "m" (arg5)) +#define __asmlinkage_protect6(ret, arg1, arg2, arg3, arg4, arg5, arg6) \ + __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ + "m" (arg4), "m" (arg5), "m" (arg6)) + #endif diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index 244e0dbe45db..0793a7f17417 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -4,7 +4,7 @@ #include <uapi/asm/unistd.h> -#define NR_syscalls 356 +#define NR_syscalls 375 #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_OLD_STAT diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h index 61fb6cb9d2ae..5e6fae6c275f 100644 --- a/arch/m68k/include/uapi/asm/unistd.h +++ b/arch/m68k/include/uapi/asm/unistd.h @@ -361,5 +361,24 @@ #define __NR_memfd_create 353 #define __NR_bpf 354 #define __NR_execveat 355 +#define __NR_socket 356 +#define __NR_socketpair 357 +#define __NR_bind 358 +#define __NR_connect 359 +#define __NR_listen 360 +#define __NR_accept4 361 +#define __NR_getsockopt 362 +#define __NR_setsockopt 363 +#define __NR_getsockname 364 +#define __NR_getpeername 365 +#define __NR_sendto 366 +#define __NR_sendmsg 367 +#define __NR_recvfrom 368 +#define __NR_recvmsg 369 +#define __NR_shutdown 370 +#define __NR_recvmmsg 371 +#define __NR_sendmmsg 372 +#define __NR_userfaultfd 373 +#define __NR_membarrier 374 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */ diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S index a0ec4303f2c8..5dd0e80042f5 100644 --- a/arch/m68k/kernel/syscalltable.S +++ b/arch/m68k/kernel/syscalltable.S @@ -376,4 +376,22 @@ ENTRY(sys_call_table) .long sys_memfd_create .long sys_bpf .long sys_execveat /* 355 */ - + .long sys_socket + .long sys_socketpair + .long sys_bind + .long sys_connect + .long sys_listen /* 360 */ + .long sys_accept4 + .long sys_getsockopt + .long sys_setsockopt + .long sys_getsockname + .long sys_getpeername /* 365 */ + .long sys_sendto + .long sys_sendmsg + .long sys_recvfrom + .long sys_recvmsg + .long sys_shutdown /* 370 */ + .long sys_recvmmsg + .long sys_sendmmsg + .long sys_userfaultfd + .long sys_membarrier diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild index df31353fd200..29acb89daaaa 100644 --- a/arch/metag/include/asm/Kbuild +++ b/arch/metag/include/asm/Kbuild @@ -54,4 +54,5 @@ generic-y += ucontext.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 2f222f355c4b..b0ae88c9fed9 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -10,3 +10,4 @@ generic-y += mm-arch-hooks.h generic-y += preempt.h generic-y += syscalls.h generic-y += trace_clock.h +generic-y += word-at-a-time.h diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index 89a628455bc2..bd634259eab9 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -933,7 +933,7 @@ void __init plat_mem_setup(void) while ((boot_mem_map.nr_map < BOOT_MEM_MAP_MAX) && (total < MAX_MEMORY)) { memory = cvmx_bootmem_phy_alloc(mem_alloc_size, - __pa_symbol(&__init_end), -1, + __pa_symbol(&_end), -1, 0x100000, CVMX_BOOTMEM_FLAG_NO_LOCKING); if (memory >= 0) { diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 40ec4ca3f946..c7fe4d01e79c 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -17,4 +17,5 @@ generic-y += segment.h generic-y += serial.h generic-y += trace_clock.h generic-y += user.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index 9e777cd42b67..d10fd80dbb7e 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -256,6 +256,7 @@ static inline void __iomem * __ioremap_mode(phys_addr_t offset, unsigned long si */ #define ioremap_nocache(offset, size) \ __ioremap_mode((offset), (size), _CACHE_UNCACHED) +#define ioremap_uc ioremap_nocache /* * ioremap_cachable - map bus memory into CPU space diff --git a/arch/mips/include/uapi/asm/swab.h b/arch/mips/include/uapi/asm/swab.h index c4ddc4f0d2dc..23cd9b118c9e 100644 --- a/arch/mips/include/uapi/asm/swab.h +++ b/arch/mips/include/uapi/asm/swab.h @@ -13,16 +13,15 @@ #define __SWAB_64_THRU_32__ -#if (defined(__mips_isa_rev) && (__mips_isa_rev >= 2)) || \ - defined(_MIPS_ARCH_LOONGSON3A) +#if !defined(__mips16) && \ + ((defined(__mips_isa_rev) && (__mips_isa_rev >= 2)) || \ + defined(_MIPS_ARCH_LOONGSON3A)) -static inline __attribute__((nomips16)) __attribute_const__ - __u16 __arch_swab16(__u16 x) +static inline __attribute_const__ __u16 __arch_swab16(__u16 x) { __asm__( " .set push \n" " .set arch=mips32r2 \n" - " .set nomips16 \n" " wsbh %0, %1 \n" " .set pop \n" : "=r" (x) @@ -32,13 +31,11 @@ static inline __attribute__((nomips16)) __attribute_const__ } #define __arch_swab16 __arch_swab16 -static inline __attribute__((nomips16)) __attribute_const__ - __u32 __arch_swab32(__u32 x) +static inline __attribute_const__ __u32 __arch_swab32(__u32 x) { __asm__( " .set push \n" " .set arch=mips32r2 \n" - " .set nomips16 \n" " wsbh %0, %1 \n" " rotr %0, %0, 16 \n" " .set pop \n" @@ -54,13 +51,11 @@ static inline __attribute__((nomips16)) __attribute_const__ * 64-bit kernel on r2 CPUs. */ #ifdef __mips64 -static inline __attribute__((nomips16)) __attribute_const__ - __u64 __arch_swab64(__u64 x) +static inline __attribute_const__ __u64 __arch_swab64(__u64 x) { __asm__( " .set push \n" " .set arch=mips64r2 \n" - " .set nomips16 \n" " dsbh %0, %1 \n" " dshd %0, %0 \n" " .set pop \n" @@ -71,5 +66,5 @@ static inline __attribute__((nomips16)) __attribute_const__ } #define __arch_swab64 __arch_swab64 #endif /* __mips64 */ -#endif /* MIPS R2 or newer or Loongson 3A */ +#endif /* (not __mips16) and (MIPS R2 or newer or Loongson 3A) */ #endif /* _ASM_SWAB_H */ diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h index c03088f9f514..cfabadb135d9 100644 --- a/arch/mips/include/uapi/asm/unistd.h +++ b/arch/mips/include/uapi/asm/unistd.h @@ -377,16 +377,18 @@ #define __NR_memfd_create (__NR_Linux + 354) #define __NR_bpf (__NR_Linux + 355) #define __NR_execveat (__NR_Linux + 356) +#define __NR_userfaultfd (__NR_Linux + 357) +#define __NR_membarrier (__NR_Linux + 358) /* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 356 +#define __NR_Linux_syscalls 358 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 356 +#define __NR_O32_Linux_syscalls 358 #if _MIPS_SIM == _MIPS_SIM_ABI64 @@ -711,16 +713,18 @@ #define __NR_memfd_create (__NR_Linux + 314) #define __NR_bpf (__NR_Linux + 315) #define __NR_execveat (__NR_Linux + 316) +#define __NR_userfaultfd (__NR_Linux + 317) +#define __NR_membarrier (__NR_Linux + 318) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 316 +#define __NR_Linux_syscalls 318 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 316 +#define __NR_64_Linux_syscalls 318 #if _MIPS_SIM == _MIPS_SIM_NABI32 @@ -1049,15 +1053,17 @@ #define __NR_memfd_create (__NR_Linux + 318) #define __NR_bpf (__NR_Linux + 319) #define __NR_execveat (__NR_Linux + 320) +#define __NR_userfaultfd (__NR_Linux + 321) +#define __NR_membarrier (__NR_Linux + 322) /* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 320 +#define __NR_Linux_syscalls 322 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 320 +#define __NR_N32_Linux_syscalls 322 #endif /* _UAPI_ASM_UNISTD_H */ diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c index 4e62bf85d0b0..459cb017306c 100644 --- a/arch/mips/jz4740/board-qi_lb60.c +++ b/arch/mips/jz4740/board-qi_lb60.c @@ -26,6 +26,7 @@ #include <linux/power/jz4740-battery.h> #include <linux/power/gpio-charger.h> +#include <asm/mach-jz4740/gpio.h> #include <asm/mach-jz4740/jz4740_fb.h> #include <asm/mach-jz4740/jz4740_mmc.h> #include <asm/mach-jz4740/jz4740_nand.h> diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c index a74e181058b0..8c6d76c9b2d6 100644 --- a/arch/mips/jz4740/gpio.c +++ b/arch/mips/jz4740/gpio.c @@ -28,6 +28,7 @@ #include <linux/seq_file.h> #include <asm/mach-jz4740/base.h> +#include <asm/mach-jz4740/gpio.h> #define JZ4740_GPIO_BASE_A (32*0) #define JZ4740_GPIO_BASE_B (32*1) diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index 9f71c06aebf6..209ded16806b 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -39,6 +39,7 @@ mfc0 \dest, CP0_CONFIG, 3 andi \dest, \dest, MIPS_CONF3_MT beqz \dest, \nomt + nop .endm .section .text.cps-vec @@ -223,10 +224,9 @@ LEAF(excep_ejtag) END(excep_ejtag) LEAF(mips_cps_core_init) -#ifdef CONFIG_MIPS_MT +#ifdef CONFIG_MIPS_MT_SMP /* Check that the core implements the MT ASE */ has_mt t0, 3f - nop .set push .set mips64r2 @@ -310,8 +310,9 @@ LEAF(mips_cps_boot_vpes) PTR_ADDU t0, t0, t1 /* Calculate this VPEs ID. If the core doesn't support MT use 0 */ + li t9, 0 +#ifdef CONFIG_MIPS_MT_SMP has_mt ta2, 1f - li t9, 0 /* Find the number of VPEs present in the core */ mfc0 t1, CP0_MVPCONF0 @@ -330,6 +331,7 @@ LEAF(mips_cps_boot_vpes) /* Retrieve the VPE ID from EBase.CPUNum */ mfc0 t9, $15, 1 and t9, t9, t1 +#endif 1: /* Calculate a pointer to this VPEs struct vpe_boot_config */ li t1, VPEBOOTCFG_SIZE @@ -337,7 +339,7 @@ LEAF(mips_cps_boot_vpes) PTR_L ta3, COREBOOTCFG_VPECONFIG(t0) PTR_ADDU v0, v0, ta3 -#ifdef CONFIG_MIPS_MT +#ifdef CONFIG_MIPS_MT_SMP /* If the core doesn't support MT then return */ bnez ta2, 1f @@ -451,7 +453,7 @@ LEAF(mips_cps_boot_vpes) 2: .set pop -#endif /* CONFIG_MIPS_MT */ +#endif /* CONFIG_MIPS_MT_SMP */ /* Return */ jr ra diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S index 423ae83af1fb..3375745b9198 100644 --- a/arch/mips/kernel/octeon_switch.S +++ b/arch/mips/kernel/octeon_switch.S @@ -18,7 +18,7 @@ .set pop /* * task_struct *resume(task_struct *prev, task_struct *next, - * struct thread_info *next_ti, int usedfpu) + * struct thread_info *next_ti) */ .align 7 LEAF(resume) @@ -28,30 +28,6 @@ cpu_save_nonscratch a0 LONG_S ra, THREAD_REG31(a0) - /* - * check if we need to save FPU registers - */ - .set push - .set noreorder - beqz a3, 1f - PTR_L t3, TASK_THREAD_INFO(a0) - .set pop - - /* - * clear saved user stack CU1 bit - */ - LONG_L t0, ST_OFF(t3) - li t1, ~ST0_CU1 - and t0, t0, t1 - LONG_S t0, ST_OFF(t3) - - .set push - .set arch=mips64r2 - fpu_save_double a0 t0 t1 # c0_status passed in t0 - # clobbers t1 - .set pop -1: - #if CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0 /* Check if we need to store CVMSEG state */ dmfc0 t0, $11,7 /* CvmMemCtl */ diff --git a/arch/mips/kernel/r2300_switch.S b/arch/mips/kernel/r2300_switch.S index 5087a4b72e6b..ac27ef7d4d0e 100644 --- a/arch/mips/kernel/r2300_switch.S +++ b/arch/mips/kernel/r2300_switch.S @@ -31,18 +31,8 @@ #define ST_OFF (_THREAD_SIZE - 32 - PT_SIZE + PT_STATUS) /* - * FPU context is saved iff the process has used it's FPU in the current - * time slice as indicated by TIF_USEDFPU. In any case, the CU1 bit for user - * space STATUS register should be 0, so that a process *always* starts its - * userland with FPU disabled after each context switch. - * - * FPU will be enabled as soon as the process accesses FPU again, through - * do_cpu() trap. - */ - -/* * task_struct *resume(task_struct *prev, task_struct *next, - * struct thread_info *next_ti, int usedfpu) + * struct thread_info *next_ti) */ LEAF(resume) mfc0 t1, CP0_STATUS @@ -50,22 +40,6 @@ LEAF(resume) cpu_save_nonscratch a0 sw ra, THREAD_REG31(a0) - beqz a3, 1f - - PTR_L t3, TASK_THREAD_INFO(a0) - - /* - * clear saved user stack CU1 bit - */ - lw t0, ST_OFF(t3) - li t1, ~ST0_CU1 - and t0, t0, t1 - sw t0, ST_OFF(t3) - - fpu_save_single a0, t0 # clobbers t0 - -1: - #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP) PTR_LA t8, __stack_chk_guard LONG_L t9, TASK_STACK_CANARY(a1) diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 4cc13508d967..65a74e4f0f45 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -36,16 +36,8 @@ NESTED(handle_sys, PT_SIZE, sp) lw t1, PT_EPC(sp) # skip syscall on return subu v0, v0, __NR_O32_Linux # check syscall number - sltiu t0, v0, __NR_O32_Linux_syscalls + 1 addiu t1, 4 # skip to next instruction sw t1, PT_EPC(sp) - beqz t0, illegal_syscall - - sll t0, v0, 2 - la t1, sys_call_table - addu t1, t0 - lw t2, (t1) # syscall routine - beqz t2, illegal_syscall sw a3, PT_R26(sp) # save a3 for syscall restarting @@ -96,6 +88,16 @@ loads_done: li t1, _TIF_WORK_SYSCALL_ENTRY and t0, t1 bnez t0, syscall_trace_entry # -> yes +syscall_common: + sltiu t0, v0, __NR_O32_Linux_syscalls + 1 + beqz t0, illegal_syscall + + sll t0, v0, 2 + la t1, sys_call_table + addu t1, t0 + lw t2, (t1) # syscall routine + + beqz t2, illegal_syscall jalr t2 # Do The Real Thing (TM) @@ -116,7 +118,7 @@ o32_syscall_exit: syscall_trace_entry: SAVE_STATIC - move s0, t2 + move s0, v0 move a0, sp /* @@ -129,27 +131,18 @@ syscall_trace_entry: 1: jal syscall_trace_enter - bltz v0, 2f # seccomp failed? Skip syscall + bltz v0, 1f # seccomp failed? Skip syscall + + move v0, s0 # restore syscall - move t0, s0 RESTORE_STATIC lw a0, PT_R4(sp) # Restore argument registers lw a1, PT_R5(sp) lw a2, PT_R6(sp) lw a3, PT_R7(sp) - jalr t0 - - li t0, -EMAXERRNO - 1 # error? - sltu t0, t0, v0 - sw t0, PT_R7(sp) # set error flag - beqz t0, 1f - - lw t1, PT_R2(sp) # syscall number - negu v0 # error - sw t1, PT_R0(sp) # save it for syscall restarting -1: sw v0, PT_R2(sp) # result + j syscall_common -2: j syscall_exit +1: j syscall_exit /* ------------------------------------------------------------------------ */ @@ -599,3 +592,5 @@ EXPORT(sys_call_table) PTR sys_memfd_create PTR sys_bpf /* 4355 */ PTR sys_execveat + PTR sys_userfaultfd + PTR sys_membarrier diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index a6f6b762c47a..e732981cf99f 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -39,18 +39,11 @@ NESTED(handle_sys64, PT_SIZE, sp) .set at #endif - dsubu t0, v0, __NR_64_Linux # check syscall number - sltiu t0, t0, __NR_64_Linux_syscalls + 1 #if !defined(CONFIG_MIPS32_O32) && !defined(CONFIG_MIPS32_N32) ld t1, PT_EPC(sp) # skip syscall on return daddiu t1, 4 # skip to next instruction sd t1, PT_EPC(sp) #endif - beqz t0, illegal_syscall - - dsll t0, v0, 3 # offset into table - ld t2, (sys_call_table - (__NR_64_Linux * 8))(t0) - # syscall routine sd a3, PT_R26(sp) # save a3 for syscall restarting @@ -59,6 +52,17 @@ NESTED(handle_sys64, PT_SIZE, sp) and t0, t1, t0 bnez t0, syscall_trace_entry +syscall_common: + dsubu t2, v0, __NR_64_Linux + sltiu t0, t2, __NR_64_Linux_syscalls + 1 + beqz t0, illegal_syscall + + dsll t0, t2, 3 # offset into table + dla t2, sys_call_table + daddu t0, t2, t0 + ld t2, (t0) # syscall routine + beqz t2, illegal_syscall + jalr t2 # Do The Real Thing (TM) li t0, -EMAXERRNO - 1 # error? @@ -78,14 +82,14 @@ n64_syscall_exit: syscall_trace_entry: SAVE_STATIC - move s0, t2 + move s0, v0 move a0, sp move a1, v0 jal syscall_trace_enter - bltz v0, 2f # seccomp failed? Skip syscall + bltz v0, 1f # seccomp failed? Skip syscall - move t0, s0 + move v0, s0 RESTORE_STATIC ld a0, PT_R4(sp) # Restore argument registers ld a1, PT_R5(sp) @@ -93,19 +97,9 @@ syscall_trace_entry: ld a3, PT_R7(sp) ld a4, PT_R8(sp) ld a5, PT_R9(sp) - jalr t0 - - li t0, -EMAXERRNO - 1 # error? - sltu t0, t0, v0 - sd t0, PT_R7(sp) # set error flag - beqz t0, 1f - - ld t1, PT_R2(sp) # syscall number - dnegu v0 # error - sd t1, PT_R0(sp) # save it for syscall restarting -1: sd v0, PT_R2(sp) # result + j syscall_common -2: j syscall_exit +1: j syscall_exit illegal_syscall: /* This also isn't a 64-bit syscall, throw an error. */ @@ -436,4 +430,6 @@ EXPORT(sys_call_table) PTR sys_memfd_create PTR sys_bpf /* 5315 */ PTR sys_execveat + PTR sys_userfaultfd + PTR sys_membarrier .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 4b2010654c46..c79484397584 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -52,6 +52,7 @@ NESTED(handle_sysn32, PT_SIZE, sp) and t0, t1, t0 bnez t0, n32_syscall_trace_entry +syscall_common: jalr t2 # Do The Real Thing (TM) li t0, -EMAXERRNO - 1 # error? @@ -75,9 +76,9 @@ n32_syscall_trace_entry: move a1, v0 jal syscall_trace_enter - bltz v0, 2f # seccomp failed? Skip syscall + bltz v0, 1f # seccomp failed? Skip syscall - move t0, s0 + move t2, s0 RESTORE_STATIC ld a0, PT_R4(sp) # Restore argument registers ld a1, PT_R5(sp) @@ -85,19 +86,9 @@ n32_syscall_trace_entry: ld a3, PT_R7(sp) ld a4, PT_R8(sp) ld a5, PT_R9(sp) - jalr t0 + j syscall_common - li t0, -EMAXERRNO - 1 # error? - sltu t0, t0, v0 - sd t0, PT_R7(sp) # set error flag - beqz t0, 1f - - ld t1, PT_R2(sp) # syscall number - dnegu v0 # error - sd t1, PT_R0(sp) # save it for syscall restarting -1: sd v0, PT_R2(sp) # result - -2: j syscall_exit +1: j syscall_exit not_n32_scall: /* This is not an n32 compatibility syscall, pass it on to @@ -429,4 +420,6 @@ EXPORT(sysn32_call_table) PTR sys_memfd_create PTR sys_bpf PTR compat_sys_execveat /* 6320 */ + PTR sys_userfaultfd + PTR sys_membarrier .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index f543ff4feef9..6369cfd390c6 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -87,6 +87,7 @@ loads_done: and t0, t1, t0 bnez t0, trace_a_syscall +syscall_common: jalr t2 # Do The Real Thing (TM) li t0, -EMAXERRNO - 1 # error? @@ -130,9 +131,9 @@ trace_a_syscall: 1: jal syscall_trace_enter - bltz v0, 2f # seccomp failed? Skip syscall + bltz v0, 1f # seccomp failed? Skip syscall - move t0, s0 + move t2, s0 RESTORE_STATIC ld a0, PT_R4(sp) # Restore argument registers ld a1, PT_R5(sp) @@ -142,19 +143,9 @@ trace_a_syscall: ld a5, PT_R9(sp) ld a6, PT_R10(sp) ld a7, PT_R11(sp) # For indirect syscalls - jalr t0 + j syscall_common - li t0, -EMAXERRNO - 1 # error? - sltu t0, t0, v0 - sd t0, PT_R7(sp) # set error flag - beqz t0, 1f - - ld t1, PT_R2(sp) # syscall number - dnegu v0 # error - sd t1, PT_R0(sp) # save it for syscall restarting -1: sd v0, PT_R2(sp) # result - -2: j syscall_exit +1: j syscall_exit /* ------------------------------------------------------------------------ */ @@ -584,4 +575,6 @@ EXPORT(sys32_call_table) PTR sys_memfd_create PTR sys_bpf /* 4355 */ PTR compat_sys_execveat + PTR sys_userfaultfd + PTR sys_membarrier .size sys32_call_table,.-sys32_call_table diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index a914dc1cb6d1..d8117be729a2 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -100,7 +100,7 @@ static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp) else #endif #if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32) - if (dev->coherent_dma_mask < DMA_BIT_MASK(64)) + if (dev->coherent_dma_mask < DMA_BIT_MASK(sizeof(phys_addr_t) * 8)) dma_flag = __GFP_DMA; else #endif diff --git a/arch/mips/net/bpf_jit_asm.S b/arch/mips/net/bpf_jit_asm.S index dabf4179cd7e..5d2e0c8d29c0 100644 --- a/arch/mips/net/bpf_jit_asm.S +++ b/arch/mips/net/bpf_jit_asm.S @@ -57,12 +57,13 @@ LEAF(sk_load_word) is_offset_negative(word) - .globl sk_load_word_positive -sk_load_word_positive: +FEXPORT(sk_load_word_positive) is_offset_in_header(4, word) /* Offset within header boundaries */ PTR_ADDU t1, $r_skb_data, offset + .set reorder lw $r_A, 0(t1) + .set noreorder #ifdef CONFIG_CPU_LITTLE_ENDIAN # if defined(__mips_isa_rev) && (__mips_isa_rev >= 2) wsbh t0, $r_A @@ -85,12 +86,13 @@ sk_load_word_positive: LEAF(sk_load_half) is_offset_negative(half) - .globl sk_load_half_positive -sk_load_half_positive: +FEXPORT(sk_load_half_positive) is_offset_in_header(2, half) /* Offset within header boundaries */ PTR_ADDU t1, $r_skb_data, offset + .set reorder lh $r_A, 0(t1) + .set noreorder #ifdef CONFIG_CPU_LITTLE_ENDIAN # if defined(__mips_isa_rev) && (__mips_isa_rev >= 2) wsbh t0, $r_A @@ -109,8 +111,7 @@ sk_load_half_positive: LEAF(sk_load_byte) is_offset_negative(byte) - .globl sk_load_byte_positive -sk_load_byte_positive: +FEXPORT(sk_load_byte_positive) is_offset_in_header(1, byte) /* Offset within header boundaries */ PTR_ADDU t1, $r_skb_data, offset diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild index 6edb9ee6128e..1c8dd0f5cd5d 100644 --- a/arch/mn10300/include/asm/Kbuild +++ b/arch/mn10300/include/asm/Kbuild @@ -9,3 +9,4 @@ generic-y += mm-arch-hooks.h generic-y += preempt.h generic-y += sections.h generic-y += trace_clock.h +generic-y += word-at-a-time.h diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index 914864eb5a25..d63330e88379 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -61,4 +61,5 @@ generic-y += types.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 6bc0ee4b1070..2c041b535a64 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -111,7 +111,7 @@ CONFIG_SCSI_QLA_FC=m CONFIG_SCSI_QLA_ISCSI=m CONFIG_SCSI_LPFC=m CONFIG_SCSI_VIRTIO=m -CONFIG_SCSI_DH=m +CONFIG_SCSI_DH=y CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_ALUA=m CONFIG_ATA=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 7991f37e5fe2..36871a4bfa54 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -114,7 +114,7 @@ CONFIG_SCSI_QLA_FC=m CONFIG_SCSI_QLA_ISCSI=m CONFIG_SCSI_LPFC=m CONFIG_SCSI_VIRTIO=m -CONFIG_SCSI_DH=m +CONFIG_SCSI_DH=y CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_ALUA=m CONFIG_ATA=y diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index cab6753f1be5..3f191f573d4f 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -61,8 +61,13 @@ struct machdep_calls { unsigned long addr, unsigned char *hpte_slot_array, int psize, int ssize, int local); - /* special for kexec, to be called in real mode, linear mapping is - * destroyed as well */ + /* + * Special for kexec. + * To be called in real mode with interrupts disabled. No locks are + * taken as such, concurrent access on pre POWER5 hardware could result + * in a deadlock. + * The linear mapping is destroyed as well. + */ void (*hpte_clear_all)(void); void __iomem * (*ioremap)(phys_addr_t addr, unsigned long size, diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index 5b3a903adae6..e4396a7d0f7c 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -40,6 +40,11 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct return (val + c->high_bits) & ~rhs; } +static inline unsigned long zero_bytemask(unsigned long mask) +{ + return ~1ul << __fls(mask); +} + #else #ifdef CONFIG_64BIT diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 13befa35d8a8..c8822af10a58 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -582,13 +582,21 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot, * be when they isi), and we are the only one left. We rely on our kernel * mapping being 0xC0's and the hardware ignoring those two real bits. * + * This must be called with interrupts disabled. + * + * Taking the native_tlbie_lock is unsafe here due to the possibility of + * lockdep being on. On pre POWER5 hardware, not taking the lock could + * cause deadlock. POWER5 and newer not taking the lock is fine. This only + * gets called during boot before secondary CPUs have come up and during + * crashdump and all bets are off anyway. + * * TODO: add batching support when enabled. remember, no dynamic memory here, * athough there is the control page available... */ static void native_hpte_clear(void) { unsigned long vpn = 0; - unsigned long slot, slots, flags; + unsigned long slot, slots; struct hash_pte *hptep = htab_address; unsigned long hpte_v; unsigned long pteg_count; @@ -596,13 +604,6 @@ static void native_hpte_clear(void) pteg_count = htab_hash_mask + 1; - local_irq_save(flags); - - /* we take the tlbie lock and hold it. Some hardware will - * deadlock if we try to tlbie from two processors at once. - */ - raw_spin_lock(&native_tlbie_lock); - slots = pteg_count * HPTES_PER_GROUP; for (slot = 0; slot < slots; slot++, hptep++) { @@ -614,8 +615,8 @@ static void native_hpte_clear(void) hpte_v = be64_to_cpu(hptep->v); /* - * Call __tlbie() here rather than tlbie() since we - * already hold the native_tlbie_lock. + * Call __tlbie() here rather than tlbie() since we can't take the + * native_tlbie_lock. */ if (hpte_v & HPTE_V_VALID) { hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn); @@ -625,8 +626,6 @@ static void native_hpte_clear(void) } asm volatile("eieio; tlbsync; ptesync":::"memory"); - raw_spin_unlock(&native_tlbie_lock); - local_irq_restore(flags); } /* diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 230f3a7cdea4..4296d55e88f3 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -487,9 +487,12 @@ int opal_machine_check(struct pt_regs *regs) * PRD component would have already got notified about this * error through other channels. * - * In any case, let us just fall through. We anyway heading - * down to panic path. + * If hardware marked this as an unrecoverable MCE, we are + * going to panic anyway. Even if it didn't, it's not safe to + * continue at this point, so we should explicitly panic. */ + + panic("PowerNV Unrecovered Machine Check"); return 0; } diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c index 09787139834d..3db53e8aff92 100644 --- a/arch/powerpc/platforms/ps3/os-area.c +++ b/arch/powerpc/platforms/ps3/os-area.c @@ -194,11 +194,6 @@ static const struct os_area_db_id os_area_db_id_rtc_diff = { .key = OS_AREA_DB_KEY_RTC_DIFF }; -static const struct os_area_db_id os_area_db_id_video_mode = { - .owner = OS_AREA_DB_OWNER_LINUX, - .key = OS_AREA_DB_KEY_VIDEO_MODE -}; - #define SECONDS_FROM_1970_TO_2000 946684800LL /** diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index d4788111c161..fac6ac9790fa 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -10,7 +10,7 @@ targets += misc.o piggy.o sizes.h head.o KBUILD_CFLAGS := -m64 -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks +KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -msoft-float KBUILD_CFLAGS += $(call cc-option,-mpacked-stack) KBUILD_CFLAGS += $(call cc-option,-ffreestanding) diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 0c98f1508542..ed7da281df66 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -381,7 +381,7 @@ CONFIG_ISCSI_TCP=m CONFIG_SCSI_DEBUG=m CONFIG_ZFCP=y CONFIG_SCSI_VIRTIO=m -CONFIG_SCSI_DH=m +CONFIG_SCSI_DH=y CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_HP_SW=m CONFIG_SCSI_DH_EMC=m diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index 82083e1fbdc4..9858b14cde1e 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -377,7 +377,7 @@ CONFIG_ISCSI_TCP=m CONFIG_SCSI_DEBUG=m CONFIG_ZFCP=y CONFIG_SCSI_VIRTIO=m -CONFIG_SCSI_DH=m +CONFIG_SCSI_DH=y CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_HP_SW=m CONFIG_SCSI_DH_EMC=m diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index c05c9e0821e3..7f14f80717d4 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -377,7 +377,7 @@ CONFIG_ISCSI_TCP=m CONFIG_SCSI_DEBUG=m CONFIG_ZFCP=y CONFIG_SCSI_VIRTIO=m -CONFIG_SCSI_DH=m +CONFIG_SCSI_DH=y CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_HP_SW=m CONFIG_SCSI_DH_EMC=m diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 5ad26dd94d77..9043d2e1e2ae 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -6,3 +6,4 @@ generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += preempt.h generic-y += trace_clock.h +generic-y += word-at-a-time.h diff --git a/arch/s390/include/asm/numa.h b/arch/s390/include/asm/numa.h index 2a0efc63b9e5..dc19ee0c92aa 100644 --- a/arch/s390/include/asm/numa.h +++ b/arch/s390/include/asm/numa.h @@ -19,7 +19,7 @@ int numa_pfn_to_nid(unsigned long pfn); int __node_distance(int a, int b); void numa_update_cpu_topology(void); -extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; +extern cpumask_t node_to_cpumask_map[MAX_NUMNODES]; extern int numa_debug_enabled; #else diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h index 27ebde643933..94fc55fc72ce 100644 --- a/arch/s390/include/asm/topology.h +++ b/arch/s390/include/asm/topology.h @@ -68,7 +68,7 @@ static inline int cpu_to_node(int cpu) #define cpumask_of_node cpumask_of_node static inline const struct cpumask *cpumask_of_node(int node) { - return node_to_cpumask_map[node]; + return &node_to_cpumask_map[node]; } /* diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 48c9af7a7683..3aeeb1b562c0 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -176,6 +176,7 @@ int main(void) DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste)); DEFINE(__LC_FP_CREG_SAVE_AREA, offsetof(struct _lowcore, fpt_creg_save_area)); DEFINE(__LC_LAST_BREAK, offsetof(struct _lowcore, breaking_event_addr)); + DEFINE(__LC_PERCPU_OFFSET, offsetof(struct _lowcore, percpu_offset)); DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data)); DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap)); DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb)); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 09b039d7983d..582fe44ab07c 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -733,6 +733,14 @@ ENTRY(psw_idle) stg %r3,__SF_EMPTY(%r15) larl %r1,.Lpsw_idle_lpsw+4 stg %r1,__SF_EMPTY+8(%r15) +#ifdef CONFIG_SMP + larl %r1,smp_cpu_mtid + llgf %r1,0(%r1) + ltgr %r1,%r1 + jz .Lpsw_idle_stcctm + .insn rsy,0xeb0000000017,%r1,5,__SF_EMPTY+16(%r15) +.Lpsw_idle_stcctm: +#endif STCK __CLOCK_IDLE_ENTER(%r2) stpt __TIMER_IDLE_ENTER(%r2) .Lpsw_idle_lpsw: @@ -1159,7 +1167,27 @@ cleanup_critical: jhe 1f mvc __CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2) mvc __TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r2) -1: # account system time going idle +1: # calculate idle cycles +#ifdef CONFIG_SMP + clg %r9,BASED(.Lcleanup_idle_insn) + jl 3f + larl %r1,smp_cpu_mtid + llgf %r1,0(%r1) + ltgr %r1,%r1 + jz 3f + .insn rsy,0xeb0000000017,%r1,5,__SF_EMPTY+80(%r15) + larl %r3,mt_cycles + ag %r3,__LC_PERCPU_OFFSET + la %r4,__SF_EMPTY+16(%r15) +2: lg %r0,0(%r3) + slg %r0,0(%r4) + alg %r0,64(%r4) + stg %r0,0(%r3) + la %r3,8(%r3) + la %r4,8(%r4) + brct %r1,2b +#endif +3: # account system time going idle lg %r9,__LC_STEAL_TIMER alg %r9,__CLOCK_IDLE_ENTER(%r2) slg %r9,__LC_LAST_UPDATE_CLOCK diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index c8653435c70d..dafc44f519c3 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -25,7 +25,7 @@ static DEFINE_SPINLOCK(virt_timer_lock); static atomic64_t virt_timer_current; static atomic64_t virt_timer_elapsed; -static DEFINE_PER_CPU(u64, mt_cycles[32]); +DEFINE_PER_CPU(u64, mt_cycles[8]); static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 }; static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 }; static DEFINE_PER_CPU(u64, mt_scaling_jiffies); @@ -60,6 +60,34 @@ static inline int virt_timer_forward(u64 elapsed) return elapsed >= atomic64_read(&virt_timer_current); } +static void update_mt_scaling(void) +{ + u64 cycles_new[8], *cycles_old; + u64 delta, fac, mult, div; + int i; + + stcctm5(smp_cpu_mtid + 1, cycles_new); + cycles_old = this_cpu_ptr(mt_cycles); + fac = 1; + mult = div = 0; + for (i = 0; i <= smp_cpu_mtid; i++) { + delta = cycles_new[i] - cycles_old[i]; + div += delta; + mult *= i + 1; + mult += delta * fac; + fac *= i + 1; + } + div *= fac; + if (div > 0) { + /* Update scaling factor */ + __this_cpu_write(mt_scaling_mult, mult); + __this_cpu_write(mt_scaling_div, div); + memcpy(cycles_old, cycles_new, + sizeof(u64) * (smp_cpu_mtid + 1)); + } + __this_cpu_write(mt_scaling_jiffies, jiffies_64); +} + /* * Update process times based on virtual cpu times stored by entry.S * to the lowcore fields user_timer, system_timer & steal_clock. @@ -69,7 +97,6 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset) struct thread_info *ti = task_thread_info(tsk); u64 timer, clock, user, system, steal; u64 user_scaled, system_scaled; - int i; timer = S390_lowcore.last_update_timer; clock = S390_lowcore.last_update_clock; @@ -85,34 +112,10 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset) S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock; - /* Do MT utilization calculation */ + /* Update MT utilization calculation */ if (smp_cpu_mtid && - time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies))) { - u64 cycles_new[32], *cycles_old; - u64 delta, fac, mult, div; - - cycles_old = this_cpu_ptr(mt_cycles); - if (stcctm5(smp_cpu_mtid + 1, cycles_new) < 2) { - fac = 1; - mult = div = 0; - for (i = 0; i <= smp_cpu_mtid; i++) { - delta = cycles_new[i] - cycles_old[i]; - div += delta; - mult *= i + 1; - mult += delta * fac; - fac *= i + 1; - } - div *= fac; - if (div > 0) { - /* Update scaling factor */ - __this_cpu_write(mt_scaling_mult, mult); - __this_cpu_write(mt_scaling_div, div); - memcpy(cycles_old, cycles_new, - sizeof(u64) * (smp_cpu_mtid + 1)); - } - } - __this_cpu_write(mt_scaling_jiffies, jiffies_64); - } + time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies))) + update_mt_scaling(); user = S390_lowcore.user_timer - ti->user_timer; S390_lowcore.steal_timer -= user; @@ -181,6 +184,11 @@ void vtime_account_irq_enter(struct task_struct *tsk) S390_lowcore.last_update_timer = get_vtimer(); S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; + /* Update MT utilization calculation */ + if (smp_cpu_mtid && + time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies))) + update_mt_scaling(); + system = S390_lowcore.system_timer - ti->system_timer; S390_lowcore.steal_timer -= system; ti->system_timer = S390_lowcore.system_timer; diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c index 7de4e2f780d7..30b2698a28e2 100644 --- a/arch/s390/numa/mode_emu.c +++ b/arch/s390/numa/mode_emu.c @@ -368,7 +368,7 @@ static void topology_add_core(struct toptree *core) cpumask_copy(&top->thread_mask, &core->mask); cpumask_copy(&top->core_mask, &core_mc(core)->mask); cpumask_copy(&top->book_mask, &core_book(core)->mask); - cpumask_set_cpu(cpu, node_to_cpumask_map[core_node(core)->id]); + cpumask_set_cpu(cpu, &node_to_cpumask_map[core_node(core)->id]); top->node_id = core_node(core)->id; } } @@ -383,7 +383,7 @@ static void toptree_to_topology(struct toptree *numa) /* Clear all node masks */ for (i = 0; i < MAX_NUMNODES; i++) - cpumask_clear(node_to_cpumask_map[i]); + cpumask_clear(&node_to_cpumask_map[i]); /* Rebuild all masks */ toptree_for_each(core, numa, CORE) diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index 09b1d2355bd9..43f32ce60aa3 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -23,7 +23,7 @@ pg_data_t *node_data[MAX_NUMNODES]; EXPORT_SYMBOL(node_data); -cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; +cpumask_t node_to_cpumask_map[MAX_NUMNODES]; EXPORT_SYMBOL(node_to_cpumask_map); const struct numa_mode numa_mode_plain = { @@ -144,7 +144,7 @@ void __init numa_setup(void) static int __init numa_init_early(void) { /* Attach all possible CPUs to node 0 for now. */ - cpumask_copy(node_to_cpumask_map[0], cpu_possible_mask); + cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask); return 0; } early_initcall(numa_init_early); diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild index 92ffe397b893..a05218ff3fe4 100644 --- a/arch/score/include/asm/Kbuild +++ b/arch/score/include/asm/Kbuild @@ -13,3 +13,4 @@ generic-y += sections.h generic-y += trace_clock.h generic-y += xor.h generic-y += serial.h +generic-y += word-at-a-time.h diff --git a/arch/sh/include/asm/page.h b/arch/sh/include/asm/page.h index fe20d14ae051..ceb5201a30ed 100644 --- a/arch/sh/include/asm/page.h +++ b/arch/sh/include/asm/page.h @@ -59,6 +59,7 @@ pages_do_alias(unsigned long addr1, unsigned long addr2) #define clear_page(page) memset((void *)(page), 0, PAGE_SIZE) extern void copy_page(void *to, void *from); +#define copy_user_page(to, from, vaddr, pg) __copy_user(to, from, PAGE_SIZE) struct page; struct vm_area_struct; diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c index 2e48eb8813ff..c90930de76ba 100644 --- a/arch/sparc/crypto/aes_glue.c +++ b/arch/sparc/crypto/aes_glue.c @@ -433,6 +433,7 @@ static struct crypto_alg algs[] = { { .blkcipher = { .min_keysize = AES_MIN_KEY_SIZE, .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, .setkey = aes_set_key, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, @@ -452,6 +453,7 @@ static struct crypto_alg algs[] = { { .blkcipher = { .min_keysize = AES_MIN_KEY_SIZE, .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, .setkey = aes_set_key, .encrypt = ctr_crypt, .decrypt = ctr_crypt, diff --git a/arch/sparc/crypto/camellia_glue.c b/arch/sparc/crypto/camellia_glue.c index 6bf2479a12fb..561a84d93cf6 100644 --- a/arch/sparc/crypto/camellia_glue.c +++ b/arch/sparc/crypto/camellia_glue.c @@ -274,6 +274,7 @@ static struct crypto_alg algs[] = { { .blkcipher = { .min_keysize = CAMELLIA_MIN_KEY_SIZE, .max_keysize = CAMELLIA_MAX_KEY_SIZE, + .ivsize = CAMELLIA_BLOCK_SIZE, .setkey = camellia_set_key, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c index dd6a34fa6e19..61af794aa2d3 100644 --- a/arch/sparc/crypto/des_glue.c +++ b/arch/sparc/crypto/des_glue.c @@ -429,6 +429,7 @@ static struct crypto_alg algs[] = { { .blkcipher = { .min_keysize = DES_KEY_SIZE, .max_keysize = DES_KEY_SIZE, + .ivsize = DES_BLOCK_SIZE, .setkey = des_set_key, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, @@ -485,6 +486,7 @@ static struct crypto_alg algs[] = { { .blkcipher = { .min_keysize = DES3_EDE_KEY_SIZE, .max_keysize = DES3_EDE_KEY_SIZE, + .ivsize = DES3_EDE_BLOCK_SIZE, .setkey = des3_ede_set_key, .encrypt = cbc3_encrypt, .decrypt = cbc3_decrypt, diff --git a/arch/tile/gxio/mpipe.c b/arch/tile/gxio/mpipe.c index ee186e13dfe6..f102048d9c0e 100644 --- a/arch/tile/gxio/mpipe.c +++ b/arch/tile/gxio/mpipe.c @@ -19,6 +19,7 @@ #include <linux/errno.h> #include <linux/io.h> #include <linux/module.h> +#include <linux/string.h> #include <gxio/iorpc_globals.h> #include <gxio/iorpc_mpipe.h> @@ -29,32 +30,6 @@ /* HACK: Avoid pointless "shadow" warnings. */ #define link link_shadow -/** - * strscpy - Copy a C-string into a sized buffer, but only if it fits - * @dest: Where to copy the string to - * @src: Where to copy the string from - * @size: size of destination buffer - * - * Use this routine to avoid copying too-long strings. - * The routine returns the total number of bytes copied - * (including the trailing NUL) or zero if the buffer wasn't - * big enough. To ensure that programmers pay attention - * to the return code, the destination has a single NUL - * written at the front (if size is non-zero) when the - * buffer is not big enough. - */ -static size_t strscpy(char *dest, const char *src, size_t size) -{ - size_t len = strnlen(src, size) + 1; - if (len > size) { - if (size) - dest[0] = '\0'; - return 0; - } - memcpy(dest, src, len); - return len; -} - int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index) { char file[32]; @@ -540,7 +515,7 @@ int gxio_mpipe_link_instance(const char *link_name) if (!context) return GXIO_ERR_NO_DEVICE; - if (strscpy(name.name, link_name, sizeof(name.name)) == 0) + if (strscpy(name.name, link_name, sizeof(name.name)) < 0) return GXIO_ERR_NO_DEVICE; return gxio_mpipe_info_instance_aux(context, name); @@ -559,7 +534,7 @@ int gxio_mpipe_link_enumerate_mac(int idx, char *link_name, uint8_t *link_mac) rv = gxio_mpipe_info_enumerate_aux(context, idx, &name, &mac); if (rv >= 0) { - if (strscpy(link_name, name.name, sizeof(name.name)) == 0) + if (strscpy(link_name, name.name, sizeof(name.name)) < 0) return GXIO_ERR_INVAL_MEMORY_SIZE; memcpy(link_mac, mac.mac, sizeof(mac.mac)); } @@ -576,7 +551,7 @@ int gxio_mpipe_link_open(gxio_mpipe_link_t *link, _gxio_mpipe_link_name_t name; int rv; - if (strscpy(name.name, link_name, sizeof(name.name)) == 0) + if (strscpy(name.name, link_name, sizeof(name.name)) < 0) return GXIO_ERR_NO_DEVICE; rv = gxio_mpipe_link_open_aux(context, name, flags); diff --git a/arch/tile/include/asm/word-at-a-time.h b/arch/tile/include/asm/word-at-a-time.h index 9e5ce0d7b292..b66a693c2c34 100644 --- a/arch/tile/include/asm/word-at-a-time.h +++ b/arch/tile/include/asm/word-at-a-time.h @@ -6,7 +6,7 @@ struct word_at_a_time { /* unused */ }; #define WORD_AT_A_TIME_CONSTANTS {} -/* Generate 0x01 byte values for non-zero bytes using a SIMD instruction. */ +/* Generate 0x01 byte values for zero bytes using a SIMD instruction. */ static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) { @@ -33,4 +33,10 @@ static inline long find_zero(unsigned long mask) #endif } +#ifdef __BIG_ENDIAN +#define zero_bytemask(mask) (~1ul << (63 - __builtin_clzl(mask))) +#else +#define zero_bytemask(mask) ((2ul << __builtin_ctzl(mask)) - 1) +#endif + #endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index 149ec55f9c46..904f3ebf4220 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -25,4 +25,5 @@ generic-y += preempt.h generic-y += switch_to.h generic-y += topology.h generic-y += trace_clock.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 1fc7a286dc6f..256c45b3ae34 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -62,4 +62,5 @@ generic-y += ucontext.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 328c8352480c..96d058a87100 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1308,6 +1308,7 @@ config HIGHMEM config X86_PAE bool "PAE (Physical Address Extension) Support" depends on X86_32 && !HIGHMEM4G + select SWIOTLB ---help--- PAE is required for NX support, and furthermore enables larger swapspace support for non-overcommit purposes. It diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 80a0e4389c9a..bacaa13acac5 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -554,6 +554,11 @@ static int __init camellia_aesni_init(void) { const char *feature_name; + if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { + pr_info("AVX or AES-NI instructions are not detected.\n"); + return -ENODEV; + } + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index e6cf2ad350d1..9727b3b48bd1 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -193,7 +193,7 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_HWP ( 7*32+ 10) /* "hwp" Intel HWP */ -#define X86_FEATURE_HWP_NOITFY ( 7*32+ 11) /* Intel HWP_NOTIFY */ +#define X86_FEATURE_HWP_NOTIFY ( 7*32+ 11) /* Intel HWP_NOTIFY */ #define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */ #define X86_FEATURE_HWP_EPP ( 7*32+13) /* Intel HWP_EPP */ #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2beee0382088..3a36ee704c30 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1226,10 +1226,8 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); int kvm_is_in_guest(void); -int __x86_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem); -int x86_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem); +int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); +int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu); bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 83aea8055119..4c20dd333412 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -336,10 +336,10 @@ HYPERVISOR_update_descriptor(u64 ma, u64 desc) return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32); } -static inline int +static inline long HYPERVISOR_memory_op(unsigned int cmd, void *arg) { - return _hypercall2(int, memory_op, cmd, arg); + return _hypercall2(long, memory_op, cmd, arg); } static inline int diff --git a/arch/x86/include/uapi/asm/bitsperlong.h b/arch/x86/include/uapi/asm/bitsperlong.h index b0ae1c4dc791..217909b4d6f5 100644 --- a/arch/x86/include/uapi/asm/bitsperlong.h +++ b/arch/x86/include/uapi/asm/bitsperlong.h @@ -1,7 +1,7 @@ #ifndef __ASM_X86_BITSPERLONG_H #define __ASM_X86_BITSPERLONG_H -#ifdef __x86_64__ +#if defined(__x86_64__) && !defined(__ILP32__) # define __BITS_PER_LONG 64 #else # define __BITS_PER_LONG 32 diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 381c8b9b3a33..20e242ea1bc4 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -34,11 +34,10 @@ struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); -static void (*hv_kexec_handler)(void); -static void (*hv_crash_handler)(struct pt_regs *regs); - #if IS_ENABLED(CONFIG_HYPERV) static void (*vmbus_handler)(void); +static void (*hv_kexec_handler)(void); +static void (*hv_crash_handler)(struct pt_regs *regs); void hyperv_vector_handler(struct pt_regs *regs) { @@ -96,8 +95,8 @@ void hv_remove_crash_handler(void) hv_crash_handler = NULL; } EXPORT_SYMBOL_GPL(hv_remove_crash_handler); -#endif +#ifdef CONFIG_KEXEC_CORE static void hv_machine_shutdown(void) { if (kexec_in_progress && hv_kexec_handler) @@ -111,7 +110,8 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hv_crash_handler(regs); native_machine_crash_shutdown(regs); } - +#endif /* CONFIG_KEXEC_CORE */ +#endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) { @@ -186,8 +186,10 @@ static void __init ms_hyperv_init_platform(void) no_timer_check = 1; #endif +#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE) machine_ops.shutdown = hv_machine_shutdown; machine_ops.crash_shutdown = hv_machine_crash_shutdown; +#endif mark_tsc_unstable("running on Hyper-V"); } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 3d423a101fae..608fb26c7254 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -37,7 +37,7 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, { X86_FEATURE_HWP, CR_EAX, 7, 0x00000006, 0 }, - { X86_FEATURE_HWP_NOITFY, CR_EAX, 8, 0x00000006, 0 }, + { X86_FEATURE_HWP_NOTIFY, CR_EAX, 8, 0x00000006, 0 }, { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 }, { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 }, { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 }, diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index e068d6683dba..74ca2fe7a0b3 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -185,10 +185,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs) } #ifdef CONFIG_KEXEC_FILE -static int get_nr_ram_ranges_callback(unsigned long start_pfn, - unsigned long nr_pfn, void *arg) +static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg) { - int *nr_ranges = arg; + unsigned int *nr_ranges = arg; (*nr_ranges)++; return 0; @@ -214,7 +213,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced, ced->image = image; - walk_system_ram_range(0, -1, &nr_ranges, + walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); ced->max_nr_ranges = nr_ranges; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 6d0e62ae8516..39e585a554b7 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -506,3 +506,58 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) return randomize_range(mm->brk, range_end, 0) ? : mm->brk; } +/* + * Called from fs/proc with a reference on @p to find the function + * which called into schedule(). This needs to be done carefully + * because the task might wake up and we might look at a stack + * changing under us. + */ +unsigned long get_wchan(struct task_struct *p) +{ + unsigned long start, bottom, top, sp, fp, ip; + int count = 0; + + if (!p || p == current || p->state == TASK_RUNNING) + return 0; + + start = (unsigned long)task_stack_page(p); + if (!start) + return 0; + + /* + * Layout of the stack page: + * + * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long) + * PADDING + * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING + * stack + * ----------- bottom = start + sizeof(thread_info) + * thread_info + * ----------- start + * + * The tasks stack pointer points at the location where the + * framepointer is stored. The data on the stack is: + * ... IP FP ... IP FP + * + * We need to read FP and IP, so we need to adjust the upper + * bound by another unsigned long. + */ + top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; + top -= 2 * sizeof(unsigned long); + bottom = start + sizeof(struct thread_info); + + sp = READ_ONCE(p->thread.sp); + if (sp < bottom || sp > top) + return 0; + + fp = READ_ONCE(*(unsigned long *)sp); + do { + if (fp < bottom || fp > top) + return 0; + ip = READ_ONCE(*(unsigned long *)(fp + sizeof(unsigned long))); + if (!in_sched_functions(ip)) + return ip; + fp = READ_ONCE(*(unsigned long *)fp); + } while (count++ < 16 && p->state != TASK_RUNNING); + return 0; +} diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c13df2c735f8..737527b40e5b 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -324,31 +324,3 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } - -#define top_esp (THREAD_SIZE - sizeof(unsigned long)) -#define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long)) - -unsigned long get_wchan(struct task_struct *p) -{ - unsigned long bp, sp, ip; - unsigned long stack_page; - int count = 0; - if (!p || p == current || p->state == TASK_RUNNING) - return 0; - stack_page = (unsigned long)task_stack_page(p); - sp = p->thread.sp; - if (!stack_page || sp < stack_page || sp > top_esp+stack_page) - return 0; - /* include/asm-i386/system.h:switch_to() pushes bp last. */ - bp = *(unsigned long *) sp; - do { - if (bp < stack_page || bp > top_ebp+stack_page) - return 0; - ip = *(unsigned long *) (bp+4); - if (!in_sched_functions(ip)) - return ip; - bp = *(unsigned long *) bp; - } while (count++ < 16); - return 0; -} - diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3c1bbcf12924..b35921a670b2 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -499,30 +499,6 @@ void set_personality_ia32(bool x32) } EXPORT_SYMBOL_GPL(set_personality_ia32); -unsigned long get_wchan(struct task_struct *p) -{ - unsigned long stack; - u64 fp, ip; - int count = 0; - - if (!p || p == current || p->state == TASK_RUNNING) - return 0; - stack = (unsigned long)task_stack_page(p); - if (p->thread.sp < stack || p->thread.sp >= stack+THREAD_SIZE) - return 0; - fp = *(u64 *)(p->thread.sp); - do { - if (fp < (unsigned long)stack || - fp >= (unsigned long)stack+THREAD_SIZE) - return 0; - ip = *(u64 *)(fp+8); - if (!in_sched_functions(ip)) - return ip; - fp = *(u64 *)fp; - } while (count++ < 16); - return 0; -} - long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) { int ret = 0; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index b372a7557c16..9da95b9daf8d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2418,7 +2418,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) u64 val, cr0, cr4; u32 base3; u16 selector; - int i; + int i, r; for (i = 0; i < 16; i++) *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8); @@ -2460,13 +2460,17 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) dt.address = GET_SMSTATE(u64, smbase, 0x7e68); ctxt->ops->set_gdt(ctxt, &dt); + r = rsm_enter_protected_mode(ctxt, cr0, cr4); + if (r != X86EMUL_CONTINUE) + return r; + for (i = 0; i < 6; i++) { - int r = rsm_load_seg_64(ctxt, smbase, i); + r = rsm_load_seg_64(ctxt, smbase, i); if (r != X86EMUL_CONTINUE) return r; } - return rsm_enter_protected_mode(ctxt, cr0, cr4); + return X86EMUL_CONTINUE; } static int em_rsm(struct x86_emulate_ctxt *ctxt) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 06ef4908ba61..6a8bc64566ab 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4105,17 +4105,13 @@ static void seg_setup(int seg) static int alloc_apic_access_page(struct kvm *kvm) { struct page *page; - struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; mutex_lock(&kvm->slots_lock); if (kvm->arch.apic_access_page_done) goto out; - kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; - kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE; - kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __x86_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); if (r) goto out; @@ -4140,17 +4136,12 @@ static int alloc_identity_pagetable(struct kvm *kvm) { /* Called with kvm->slots_lock held. */ - struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; BUG_ON(kvm->arch.ept_identity_pagetable_done); - kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; - kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = - kvm->arch.ept_identity_map_addr; - kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __x86_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, + kvm->arch.ept_identity_map_addr, PAGE_SIZE); return r; } @@ -4949,14 +4940,9 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { int ret; - struct kvm_userspace_memory_region tss_mem = { - .slot = TSS_PRIVATE_MEMSLOT, - .guest_phys_addr = addr, - .memory_size = PAGE_SIZE * 3, - .flags = 0, - }; - ret = x86_set_memory_region(kvm, &tss_mem); + ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, + PAGE_SIZE * 3); if (ret) return ret; kvm->arch.tss_addr = addr; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 92511d4b7236..9a9a19830321 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6453,6 +6453,12 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) return 1; } +static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted); +} + static int vcpu_run(struct kvm_vcpu *vcpu) { int r; @@ -6461,8 +6467,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); for (;;) { - if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted) + if (kvm_vcpu_running(vcpu)) r = vcpu_enter_guest(vcpu); else r = vcpu_block(kvm, vcpu); @@ -7474,34 +7479,66 @@ void kvm_arch_sync_events(struct kvm *kvm) kvm_free_pit(kvm); } -int __x86_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem) +int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) { int i, r; + unsigned long hva; + struct kvm_memslots *slots = kvm_memslots(kvm); + struct kvm_memory_slot *slot, old; /* Called with kvm->slots_lock held. */ - BUG_ON(mem->slot >= KVM_MEM_SLOTS_NUM); + if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) + return -EINVAL; + + slot = id_to_memslot(slots, id); + if (size) { + if (WARN_ON(slot->npages)) + return -EEXIST; + + /* + * MAP_SHARED to prevent internal slot pages from being moved + * by fork()/COW. + */ + hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, 0); + if (IS_ERR((void *)hva)) + return PTR_ERR((void *)hva); + } else { + if (!slot->npages) + return 0; + hva = 0; + } + + old = *slot; for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_userspace_memory_region m = *mem; + struct kvm_userspace_memory_region m; - m.slot |= i << 16; + m.slot = id | (i << 16); + m.flags = 0; + m.guest_phys_addr = gpa; + m.userspace_addr = hva; + m.memory_size = size; r = __kvm_set_memory_region(kvm, &m); if (r < 0) return r; } + if (!size) { + r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); + WARN_ON(r < 0); + } + return 0; } EXPORT_SYMBOL_GPL(__x86_set_memory_region); -int x86_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem) +int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) { int r; mutex_lock(&kvm->slots_lock); - r = __x86_set_memory_region(kvm, mem); + r = __x86_set_memory_region(kvm, id, gpa, size); mutex_unlock(&kvm->slots_lock); return r; @@ -7516,16 +7553,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) * unless the the memory map has changed due to process exit * or fd copying. */ - struct kvm_userspace_memory_region mem; - memset(&mem, 0, sizeof(mem)); - mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; - x86_set_memory_region(kvm, &mem); - - mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; - x86_set_memory_region(kvm, &mem); - - mem.slot = TSS_PRIVATE_MEMSLOT; - x86_set_memory_region(kvm, &mem); + x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); + x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0); + x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); } kvm_iommu_unmap_guest(kvm); kfree(kvm->arch.vpic); @@ -7628,27 +7658,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { - /* - * Only private memory slots need to be mapped here since - * KVM_SET_MEMORY_REGION ioctl is no longer supported. - */ - if ((memslot->id >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_CREATE)) { - unsigned long userspace_addr; - - /* - * MAP_SHARED to prevent internal slot pages from being moved - * by fork()/COW. - */ - userspace_addr = vm_mmap(NULL, 0, memslot->npages * PAGE_SIZE, - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_ANONYMOUS, 0); - - if (IS_ERR((void *)userspace_addr)) - return PTR_ERR((void *)userspace_addr); - - memslot->userspace_addr = userspace_addr; - } - return 0; } @@ -7710,17 +7719,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, { int nr_mmu_pages = 0; - if (change == KVM_MR_DELETE && old->id >= KVM_USER_MEM_SLOTS) { - int ret; - - ret = vm_munmap(old->userspace_addr, - old->npages * PAGE_SIZE); - if (ret < 0) - printk(KERN_WARNING - "kvm_vm_ioctl_set_memory_region: " - "failed to munmap memory\n"); - } - if (!kvm->arch.n_requested_mmu_pages) nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); @@ -7769,19 +7767,36 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, kvm_mmu_invalidate_zap_all_pages(kvm); } +static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) +{ + if (!list_empty_careful(&vcpu->async_pf.done)) + return true; + + if (kvm_apic_has_events(vcpu)) + return true; + + if (vcpu->arch.pv.pv_unhalted) + return true; + + if (atomic_read(&vcpu->arch.nmi_queued)) + return true; + + if (test_bit(KVM_REQ_SMI, &vcpu->requests)) + return true; + + if (kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_has_interrupt(vcpu)) + return true; + + return false; +} + int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) kvm_x86_ops->check_nested_events(vcpu, false); - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted) - || !list_empty_careful(&vcpu->async_pf.done) - || kvm_apic_has_events(vcpu) - || vcpu->arch.pv.pv_unhalted - || atomic_read(&vcpu->arch.nmi_queued) || - (kvm_arch_interrupt_allowed(vcpu) && - kvm_cpu_has_interrupt(vcpu)); + return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 30564e2752d3..df48430c279b 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1132,7 +1132,7 @@ void mark_rodata_ro(void) * has been zapped already via cleanup_highmem(). */ all_end = roundup((unsigned long)_brk_end, PMD_SIZE); - set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT); + set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT); rodata_test(); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 1db84c0758b7..6a28ded74211 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -705,6 +705,70 @@ out: } /* + * Iterate the EFI memory map in reverse order because the regions + * will be mapped top-down. The end result is the same as if we had + * mapped things forward, but doesn't require us to change the + * existing implementation of efi_map_region(). + */ +static inline void *efi_map_next_entry_reverse(void *entry) +{ + /* Initial call */ + if (!entry) + return memmap.map_end - memmap.desc_size; + + entry -= memmap.desc_size; + if (entry < memmap.map) + return NULL; + + return entry; +} + +/* + * efi_map_next_entry - Return the next EFI memory map descriptor + * @entry: Previous EFI memory map descriptor + * + * This is a helper function to iterate over the EFI memory map, which + * we do in different orders depending on the current configuration. + * + * To begin traversing the memory map @entry must be %NULL. + * + * Returns %NULL when we reach the end of the memory map. + */ +static void *efi_map_next_entry(void *entry) +{ + if (!efi_enabled(EFI_OLD_MEMMAP) && efi_enabled(EFI_64BIT)) { + /* + * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE + * config table feature requires us to map all entries + * in the same order as they appear in the EFI memory + * map. That is to say, entry N must have a lower + * virtual address than entry N+1. This is because the + * firmware toolchain leaves relative references in + * the code/data sections, which are split and become + * separate EFI memory regions. Mapping things + * out-of-order leads to the firmware accessing + * unmapped addresses. + * + * Since we need to map things this way whether or not + * the kernel actually makes use of + * EFI_PROPERTIES_TABLE, let's just switch to this + * scheme by default for 64-bit. + */ + return efi_map_next_entry_reverse(entry); + } + + /* Initial call */ + if (!entry) + return memmap.map; + + entry += memmap.desc_size; + if (entry >= memmap.map_end) + return NULL; + + return entry; +} + +/* * Map the efi memory ranges of the runtime services and update new_mmap with * virtual addresses. */ @@ -714,7 +778,8 @@ static void * __init efi_map_regions(int *count, int *pg_shift) unsigned long left = 0; efi_memory_desc_t *md; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + p = NULL; + while ((p = efi_map_next_entry(p))) { md = p; if (!(md->attribute & EFI_MEMORY_RUNTIME)) { #ifdef CONFIG_X86_64 diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 30d12afe52ed..993b7a71386d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -33,6 +33,10 @@ #include <linux/memblock.h> #include <linux/edd.h> +#ifdef CONFIG_KEXEC_CORE +#include <linux/kexec.h> +#endif + #include <xen/xen.h> #include <xen/events.h> #include <xen/interface/xen.h> @@ -1077,6 +1081,7 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) /* Fast syscall setup is all done in hypercalls, so these are all ignored. Stub them out here to stop Xen console noise. */ + break; default: if (!pmu_msr_write(msr, low, high, &ret)) @@ -1807,6 +1812,21 @@ static struct notifier_block xen_hvm_cpu_notifier = { .notifier_call = xen_hvm_cpu_notify, }; +#ifdef CONFIG_KEXEC_CORE +static void xen_hvm_shutdown(void) +{ + native_machine_shutdown(); + if (kexec_in_progress) + xen_reboot(SHUTDOWN_soft_reset); +} + +static void xen_hvm_crash_shutdown(struct pt_regs *regs) +{ + native_machine_crash_shutdown(regs); + xen_reboot(SHUTDOWN_soft_reset); +} +#endif + static void __init xen_hvm_guest_init(void) { if (xen_pv_domain()) @@ -1826,6 +1846,10 @@ static void __init xen_hvm_guest_init(void) x86_init.irqs.intr_init = xen_init_IRQ; xen_hvm_init_time_ops(); xen_hvm_init_mmu_ops(); +#ifdef CONFIG_KEXEC_CORE + machine_ops.shutdown = xen_hvm_shutdown; + machine_ops.crash_shutdown = xen_hvm_crash_shutdown; +#endif } #endif diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index bfc08b13044b..660b3cfef234 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -112,6 +112,15 @@ static unsigned long *p2m_identity; static pte_t *p2m_missing_pte; static pte_t *p2m_identity_pte; +/* + * Hint at last populated PFN. + * + * Used to set HYPERVISOR_shared_info->arch.max_pfn so the toolstack + * can avoid scanning the whole P2M (which may be sized to account for + * hotplugged memory). + */ +static unsigned long xen_p2m_last_pfn; + static inline unsigned p2m_top_index(unsigned long pfn) { BUG_ON(pfn >= MAX_P2M_PFN); @@ -270,7 +279,7 @@ void xen_setup_mfn_list_list(void) else HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = virt_to_mfn(p2m_top_mfn); - HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn; + HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn; HYPERVISOR_shared_info->arch.p2m_generation = 0; HYPERVISOR_shared_info->arch.p2m_vaddr = (unsigned long)xen_p2m_addr; HYPERVISOR_shared_info->arch.p2m_cr3 = @@ -406,6 +415,8 @@ void __init xen_vmalloc_p2m_tree(void) static struct vm_struct vm; unsigned long p2m_limit; + xen_p2m_last_pfn = xen_max_p2m_pfn; + p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE; vm.flags = VM_ALLOC; vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit), @@ -608,6 +619,12 @@ static bool alloc_p2m(unsigned long pfn) free_p2m_page(p2m); } + /* Expanded the p2m? */ + if (pfn > xen_p2m_last_pfn) { + xen_p2m_last_pfn = pfn; + HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn; + } + return true; } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index f5ef6746d47a..1c30e4ab1022 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -548,7 +548,7 @@ static unsigned long __init xen_get_max_pages(void) { unsigned long max_pages, limit; domid_t domid = DOMID_SELF; - int ret; + long ret; limit = xen_get_pages_limit(); max_pages = limit; @@ -798,7 +798,7 @@ char * __init xen_memory_setup(void) xen_ignore_unusable(); /* Make sure the Xen-supplied memory map is well-ordered. */ - sanitize_e820_map(xen_e820_map, xen_e820_map_entries, + sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map), &xen_e820_map_entries); max_pages = xen_get_max_pages(); diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 63c223dff5f1..b56855a1382a 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -28,4 +28,5 @@ generic-y += statfs.h generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index 1e28ddb656b8..8764c241e5bb 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -31,7 +31,8 @@ static int get_first_sibling(unsigned int cpu) return cpu; } -int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues) +int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues, + const struct cpumask *online_mask) { unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling; cpumask_var_t cpus; @@ -41,7 +42,7 @@ int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues) cpumask_clear(cpus); nr_cpus = nr_uniq_cpus = 0; - for_each_online_cpu(i) { + for_each_cpu(i, online_mask) { nr_cpus++; first_sibling = get_first_sibling(i); if (!cpumask_test_cpu(first_sibling, cpus)) @@ -51,7 +52,7 @@ int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues) queue = 0; for_each_possible_cpu(i) { - if (!cpu_online(i)) { + if (!cpumask_test_cpu(i, online_mask)) { map[i] = 0; continue; } @@ -95,7 +96,7 @@ unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set) if (!map) return NULL; - if (!blk_mq_update_queue_map(map, set->nr_hw_queues)) + if (!blk_mq_update_queue_map(map, set->nr_hw_queues, cpu_online_mask)) return map; kfree(map); diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 279c5d674edf..788fffd9b409 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -229,8 +229,6 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page) unsigned int i, first = 1; ssize_t ret = 0; - blk_mq_disable_hotplug(); - for_each_cpu(i, hctx->cpumask) { if (first) ret += sprintf(ret + page, "%u", i); @@ -240,8 +238,6 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page) first = 0; } - blk_mq_enable_hotplug(); - ret += sprintf(ret + page, "\n"); return ret; } @@ -343,7 +339,7 @@ static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx) struct blk_mq_ctx *ctx; int i; - if (!hctx->nr_ctx || !(hctx->flags & BLK_MQ_F_SYSFS_UP)) + if (!hctx->nr_ctx) return; hctx_for_each_ctx(hctx, ctx, i) @@ -358,7 +354,7 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx) struct blk_mq_ctx *ctx; int i, ret; - if (!hctx->nr_ctx || !(hctx->flags & BLK_MQ_F_SYSFS_UP)) + if (!hctx->nr_ctx) return 0; ret = kobject_add(&hctx->kobj, &q->mq_kobj, "%u", hctx->queue_num); @@ -381,6 +377,8 @@ void blk_mq_unregister_disk(struct gendisk *disk) struct blk_mq_ctx *ctx; int i, j; + blk_mq_disable_hotplug(); + queue_for_each_hw_ctx(q, hctx, i) { blk_mq_unregister_hctx(hctx); @@ -395,6 +393,9 @@ void blk_mq_unregister_disk(struct gendisk *disk) kobject_put(&q->mq_kobj); kobject_put(&disk_to_dev(disk)->kobj); + + q->mq_sysfs_init_done = false; + blk_mq_enable_hotplug(); } static void blk_mq_sysfs_init(struct request_queue *q) @@ -425,27 +426,30 @@ int blk_mq_register_disk(struct gendisk *disk) struct blk_mq_hw_ctx *hctx; int ret, i; + blk_mq_disable_hotplug(); + blk_mq_sysfs_init(q); ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq"); if (ret < 0) - return ret; + goto out; kobject_uevent(&q->mq_kobj, KOBJ_ADD); queue_for_each_hw_ctx(q, hctx, i) { - hctx->flags |= BLK_MQ_F_SYSFS_UP; ret = blk_mq_register_hctx(hctx); if (ret) break; } - if (ret) { + if (ret) blk_mq_unregister_disk(disk); - return ret; - } + else + q->mq_sysfs_init_done = true; +out: + blk_mq_enable_hotplug(); - return 0; + return ret; } EXPORT_SYMBOL_GPL(blk_mq_register_disk); @@ -454,6 +458,9 @@ void blk_mq_sysfs_unregister(struct request_queue *q) struct blk_mq_hw_ctx *hctx; int i; + if (!q->mq_sysfs_init_done) + return; + queue_for_each_hw_ctx(q, hctx, i) blk_mq_unregister_hctx(hctx); } @@ -463,6 +470,9 @@ int blk_mq_sysfs_register(struct request_queue *q) struct blk_mq_hw_ctx *hctx; int i, ret = 0; + if (!q->mq_sysfs_init_done) + return ret; + queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_register_hctx(hctx); if (ret) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 9115c6d59948..ed96474d75cb 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -471,17 +471,30 @@ void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, } EXPORT_SYMBOL(blk_mq_all_tag_busy_iter); -void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn, +void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, void *priv) { - struct blk_mq_tags *tags = hctx->tags; + struct blk_mq_hw_ctx *hctx; + int i; + + + queue_for_each_hw_ctx(q, hctx, i) { + struct blk_mq_tags *tags = hctx->tags; + + /* + * If not software queues are currently mapped to this + * hardware queue, there's nothing to check + */ + if (!blk_mq_hw_queue_mapped(hctx)) + continue; + + if (tags->nr_reserved_tags) + bt_for_each(hctx, &tags->breserved_tags, 0, fn, priv, true); + bt_for_each(hctx, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv, + false); + } - if (tags->nr_reserved_tags) - bt_for_each(hctx, &tags->breserved_tags, 0, fn, priv, true); - bt_for_each(hctx, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv, - false); } -EXPORT_SYMBOL(blk_mq_tag_busy_iter); static unsigned int bt_unused_tags(struct blk_mq_bitmap_tags *bt) { diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 9eb2cf4f01cb..d468a79f2c4a 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -58,6 +58,8 @@ extern ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page); extern void blk_mq_tag_init_last_tag(struct blk_mq_tags *tags, unsigned int *last_tag); extern int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int depth); extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool); +void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, + void *priv); enum { BLK_MQ_TAG_CACHE_MIN = 1, diff --git a/block/blk-mq.c b/block/blk-mq.c index f2d67b4047a0..7785ae96267a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -393,14 +393,16 @@ void __blk_mq_complete_request(struct request *rq) * Ends all I/O on a request. It does not handle partial completions. * The actual completion happens out-of-order, through a IPI handler. **/ -void blk_mq_complete_request(struct request *rq) +void blk_mq_complete_request(struct request *rq, int error) { struct request_queue *q = rq->q; if (unlikely(blk_should_fake_timeout(q))) return; - if (!blk_mark_rq_complete(rq)) + if (!blk_mark_rq_complete(rq)) { + rq->errors = error; __blk_mq_complete_request(rq); + } } EXPORT_SYMBOL(blk_mq_complete_request); @@ -616,10 +618,8 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, * If a request wasn't started before the queue was * marked dying, kill it here or it'll go unnoticed. */ - if (unlikely(blk_queue_dying(rq->q))) { - rq->errors = -EIO; - blk_mq_complete_request(rq); - } + if (unlikely(blk_queue_dying(rq->q))) + blk_mq_complete_request(rq, -EIO); return; } if (rq->cmd_flags & REQ_NO_TIMEOUT) @@ -641,24 +641,16 @@ static void blk_mq_rq_timer(unsigned long priv) .next = 0, .next_set = 0, }; - struct blk_mq_hw_ctx *hctx; int i; - queue_for_each_hw_ctx(q, hctx, i) { - /* - * If not software queues are currently mapped to this - * hardware queue, there's nothing to check - */ - if (!blk_mq_hw_queue_mapped(hctx)) - continue; - - blk_mq_tag_busy_iter(hctx, blk_mq_check_expired, &data); - } + blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data); if (data.next_set) { data.next = blk_rq_timeout(round_jiffies_up(data.next)); mod_timer(&q->timeout, data.next); } else { + struct blk_mq_hw_ctx *hctx; + queue_for_each_hw_ctx(q, hctx, i) { /* the hctx may be unmapped, so check it here */ if (blk_mq_hw_queue_mapped(hctx)) @@ -1789,13 +1781,19 @@ static void blk_mq_init_cpu_queues(struct request_queue *q, } } -static void blk_mq_map_swqueue(struct request_queue *q) +static void blk_mq_map_swqueue(struct request_queue *q, + const struct cpumask *online_mask) { unsigned int i; struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; struct blk_mq_tag_set *set = q->tag_set; + /* + * Avoid others reading imcomplete hctx->cpumask through sysfs + */ + mutex_lock(&q->sysfs_lock); + queue_for_each_hw_ctx(q, hctx, i) { cpumask_clear(hctx->cpumask); hctx->nr_ctx = 0; @@ -1806,16 +1804,17 @@ static void blk_mq_map_swqueue(struct request_queue *q) */ queue_for_each_ctx(q, ctx, i) { /* If the cpu isn't online, the cpu is mapped to first hctx */ - if (!cpu_online(i)) + if (!cpumask_test_cpu(i, online_mask)) continue; hctx = q->mq_ops->map_queue(q, i); cpumask_set_cpu(i, hctx->cpumask); - cpumask_set_cpu(i, hctx->tags->cpumask); ctx->index_hw = hctx->nr_ctx; hctx->ctxs[hctx->nr_ctx++] = ctx; } + mutex_unlock(&q->sysfs_lock); + queue_for_each_hw_ctx(q, hctx, i) { struct blk_mq_ctxmap *map = &hctx->ctx_map; @@ -1851,6 +1850,14 @@ static void blk_mq_map_swqueue(struct request_queue *q) hctx->next_cpu = cpumask_first(hctx->cpumask); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } + + queue_for_each_ctx(q, ctx, i) { + if (!cpumask_test_cpu(i, online_mask)) + continue; + + hctx = q->mq_ops->map_queue(q, i); + cpumask_set_cpu(i, hctx->tags->cpumask); + } } static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set) @@ -1918,6 +1925,9 @@ void blk_mq_release(struct request_queue *q) kfree(hctx); } + kfree(q->mq_map); + q->mq_map = NULL; + kfree(q->queue_hw_ctx); /* ctx kobj stays in queue_ctx */ @@ -2027,13 +2037,15 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, if (blk_mq_init_hw_queues(q, set)) goto err_hctxs; + get_online_cpus(); mutex_lock(&all_q_mutex); - list_add_tail(&q->all_q_node, &all_q_list); - mutex_unlock(&all_q_mutex); + list_add_tail(&q->all_q_node, &all_q_list); blk_mq_add_queue_tag_set(set, q); + blk_mq_map_swqueue(q, cpu_online_mask); - blk_mq_map_swqueue(q); + mutex_unlock(&all_q_mutex); + put_online_cpus(); return q; @@ -2057,30 +2069,27 @@ void blk_mq_free_queue(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; + mutex_lock(&all_q_mutex); + list_del_init(&q->all_q_node); + mutex_unlock(&all_q_mutex); + blk_mq_del_queue_tag_set(q); blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); blk_mq_free_hw_queues(q, set); percpu_ref_exit(&q->mq_usage_counter); - - kfree(q->mq_map); - - q->mq_map = NULL; - - mutex_lock(&all_q_mutex); - list_del_init(&q->all_q_node); - mutex_unlock(&all_q_mutex); } /* Basically redo blk_mq_init_queue with queue frozen */ -static void blk_mq_queue_reinit(struct request_queue *q) +static void blk_mq_queue_reinit(struct request_queue *q, + const struct cpumask *online_mask) { WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth)); blk_mq_sysfs_unregister(q); - blk_mq_update_queue_map(q->mq_map, q->nr_hw_queues); + blk_mq_update_queue_map(q->mq_map, q->nr_hw_queues, online_mask); /* * redo blk_mq_init_cpu_queues and blk_mq_init_hw_queues. FIXME: maybe @@ -2088,7 +2097,7 @@ static void blk_mq_queue_reinit(struct request_queue *q) * involves free and re-allocate memory, worthy doing?) */ - blk_mq_map_swqueue(q); + blk_mq_map_swqueue(q, online_mask); blk_mq_sysfs_register(q); } @@ -2097,16 +2106,43 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb, unsigned long action, void *hcpu) { struct request_queue *q; + int cpu = (unsigned long)hcpu; + /* + * New online cpumask which is going to be set in this hotplug event. + * Declare this cpumasks as global as cpu-hotplug operation is invoked + * one-by-one and dynamically allocating this could result in a failure. + */ + static struct cpumask online_new; /* - * Before new mappings are established, hotadded cpu might already - * start handling requests. This doesn't break anything as we map - * offline CPUs to first hardware queue. We will re-init the queue - * below to get optimal settings. + * Before hotadded cpu starts handling requests, new mappings must + * be established. Otherwise, these requests in hw queue might + * never be dispatched. + * + * For example, there is a single hw queue (hctx) and two CPU queues + * (ctx0 for CPU0, and ctx1 for CPU1). + * + * Now CPU1 is just onlined and a request is inserted into + * ctx1->rq_list and set bit0 in pending bitmap as ctx1->index_hw is + * still zero. + * + * And then while running hw queue, flush_busy_ctxs() finds bit0 is + * set in pending bitmap and tries to retrieve requests in + * hctx->ctxs[0]->rq_list. But htx->ctxs[0] is a pointer to ctx0, + * so the request in ctx1->rq_list is ignored. */ - if (action != CPU_DEAD && action != CPU_DEAD_FROZEN && - action != CPU_ONLINE && action != CPU_ONLINE_FROZEN) + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DEAD: + case CPU_UP_CANCELED: + cpumask_copy(&online_new, cpu_online_mask); + break; + case CPU_UP_PREPARE: + cpumask_copy(&online_new, cpu_online_mask); + cpumask_set_cpu(cpu, &online_new); + break; + default: return NOTIFY_OK; + } mutex_lock(&all_q_mutex); @@ -2130,7 +2166,7 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb, } list_for_each_entry(q, &all_q_list, all_q_node) - blk_mq_queue_reinit(q); + blk_mq_queue_reinit(q, &online_new); list_for_each_entry(q, &all_q_list, all_q_node) blk_mq_unfreeze_queue(q); diff --git a/block/blk-mq.h b/block/blk-mq.h index 6a48c4c0d8a2..f4fea7964910 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -51,7 +51,8 @@ void blk_mq_disable_hotplug(void); * CPU -> queue mappings */ extern unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set); -extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues); +extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues, + const struct cpumask *online_mask); extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int); /* diff --git a/crypto/ahash.c b/crypto/ahash.c index 8acb886032ae..9c1dc8d6106a 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -544,7 +544,8 @@ static int ahash_prepare_alg(struct ahash_alg *alg) struct crypto_alg *base = &alg->halg.base; if (alg->halg.digestsize > PAGE_SIZE / 8 || - alg->halg.statesize > PAGE_SIZE / 8) + alg->halg.statesize > PAGE_SIZE / 8 || + alg->halg.statesize == 0) return -EINVAL; base->cra_type = &crypto_ahash_type; diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h index 09f37b516808..4dde37c3d8fc 100644 --- a/drivers/acpi/acpica/acglobal.h +++ b/drivers/acpi/acpica/acglobal.h @@ -61,6 +61,7 @@ ACPI_GLOBAL(struct acpi_table_header, acpi_gbl_original_dsdt_header); ACPI_INIT_GLOBAL(u32, acpi_gbl_dsdt_index, ACPI_INVALID_TABLE_INDEX); ACPI_INIT_GLOBAL(u32, acpi_gbl_facs_index, ACPI_INVALID_TABLE_INDEX); ACPI_INIT_GLOBAL(u32, acpi_gbl_xfacs_index, ACPI_INVALID_TABLE_INDEX); +ACPI_INIT_GLOBAL(u32, acpi_gbl_fadt_index, ACPI_INVALID_TABLE_INDEX); #if (!ACPI_REDUCED_HARDWARE) ACPI_GLOBAL(struct acpi_table_facs *, acpi_gbl_FACS); diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h index f7731f260c31..591ea95319e2 100644 --- a/drivers/acpi/acpica/actables.h +++ b/drivers/acpi/acpica/actables.h @@ -85,7 +85,7 @@ void acpi_tb_set_table_loaded_flag(u32 table_index, u8 is_loaded); /* * tbfadt - FADT parse/convert/validate */ -void acpi_tb_parse_fadt(u32 table_index); +void acpi_tb_parse_fadt(void); void acpi_tb_create_local_fadt(struct acpi_table_header *table, u32 length); @@ -138,8 +138,6 @@ acpi_status acpi_tb_get_owner_id(u32 table_index, acpi_owner_id *owner_id); */ acpi_status acpi_tb_initialize_facs(void); -u8 acpi_tb_tables_loaded(void); - void acpi_tb_print_table_header(acpi_physical_address address, struct acpi_table_header *header); diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c index faad911d46b5..10ce48e16ebf 100644 --- a/drivers/acpi/acpica/evxfevnt.c +++ b/drivers/acpi/acpica/evxfevnt.c @@ -71,7 +71,7 @@ acpi_status acpi_enable(void) /* ACPI tables must be present */ - if (!acpi_tb_tables_loaded()) { + if (acpi_gbl_fadt_index == ACPI_INVALID_TABLE_INDEX) { return_ACPI_STATUS(AE_NO_ACPI_TABLES); } diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c index 455a0700db39..a6454f4a6fb3 100644 --- a/drivers/acpi/acpica/tbfadt.c +++ b/drivers/acpi/acpica/tbfadt.c @@ -298,7 +298,7 @@ acpi_tb_select_address(char *register_name, u32 address32, u64 address64) * * FUNCTION: acpi_tb_parse_fadt * - * PARAMETERS: table_index - Index for the FADT + * PARAMETERS: None * * RETURN: None * @@ -307,7 +307,7 @@ acpi_tb_select_address(char *register_name, u32 address32, u64 address64) * ******************************************************************************/ -void acpi_tb_parse_fadt(u32 table_index) +void acpi_tb_parse_fadt(void) { u32 length; struct acpi_table_header *table; @@ -319,11 +319,11 @@ void acpi_tb_parse_fadt(u32 table_index) * Get a local copy of the FADT and convert it to a common format * Map entire FADT, assumed to be smaller than one page. */ - length = acpi_gbl_root_table_list.tables[table_index].length; + length = acpi_gbl_root_table_list.tables[acpi_gbl_fadt_index].length; table = - acpi_os_map_memory(acpi_gbl_root_table_list.tables[table_index]. - address, length); + acpi_os_map_memory(acpi_gbl_root_table_list. + tables[acpi_gbl_fadt_index].address, length); if (!table) { return; } diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c index 4337990127cc..d8ddef38c947 100644 --- a/drivers/acpi/acpica/tbutils.c +++ b/drivers/acpi/acpica/tbutils.c @@ -99,29 +99,6 @@ acpi_status acpi_tb_initialize_facs(void) /******************************************************************************* * - * FUNCTION: acpi_tb_tables_loaded - * - * PARAMETERS: None - * - * RETURN: TRUE if required ACPI tables are loaded - * - * DESCRIPTION: Determine if the minimum required ACPI tables are present - * (FADT, FACS, DSDT) - * - ******************************************************************************/ - -u8 acpi_tb_tables_loaded(void) -{ - - if (acpi_gbl_root_table_list.current_table_count >= 4) { - return (TRUE); - } - - return (FALSE); -} - -/******************************************************************************* - * * FUNCTION: acpi_tb_check_dsdt_header * * PARAMETERS: None @@ -392,7 +369,8 @@ acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address) ACPI_COMPARE_NAME(&acpi_gbl_root_table_list. tables[table_index].signature, ACPI_SIG_FADT)) { - acpi_tb_parse_fadt(table_index); + acpi_gbl_fadt_index = table_index; + acpi_tb_parse_fadt(); } next_table: diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c index 2a4154a09e4d..85e17bacc834 100644 --- a/drivers/base/power/domain_governor.c +++ b/drivers/base/power/domain_governor.c @@ -77,13 +77,16 @@ static bool default_stop_ok(struct device *dev) dev_update_qos_constraint); if (constraint_ns > 0) { - constraint_ns -= td->start_latency_ns; + constraint_ns -= td->save_state_latency_ns + + td->stop_latency_ns + + td->start_latency_ns + + td->restore_state_latency_ns; if (constraint_ns == 0) return false; } td->effective_constraint_ns = constraint_ns; - td->cached_stop_ok = constraint_ns > td->stop_latency_ns || - constraint_ns == 0; + td->cached_stop_ok = constraint_ns >= 0; + /* * The children have been suspended already, so we don't need to take * their stop latencies into account here. @@ -126,18 +129,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) off_on_time_ns = genpd->power_off_latency_ns + genpd->power_on_latency_ns; - /* - * It doesn't make sense to remove power from the domain if saving - * the state of all devices in it and the power off/power on operations - * take too much time. - * - * All devices in this domain have been stopped already at this point. - */ - list_for_each_entry(pdd, &genpd->dev_list, list_node) { - if (pdd->dev->driver) - off_on_time_ns += - to_gpd_data(pdd)->td.save_state_latency_ns; - } min_off_time_ns = -1; /* @@ -193,7 +184,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) * constraint_ns cannot be negative here, because the device has * been suspended. */ - constraint_ns -= td->restore_state_latency_ns; if (constraint_ns <= off_on_time_ns) return false; diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index f42f2bac6466..4c55cfbad19e 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -32,8 +32,7 @@ static DEFINE_MUTEX(regmap_debugfs_early_lock); /* Calculate the length of a fixed format */ static size_t regmap_calc_reg_len(int max_val, char *buf, size_t buf_size) { - snprintf(buf, buf_size, "%x", max_val); - return strlen(buf); + return snprintf(NULL, 0, "%x", max_val); } static ssize_t regmap_name_read_file(struct file *file, @@ -432,7 +431,7 @@ static ssize_t regmap_access_read_file(struct file *file, /* If we're in the region the user is trying to read */ if (p >= *ppos) { /* ...but not beyond it */ - if (buf_pos >= count - 1 - tot_len) + if (buf_pos + tot_len + 1 >= count) break; /* Format the register */ diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f9889b6bc02c..674f800a3b57 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1486,17 +1486,16 @@ static void loop_handle_cmd(struct loop_cmd *cmd) { const bool write = cmd->rq->cmd_flags & REQ_WRITE; struct loop_device *lo = cmd->rq->q->queuedata; - int ret = -EIO; + int ret = 0; - if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) + if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) { + ret = -EIO; goto failed; + } ret = do_req_filebacked(lo, cmd->rq); - failed: - if (ret) - cmd->rq->errors = -EIO; - blk_mq_complete_request(cmd->rq); + blk_mq_complete_request(cmd->rq, ret ? -EIO : 0); } static void loop_queue_write_work(struct work_struct *work) diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index a295b98c6bae..1c9e4fe5aa44 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -289,7 +289,7 @@ static inline void null_handle_cmd(struct nullb_cmd *cmd) case NULL_IRQ_SOFTIRQ: switch (queue_mode) { case NULL_Q_MQ: - blk_mq_complete_request(cmd->rq); + blk_mq_complete_request(cmd->rq, cmd->rq->errors); break; case NULL_Q_RQ: blk_complete_request(cmd->rq); diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index b97fc3fe0916..6f04771f1019 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -618,16 +618,15 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx, spin_unlock_irqrestore(req->q->queue_lock, flags); return; } + if (req->cmd_type == REQ_TYPE_DRV_PRIV) { if (cmd_rq->ctx == CMD_CTX_CANCELLED) - req->errors = -EINTR; - else - req->errors = status; + status = -EINTR; } else { - req->errors = nvme_error_status(status); + status = nvme_error_status(status); } - } else - req->errors = 0; + } + if (req->cmd_type == REQ_TYPE_DRV_PRIV) { u32 result = le32_to_cpup(&cqe->result); req->special = (void *)(uintptr_t)result; @@ -650,7 +649,7 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx, } nvme_free_iod(nvmeq->dev, iod); - blk_mq_complete_request(req); + blk_mq_complete_request(req, status); } /* length is in bytes. gfp flags indicates whether we may sleep. */ @@ -863,8 +862,7 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, if (ns && ns->ms && !blk_integrity_rq(req)) { if (!(ns->pi_type && ns->ms == 8) && req->cmd_type != REQ_TYPE_DRV_PRIV) { - req->errors = -EFAULT; - blk_mq_complete_request(req); + blk_mq_complete_request(req, -EFAULT); return BLK_MQ_RQ_QUEUE_OK; } } @@ -2439,6 +2437,22 @@ static void nvme_scan_namespaces(struct nvme_dev *dev, unsigned nn) list_sort(NULL, &dev->namespaces, ns_cmp); } +static void nvme_set_irq_hints(struct nvme_dev *dev) +{ + struct nvme_queue *nvmeq; + int i; + + for (i = 0; i < dev->online_queues; i++) { + nvmeq = dev->queues[i]; + + if (!nvmeq->tags || !(*nvmeq->tags)) + continue; + + irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector, + blk_mq_tags_cpumask(*nvmeq->tags)); + } +} + static void nvme_dev_scan(struct work_struct *work) { struct nvme_dev *dev = container_of(work, struct nvme_dev, scan_work); @@ -2450,6 +2464,7 @@ static void nvme_dev_scan(struct work_struct *work) return; nvme_scan_namespaces(dev, le32_to_cpup(&ctrl->nn)); kfree(ctrl); + nvme_set_irq_hints(dev); } /* @@ -2953,22 +2968,6 @@ static const struct file_operations nvme_dev_fops = { .compat_ioctl = nvme_dev_ioctl, }; -static void nvme_set_irq_hints(struct nvme_dev *dev) -{ - struct nvme_queue *nvmeq; - int i; - - for (i = 0; i < dev->online_queues; i++) { - nvmeq = dev->queues[i]; - - if (!nvmeq->tags || !(*nvmeq->tags)) - continue; - - irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector, - blk_mq_tags_cpumask(*nvmeq->tags)); - } -} - static int nvme_dev_start(struct nvme_dev *dev) { int result; @@ -3010,8 +3009,6 @@ static int nvme_dev_start(struct nvme_dev *dev) if (result) goto free_tags; - nvme_set_irq_hints(dev); - dev->event_limit = 1; return result; @@ -3062,7 +3059,6 @@ static int nvme_dev_resume(struct nvme_dev *dev) } else { nvme_unfreeze_queues(dev); nvme_dev_add(dev); - nvme_set_irq_hints(dev); } return 0; } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index d93a0372b37b..f5e49b639818 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -1863,9 +1863,11 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req, rbd_osd_read_callback(obj_request); break; case CEPH_OSD_OP_SETALLOCHINT: - rbd_assert(osd_req->r_ops[1].op == CEPH_OSD_OP_WRITE); + rbd_assert(osd_req->r_ops[1].op == CEPH_OSD_OP_WRITE || + osd_req->r_ops[1].op == CEPH_OSD_OP_WRITEFULL); /* fall through */ case CEPH_OSD_OP_WRITE: + case CEPH_OSD_OP_WRITEFULL: rbd_osd_write_callback(obj_request); break; case CEPH_OSD_OP_STAT: @@ -2401,7 +2403,10 @@ static void rbd_img_obj_request_fill(struct rbd_obj_request *obj_request, opcode = CEPH_OSD_OP_ZERO; } } else if (op_type == OBJ_OP_WRITE) { - opcode = CEPH_OSD_OP_WRITE; + if (!offset && length == object_size) + opcode = CEPH_OSD_OP_WRITEFULL; + else + opcode = CEPH_OSD_OP_WRITE; osd_req_op_alloc_hint_init(osd_request, num_ops, object_size, object_size); num_ops++; @@ -3760,6 +3765,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) /* set io sizes to object size */ segment_size = rbd_obj_bytes(&rbd_dev->header); blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE); + q->limits.max_sectors = queue_max_hw_sectors(q); blk_queue_max_segments(q, segment_size / SECTOR_SIZE); blk_queue_max_segment_size(q, segment_size); blk_queue_io_min(q, segment_size); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index e93899cc6f60..6ca35495a5be 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -144,7 +144,7 @@ static void virtblk_done(struct virtqueue *vq) do { virtqueue_disable_cb(vq); while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) { - blk_mq_complete_request(vbr->req); + blk_mq_complete_request(vbr->req, vbr->req->errors); req_done = true; } if (unlikely(virtqueue_is_broken(vq))) diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index deb3f001791f..767657565de6 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -212,6 +212,9 @@ static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t *gref, static int xen_blkif_disconnect(struct xen_blkif *blkif) { + struct pending_req *req, *n; + int i = 0, j; + if (blkif->xenblkd) { kthread_stop(blkif->xenblkd); wake_up(&blkif->shutdown_wq); @@ -238,13 +241,28 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) /* Remove all persistent grants and the cache of ballooned pages. */ xen_blkbk_free_caches(blkif); + /* Check that there is no request in use */ + list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) { + list_del(&req->free_list); + + for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) + kfree(req->segments[j]); + + for (j = 0; j < MAX_INDIRECT_PAGES; j++) + kfree(req->indirect_pages[j]); + + kfree(req); + i++; + } + + WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages)); + blkif->nr_ring_pages = 0; + return 0; } static void xen_blkif_free(struct xen_blkif *blkif) { - struct pending_req *req, *n; - int i = 0, j; xen_blkif_disconnect(blkif); xen_vbd_free(&blkif->vbd); @@ -257,22 +275,6 @@ static void xen_blkif_free(struct xen_blkif *blkif) BUG_ON(!list_empty(&blkif->free_pages)); BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts)); - /* Check that there is no request in use */ - list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) { - list_del(&req->free_list); - - for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) - kfree(req->segments[j]); - - for (j = 0; j < MAX_INDIRECT_PAGES; j++) - kfree(req->indirect_pages[j]); - - kfree(req); - i++; - } - - WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages)); - kmem_cache_free(xen_blkif_cachep, blkif); } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 0823a96902f8..611170896b8c 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1142,6 +1142,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) RING_IDX i, rp; unsigned long flags; struct blkfront_info *info = (struct blkfront_info *)dev_id; + int error; spin_lock_irqsave(&info->io_lock, flags); @@ -1182,37 +1183,37 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) continue; } - req->errors = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO; + error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO; switch (bret->operation) { case BLKIF_OP_DISCARD: if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) { struct request_queue *rq = info->rq; printk(KERN_WARNING "blkfront: %s: %s op failed\n", info->gd->disk_name, op_name(bret->operation)); - req->errors = -EOPNOTSUPP; + error = -EOPNOTSUPP; info->feature_discard = 0; info->feature_secdiscard = 0; queue_flag_clear(QUEUE_FLAG_DISCARD, rq); queue_flag_clear(QUEUE_FLAG_SECDISCARD, rq); } - blk_mq_complete_request(req); + blk_mq_complete_request(req, error); break; case BLKIF_OP_FLUSH_DISKCACHE: case BLKIF_OP_WRITE_BARRIER: if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) { printk(KERN_WARNING "blkfront: %s: %s op failed\n", info->gd->disk_name, op_name(bret->operation)); - req->errors = -EOPNOTSUPP; + error = -EOPNOTSUPP; } if (unlikely(bret->status == BLKIF_RSP_ERROR && info->shadow[id].req.u.rw.nr_segments == 0)) { printk(KERN_WARNING "blkfront: %s: empty %s op failed\n", info->gd->disk_name, op_name(bret->operation)); - req->errors = -EOPNOTSUPP; + error = -EOPNOTSUPP; } - if (unlikely(req->errors)) { - if (req->errors == -EOPNOTSUPP) - req->errors = 0; + if (unlikely(error)) { + if (error == -EOPNOTSUPP) + error = 0; info->feature_flush = 0; xlvbd_flush(info); } @@ -1223,7 +1224,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) dev_dbg(&info->xbdev->dev, "Bad return from blkdev data " "request: %x\n", bret->status); - blk_mq_complete_request(req); + blk_mq_complete_request(req, error); break; default: BUG(); diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig index 1a82f3a17681..0ebca8ba7bc4 100644 --- a/drivers/bus/Kconfig +++ b/drivers/bus/Kconfig @@ -36,7 +36,6 @@ config ARM_CCI400_PORT_CTRL config ARM_CCI500_PMU bool "ARM CCI500 PMU support" - default y depends on (ARM && CPU_V7) || ARM64 depends on PERF_EVENTS select ARM_CCI_PMU diff --git a/drivers/clk/mvebu/clk-cpu.c b/drivers/clk/mvebu/clk-cpu.c index 5837eb8a212f..85da8b983256 100644 --- a/drivers/clk/mvebu/clk-cpu.c +++ b/drivers/clk/mvebu/clk-cpu.c @@ -197,6 +197,7 @@ static void __init of_cpu_clk_setup(struct device_node *node) for_each_node_by_type(dn, "cpu") { struct clk_init_data init; struct clk *clk; + struct clk *parent_clk; char *clk_name = kzalloc(5, GFP_KERNEL); int cpu, err; @@ -208,8 +209,9 @@ static void __init of_cpu_clk_setup(struct device_node *node) goto bail_out; sprintf(clk_name, "cpu%d", cpu); + parent_clk = of_clk_get(node, 0); - cpuclk[cpu].parent_name = of_clk_get_parent_name(node, 0); + cpuclk[cpu].parent_name = __clk_get_name(parent_clk); cpuclk[cpu].clk_name = clk_name; cpuclk[cpu].cpu = cpu; cpuclk[cpu].reg_base = clock_complex_base; diff --git a/drivers/clk/samsung/clk-cpu.c b/drivers/clk/samsung/clk-cpu.c index 7c1e1f58e2da..2fe37f708dc7 100644 --- a/drivers/clk/samsung/clk-cpu.c +++ b/drivers/clk/samsung/clk-cpu.c @@ -164,7 +164,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata, * the values for DIV_COPY and DIV_HPM dividers need not be set. */ div0 = cfg_data->div0; - if (test_bit(CLK_CPU_HAS_DIV1, &cpuclk->flags)) { + if (cpuclk->flags & CLK_CPU_HAS_DIV1) { div1 = cfg_data->div1; if (readl(base + E4210_SRC_CPU) & E4210_MUX_HPM_MASK) div1 = readl(base + E4210_DIV_CPU1) & @@ -185,7 +185,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata, alt_div = DIV_ROUND_UP(alt_prate, tmp_rate) - 1; WARN_ON(alt_div >= MAX_DIV); - if (test_bit(CLK_CPU_NEEDS_DEBUG_ALT_DIV, &cpuclk->flags)) { + if (cpuclk->flags & CLK_CPU_NEEDS_DEBUG_ALT_DIV) { /* * In Exynos4210, ATB clock parent is also mout_core. So * ATB clock also needs to be mantained at safe speed. @@ -206,7 +206,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata, writel(div0, base + E4210_DIV_CPU0); wait_until_divider_stable(base + E4210_DIV_STAT_CPU0, DIV_MASK_ALL); - if (test_bit(CLK_CPU_HAS_DIV1, &cpuclk->flags)) { + if (cpuclk->flags & CLK_CPU_HAS_DIV1) { writel(div1, base + E4210_DIV_CPU1); wait_until_divider_stable(base + E4210_DIV_STAT_CPU1, DIV_MASK_ALL); @@ -225,7 +225,7 @@ static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata, unsigned long mux_reg; /* find out the divider values to use for clock data */ - if (test_bit(CLK_CPU_NEEDS_DEBUG_ALT_DIV, &cpuclk->flags)) { + if (cpuclk->flags & CLK_CPU_NEEDS_DEBUG_ALT_DIV) { while ((cfg_data->prate * 1000) != ndata->new_rate) { if (cfg_data->prate == 0) return -EINVAL; @@ -240,7 +240,7 @@ static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata, writel(mux_reg & ~(1 << 16), base + E4210_SRC_CPU); wait_until_mux_stable(base + E4210_STAT_CPU, 16, 1); - if (test_bit(CLK_CPU_NEEDS_DEBUG_ALT_DIV, &cpuclk->flags)) { + if (cpuclk->flags & CLK_CPU_NEEDS_DEBUG_ALT_DIV) { div |= (cfg_data->div0 & E4210_DIV0_ATB_MASK); div_mask |= E4210_DIV0_ATB_MASK; } diff --git a/drivers/clk/ti/clk-3xxx.c b/drivers/clk/ti/clk-3xxx.c index 676ee8f6d813..8831e1a05367 100644 --- a/drivers/clk/ti/clk-3xxx.c +++ b/drivers/clk/ti/clk-3xxx.c @@ -374,7 +374,6 @@ static struct ti_dt_clk omap3xxx_clks[] = { DT_CLK(NULL, "gpio2_ick", "gpio2_ick"), DT_CLK(NULL, "wdt3_ick", "wdt3_ick"), DT_CLK(NULL, "uart3_ick", "uart3_ick"), - DT_CLK(NULL, "uart4_ick", "uart4_ick"), DT_CLK(NULL, "gpt9_ick", "gpt9_ick"), DT_CLK(NULL, "gpt8_ick", "gpt8_ick"), DT_CLK(NULL, "gpt7_ick", "gpt7_ick"), @@ -519,6 +518,7 @@ static struct ti_dt_clk am35xx_clks[] = { static struct ti_dt_clk omap36xx_clks[] = { DT_CLK(NULL, "omap_192m_alwon_fck", "omap_192m_alwon_fck"), DT_CLK(NULL, "uart4_fck", "uart4_fck"), + DT_CLK(NULL, "uart4_ick", "uart4_ick"), { .node_name = NULL }, }; diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c index 9b5b289e6334..a911d7de3377 100644 --- a/drivers/clk/ti/clk-7xx.c +++ b/drivers/clk/ti/clk-7xx.c @@ -18,7 +18,6 @@ #include "clock.h" -#define DRA7_DPLL_ABE_DEFFREQ 180633600 #define DRA7_DPLL_GMAC_DEFFREQ 1000000000 #define DRA7_DPLL_USB_DEFFREQ 960000000 @@ -313,27 +312,12 @@ static struct ti_dt_clk dra7xx_clks[] = { int __init dra7xx_dt_clk_init(void) { int rc; - struct clk *abe_dpll_mux, *sys_clkin2, *dpll_ck, *hdcp_ck; + struct clk *dpll_ck, *hdcp_ck; ti_dt_clocks_register(dra7xx_clks); omap2_clk_disable_autoidle_all(); - abe_dpll_mux = clk_get_sys(NULL, "abe_dpll_sys_clk_mux"); - sys_clkin2 = clk_get_sys(NULL, "sys_clkin2"); - dpll_ck = clk_get_sys(NULL, "dpll_abe_ck"); - - rc = clk_set_parent(abe_dpll_mux, sys_clkin2); - if (!rc) - rc = clk_set_rate(dpll_ck, DRA7_DPLL_ABE_DEFFREQ); - if (rc) - pr_err("%s: failed to configure ABE DPLL!\n", __func__); - - dpll_ck = clk_get_sys(NULL, "dpll_abe_m2x2_ck"); - rc = clk_set_rate(dpll_ck, DRA7_DPLL_ABE_DEFFREQ * 2); - if (rc) - pr_err("%s: failed to configure ABE DPLL m2x2!\n", __func__); - dpll_ck = clk_get_sys(NULL, "dpll_gmac_ck"); rc = clk_set_rate(dpll_ck, DRA7_DPLL_GMAC_DEFFREQ); if (rc) diff --git a/drivers/clk/ti/clkt_dflt.c b/drivers/clk/ti/clkt_dflt.c index 90d7d8a21c49..1ddc288fce4e 100644 --- a/drivers/clk/ti/clkt_dflt.c +++ b/drivers/clk/ti/clkt_dflt.c @@ -222,7 +222,7 @@ int omap2_dflt_clk_enable(struct clk_hw *hw) } } - if (unlikely(!clk->enable_reg)) { + if (unlikely(IS_ERR(clk->enable_reg))) { pr_err("%s: %s missing enable_reg\n", __func__, clk_hw_get_name(hw)); ret = -EINVAL; @@ -264,7 +264,7 @@ void omap2_dflt_clk_disable(struct clk_hw *hw) u32 v; clk = to_clk_hw_omap(hw); - if (!clk->enable_reg) { + if (IS_ERR(clk->enable_reg)) { /* * 'independent' here refers to a clock which is not * controlled by its parent. diff --git a/drivers/clocksource/rockchip_timer.c b/drivers/clocksource/rockchip_timer.c index bb2c2b050964..d3c1742ded1a 100644 --- a/drivers/clocksource/rockchip_timer.c +++ b/drivers/clocksource/rockchip_timer.c @@ -148,7 +148,7 @@ static void __init rk_timer_init(struct device_node *np) bc_timer.freq = clk_get_rate(timer_clk); irq = irq_of_parse_and_map(np, 0); - if (irq == NO_IRQ) { + if (!irq) { pr_err("Failed to map interrupts for '%s'\n", TIMER_NAME); return; } diff --git a/drivers/clocksource/timer-keystone.c b/drivers/clocksource/timer-keystone.c index edacf3902e10..1cea08cf603e 100644 --- a/drivers/clocksource/timer-keystone.c +++ b/drivers/clocksource/timer-keystone.c @@ -152,7 +152,7 @@ static void __init keystone_timer_init(struct device_node *np) int irq, error; irq = irq_of_parse_and_map(np, 0); - if (irq == NO_IRQ) { + if (!irq) { pr_err("%s: failed to map interrupts\n", __func__); return; } diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 798277227de7..cec1ee2d2f74 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -149,6 +149,9 @@ static ssize_t show_freqdomain_cpus(struct cpufreq_policy *policy, char *buf) { struct acpi_cpufreq_data *data = policy->driver_data; + if (unlikely(!data)) + return -ENODEV; + return cpufreq_show_cpus(data->freqdomain_cpus, buf); } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index ef5ed9470de9..25c4c15103a0 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1436,8 +1436,10 @@ static void cpufreq_offline_finish(unsigned int cpu) * since this is a core component, and is essential for the * subsequent light-weight ->init() to succeed. */ - if (cpufreq_driver->exit) + if (cpufreq_driver->exit) { cpufreq_driver->exit(policy); + policy->freq_table = NULL; + } } /** diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 3af9dd7332e6..aa33b92b3e3e 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -776,6 +776,11 @@ static inline void intel_pstate_sample(struct cpudata *cpu) local_irq_save(flags); rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); + if (cpu->prev_mperf == mperf) { + local_irq_restore(flags); + return; + } + tsc = rdtsc(); local_irq_restore(flags); diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 3927ed9fdbd5..ca848cc6a8fd 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -492,7 +492,7 @@ struct devfreq *devfreq_add_device(struct device *dev, if (err) { put_device(&devfreq->dev); mutex_unlock(&devfreq->lock); - goto err_dev; + goto err_out; } mutex_unlock(&devfreq->lock); @@ -518,7 +518,6 @@ struct devfreq *devfreq_add_device(struct device *dev, err_init: list_del(&devfreq->node); device_unregister(&devfreq->dev); -err_dev: kfree(devfreq); err_out: return ERR_PTR(err); @@ -795,8 +794,10 @@ static ssize_t governor_store(struct device *dev, struct device_attribute *attr, ret = PTR_ERR(governor); goto out; } - if (df->governor == governor) + if (df->governor == governor) { + ret = 0; goto out; + } if (df->governor) { ret = df->governor->event_handler(df, DEVFREQ_GOV_STOP, NULL); diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index a165b4bfd330..dd24375b76dd 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -455,6 +455,15 @@ static struct at_xdmac_desc *at_xdmac_alloc_desc(struct dma_chan *chan, return desc; } +void at_xdmac_init_used_desc(struct at_xdmac_desc *desc) +{ + memset(&desc->lld, 0, sizeof(desc->lld)); + INIT_LIST_HEAD(&desc->descs_list); + desc->direction = DMA_TRANS_NONE; + desc->xfer_size = 0; + desc->active_xfer = false; +} + /* Call must be protected by lock. */ static struct at_xdmac_desc *at_xdmac_get_desc(struct at_xdmac_chan *atchan) { @@ -466,7 +475,7 @@ static struct at_xdmac_desc *at_xdmac_get_desc(struct at_xdmac_chan *atchan) desc = list_first_entry(&atchan->free_descs_list, struct at_xdmac_desc, desc_node); list_del(&desc->desc_node); - desc->active_xfer = false; + at_xdmac_init_used_desc(desc); } return desc; @@ -875,14 +884,14 @@ at_xdmac_interleaved_queue_desc(struct dma_chan *chan, if (xt->src_inc) { if (xt->src_sgl) - chan_cc |= AT_XDMAC_CC_SAM_UBS_DS_AM; + chan_cc |= AT_XDMAC_CC_SAM_UBS_AM; else chan_cc |= AT_XDMAC_CC_SAM_INCREMENTED_AM; } if (xt->dst_inc) { if (xt->dst_sgl) - chan_cc |= AT_XDMAC_CC_DAM_UBS_DS_AM; + chan_cc |= AT_XDMAC_CC_DAM_UBS_AM; else chan_cc |= AT_XDMAC_CC_DAM_INCREMENTED_AM; } diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 3ff284c8e3d5..09479d4be4db 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -554,10 +554,18 @@ struct dma_chan *dma_get_slave_channel(struct dma_chan *chan) mutex_lock(&dma_list_mutex); if (chan->client_count == 0) { + struct dma_device *device = chan->device; + + dma_cap_set(DMA_PRIVATE, device->cap_mask); + device->privatecnt++; err = dma_chan_get(chan); - if (err) + if (err) { pr_debug("%s: failed to get %s: (%d)\n", __func__, dma_chan_name(chan), err); + chan = NULL; + if (--device->privatecnt == 0) + dma_cap_clear(DMA_PRIVATE, device->cap_mask); + } } else chan = NULL; diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index cf1c87fa1edd..bedce038c6e2 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -1591,7 +1591,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) INIT_LIST_HEAD(&dw->dma.channels); for (i = 0; i < nr_channels; i++) { struct dw_dma_chan *dwc = &dw->chan[i]; - int r = nr_channels - i - 1; dwc->chan.device = &dw->dma; dma_cookie_init(&dwc->chan); @@ -1603,7 +1602,7 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) /* 7 is highest priority & 0 is lowest. */ if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING) - dwc->priority = r; + dwc->priority = nr_channels - i - 1; else dwc->priority = i; @@ -1622,6 +1621,7 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) /* Hardware configuration */ if (autocfg) { unsigned int dwc_params; + unsigned int r = DW_DMA_MAX_NR_CHANNELS - i - 1; void __iomem *addr = chip->regs + r * sizeof(u32); dwc_params = dma_read_byaddr(addr, DWC_PARAMS); diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c index 18c14e1f1414..48d6d9e94f67 100644 --- a/drivers/dma/idma64.c +++ b/drivers/dma/idma64.c @@ -355,23 +355,23 @@ static size_t idma64_active_desc_size(struct idma64_chan *idma64c) struct idma64_desc *desc = idma64c->desc; struct idma64_hw_desc *hw; size_t bytes = desc->length; - u64 llp; - u32 ctlhi; + u64 llp = channel_readq(idma64c, LLP); + u32 ctlhi = channel_readl(idma64c, CTL_HI); unsigned int i = 0; - llp = channel_readq(idma64c, LLP); do { hw = &desc->hw[i]; - } while ((hw->llp != llp) && (++i < desc->ndesc)); + if (hw->llp == llp) + break; + bytes -= hw->len; + } while (++i < desc->ndesc); if (!i) return bytes; - do { - bytes -= desc->hw[--i].len; - } while (i); + /* The current chunk is not fully transfered yet */ + bytes += desc->hw[--i].len; - ctlhi = channel_readl(idma64c, CTL_HI); return bytes - IDMA64C_CTLH_BLOCK_TS(ctlhi); } diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c index 5cb61ce01036..fc4156afa070 100644 --- a/drivers/dma/pxa_dma.c +++ b/drivers/dma/pxa_dma.c @@ -473,8 +473,10 @@ static void pxad_free_phy(struct pxad_chan *chan) return; /* clear the channel mapping in DRCMR */ - reg = pxad_drcmr(chan->drcmr); - writel_relaxed(0, chan->phy->base + reg); + if (chan->drcmr <= DRCMR_CHLNUM) { + reg = pxad_drcmr(chan->drcmr); + writel_relaxed(0, chan->phy->base + reg); + } spin_lock_irqsave(&pdev->phy_lock, flags); for (i = 0; i < 32; i++) @@ -516,8 +518,10 @@ static void phy_enable(struct pxad_phy *phy, bool misaligned) "%s(); phy=%p(%d) misaligned=%d\n", __func__, phy, phy->idx, misaligned); - reg = pxad_drcmr(phy->vchan->drcmr); - writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg); + if (phy->vchan->drcmr <= DRCMR_CHLNUM) { + reg = pxad_drcmr(phy->vchan->drcmr); + writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg); + } dalgn = phy_readl_relaxed(phy, DALGN); if (misaligned) @@ -887,6 +891,7 @@ pxad_tx_prep(struct virt_dma_chan *vc, struct virt_dma_desc *vd, struct dma_async_tx_descriptor *tx; struct pxad_chan *chan = container_of(vc, struct pxad_chan, vc); + INIT_LIST_HEAD(&vd->node); tx = vchan_tx_prep(vc, vd, tx_flags); tx->tx_submit = pxad_tx_submit; dev_dbg(&chan->vc.chan.dev->device, @@ -910,14 +915,18 @@ static void pxad_get_config(struct pxad_chan *chan, width = chan->cfg.src_addr_width; dev_addr = chan->cfg.src_addr; *dev_src = dev_addr; - *dcmd |= PXA_DCMD_INCTRGADDR | PXA_DCMD_FLOWSRC; + *dcmd |= PXA_DCMD_INCTRGADDR; + if (chan->drcmr <= DRCMR_CHLNUM) + *dcmd |= PXA_DCMD_FLOWSRC; } if (dir == DMA_MEM_TO_DEV) { maxburst = chan->cfg.dst_maxburst; width = chan->cfg.dst_addr_width; dev_addr = chan->cfg.dst_addr; *dev_dst = dev_addr; - *dcmd |= PXA_DCMD_INCSRCADDR | PXA_DCMD_FLOWTRG; + *dcmd |= PXA_DCMD_INCSRCADDR; + if (chan->drcmr <= DRCMR_CHLNUM) + *dcmd |= PXA_DCMD_FLOWTRG; } if (dir == DMA_MEM_TO_MEM) *dcmd |= PXA_DCMD_BURST32 | PXA_DCMD_INCTRGADDR | @@ -1177,6 +1186,16 @@ static unsigned int pxad_residue(struct pxad_chan *chan, else curr = phy_readl_relaxed(chan->phy, DTADR); + /* + * curr has to be actually read before checking descriptor + * completion, so that a curr inside a status updater + * descriptor implies the following test returns true, and + * preventing reordering of curr load and the test. + */ + rmb(); + if (is_desc_completed(vd)) + goto out; + for (i = 0; i < sw_desc->nb_desc - 1; i++) { hw_desc = sw_desc->hw_desc[i]; if (sw_desc->hw_desc[0]->dcmd & PXA_DCMD_INCSRCADDR) diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c index a1a500d96ff2..1661d518224a 100644 --- a/drivers/dma/sun4i-dma.c +++ b/drivers/dma/sun4i-dma.c @@ -599,13 +599,13 @@ get_next_cyclic_promise(struct sun4i_dma_contract *contract) static void sun4i_dma_free_contract(struct virt_dma_desc *vd) { struct sun4i_dma_contract *contract = to_sun4i_dma_contract(vd); - struct sun4i_dma_promise *promise; + struct sun4i_dma_promise *promise, *tmp; /* Free all the demands and completed demands */ - list_for_each_entry(promise, &contract->demands, list) + list_for_each_entry_safe(promise, tmp, &contract->demands, list) kfree(promise); - list_for_each_entry(promise, &contract->completed_demands, list) + list_for_each_entry_safe(promise, tmp, &contract->completed_demands, list) kfree(promise); kfree(contract); diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c index b23e8d52d126..8d57b1b12e41 100644 --- a/drivers/dma/xgene-dma.c +++ b/drivers/dma/xgene-dma.c @@ -59,7 +59,6 @@ #define XGENE_DMA_RING_MEM_RAM_SHUTDOWN 0xD070 #define XGENE_DMA_RING_BLK_MEM_RDY 0xD074 #define XGENE_DMA_RING_BLK_MEM_RDY_VAL 0xFFFFFFFF -#define XGENE_DMA_RING_DESC_CNT(v) (((v) & 0x0001FFFE) >> 1) #define XGENE_DMA_RING_ID_GET(owner, num) (((owner) << 6) | (num)) #define XGENE_DMA_RING_DST_ID(v) ((1 << 10) | (v)) #define XGENE_DMA_RING_CMD_OFFSET 0x2C @@ -379,14 +378,6 @@ static u8 xgene_dma_encode_xor_flyby(u32 src_cnt) return flyby_type[src_cnt]; } -static u32 xgene_dma_ring_desc_cnt(struct xgene_dma_ring *ring) -{ - u32 __iomem *cmd_base = ring->cmd_base; - u32 ring_state = ioread32(&cmd_base[1]); - - return XGENE_DMA_RING_DESC_CNT(ring_state); -} - static void xgene_dma_set_src_buffer(__le64 *ext8, size_t *len, dma_addr_t *paddr) { @@ -659,15 +650,12 @@ static void xgene_dma_clean_running_descriptor(struct xgene_dma_chan *chan, dma_pool_free(chan->desc_pool, desc, desc->tx.phys); } -static int xgene_chan_xfer_request(struct xgene_dma_ring *ring, - struct xgene_dma_desc_sw *desc_sw) +static void xgene_chan_xfer_request(struct xgene_dma_chan *chan, + struct xgene_dma_desc_sw *desc_sw) { + struct xgene_dma_ring *ring = &chan->tx_ring; struct xgene_dma_desc_hw *desc_hw; - /* Check if can push more descriptor to hw for execution */ - if (xgene_dma_ring_desc_cnt(ring) > (ring->slots - 2)) - return -EBUSY; - /* Get hw descriptor from DMA tx ring */ desc_hw = &ring->desc_hw[ring->head]; @@ -694,11 +682,13 @@ static int xgene_chan_xfer_request(struct xgene_dma_ring *ring, memcpy(desc_hw, &desc_sw->desc2, sizeof(*desc_hw)); } + /* Increment the pending transaction count */ + chan->pending += ((desc_sw->flags & + XGENE_DMA_FLAG_64B_DESC) ? 2 : 1); + /* Notify the hw that we have descriptor ready for execution */ iowrite32((desc_sw->flags & XGENE_DMA_FLAG_64B_DESC) ? 2 : 1, ring->cmd); - - return 0; } /** @@ -710,7 +700,6 @@ static int xgene_chan_xfer_request(struct xgene_dma_ring *ring, static void xgene_chan_xfer_ld_pending(struct xgene_dma_chan *chan) { struct xgene_dma_desc_sw *desc_sw, *_desc_sw; - int ret; /* * If the list of pending descriptors is empty, then we @@ -735,18 +724,13 @@ static void xgene_chan_xfer_ld_pending(struct xgene_dma_chan *chan) if (chan->pending >= chan->max_outstanding) return; - ret = xgene_chan_xfer_request(&chan->tx_ring, desc_sw); - if (ret) - return; + xgene_chan_xfer_request(chan, desc_sw); /* * Delete this element from ld pending queue and append it to * ld running queue */ list_move_tail(&desc_sw->node, &chan->ld_running); - - /* Increment the pending transaction count */ - chan->pending++; } } @@ -821,7 +805,8 @@ static void xgene_dma_cleanup_descriptors(struct xgene_dma_chan *chan) * Decrement the pending transaction count * as we have processed one */ - chan->pending--; + chan->pending -= ((desc_sw->flags & + XGENE_DMA_FLAG_64B_DESC) ? 2 : 1); /* * Delete this node from ld running queue and append it to @@ -1421,15 +1406,18 @@ static int xgene_dma_create_ring_one(struct xgene_dma_chan *chan, struct xgene_dma_ring *ring, enum xgene_dma_ring_cfgsize cfgsize) { + int ret; + /* Setup DMA ring descriptor variables */ ring->pdma = chan->pdma; ring->cfgsize = cfgsize; ring->num = chan->pdma->ring_num++; ring->id = XGENE_DMA_RING_ID_GET(ring->owner, ring->buf_num); - ring->size = xgene_dma_get_ring_size(chan, cfgsize); - if (ring->size <= 0) - return ring->size; + ret = xgene_dma_get_ring_size(chan, cfgsize); + if (ret <= 0) + return ret; + ring->size = ret; /* Allocate memory for DMA ring descriptor */ ring->desc_vaddr = dma_zalloc_coherent(chan->dev, ring->size, @@ -1482,7 +1470,7 @@ static int xgene_dma_create_chan_rings(struct xgene_dma_chan *chan) tx_ring->id, tx_ring->num, tx_ring->desc_vaddr); /* Set the max outstanding request possible to this channel */ - chan->max_outstanding = rx_ring->slots; + chan->max_outstanding = tx_ring->slots; return ret; } diff --git a/drivers/dma/zx296702_dma.c b/drivers/dma/zx296702_dma.c index 39915a6b7986..c017fcd8e07c 100644 --- a/drivers/dma/zx296702_dma.c +++ b/drivers/dma/zx296702_dma.c @@ -739,7 +739,7 @@ static struct dma_chan *zx_of_dma_simple_xlate(struct of_phandle_args *dma_spec, struct dma_chan *chan; struct zx_dma_chan *c; - if (request > d->dma_requests) + if (request >= d->dma_requests) return NULL; chan = dma_get_any_slave_channel(&d->slave); diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index e29560e6b40b..950c87f5d279 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -13,6 +13,7 @@ */ #include <linux/efi.h> +#include <linux/sort.h> #include <asm/efi.h> #include "efistub.h" @@ -305,6 +306,44 @@ fail: */ #define EFI_RT_VIRTUAL_BASE 0x40000000 +static int cmp_mem_desc(const void *l, const void *r) +{ + const efi_memory_desc_t *left = l, *right = r; + + return (left->phys_addr > right->phys_addr) ? 1 : -1; +} + +/* + * Returns whether region @left ends exactly where region @right starts, + * or false if either argument is NULL. + */ +static bool regions_are_adjacent(efi_memory_desc_t *left, + efi_memory_desc_t *right) +{ + u64 left_end; + + if (left == NULL || right == NULL) + return false; + + left_end = left->phys_addr + left->num_pages * EFI_PAGE_SIZE; + + return left_end == right->phys_addr; +} + +/* + * Returns whether region @left and region @right have compatible memory type + * mapping attributes, and are both EFI_MEMORY_RUNTIME regions. + */ +static bool regions_have_compatible_memory_type_attrs(efi_memory_desc_t *left, + efi_memory_desc_t *right) +{ + static const u64 mem_type_mask = EFI_MEMORY_WB | EFI_MEMORY_WT | + EFI_MEMORY_WC | EFI_MEMORY_UC | + EFI_MEMORY_RUNTIME; + + return ((left->attribute ^ right->attribute) & mem_type_mask) == 0; +} + /* * efi_get_virtmap() - create a virtual mapping for the EFI memory map * @@ -317,33 +356,52 @@ void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size, int *count) { u64 efi_virt_base = EFI_RT_VIRTUAL_BASE; - efi_memory_desc_t *out = runtime_map; + efi_memory_desc_t *in, *prev = NULL, *out = runtime_map; int l; - for (l = 0; l < map_size; l += desc_size) { - efi_memory_desc_t *in = (void *)memory_map + l; + /* + * To work around potential issues with the Properties Table feature + * introduced in UEFI 2.5, which may split PE/COFF executable images + * in memory into several RuntimeServicesCode and RuntimeServicesData + * regions, we need to preserve the relative offsets between adjacent + * EFI_MEMORY_RUNTIME regions with the same memory type attributes. + * The easiest way to find adjacent regions is to sort the memory map + * before traversing it. + */ + sort(memory_map, map_size / desc_size, desc_size, cmp_mem_desc, NULL); + + for (l = 0; l < map_size; l += desc_size, prev = in) { u64 paddr, size; + in = (void *)memory_map + l; if (!(in->attribute & EFI_MEMORY_RUNTIME)) continue; + paddr = in->phys_addr; + size = in->num_pages * EFI_PAGE_SIZE; + /* * Make the mapping compatible with 64k pages: this allows * a 4k page size kernel to kexec a 64k page size kernel and * vice versa. */ - paddr = round_down(in->phys_addr, SZ_64K); - size = round_up(in->num_pages * EFI_PAGE_SIZE + - in->phys_addr - paddr, SZ_64K); - - /* - * Avoid wasting memory on PTEs by choosing a virtual base that - * is compatible with section mappings if this region has the - * appropriate size and physical alignment. (Sections are 2 MB - * on 4k granule kernels) - */ - if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M) - efi_virt_base = round_up(efi_virt_base, SZ_2M); + if (!regions_are_adjacent(prev, in) || + !regions_have_compatible_memory_type_attrs(prev, in)) { + + paddr = round_down(in->phys_addr, SZ_64K); + size += in->phys_addr - paddr; + + /* + * Avoid wasting memory on PTEs by choosing a virtual + * base that is compatible with section mappings if this + * region has the appropriate size and physical + * alignment. (Sections are 2 MB on 4k granule kernels) + */ + if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M) + efi_virt_base = round_up(efi_virt_base, SZ_2M); + else + efi_virt_base = round_up(efi_virt_base, SZ_64K); + } in->virt_addr = efi_virt_base + in->phys_addr - paddr; efi_virt_base += size; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 77f1d7c6ea3a..9416e0f5c1db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -672,8 +672,12 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev) /* disp clock */ adev->clock.default_dispclk = le32_to_cpu(firmware_info->info_21.ulDefaultDispEngineClkFreq); - if (adev->clock.default_dispclk == 0) - adev->clock.default_dispclk = 54000; /* 540 Mhz */ + /* set a reasonable default for DP */ + if (adev->clock.default_dispclk < 53900) { + DRM_INFO("Changing default dispclk from %dMhz to 600Mhz\n", + adev->clock.default_dispclk / 100); + adev->clock.default_dispclk = 60000; + } adev->clock.dp_extclk = le16_to_cpu(firmware_info->info_21.usUniphyDPModeExtClkFreq); adev->clock.current_dispclk = adev->clock.default_dispclk; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index 1c3fc99c5465..8e995148f56e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -208,44 +208,6 @@ static int amdgpu_cgs_alloc_gpu_mem(void *cgs_device, return ret; } -static int amdgpu_cgs_import_gpu_mem(void *cgs_device, int dmabuf_fd, - cgs_handle_t *handle) -{ - CGS_FUNC_ADEV; - int r; - uint32_t dma_handle; - struct drm_gem_object *obj; - struct amdgpu_bo *bo; - struct drm_device *dev = adev->ddev; - struct drm_file *file_priv = NULL, *priv; - - mutex_lock(&dev->struct_mutex); - list_for_each_entry(priv, &dev->filelist, lhead) { - rcu_read_lock(); - if (priv->pid == get_pid(task_pid(current))) - file_priv = priv; - rcu_read_unlock(); - if (file_priv) - break; - } - mutex_unlock(&dev->struct_mutex); - r = dev->driver->prime_fd_to_handle(dev, - file_priv, dmabuf_fd, - &dma_handle); - spin_lock(&file_priv->table_lock); - - /* Check if we currently have a reference on the object */ - obj = idr_find(&file_priv->object_idr, dma_handle); - if (obj == NULL) { - spin_unlock(&file_priv->table_lock); - return -EINVAL; - } - spin_unlock(&file_priv->table_lock); - bo = gem_to_amdgpu_bo(obj); - *handle = (cgs_handle_t)bo; - return 0; -} - static int amdgpu_cgs_free_gpu_mem(void *cgs_device, cgs_handle_t handle) { struct amdgpu_bo *obj = (struct amdgpu_bo *)handle; @@ -810,7 +772,6 @@ static const struct cgs_ops amdgpu_cgs_ops = { }; static const struct cgs_os_ops amdgpu_cgs_os_ops = { - amdgpu_cgs_import_gpu_mem, amdgpu_cgs_add_irq_source, amdgpu_cgs_irq_get, amdgpu_cgs_irq_put diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 749420f1ea6f..fd16652aa277 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -156,7 +156,8 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) uint64_t *chunk_array_user; uint64_t *chunk_array; struct amdgpu_fpriv *fpriv = p->filp->driver_priv; - unsigned size, i; + unsigned size; + int i; int ret; if (cs->in.num_chunks == 0) @@ -176,7 +177,7 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) /* get chunks */ INIT_LIST_HEAD(&p->validated); - chunk_array_user = (uint64_t __user *)(cs->in.chunks); + chunk_array_user = (uint64_t __user *)(unsigned long)(cs->in.chunks); if (copy_from_user(chunk_array, chunk_array_user, sizeof(uint64_t)*cs->in.num_chunks)) { ret = -EFAULT; @@ -196,7 +197,7 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) struct drm_amdgpu_cs_chunk user_chunk; uint32_t __user *cdata; - chunk_ptr = (void __user *)chunk_array[i]; + chunk_ptr = (void __user *)(unsigned long)chunk_array[i]; if (copy_from_user(&user_chunk, chunk_ptr, sizeof(struct drm_amdgpu_cs_chunk))) { ret = -EFAULT; @@ -207,7 +208,7 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) p->chunks[i].length_dw = user_chunk.length_dw; size = p->chunks[i].length_dw; - cdata = (void __user *)user_chunk.chunk_data; + cdata = (void __user *)(unsigned long)user_chunk.chunk_data; p->chunks[i].user_ptr = cdata; p->chunks[i].kdata = drm_malloc_ab(size, sizeof(uint32_t)); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index e3d70772b531..dc29ed8145c2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -85,8 +85,6 @@ static void amdgpu_flip_work_func(struct work_struct *__work) /* We borrow the event spin lock for protecting flip_status */ spin_lock_irqsave(&crtc->dev->event_lock, flags); - /* set the proper interrupt */ - amdgpu_irq_get(adev, &adev->pageflip_irq, work->crtc_id); /* do the flip (mmio) */ adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base); /* set the flip status */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index adb48353f2e1..b190c2a83680 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -242,11 +242,11 @@ static struct pci_device_id pciidlist[] = { {0x1002, 0x985F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|AMD_IS_MOBILITY|AMD_IS_APU}, #endif /* topaz */ - {0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, - {0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, - {0x1002, 0x6902, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, - {0x1002, 0x6903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, - {0x1002, 0x6907, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x6902, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x6903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x6907, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, /* tonga */ {0x1002, 0x6920, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TONGA}, {0x1002, 0x6921, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TONGA}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index 8a122b1b7786..96290d9cddca 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -402,3 +402,19 @@ bool amdgpu_fbdev_robj_is_fb(struct amdgpu_device *adev, struct amdgpu_bo *robj) return true; return false; } + +void amdgpu_fbdev_restore_mode(struct amdgpu_device *adev) +{ + struct amdgpu_fbdev *afbdev = adev->mode_info.rfbdev; + struct drm_fb_helper *fb_helper; + int ret; + + if (!afbdev) + return; + + fb_helper = &afbdev->helper; + + ret = drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper); + if (ret) + DRM_DEBUG("failed to restore crtc mode\n"); +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 8c735f544b66..5d11e798230c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -485,7 +485,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file * Outdated mess for old drm with Xorg being in charge (void function now). */ /** - * amdgpu_driver_firstopen_kms - drm callback for last close + * amdgpu_driver_lastclose_kms - drm callback for last close * * @dev: drm dev pointer * @@ -493,6 +493,9 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file */ void amdgpu_driver_lastclose_kms(struct drm_device *dev) { + struct amdgpu_device *adev = dev->dev_private; + + amdgpu_fbdev_restore_mode(adev); vga_switcheroo_process_delayed_switch(); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index 64efe5b52e65..7bd470d9ac30 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -567,6 +567,7 @@ void amdgpu_fbdev_fini(struct amdgpu_device *adev); void amdgpu_fbdev_set_suspend(struct amdgpu_device *adev, int state); int amdgpu_fbdev_total_size(struct amdgpu_device *adev); bool amdgpu_fbdev_robj_is_fb(struct amdgpu_device *adev, struct amdgpu_bo *robj); +void amdgpu_fbdev_restore_mode(struct amdgpu_device *adev); void amdgpu_fb_output_poll_changed(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 1e14531353e0..53d551f2d839 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -455,8 +455,10 @@ int amdgpu_vm_update_page_directory(struct amdgpu_device *adev, return -ENOMEM; r = amdgpu_ib_get(ring, NULL, ndw * 4, ib); - if (r) + if (r) { + kfree(ib); return r; + } ib->length_dw = 0; /* walk over the address space and update the page directory */ diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index cd6edc40c9cd..1e0bba29e167 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -1279,8 +1279,7 @@ amdgpu_atombios_encoder_setup_dig(struct drm_encoder *encoder, int action) amdgpu_atombios_encoder_setup_dig_encoder(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON, 0); } if (amdgpu_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) - amdgpu_atombios_encoder_setup_dig_transmitter(encoder, - ATOM_TRANSMITTER_ACTION_LCD_BLON, 0, 0); + amdgpu_atombios_encoder_set_backlight_level(amdgpu_encoder, dig->backlight_level); if (ext_encoder) amdgpu_atombios_encoder_setup_external_encoder(encoder, ext_encoder, ATOM_ENABLE); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c index 82e8d0730517..a1a35a5df8e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c @@ -6185,6 +6185,11 @@ static int ci_dpm_late_init(void *handle) if (!amdgpu_dpm) return 0; + /* init the sysfs and debugfs files late */ + ret = amdgpu_pm_sysfs_init(adev); + if (ret) + return ret; + ret = ci_set_temperature_range(adev); if (ret) return ret; @@ -6232,9 +6237,6 @@ static int ci_dpm_sw_init(void *handle) adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps; if (amdgpu_dpm == 1) amdgpu_pm_print_power_states(adev); - ret = amdgpu_pm_sysfs_init(adev); - if (ret) - goto dpm_failed; mutex_unlock(&adev->pm.mutex); DRM_INFO("amdgpu: dpm initialized\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 4b6ce74753cd..484710cfdf82 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -1567,6 +1567,9 @@ static void cik_pcie_gen3_enable(struct amdgpu_device *adev) int ret, i; u16 tmp16; + if (pci_is_root_bus(adev->pdev->bus)) + return; + if (amdgpu_pcie_gen2 == 0) return; diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c index 44fa96ad4709..2e3373ed4c94 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c @@ -596,6 +596,12 @@ static int cz_dpm_late_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; if (amdgpu_dpm) { + int ret; + /* init the sysfs and debugfs files late */ + ret = amdgpu_pm_sysfs_init(adev); + if (ret) + return ret; + /* powerdown unused blocks for now */ cz_dpm_powergate_uvd(adev, true); cz_dpm_powergate_vce(adev, true); @@ -632,10 +638,6 @@ static int cz_dpm_sw_init(void *handle) if (amdgpu_dpm == 1) amdgpu_pm_print_power_states(adev); - ret = amdgpu_pm_sysfs_init(adev); - if (ret) - goto dpm_init_failed; - mutex_unlock(&adev->pm.mutex); DRM_INFO("amdgpu: dpm initialized\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index e4d101b1252a..d4c82b625727 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -255,6 +255,24 @@ static u32 dce_v10_0_vblank_get_counter(struct amdgpu_device *adev, int crtc) return RREG32(mmCRTC_STATUS_FRAME_COUNT + crtc_offsets[crtc]); } +static void dce_v10_0_pageflip_interrupt_init(struct amdgpu_device *adev) +{ + unsigned i; + + /* Enable pflip interrupts */ + for (i = 0; i < adev->mode_info.num_crtc; i++) + amdgpu_irq_get(adev, &adev->pageflip_irq, i); +} + +static void dce_v10_0_pageflip_interrupt_fini(struct amdgpu_device *adev) +{ + unsigned i; + + /* Disable pflip interrupts */ + for (i = 0; i < adev->mode_info.num_crtc; i++) + amdgpu_irq_put(adev, &adev->pageflip_irq, i); +} + /** * dce_v10_0_page_flip - pageflip callback. * @@ -2663,9 +2681,10 @@ static void dce_v10_0_crtc_dpms(struct drm_crtc *crtc, int mode) dce_v10_0_vga_enable(crtc, true); amdgpu_atombios_crtc_blank(crtc, ATOM_DISABLE); dce_v10_0_vga_enable(crtc, false); - /* Make sure VBLANK interrupt is still enabled */ + /* Make sure VBLANK and PFLIP interrupts are still enabled */ type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id); amdgpu_irq_update(adev, &adev->crtc_irq, type); + amdgpu_irq_update(adev, &adev->pageflip_irq, type); drm_vblank_post_modeset(dev, amdgpu_crtc->crtc_id); dce_v10_0_crtc_load_lut(crtc); break; @@ -3025,6 +3044,8 @@ static int dce_v10_0_hw_init(void *handle) dce_v10_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); } + dce_v10_0_pageflip_interrupt_init(adev); + return 0; } @@ -3039,6 +3060,8 @@ static int dce_v10_0_hw_fini(void *handle) dce_v10_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); } + dce_v10_0_pageflip_interrupt_fini(adev); + return 0; } @@ -3050,6 +3073,8 @@ static int dce_v10_0_suspend(void *handle) dce_v10_0_hpd_fini(adev); + dce_v10_0_pageflip_interrupt_fini(adev); + return 0; } @@ -3075,6 +3100,8 @@ static int dce_v10_0_resume(void *handle) /* initialize hpd */ dce_v10_0_hpd_init(adev); + dce_v10_0_pageflip_interrupt_init(adev); + return 0; } @@ -3369,7 +3396,6 @@ static int dce_v10_0_pageflip_irq(struct amdgpu_device *adev, spin_unlock_irqrestore(&adev->ddev->event_lock, flags); drm_vblank_put(adev->ddev, amdgpu_crtc->crtc_id); - amdgpu_irq_put(adev, &adev->pageflip_irq, crtc_id); queue_work(amdgpu_crtc->pflip_queue, &works->unpin_work); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 6411e8244671..7e1cf5e4eebf 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -233,6 +233,24 @@ static u32 dce_v11_0_vblank_get_counter(struct amdgpu_device *adev, int crtc) return RREG32(mmCRTC_STATUS_FRAME_COUNT + crtc_offsets[crtc]); } +static void dce_v11_0_pageflip_interrupt_init(struct amdgpu_device *adev) +{ + unsigned i; + + /* Enable pflip interrupts */ + for (i = 0; i < adev->mode_info.num_crtc; i++) + amdgpu_irq_get(adev, &adev->pageflip_irq, i); +} + +static void dce_v11_0_pageflip_interrupt_fini(struct amdgpu_device *adev) +{ + unsigned i; + + /* Disable pflip interrupts */ + for (i = 0; i < adev->mode_info.num_crtc; i++) + amdgpu_irq_put(adev, &adev->pageflip_irq, i); +} + /** * dce_v11_0_page_flip - pageflip callback. * @@ -2640,9 +2658,10 @@ static void dce_v11_0_crtc_dpms(struct drm_crtc *crtc, int mode) dce_v11_0_vga_enable(crtc, true); amdgpu_atombios_crtc_blank(crtc, ATOM_DISABLE); dce_v11_0_vga_enable(crtc, false); - /* Make sure VBLANK interrupt is still enabled */ + /* Make sure VBLANK and PFLIP interrupts are still enabled */ type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id); amdgpu_irq_update(adev, &adev->crtc_irq, type); + amdgpu_irq_update(adev, &adev->pageflip_irq, type); drm_vblank_post_modeset(dev, amdgpu_crtc->crtc_id); dce_v11_0_crtc_load_lut(crtc); break; @@ -2888,7 +2907,7 @@ static int dce_v11_0_early_init(void *handle) switch (adev->asic_type) { case CHIP_CARRIZO: - adev->mode_info.num_crtc = 4; + adev->mode_info.num_crtc = 3; adev->mode_info.num_hpd = 6; adev->mode_info.num_dig = 9; break; @@ -3000,6 +3019,8 @@ static int dce_v11_0_hw_init(void *handle) dce_v11_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); } + dce_v11_0_pageflip_interrupt_init(adev); + return 0; } @@ -3014,6 +3035,8 @@ static int dce_v11_0_hw_fini(void *handle) dce_v11_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); } + dce_v11_0_pageflip_interrupt_fini(adev); + return 0; } @@ -3025,6 +3048,8 @@ static int dce_v11_0_suspend(void *handle) dce_v11_0_hpd_fini(adev); + dce_v11_0_pageflip_interrupt_fini(adev); + return 0; } @@ -3051,6 +3076,8 @@ static int dce_v11_0_resume(void *handle) /* initialize hpd */ dce_v11_0_hpd_init(adev); + dce_v11_0_pageflip_interrupt_init(adev); + return 0; } @@ -3345,7 +3372,6 @@ static int dce_v11_0_pageflip_irq(struct amdgpu_device *adev, spin_unlock_irqrestore(&adev->ddev->event_lock, flags); drm_vblank_put(adev->ddev, amdgpu_crtc->crtc_id); - amdgpu_irq_put(adev, &adev->pageflip_irq, crtc_id); queue_work(amdgpu_crtc->pflip_queue, &works->unpin_work); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index c86911c2ea2a..34b9c2a9d8d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -204,6 +204,24 @@ static u32 dce_v8_0_vblank_get_counter(struct amdgpu_device *adev, int crtc) return RREG32(mmCRTC_STATUS_FRAME_COUNT + crtc_offsets[crtc]); } +static void dce_v8_0_pageflip_interrupt_init(struct amdgpu_device *adev) +{ + unsigned i; + + /* Enable pflip interrupts */ + for (i = 0; i < adev->mode_info.num_crtc; i++) + amdgpu_irq_get(adev, &adev->pageflip_irq, i); +} + +static void dce_v8_0_pageflip_interrupt_fini(struct amdgpu_device *adev) +{ + unsigned i; + + /* Disable pflip interrupts */ + for (i = 0; i < adev->mode_info.num_crtc; i++) + amdgpu_irq_put(adev, &adev->pageflip_irq, i); +} + /** * dce_v8_0_page_flip - pageflip callback. * @@ -2575,9 +2593,10 @@ static void dce_v8_0_crtc_dpms(struct drm_crtc *crtc, int mode) dce_v8_0_vga_enable(crtc, true); amdgpu_atombios_crtc_blank(crtc, ATOM_DISABLE); dce_v8_0_vga_enable(crtc, false); - /* Make sure VBLANK interrupt is still enabled */ + /* Make sure VBLANK and PFLIP interrupts are still enabled */ type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id); amdgpu_irq_update(adev, &adev->crtc_irq, type); + amdgpu_irq_update(adev, &adev->pageflip_irq, type); drm_vblank_post_modeset(dev, amdgpu_crtc->crtc_id); dce_v8_0_crtc_load_lut(crtc); break; @@ -2933,6 +2952,8 @@ static int dce_v8_0_hw_init(void *handle) dce_v8_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); } + dce_v8_0_pageflip_interrupt_init(adev); + return 0; } @@ -2947,6 +2968,8 @@ static int dce_v8_0_hw_fini(void *handle) dce_v8_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); } + dce_v8_0_pageflip_interrupt_fini(adev); + return 0; } @@ -2958,6 +2981,8 @@ static int dce_v8_0_suspend(void *handle) dce_v8_0_hpd_fini(adev); + dce_v8_0_pageflip_interrupt_fini(adev); + return 0; } @@ -2981,6 +3006,8 @@ static int dce_v8_0_resume(void *handle) /* initialize hpd */ dce_v8_0_hpd_init(adev); + dce_v8_0_pageflip_interrupt_init(adev); + return 0; } @@ -3376,7 +3403,6 @@ static int dce_v8_0_pageflip_irq(struct amdgpu_device *adev, spin_unlock_irqrestore(&adev->ddev->event_lock, flags); drm_vblank_put(adev->ddev, amdgpu_crtc->crtc_id); - amdgpu_irq_put(adev, &adev->pageflip_irq, crtc_id); queue_work(amdgpu_crtc->pflip_queue, &works->unpin_work); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 774528ab8704..fab5471d25d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -1262,6 +1262,12 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev, addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR); status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS); mc_client = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_MCCLIENT); + /* reset addr and status */ + WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1); + + if (!addr && !status) + return 0; + dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n", entry->src_id, entry->src_data); dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n", @@ -1269,8 +1275,6 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev, dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n", status); gmc_v7_0_vm_decode_fault(adev, status, addr, mc_client); - /* reset addr and status */ - WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 9a07742620d0..7bc9e9fcf3d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -1262,6 +1262,12 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev, addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR); status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS); mc_client = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_MCCLIENT); + /* reset addr and status */ + WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1); + + if (!addr && !status) + return 0; + dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n", entry->src_id, entry->src_data); dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n", @@ -1269,8 +1275,6 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev, dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n", status); gmc_v8_0_vm_decode_fault(adev, status, addr, mc_client); - /* reset addr and status */ - WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c index 94ec04a9c4d5..9745ed3a9aef 100644 --- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c @@ -2995,6 +2995,12 @@ static int kv_dpm_late_init(void *handle) { /* powerdown unused blocks for now */ struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int ret; + + /* init the sysfs and debugfs files late */ + ret = amdgpu_pm_sysfs_init(adev); + if (ret) + return ret; kv_dpm_powergate_acp(adev, true); kv_dpm_powergate_samu(adev, true); @@ -3038,9 +3044,6 @@ static int kv_dpm_sw_init(void *handle) adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps; if (amdgpu_dpm == 1) amdgpu_pm_print_power_states(adev); - ret = amdgpu_pm_sysfs_init(adev); - if (ret) - goto dpm_failed; mutex_unlock(&adev->pm.mutex); DRM_INFO("amdgpu: dpm initialized\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index b55ceb14fdcd..0bac8702e934 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -1005,6 +1005,9 @@ static void vi_pcie_gen3_enable(struct amdgpu_device *adev) u32 mask; int ret; + if (pci_is_root_bus(adev->pdev->bus)) + return; + if (amdgpu_pcie_gen2 == 0) return; diff --git a/drivers/gpu/drm/amd/include/cgs_linux.h b/drivers/gpu/drm/amd/include/cgs_linux.h index 488642f08267..3b47ae313e36 100644 --- a/drivers/gpu/drm/amd/include/cgs_linux.h +++ b/drivers/gpu/drm/amd/include/cgs_linux.h @@ -27,19 +27,6 @@ #include "cgs_common.h" /** - * cgs_import_gpu_mem() - Import dmabuf handle - * @cgs_device: opaque device handle - * @dmabuf_fd: DMABuf file descriptor - * @handle: memory handle (output) - * - * Must be called in the process context that dmabuf_fd belongs to. - * - * Return: 0 on success, -errno otherwise - */ -typedef int (*cgs_import_gpu_mem_t)(void *cgs_device, int dmabuf_fd, - cgs_handle_t *handle); - -/** * cgs_irq_source_set_func() - Callback for enabling/disabling interrupt sources * @private_data: private data provided to cgs_add_irq_source * @src_id: interrupt source ID @@ -114,16 +101,12 @@ typedef int (*cgs_irq_get_t)(void *cgs_device, unsigned src_id, unsigned type); typedef int (*cgs_irq_put_t)(void *cgs_device, unsigned src_id, unsigned type); struct cgs_os_ops { - cgs_import_gpu_mem_t import_gpu_mem; - /* IRQ handling */ cgs_add_irq_source_t add_irq_source; cgs_irq_get_t irq_get; cgs_irq_put_t irq_put; }; -#define cgs_import_gpu_mem(dev,dmabuf_fd,handle) \ - CGS_OS_CALL(import_gpu_mem,dev,dmabuf_fd,handle) #define cgs_add_irq_source(dev,src_id,num_types,set,handler,private_data) \ CGS_OS_CALL(add_irq_source,dev,src_id,num_types,set,handler, \ private_data) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index e23df5fd3836..5bca390d9ae2 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -53,8 +53,8 @@ static int drm_dp_send_dpcd_write(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, int offset, int size, u8 *bytes); -static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_branch *mstb); +static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_branch *mstb); static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_branch *mstb, struct drm_dp_mst_port *port); @@ -804,8 +804,6 @@ static void drm_dp_destroy_mst_branch_device(struct kref *kref) struct drm_dp_mst_port *port, *tmp; bool wake_tx = false; - cancel_work_sync(&mstb->mgr->work); - /* * destroy all ports - don't need lock * as there are no more references to the mst branch @@ -863,29 +861,33 @@ static void drm_dp_destroy_port(struct kref *kref) { struct drm_dp_mst_port *port = container_of(kref, struct drm_dp_mst_port, kref); struct drm_dp_mst_topology_mgr *mgr = port->mgr; + if (!port->input) { port->vcpi.num_slots = 0; kfree(port->cached_edid); - /* we can't destroy the connector here, as - we might be holding the mode_config.mutex - from an EDID retrieval */ + /* + * The only time we don't have a connector + * on an output port is if the connector init + * fails. + */ if (port->connector) { + /* we can't destroy the connector here, as + * we might be holding the mode_config.mutex + * from an EDID retrieval */ + mutex_lock(&mgr->destroy_connector_lock); list_add(&port->next, &mgr->destroy_connector_list); mutex_unlock(&mgr->destroy_connector_lock); schedule_work(&mgr->destroy_connector_work); return; } + /* no need to clean up vcpi + * as if we have no connector we never setup a vcpi */ drm_dp_port_teardown_pdt(port, port->pdt); - - if (!port->input && port->vcpi.vcpi > 0) - drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); } kfree(port); - - (*mgr->cbs->hotplug)(mgr); } static void drm_dp_put_port(struct drm_dp_mst_port *port) @@ -1027,8 +1029,8 @@ static void drm_dp_check_port_guid(struct drm_dp_mst_branch *mstb, } } -static void build_mst_prop_path(struct drm_dp_mst_port *port, - struct drm_dp_mst_branch *mstb, +static void build_mst_prop_path(const struct drm_dp_mst_branch *mstb, + int pnum, char *proppath, size_t proppath_size) { @@ -1041,7 +1043,7 @@ static void build_mst_prop_path(struct drm_dp_mst_port *port, snprintf(temp, sizeof(temp), "-%d", port_num); strlcat(proppath, temp, proppath_size); } - snprintf(temp, sizeof(temp), "-%d", port->port_num); + snprintf(temp, sizeof(temp), "-%d", pnum); strlcat(proppath, temp, proppath_size); } @@ -1105,22 +1107,32 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb, drm_dp_port_teardown_pdt(port, old_pdt); ret = drm_dp_port_setup_pdt(port); - if (ret == true) { + if (ret == true) drm_dp_send_link_address(mstb->mgr, port->mstb); - port->mstb->link_address_sent = true; - } } if (created && !port->input) { char proppath[255]; - build_mst_prop_path(port, mstb, proppath, sizeof(proppath)); - port->connector = (*mstb->mgr->cbs->add_connector)(mstb->mgr, port, proppath); - if (port->port_num >= 8) { + build_mst_prop_path(mstb, port->port_num, proppath, sizeof(proppath)); + port->connector = (*mstb->mgr->cbs->add_connector)(mstb->mgr, port, proppath); + if (!port->connector) { + /* remove it from the port list */ + mutex_lock(&mstb->mgr->lock); + list_del(&port->next); + mutex_unlock(&mstb->mgr->lock); + /* drop port list reference */ + drm_dp_put_port(port); + goto out; + } + if (port->port_num >= DP_MST_LOGICAL_PORT_0) { port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc); + drm_mode_connector_set_tile_property(port->connector); } + (*mstb->mgr->cbs->register_connector)(port->connector); } +out: /* put reference to this port */ drm_dp_put_port(port); } @@ -1202,10 +1214,9 @@ static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *m { struct drm_dp_mst_port *port; struct drm_dp_mst_branch *mstb_child; - if (!mstb->link_address_sent) { + if (!mstb->link_address_sent) drm_dp_send_link_address(mgr, mstb); - mstb->link_address_sent = true; - } + list_for_each_entry(port, &mstb->ports, next) { if (port->input) continue; @@ -1458,8 +1469,8 @@ static void drm_dp_queue_down_tx(struct drm_dp_mst_topology_mgr *mgr, mutex_unlock(&mgr->qlock); } -static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_branch *mstb) +static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_branch *mstb) { int len; struct drm_dp_sideband_msg_tx *txmsg; @@ -1467,11 +1478,12 @@ static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL); if (!txmsg) - return -ENOMEM; + return; txmsg->dst = mstb; len = build_link_address(txmsg); + mstb->link_address_sent = true; drm_dp_queue_down_tx(mgr, txmsg); ret = drm_dp_mst_wait_tx_reply(mstb, txmsg); @@ -1499,11 +1511,12 @@ static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, } (*mgr->cbs->hotplug)(mgr); } - } else + } else { + mstb->link_address_sent = false; DRM_DEBUG_KMS("link address failed %d\n", ret); + } kfree(txmsg); - return 0; } static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, @@ -1978,6 +1991,8 @@ void drm_dp_mst_topology_mgr_suspend(struct drm_dp_mst_topology_mgr *mgr) drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, DP_MST_EN | DP_UPSTREAM_IS_SRC); mutex_unlock(&mgr->lock); + flush_work(&mgr->work); + flush_work(&mgr->destroy_connector_work); } EXPORT_SYMBOL(drm_dp_mst_topology_mgr_suspend); @@ -2263,10 +2278,10 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_ if (port->cached_edid) edid = drm_edid_duplicate(port->cached_edid); - else + else { edid = drm_get_edid(connector, &port->aux.ddc); - - drm_mode_connector_set_tile_property(connector); + drm_mode_connector_set_tile_property(connector); + } drm_dp_put_port(port); return edid; } @@ -2671,7 +2686,7 @@ static void drm_dp_destroy_connector_work(struct work_struct *work) { struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, destroy_connector_work); struct drm_dp_mst_port *port; - + bool send_hotplug = false; /* * Not a regular list traverse as we have to drop the destroy * connector lock before destroying the connector, to avoid AB->BA @@ -2694,7 +2709,10 @@ static void drm_dp_destroy_connector_work(struct work_struct *work) if (!port->input && port->vcpi.vcpi > 0) drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); kfree(port); + send_hotplug = true; } + if (send_hotplug) + (*mgr->cbs->hotplug)(mgr); } /** @@ -2747,6 +2765,7 @@ EXPORT_SYMBOL(drm_dp_mst_topology_mgr_init); */ void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr) { + flush_work(&mgr->work); flush_work(&mgr->destroy_connector_work); mutex_lock(&mgr->payload_lock); kfree(mgr->payloads); @@ -2782,12 +2801,13 @@ static int drm_dp_mst_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs if (msgs[num - 1].flags & I2C_M_RD) reading = true; - if (!reading) { + if (!reading || (num - 1 > DP_REMOTE_I2C_READ_MAX_TRANSACTIONS)) { DRM_DEBUG_KMS("Unsupported I2C transaction for MST device\n"); ret = -EIO; goto out; } + memset(&msg, 0, sizeof(msg)); msg.req_type = DP_REMOTE_I2C_READ; msg.u.i2c_read.num_transactions = num - 1; msg.u.i2c_read.port_number = port->port_num; diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 418d299f3b12..ca08c472311b 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -345,7 +345,11 @@ static bool restore_fbdev_mode(struct drm_fb_helper *fb_helper) struct drm_crtc *crtc = mode_set->crtc; int ret; - if (crtc->funcs->cursor_set) { + if (crtc->funcs->cursor_set2) { + ret = crtc->funcs->cursor_set2(crtc, NULL, 0, 0, 0, 0, 0); + if (ret) + error = true; + } else if (crtc->funcs->cursor_set) { ret = crtc->funcs->cursor_set(crtc, NULL, 0, 0, 0); if (ret) error = true; diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index d734780b31c0..a18164f2f6d2 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -94,7 +94,18 @@ static int drm_helper_probe_add_cmdline_mode(struct drm_connector *connector) } #define DRM_OUTPUT_POLL_PERIOD (10*HZ) -static void __drm_kms_helper_poll_enable(struct drm_device *dev) +/** + * drm_kms_helper_poll_enable_locked - re-enable output polling. + * @dev: drm_device + * + * This function re-enables the output polling work without + * locking the mode_config mutex. + * + * This is like drm_kms_helper_poll_enable() however it is to be + * called from a context where the mode_config mutex is locked + * already. + */ +void drm_kms_helper_poll_enable_locked(struct drm_device *dev) { bool poll = false; struct drm_connector *connector; @@ -113,6 +124,8 @@ static void __drm_kms_helper_poll_enable(struct drm_device *dev) if (poll) schedule_delayed_work(&dev->mode_config.output_poll_work, DRM_OUTPUT_POLL_PERIOD); } +EXPORT_SYMBOL(drm_kms_helper_poll_enable_locked); + static int drm_helper_probe_single_connector_modes_merge_bits(struct drm_connector *connector, uint32_t maxX, uint32_t maxY, bool merge_type_bits) @@ -174,7 +187,7 @@ static int drm_helper_probe_single_connector_modes_merge_bits(struct drm_connect /* Re-enable polling in case the global poll config changed. */ if (drm_kms_helper_poll != dev->mode_config.poll_running) - __drm_kms_helper_poll_enable(dev); + drm_kms_helper_poll_enable_locked(dev); dev->mode_config.poll_running = drm_kms_helper_poll; @@ -428,7 +441,7 @@ EXPORT_SYMBOL(drm_kms_helper_poll_disable); void drm_kms_helper_poll_enable(struct drm_device *dev) { mutex_lock(&dev->mode_config.mutex); - __drm_kms_helper_poll_enable(dev); + drm_kms_helper_poll_enable_locked(dev); mutex_unlock(&dev->mode_config.mutex); } EXPORT_SYMBOL(drm_kms_helper_poll_enable); diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c index 0f6cd33b531f..684bd4a13843 100644 --- a/drivers/gpu/drm/drm_sysfs.c +++ b/drivers/gpu/drm/drm_sysfs.c @@ -235,18 +235,12 @@ static ssize_t dpms_show(struct device *device, char *buf) { struct drm_connector *connector = to_drm_connector(device); - struct drm_device *dev = connector->dev; - uint64_t dpms_status; - int ret; + int dpms; - ret = drm_object_property_get_value(&connector->base, - dev->mode_config.dpms_property, - &dpms_status); - if (ret) - return 0; + dpms = READ_ONCE(connector->dpms); return snprintf(buf, PAGE_SIZE, "%s\n", - drm_get_dpms_name((int)dpms_status)); + drm_get_dpms_name(dpms)); } static ssize_t enabled_show(struct device *device, diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index cbdb78ef3bac..e6cbaca821a4 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -37,7 +37,6 @@ * DECON stands for Display and Enhancement controller. */ -#define DECON_DEFAULT_FRAMERATE 60 #define MIN_FB_WIDTH_FOR_16WORD_BURST 128 #define WINDOWS_NR 2 @@ -165,16 +164,6 @@ static u32 decon_calc_clkdiv(struct decon_context *ctx, return (clkdiv < 0x100) ? clkdiv : 0xff; } -static bool decon_mode_fixup(struct exynos_drm_crtc *crtc, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - if (adjusted_mode->vrefresh == 0) - adjusted_mode->vrefresh = DECON_DEFAULT_FRAMERATE; - - return true; -} - static void decon_commit(struct exynos_drm_crtc *crtc) { struct decon_context *ctx = crtc->ctx; @@ -637,7 +626,6 @@ static void decon_disable(struct exynos_drm_crtc *crtc) static const struct exynos_drm_crtc_ops decon_crtc_ops = { .enable = decon_enable, .disable = decon_disable, - .mode_fixup = decon_mode_fixup, .commit = decon_commit, .enable_vblank = decon_enable_vblank, .disable_vblank = decon_disable_vblank, diff --git a/drivers/gpu/drm/exynos/exynos_dp_core.c b/drivers/gpu/drm/exynos/exynos_dp_core.c index d66ade0efac8..124fb9a56f02 100644 --- a/drivers/gpu/drm/exynos/exynos_dp_core.c +++ b/drivers/gpu/drm/exynos/exynos_dp_core.c @@ -1383,28 +1383,6 @@ static int exynos_dp_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP -static int exynos_dp_suspend(struct device *dev) -{ - struct exynos_dp_device *dp = dev_get_drvdata(dev); - - exynos_dp_disable(&dp->encoder); - return 0; -} - -static int exynos_dp_resume(struct device *dev) -{ - struct exynos_dp_device *dp = dev_get_drvdata(dev); - - exynos_dp_enable(&dp->encoder); - return 0; -} -#endif - -static const struct dev_pm_ops exynos_dp_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(exynos_dp_suspend, exynos_dp_resume) -}; - static const struct of_device_id exynos_dp_match[] = { { .compatible = "samsung,exynos5-dp" }, {}, @@ -1417,7 +1395,6 @@ struct platform_driver dp_driver = { .driver = { .name = "exynos-dp", .owner = THIS_MODULE, - .pm = &exynos_dp_pm_ops, .of_match_table = exynos_dp_match, }, }; diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c index c68a6a2a9b57..7f55ba6771c6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_core.c +++ b/drivers/gpu/drm/exynos/exynos_drm_core.c @@ -28,7 +28,6 @@ int exynos_drm_subdrv_register(struct exynos_drm_subdrv *subdrv) return 0; } -EXPORT_SYMBOL_GPL(exynos_drm_subdrv_register); int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *subdrv) { @@ -39,7 +38,6 @@ int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *subdrv) return 0; } -EXPORT_SYMBOL_GPL(exynos_drm_subdrv_unregister); int exynos_drm_device_subdrv_probe(struct drm_device *dev) { @@ -69,7 +67,6 @@ int exynos_drm_device_subdrv_probe(struct drm_device *dev) return 0; } -EXPORT_SYMBOL_GPL(exynos_drm_device_subdrv_probe); int exynos_drm_device_subdrv_remove(struct drm_device *dev) { @@ -87,7 +84,6 @@ int exynos_drm_device_subdrv_remove(struct drm_device *dev) return 0; } -EXPORT_SYMBOL_GPL(exynos_drm_device_subdrv_remove); int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file) { @@ -111,7 +107,6 @@ err: } return ret; } -EXPORT_SYMBOL_GPL(exynos_drm_subdrv_open); void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file) { @@ -122,4 +117,3 @@ void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file) subdrv->close(dev, subdrv->dev, file); } } -EXPORT_SYMBOL_GPL(exynos_drm_subdrv_close); diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c index 0872aa2f450f..ed28823d3b35 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c @@ -41,20 +41,6 @@ static void exynos_drm_crtc_disable(struct drm_crtc *crtc) exynos_crtc->ops->disable(exynos_crtc); } -static bool -exynos_drm_crtc_mode_fixup(struct drm_crtc *crtc, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc); - - if (exynos_crtc->ops->mode_fixup) - return exynos_crtc->ops->mode_fixup(exynos_crtc, mode, - adjusted_mode); - - return true; -} - static void exynos_drm_crtc_mode_set_nofb(struct drm_crtc *crtc) { @@ -99,7 +85,6 @@ static void exynos_crtc_atomic_flush(struct drm_crtc *crtc, static struct drm_crtc_helper_funcs exynos_crtc_helper_funcs = { .enable = exynos_drm_crtc_enable, .disable = exynos_drm_crtc_disable, - .mode_fixup = exynos_drm_crtc_mode_fixup, .mode_set_nofb = exynos_drm_crtc_mode_set_nofb, .atomic_begin = exynos_crtc_atomic_begin, .atomic_flush = exynos_crtc_atomic_flush, diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index 831d2e4cacf9..ae9e6b2d3758 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -304,6 +304,7 @@ int exynos_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state, return 0; } +#ifdef CONFIG_PM_SLEEP static int exynos_drm_suspend(struct drm_device *dev, pm_message_t state) { struct drm_connector *connector; @@ -340,6 +341,7 @@ static int exynos_drm_resume(struct drm_device *dev) return 0; } +#endif static int exynos_drm_open(struct drm_device *dev, struct drm_file *file) { diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index b7ba21dfb696..6c717ba672db 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -82,7 +82,6 @@ struct exynos_drm_plane { * * @enable: enable the device * @disable: disable the device - * @mode_fixup: fix mode data before applying it * @commit: set current hw specific display mode to hw. * @enable_vblank: specific driver callback for enabling vblank interrupt. * @disable_vblank: specific driver callback for disabling vblank interrupt. @@ -103,9 +102,6 @@ struct exynos_drm_crtc; struct exynos_drm_crtc_ops { void (*enable)(struct exynos_drm_crtc *crtc); void (*disable)(struct exynos_drm_crtc *crtc); - bool (*mode_fixup)(struct exynos_drm_crtc *crtc, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode); void (*commit)(struct exynos_drm_crtc *crtc); int (*enable_vblank)(struct exynos_drm_crtc *crtc); void (*disable_vblank)(struct exynos_drm_crtc *crtc); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index 2a652359af64..dd3a5e6d58c8 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -1206,23 +1206,6 @@ static struct exynos_drm_ipp_ops fimc_dst_ops = { .set_addr = fimc_dst_set_addr, }; -static int fimc_clk_ctrl(struct fimc_context *ctx, bool enable) -{ - DRM_DEBUG_KMS("enable[%d]\n", enable); - - if (enable) { - clk_prepare_enable(ctx->clocks[FIMC_CLK_GATE]); - clk_prepare_enable(ctx->clocks[FIMC_CLK_WB_A]); - ctx->suspended = false; - } else { - clk_disable_unprepare(ctx->clocks[FIMC_CLK_GATE]); - clk_disable_unprepare(ctx->clocks[FIMC_CLK_WB_A]); - ctx->suspended = true; - } - - return 0; -} - static irqreturn_t fimc_irq_handler(int irq, void *dev_id) { struct fimc_context *ctx = dev_id; @@ -1780,6 +1763,24 @@ static int fimc_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM +static int fimc_clk_ctrl(struct fimc_context *ctx, bool enable) +{ + DRM_DEBUG_KMS("enable[%d]\n", enable); + + if (enable) { + clk_prepare_enable(ctx->clocks[FIMC_CLK_GATE]); + clk_prepare_enable(ctx->clocks[FIMC_CLK_WB_A]); + ctx->suspended = false; + } else { + clk_disable_unprepare(ctx->clocks[FIMC_CLK_GATE]); + clk_disable_unprepare(ctx->clocks[FIMC_CLK_WB_A]); + ctx->suspended = true; + } + + return 0; +} + #ifdef CONFIG_PM_SLEEP static int fimc_suspend(struct device *dev) { @@ -1806,7 +1807,6 @@ static int fimc_resume(struct device *dev) } #endif -#ifdef CONFIG_PM static int fimc_runtime_suspend(struct device *dev) { struct fimc_context *ctx = get_fimc_context(dev); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 750a9e6b9e8d..3d1aba67758b 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -41,7 +41,6 @@ * CPU Interface. */ -#define FIMD_DEFAULT_FRAMERATE 60 #define MIN_FB_WIDTH_FOR_16WORD_BURST 128 /* position control register for hardware window 0, 2 ~ 4.*/ @@ -377,16 +376,6 @@ static u32 fimd_calc_clkdiv(struct fimd_context *ctx, return (clkdiv < 0x100) ? clkdiv : 0xff; } -static bool fimd_mode_fixup(struct exynos_drm_crtc *crtc, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - if (adjusted_mode->vrefresh == 0) - adjusted_mode->vrefresh = FIMD_DEFAULT_FRAMERATE; - - return true; -} - static void fimd_commit(struct exynos_drm_crtc *crtc) { struct fimd_context *ctx = crtc->ctx; @@ -882,13 +871,12 @@ static void fimd_dp_clock_enable(struct exynos_drm_crtc *crtc, bool enable) return; val = enable ? DP_MIE_CLK_DP_ENABLE : DP_MIE_CLK_DISABLE; - writel(DP_MIE_CLK_DP_ENABLE, ctx->regs + DP_MIE_CLKCON); + writel(val, ctx->regs + DP_MIE_CLKCON); } static const struct exynos_drm_crtc_ops fimd_crtc_ops = { .enable = fimd_enable, .disable = fimd_disable, - .mode_fixup = fimd_mode_fixup, .commit = fimd_commit, .enable_vblank = fimd_enable_vblank, .disable_vblank = fimd_disable_vblank, diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 3734c34aed16..c17efdb238a6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -1059,7 +1059,6 @@ int exynos_g2d_get_ver_ioctl(struct drm_device *drm_dev, void *data, return 0; } -EXPORT_SYMBOL_GPL(exynos_g2d_get_ver_ioctl); int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data, struct drm_file *file) @@ -1230,7 +1229,6 @@ err: g2d_put_cmdlist(g2d, node); return ret; } -EXPORT_SYMBOL_GPL(exynos_g2d_set_cmdlist_ioctl); int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data, struct drm_file *file) @@ -1293,7 +1291,6 @@ int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data, out: return 0; } -EXPORT_SYMBOL_GPL(exynos_g2d_exec_ioctl); static int g2d_subdrv_probe(struct drm_device *drm_dev, struct device *dev) { diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index f12fbc36b120..407afedb6003 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -56,39 +56,35 @@ static int exynos_drm_alloc_buf(struct exynos_drm_gem_obj *obj) nr_pages = obj->size >> PAGE_SHIFT; if (!is_drm_iommu_supported(dev)) { - dma_addr_t start_addr; - unsigned int i = 0; - obj->pages = drm_calloc_large(nr_pages, sizeof(struct page *)); if (!obj->pages) { DRM_ERROR("failed to allocate pages.\n"); return -ENOMEM; } + } - obj->cookie = dma_alloc_attrs(dev->dev, - obj->size, - &obj->dma_addr, GFP_KERNEL, - &obj->dma_attrs); - if (!obj->cookie) { - DRM_ERROR("failed to allocate buffer.\n"); + obj->cookie = dma_alloc_attrs(dev->dev, obj->size, &obj->dma_addr, + GFP_KERNEL, &obj->dma_attrs); + if (!obj->cookie) { + DRM_ERROR("failed to allocate buffer.\n"); + if (obj->pages) drm_free_large(obj->pages); - return -ENOMEM; - } + return -ENOMEM; + } + + if (obj->pages) { + dma_addr_t start_addr; + unsigned int i = 0; start_addr = obj->dma_addr; while (i < nr_pages) { - obj->pages[i] = phys_to_page(start_addr); + obj->pages[i] = pfn_to_page(dma_to_pfn(dev->dev, + start_addr)); start_addr += PAGE_SIZE; i++; } } else { - obj->pages = dma_alloc_attrs(dev->dev, obj->size, - &obj->dma_addr, GFP_KERNEL, - &obj->dma_attrs); - if (!obj->pages) { - DRM_ERROR("failed to allocate buffer.\n"); - return -ENOMEM; - } + obj->pages = obj->cookie; } DRM_DEBUG_KMS("dma_addr(0x%lx), size(0x%lx)\n", @@ -110,15 +106,11 @@ static void exynos_drm_free_buf(struct exynos_drm_gem_obj *obj) DRM_DEBUG_KMS("dma_addr(0x%lx), size(0x%lx)\n", (unsigned long)obj->dma_addr, obj->size); - if (!is_drm_iommu_supported(dev)) { - dma_free_attrs(dev->dev, obj->size, obj->cookie, - (dma_addr_t)obj->dma_addr, &obj->dma_attrs); - drm_free_large(obj->pages); - } else - dma_free_attrs(dev->dev, obj->size, obj->pages, - (dma_addr_t)obj->dma_addr, &obj->dma_attrs); + dma_free_attrs(dev->dev, obj->size, obj->cookie, + (dma_addr_t)obj->dma_addr, &obj->dma_attrs); - obj->dma_addr = (dma_addr_t)NULL; + if (!is_drm_iommu_supported(dev)) + drm_free_large(obj->pages); } static int exynos_drm_gem_handle_create(struct drm_gem_object *obj, @@ -156,18 +148,14 @@ void exynos_drm_gem_destroy(struct exynos_drm_gem_obj *exynos_gem_obj) * once dmabuf's refcount becomes 0. */ if (obj->import_attach) - goto out; - - exynos_drm_free_buf(exynos_gem_obj); - -out: - drm_gem_free_mmap_offset(obj); + drm_prime_gem_destroy(obj, exynos_gem_obj->sgt); + else + exynos_drm_free_buf(exynos_gem_obj); /* release file pointer to gem object. */ drm_gem_object_release(obj); kfree(exynos_gem_obj); - exynos_gem_obj = NULL; } unsigned long exynos_drm_gem_get_size(struct drm_device *dev, @@ -190,8 +178,7 @@ unsigned long exynos_drm_gem_get_size(struct drm_device *dev, return exynos_gem_obj->size; } - -struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev, +static struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev, unsigned long size) { struct exynos_drm_gem_obj *exynos_gem_obj; @@ -212,6 +199,13 @@ struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev, return ERR_PTR(ret); } + ret = drm_gem_create_mmap_offset(obj); + if (ret < 0) { + drm_gem_object_release(obj); + kfree(exynos_gem_obj); + return ERR_PTR(ret); + } + DRM_DEBUG_KMS("created file object = 0x%x\n", (unsigned int)obj->filp); return exynos_gem_obj; @@ -313,7 +307,7 @@ void exynos_drm_gem_put_dma_addr(struct drm_device *dev, drm_gem_object_unreference_unlocked(obj); } -int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem_obj *exynos_gem_obj, +static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem_obj *exynos_gem_obj, struct vm_area_struct *vma) { struct drm_device *drm_dev = exynos_gem_obj->base.dev; @@ -342,7 +336,8 @@ int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem_obj *exynos_gem_obj, int exynos_drm_gem_get_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) -{ struct exynos_drm_gem_obj *exynos_gem_obj; +{ + struct exynos_drm_gem_obj *exynos_gem_obj; struct drm_exynos_gem_info *args = data; struct drm_gem_object *obj; @@ -402,6 +397,7 @@ int exynos_drm_gem_dumb_create(struct drm_file *file_priv, struct drm_mode_create_dumb *args) { struct exynos_drm_gem_obj *exynos_gem_obj; + unsigned int flags; int ret; /* @@ -413,16 +409,12 @@ int exynos_drm_gem_dumb_create(struct drm_file *file_priv, args->pitch = args->width * ((args->bpp + 7) / 8); args->size = args->pitch * args->height; - if (is_drm_iommu_supported(dev)) { - exynos_gem_obj = exynos_drm_gem_create(dev, - EXYNOS_BO_NONCONTIG | EXYNOS_BO_WC, - args->size); - } else { - exynos_gem_obj = exynos_drm_gem_create(dev, - EXYNOS_BO_CONTIG | EXYNOS_BO_WC, - args->size); - } + if (is_drm_iommu_supported(dev)) + flags = EXYNOS_BO_NONCONTIG | EXYNOS_BO_WC; + else + flags = EXYNOS_BO_CONTIG | EXYNOS_BO_WC; + exynos_gem_obj = exynos_drm_gem_create(dev, flags, args->size); if (IS_ERR(exynos_gem_obj)) { dev_warn(dev->dev, "FB allocation failed.\n"); return PTR_ERR(exynos_gem_obj); @@ -460,14 +452,9 @@ int exynos_drm_gem_dumb_map_offset(struct drm_file *file_priv, goto unlock; } - ret = drm_gem_create_mmap_offset(obj); - if (ret) - goto out; - *offset = drm_vma_node_offset_addr(&obj->vma_node); DRM_DEBUG_KMS("offset = 0x%lx\n", (unsigned long)*offset); -out: drm_gem_object_unreference(obj); unlock: mutex_unlock(&dev->struct_mutex); @@ -543,7 +530,6 @@ int exynos_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma) err_close_vm: drm_gem_vm_close(vma); - drm_gem_free_mmap_offset(obj); return ret; } @@ -588,6 +574,8 @@ exynos_drm_gem_prime_import_sg_table(struct drm_device *dev, if (ret < 0) goto err_free_large; + exynos_gem_obj->sgt = sgt; + if (sgt->nents == 1) { /* always physically continuous memory if sgt->nents is 1. */ exynos_gem_obj->flags |= EXYNOS_BO_CONTIG; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h index cd62f8410d1e..b62d1007c0e0 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.h +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h @@ -39,6 +39,7 @@ * - this address could be physical address without IOMMU and * device address with IOMMU. * @pages: Array of backing pages. + * @sgt: Imported sg_table. * * P.S. this object would be transferred to user as kms_bo.handle so * user can access the buffer through kms_bo.handle. @@ -52,6 +53,7 @@ struct exynos_drm_gem_obj { dma_addr_t dma_addr; struct dma_attrs dma_attrs; struct page **pages; + struct sg_table *sgt; }; struct page **exynos_gem_get_pages(struct drm_gem_object *obj, gfp_t gfpmask); @@ -59,10 +61,6 @@ struct page **exynos_gem_get_pages(struct drm_gem_object *obj, gfp_t gfpmask); /* destroy a buffer with gem object */ void exynos_drm_gem_destroy(struct exynos_drm_gem_obj *exynos_gem_obj); -/* create a private gem object and initialize it. */ -struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev, - unsigned long size); - /* create a new buffer with gem object */ struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_device *dev, unsigned int flags, diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c index 425e70625388..2f5c118f4c8e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c +++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c @@ -786,6 +786,7 @@ static int rotator_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM static int rotator_clk_crtl(struct rot_context *rot, bool enable) { if (enable) { @@ -822,7 +823,6 @@ static int rotator_resume(struct device *dev) } #endif -#ifdef CONFIG_PM static int rotator_runtime_suspend(struct device *dev) { struct rot_context *rot = dev_get_drvdata(dev); diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 3e4be5a3becd..6ade06888432 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -462,11 +462,17 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0); drm_mode_connector_set_path_property(connector, pathprop); + return connector; +} + +static void intel_dp_register_mst_connector(struct drm_connector *connector) +{ + struct intel_connector *intel_connector = to_intel_connector(connector); + struct drm_device *dev = connector->dev; drm_modeset_lock_all(dev); intel_connector_add_to_fbdev(intel_connector); drm_modeset_unlock_all(dev); drm_connector_register(&intel_connector->base); - return connector; } static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, @@ -512,6 +518,7 @@ static void intel_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) static struct drm_dp_mst_topology_cbs mst_cbs = { .add_connector = intel_dp_add_mst_connector, + .register_connector = intel_dp_register_mst_connector, .destroy_connector = intel_dp_destroy_mst_connector, .hotplug = intel_dp_mst_hotplug, }; diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c index 53c0173a39fe..b17785719598 100644 --- a/drivers/gpu/drm/i915/intel_hotplug.c +++ b/drivers/gpu/drm/i915/intel_hotplug.c @@ -180,7 +180,7 @@ static void intel_hpd_irq_storm_disable(struct drm_i915_private *dev_priv) /* Enable polling and queue hotplug re-enabling. */ if (hpd_disabled) { - drm_kms_helper_poll_enable(dev); + drm_kms_helper_poll_enable_locked(dev); mod_delayed_work(system_wq, &dev_priv->hotplug.reenable_work, msecs_to_jiffies(HPD_STORM_REENABLE_DELAY)); } diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 72e0edd7bbde..7412caedcf7f 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -484,18 +484,18 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring) status_pointer = I915_READ(RING_CONTEXT_STATUS_PTR(ring)); read_pointer = ring->next_context_status_buffer; - write_pointer = status_pointer & 0x07; + write_pointer = status_pointer & GEN8_CSB_PTR_MASK; if (read_pointer > write_pointer) - write_pointer += 6; + write_pointer += GEN8_CSB_ENTRIES; spin_lock(&ring->execlist_lock); while (read_pointer < write_pointer) { read_pointer++; status = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + - (read_pointer % 6) * 8); + (read_pointer % GEN8_CSB_ENTRIES) * 8); status_id = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + - (read_pointer % 6) * 8 + 4); + (read_pointer % GEN8_CSB_ENTRIES) * 8 + 4); if (status & GEN8_CTX_STATUS_IDLE_ACTIVE) continue; @@ -521,10 +521,12 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring) spin_unlock(&ring->execlist_lock); WARN(submit_contexts > 2, "More than two context complete events?\n"); - ring->next_context_status_buffer = write_pointer % 6; + ring->next_context_status_buffer = write_pointer % GEN8_CSB_ENTRIES; I915_WRITE(RING_CONTEXT_STATUS_PTR(ring), - _MASKED_FIELD(0x07 << 8, ((u32)ring->next_context_status_buffer & 0x07) << 8)); + _MASKED_FIELD(GEN8_CSB_PTR_MASK << 8, + ((u32)ring->next_context_status_buffer & + GEN8_CSB_PTR_MASK) << 8)); } static int execlists_context_queue(struct drm_i915_gem_request *request) @@ -1422,6 +1424,7 @@ static int gen8_init_common_ring(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; + u8 next_context_status_buffer_hw; I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | ring->irq_keep_mask)); I915_WRITE(RING_HWSTAM(ring->mmio_base), 0xffffffff); @@ -1436,7 +1439,29 @@ static int gen8_init_common_ring(struct intel_engine_cs *ring) _MASKED_BIT_DISABLE(GFX_REPLAY_MODE) | _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE)); POSTING_READ(RING_MODE_GEN7(ring)); - ring->next_context_status_buffer = 0; + + /* + * Instead of resetting the Context Status Buffer (CSB) read pointer to + * zero, we need to read the write pointer from hardware and use its + * value because "this register is power context save restored". + * Effectively, these states have been observed: + * + * | Suspend-to-idle (freeze) | Suspend-to-RAM (mem) | + * BDW | CSB regs not reset | CSB regs reset | + * CHT | CSB regs not reset | CSB regs not reset | + */ + next_context_status_buffer_hw = (I915_READ(RING_CONTEXT_STATUS_PTR(ring)) + & GEN8_CSB_PTR_MASK); + + /* + * When the CSB registers are reset (also after power-up / gpu reset), + * CSB write pointer is set to all 1's, which is not valid, use '5' in + * this special case, so the first element read is CSB[0]. + */ + if (next_context_status_buffer_hw == GEN8_CSB_PTR_MASK) + next_context_status_buffer_hw = (GEN8_CSB_ENTRIES - 1); + + ring->next_context_status_buffer = next_context_status_buffer_hw; DRM_DEBUG_DRIVER("Execlists enabled for %s\n", ring->name); memset(&ring->hangcheck, 0, sizeof(ring->hangcheck)); diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h index 64f89f9982a2..3c63bb32ad81 100644 --- a/drivers/gpu/drm/i915/intel_lrc.h +++ b/drivers/gpu/drm/i915/intel_lrc.h @@ -25,6 +25,8 @@ #define _INTEL_LRC_H_ #define GEN8_LR_CONTEXT_ALIGN 4096 +#define GEN8_CSB_ENTRIES 6 +#define GEN8_CSB_PTR_MASK 0x07 /* Execlists regs */ #define RING_ELSP(ring) ((ring)->mmio_base+0x230) diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index af7fdb3bd663..7401cf90b0db 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -246,7 +246,8 @@ static void skl_power_well_post_enable(struct drm_i915_private *dev_priv, } if (power_well->data == SKL_DISP_PW_1) { - intel_prepare_ddi(dev); + if (!dev_priv->power_domains.initializing) + intel_prepare_ddi(dev); gen8_irq_power_well_post_enable(dev_priv, 1 << PIPE_A); } } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index cc6c228e11c8..e905c00acf1a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -469,9 +469,13 @@ nouveau_display_create(struct drm_device *dev) if (drm->device.info.family < NV_DEVICE_INFO_V0_TESLA) { dev->mode_config.max_width = 4096; dev->mode_config.max_height = 4096; - } else { + } else + if (drm->device.info.family < NV_DEVICE_INFO_V0_FERMI) { dev->mode_config.max_width = 8192; dev->mode_config.max_height = 8192; + } else { + dev->mode_config.max_width = 16384; + dev->mode_config.max_height = 16384; } dev->mode_config.preferred_depth = 24; diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 2791701685dc..59f27e774acb 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -178,8 +178,30 @@ nouveau_fbcon_sync(struct fb_info *info) return 0; } +static int +nouveau_fbcon_open(struct fb_info *info, int user) +{ + struct nouveau_fbdev *fbcon = info->par; + struct nouveau_drm *drm = nouveau_drm(fbcon->dev); + int ret = pm_runtime_get_sync(drm->dev->dev); + if (ret < 0 && ret != -EACCES) + return ret; + return 0; +} + +static int +nouveau_fbcon_release(struct fb_info *info, int user) +{ + struct nouveau_fbdev *fbcon = info->par; + struct nouveau_drm *drm = nouveau_drm(fbcon->dev); + pm_runtime_put(drm->dev->dev); + return 0; +} + static struct fb_ops nouveau_fbcon_ops = { .owner = THIS_MODULE, + .fb_open = nouveau_fbcon_open, + .fb_release = nouveau_fbcon_release, .fb_check_var = drm_fb_helper_check_var, .fb_set_par = drm_fb_helper_set_par, .fb_fillrect = nouveau_fbcon_fillrect, @@ -195,6 +217,8 @@ static struct fb_ops nouveau_fbcon_ops = { static struct fb_ops nouveau_fbcon_sw_ops = { .owner = THIS_MODULE, + .fb_open = nouveau_fbcon_open, + .fb_release = nouveau_fbcon_release, .fb_check_var = drm_fb_helper_check_var, .fb_set_par = drm_fb_helper_set_par, .fb_fillrect = drm_fb_helper_cfb_fillrect, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c index 65af31441e9c..a7d69ce7abc1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c @@ -267,6 +267,12 @@ init_i2c(struct nvbios_init *init, int index) index = NVKM_I2C_BUS_PRI; if (init->outp && init->outp->i2c_upper_default) index = NVKM_I2C_BUS_SEC; + } else + if (index == 0x80) { + index = NVKM_I2C_BUS_PRI; + } else + if (index == 0x81) { + index = NVKM_I2C_BUS_SEC; } bus = nvkm_i2c_bus_find(i2c, index); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h index e0ec2a6b7b79..212800ecdce9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h @@ -8,7 +8,10 @@ struct nvbios_source { void *(*init)(struct nvkm_bios *, const char *); void (*fini)(void *); u32 (*read)(void *, u32 offset, u32 length, struct nvkm_bios *); + u32 (*size)(void *); bool rw; + bool ignore_checksum; + bool no_pcir; }; int nvbios_extend(struct nvkm_bios *, u32 length); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c index 792f017525f6..b2557e87afdd 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c @@ -45,7 +45,7 @@ shadow_fetch(struct nvkm_bios *bios, struct shadow *mthd, u32 upto) u32 read = mthd->func->read(data, start, limit - start, bios); bios->size = start + read; } - return bios->size >= limit; + return bios->size >= upto; } static int @@ -55,14 +55,22 @@ shadow_image(struct nvkm_bios *bios, int idx, u32 offset, struct shadow *mthd) struct nvbios_image image; int score = 1; - if (!shadow_fetch(bios, mthd, offset + 0x1000)) { - nvkm_debug(subdev, "%08x: header fetch failed\n", offset); - return 0; - } + if (mthd->func->no_pcir) { + image.base = 0; + image.type = 0; + image.size = mthd->func->size(mthd->data); + image.last = 1; + } else { + if (!shadow_fetch(bios, mthd, offset + 0x1000)) { + nvkm_debug(subdev, "%08x: header fetch failed\n", + offset); + return 0; + } - if (!nvbios_image(bios, idx, &image)) { - nvkm_debug(subdev, "image %d invalid\n", idx); - return 0; + if (!nvbios_image(bios, idx, &image)) { + nvkm_debug(subdev, "image %d invalid\n", idx); + return 0; + } } nvkm_debug(subdev, "%08x: type %02x, %d bytes\n", image.base, image.type, image.size); @@ -74,7 +82,8 @@ shadow_image(struct nvkm_bios *bios, int idx, u32 offset, struct shadow *mthd) switch (image.type) { case 0x00: - if (nvbios_checksum(&bios->data[image.base], image.size)) { + if (!mthd->func->ignore_checksum && + nvbios_checksum(&bios->data[image.base], image.size)) { nvkm_debug(subdev, "%08x: checksum failed\n", image.base); if (mthd->func->rw) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c index bd60d7dd09f5..4bf486b57101 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c @@ -21,6 +21,7 @@ * */ #include "priv.h" + #include <core/pci.h> #if defined(__powerpc__) @@ -33,17 +34,26 @@ static u32 of_read(void *data, u32 offset, u32 length, struct nvkm_bios *bios) { struct priv *priv = data; - if (offset + length <= priv->size) { + if (offset < priv->size) { + length = min_t(u32, length, priv->size - offset); memcpy_fromio(bios->data + offset, priv->data + offset, length); return length; } return 0; } +static u32 +of_size(void *data) +{ + struct priv *priv = data; + return priv->size; +} + static void * of_init(struct nvkm_bios *bios, const char *name) { - struct pci_dev *pdev = bios->subdev.device->func->pci(bios->subdev.device)->pdev; + struct nvkm_device *device = bios->subdev.device; + struct pci_dev *pdev = device->func->pci(device)->pdev; struct device_node *dn; struct priv *priv; if (!(dn = pci_device_to_OF_node(pdev))) @@ -62,7 +72,10 @@ nvbios_of = { .init = of_init, .fini = (void(*)(void *))kfree, .read = of_read, + .size = of_size, .rw = false, + .ignore_checksum = true, + .no_pcir = true, }; #else const struct nvbios_source diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/agp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/agp.c index 814cb51cc873..385a90f91ed6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/agp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/agp.c @@ -35,6 +35,8 @@ static const struct nvkm_device_agp_quirk nvkm_device_agp_quirks[] = { /* VIA Apollo PRO133x / GeForce FX 5600 Ultra - fdo#20341 */ { PCI_VENDOR_ID_VIA, 0x0691, PCI_VENDOR_ID_NVIDIA, 0x0311, 2 }, + /* SiS 761 does not support AGP cards, use PCI mode */ + { PCI_VENDOR_ID_SI, 0x0761, PCI_ANY_ID, PCI_ANY_ID, 0 }, {}, }; @@ -137,8 +139,10 @@ nvkm_agp_ctor(struct nvkm_pci *pci) while (quirk->hostbridge_vendor) { if (info.device->vendor == quirk->hostbridge_vendor && info.device->device == quirk->hostbridge_device && - pci->pdev->vendor == quirk->chip_vendor && - pci->pdev->device == quirk->chip_device) { + (quirk->chip_vendor == (u16)PCI_ANY_ID || + pci->pdev->vendor == quirk->chip_vendor) && + (quirk->chip_device == (u16)PCI_ANY_ID || + pci->pdev->device == quirk->chip_device)) { nvkm_info(subdev, "forcing default agp mode to %dX, " "use NvAGP=<mode> to override\n", quirk->mode); diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index dd845f82cc24..183aea1abebc 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -244,6 +244,10 @@ static int qxl_crtc_page_flip(struct drm_crtc *crtc, ret = qxl_bo_reserve(bo, false); if (ret) return ret; + ret = qxl_bo_pin(bo, bo->type, NULL); + qxl_bo_unreserve(bo); + if (ret) + return ret; qxl_draw_dirty_fb(qdev, qfb_src, bo, 0, 0, &norect, one_clip_rect, inc); @@ -257,7 +261,11 @@ static int qxl_crtc_page_flip(struct drm_crtc *crtc, } drm_vblank_put(dev, qcrtc->index); - qxl_bo_unreserve(bo); + ret = qxl_bo_reserve(bo, false); + if (!ret) { + qxl_bo_unpin(bo); + qxl_bo_unreserve(bo); + } return 0; } @@ -618,7 +626,7 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc, adjusted_mode->hdisplay, adjusted_mode->vdisplay); - if (qcrtc->index == 0) + if (bo->is_primary == false) recreate_primary = true; if (bo->surf.stride * bo->surf.height > qdev->vram_size) { diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c index 41c422fee31a..c4a552637c93 100644 --- a/drivers/gpu/drm/qxl/qxl_fb.c +++ b/drivers/gpu/drm/qxl/qxl_fb.c @@ -144,14 +144,17 @@ static void qxl_dirty_update(struct qxl_fbdev *qfbdev, spin_lock_irqsave(&qfbdev->dirty.lock, flags); - if (qfbdev->dirty.y1 < y) - y = qfbdev->dirty.y1; - if (qfbdev->dirty.y2 > y2) - y2 = qfbdev->dirty.y2; - if (qfbdev->dirty.x1 < x) - x = qfbdev->dirty.x1; - if (qfbdev->dirty.x2 > x2) - x2 = qfbdev->dirty.x2; + if ((qfbdev->dirty.y2 - qfbdev->dirty.y1) && + (qfbdev->dirty.x2 - qfbdev->dirty.x1)) { + if (qfbdev->dirty.y1 < y) + y = qfbdev->dirty.y1; + if (qfbdev->dirty.y2 > y2) + y2 = qfbdev->dirty.y2; + if (qfbdev->dirty.x1 < x) + x = qfbdev->dirty.x1; + if (qfbdev->dirty.x2 > x2) + x2 = qfbdev->dirty.x2; + } qfbdev->dirty.x1 = x; qfbdev->dirty.x2 = x2; diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c index b66ec331c17c..4efa8e261baf 100644 --- a/drivers/gpu/drm/qxl/qxl_release.c +++ b/drivers/gpu/drm/qxl/qxl_release.c @@ -307,7 +307,7 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev, idr_ret = qxl_release_alloc(qdev, QXL_RELEASE_SURFACE_CMD, release); if (idr_ret < 0) return idr_ret; - bo = qxl_bo_ref(to_qxl_bo(entry->tv.bo)); + bo = to_qxl_bo(entry->tv.bo); (*release)->release_offset = create_rel->release_offset + 64; @@ -316,8 +316,6 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev, info = qxl_release_map(qdev, *release); info->id = idr_ret; qxl_release_unmap(qdev, *release, info); - - qxl_bo_unref(&bo); return 0; } diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index c3872598b85a..65adb9c72377 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -1624,8 +1624,9 @@ radeon_atom_encoder_dpms_avivo(struct drm_encoder *encoder, int mode) } else atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) { - args.ucAction = ATOM_LCD_BLON; - atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); + struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; + + atombios_set_backlight_level(radeon_encoder, dig->backlight_level); } break; case DRM_MODE_DPMS_STANDBY: @@ -1706,8 +1707,7 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON, 0); } if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) - atombios_dig_transmitter_setup(encoder, - ATOM_TRANSMITTER_ACTION_LCD_BLON, 0, 0); + atombios_set_backlight_level(radeon_encoder, dig->backlight_level); if (ext_encoder) atombios_external_encoder_setup(encoder, ext_encoder, ATOM_ENABLE); break; diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index d2e9e9efc159..6743174acdbc 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -1633,18 +1633,8 @@ int radeon_modeset_init(struct radeon_device *rdev) radeon_fbdev_init(rdev); drm_kms_helper_poll_init(rdev->ddev); - if (rdev->pm.dpm_enabled) { - /* do dpm late init */ - ret = radeon_pm_late_init(rdev); - if (ret) { - rdev->pm.dpm_enabled = false; - DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n"); - } - /* set the dpm state for PX since there won't be - * a modeset to call this. - */ - radeon_pm_compute_clocks(rdev); - } + /* do pm late init */ + ret = radeon_pm_late_init(rdev); return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c index 5e09c061847f..744f5c49c664 100644 --- a/drivers/gpu/drm/radeon/radeon_dp_mst.c +++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c @@ -265,7 +265,6 @@ static struct drm_connector *radeon_dp_add_mst_connector(struct drm_dp_mst_topol { struct radeon_connector *master = container_of(mgr, struct radeon_connector, mst_mgr); struct drm_device *dev = master->base.dev; - struct radeon_device *rdev = dev->dev_private; struct radeon_connector *radeon_connector; struct drm_connector *connector; @@ -284,14 +283,22 @@ static struct drm_connector *radeon_dp_add_mst_connector(struct drm_dp_mst_topol radeon_connector->mst_encoder = radeon_dp_create_fake_mst_encoder(master); drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0); + drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0); drm_mode_connector_set_path_property(connector, pathprop); + return connector; +} + +static void radeon_dp_register_mst_connector(struct drm_connector *connector) +{ + struct drm_device *dev = connector->dev; + struct radeon_device *rdev = dev->dev_private; + drm_modeset_lock_all(dev); radeon_fb_add_connector(rdev, connector); drm_modeset_unlock_all(dev); drm_connector_register(connector); - return connector; } static void radeon_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, @@ -324,6 +331,7 @@ static void radeon_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) struct drm_dp_mst_topology_cbs mst_cbs = { .add_connector = radeon_dp_add_mst_connector, + .register_connector = radeon_dp_register_mst_connector, .destroy_connector = radeon_dp_destroy_mst_connector, .hotplug = radeon_dp_mst_hotplug, }; diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c index 7214858ffcea..26da2f4d7b4f 100644 --- a/drivers/gpu/drm/radeon/radeon_fb.c +++ b/drivers/gpu/drm/radeon/radeon_fb.c @@ -48,40 +48,10 @@ struct radeon_fbdev { struct radeon_device *rdev; }; -/** - * radeon_fb_helper_set_par - Hide cursor on CRTCs used by fbdev. - * - * @info: fbdev info - * - * This function hides the cursor on all CRTCs used by fbdev. - */ -static int radeon_fb_helper_set_par(struct fb_info *info) -{ - int ret; - - ret = drm_fb_helper_set_par(info); - - /* XXX: with universal plane support fbdev will automatically disable - * all non-primary planes (including the cursor) - */ - if (ret == 0) { - struct drm_fb_helper *fb_helper = info->par; - int i; - - for (i = 0; i < fb_helper->crtc_count; i++) { - struct drm_crtc *crtc = fb_helper->crtc_info[i].mode_set.crtc; - - radeon_crtc_cursor_set2(crtc, NULL, 0, 0, 0, 0, 0); - } - } - - return ret; -} - static struct fb_ops radeonfb_ops = { .owner = THIS_MODULE, .fb_check_var = drm_fb_helper_check_var, - .fb_set_par = radeon_fb_helper_set_par, + .fb_set_par = drm_fb_helper_set_par, .fb_fillrect = drm_fb_helper_cfb_fillrect, .fb_copyarea = drm_fb_helper_cfb_copyarea, .fb_imageblit = drm_fb_helper_cfb_imageblit, @@ -427,3 +397,19 @@ void radeon_fb_remove_connector(struct radeon_device *rdev, struct drm_connector { drm_fb_helper_remove_one_connector(&rdev->mode_info.rfbdev->helper, connector); } + +void radeon_fbdev_restore_mode(struct radeon_device *rdev) +{ + struct radeon_fbdev *rfbdev = rdev->mode_info.rfbdev; + struct drm_fb_helper *fb_helper; + int ret; + + if (!rfbdev) + return; + + fb_helper = &rfbdev->helper; + + ret = drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper); + if (ret) + DRM_DEBUG("failed to restore crtc mode\n"); +} diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 4a119c255ba9..0e932bf932c1 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -598,7 +598,7 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file * Outdated mess for old drm with Xorg being in charge (void function now). */ /** - * radeon_driver_firstopen_kms - drm callback for last close + * radeon_driver_lastclose_kms - drm callback for last close * * @dev: drm dev pointer * @@ -606,6 +606,9 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file */ void radeon_driver_lastclose_kms(struct drm_device *dev) { + struct radeon_device *rdev = dev->dev_private; + + radeon_fbdev_restore_mode(rdev); vga_switcheroo_process_delayed_switch(); } diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h index aecc3e3dec0c..457b026a0972 100644 --- a/drivers/gpu/drm/radeon/radeon_mode.h +++ b/drivers/gpu/drm/radeon/radeon_mode.h @@ -980,6 +980,7 @@ int radeon_fbdev_init(struct radeon_device *rdev); void radeon_fbdev_fini(struct radeon_device *rdev); void radeon_fbdev_set_suspend(struct radeon_device *rdev, int state); bool radeon_fbdev_robj_is_fb(struct radeon_device *rdev, struct radeon_bo *robj); +void radeon_fbdev_restore_mode(struct radeon_device *rdev); void radeon_fb_output_poll_changed(struct radeon_device *rdev); diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 05751f3f8444..44489cce7458 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1326,14 +1326,6 @@ static int radeon_pm_init_old(struct radeon_device *rdev) INIT_DELAYED_WORK(&rdev->pm.dynpm_idle_work, radeon_dynpm_idle_work_handler); if (rdev->pm.num_power_states > 1) { - /* where's the best place to put these? */ - ret = device_create_file(rdev->dev, &dev_attr_power_profile); - if (ret) - DRM_ERROR("failed to create device file for power profile\n"); - ret = device_create_file(rdev->dev, &dev_attr_power_method); - if (ret) - DRM_ERROR("failed to create device file for power method\n"); - if (radeon_debugfs_pm_init(rdev)) { DRM_ERROR("Failed to register debugfs file for PM!\n"); } @@ -1391,20 +1383,6 @@ static int radeon_pm_init_dpm(struct radeon_device *rdev) goto dpm_failed; rdev->pm.dpm_enabled = true; - ret = device_create_file(rdev->dev, &dev_attr_power_dpm_state); - if (ret) - DRM_ERROR("failed to create device file for dpm state\n"); - ret = device_create_file(rdev->dev, &dev_attr_power_dpm_force_performance_level); - if (ret) - DRM_ERROR("failed to create device file for dpm state\n"); - /* XXX: these are noops for dpm but are here for backwards compat */ - ret = device_create_file(rdev->dev, &dev_attr_power_profile); - if (ret) - DRM_ERROR("failed to create device file for power profile\n"); - ret = device_create_file(rdev->dev, &dev_attr_power_method); - if (ret) - DRM_ERROR("failed to create device file for power method\n"); - if (radeon_debugfs_pm_init(rdev)) { DRM_ERROR("Failed to register debugfs file for dpm!\n"); } @@ -1545,9 +1523,44 @@ int radeon_pm_late_init(struct radeon_device *rdev) int ret = 0; if (rdev->pm.pm_method == PM_METHOD_DPM) { - mutex_lock(&rdev->pm.mutex); - ret = radeon_dpm_late_enable(rdev); - mutex_unlock(&rdev->pm.mutex); + if (rdev->pm.dpm_enabled) { + ret = device_create_file(rdev->dev, &dev_attr_power_dpm_state); + if (ret) + DRM_ERROR("failed to create device file for dpm state\n"); + ret = device_create_file(rdev->dev, &dev_attr_power_dpm_force_performance_level); + if (ret) + DRM_ERROR("failed to create device file for dpm state\n"); + /* XXX: these are noops for dpm but are here for backwards compat */ + ret = device_create_file(rdev->dev, &dev_attr_power_profile); + if (ret) + DRM_ERROR("failed to create device file for power profile\n"); + ret = device_create_file(rdev->dev, &dev_attr_power_method); + if (ret) + DRM_ERROR("failed to create device file for power method\n"); + + mutex_lock(&rdev->pm.mutex); + ret = radeon_dpm_late_enable(rdev); + mutex_unlock(&rdev->pm.mutex); + if (ret) { + rdev->pm.dpm_enabled = false; + DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n"); + } else { + /* set the dpm state for PX since there won't be + * a modeset to call this. + */ + radeon_pm_compute_clocks(rdev); + } + } + } else { + if (rdev->pm.num_power_states > 1) { + /* where's the best place to put these? */ + ret = device_create_file(rdev->dev, &dev_attr_power_profile); + if (ret) + DRM_ERROR("failed to create device file for power profile\n"); + ret = device_create_file(rdev->dev, &dev_attr_power_method); + if (ret) + DRM_ERROR("failed to create device file for power method\n"); + } } return ret; } diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index e9115d3f67b0..e72bf46042e0 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2928,6 +2928,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = { { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1762, 0x2015, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 }, { 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/virtio/virtgpu_debugfs.c b/drivers/gpu/drm/virtio/virtgpu_debugfs.c index db8b49101a8b..512263919282 100644 --- a/drivers/gpu/drm/virtio/virtgpu_debugfs.c +++ b/drivers/gpu/drm/virtio/virtgpu_debugfs.c @@ -34,8 +34,8 @@ virtio_gpu_debugfs_irq_info(struct seq_file *m, void *data) struct drm_info_node *node = (struct drm_info_node *) m->private; struct virtio_gpu_device *vgdev = node->minor->dev->dev_private; - seq_printf(m, "fence %ld %lld\n", - atomic64_read(&vgdev->fence_drv.last_seq), + seq_printf(m, "fence %llu %lld\n", + (u64)atomic64_read(&vgdev->fence_drv.last_seq), vgdev->fence_drv.sync_seq); return 0; } diff --git a/drivers/gpu/drm/virtio/virtgpu_fence.c b/drivers/gpu/drm/virtio/virtgpu_fence.c index 1da632631dac..67097c9ce9c1 100644 --- a/drivers/gpu/drm/virtio/virtgpu_fence.c +++ b/drivers/gpu/drm/virtio/virtgpu_fence.c @@ -61,7 +61,7 @@ static void virtio_timeline_value_str(struct fence *f, char *str, int size) { struct virtio_gpu_fence *fence = to_virtio_fence(f); - snprintf(str, size, "%lu", atomic64_read(&fence->drv->last_seq)); + snprintf(str, size, "%llu", (u64)atomic64_read(&fence->drv->last_seq)); } static const struct fence_ops virtio_fence_ops = { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c index 5ae8f921da2a..8a76821177a6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c @@ -681,6 +681,14 @@ static bool vmw_cmdbuf_try_alloc(struct vmw_cmdbuf_man *man, 0, 0, DRM_MM_SEARCH_DEFAULT, DRM_MM_CREATE_DEFAULT); + if (ret) { + (void) vmw_cmdbuf_man_process(man); + ret = drm_mm_insert_node_generic(&man->mm, info->node, + info->page_size, 0, 0, + DRM_MM_SEARCH_DEFAULT, + DRM_MM_CREATE_DEFAULT); + } + spin_unlock_bh(&man->lock); info->done = !ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 64b50409fa07..03f63c749c02 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -657,7 +657,8 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base) struct vmw_resource *res = &user_srf->srf.res; *p_base = NULL; - ttm_base_object_unref(&user_srf->backup_base); + if (user_srf->backup_base) + ttm_base_object_unref(&user_srf->backup_base); vmw_resource_unreference(&res); } diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index 3dd2de31a2f8..472b88285c75 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -24,6 +24,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/delay.h> +#include <linux/dmi.h> #include <linux/i2c.h> #include <linux/clk.h> #include <linux/clk-provider.h> @@ -51,6 +52,22 @@ static u32 i2c_dw_get_clk_rate_khz(struct dw_i2c_dev *dev) } #ifdef CONFIG_ACPI +/* + * The HCNT/LCNT information coming from ACPI should be the most accurate + * for given platform. However, some systems get it wrong. On such systems + * we get better results by calculating those based on the input clock. + */ +static const struct dmi_system_id dw_i2c_no_acpi_params[] = { + { + .ident = "Dell Inspiron 7348", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7348"), + }, + }, + { } +}; + static void dw_i2c_acpi_params(struct platform_device *pdev, char method[], u16 *hcnt, u16 *lcnt, u32 *sda_hold) { @@ -58,6 +75,9 @@ static void dw_i2c_acpi_params(struct platform_device *pdev, char method[], acpi_handle handle = ACPI_HANDLE(&pdev->dev); union acpi_object *obj; + if (dmi_check_system(dw_i2c_no_acpi_params)) + return; + if (ACPI_FAILURE(acpi_evaluate_object(handle, method, NULL, &buf))) return; @@ -253,12 +273,6 @@ static int dw_i2c_probe(struct platform_device *pdev) adap->dev.parent = &pdev->dev; adap->dev.of_node = pdev->dev.of_node; - r = i2c_add_numbered_adapter(adap); - if (r) { - dev_err(&pdev->dev, "failure adding adapter\n"); - return r; - } - if (dev->pm_runtime_disabled) { pm_runtime_forbid(&pdev->dev); } else { @@ -268,6 +282,13 @@ static int dw_i2c_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); } + r = i2c_add_numbered_adapter(adap); + if (r) { + dev_err(&pdev->dev, "failure adding adapter\n"); + pm_runtime_disable(&pdev->dev); + return r; + } + return 0; } diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index d8361dada584..d8b5a8fee1e6 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -690,15 +690,16 @@ static int rcar_i2c_probe(struct platform_device *pdev) return ret; } + pm_runtime_enable(dev); + platform_set_drvdata(pdev, priv); + ret = i2c_add_numbered_adapter(adap); if (ret < 0) { dev_err(dev, "reg adap failed: %d\n", ret); + pm_runtime_disable(dev); return ret; } - pm_runtime_enable(dev); - platform_set_drvdata(pdev, priv); - dev_info(dev, "probed\n"); return 0; diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index 50bfd8cef5f2..5df819610d52 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -1243,17 +1243,19 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) i2c->adap.nr = i2c->pdata->bus_num; i2c->adap.dev.of_node = pdev->dev.of_node; + platform_set_drvdata(pdev, i2c); + + pm_runtime_enable(&pdev->dev); + ret = i2c_add_numbered_adapter(&i2c->adap); if (ret < 0) { dev_err(&pdev->dev, "failed to add bus to i2c core\n"); + pm_runtime_disable(&pdev->dev); s3c24xx_i2c_deregister_cpufreq(i2c); clk_unprepare(i2c->clk); return ret; } - platform_set_drvdata(pdev, i2c); - - pm_runtime_enable(&pdev->dev); pm_runtime_enable(&i2c->adap.dev); dev_info(&pdev->dev, "%s: S3C I2C adapter\n", dev_name(&i2c->adap.dev)); diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 5f89f1e3c2f2..a59c3111f7fb 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -694,12 +694,12 @@ static int i2c_device_probe(struct device *dev) goto err_clear_wakeup_irq; status = dev_pm_domain_attach(&client->dev, true); - if (status != -EPROBE_DEFER) { - status = driver->probe(client, i2c_match_id(driver->id_table, - client)); - if (status) - goto err_detach_pm_domain; - } + if (status == -EPROBE_DEFER) + goto err_clear_wakeup_irq; + + status = driver->probe(client, i2c_match_id(driver->id_table, client)); + if (status) + goto err_detach_pm_domain; return 0; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index b1ab13f3e182..59a2dafc8c57 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1232,14 +1232,32 @@ static bool cma_match_private_data(struct rdma_id_private *id_priv, return true; } +static bool cma_protocol_roce_dev_port(struct ib_device *device, int port_num) +{ + enum rdma_link_layer ll = rdma_port_get_link_layer(device, port_num); + enum rdma_transport_type transport = + rdma_node_get_transport(device->node_type); + + return ll == IB_LINK_LAYER_ETHERNET && transport == RDMA_TRANSPORT_IB; +} + +static bool cma_protocol_roce(const struct rdma_cm_id *id) +{ + struct ib_device *device = id->device; + const int port_num = id->port_num ?: rdma_start_port(device); + + return cma_protocol_roce_dev_port(device, port_num); +} + static bool cma_match_net_dev(const struct rdma_id_private *id_priv, const struct net_device *net_dev) { const struct rdma_addr *addr = &id_priv->id.route.addr; if (!net_dev) - /* This request is an AF_IB request */ - return addr->src_addr.ss_family == AF_IB; + /* This request is an AF_IB request or a RoCE request */ + return addr->src_addr.ss_family == AF_IB || + cma_protocol_roce(&id_priv->id); return !addr->dev_addr.bound_dev_if || (net_eq(dev_net(net_dev), &init_net) && @@ -1294,6 +1312,10 @@ static struct rdma_id_private *cma_id_from_event(struct ib_cm_id *cm_id, if (PTR_ERR(*net_dev) == -EAFNOSUPPORT) { /* Assuming the protocol is AF_IB */ *net_dev = NULL; + } else if (cma_protocol_roce_dev_port(req.device, req.port)) { + /* TODO find the net dev matching the request parameters + * through the RoCE GID table */ + *net_dev = NULL; } else { return ERR_CAST(*net_dev); } @@ -1593,11 +1615,16 @@ static struct rdma_id_private *cma_new_conn_id(struct rdma_cm_id *listen_id, if (ret) goto err; } else { - /* An AF_IB connection */ - WARN_ON_ONCE(ss_family != AF_IB); - - cma_translate_ib((struct sockaddr_ib *)cma_src_addr(id_priv), - &rt->addr.dev_addr); + if (!cma_protocol_roce(listen_id) && + cma_any_addr(cma_src_addr(id_priv))) { + rt->addr.dev_addr.dev_type = ARPHRD_INFINIBAND; + rdma_addr_set_sgid(&rt->addr.dev_addr, &rt->path_rec[0].sgid); + ib_addr_set_pkey(&rt->addr.dev_addr, be16_to_cpu(rt->path_rec[0].pkey)); + } else if (!cma_any_addr(cma_src_addr(id_priv))) { + ret = cma_translate_addr(cma_src_addr(id_priv), &rt->addr.dev_addr); + if (ret) + goto err; + } } rdma_addr_set_dgid(&rt->addr.dev_addr, &rt->path_rec[0].dgid); @@ -1635,13 +1662,12 @@ static struct rdma_id_private *cma_new_udp_id(struct rdma_cm_id *listen_id, if (ret) goto err; } else { - /* An AF_IB connection */ - WARN_ON_ONCE(ss_family != AF_IB); - - if (!cma_any_addr(cma_src_addr(id_priv))) - cma_translate_ib((struct sockaddr_ib *) - cma_src_addr(id_priv), - &id->route.addr.dev_addr); + if (!cma_any_addr(cma_src_addr(id_priv))) { + ret = cma_translate_addr(cma_src_addr(id_priv), + &id->route.addr.dev_addr); + if (ret) + goto err; + } } id_priv->state = RDMA_CM_CONNECT; diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c index 70acda91eb2a..6a0bdfa0ce2e 100644 --- a/drivers/infiniband/hw/nes/nes_nic.c +++ b/drivers/infiniband/hw/nes/nes_nic.c @@ -1325,9 +1325,6 @@ static void nes_netdev_get_drvinfo(struct net_device *netdev, "%u.%u", nesadapter->firmware_version >> 16, nesadapter->firmware_version & 0x000000ff); strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version)); - drvinfo->testinfo_len = 0; - drvinfo->eedump_len = 0; - drvinfo->regdump_len = 0; } diff --git a/drivers/infiniband/hw/usnic/usnic.h b/drivers/infiniband/hw/usnic/usnic.h index 5be13d8991bc..f903502d3883 100644 --- a/drivers/infiniband/hw/usnic/usnic.h +++ b/drivers/infiniband/hw/usnic/usnic.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_abi.h b/drivers/infiniband/hw/usnic/usnic_abi.h index 04a66229584e..7fe9502ce8d3 100644 --- a/drivers/infiniband/hw/usnic/usnic_abi.h +++ b/drivers/infiniband/hw/usnic/usnic_abi.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_common_pkt_hdr.h b/drivers/infiniband/hw/usnic/usnic_common_pkt_hdr.h index 393567266142..596e0ed49a8e 100644 --- a/drivers/infiniband/hw/usnic/usnic_common_pkt_hdr.h +++ b/drivers/infiniband/hw/usnic/usnic_common_pkt_hdr.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_common_util.h b/drivers/infiniband/hw/usnic/usnic_common_util.h index 9d737ed5e55d..b54986de5f0c 100644 --- a/drivers/infiniband/hw/usnic/usnic_common_util.h +++ b/drivers/infiniband/hw/usnic/usnic_common_util.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_debugfs.c b/drivers/infiniband/hw/usnic/usnic_debugfs.c index 5d13860161a4..5e55b8bc6fe4 100644 --- a/drivers/infiniband/hw/usnic/usnic_debugfs.c +++ b/drivers/infiniband/hw/usnic/usnic_debugfs.c @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_debugfs.h b/drivers/infiniband/hw/usnic/usnic_debugfs.h index 4087d24a88f6..98453e91daa6 100644 --- a/drivers/infiniband/hw/usnic/usnic_debugfs.h +++ b/drivers/infiniband/hw/usnic/usnic_debugfs.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_fwd.c b/drivers/infiniband/hw/usnic/usnic_fwd.c index e3c9bd9d3ba3..3c37dd59c04e 100644 --- a/drivers/infiniband/hw/usnic/usnic_fwd.c +++ b/drivers/infiniband/hw/usnic/usnic_fwd.c @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_fwd.h b/drivers/infiniband/hw/usnic/usnic_fwd.h index 93713a2230b3..3a8add9ddf46 100644 --- a/drivers/infiniband/hw/usnic/usnic_fwd.h +++ b/drivers/infiniband/hw/usnic/usnic_fwd.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_ib.h b/drivers/infiniband/hw/usnic/usnic_ib.h index e5a9297dd1bd..525bf272671e 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib.h +++ b/drivers/infiniband/hw/usnic/usnic_ib.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index 34c49b8105fe..0c15bd885035 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c index db3588df3546..85dc3f989ff7 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.h b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.h index b0aafe8db0c3..b1458be1d402 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.h +++ b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c index 27dc67c1689f..3412ea06116e 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.h b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.h index 0d09b493cd02..3d98e16cfeaf 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.h +++ b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c index 7df43827cb29..f8e3211689a3 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h index 0bd04efa16f3..414eaa566bd9 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_log.h b/drivers/infiniband/hw/usnic/usnic_log.h index 75777a66c684..183fcb6a952f 100644 --- a/drivers/infiniband/hw/usnic/usnic_log.h +++ b/drivers/infiniband/hw/usnic/usnic_log.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_transport.c b/drivers/infiniband/hw/usnic/usnic_transport.c index ddef6f77a78c..de318389a301 100644 --- a/drivers/infiniband/hw/usnic/usnic_transport.c +++ b/drivers/infiniband/hw/usnic/usnic_transport.c @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_transport.h b/drivers/infiniband/hw/usnic/usnic_transport.h index 7e5dc6d9f462..9a7a2d9755c0 100644 --- a/drivers/infiniband/hw/usnic/usnic_transport.h +++ b/drivers/infiniband/hw/usnic/usnic_transport.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c index cb2337f0532b..645a5f6e6c88 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom.c @@ -7,7 +7,7 @@ * 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: + * BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.h b/drivers/infiniband/hw/usnic/usnic_uiom.h index 70440996e8f2..45ca7c1613a7 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom.h +++ b/drivers/infiniband/hw/usnic/usnic_uiom.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c index 3a4288e0fbac..42b4b4c4e452 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c @@ -1,9 +1,24 @@ /* * Copyright (c) 2014, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.h b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.h index d4f752e258fd..c0b0b876ab90 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.h +++ b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_vnic.c b/drivers/infiniband/hw/usnic/usnic_vnic.c index 656b88c39eda..66de93fb8ea9 100644 --- a/drivers/infiniband/hw/usnic/usnic_vnic.c +++ b/drivers/infiniband/hw/usnic/usnic_vnic.c @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/hw/usnic/usnic_vnic.h b/drivers/infiniband/hw/usnic/usnic_vnic.h index 14d931a8829d..a08423e478af 100644 --- a/drivers/infiniband/hw/usnic/usnic_vnic.h +++ b/drivers/infiniband/hw/usnic/usnic_vnic.h @@ -1,9 +1,24 @@ /* * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved. * - * This program is free software; you may redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. + * 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 + * 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 diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 4cd5428a2399..edc5b8565d6d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -495,6 +495,7 @@ void ipoib_dev_cleanup(struct net_device *dev); void ipoib_mcast_join_task(struct work_struct *work); void ipoib_mcast_carrier_on_task(struct work_struct *work); void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb); +void ipoib_mcast_free(struct ipoib_mcast *mc); void ipoib_mcast_restart_task(struct work_struct *work); int ipoib_mcast_start_thread(struct net_device *dev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index f74316e679d2..babba05d7a0e 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1207,8 +1207,10 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) out_unlock: spin_unlock_irqrestore(&priv->lock, flags); - list_for_each_entry_safe(mcast, tmcast, &remove_list, list) + list_for_each_entry_safe(mcast, tmcast, &remove_list, list) { ipoib_mcast_leave(dev, mcast); + ipoib_mcast_free(mcast); + } } static void ipoib_reap_neigh(struct work_struct *work) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 136cbefe00f8..d750a86042f3 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -106,7 +106,7 @@ static void __ipoib_mcast_schedule_join_thread(struct ipoib_dev_priv *priv, queue_delayed_work(priv->wq, &priv->mcast_task, 0); } -static void ipoib_mcast_free(struct ipoib_mcast *mcast) +void ipoib_mcast_free(struct ipoib_mcast *mcast) { struct net_device *dev = mcast->dev; int tx_dropped = 0; diff --git a/drivers/input/joystick/walkera0701.c b/drivers/input/joystick/walkera0701.c index b76ac580703c..a8bc2fe170dd 100644 --- a/drivers/input/joystick/walkera0701.c +++ b/drivers/input/joystick/walkera0701.c @@ -150,7 +150,7 @@ static void walkera0701_irq_handler(void *handler_data) if (w->counter == 24) { /* full frame */ walkera0701_parse_frame(w); w->counter = NO_SYNC; - if (abs(pulse_time - SYNC_PULSE) < RESERVE) /* new frame sync */ + if (abs64(pulse_time - SYNC_PULSE) < RESERVE) /* new frame sync */ w->counter = 0; } else { if ((pulse_time > (ANALOG_MIN_PULSE - RESERVE) @@ -161,7 +161,7 @@ static void walkera0701_irq_handler(void *handler_data) } else w->counter = NO_SYNC; } - } else if (abs(pulse_time - SYNC_PULSE - BIN0_PULSE) < + } else if (abs64(pulse_time - SYNC_PULSE - BIN0_PULSE) < RESERVE + BIN1_PULSE - BIN0_PULSE) /* frame sync .. */ w->counter = 0; diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c index b052afec9a11..6639b2b8528a 100644 --- a/drivers/input/keyboard/omap4-keypad.c +++ b/drivers/input/keyboard/omap4-keypad.c @@ -266,7 +266,7 @@ static int omap4_keypad_probe(struct platform_device *pdev) error = omap4_keypad_parse_dt(&pdev->dev, keypad_data); if (error) - return error; + goto err_free_keypad; res = request_mem_region(res->start, resource_size(res), pdev->name); if (!res) { diff --git a/drivers/input/misc/pm8941-pwrkey.c b/drivers/input/misc/pm8941-pwrkey.c index 867db8a91372..e317b75357a0 100644 --- a/drivers/input/misc/pm8941-pwrkey.c +++ b/drivers/input/misc/pm8941-pwrkey.c @@ -93,7 +93,7 @@ static int pm8941_reboot_notify(struct notifier_block *nb, default: reset_type = PON_PS_HOLD_TYPE_HARD_RESET; break; - }; + } error = regmap_update_bits(pwrkey->regmap, pwrkey->baseaddr + PON_PS_HOLD_RST_CTL, diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index 345df9b03aed..5adbcedcb81c 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -414,7 +414,7 @@ static int uinput_setup_device(struct uinput_device *udev, dev->id.product = user_dev->id.product; dev->id.version = user_dev->id.version; - for_each_set_bit(i, dev->absbit, ABS_CNT) { + for (i = 0; i < ABS_CNT; i++) { input_abs_set_max(dev, i, user_dev->absmax[i]); input_abs_set_min(dev, i, user_dev->absmin[i]); input_abs_set_fuzz(dev, i, user_dev->absfuzz[i]); diff --git a/drivers/input/mouse/cyapa_gen6.c b/drivers/input/mouse/cyapa_gen6.c index 5f191071d44a..e4eb048d1bf6 100644 --- a/drivers/input/mouse/cyapa_gen6.c +++ b/drivers/input/mouse/cyapa_gen6.c @@ -241,14 +241,10 @@ static int cyapa_gen6_read_sys_info(struct cyapa *cyapa) memcpy(&cyapa->product_id[13], &resp_data[62], 2); cyapa->product_id[15] = '\0'; + /* Get the number of Rx electrodes. */ rotat_align = resp_data[68]; - if (rotat_align) { - cyapa->electrodes_rx = cyapa->electrodes_y; - cyapa->electrodes_rx = cyapa->electrodes_y; - } else { - cyapa->electrodes_rx = cyapa->electrodes_x; - cyapa->electrodes_rx = cyapa->electrodes_y; - } + cyapa->electrodes_rx = + rotat_align ? cyapa->electrodes_y : cyapa->electrodes_x; cyapa->aligned_electrodes_rx = (cyapa->electrodes_rx + 3) & ~3u; if (!cyapa->electrodes_x || !cyapa->electrodes_y || diff --git a/drivers/input/mouse/elan_i2c.h b/drivers/input/mouse/elan_i2c.h index 73670f2aebfd..c0ec26118732 100644 --- a/drivers/input/mouse/elan_i2c.h +++ b/drivers/input/mouse/elan_i2c.h @@ -60,7 +60,7 @@ struct elan_transport_ops { int (*get_sm_version)(struct i2c_client *client, u8* ic_type, u8 *version); int (*get_checksum)(struct i2c_client *client, bool iap, u16 *csum); - int (*get_product_id)(struct i2c_client *client, u8 *id); + int (*get_product_id)(struct i2c_client *client, u16 *id); int (*get_max)(struct i2c_client *client, unsigned int *max_x, unsigned int *max_y); diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index fa945304b9a5..5e1665bbaa0b 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -40,7 +40,7 @@ #include "elan_i2c.h" #define DRIVER_NAME "elan_i2c" -#define ELAN_DRIVER_VERSION "1.6.0" +#define ELAN_DRIVER_VERSION "1.6.1" #define ETP_MAX_PRESSURE 255 #define ETP_FWIDTH_REDUCE 90 #define ETP_FINGER_WIDTH 15 @@ -76,7 +76,7 @@ struct elan_tp_data { unsigned int x_res; unsigned int y_res; - u8 product_id; + u16 product_id; u8 fw_version; u8 sm_version; u8 iap_version; @@ -98,15 +98,25 @@ static int elan_get_fwinfo(u8 iap_version, u16 *validpage_count, u16 *signature_address) { switch (iap_version) { + case 0x00: + case 0x06: case 0x08: *validpage_count = 512; break; + case 0x03: + case 0x07: case 0x09: + case 0x0A: + case 0x0B: + case 0x0C: *validpage_count = 768; break; case 0x0D: *validpage_count = 896; break; + case 0x0E: + *validpage_count = 640; + break; default: /* unknown ic type clear value */ *validpage_count = 0; @@ -266,11 +276,10 @@ static int elan_query_device_info(struct elan_tp_data *data) error = elan_get_fwinfo(data->iap_version, &data->fw_validpage_count, &data->fw_signature_address); - if (error) { - dev_err(&data->client->dev, - "unknown iap version %d\n", data->iap_version); - return error; - } + if (error) + dev_warn(&data->client->dev, + "unexpected iap version %#04x (ic type: %#04x), firmware update will not work\n", + data->iap_version, data->ic_type); return 0; } @@ -486,6 +495,9 @@ static ssize_t elan_sysfs_update_fw(struct device *dev, const u8 *fw_signature; static const u8 signature[] = {0xAA, 0x55, 0xCC, 0x33, 0xFF, 0xFF}; + if (data->fw_validpage_count == 0) + return -EINVAL; + /* Look for a firmware with the product id appended. */ fw_name = kasprintf(GFP_KERNEL, ETP_FW_NAME, data->product_id); if (!fw_name) { diff --git a/drivers/input/mouse/elan_i2c_i2c.c b/drivers/input/mouse/elan_i2c_i2c.c index 683c840c9dd7..a679e56c44cd 100644 --- a/drivers/input/mouse/elan_i2c_i2c.c +++ b/drivers/input/mouse/elan_i2c_i2c.c @@ -276,7 +276,7 @@ static int elan_i2c_get_sm_version(struct i2c_client *client, return 0; } -static int elan_i2c_get_product_id(struct i2c_client *client, u8 *id) +static int elan_i2c_get_product_id(struct i2c_client *client, u16 *id) { int error; u8 val[3]; @@ -287,7 +287,7 @@ static int elan_i2c_get_product_id(struct i2c_client *client, u8 *id) return error; } - *id = val[0]; + *id = le16_to_cpup((__le16 *)val); return 0; } diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c index ff36a366b2aa..cb6aecbc1dc2 100644 --- a/drivers/input/mouse/elan_i2c_smbus.c +++ b/drivers/input/mouse/elan_i2c_smbus.c @@ -183,7 +183,7 @@ static int elan_smbus_get_sm_version(struct i2c_client *client, return 0; } -static int elan_smbus_get_product_id(struct i2c_client *client, u8 *id) +static int elan_smbus_get_product_id(struct i2c_client *client, u16 *id) { int error; u8 val[3]; @@ -195,7 +195,7 @@ static int elan_smbus_get_product_id(struct i2c_client *client, u8 *id) return error; } - *id = val[1]; + *id = be16_to_cpup((__be16 *)val); return 0; } diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 994ae7886156..6025eb430c0a 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -519,18 +519,14 @@ static int synaptics_set_mode(struct psmouse *psmouse) struct synaptics_data *priv = psmouse->private; priv->mode = 0; - - if (priv->absolute_mode) { + if (priv->absolute_mode) priv->mode |= SYN_BIT_ABSOLUTE_MODE; - if (SYN_CAP_EXTENDED(priv->capabilities)) - priv->mode |= SYN_BIT_W_MODE; - } - - if (!SYN_MODE_WMODE(priv->mode) && priv->disable_gesture) + if (priv->disable_gesture) priv->mode |= SYN_BIT_DISABLE_GESTURE; - if (psmouse->rate >= 80) priv->mode |= SYN_BIT_HIGH_RATE; + if (SYN_CAP_EXTENDED(priv->capabilities)) + priv->mode |= SYN_BIT_W_MODE; if (synaptics_mode_cmd(psmouse, priv->mode)) return -1; diff --git a/drivers/input/serio/libps2.c b/drivers/input/serio/libps2.c index 75516996db20..316f2c897101 100644 --- a/drivers/input/serio/libps2.c +++ b/drivers/input/serio/libps2.c @@ -212,12 +212,17 @@ int __ps2_command(struct ps2dev *ps2dev, unsigned char *param, int command) * time before the ACK arrives. */ if (ps2_sendbyte(ps2dev, command & 0xff, - command == PS2_CMD_RESET_BAT ? 1000 : 200)) - goto out; + command == PS2_CMD_RESET_BAT ? 1000 : 200)) { + serio_pause_rx(ps2dev->serio); + goto out_reset_flags; + } - for (i = 0; i < send; i++) - if (ps2_sendbyte(ps2dev, param[i], 200)) - goto out; + for (i = 0; i < send; i++) { + if (ps2_sendbyte(ps2dev, param[i], 200)) { + serio_pause_rx(ps2dev->serio); + goto out_reset_flags; + } + } /* * The reset command takes a long time to execute. @@ -234,17 +239,18 @@ int __ps2_command(struct ps2dev *ps2dev, unsigned char *param, int command) !(ps2dev->flags & PS2_FLAG_CMD), timeout); } + serio_pause_rx(ps2dev->serio); + if (param) for (i = 0; i < receive; i++) param[i] = ps2dev->cmdbuf[(receive - 1) - i]; if (ps2dev->cmdcnt && (command != PS2_CMD_RESET_BAT || ps2dev->cmdcnt != 1)) - goto out; + goto out_reset_flags; rc = 0; - out: - serio_pause_rx(ps2dev->serio); + out_reset_flags: ps2dev->flags = 0; serio_continue_rx(ps2dev->serio); diff --git a/drivers/input/serio/parkbd.c b/drivers/input/serio/parkbd.c index 26b45936f9fd..1e8cd6f1fe9e 100644 --- a/drivers/input/serio/parkbd.c +++ b/drivers/input/serio/parkbd.c @@ -194,6 +194,7 @@ static int __init parkbd_init(void) parkbd_port = parkbd_allocate_serio(); if (!parkbd_port) { parport_release(parkbd_dev); + parport_unregister_device(parkbd_dev); return -ENOMEM; } diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index 0f5f968592bd..04edc8f7122f 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -668,18 +668,22 @@ static int ads7846_no_filter(void *ads, int data_idx, int *val) static int ads7846_get_value(struct ads7846 *ts, struct spi_message *m) { + int value; struct spi_transfer *t = list_entry(m->transfers.prev, struct spi_transfer, transfer_list); if (ts->model == 7845) { - return be16_to_cpup((__be16 *)&(((char*)t->rx_buf)[1])) >> 3; + value = be16_to_cpup((__be16 *)&(((char *)t->rx_buf)[1])); } else { /* * adjust: on-wire is a must-ignore bit, a BE12 value, then * padding; built from two 8 bit values written msb-first. */ - return be16_to_cpup((__be16 *)t->rx_buf) >> 3; + value = be16_to_cpup((__be16 *)t->rx_buf); } + + /* enforce ADC output is 12 bits width */ + return (value >> 3) & 0xfff; } static void ads7846_update_value(struct spi_message *m, int val) diff --git a/drivers/input/touchscreen/imx6ul_tsc.c b/drivers/input/touchscreen/imx6ul_tsc.c index ff0b75813daa..8275267eac25 100644 --- a/drivers/input/touchscreen/imx6ul_tsc.c +++ b/drivers/input/touchscreen/imx6ul_tsc.c @@ -94,7 +94,7 @@ struct imx6ul_tsc { * TSC module need ADC to get the measure value. So * before config TSC, we should initialize ADC module. */ -static void imx6ul_adc_init(struct imx6ul_tsc *tsc) +static int imx6ul_adc_init(struct imx6ul_tsc *tsc) { int adc_hc = 0; int adc_gc; @@ -122,17 +122,23 @@ static void imx6ul_adc_init(struct imx6ul_tsc *tsc) timeout = wait_for_completion_timeout (&tsc->completion, ADC_TIMEOUT); - if (timeout == 0) + if (timeout == 0) { dev_err(tsc->dev, "Timeout for adc calibration\n"); + return -ETIMEDOUT; + } adc_gs = readl(tsc->adc_regs + REG_ADC_GS); - if (adc_gs & ADC_CALF) + if (adc_gs & ADC_CALF) { dev_err(tsc->dev, "ADC calibration failed\n"); + return -EINVAL; + } /* TSC need the ADC work in hardware trigger */ adc_cfg = readl(tsc->adc_regs + REG_ADC_CFG); adc_cfg |= ADC_HARDWARE_TRIGGER; writel(adc_cfg, tsc->adc_regs + REG_ADC_CFG); + + return 0; } /* @@ -188,11 +194,17 @@ static void imx6ul_tsc_set(struct imx6ul_tsc *tsc) writel(start, tsc->tsc_regs + REG_TSC_FLOW_CONTROL); } -static void imx6ul_tsc_init(struct imx6ul_tsc *tsc) +static int imx6ul_tsc_init(struct imx6ul_tsc *tsc) { - imx6ul_adc_init(tsc); + int err; + + err = imx6ul_adc_init(tsc); + if (err) + return err; imx6ul_tsc_channel_config(tsc); imx6ul_tsc_set(tsc); + + return 0; } static void imx6ul_tsc_disable(struct imx6ul_tsc *tsc) @@ -311,9 +323,7 @@ static int imx6ul_tsc_open(struct input_dev *input_dev) return err; } - imx6ul_tsc_init(tsc); - - return 0; + return imx6ul_tsc_init(tsc); } static void imx6ul_tsc_close(struct input_dev *input_dev) @@ -337,7 +347,7 @@ static int imx6ul_tsc_probe(struct platform_device *pdev) int tsc_irq; int adc_irq; - tsc = devm_kzalloc(&pdev->dev, sizeof(struct imx6ul_tsc), GFP_KERNEL); + tsc = devm_kzalloc(&pdev->dev, sizeof(*tsc), GFP_KERNEL); if (!tsc) return -ENOMEM; @@ -345,7 +355,7 @@ static int imx6ul_tsc_probe(struct platform_device *pdev) if (!input_dev) return -ENOMEM; - input_dev->name = "iMX6UL TouchScreen Controller"; + input_dev->name = "iMX6UL Touchscreen Controller"; input_dev->id.bustype = BUS_HOST; input_dev->open = imx6ul_tsc_open; @@ -406,7 +416,7 @@ static int imx6ul_tsc_probe(struct platform_device *pdev) } adc_irq = platform_get_irq(pdev, 1); - if (adc_irq <= 0) { + if (adc_irq < 0) { dev_err(&pdev->dev, "no adc irq resource?\n"); return adc_irq; } @@ -491,7 +501,7 @@ static int __maybe_unused imx6ul_tsc_resume(struct device *dev) goto out; } - imx6ul_tsc_init(tsc); + retval = imx6ul_tsc_init(tsc); } out: diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c index 7cce87650fc8..1fafc9f57af6 100644 --- a/drivers/input/touchscreen/mms114.c +++ b/drivers/input/touchscreen/mms114.c @@ -394,12 +394,12 @@ static struct mms114_platform_data *mms114_parse_dt(struct device *dev) if (of_property_read_u32(np, "x-size", &pdata->x_size)) { dev_err(dev, "failed to get x-size property\n"); return NULL; - }; + } if (of_property_read_u32(np, "y-size", &pdata->y_size)) { dev_err(dev, "failed to get y-size property\n"); return NULL; - }; + } of_property_read_u32(np, "contact-threshold", &pdata->contact_threshold); diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index d9da766719c8..cbe6a890a93a 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -23,8 +23,7 @@ config IOMMU_IO_PGTABLE config IOMMU_IO_PGTABLE_LPAE bool "ARMv7/v8 Long Descriptor Format" select IOMMU_IO_PGTABLE - # SWIOTLB guarantees a dma_to_phys() implementation - depends on ARM || ARM64 || (COMPILE_TEST && SWIOTLB) + depends on HAS_DMA && (ARM || ARM64 || COMPILE_TEST) help Enable support for the ARM long descriptor pagetable format. This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index f82060e778a2..08d2775887f7 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2006,6 +2006,15 @@ static void do_detach(struct iommu_dev_data *dev_data) { struct amd_iommu *iommu; + /* + * First check if the device is still attached. It might already + * be detached from its domain because the generic + * iommu_detach_group code detached it and we try again here in + * our alias handling. + */ + if (!dev_data->domain) + return; + iommu = amd_iommu_rlookup_table[dev_data->devid]; /* decrease reference counters */ diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 5ef347a13cb5..1b066e7d144d 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1256,6 +1256,9 @@ static int iommu_init_pci(struct amd_iommu *iommu) if (!iommu->dev) return -ENODEV; + /* Prevent binding other PCI device drivers to IOMMU devices */ + iommu->dev->match_driver = false; + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, &iommu->cap); pci_read_config_dword(iommu->dev, cap_ptr + MMIO_RANGE_OFFSET, diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index dafaf59dc3b8..286e890e7d64 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -56,6 +56,7 @@ #define IDR0_TTF_SHIFT 2 #define IDR0_TTF_MASK 0x3 #define IDR0_TTF_AARCH64 (2 << IDR0_TTF_SHIFT) +#define IDR0_TTF_AARCH32_64 (3 << IDR0_TTF_SHIFT) #define IDR0_S1P (1 << 1) #define IDR0_S2P (1 << 0) @@ -342,7 +343,8 @@ #define CMDQ_TLBI_0_VMID_SHIFT 32 #define CMDQ_TLBI_0_ASID_SHIFT 48 #define CMDQ_TLBI_1_LEAF (1UL << 0) -#define CMDQ_TLBI_1_ADDR_MASK ~0xfffUL +#define CMDQ_TLBI_1_VA_MASK ~0xfffUL +#define CMDQ_TLBI_1_IPA_MASK 0xfffffffff000UL #define CMDQ_PRI_0_SSID_SHIFT 12 #define CMDQ_PRI_0_SSID_MASK 0xfffffUL @@ -770,11 +772,13 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) break; case CMDQ_OP_TLBI_NH_VA: cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT; - /* Fallthrough */ + cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0; + cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK; + break; case CMDQ_OP_TLBI_S2_IPA: cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT; cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0; - cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_ADDR_MASK; + cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK; break; case CMDQ_OP_TLBI_NH_ASID: cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT; @@ -2460,7 +2464,13 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu) } /* We only support the AArch64 table format at present */ - if ((reg & IDR0_TTF_MASK << IDR0_TTF_SHIFT) < IDR0_TTF_AARCH64) { + switch (reg & IDR0_TTF_MASK << IDR0_TTF_SHIFT) { + case IDR0_TTF_AARCH32_64: + smmu->ias = 40; + /* Fallthrough */ + case IDR0_TTF_AARCH64: + break; + default: dev_err(smmu->dev, "AArch64 table format not supported!\n"); return -ENXIO; } @@ -2541,8 +2551,7 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu) dev_warn(smmu->dev, "failed to set DMA mask for table walker\n"); - if (!smmu->ias) - smmu->ias = smmu->oas; + smmu->ias = max(smmu->ias, smmu->oas); dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n", smmu->ias, smmu->oas, smmu->features); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 041bc1810a86..35365f046923 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2301,6 +2301,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, if (ret) { spin_unlock_irqrestore(&device_domain_lock, flags); + free_devinfo_mem(info); return NULL; } diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 73c07482f487..7df97777662d 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -202,9 +202,9 @@ typedef u64 arm_lpae_iopte; static bool selftest_running = false; -static dma_addr_t __arm_lpae_dma_addr(struct device *dev, void *pages) +static dma_addr_t __arm_lpae_dma_addr(void *pages) { - return phys_to_dma(dev, virt_to_phys(pages)); + return (dma_addr_t)virt_to_phys(pages); } static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp, @@ -223,10 +223,10 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp, goto out_free; /* * We depend on the IOMMU being able to work with any physical - * address directly, so if the DMA layer suggests it can't by - * giving us back some translation, that bodes very badly... + * address directly, so if the DMA layer suggests otherwise by + * translating or truncating them, that bodes very badly... */ - if (dma != __arm_lpae_dma_addr(dev, pages)) + if (dma != virt_to_phys(pages)) goto out_unmap; } @@ -243,10 +243,8 @@ out_free: static void __arm_lpae_free_pages(void *pages, size_t size, struct io_pgtable_cfg *cfg) { - struct device *dev = cfg->iommu_dev; - if (!selftest_running) - dma_unmap_single(dev, __arm_lpae_dma_addr(dev, pages), + dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages), size, DMA_TO_DEVICE); free_pages_exact(pages, size); } @@ -254,12 +252,11 @@ static void __arm_lpae_free_pages(void *pages, size_t size, static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte, struct io_pgtable_cfg *cfg) { - struct device *dev = cfg->iommu_dev; - *ptep = pte; if (!selftest_running) - dma_sync_single_for_device(dev, __arm_lpae_dma_addr(dev, ptep), + dma_sync_single_for_device(cfg->iommu_dev, + __arm_lpae_dma_addr(ptep), sizeof(pte), DMA_TO_DEVICE); } @@ -629,6 +626,11 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg) if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS) return NULL; + if (!selftest_running && cfg->iommu_dev->dma_pfn_offset) { + dev_err(cfg->iommu_dev, "Cannot accommodate DMA offset for IOMMU page tables\n"); + return NULL; + } + data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return NULL; diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c index cf351c637464..a7c8c9ffbafd 100644 --- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c @@ -62,7 +62,7 @@ static int its_get_pci_alias(struct pci_dev *pdev, u16 alias, void *data) dev_alias->dev_id = alias; if (pdev != dev_alias->pdev) - dev_alias->count += its_pci_msi_vec_count(dev_alias->pdev); + dev_alias->count += its_pci_msi_vec_count(pdev); return 0; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index ac7ae2b3cb83..25ceae9f7348 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -719,6 +719,9 @@ static unsigned long *its_lpi_alloc_chunks(int nr_irqs, int *base, int *nr_ids) out: spin_unlock(&lpi_lock); + if (!bitmap) + *base = *nr_ids = 0; + return bitmap; } diff --git a/drivers/isdn/mISDN/dsp_pipeline.c b/drivers/isdn/mISDN/dsp_pipeline.c index 8b1a66c6ca8a..e72b4e73cd61 100644 --- a/drivers/isdn/mISDN/dsp_pipeline.c +++ b/drivers/isdn/mISDN/dsp_pipeline.c @@ -235,7 +235,7 @@ void dsp_pipeline_destroy(struct dsp_pipeline *pipeline) int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg) { - int len, incomplete = 0, found = 0; + int incomplete = 0, found = 0; char *dup, *tok, *name, *args; struct dsp_element_entry *entry, *n; struct dsp_pipeline_entry *pipeline_entry; @@ -247,17 +247,9 @@ int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg) if (!list_empty(&pipeline->list)) _dsp_pipeline_destroy(pipeline); - if (!cfg) - return 0; - - len = strlen(cfg); - if (!len) - return 0; - - dup = kmalloc(len + 1, GFP_ATOMIC); + dup = kstrdup(cfg, GFP_ATOMIC); if (!dup) return 0; - strcpy(dup, cfg); while ((tok = strsep(&dup, "|"))) { if (!strlen(tok)) continue; diff --git a/drivers/mcb/mcb-pci.c b/drivers/mcb/mcb-pci.c index de36237d7c6b..051645498b53 100644 --- a/drivers/mcb/mcb-pci.c +++ b/drivers/mcb/mcb-pci.c @@ -74,7 +74,7 @@ static int mcb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = -ENOTSUPP; dev_err(&pdev->dev, "IO mapped PCI devices are not supported\n"); - goto out_release; + goto out_iounmap; } pci_set_drvdata(pdev, priv); @@ -89,7 +89,7 @@ static int mcb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = chameleon_parse_cells(priv->bus, priv->mapbase, priv->base); if (ret < 0) - goto out_iounmap; + goto out_mcb_bus; num_cells = ret; dev_dbg(&pdev->dev, "Found %d cells\n", num_cells); @@ -98,6 +98,8 @@ static int mcb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; +out_mcb_bus: + mcb_release_bus(priv->bus); out_iounmap: iounmap(priv->base); out_release: diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index e51de52eeb94..48b5890c28e3 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1997,7 +1997,8 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks, if (bitmap->mddev->bitmap_info.offset || bitmap->mddev->bitmap_info.file) ret = bitmap_storage_alloc(&store, chunks, !bitmap->mddev->bitmap_info.external, - bitmap->cluster_slot); + mddev_is_clustered(bitmap->mddev) + ? bitmap->cluster_slot : 0); if (ret) goto err; diff --git a/drivers/md/dm-cache-policy-cleaner.c b/drivers/md/dm-cache-policy-cleaner.c index 240c9f0e85e7..8a096456579b 100644 --- a/drivers/md/dm-cache-policy-cleaner.c +++ b/drivers/md/dm-cache-policy-cleaner.c @@ -436,7 +436,7 @@ static struct dm_cache_policy *wb_create(dm_cblock_t cache_size, static struct dm_cache_policy_type wb_policy_type = { .name = "cleaner", .version = {1, 0, 0}, - .hint_size = 0, + .hint_size = 4, .owner = THIS_MODULE, .create = wb_create }; diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c index ebaa4f803eec..192bb8beeb6b 100644 --- a/drivers/md/dm-exception-store.c +++ b/drivers/md/dm-exception-store.c @@ -203,7 +203,7 @@ int dm_exception_store_create(struct dm_target *ti, int argc, char **argv, return -EINVAL; } - tmp_store = kmalloc(sizeof(*tmp_store), GFP_KERNEL); + tmp_store = kzalloc(sizeof(*tmp_store), GFP_KERNEL); if (!tmp_store) { ti->error = "Exception store allocation failed"; return -ENOMEM; @@ -215,7 +215,7 @@ int dm_exception_store_create(struct dm_target *ti, int argc, char **argv, else if (persistent == 'N') type = get_type("N"); else { - ti->error = "Persistent flag is not P or N"; + ti->error = "Exception store type is not P or N"; r = -EINVAL; goto bad_type; } @@ -233,7 +233,7 @@ int dm_exception_store_create(struct dm_target *ti, int argc, char **argv, if (r) goto bad; - r = type->ctr(tmp_store, 0, NULL); + r = type->ctr(tmp_store, (strlen(argv[0]) > 1 ? &argv[0][1] : NULL)); if (r) { ti->error = "Exception store type constructor failed"; goto bad; diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index 0b2536247cf5..fae34e7a0b1e 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -42,8 +42,7 @@ struct dm_exception_store_type { const char *name; struct module *module; - int (*ctr) (struct dm_exception_store *store, - unsigned argc, char **argv); + int (*ctr) (struct dm_exception_store *store, char *options); /* * Destroys this object when you've finished with it. @@ -123,6 +122,8 @@ struct dm_exception_store { unsigned chunk_shift; void *context; + + bool userspace_supports_overflow; }; /* diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 97e165183e79..a0901214aef5 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -329,8 +329,7 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size) */ if (min_region_size > (1 << 13)) { /* If not a power of 2, make it the next power of 2 */ - if (min_region_size & (min_region_size - 1)) - region_size = 1 << fls(region_size); + region_size = roundup_pow_of_two(min_region_size); DMINFO("Choosing default region size of %lu sectors", region_size); } else { diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index bf71583296f7..117a05e40090 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -7,6 +7,7 @@ #include "dm-exception-store.h" +#include <linux/ctype.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/vmalloc.h> @@ -843,10 +844,10 @@ static void persistent_drop_snapshot(struct dm_exception_store *store) DMWARN("write header failed"); } -static int persistent_ctr(struct dm_exception_store *store, - unsigned argc, char **argv) +static int persistent_ctr(struct dm_exception_store *store, char *options) { struct pstore *ps; + int r; /* allocate the pstore */ ps = kzalloc(sizeof(*ps), GFP_KERNEL); @@ -868,14 +869,32 @@ static int persistent_ctr(struct dm_exception_store *store, ps->metadata_wq = alloc_workqueue("ksnaphd", WQ_MEM_RECLAIM, 0); if (!ps->metadata_wq) { - kfree(ps); DMERR("couldn't start header metadata update thread"); - return -ENOMEM; + r = -ENOMEM; + goto err_workqueue; + } + + if (options) { + char overflow = toupper(options[0]); + if (overflow == 'O') + store->userspace_supports_overflow = true; + else { + DMERR("Unsupported persistent store option: %s", options); + r = -EINVAL; + goto err_options; + } } store->context = ps; return 0; + +err_options: + destroy_workqueue(ps->metadata_wq); +err_workqueue: + kfree(ps); + + return r; } static unsigned persistent_status(struct dm_exception_store *store, @@ -888,7 +907,8 @@ static unsigned persistent_status(struct dm_exception_store *store, case STATUSTYPE_INFO: break; case STATUSTYPE_TABLE: - DMEMIT(" P %llu", (unsigned long long)store->chunk_size); + DMEMIT(" %s %llu", store->userspace_supports_overflow ? "PO" : "P", + (unsigned long long)store->chunk_size); } return sz; diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c index 1ce9a2586e41..9b7c8c8049d6 100644 --- a/drivers/md/dm-snap-transient.c +++ b/drivers/md/dm-snap-transient.c @@ -70,8 +70,7 @@ static void transient_usage(struct dm_exception_store *store, *metadata_sectors = 0; } -static int transient_ctr(struct dm_exception_store *store, - unsigned argc, char **argv) +static int transient_ctr(struct dm_exception_store *store, char *options) { struct transient_c *tc; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index c0bcd6516dfe..c06b74e91cd6 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1098,7 +1098,7 @@ static void stop_merge(struct dm_snapshot *s) } /* - * Construct a snapshot mapping: <origin_dev> <COW-dev> <p/n> <chunk-size> + * Construct a snapshot mapping: <origin_dev> <COW-dev> <p|po|n> <chunk-size> */ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) { @@ -1302,6 +1302,7 @@ static void __handover_exceptions(struct dm_snapshot *snap_src, u.store_swap = snap_dest->store; snap_dest->store = snap_src->store; + snap_dest->store->userspace_supports_overflow = u.store_swap->userspace_supports_overflow; snap_src->store = u.store_swap; snap_dest->store->snap = snap_dest; @@ -1739,8 +1740,11 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) pe = __find_pending_exception(s, pe, chunk); if (!pe) { - s->snapshot_overflowed = 1; - DMERR("Snapshot overflowed: Unable to allocate exception."); + if (s->store->userspace_supports_overflow) { + s->snapshot_overflowed = 1; + DMERR("Snapshot overflowed: Unable to allocate exception."); + } else + __invalidate_snapshot(s, -ENOMEM); r = -EIO; goto out_unlock; } @@ -2365,7 +2369,7 @@ static struct target_type origin_target = { static struct target_type snapshot_target = { .name = "snapshot", - .version = {1, 14, 0}, + .version = {1, 15, 0}, .module = THIS_MODULE, .ctr = snapshot_ctr, .dtr = snapshot_dtr, @@ -2379,7 +2383,7 @@ static struct target_type snapshot_target = { static struct target_type merge_target = { .name = dm_snapshot_merge_target_name, - .version = {1, 3, 0}, + .version = {1, 4, 0}, .module = THIS_MODULE, .ctr = snapshot_ctr, .dtr = snapshot_dtr, diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 6fcbfb063366..3897b90bd462 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -3201,7 +3201,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) metadata_low_callback, pool); if (r) - goto out_free_pt; + goto out_flags_changed; pt->callbacks.congested_fn = pool_is_congested; dm_table_add_target_callbacks(ti->table, &pt->callbacks); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 6264781dc69a..1b5c6047e4f1 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1001,6 +1001,7 @@ static void end_clone_bio(struct bio *clone) struct dm_rq_target_io *tio = info->tio; struct bio *bio = info->orig; unsigned int nr_bytes = info->orig->bi_iter.bi_size; + int error = clone->bi_error; bio_put(clone); @@ -1011,13 +1012,13 @@ static void end_clone_bio(struct bio *clone) * the remainder. */ return; - else if (bio->bi_error) { + else if (error) { /* * Don't notice the error to the upper layer yet. * The error handling decision is made by the target driver, * when the request is completed. */ - tio->error = bio->bi_error; + tio->error = error; return; } @@ -2837,8 +2838,6 @@ static void __dm_destroy(struct mapped_device *md, bool wait) might_sleep(); - map = dm_get_live_table(md, &srcu_idx); - spin_lock(&_minor_lock); idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md)))); set_bit(DMF_FREEING, &md->flags); @@ -2852,14 +2851,14 @@ static void __dm_destroy(struct mapped_device *md, bool wait) * do not race with internal suspend. */ mutex_lock(&md->suspend_lock); + map = dm_get_live_table(md, &srcu_idx); if (!dm_suspended_md(md)) { dm_table_presuspend_targets(map); dm_table_postsuspend_targets(map); } - mutex_unlock(&md->suspend_lock); - /* dm_put_live_table must be before msleep, otherwise deadlock is possible */ dm_put_live_table(md, srcu_idx); + mutex_unlock(&md->suspend_lock); /* * Rare, but there may be I/O requests still going to complete, diff --git a/drivers/md/md.c b/drivers/md/md.c index 4f5ecbe94ccb..c702de18207a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5409,9 +5409,13 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) * which will now never happen */ wake_up_process(mddev->sync_thread->tsk); + if (mddev->external && test_bit(MD_CHANGE_PENDING, &mddev->flags)) + return -EBUSY; mddev_unlock(mddev); wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)); + wait_event(mddev->sb_wait, + !test_bit(MD_CHANGE_PENDING, &mddev->flags)); mddev_lock_nointr(mddev); mutex_lock(&mddev->open_mutex); @@ -8160,6 +8164,7 @@ void md_check_recovery(struct mddev *mddev) md_reap_sync_thread(mddev); clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + clear_bit(MD_CHANGE_PENDING, &mddev->flags); goto unlock; } diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index d222522c52e0..d132f06afdd1 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -470,8 +470,7 @@ static int multipath_run (struct mddev *mddev) return 0; out_free_conf: - if (conf->pool) - mempool_destroy(conf->pool); + mempool_destroy(conf->pool); kfree(conf->multipaths); kfree(conf); mddev->private = NULL; diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 63e619b2f44e..f8e5db0cb5aa 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -376,12 +376,6 @@ static int raid0_run(struct mddev *mddev) struct md_rdev *rdev; bool discard_supported = false; - rdev_for_each(rdev, mddev) { - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; - } blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); @@ -390,6 +384,12 @@ static int raid0_run(struct mddev *mddev) blk_queue_io_opt(mddev->queue, (mddev->chunk_sectors << 9) * mddev->raid_disks); + rdev_for_each(rdev, mddev) { + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); + if (blk_queue_discard(bdev_get_queue(rdev->bdev))) + discard_supported = true; + } if (!discard_supported) queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); else diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 4517f06c41ba..ddd8a5f572aa 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -881,8 +881,7 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio) } if (bio && bio_data_dir(bio) == WRITE) { - if (bio->bi_iter.bi_sector >= - conf->mddev->curr_resync_completed) { + if (bio->bi_iter.bi_sector >= conf->next_resync) { if (conf->start_next_window == MaxSector) conf->start_next_window = conf->next_resync + @@ -1516,7 +1515,7 @@ static void close_sync(struct r1conf *conf) conf->r1buf_pool = NULL; spin_lock_irq(&conf->resync_lock); - conf->next_resync = 0; + conf->next_resync = MaxSector - 2 * NEXT_NORMALIO_DISTANCE; conf->start_next_window = MaxSector; conf->current_window_requests += conf->next_window_requests; @@ -2383,8 +2382,8 @@ static void raid1d(struct md_thread *thread) } spin_unlock_irqrestore(&conf->device_lock, flags); while (!list_empty(&tmp)) { - r1_bio = list_first_entry(&conf->bio_end_io_list, - struct r1bio, retry_list); + r1_bio = list_first_entry(&tmp, struct r1bio, + retry_list); list_del(&r1_bio->retry_list); raid_end_bio_io(r1_bio); } @@ -2843,8 +2842,7 @@ static struct r1conf *setup_conf(struct mddev *mddev) abort: if (conf) { - if (conf->r1bio_pool) - mempool_destroy(conf->r1bio_pool); + mempool_destroy(conf->r1bio_pool); kfree(conf->mirrors); safe_put_page(conf->tmppage); kfree(conf->poolinfo); @@ -2946,8 +2944,7 @@ static void raid1_free(struct mddev *mddev, void *priv) { struct r1conf *conf = priv; - if (conf->r1bio_pool) - mempool_destroy(conf->r1bio_pool); + mempool_destroy(conf->r1bio_pool); kfree(conf->mirrors); safe_put_page(conf->tmppage); kfree(conf->poolinfo); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 0fc33eb88855..9f69dc526f8c 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2688,8 +2688,8 @@ static void raid10d(struct md_thread *thread) } spin_unlock_irqrestore(&conf->device_lock, flags); while (!list_empty(&tmp)) { - r10_bio = list_first_entry(&conf->bio_end_io_list, - struct r10bio, retry_list); + r10_bio = list_first_entry(&tmp, struct r10bio, + retry_list); list_del(&r10_bio->retry_list); raid_end_bio_io(r10_bio); } @@ -3486,8 +3486,7 @@ static struct r10conf *setup_conf(struct mddev *mddev) printk(KERN_ERR "md/raid10:%s: couldn't allocate memory.\n", mdname(mddev)); if (conf) { - if (conf->r10bio_pool) - mempool_destroy(conf->r10bio_pool); + mempool_destroy(conf->r10bio_pool); kfree(conf->mirrors); safe_put_page(conf->tmppage); kfree(conf); @@ -3682,8 +3681,7 @@ static int run(struct mddev *mddev) out_free_conf: md_unregister_thread(&mddev->thread); - if (conf->r10bio_pool) - mempool_destroy(conf->r10bio_pool); + mempool_destroy(conf->r10bio_pool); safe_put_page(conf->tmppage); kfree(conf->mirrors); kfree(conf); @@ -3696,8 +3694,7 @@ static void raid10_free(struct mddev *mddev, void *priv) { struct r10conf *conf = priv; - if (conf->r10bio_pool) - mempool_destroy(conf->r10bio_pool); + mempool_destroy(conf->r10bio_pool); safe_put_page(conf->tmppage); kfree(conf->mirrors); kfree(conf->mirrors_old); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 15ef2c641b2b..49bb8d3ff9be 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2271,8 +2271,7 @@ static void shrink_stripes(struct r5conf *conf) drop_one_stripe(conf)) ; - if (conf->slab_cache) - kmem_cache_destroy(conf->slab_cache); + kmem_cache_destroy(conf->slab_cache); conf->slab_cache = NULL; } @@ -3150,6 +3149,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, spin_unlock_irq(&sh->stripe_lock); if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) wake_up(&conf->wait_for_overlap); + if (bi) + s->to_read--; while (bi && bi->bi_iter.bi_sector < sh->dev[i].sector + STRIPE_SECTORS) { struct bio *nextbi = @@ -3169,6 +3170,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, */ clear_bit(R5_LOCKED, &sh->dev[i].flags); } + s->to_write = 0; + s->written = 0; if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state)) if (atomic_dec_and_test(&conf->pending_full_writes)) @@ -3300,7 +3303,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s, */ return 0; - for (i = 0; i < s->failed; i++) { + for (i = 0; i < s->failed && i < 2; i++) { if (fdev[i]->towrite && !test_bit(R5_UPTODATE, &fdev[i]->flags) && !test_bit(R5_OVERWRITE, &fdev[i]->flags)) @@ -3324,7 +3327,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s, sh->sector < sh->raid_conf->mddev->recovery_cp) /* reconstruct-write isn't being forced */ return 0; - for (i = 0; i < s->failed; i++) { + for (i = 0; i < s->failed && i < 2; i++) { if (s->failed_num[i] != sh->pd_idx && s->failed_num[i] != sh->qd_idx && !test_bit(R5_UPTODATE, &fdev[i]->flags) && diff --git a/drivers/mfd/intel-lpss.h b/drivers/mfd/intel-lpss.h index f28cb28a62f8..2c7f8d7c0595 100644 --- a/drivers/mfd/intel-lpss.h +++ b/drivers/mfd/intel-lpss.h @@ -42,6 +42,8 @@ int intel_lpss_resume(struct device *dev); .thaw = intel_lpss_resume, \ .poweroff = intel_lpss_suspend, \ .restore = intel_lpss_resume, +#else +#define INTEL_LPSS_SLEEP_PM_OPS #endif #define INTEL_LPSS_RUNTIME_PM_OPS \ diff --git a/drivers/mfd/max77843.c b/drivers/mfd/max77843.c index c52162ea3d0a..586098f1b233 100644 --- a/drivers/mfd/max77843.c +++ b/drivers/mfd/max77843.c @@ -80,7 +80,7 @@ static int max77843_chg_init(struct max77693_dev *max77843) if (!max77843->i2c_chg) { dev_err(&max77843->i2c->dev, "Cannot allocate I2C device for Charger\n"); - return PTR_ERR(max77843->i2c_chg); + return -ENODEV; } i2c_set_clientdata(max77843->i2c_chg, max77843); diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c index 8af12c884b04..103baf0e0c5b 100644 --- a/drivers/misc/cxl/api.c +++ b/drivers/misc/cxl/api.c @@ -105,6 +105,7 @@ EXPORT_SYMBOL_GPL(cxl_allocate_afu_irqs); void cxl_free_afu_irqs(struct cxl_context *ctx) { + afu_irq_name_free(ctx); cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter); } EXPORT_SYMBOL_GPL(cxl_free_afu_irqs); diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c index e762f85ee233..2faa1270d085 100644 --- a/drivers/misc/cxl/context.c +++ b/drivers/misc/cxl/context.c @@ -275,6 +275,9 @@ static void reclaim_ctx(struct rcu_head *rcu) if (ctx->kernelapi) kfree(ctx->mapping); + if (ctx->irq_bitmap) + kfree(ctx->irq_bitmap); + kfree(ctx); } diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index 1c30ef77073d..0cfb9c129f27 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -677,6 +677,7 @@ int cxl_register_serr_irq(struct cxl_afu *afu); void cxl_release_serr_irq(struct cxl_afu *afu); int afu_register_irqs(struct cxl_context *ctx, u32 count); void afu_release_irqs(struct cxl_context *ctx, void *cookie); +void afu_irq_name_free(struct cxl_context *ctx); irqreturn_t cxl_slice_irq_err(int irq, void *data); int cxl_debugfs_init(void); diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c index a30bf285b5bd..7ccd2998be92 100644 --- a/drivers/misc/cxl/file.c +++ b/drivers/misc/cxl/file.c @@ -120,9 +120,16 @@ int afu_release(struct inode *inode, struct file *file) __func__, ctx->pe); cxl_context_detach(ctx); - mutex_lock(&ctx->mapping_lock); - ctx->mapping = NULL; - mutex_unlock(&ctx->mapping_lock); + + /* + * Delete the context's mapping pointer, unless it's created by the + * kernel API, in which case leave it so it can be freed by reclaim_ctx() + */ + if (!ctx->kernelapi) { + mutex_lock(&ctx->mapping_lock); + ctx->mapping = NULL; + mutex_unlock(&ctx->mapping_lock); + } put_device(&ctx->afu->dev); diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c index 583b42afeda2..09a406058c46 100644 --- a/drivers/misc/cxl/irq.c +++ b/drivers/misc/cxl/irq.c @@ -414,7 +414,7 @@ void cxl_release_psl_irq(struct cxl_afu *afu) kfree(afu->psl_irq_name); } -static void afu_irq_name_free(struct cxl_context *ctx) +void afu_irq_name_free(struct cxl_context *ctx) { struct cxl_irq_name *irq_name, *tmp; @@ -524,7 +524,5 @@ void afu_release_irqs(struct cxl_context *ctx, void *cookie) afu_irq_name_free(ctx); cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter); - kfree(ctx->irq_bitmap); - ctx->irq_bitmap = NULL; ctx->irq_count = 0; } diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c index b37f2e8004f5..d2e75c88f4d2 100644 --- a/drivers/misc/cxl/native.c +++ b/drivers/misc/cxl/native.c @@ -457,6 +457,7 @@ static int activate_afu_directed(struct cxl_afu *afu) dev_info(&afu->dev, "Activating AFU directed mode\n"); + afu->num_procs = afu->max_procs_virtualised; if (afu->spa == NULL) { if (cxl_alloc_spa(afu)) return -ENOMEM; @@ -468,7 +469,6 @@ static int activate_afu_directed(struct cxl_afu *afu) cxl_p1n_write(afu, CXL_PSL_ID_An, CXL_PSL_ID_An_F | CXL_PSL_ID_An_L); afu->current_mode = CXL_MODE_DIRECTED; - afu->num_procs = afu->max_procs_virtualised; if ((rc = cxl_chardev_m_afu_add(afu))) return rc; diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index a5e977192b61..85761d7eb333 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -1035,6 +1035,32 @@ static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev) return 0; } +/* + * Workaround a PCIe Host Bridge defect on some cards, that can cause + * malformed Transaction Layer Packet (TLP) errors to be erroneously + * reported. Mask this error in the Uncorrectable Error Mask Register. + * + * The upper nibble of the PSL revision is used to distinguish between + * different cards. The affected ones have it set to 0. + */ +static void cxl_fixup_malformed_tlp(struct cxl *adapter, struct pci_dev *dev) +{ + int aer; + u32 data; + + if (adapter->psl_rev & 0xf000) + return; + if (!(aer = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR))) + return; + pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, &data); + if (data & PCI_ERR_UNC_MALF_TLP) + if (data & PCI_ERR_UNC_INTN) + return; + data |= PCI_ERR_UNC_MALF_TLP; + data |= PCI_ERR_UNC_INTN; + pci_write_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, data); +} + static int cxl_vsec_looks_ok(struct cxl *adapter, struct pci_dev *dev) { if (adapter->vsec_status & CXL_STATUS_SECOND_PORT) @@ -1134,6 +1160,8 @@ static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev) if ((rc = cxl_vsec_looks_ok(adapter, dev))) return rc; + cxl_fixup_malformed_tlp(adapter, dev); + if ((rc = setup_cxl_bars(dev))) return rc; diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c index 8eec887c8f70..6d7c188fb65c 100644 --- a/drivers/misc/mei/hbm.c +++ b/drivers/misc/mei/hbm.c @@ -1209,7 +1209,7 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) * after the host receives the enum_resp * message clients may be added or removed */ - if (dev->hbm_state <= MEI_HBM_ENUM_CLIENTS && + if (dev->hbm_state <= MEI_HBM_ENUM_CLIENTS || dev->hbm_state >= MEI_HBM_STOPPED) { dev_err(dev->dev, "hbm: add client: state mismatch, [%d, %d]\n", dev->dev_state, dev->hbm_state); diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 781e4db31767..7fb0753abe30 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -182,6 +182,7 @@ struct omap_hsmmc_host { struct clk *fclk; struct clk *dbclk; struct regulator *pbias; + bool pbias_enabled; void __iomem *base; int vqmmc_enabled; resource_size_t mapbase; @@ -328,20 +329,22 @@ static int omap_hsmmc_set_pbias(struct omap_hsmmc_host *host, bool power_on, return ret; } - if (!regulator_is_enabled(host->pbias)) { + if (host->pbias_enabled == 0) { ret = regulator_enable(host->pbias); if (ret) { dev_err(host->dev, "pbias reg enable fail\n"); return ret; } + host->pbias_enabled = 1; } } else { - if (regulator_is_enabled(host->pbias)) { + if (host->pbias_enabled == 1) { ret = regulator_disable(host->pbias); if (ret) { dev_err(host->dev, "pbias reg disable fail\n"); return ret; } + host->pbias_enabled = 0; } } @@ -475,7 +478,7 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host) mmc->supply.vmmc = devm_regulator_get_optional(host->dev, "vmmc"); if (IS_ERR(mmc->supply.vmmc)) { ret = PTR_ERR(mmc->supply.vmmc); - if (ret != -ENODEV) + if ((ret != -ENODEV) && host->dev->of_node) return ret; dev_dbg(host->dev, "unable to get vmmc regulator %ld\n", PTR_ERR(mmc->supply.vmmc)); @@ -490,7 +493,7 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host) mmc->supply.vqmmc = devm_regulator_get_optional(host->dev, "vmmc_aux"); if (IS_ERR(mmc->supply.vqmmc)) { ret = PTR_ERR(mmc->supply.vqmmc); - if (ret != -ENODEV) + if ((ret != -ENODEV) && host->dev->of_node) return ret; dev_dbg(host->dev, "unable to get vmmc_aux regulator %ld\n", PTR_ERR(mmc->supply.vqmmc)); @@ -500,7 +503,7 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host) host->pbias = devm_regulator_get_optional(host->dev, "pbias"); if (IS_ERR(host->pbias)) { ret = PTR_ERR(host->pbias); - if (ret != -ENODEV) + if ((ret != -ENODEV) && host->dev->of_node) return ret; dev_dbg(host->dev, "unable to get pbias regulator %ld\n", PTR_ERR(host->pbias)); @@ -2053,6 +2056,7 @@ static int omap_hsmmc_probe(struct platform_device *pdev) host->base = base + pdata->reg_offset; host->power_mode = MMC_POWER_OFF; host->next_data.cookie = 1; + host->pbias_enabled = 0; host->vqmmc_enabled = 0; ret = omap_hsmmc_gpio_init(mmc, host, pdata); diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c index d1556643a41d..a0f05de5409f 100644 --- a/drivers/mmc/host/sdhci-of-at91.c +++ b/drivers/mmc/host/sdhci-of-at91.c @@ -43,6 +43,7 @@ static const struct sdhci_ops sdhci_at91_sama5d2_ops = { static const struct sdhci_pltfm_data soc_data_sama5d2 = { .ops = &sdhci_at91_sama5d2_ops, + .quirks2 = SDHCI_QUIRK2_NEED_DELAY_AFTER_INT_CLK_RST, }; static const struct of_device_id sdhci_at91_dt_match[] = { diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c index 946d37f94a31..f5edf9d3a18a 100644 --- a/drivers/mmc/host/sdhci-pxav3.c +++ b/drivers/mmc/host/sdhci-pxav3.c @@ -135,6 +135,7 @@ static int armada_38x_quirks(struct platform_device *pdev, struct sdhci_pxa *pxa = pltfm_host->priv; struct resource *res; + host->quirks &= ~SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN; host->quirks |= SDHCI_QUIRK_MISSING_CAPS; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "conf-sdio3"); @@ -290,6 +291,9 @@ static void pxav3_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs) uhs == MMC_TIMING_UHS_DDR50) { reg_val &= ~SDIO3_CONF_CLK_INV; reg_val |= SDIO3_CONF_SD_FB_CLK; + } else if (uhs == MMC_TIMING_MMC_HS) { + reg_val &= ~SDIO3_CONF_CLK_INV; + reg_val &= ~SDIO3_CONF_SD_FB_CLK; } else { reg_val |= SDIO3_CONF_CLK_INV; reg_val &= ~SDIO3_CONF_SD_FB_CLK; @@ -398,7 +402,7 @@ static int sdhci_pxav3_probe(struct platform_device *pdev) if (of_device_is_compatible(np, "marvell,armada-380-sdhci")) { ret = armada_38x_quirks(pdev, host); if (ret < 0) - goto err_clk_get; + goto err_mbus_win; ret = mv_conf_mbus_windows(pdev, mv_mbus_dram_info()); if (ret < 0) goto err_mbus_win; diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 64b7fdbd1a9c..fbc7efdddcb5 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1160,6 +1160,8 @@ void sdhci_set_clock(struct sdhci_host *host, unsigned int clock) host->mmc->actual_clock = 0; sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL); + if (host->quirks2 & SDHCI_QUIRK2_NEED_DELAY_AFTER_INT_CLK_RST) + mdelay(1); if (clock == 0) return; diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index 7c02ff46c8ac..9d4aa31b683a 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -412,6 +412,11 @@ struct sdhci_host { #define SDHCI_QUIRK2_ACMD23_BROKEN (1<<14) /* Broken Clock divider zero in controller */ #define SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN (1<<15) +/* + * When internal clock is disabled, a delay is needed before modifying the + * SD clock frequency or enabling back the internal clock. + */ +#define SDHCI_QUIRK2_NEED_DELAY_AFTER_INT_CLK_RST (1<<16) int irq; /* Device IRQ */ void __iomem *ioaddr; /* Mapped address */ diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c index 2426db88db36..f04445b992f5 100644 --- a/drivers/mtd/nand/mxc_nand.c +++ b/drivers/mtd/nand/mxc_nand.c @@ -879,7 +879,7 @@ static void copy_spare(struct mtd_info *mtd, bool bfrom) oob_chunk_size); /* the last chunk */ - memcpy16_toio(&s[oob_chunk_size * sparebuf_size], + memcpy16_toio(&s[i * sparebuf_size], &d[i * oob_chunk_size], host->used_oobsize - i * oob_chunk_size); } diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c index f97a58d6aae1..e7d333c162be 100644 --- a/drivers/mtd/nand/sunxi_nand.c +++ b/drivers/mtd/nand/sunxi_nand.c @@ -147,6 +147,10 @@ #define NFC_ECC_MODE GENMASK(15, 12) #define NFC_RANDOM_SEED GENMASK(30, 16) +/* NFC_USER_DATA helper macros */ +#define NFC_BUF_TO_USER_DATA(buf) ((buf)[0] | ((buf)[1] << 8) | \ + ((buf)[2] << 16) | ((buf)[3] << 24)) + #define NFC_DEFAULT_TIMEOUT_MS 1000 #define NFC_SRAM_SIZE 1024 @@ -646,15 +650,9 @@ static int sunxi_nfc_hw_ecc_write_page(struct mtd_info *mtd, offset = layout->eccpos[i * ecc->bytes] - 4 + mtd->writesize; /* Fill OOB data in */ - if (oob_required) { - tmp = 0xffffffff; - memcpy_toio(nfc->regs + NFC_REG_USER_DATA_BASE, &tmp, - 4); - } else { - memcpy_toio(nfc->regs + NFC_REG_USER_DATA_BASE, - chip->oob_poi + offset - mtd->writesize, - 4); - } + writel(NFC_BUF_TO_USER_DATA(chip->oob_poi + + layout->oobfree[i].offset), + nfc->regs + NFC_REG_USER_DATA_BASE); chip->cmdfunc(mtd, NAND_CMD_RNDIN, offset, -1); @@ -784,14 +782,8 @@ static int sunxi_nfc_hw_syndrome_ecc_write_page(struct mtd_info *mtd, offset += ecc->size; /* Fill OOB data in */ - if (oob_required) { - tmp = 0xffffffff; - memcpy_toio(nfc->regs + NFC_REG_USER_DATA_BASE, &tmp, - 4); - } else { - memcpy_toio(nfc->regs + NFC_REG_USER_DATA_BASE, oob, - 4); - } + writel(NFC_BUF_TO_USER_DATA(oob), + nfc->regs + NFC_REG_USER_DATA_BASE); tmp = NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD | NFC_ACCESS_DIR | (1 << 30); @@ -1389,6 +1381,7 @@ static void sunxi_nand_chips_cleanup(struct sunxi_nfc *nfc) node); nand_release(&chip->mtd); sunxi_nand_ecc_cleanup(&chip->nand.ecc); + list_del(&chip->node); } } diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index b9ebd0d18a52..f184fb5bd110 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -298,8 +298,10 @@ config NLMON config NET_VRF tristate "Virtual Routing and Forwarding (Lite)" - depends on IP_MULTIPLE_TABLES && IPV6_MULTIPLE_TABLES + depends on IP_MULTIPLE_TABLES depends on NET_L3_MASTER_DEV + depends on IPV6 || IPV6=n + depends on IPV6_MULTIPLE_TABLES || IPV6=n ---help--- This option enables the support for mapping interfaces into VRF's. The support enables VRF devices. diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 90f2615428c0..d0f23cd6e236 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1071,7 +1071,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev, NETIF_F_HIGHDMA | NETIF_F_LRO) #define BOND_ENC_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | NETIF_F_RXCSUM |\ - NETIF_F_TSO) + NETIF_F_ALL_TSO) static void bond_compute_features(struct bonding *bond) { diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 945c0955a967..8b3275d7792a 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -8,15 +8,6 @@ * Public License ("GPL") version 2 as distributed in the 'COPYING' * file from the main directory of the linux kernel source. * - * - * Your platform definition file should specify something like: - * - * static struct at91_can_data ek_can_data = { - * transceiver_switch = sam9263ek_transceiver_switch, - * }; - * - * at91_add_device_can(&ek_can_data); - * */ #include <linux/clk.h> @@ -33,7 +24,6 @@ #include <linux/spinlock.h> #include <linux/string.h> #include <linux/types.h> -#include <linux/platform_data/atmel.h> #include <linux/can/dev.h> #include <linux/can/error.h> @@ -324,15 +314,6 @@ static inline u32 at91_can_id_to_reg_mid(canid_t can_id) return reg_mid; } -/* - * Swtich transceiver on or off - */ -static void at91_transceiver_switch(const struct at91_priv *priv, int on) -{ - if (priv->pdata && priv->pdata->transceiver_switch) - priv->pdata->transceiver_switch(on); -} - static void at91_setup_mailboxes(struct net_device *dev) { struct at91_priv *priv = netdev_priv(dev); @@ -416,7 +397,6 @@ static void at91_chip_start(struct net_device *dev) at91_set_bittiming(dev); at91_setup_mailboxes(dev); - at91_transceiver_switch(priv, 1); /* enable chip */ if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) @@ -444,7 +424,6 @@ static void at91_chip_stop(struct net_device *dev, enum can_state state) reg_mr = at91_read(priv, AT91_MR); at91_write(priv, AT91_MR, reg_mr & ~AT91_MR_CANEN); - at91_transceiver_switch(priv, 0); priv->can.state = state; } diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c index e5fac368068a..131026fbc2d7 100644 --- a/drivers/net/can/sja1000/peak_pci.c +++ b/drivers/net/can/sja1000/peak_pci.c @@ -87,6 +87,7 @@ static const struct pci_device_id peak_pci_tbl[] = { {PEAK_PCI_VENDOR_ID, PEAK_PC_104P_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,}, {PEAK_PCI_VENDOR_ID, PEAK_PCI_104E_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,}, {PEAK_PCI_VENDOR_ID, PEAK_CPCI_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,}, + {PEAK_PCI_VENDOR_ID, PEAK_PCIE_OEM_ID, PCI_ANY_ID, PCI_ANY_ID,}, #ifdef CONFIG_CAN_PEAK_PCIEC {PEAK_PCI_VENDOR_ID, PEAK_PCIEC_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,}, {PEAK_PCI_VENDOR_ID, PEAK_PCIEC34_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,}, diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 10d8497635e8..d9a42c646783 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -601,7 +601,7 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status) stats->tx_errors++; if (likely(skb)) { cf->can_id |= CAN_ERR_LOSTARB; - cf->data[0] = (alc & 0x1f) >> 8; + cf->data[0] = (alc >> 8) & 0x1f; } } @@ -854,4 +854,4 @@ module_platform_driver(sun4i_can_driver); MODULE_AUTHOR("Peter Chen <[email protected]>"); MODULE_AUTHOR("Gerhard Bertelsmann <[email protected]>"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_DESCRIPTION(DRV_NAME "CAN driver for Allwinner SoCs (A10/A20)"); +MODULE_DESCRIPTION("CAN driver for Allwinner SoCs (A10/A20)"); diff --git a/drivers/net/dsa/mv88e6171.c b/drivers/net/dsa/mv88e6171.c index ca3330aec740..dfca352e78e3 100644 --- a/drivers/net/dsa/mv88e6171.c +++ b/drivers/net/dsa/mv88e6171.c @@ -113,8 +113,6 @@ struct dsa_switch_driver mv88e6171_switch_driver = { #endif .get_regs_len = mv88e6xxx_get_regs_len, .get_regs = mv88e6xxx_get_regs, - .port_join_bridge = mv88e6xxx_join_bridge, - .port_leave_bridge = mv88e6xxx_leave_bridge, .port_stp_update = mv88e6xxx_port_stp_update, .port_pvid_get = mv88e6xxx_port_pvid_get, .port_pvid_set = mv88e6xxx_port_pvid_set, diff --git a/drivers/net/dsa/mv88e6352.c b/drivers/net/dsa/mv88e6352.c index 078a358c1b83..796fdcbe3c6e 100644 --- a/drivers/net/dsa/mv88e6352.c +++ b/drivers/net/dsa/mv88e6352.c @@ -340,8 +340,6 @@ struct dsa_switch_driver mv88e6352_switch_driver = { .set_eeprom = mv88e6352_set_eeprom, .get_regs_len = mv88e6xxx_get_regs_len, .get_regs = mv88e6xxx_get_regs, - .port_join_bridge = mv88e6xxx_join_bridge, - .port_leave_bridge = mv88e6xxx_leave_bridge, .port_stp_update = mv88e6xxx_port_stp_update, .port_pvid_get = mv88e6xxx_port_pvid_get, .port_pvid_set = mv88e6xxx_port_pvid_set, diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 87b405e4f9f6..4591240eb795 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -1046,11 +1046,6 @@ static int _mv88e6xxx_atu_flush(struct dsa_switch *ds, u16 fid, bool static_too) return _mv88e6xxx_atu_flush_move(ds, &entry, static_too); } -static int _mv88e6xxx_flush_fid(struct dsa_switch *ds, int fid) -{ - return _mv88e6xxx_atu_flush(ds, fid, false); -} - static int _mv88e6xxx_atu_move(struct dsa_switch *ds, u16 fid, int from_port, int to_port, bool static_too) { @@ -1112,130 +1107,21 @@ abort: return ret; } -/* Must be called with smi lock held */ -static int _mv88e6xxx_update_port_config(struct dsa_switch *ds, int port) -{ - struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - u8 fid = ps->fid[port]; - u16 reg = fid << 12; - - if (dsa_is_cpu_port(ds, port)) - reg |= ds->phys_port_mask; - else - reg |= (ps->bridge_mask[fid] | - (1 << dsa_upstream_port(ds))) & ~(1 << port); - - return _mv88e6xxx_reg_write(ds, REG_PORT(port), PORT_BASE_VLAN, reg); -} - -/* Must be called with smi lock held */ -static int _mv88e6xxx_update_bridge_config(struct dsa_switch *ds, int fid) +static int _mv88e6xxx_port_vlan_map_set(struct dsa_switch *ds, int port, + u16 output_ports) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - int port; - u32 mask; - int ret; - - mask = ds->phys_port_mask; - while (mask) { - port = __ffs(mask); - mask &= ~(1 << port); - if (ps->fid[port] != fid) - continue; - - ret = _mv88e6xxx_update_port_config(ds, port); - if (ret) - return ret; - } - - return _mv88e6xxx_flush_fid(ds, fid); -} - -/* Bridge handling functions */ - -int mv88e6xxx_join_bridge(struct dsa_switch *ds, int port, u32 br_port_mask) -{ - struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - int ret = 0; - u32 nmask; - int fid; - - /* If the bridge group is not empty, join that group. - * Otherwise create a new group. - */ - fid = ps->fid[port]; - nmask = br_port_mask & ~(1 << port); - if (nmask) - fid = ps->fid[__ffs(nmask)]; - - nmask = ps->bridge_mask[fid] | (1 << port); - if (nmask != br_port_mask) { - netdev_err(ds->ports[port], - "join: Bridge port mask mismatch fid=%d mask=0x%x expected 0x%x\n", - fid, br_port_mask, nmask); - return -EINVAL; - } - - mutex_lock(&ps->smi_mutex); - - ps->bridge_mask[fid] = br_port_mask; - - if (fid != ps->fid[port]) { - clear_bit(ps->fid[port], ps->fid_bitmap); - ps->fid[port] = fid; - ret = _mv88e6xxx_update_bridge_config(ds, fid); - } - - mutex_unlock(&ps->smi_mutex); - - return ret; -} - -int mv88e6xxx_leave_bridge(struct dsa_switch *ds, int port, u32 br_port_mask) -{ - struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - u8 fid, newfid; - int ret; - - fid = ps->fid[port]; - - if (ps->bridge_mask[fid] != br_port_mask) { - netdev_err(ds->ports[port], - "leave: Bridge port mask mismatch fid=%d mask=0x%x expected 0x%x\n", - fid, br_port_mask, ps->bridge_mask[fid]); - return -EINVAL; - } - - /* If the port was the last port of a bridge, we are done. - * Otherwise assign a new fid to the port, and fix up - * the bridge configuration. - */ - if (br_port_mask == (1 << port)) - return 0; - - mutex_lock(&ps->smi_mutex); - - newfid = find_next_zero_bit(ps->fid_bitmap, VLAN_N_VID, 1); - if (unlikely(newfid > ps->num_ports)) { - netdev_err(ds->ports[port], "all first %d FIDs are used\n", - ps->num_ports); - ret = -ENOSPC; - goto unlock; - } - - ps->fid[port] = newfid; - set_bit(newfid, ps->fid_bitmap); - ps->bridge_mask[fid] &= ~(1 << port); - ps->bridge_mask[newfid] = 1 << port; + const u16 mask = (1 << ps->num_ports) - 1; + int reg; - ret = _mv88e6xxx_update_bridge_config(ds, fid); - if (!ret) - ret = _mv88e6xxx_update_bridge_config(ds, newfid); + reg = _mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_BASE_VLAN); + if (reg < 0) + return reg; -unlock: - mutex_unlock(&ps->smi_mutex); + reg &= ~mask; + reg |= output_ports & mask; - return ret; + return _mv88e6xxx_reg_write(ds, REG_PORT(port), PORT_BASE_VLAN, reg); } int mv88e6xxx_port_stp_update(struct dsa_switch *ds, int port, u8 state) @@ -1547,6 +1433,7 @@ static int _mv88e6xxx_vlan_init(struct dsa_switch *ds, u16 vid, struct mv88e6xxx_vtu_stu_entry vlan = { .valid = true, .vid = vid, + .fid = vid, /* We use one FID per VLAN */ }; int i; @@ -1580,22 +1467,10 @@ static int _mv88e6xxx_vlan_init(struct dsa_switch *ds, u16 vid, return err; } - /* Non-bridged ports and bridge groups use FIDs from 1 to - * num_ports; VLANs use FIDs from num_ports+1 to 4095. - */ - vlan.fid = find_next_zero_bit(ps->fid_bitmap, VLAN_N_VID, - ps->num_ports + 1); - if (unlikely(vlan.fid == VLAN_N_VID)) { - pr_err("no more FID available for VLAN %d\n", vid); - return -ENOSPC; - } - /* Clear all MAC addresses from the new database */ err = _mv88e6xxx_atu_flush(ds, vlan.fid, true); if (err) return err; - - set_bit(vlan.fid, ps->fid_bitmap); } *entry = vlan; @@ -1635,7 +1510,6 @@ int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, u16 vid) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); struct mv88e6xxx_vtu_stu_entry vlan; - bool keep = false; int i, err; mutex_lock(&ps->smi_mutex); @@ -1653,28 +1527,22 @@ int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, u16 vid) vlan.data[port] = GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER; /* keep the VLAN unless all ports are excluded */ + vlan.valid = false; for (i = 0; i < ps->num_ports; ++i) { if (dsa_is_cpu_port(ds, i)) continue; if (vlan.data[i] != GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER) { - keep = true; + vlan.valid = true; break; } } - vlan.valid = keep; err = _mv88e6xxx_vtu_loadpurge(ds, &vlan); if (err) goto unlock; err = _mv88e6xxx_atu_remove(ds, vlan.fid, port, false); - if (err) - goto unlock; - - if (!keep) - clear_bit(vlan.fid, ps->fid_bitmap); - unlock: mutex_unlock(&ps->smi_mutex); @@ -1801,37 +1669,13 @@ static int _mv88e6xxx_atu_load(struct dsa_switch *ds, return _mv88e6xxx_atu_cmd(ds, GLOBAL_ATU_OP_LOAD_DB); } -static int _mv88e6xxx_port_vid_to_fid(struct dsa_switch *ds, int port, u16 vid) -{ - struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - struct mv88e6xxx_vtu_stu_entry vlan; - int err; - - if (vid == 0) - return ps->fid[port]; - - err = _mv88e6xxx_port_vtu_getnext(ds, port, vid - 1, &vlan); - if (err) - return err; - - if (vlan.vid == vid) - return vlan.fid; - - return -ENOENT; -} - static int _mv88e6xxx_port_fdb_load(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, u8 state) { struct mv88e6xxx_atu_entry entry = { 0 }; - int ret; - ret = _mv88e6xxx_port_vid_to_fid(ds, port, vid); - if (ret < 0) - return ret; - - entry.fid = ret; + entry.fid = vid; /* We use one FID per VLAN */ entry.state = state; ether_addr_copy(entry.mac, addr); if (state != GLOBAL_ATU_DATA_STATE_UNUSED) { @@ -1846,6 +1690,10 @@ int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans) { + /* We don't use per-port FDB */ + if (fdb->vid == 0) + return -EOPNOTSUPP; + /* We don't need any dynamic resource from the kernel (yet), * so skip the prepare phase. */ @@ -1943,16 +1791,11 @@ int mv88e6xxx_port_fdb_getnext(struct dsa_switch *ds, int port, { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); struct mv88e6xxx_atu_entry next; - u16 fid; + u16 fid = *vid; /* We use one FID per VLAN */ int ret; mutex_lock(&ps->smi_mutex); - ret = _mv88e6xxx_port_vid_to_fid(ds, port, *vid); - if (ret < 0) - goto unlock; - fid = ret; - do { if (is_broadcast_ether_addr(addr)) { struct mv88e6xxx_vtu_stu_entry vtu; @@ -2003,7 +1846,7 @@ static void mv88e6xxx_bridge_work(struct work_struct *work) static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - int ret, fid; + int ret; u16 reg; mutex_lock(&ps->smi_mutex); @@ -2129,7 +1972,7 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) reg |= PORT_CONTROL_2_FORWARD_UNKNOWN; } - reg |= PORT_CONTROL_2_8021Q_FALLBACK; + reg |= PORT_CONTROL_2_8021Q_SECURE; if (reg) { ret = _mv88e6xxx_reg_write(ds, REG_PORT(port), @@ -2222,19 +2065,11 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) if (ret) goto abort; - /* Port based VLAN map: give each port its own address - * database, allow the CPU port to talk to each of the 'real' - * ports, and allow each of the 'real' ports to only talk to - * the upstream port. + /* Port based VLAN map: do not give each port its own address + * database, and allow every port to egress frames on all other ports. */ - fid = port + 1; - ps->fid[port] = fid; - set_bit(fid, ps->fid_bitmap); - - if (!dsa_is_cpu_port(ds, port)) - ps->bridge_mask[fid] = 1 << port; - - ret = _mv88e6xxx_update_port_config(ds, port); + reg = BIT(ps->num_ports) - 1; /* all ports */ + ret = _mv88e6xxx_port_vlan_map_set(ds, port, reg & ~port); if (ret) goto abort; diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index 8325c11b9be2..4ba69f339bfe 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -402,12 +402,6 @@ struct mv88e6xxx_priv_state { int id; /* switch product id */ int num_ports; /* number of switch ports */ - /* hw bridging */ - - DECLARE_BITMAP(fid_bitmap, VLAN_N_VID); /* FIDs 1 to 4095 available */ - u16 fid[DSA_MAX_PORTS]; /* per (non-bridged) port FID */ - u16 bridge_mask[DSA_MAX_PORTS]; /* br groups (indexed by FID) */ - unsigned long port_state_update_mask; u8 port_state[DSA_MAX_PORTS]; @@ -464,8 +458,6 @@ int mv88e6xxx_phy_write_indirect(struct dsa_switch *ds, int addr, int regnum, int mv88e6xxx_get_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e); int mv88e6xxx_set_eee(struct dsa_switch *ds, int port, struct phy_device *phydev, struct ethtool_eee *e); -int mv88e6xxx_join_bridge(struct dsa_switch *ds, int port, u32 br_port_mask); -int mv88e6xxx_leave_bridge(struct dsa_switch *ds, int port, u32 br_port_mask); int mv88e6xxx_port_stp_update(struct dsa_switch *ds, int port, u8 state); int mv88e6xxx_port_pvid_get(struct dsa_switch *ds, int port, u16 *vid); int mv88e6xxx_port_pvid_set(struct dsa_switch *ds, int port, u16 vid); diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index 815eb94990f5..69fc8409a973 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -147,8 +147,12 @@ static void dummy_setup(struct net_device *dev) dev->flags |= IFF_NOARP; dev->flags &= ~IFF_MULTICAST; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; - dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_TSO; + dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST; + dev->features |= NETIF_F_ALL_TSO | NETIF_F_UFO; dev->features |= NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX; + dev->features |= NETIF_F_GSO_ENCAP_ALL; + dev->hw_features |= dev->features; + dev->hw_enc_features |= dev->features; eth_hw_addr_random(dev); } diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index ae89de7deb13..20bf55dbd76f 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -1141,8 +1141,6 @@ static void greth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *in strlcpy(info->version, "revision: 1.0", sizeof(info->version)); strlcpy(info->bus_info, greth->dev->bus->name, sizeof(info->bus_info)); strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); - info->eedump_len = 0; - info->regdump_len = sizeof(struct greth_regs); } static void greth_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *p) diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index cb367cc59e0b..5330bcb8a944 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -714,7 +714,6 @@ au1000_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) strlcpy(info->version, DRV_VERSION, sizeof(info->version)); snprintf(info->bus_info, sizeof(info->bus_info), "%s %d", DRV_NAME, aup->mac_id); - info->regdump_len = 0; } static void au1000_set_msglevel(struct net_device *dev, u32 value) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c index 2c063b60db4b..96f485ab612e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c @@ -327,9 +327,13 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata) pdata->debugfs_xpcs_reg = 0; buf = kasprintf(GFP_KERNEL, "amd-xgbe-%s", pdata->netdev->name); + if (!buf) + return; + pdata->xgbe_debugfs = debugfs_create_dir(buf, NULL); if (!pdata->xgbe_debugfs) { netdev_err(pdata->netdev, "debugfs_create_dir failed\n"); + kfree(buf); return; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 14bad8c44c87..49f796aaad4f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -365,7 +365,7 @@ static irqreturn_t xgbe_isr(int irq, void *data) /* Restart the device on a Fatal Bus Error */ if (XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, FBE)) - queue_work(pdata->dev_workqueue, &pdata->restart_work); + schedule_work(&pdata->restart_work); /* Clear all interrupt signals */ XGMAC_DMA_IOWRITE(channel, DMA_CH_SR, dma_ch_isr); @@ -1537,7 +1537,7 @@ static void xgbe_tx_timeout(struct net_device *netdev) struct xgbe_prv_data *pdata = netdev_priv(netdev); netdev_warn(netdev, "tx timeout, device restarting\n"); - queue_work(pdata->dev_workqueue, &pdata->restart_work); + schedule_work(&pdata->restart_work); } static struct rtnl_link_stats64 *xgbe_get_stats64(struct net_device *netdev, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index 204fb3afb182..6040293db9c1 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -375,7 +375,6 @@ static void xgbe_get_drvinfo(struct net_device *netdev, XGMAC_GET_BITS(hw_feat->version, MAC_VR, USERVER), XGMAC_GET_BITS(hw_feat->version, MAC_VR, DEVID), XGMAC_GET_BITS(hw_feat->version, MAC_VR, SNPSVER)); - drvinfo->n_stats = XGBE_STATS_COUNT; } static u32 xgbe_get_msglevel(struct net_device *netdev) diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c index 48694c239d5c..872b7abb0196 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c @@ -233,10 +233,6 @@ static void atl1c_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_stats = 0; - drvinfo->testinfo_len = 0; - drvinfo->regdump_len = atl1c_get_regs_len(netdev); - drvinfo->eedump_len = atl1c_get_eeprom_len(netdev); } static void atl1c_get_wol(struct net_device *netdev, diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c index 1be072f4afc2..8e3dbd4d9f79 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c @@ -316,10 +316,6 @@ static void atl1e_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->fw_version, "L1e", sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_stats = 0; - drvinfo->testinfo_len = 0; - drvinfo->regdump_len = atl1e_get_regs_len(netdev); - drvinfo->eedump_len = atl1e_get_eeprom_len(netdev); } static void atl1e_get_wol(struct net_device *netdev, diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index eca1d113fee1..529bca718334 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -3388,7 +3388,6 @@ static void atl1_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->eedump_len = ATL1_EEDUMP_LEN; } static void atl1_get_wol(struct net_device *netdev, diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index 46a535318c7a..8f76f4558a88 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -2030,10 +2030,6 @@ static void atl2_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->fw_version, "L2", sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_stats = 0; - drvinfo->testinfo_len = 0; - drvinfo->regdump_len = atl2_get_regs_len(netdev); - drvinfo->eedump_len = atl2_get_eeprom_len(netdev); } static void atl2_get_wol(struct net_device *netdev, diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index a7f2cc3e485e..95af75d35bc5 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1333,7 +1333,6 @@ static void bcm_enet_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->version)); strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, "bcm63xx", sizeof(drvinfo->bus_info)); - drvinfo->n_stats = BCM_ENET_STATS_LEN; } static int bcm_enet_get_sset_count(struct net_device *netdev, @@ -2597,7 +2596,6 @@ static void bcm_enetsw_get_drvinfo(struct net_device *netdev, strncpy(drvinfo->version, bcm_enet_driver_version, 32); strncpy(drvinfo->fw_version, "N/A", 32); strncpy(drvinfo->bus_info, "bcm63xx", 32); - drvinfo->n_stats = BCM_ENETSW_STATS_LEN; } static void bcm_enetsw_get_ethtool_stats(struct net_device *netdev, diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index f1b5364f3521..858106352ce9 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -287,7 +287,6 @@ static void bcm_sysport_get_drvinfo(struct net_device *dev, strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver)); strlcpy(info->version, "0.1", sizeof(info->version)); strlcpy(info->bus_info, "platform", sizeof(info->bus_info)); - info->n_stats = BCM_SYSPORT_STATS_LEN; } static u32 bcm_sysport_get_msglvl(struct net_device *dev) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index aeb7ce64452e..d84efcd34fac 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1090,10 +1090,6 @@ static void bnx2x_get_drvinfo(struct net_device *dev, bnx2x_fill_fw_str(bp, info->fw_version, sizeof(info->fw_version)); strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info)); - info->n_stats = BNX2X_NUM_STATS; - info->testinfo_len = BNX2X_NUM_TESTS(bp); - info->eedump_len = bp->common.flash_size; - info->regdump_len = bnx2x_get_regs_len(dev); } static void bnx2x_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) @@ -3351,6 +3347,13 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info) udp_rss_requested = 0; else return -EINVAL; + + if (CHIP_IS_E1x(bp) && udp_rss_requested) { + DP(BNX2X_MSG_ETHTOOL, + "57710, 57711 boards don't support RSS according to UDP 4-tuple\n"); + return -EINVAL; + } + if ((info->flow_type == UDP_V4_FLOW) && (bp->rss_conf_obj.udp_rss_v4 != udp_rss_requested)) { bp->rss_conf_obj.udp_rss_v4 = udp_rss_requested; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 1a3988f51305..50f63b7f3c3e 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -793,7 +793,6 @@ static void bcmgenet_get_drvinfo(struct net_device *dev, { strlcpy(info->driver, "bcmgenet", sizeof(info->driver)); strlcpy(info->version, "v2.0", sizeof(info->version)); - info->n_stats = BCMGENET_STATS_LEN; } static int bcmgenet_get_sset_count(struct net_device *dev, int string_set) @@ -1832,6 +1831,24 @@ static void bcmgenet_intr_disable(struct bcmgenet_priv *priv) bcmgenet_intrl2_1_writel(priv, 0, INTRL2_CPU_MASK_CLEAR); } +static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv) +{ + u32 int0_enable = 0; + + /* Monitor cable plug/unplugged event for internal PHY, external PHY + * and MoCA PHY + */ + if (priv->internal_phy) { + int0_enable |= UMAC_IRQ_LINK_EVENT; + } else if (priv->ext_phy) { + int0_enable |= UMAC_IRQ_LINK_EVENT; + } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { + if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET) + int0_enable |= UMAC_IRQ_LINK_EVENT; + } + bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR); +} + static int init_umac(struct bcmgenet_priv *priv) { struct device *kdev = &priv->pdev->dev; @@ -1872,15 +1889,8 @@ static int init_umac(struct bcmgenet_priv *priv) /* Enable Tx default queue 16 interrupts */ int0_enable |= UMAC_IRQ_TXDMA_DONE; - /* Monitor cable plug/unplugged event for internal PHY */ - if (priv->internal_phy) { - int0_enable |= UMAC_IRQ_LINK_EVENT; - } else if (priv->ext_phy) { - int0_enable |= UMAC_IRQ_LINK_EVENT; - } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { - if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET) - int0_enable |= UMAC_IRQ_LINK_EVENT; - + /* Configure backpressure vectors for MoCA */ + if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { reg = bcmgenet_bp_mc_get(priv); reg |= BIT(priv->hw_params->bp_in_en_shift); @@ -2794,6 +2804,9 @@ static void bcmgenet_netif_start(struct net_device *dev) netif_tx_start_all_queues(dev); + /* Monitor link interrupts now */ + bcmgenet_link_intr_enable(priv); + phy_start(priv->phydev); } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 29f330831784..245c063ed4db 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -153,7 +153,6 @@ lio_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) strncpy(drvinfo->fw_version, oct->fw_info.liquidio_firmware_version, ETHTOOL_FWVERS_LEN); strncpy(drvinfo->bus_info, pci_name(oct->pci_dev), 32); - drvinfo->regdump_len = OCT_ETHTOOL_REGDUMP_LEN; } static void diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 02e4e028a647..a077f9476daf 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -35,79 +35,79 @@ static void set_msglevel(struct net_device *dev, u32 val) } static const char stats_strings[][ETH_GSTRING_LEN] = { - "TxOctetsOK ", - "TxFramesOK ", - "TxBroadcastFrames ", - "TxMulticastFrames ", - "TxUnicastFrames ", - "TxErrorFrames ", - - "TxFrames64 ", - "TxFrames65To127 ", - "TxFrames128To255 ", - "TxFrames256To511 ", - "TxFrames512To1023 ", - "TxFrames1024To1518 ", - "TxFrames1519ToMax ", - - "TxFramesDropped ", - "TxPauseFrames ", - "TxPPP0Frames ", - "TxPPP1Frames ", - "TxPPP2Frames ", - "TxPPP3Frames ", - "TxPPP4Frames ", - "TxPPP5Frames ", - "TxPPP6Frames ", - "TxPPP7Frames ", - - "RxOctetsOK ", - "RxFramesOK ", - "RxBroadcastFrames ", - "RxMulticastFrames ", - "RxUnicastFrames ", - - "RxFramesTooLong ", - "RxJabberErrors ", - "RxFCSErrors ", - "RxLengthErrors ", - "RxSymbolErrors ", - "RxRuntFrames ", - - "RxFrames64 ", - "RxFrames65To127 ", - "RxFrames128To255 ", - "RxFrames256To511 ", - "RxFrames512To1023 ", - "RxFrames1024To1518 ", - "RxFrames1519ToMax ", - - "RxPauseFrames ", - "RxPPP0Frames ", - "RxPPP1Frames ", - "RxPPP2Frames ", - "RxPPP3Frames ", - "RxPPP4Frames ", - "RxPPP5Frames ", - "RxPPP6Frames ", - "RxPPP7Frames ", - - "RxBG0FramesDropped ", - "RxBG1FramesDropped ", - "RxBG2FramesDropped ", - "RxBG3FramesDropped ", - "RxBG0FramesTrunc ", - "RxBG1FramesTrunc ", - "RxBG2FramesTrunc ", - "RxBG3FramesTrunc ", - - "TSO ", - "TxCsumOffload ", - "RxCsumGood ", - "VLANextractions ", - "VLANinsertions ", - "GROpackets ", - "GROmerged ", + "tx_octets_ok ", + "tx_frames_ok ", + "tx_broadcast_frames ", + "tx_multicast_frames ", + "tx_unicast_frames ", + "tx_error_frames ", + + "tx_frames_64 ", + "tx_frames_65_to_127 ", + "tx_frames_128_to_255 ", + "tx_frames_256_to_511 ", + "tx_frames_512_to_1023 ", + "tx_frames_1024_to_1518 ", + "tx_frames_1519_to_max ", + + "tx_frames_dropped ", + "tx_pause_frames ", + "tx_ppp0_frames ", + "tx_ppp1_frames ", + "tx_ppp2_frames ", + "tx_ppp3_frames ", + "tx_ppp4_frames ", + "tx_ppp5_frames ", + "tx_ppp6_frames ", + "tx_ppp7_frames ", + + "rx_octets_ok ", + "rx_frames_ok ", + "rx_broadcast_frames ", + "rx_multicast_frames ", + "rx_unicast_frames ", + + "rx_frames_too_long ", + "rx_jabber_errors ", + "rx_fcs_errors ", + "rx_length_errors ", + "rx_symbol_errors ", + "rx_runt_frames ", + + "rx_frames_64 ", + "rx_frames_65_to_127 ", + "rx_frames_128_to_255 ", + "rx_frames_256_to_511 ", + "rx_frames_512_to_1023 ", + "rx_frames_1024_to_1518 ", + "rx_frames_1519_to_max ", + + "rx_pause_frames ", + "rx_ppp0_frames ", + "rx_ppp1_frames ", + "rx_ppp2_frames ", + "rx_ppp3_frames ", + "rx_ppp4_frames ", + "rx_ppp5_frames ", + "rx_ppp6_frames ", + "rx_ppp7_frames ", + + "rx_bg0_frames_dropped ", + "rx_bg1_frames_dropped ", + "rx_bg2_frames_dropped ", + "rx_bg3_frames_dropped ", + "rx_bg0_frames_trunc ", + "rx_bg1_frames_trunc ", + "rx_bg2_frames_trunc ", + "rx_bg3_frames_trunc ", + + "tso ", + "tx_csum_offload ", + "rx_csum_good ", + "vlan_extractions ", + "vlan_insertions ", + "gro_packets ", + "gro_merged ", }; static char adapter_stats_strings[][ETH_GSTRING_LEN] = { @@ -211,8 +211,11 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) sizeof(info->version)); strlcpy(info->bus_info, pci_name(adapter->pdev), sizeof(info->bus_info)); + info->regdump_len = get_regs_len(dev); - if (adapter->params.fw_vers) + if (!adapter->params.fw_vers) + strcpy(info->fw_version, "N/A"); + else snprintf(info->fw_version, sizeof(info->fw_version), "%u.%u.%u.%u, TP %u.%u.%u.%u", FW_HDR_FW_VER_MAJOR_G(adapter->params.fw_vers), @@ -612,6 +615,8 @@ static int set_settings(struct net_device *dev, struct ethtool_cmd *cmd) struct port_info *p = netdev_priv(dev); struct link_config *lc = &p->link_cfg; u32 speed = ethtool_cmd_speed(cmd); + struct link_config old_lc; + int ret; if (cmd->duplex != DUPLEX_FULL) /* only full-duplex supported */ return -EINVAL; @@ -626,13 +631,11 @@ static int set_settings(struct net_device *dev, struct ethtool_cmd *cmd) return -EINVAL; } + old_lc = *lc; if (cmd->autoneg == AUTONEG_DISABLE) { cap = speed_to_caps(speed); - if (!(lc->supported & cap) || - (speed == 1000) || - (speed == 10000) || - (speed == 40000)) + if (!(lc->supported & cap)) return -EINVAL; lc->requested_speed = cap; lc->advertising = 0; @@ -645,10 +648,14 @@ static int set_settings(struct net_device *dev, struct ethtool_cmd *cmd) } lc->autoneg = cmd->autoneg; - if (netif_running(dev)) - return t4_link_l1cfg(p->adapter, p->adapter->pf, p->tx_chan, - lc); - return 0; + /* If the firmware rejects the Link Configuration request, back out + * the changes and report the error. + */ + ret = t4_link_l1cfg(p->adapter, p->adapter->mbox, p->tx_chan, lc); + if (ret) + *lc = old_lc; + + return ret; } static void get_pauseparam(struct net_device *dev, @@ -847,7 +854,7 @@ static int get_eeprom(struct net_device *dev, struct ethtool_eeprom *e, { int i, err = 0; struct adapter *adapter = netdev2adap(dev); - u8 *buf = kmalloc(EEPROMSIZE, GFP_KERNEL); + u8 *buf = t4_alloc_mem(EEPROMSIZE); if (!buf) return -ENOMEM; @@ -858,7 +865,7 @@ static int get_eeprom(struct net_device *dev, struct ethtool_eeprom *e, if (!err) memcpy(data, buf + e->offset, e->len); - kfree(buf); + t4_free_mem(buf); return err; } @@ -887,7 +894,7 @@ static int set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, if (aligned_offset != eeprom->offset || aligned_len != eeprom->len) { /* RMW possibly needed for first or last words. */ - buf = kmalloc(aligned_len, GFP_KERNEL); + buf = t4_alloc_mem(aligned_len); if (!buf) return -ENOMEM; err = eeprom_rd_phys(adapter, aligned_offset, (u32 *)buf); @@ -915,7 +922,7 @@ static int set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, err = t4_seeprom_wp(adapter, true); out: if (buf != data) - kfree(buf); + t4_free_mem(buf); return err; } @@ -1011,11 +1018,15 @@ static int set_rss_table(struct net_device *dev, const u32 *p, const u8 *key, if (!p) return 0; - for (i = 0; i < pi->rss_size; i++) - pi->rss[i] = p[i]; - if (pi->adapter->flags & FULL_INIT_DONE) + /* Interface must be brought up atleast once */ + if (pi->adapter->flags & FULL_INIT_DONE) { + for (i = 0; i < pi->rss_size; i++) + pi->rss[i] = p[i]; + return cxgb4_write_rss(pi, pi->rss); - return 0; + } + + return -EPERM; } static int get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index c29227ee9ee8..2cf81857a297 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -83,7 +83,7 @@ char cxgb4_driver_name[] = KBUILD_MODNAME; #endif #define DRV_VERSION "2.0.0-ko" const char cxgb4_driver_version[] = DRV_VERSION; -#define DRV_DESC "Chelsio T4/T5 Network Driver" +#define DRV_DESC "Chelsio T4/T5/T6 Network Driver" /* Host shadow copy of ingress filter entry. This is in host native format * and doesn't match the ordering or bit order, etc. of the hardware of the @@ -151,6 +151,7 @@ MODULE_VERSION(DRV_VERSION); MODULE_DEVICE_TABLE(pci, cxgb4_pci_tbl); MODULE_FIRMWARE(FW4_FNAME); MODULE_FIRMWARE(FW5_FNAME); +MODULE_FIRMWARE(FW6_FNAME); /* * Normally we're willing to become the firmware's Master PF but will be happy @@ -4485,6 +4486,10 @@ static int enable_msix(struct adapter *adap) } for (i = 0; i < allocated; ++i) adap->msix_info[i].vec = entries[i].vector; + dev_info(adap->pdev_dev, "%d MSI-X vectors allocated, " + "nic %d iscsi %d rdma cpl %d rdma ciq %d\n", + allocated, s->max_ethqsets, s->ofldqsets, s->rdmaqs, + s->rdmaciqs); kfree(entries); return 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index b2b5e5bbe04c..0cfa5d72cafd 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -56,7 +56,7 @@ * Generic information about the driver. */ #define DRV_VERSION "2.0.0-ko" -#define DRV_DESC "Chelsio T4/T5 Virtual Function (VF) Network Driver" +#define DRV_DESC "Chelsio T4/T5/T6 Virtual Function (VF) Network Driver" /* * Module Parameters. diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index a02ecc4f9002..cadcee645f74 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -1597,7 +1597,6 @@ static void de_get_drvinfo (struct net_device *dev,struct ethtool_drvinfo *info) strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(de->pdev), sizeof(info->bus_info)); - info->eedump_len = DE_EEPROM_SIZE; } static int de_get_regs_len(struct net_device *dev) diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 821540913343..d463563e1f70 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -592,6 +592,7 @@ struct be_adapter { int be_get_temp_freq; struct be_hwmon hwmon_info; u8 pf_number; + u8 pci_func_num; struct rss_info rss_info; /* Filters for packets that need to be sent to BMC */ u32 bmc_filt_mask; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index eb323913cd39..1795c935ff02 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -851,8 +851,10 @@ static int be_cmd_notify_wait(struct be_adapter *adapter, return status; dest_wrb = be_cmd_copy(adapter, wrb); - if (!dest_wrb) - return -EBUSY; + if (!dest_wrb) { + status = -EBUSY; + goto unlock; + } if (use_mcc(adapter)) status = be_mcc_notify_wait(adapter); @@ -862,6 +864,7 @@ static int be_cmd_notify_wait(struct be_adapter *adapter, if (!status) memcpy(wrb, dest_wrb, sizeof(*wrb)); +unlock: be_cmd_unlock(adapter); return status; } @@ -1984,6 +1987,8 @@ int be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value) be_if_cap_flags(adapter)); } flags &= be_if_cap_flags(adapter); + if (!flags) + return -ENOTSUPP; return __be_cmd_rx_filter(adapter, flags, value); } @@ -2887,6 +2892,7 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter) if (!status) { attribs = attribs_cmd.va + sizeof(struct be_cmd_resp_hdr); adapter->hba_port_num = attribs->hba_attribs.phy_port; + adapter->pci_func_num = attribs->pci_func_num; serial_num = attribs->hba_attribs.controller_serial_number; for (i = 0; i < CNTL_SERIAL_NUM_WORDS; i++) adapter->serial_num[i] = le32_to_cpu(serial_num[i]) & @@ -3709,7 +3715,6 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res) status = -EINVAL; goto err; } - adapter->pf_number = desc->pf_num; be_copy_nic_desc(res, desc); } @@ -3721,7 +3726,10 @@ err: return status; } -/* Will use MBOX only if MCCQ has not been created */ +/* Will use MBOX only if MCCQ has not been created + * non-zero domain => a PF is querying this on behalf of a VF + * zero domain => a PF or a VF is querying this for itself + */ int be_cmd_get_profile_config(struct be_adapter *adapter, struct be_resources *res, u8 query, u8 domain) { @@ -3748,10 +3756,15 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, OPCODE_COMMON_GET_PROFILE_CONFIG, cmd.size, &wrb, &cmd); - req->hdr.domain = domain; if (!lancer_chip(adapter)) req->hdr.version = 1; req->type = ACTIVE_PROFILE_TYPE; + /* When a function is querying profile information relating to + * itself hdr.pf_number must be set to it's pci_func_num + 1 + */ + req->hdr.domain = domain; + if (domain == 0) + req->hdr.pf_num = adapter->pci_func_num + 1; /* When QUERY_MODIFIABLE_FIELDS_TYPE bit is set, cmd returns the * descriptors with all bits set to "1" for the fields which can be @@ -3921,12 +3934,16 @@ static void be_fill_vf_res_template(struct be_adapter *adapter, vf_if_cap_flags &= ~(BE_IF_FLAGS_RSS | BE_IF_FLAGS_DEFQ_RSS); } - - nic_vft->cap_flags = cpu_to_le32(vf_if_cap_flags); } 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); diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 7d178bdb112e..91155ea74f34 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -289,7 +289,9 @@ struct be_cmd_req_hdr { u32 timeout; /* dword 1 */ u32 request_length; /* dword 2 */ u8 version; /* dword 3 */ - u8 rsvd[3]; /* dword 3 */ + u8 rsvd1; /* dword 3 */ + u8 pf_num; /* dword 3 */ + u8 rsvd2; /* dword 3 */ }; #define RESP_HDR_INFO_OPCODE_SHIFT 0 /* bits 0 - 7 */ @@ -1652,7 +1654,11 @@ struct mgmt_hba_attribs { struct mgmt_controller_attrib { struct mgmt_hba_attribs hba_attribs; - u32 rsvd0[10]; + u32 rsvd0[2]; + u16 rsvd1; + u8 pci_func_num; + u8 rsvd2; + u32 rsvd3[7]; } __packed; struct be_cmd_req_cntl_attribs { diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 2c9ed1710ba6..f4cb8e425853 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -234,9 +234,6 @@ static void be_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->testinfo_len = 0; - drvinfo->regdump_len = 0; - drvinfo->eedump_len = 0; } static u32 lancer_cmd_get_file_len(struct be_adapter *adapter, u8 *file_name) diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 7bf51a1a0a77..eb48a977f8da 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1123,11 +1123,12 @@ static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter, struct sk_buff *skb, struct be_wrb_params *wrb_params) { - /* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or - * less may cause a transmit stall on that port. So the work-around is - * to pad short packets (<= 32 bytes) to a 36-byte length. + /* Lancer, SH and BE3 in SRIOV mode have a bug wherein + * packets that are 32b or less may cause a transmit stall + * on that port. The workaround is to pad such packets + * (len <= 32 bytes) to a minimum length of 36b. */ - if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) { + if (skb->len <= 32) { if (skb_put_padto(skb, 36)) return NULL; } @@ -4205,10 +4206,6 @@ static int be_get_config(struct be_adapter *adapter) int status, level; u16 profile_id; - status = be_cmd_get_cntl_attributes(adapter); - if (status) - return status; - status = be_cmd_query_fw_cfg(adapter); if (status) return status; @@ -4407,6 +4404,11 @@ static int be_setup(struct be_adapter *adapter) if (!lancer_chip(adapter)) be_cmd_req_native_mode(adapter); + /* Need to invoke this cmd first to get the PCI Function Number */ + status = be_cmd_get_cntl_attributes(adapter); + if (status) + return status; + if (!BE2_chip(adapter) && be_physfn(adapter)) be_alloc_sriov_res(adapter); @@ -4999,7 +5001,15 @@ static bool be_check_ufi_compatibility(struct be_adapter *adapter, return false; } - return (fhdr->asic_type_rev >= adapter->asic_rev); + /* In BE3 FW images the "asic_type_rev" field doesn't track the + * asic_rev of the chips it is compatible with. + * When asic_type_rev is 0 the image is compatible only with + * pre-BE3-R chips (asic_rev < 0x10) + */ + if (BEx_chip(adapter) && fhdr->asic_type_rev == 0) + return adapter->asic_rev < 0x10; + else + return (fhdr->asic_type_rev >= adapter->asic_rev); } static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw) diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index 3c40f6b99224..55c36230e176 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -198,11 +198,13 @@ static int fsl_pq_mdio_reset(struct mii_bus *bus) #if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE) /* + * Return the TBIPA address, starting from the address + * of the mapped GFAR MDIO registers (struct gfar) * This is mildly evil, but so is our hardware for doing this. * Also, we have to cast back to struct gfar because of * definition weirdness done in gianfar.h. */ -static uint32_t __iomem *get_gfar_tbipa(void __iomem *p) +static uint32_t __iomem *get_gfar_tbipa_from_mdio(void __iomem *p) { struct gfar __iomem *enet_regs = p; @@ -210,6 +212,15 @@ static uint32_t __iomem *get_gfar_tbipa(void __iomem *p) } /* + * Return the TBIPA address, starting from the address + * of the mapped GFAR MII registers (gfar_mii_regs[] within struct gfar) + */ +static uint32_t __iomem *get_gfar_tbipa_from_mii(void __iomem *p) +{ + return get_gfar_tbipa_from_mdio(container_of(p, struct gfar, gfar_mii_regs)); +} + +/* * Return the TBIPAR address for an eTSEC2 node */ static uint32_t __iomem *get_etsec_tbipa(void __iomem *p) @@ -220,11 +231,12 @@ static uint32_t __iomem *get_etsec_tbipa(void __iomem *p) #if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE) /* - * Return the TBIPAR address for a QE MDIO node + * Return the TBIPAR address for a QE MDIO node, starting from the address + * of the mapped MII registers (struct fsl_pq_mii) */ static uint32_t __iomem *get_ucc_tbipa(void __iomem *p) { - struct fsl_pq_mdio __iomem *mdio = p; + struct fsl_pq_mdio __iomem *mdio = container_of(p, struct fsl_pq_mdio, mii); return &mdio->utbipar; } @@ -300,14 +312,14 @@ static const struct of_device_id fsl_pq_mdio_match[] = { .compatible = "fsl,gianfar-tbi", .data = &(struct fsl_pq_mdio_data) { .mii_offset = 0, - .get_tbipa = get_gfar_tbipa, + .get_tbipa = get_gfar_tbipa_from_mii, }, }, { .compatible = "fsl,gianfar-mdio", .data = &(struct fsl_pq_mdio_data) { .mii_offset = 0, - .get_tbipa = get_gfar_tbipa, + .get_tbipa = get_gfar_tbipa_from_mii, }, }, { @@ -315,7 +327,7 @@ static const struct of_device_id fsl_pq_mdio_match[] = { .compatible = "gianfar", .data = &(struct fsl_pq_mdio_data) { .mii_offset = offsetof(struct fsl_pq_mdio, mii), - .get_tbipa = get_gfar_tbipa, + .get_tbipa = get_gfar_tbipa_from_mdio, }, }, { @@ -445,6 +457,16 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) tbipa = data->get_tbipa(priv->map); + /* + * Add consistency check to make sure TBI is contained + * within the mapped range (not because we would get a + * segfault, rather to catch bugs in computing TBI + * address). Print error message but continue anyway. + */ + if ((void *)tbipa > priv->map + resource_size(&res) - 4) + dev_err(&pdev->dev, "invalid register map (should be at least 0x%04x to contain TBI address)\n", + ((void *)tbipa - priv->map) + 4); + iowrite32be(be32_to_cpup(prop), tbipa); } } diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index fb7f8d67aef4..928ca2bdd238 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -182,8 +182,6 @@ static void gfar_gdrvinfo(struct net_device *dev, sizeof(drvinfo->version)); strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, "N/A", sizeof(drvinfo->bus_info)); - drvinfo->regdump_len = 0; - drvinfo->eedump_len = 0; } diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c index cc83350d56ba..89714f5e0dfc 100644 --- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c +++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c @@ -351,8 +351,6 @@ uec_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version)); strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, "QUICC ENGINE", sizeof(drvinfo->bus_info)); - drvinfo->eedump_len = 0; - drvinfo->regdump_len = uec_get_regs_len(netdev); } #ifdef CONFIG_PM diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 8d12b587809e..f250dec488fd 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 ARM || ARM64 + depends on OF && (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 a5e077eac99a..e51892d518ff 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -371,7 +371,7 @@ static void hix5hd2_port_enable(struct hix5hd2_priv *priv) static void hix5hd2_port_disable(struct hix5hd2_priv *priv) { - writel_relaxed(~(BITS_RX_EN | BITS_TX_EN), priv->base + PORT_EN); + writel_relaxed(~(u32)(BITS_RX_EN | BITS_TX_EN), priv->base + PORT_EN); writel_relaxed(0, priv->base + DESC_WR_RD_ENA); } diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index f52e99acf463..b3645297477e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -436,60 +436,10 @@ void hnae_ae_unregister(struct hnae_ae_dev *hdev) } EXPORT_SYMBOL(hnae_ae_unregister); -static ssize_t handles_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - ssize_t s = 0; - struct hnae_ae_dev *hdev = cls_to_ae_dev(dev); - struct hnae_handle *h; - int i = 0, j; - - list_for_each_entry_rcu(h, &hdev->handle_list, node) { - s += sprintf(buf + s, "handle %d (eport_id=%u from %s):\n", - i++, h->eport_id, h->dev->name); - for (j = 0; j < h->q_num; j++) { - s += sprintf(buf + s, "\tqueue[%d] on %p\n", - j, h->qs[i]->io_base); -#define HANDEL_TX_MSG "\t\ttx_ring on %p:%u,%u,%u,%u,%u,%llu,%llu\n" - s += sprintf(buf + s, - HANDEL_TX_MSG, - h->qs[i]->tx_ring.io_base, - h->qs[i]->tx_ring.buf_size, - h->qs[i]->tx_ring.desc_num, - h->qs[i]->tx_ring.max_desc_num_per_pkt, - h->qs[i]->tx_ring.max_raw_data_sz_per_desc, - h->qs[i]->tx_ring.max_pkt_size, - h->qs[i]->tx_ring.stats.sw_err_cnt, - h->qs[i]->tx_ring.stats.io_err_cnt); - s += sprintf(buf + s, - "\t\trx_ring on %p:%u,%u,%llu,%llu,%llu\n", - h->qs[i]->rx_ring.io_base, - h->qs[i]->rx_ring.buf_size, - h->qs[i]->rx_ring.desc_num, - h->qs[i]->rx_ring.stats.sw_err_cnt, - h->qs[i]->rx_ring.stats.io_err_cnt, - h->qs[i]->rx_ring.stats.seg_pkt_cnt); - } - } - - return s; -} - -static DEVICE_ATTR_RO(handles); -static struct attribute *hnae_class_attrs[] = { - &dev_attr_handles.attr, - NULL, -}; -ATTRIBUTE_GROUPS(hnae_class); - static int __init hnae_init(void) { hnae_class = class_create(THIS_MODULE, "hnae"); - if (IS_ERR(hnae_class)) - return PTR_ERR(hnae_class); - - hnae_class->dev_groups = hnae_class_groups; - return 0; + return PTR_ERR_OR_ZERO(hnae_class); } static void __exit hnae_exit(void) diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index d4a1eb1b8e54..cec95ac8687d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -430,6 +430,7 @@ struct hnae_ae_ops { void (*set_coalesce_usecs)(struct hnae_handle *handle, u32 timeout); int (*set_coalesce_frames)(struct hnae_handle *handle, u32 coalesce_frames); + 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); int (*set_mc_addr)(struct hnae_handle *handle, void *addr); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index a2c72f84e397..1a16c0307b47 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -392,6 +392,11 @@ static int hns_ae_set_autoneg(struct hnae_handle *handle, u8 enable) return hns_mac_set_autoneg(hns_get_mac_cb(handle), enable); } +static void hns_ae_set_promisc_mode(struct hnae_handle *handle, u32 en) +{ + hns_dsaf_set_promisc_mode(hns_ae_get_dsaf_dev(handle->dev), en); +} + static int hns_ae_get_autoneg(struct hnae_handle *handle) { u32 auto_neg; @@ -748,6 +753,7 @@ 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, + .set_promisc_mode = hns_ae_set_promisc_mode, .set_mac_addr = hns_ae_set_mac_address, .set_mc_addr = hns_ae_set_multicast_one, .set_mtu = hns_ae_set_mtu, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 95bf42aae24c..026b38676cba 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -179,7 +179,7 @@ static int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb, return -EINVAL; } } else if (mac_cb->dsaf_dev->dsaf_mode < DSAF_MODE_MAX) { - if (mac_cb->mac_id <= DSAF_MAX_PORT_NUM_PER_CHIP) { + if (mac_cb->mac_id >= DSAF_MAX_PORT_NUM_PER_CHIP) { dev_err(mac_cb->dev, "input invalid,%s mac%d vmid%d!\n", mac_cb->dsaf_dev->ae_dev.name, @@ -744,9 +744,11 @@ int hns_mac_get_cfg(struct dsaf_device *dsaf_dev, int mac_idx) mac_cb->serdes_vaddr = dsaf_dev->sds_base; if (dsaf_dev->cpld_base && - mac_idx < DSAF_SERVICE_PORT_NUM_PER_DSAF) + mac_idx < DSAF_SERVICE_PORT_NUM_PER_DSAF) { mac_cb->cpld_vaddr = dsaf_dev->cpld_base + mac_cb->mac_id * CPLD_ADDR_PORT_OFFSET; + cpld_led_reset(mac_cb); + } mac_cb->sfp_prsnt = 0; mac_cb->txpkt_for_led = 0; mac_cb->rxpkt_for_led = 0; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 26ae6c64d74c..2a98eba660c0 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -17,6 +17,8 @@ #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/device.h> +#include <linux/vmalloc.h> + #include "hns_dsaf_main.h" #include "hns_dsaf_rcb.h" #include "hns_dsaf_ppe.h" @@ -217,6 +219,25 @@ hns_dsaf_ppe_qid_cfg(struct dsaf_device *dsaf_dev, u32 qid_cfg) } } +static void hns_dsaf_mix_def_qid_cfg(struct dsaf_device *dsaf_dev) +{ + u16 max_q_per_vf, max_vfn; + u32 q_id, q_num_per_port; + u32 i; + + hns_rcb_get_queue_mode(dsaf_dev->dsaf_mode, + HNS_DSAF_COMM_SERVICE_NW_IDX, + &max_vfn, &max_q_per_vf); + q_num_per_port = max_vfn * max_q_per_vf; + + for (i = 0, q_id = 0; i < DSAF_SERVICE_NW_NUM; i++) { + dsaf_set_dev_field(dsaf_dev, + DSAF_MIX_DEF_QID_0_REG + 0x0004 * i, + 0xff, 0, q_id); + q_id += q_num_per_port; + } +} + /** * hns_dsaf_sw_port_type_cfg - cfg sw type * @dsaf_id: dsa fabric id @@ -592,6 +613,11 @@ static void hns_dsaf_tbl_tcam_data_ucast_pul( dsaf_write_dev(dsaf_dev, DSAF_TBL_PUL_0_REG, o_tbl_pul); } +void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en) +{ + dsaf_set_dev_bit(dsaf_dev, DSAF_CFG_0_REG, DSAF_CFG_MIX_MODE_S, !!en); +} + /** * hns_dsaf_tbl_stat_en - tbl * @dsaf_id: dsa fabric id @@ -920,6 +946,9 @@ static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev) /* set 22 queue per tx ppe engine, only used in switch mode */ hns_dsaf_ppe_qid_cfg(dsaf_dev, DSAF_DEFAUTL_QUEUE_NUM_PER_PPE); + /* set promisc def queue id */ + hns_dsaf_mix_def_qid_cfg(dsaf_dev); + /* in non switch mode, set all port to access mode */ hns_dsaf_sw_port_type_cfg(dsaf_dev, DSAF_SW_PORT_TYPE_NON_VLAN); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 315b07ecd291..b2b93484995c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -423,5 +423,6 @@ void hns_dsaf_get_strings(int stringset, u8 *data, int port); void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data); int hns_dsaf_get_regs_count(void); +void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en); #endif /* __HNS_DSAF_MAIN_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index 05ea244d999c..4db32c62f062 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -575,8 +575,8 @@ int hns_rcb_set_coalesced_frames(struct dsaf_device *dsaf_dev, *@max_vfn : max vfn number *@max_q_per_vf:max ring number per vm */ -static void hns_rcb_get_queue_mode(enum dsaf_mode dsaf_mode, int comm_index, - u16 *max_vfn, u16 *max_q_per_vf) +void hns_rcb_get_queue_mode(enum dsaf_mode dsaf_mode, int comm_index, + u16 *max_vfn, u16 *max_q_per_vf) { if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) { switch (dsaf_mode) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h index c7db6130a3cf..3a2afe2dd8bb 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h @@ -107,6 +107,8 @@ int hns_rcb_common_init_hw(struct rcb_common_cb *rcb_common); void hns_rcb_start(struct hnae_queue *q, u32 val); void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common); void hns_rcb_common_init_commit_hw(struct rcb_common_cb *rcb_common); +void hns_rcb_get_queue_mode(enum dsaf_mode dsaf_mode, int comm_index, + u16 *max_vfn, u16 *max_q_per_vf); void hns_rcb_ring_enable_hw(struct hnae_queue *q, u32 val); void hns_rcb_int_clr_hw(struct hnae_queue *q, u32 flag); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c index dab5ecf382a0..802d55457f19 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c @@ -51,9 +51,9 @@ static const struct mac_stats_string g_xgmac_stats_string[] = { {"xgmac_rx_bad_pkt_from_dsaf", MAC_STATS_FIELD_OFF(rx_bad_from_sw)}, {"xgmac_tx_bad_pkt_64tomax", MAC_STATS_FIELD_OFF(tx_bad_pkts)}, - {"xgmac_rx_not_well_pkt", MAC_STATS_FIELD_OFF(rx_fragment_err)}, - {"xgmac_rx_good_well_pkt", MAC_STATS_FIELD_OFF(rx_undersize)}, - {"xgmac_rx_total_pkt", MAC_STATS_FIELD_OFF(rx_under_min)}, + {"xgmac_rx_bad_pkts_minto64", MAC_STATS_FIELD_OFF(rx_fragment_err)}, + {"xgmac_rx_good_pkts_minto64", MAC_STATS_FIELD_OFF(rx_undersize)}, + {"xgmac_rx_total_pkts_minto64", MAC_STATS_FIELD_OFF(rx_under_min)}, {"xgmac_rx_pkt_64", MAC_STATS_FIELD_OFF(rx_64bytes)}, {"xgmac_rx_pkt_65to127", MAC_STATS_FIELD_OFF(rx_65to127)}, {"xgmac_rx_pkt_128to255", MAC_STATS_FIELD_OFF(rx_128to255)}, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index ce7f2e0e3fd1..302d3ae8e9e5 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1161,6 +1161,21 @@ void hns_set_multicast_list(struct net_device *ndev) } } +void hns_nic_set_rx_mode(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + + if (h->dev->ops->set_promisc_mode) { + if (ndev->flags & IFF_PROMISC) + h->dev->ops->set_promisc_mode(h, 1); + else + h->dev->ops->set_promisc_mode(h, 0); + } + + hns_set_multicast_list(ndev); +} + struct rtnl_link_stats64 *hns_nic_get_stats64(struct net_device *ndev, struct rtnl_link_stats64 *stats) { @@ -1220,7 +1235,7 @@ static const struct net_device_ops hns_nic_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = hns_nic_poll_controller, #endif - .ndo_set_rx_mode = hns_set_multicast_list, + .ndo_set_rx_mode = hns_nic_set_rx_mode, }; static void hns_nic_update_link_status(struct net_device *netdev) @@ -1300,16 +1315,15 @@ static void hns_nic_reset_subtask(struct hns_nic_priv *priv) return; hns_nic_dump(priv); - netdev_err(priv->netdev, "Reset %s port\n", - (type == HNAE_PORT_DEBUG ? "debug" : "business")); + netdev_info(priv->netdev, "Reset %s port\n", + (type == HNAE_PORT_DEBUG ? "debug" : "business")); rtnl_lock(); - if (type == HNAE_PORT_DEBUG) { + /* put off any impending NetWatchDogTimeout */ + priv->netdev->trans_start = jiffies; + + if (type == HNAE_PORT_DEBUG) hns_nic_net_reinit(priv->netdev); - } else { - hns_nic_net_down(priv->netdev); - hns_nic_net_reset(priv->netdev); - } rtnl_unlock(); } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 2550208cb22e..a0332129970b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -194,9 +194,7 @@ static int hns_nic_set_settings(struct net_device *net_dev, { struct hns_nic_priv *priv = netdev_priv(net_dev); struct hnae_handle *h; - int link_stat; u32 speed; - u8 duplex, autoneg; if (!netif_running(net_dev)) return -ESRCH; @@ -206,48 +204,35 @@ static int hns_nic_set_settings(struct net_device *net_dev, return -ENODEV; h = priv->ae_handle; - link_stat = hns_nic_get_link(net_dev); - duplex = cmd->duplex; speed = ethtool_cmd_speed(cmd); - autoneg = cmd->autoneg; - - if (!link_stat) { - if (duplex != (u8)DUPLEX_UNKNOWN || speed != (u32)SPEED_UNKNOWN) - return -EINVAL; - - if (h->phy_if == PHY_INTERFACE_MODE_SGMII && h->phy_node) { - priv->phy->autoneg = autoneg; - return phy_start_aneg(priv->phy); - } - } if (h->phy_if == PHY_INTERFACE_MODE_XGMII) { - if (autoneg != AUTONEG_DISABLE) - return -EINVAL; - - if (speed != SPEED_10000 || duplex != DUPLEX_FULL) + if (cmd->autoneg == AUTONEG_ENABLE || speed != SPEED_10000 || + cmd->duplex != DUPLEX_FULL) return -EINVAL; } else if (h->phy_if == PHY_INTERFACE_MODE_SGMII) { - if (!h->phy_node && autoneg != AUTONEG_DISABLE) + if (!priv->phy && cmd->autoneg == AUTONEG_ENABLE) return -EINVAL; - if (speed == SPEED_1000 && duplex == DUPLEX_HALF) + if (speed == SPEED_1000 && cmd->duplex == DUPLEX_HALF) return -EINVAL; + if (priv->phy) + return phy_ethtool_sset(priv->phy, cmd); - if (speed != SPEED_10 && speed != SPEED_100 && - speed != SPEED_1000) + if ((speed != SPEED_10 && speed != SPEED_100 && + speed != SPEED_1000) || (cmd->duplex != DUPLEX_HALF && + cmd->duplex != DUPLEX_FULL)) return -EINVAL; } else { netdev_err(net_dev, "Not supported!"); return -ENOTSUPP; } - if (priv->phy) { - return phy_ethtool_sset(priv->phy, cmd); - } else if (h->dev->ops->adjust_link && link_stat) { - h->dev->ops->adjust_link(h, speed, duplex); + if (h->dev->ops->adjust_link) { + h->dev->ops->adjust_link(h, (int)speed, cmd->duplex); return 0; } + netdev_err(net_dev, "Not supported!"); return -ENOTSUPP; } @@ -682,7 +667,6 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev, drvinfo->bus_info[ETHTOOL_BUSINFO_LEN - 1] = '\0'; strncpy(drvinfo->fw_version, "N/A", ETHTOOL_FWVERS_LEN); - drvinfo->eedump_len = 0; } /** diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index e4ec52ae61ff..37491c85bc42 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -11,6 +11,7 @@ #include <linux/etherdevice.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/mfd/syscon.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/netdevice.h> @@ -20,6 +21,7 @@ #include <linux/of_platform.h> #include <linux/phy.h> #include <linux/platform_device.h> +#include <linux/regmap.h> #include <linux/spinlock_types.h> #define MDIO_DRV_NAME "Hi-HNS_MDIO" @@ -36,7 +38,7 @@ struct hns_mdio_device { void *vbase; /* mdio reg base address */ - void *sys_vbase; + struct regmap *subctrl_vbase; }; /* mdio reg */ @@ -155,10 +157,10 @@ static int mdio_sc_cfg_reg_write(struct hns_mdio_device *mdio_dev, u32 time_cnt; u32 reg_value; - mdio_write_reg((void *)mdio_dev->sys_vbase, cfg_reg, set_val); + regmap_write(mdio_dev->subctrl_vbase, cfg_reg, set_val); for (time_cnt = MDIO_TIMEOUT; time_cnt; time_cnt--) { - reg_value = mdio_read_reg((void *)mdio_dev->sys_vbase, st_reg); + regmap_read(mdio_dev->subctrl_vbase, st_reg, ®_value); reg_value &= st_msk; if ((!!check_st) == (!!reg_value)) break; @@ -352,7 +354,7 @@ static int hns_mdio_reset(struct mii_bus *bus) struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv; int ret; - if (!mdio_dev->sys_vbase) { + if (!mdio_dev->subctrl_vbase) { dev_err(&bus->dev, "mdio sys ctl reg has not maped\n"); return -ENODEV; } @@ -455,13 +457,12 @@ static int hns_mdio_probe(struct platform_device *pdev) return ret; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - mdio_dev->sys_vbase = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(mdio_dev->sys_vbase)) { - ret = PTR_ERR(mdio_dev->sys_vbase); - return ret; + mdio_dev->subctrl_vbase = + syscon_node_to_regmap(of_parse_phandle(np, "subctrl_vbase", 0)); + if (IS_ERR(mdio_dev->subctrl_vbase)) { + dev_warn(&pdev->dev, "no syscon hisilicon,peri-c-subctrl\n"); + mdio_dev->subctrl_vbase = NULL; } - new_bus->irq = devm_kcalloc(&pdev->dev, PHY_MAX_ADDR, sizeof(int), GFP_KERNEL); if (!new_bus->irq) diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index b60a34d982a9..5d7db6c01c46 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2204,7 +2204,6 @@ static void emac_ethtool_get_drvinfo(struct net_device *ndev, strlcpy(info->version, DRV_VERSION, sizeof(info->version)); snprintf(info->bus_info, sizeof(info->bus_info), "PPC 4xx EMAC-%d %s", dev->cell_index, dev->ofdev->dev.of_node->full_name); - info->regdump_len = emac_ethtool_get_regs_len(ndev); } static const struct ethtool_ops emac_ethtool_ops = { diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index 4270ad2d4ddf..83e557c7f279 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -559,8 +559,6 @@ static void e1000_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->regdump_len = e1000_get_regs_len(netdev); - drvinfo->eedump_len = e1000_get_eeprom_len(netdev); } static void e1000_get_ringparam(struct net_device *netdev, diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 74dc15055971..fd7be860c201 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -3820,7 +3820,7 @@ static int e1000_clean(struct napi_struct *napi, int budget) if (work_done < budget) { if (likely(adapter->itr_setting & 3)) e1000_set_itr(adapter); - napi_complete(napi); + napi_complete_done(napi, work_done); if (!test_bit(__E1000_DOWN, &adapter->flags)) e1000_irq_enable(adapter); } diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index ad6daa656d3e..6cab1f30d41e 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -648,8 +648,6 @@ static void e1000_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->regdump_len = e1000_get_regs_len(netdev); - drvinfo->eedump_len = e1000_get_eeprom_len(netdev); } static void e1000_get_ringparam(struct net_device *netdev, diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 2e2ddec04a50..0a854a47d31a 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -2693,7 +2693,7 @@ static int e1000e_poll(struct napi_struct *napi, int weight) if (work_done < weight) { if (adapter->itr_setting & 3) e1000_set_itr(adapter); - napi_complete(napi); + napi_complete_done(napi, work_done); if (!test_bit(__E1000_DOWN, &adapter->state)) { if (adapter->msix_entries) ew32(IMS, adapter->rx_ring->ims_val); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c index 08ecf43dffc7..5304bc1fbecd 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c @@ -176,7 +176,7 @@ void fm10k_dbg_q_vector_init(struct fm10k_q_vector *q_vector) return; /* Generate a folder for each q_vector */ - sprintf(name, "q_vector.%03d", q_vector->v_idx); + snprintf(name, sizeof(name), "q_vector.%03d", q_vector->v_idx); q_vector->dbg_q_vector = debugfs_create_dir(name, interface->dbg_intfc); if (!q_vector->dbg_q_vector) @@ -186,7 +186,7 @@ void fm10k_dbg_q_vector_init(struct fm10k_q_vector *q_vector) for (i = 0; i < q_vector->tx.count; i++) { struct fm10k_ring *ring = &q_vector->tx.ring[i]; - sprintf(name, "tx_ring.%03d", ring->queue_index); + snprintf(name, sizeof(name), "tx_ring.%03d", ring->queue_index); debugfs_create_file(name, 0600, q_vector->dbg_q_vector, ring, @@ -197,7 +197,7 @@ void fm10k_dbg_q_vector_init(struct fm10k_q_vector *q_vector) for (i = 0; i < q_vector->rx.count; i++) { struct fm10k_ring *ring = &q_vector->rx.ring[i]; - sprintf(name, "rx_ring.%03d", ring->queue_index); + snprintf(name, sizeof(name), "rx_ring.%03d", ring->queue_index); debugfs_create_file(name, 0600, q_vector->dbg_q_vector, ring, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 4ef2fbd22911..2ce0eba5e040 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -206,13 +206,13 @@ static void fm10k_get_stat_strings(struct net_device *dev, u8 *data) } for (i = 0; i < interface->hw.mac.max_queues; i++) { - sprintf(p, "tx_queue_%u_packets", i); + snprintf(p, ETH_GSTRING_LEN, "tx_queue_%u_packets", i); p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_bytes", i); + snprintf(p, ETH_GSTRING_LEN, "tx_queue_%u_bytes", i); p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_packets", i); + snprintf(p, ETH_GSTRING_LEN, "rx_queue_%u_packets", i); p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_bytes", i); + snprintf(p, ETH_GSTRING_LEN, "rx_queue_%u_bytes", i); p += ETH_GSTRING_LEN; } } @@ -515,10 +515,6 @@ static void fm10k_get_drvinfo(struct net_device *dev, sizeof(info->version) - 1); strncpy(info->bus_info, pci_name(interface->pdev), sizeof(info->bus_info) - 1); - - info->n_stats = fm10k_get_sset_count(dev, ETH_SS_STATS); - - info->regdump_len = fm10k_get_regs_len(dev); } static void fm10k_get_pauseparam(struct net_device *dev, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 2f47bfe6cc90..e76a44cf330c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -593,9 +593,9 @@ static void fm10k_receive_skb(struct fm10k_q_vector *q_vector, napi_gro_receive(&q_vector->napi, skb); } -static bool fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector, - struct fm10k_ring *rx_ring, - int budget) +static int fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector, + struct fm10k_ring *rx_ring, + int budget) { struct sk_buff *skb = rx_ring->skb; unsigned int total_bytes = 0, total_packets = 0; @@ -662,7 +662,7 @@ static bool fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector, q_vector->rx.total_packets += total_packets; q_vector->rx.total_bytes += total_bytes; - return total_packets < budget; + return total_packets; } #define VXLAN_HLEN (sizeof(struct udphdr) + 8) @@ -1422,7 +1422,7 @@ static int fm10k_poll(struct napi_struct *napi, int budget) struct fm10k_q_vector *q_vector = container_of(napi, struct fm10k_q_vector, napi); struct fm10k_ring *ring; - int per_ring_budget; + int per_ring_budget, work_done = 0; bool clean_complete = true; fm10k_for_each_ring(ring, q_vector->tx) @@ -1436,16 +1436,19 @@ static int fm10k_poll(struct napi_struct *napi, int budget) else per_ring_budget = budget; - fm10k_for_each_ring(ring, q_vector->rx) - clean_complete &= fm10k_clean_rx_irq(q_vector, ring, - per_ring_budget); + fm10k_for_each_ring(ring, q_vector->rx) { + int work = fm10k_clean_rx_irq(q_vector, ring, per_ring_budget); + + work_done += work; + clean_complete &= !!(work < per_ring_budget); + } /* If all work not completed, return budget and keep polling */ if (!clean_complete) return budget; /* all work done, exit the polling mode */ - napi_complete(napi); + napi_complete_done(napi, work_done); /* re-enable the q_vector */ fm10k_qv_enable(q_vector); @@ -1905,7 +1908,7 @@ static void fm10k_init_reta(struct fm10k_intfc *interface) u32 reta, base; /* If the netdev is initialized we have to maintain table if possible */ - if (interface->netdev->reg_state) { + if (interface->netdev->reg_state != NETREG_UNINITIALIZED) { for (i = FM10K_RETA_SIZE; i--;) { reta = interface->reta[i]; if ((((reta << 24) >> 24) < rss_i) && diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index f26dcb23ebf9..7c2b2e891f62 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -93,7 +93,7 @@ #endif /* I40E_FCOE */ #define I40E_MAX_AQ_BUF_SIZE 4096 #define I40E_AQ_LEN 256 -#define I40E_AQ_WORK_LIMIT 32 +#define I40E_AQ_WORK_LIMIT 66 /* max number of VFs + a little */ #define I40E_MAX_USER_PRIORITY 8 #define I40E_DEFAULT_MSG_ENABLE 4 #define I40E_QUEUE_WAIT_RETRY_LIMIT 10 @@ -102,11 +102,15 @@ /* Ethtool Private Flags */ #define I40E_PRIV_FLAGS_NPAR_FLAG BIT(0) #define I40E_PRIV_FLAGS_LINKPOLL_FLAG BIT(1) +#define I40E_PRIV_FLAGS_FD_ATR BIT(2) +#define I40E_PRIV_FLAGS_VEB_STATS BIT(3) #define I40E_NVM_VERSION_LO_SHIFT 0 #define I40E_NVM_VERSION_LO_MASK (0xff << I40E_NVM_VERSION_LO_SHIFT) #define I40E_NVM_VERSION_HI_SHIFT 12 #define I40E_NVM_VERSION_HI_MASK (0xf << I40E_NVM_VERSION_HI_SHIFT) +#define I40E_OEM_VER_BUILD_MASK 0xff00 +#define I40E_OEM_VER_PATCH_MASK 0xff /* The values in here are decimal coded as hex as is the case in the NVM map*/ #define I40E_CURRENT_NVM_VERSION_HI 0x2 @@ -304,7 +308,6 @@ struct i40e_pf { #ifdef I40E_FCOE #define I40E_FLAG_FCOE_ENABLED BIT_ULL(11) #endif /* I40E_FCOE */ -#define I40E_FLAG_IN_NETPOLL BIT_ULL(12) #define I40E_FLAG_16BYTE_RX_DESC_ENABLED BIT_ULL(13) #define I40E_FLAG_CLEAN_ADMINQ BIT_ULL(14) #define I40E_FLAG_FILTER_SYNC BIT_ULL(15) @@ -330,6 +333,7 @@ struct i40e_pf { #define I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT_ULL(38) #define I40E_FLAG_LINK_POLLING_ENABLED BIT_ULL(39) #define I40E_FLAG_VEB_MODE_ENABLED BIT_ULL(40) +#define I40E_FLAG_NO_PCI_LINK_CHECK BIT_ULL(42) /* tracks features that get auto disabled by errors */ u64 auto_disable_flags; @@ -464,6 +468,8 @@ struct i40e_vsi { #define I40E_VSI_FLAG_VEB_OWNER BIT(1) unsigned long flags; + /* Per VSI lock to protect elements/list (MAC filter) */ + spinlock_t mac_filter_list_lock; struct list_head mac_filter_list; /* VSI stats */ @@ -494,6 +500,7 @@ struct i40e_vsi { */ u16 rx_itr_setting; u16 tx_itr_setting; + u16 int_rate_limit; /* value in usecs */ u16 rss_table_size; u16 rss_size; @@ -570,6 +577,8 @@ struct i40e_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; +#define ITR_COUNTDOWN_START 100 + u8 itr_countdown; /* when 0 should adjust ITR */ } ____cacheline_internodealigned_in_smp; /* lan device */ @@ -579,22 +588,22 @@ struct i40e_device { }; /** - * i40e_fw_version_str - format the FW and NVM version strings + * i40e_nvm_version_str - format the NVM version strings * @hw: ptr to the hardware info **/ -static inline char *i40e_fw_version_str(struct i40e_hw *hw) +static inline char *i40e_nvm_version_str(struct i40e_hw *hw) { static char buf[32]; snprintf(buf, sizeof(buf), - "f%d.%d.%05d a%d.%d n%x.%02x e%x", - hw->aq.fw_maj_ver, hw->aq.fw_min_ver, hw->aq.fw_build, - hw->aq.api_maj_ver, hw->aq.api_min_ver, + "%x.%02x 0x%x %d.%d.%d", (hw->nvm.version & I40E_NVM_VERSION_HI_MASK) >> I40E_NVM_VERSION_HI_SHIFT, (hw->nvm.version & I40E_NVM_VERSION_LO_MASK) >> I40E_NVM_VERSION_LO_SHIFT, - (hw->nvm.eetrack & 0xffffff)); + hw->nvm.eetrack, (hw->nvm.oem_ver >> 24), + (hw->nvm.oem_ver & I40E_OEM_VER_BUILD_MASK) >> 8, + hw->nvm.oem_ver & I40E_OEM_VER_PATCH_MASK); return buf; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index fa2e916b23da..0ff8f01e57ee 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -386,7 +386,6 @@ static i40e_status i40e_init_asq(struct i40e_hw *hw) hw->aq.asq.next_to_use = 0; hw->aq.asq.next_to_clean = 0; - hw->aq.asq.count = hw->aq.num_asq_entries; /* allocate the ring memory */ ret_code = i40e_alloc_adminq_asq_ring(hw); @@ -404,6 +403,7 @@ static i40e_status i40e_init_asq(struct i40e_hw *hw) goto init_adminq_free_rings; /* success! */ + hw->aq.asq.count = hw->aq.num_asq_entries; goto init_adminq_exit; init_adminq_free_rings: @@ -445,7 +445,6 @@ static i40e_status i40e_init_arq(struct i40e_hw *hw) hw->aq.arq.next_to_use = 0; hw->aq.arq.next_to_clean = 0; - hw->aq.arq.count = hw->aq.num_arq_entries; /* allocate the ring memory */ ret_code = i40e_alloc_adminq_arq_ring(hw); @@ -463,6 +462,7 @@ static i40e_status i40e_init_arq(struct i40e_hw *hw) goto init_adminq_free_rings; /* success! */ + hw->aq.arq.count = hw->aq.num_arq_entries; goto init_adminq_exit; init_adminq_free_rings: @@ -553,8 +553,9 @@ shutdown_arq_out: **/ i40e_status i40e_init_adminq(struct i40e_hw *hw) { - i40e_status ret_code; + u16 cfg_ptr, oem_hi, oem_lo; u16 eetrack_lo, eetrack_hi; + i40e_status ret_code; int retry = 0; /* verify input for valid configuration */ @@ -613,6 +614,12 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw) i40e_read_nvm_word(hw, I40E_SR_NVM_EETRACK_LO, &eetrack_lo); i40e_read_nvm_word(hw, I40E_SR_NVM_EETRACK_HI, &eetrack_hi); hw->nvm.eetrack = (eetrack_hi << 16) | eetrack_lo; + i40e_read_nvm_word(hw, I40E_SR_BOOT_CONFIG_PTR, &cfg_ptr); + i40e_read_nvm_word(hw, (cfg_ptr + I40E_NVM_OEM_VER_OFF), + &oem_hi); + i40e_read_nvm_word(hw, (cfg_ptr + (I40E_NVM_OEM_VER_OFF + 1)), + &oem_lo); + hw->nvm.oem_ver = ((u32)oem_hi << 16) | oem_lo; if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) { ret_code = I40E_ERR_FIRMWARE_API_VERSION; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 785b3dbd22ca..6584b6cd73fd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1722,11 +1722,13 @@ struct i40e_aqc_get_link_status { u8 phy_type; /* i40e_aq_phy_type */ u8 link_speed; /* i40e_aq_link_speed */ u8 link_info; -#define I40E_AQ_LINK_UP 0x01 +#define I40E_AQ_LINK_UP 0x01 /* obsolete */ +#define I40E_AQ_LINK_UP_FUNCTION 0x01 #define I40E_AQ_LINK_FAULT 0x02 #define I40E_AQ_LINK_FAULT_TX 0x04 #define I40E_AQ_LINK_FAULT_RX 0x08 #define I40E_AQ_LINK_FAULT_REMOTE 0x10 +#define I40E_AQ_LINK_UP_PORT 0x20 #define I40E_AQ_MEDIA_AVAILABLE 0x40 #define I40E_AQ_SIGNAL_DETECT 0x80 u8 an_info; @@ -2130,6 +2132,13 @@ I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_get_cee_dcb_cfg_resp); struct i40e_aqc_lldp_set_local_mib { #define SET_LOCAL_MIB_AC_TYPE_DCBX_SHIFT 0 #define SET_LOCAL_MIB_AC_TYPE_DCBX_MASK (1 << SET_LOCAL_MIB_AC_TYPE_DCBX_SHIFT) +#define SET_LOCAL_MIB_AC_TYPE_DCBX_MASK (1 << \ + SET_LOCAL_MIB_AC_TYPE_DCBX_SHIFT) +#define SET_LOCAL_MIB_AC_TYPE_LOCAL_MIB 0x0 +#define SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS_SHIFT (1) +#define SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS_MASK (1 << \ + SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS_SHIFT) +#define SET_LOCAL_MIB_AC_TYPE_NON_WILLING_APPS 0x1 u8 type; u8 reserved0; __le16 length; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 2d012d9c22ad..c51f2fb94716 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -87,7 +87,7 @@ static i40e_status i40e_set_mac_type(struct i40e_hw *hw) * @hw: pointer to the HW structure * @aq_err: the AQ error code to convert **/ -char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err) +const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err) { switch (aq_err) { case I40E_AQ_RC_OK: @@ -147,7 +147,7 @@ char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err) * @hw: pointer to the HW structure * @stat_err: the status error code to convert **/ -char *i40e_stat_str(struct i40e_hw *hw, i40e_status stat_err) +const char *i40e_stat_str(struct i40e_hw *hw, i40e_status stat_err) { switch (stat_err) { case 0: @@ -958,6 +958,9 @@ i40e_status i40e_init_shared_code(struct i40e_hw *hw) else hw->pf_id = (u8)(func_rid & 0x7); + if (hw->mac.type == I40E_MAC_X722) + hw->flags |= I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE; + status = i40e_init_nvm(hw); return status; } @@ -1617,6 +1620,9 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw, if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) status = I40E_ERR_UNKNOWN_PHY; + if (report_init) + hw->phy.phy_types = le32_to_cpu(abilities->phy_type); + return status; } @@ -1717,14 +1723,14 @@ enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, *aq_failures |= I40E_SET_FC_AQ_FAIL_SET; } /* Update the link info */ - status = i40e_aq_get_link_info(hw, true, NULL, NULL); + status = i40e_update_link_info(hw); if (status) { /* Wait a little bit (on 40G cards it sometimes takes a really * long time for link to come back from the atomic reset) * and try once more */ msleep(1000); - status = i40e_aq_get_link_info(hw, true, NULL, NULL); + status = i40e_update_link_info(hw); } if (status) *aq_failures |= I40E_SET_FC_AQ_FAIL_UPDATE; @@ -2247,7 +2253,7 @@ i40e_status i40e_get_link_status(struct i40e_hw *hw, bool *link_up) i40e_status status = 0; if (hw->phy.get_link_info) { - status = i40e_aq_get_link_info(hw, true, NULL, NULL); + status = i40e_update_link_info(hw); if (status) i40e_debug(hw, I40E_DEBUG_LINK, "get link failed: status %d\n", @@ -2260,6 +2266,32 @@ i40e_status i40e_get_link_status(struct i40e_hw *hw, bool *link_up) } /** + * i40e_updatelink_status - update status of the HW network link + * @hw: pointer to the hw struct + **/ +i40e_status i40e_update_link_info(struct i40e_hw *hw) +{ + struct i40e_aq_get_phy_abilities_resp abilities; + i40e_status status = 0; + + status = i40e_aq_get_link_info(hw, true, NULL, NULL); + if (status) + return status; + + if (hw->phy.link_info.link_info & I40E_AQ_MEDIA_AVAILABLE) { + status = i40e_aq_get_phy_capabilities(hw, false, false, + &abilities, NULL); + if (status) + return status; + + memcpy(hw->phy.link_info.module_type, &abilities.module_type, + sizeof(hw->phy.link_info.module_type)); + } + + return status; +} + +/** * i40e_aq_add_veb - Insert a VEB between the VSI and the MAC * @hw: pointer to the hw struct * @uplink_seid: the MAC or other gizmo SEID diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c index 6fa07ef1651d..2691277c0055 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c @@ -380,7 +380,7 @@ static void i40e_parse_cee_app_tlv(struct i40e_cee_feat_tlv *tlv, { u16 length, typelength, offset = 0; struct i40e_cee_app_prio *app; - u8 i, up; + u8 i, up, selector; typelength = ntohs(tlv->hdr.typelen); length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >> @@ -393,13 +393,21 @@ static void i40e_parse_cee_app_tlv(struct i40e_cee_feat_tlv *tlv, for (i = 0; i < dcbcfg->numapps; i++) { app = (struct i40e_cee_app_prio *)(tlv->tlvinfo + offset); for (up = 0; up < I40E_MAX_USER_PRIORITY; up++) { - if (app->prio_map & (1 << up)) + if (app->prio_map & BIT(up)) break; } dcbcfg->app[i].priority = up; - /* Get Selector from lower 2 bits */ - dcbcfg->app[i].selector = (app->upper_oui_sel & - I40E_CEE_APP_SELECTOR_MASK); + + /* Get Selector from lower 2 bits, and convert to IEEE */ + selector = (app->upper_oui_sel & I40E_CEE_APP_SELECTOR_MASK); + if (selector == I40E_CEE_APP_SEL_ETHTYPE) + dcbcfg->app[i].selector = I40E_APP_SEL_ETHTYPE; + else if (selector == I40E_CEE_APP_SEL_TCPIP) + dcbcfg->app[i].selector = I40E_APP_SEL_TCPIP; + else + /* Keep selector as it is for unknown types */ + dcbcfg->app[i].selector = selector; + dcbcfg->app[i].protocolid = ntohs(app->protocol); /* Move to next app */ offset += sizeof(*app); diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c index 7c42d1340de6..886e667f2f1c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c @@ -240,10 +240,9 @@ static void i40e_dcbnl_del_app(struct i40e_pf *pf, for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v] && pf->vsi[v]->netdev) { err = i40e_dcbnl_vsi_del_app(pf->vsi[v], app); - if (err) - dev_info(&pf->pdev->dev, "Failed deleting app for VSI seid=%d err=%d sel=%d proto=0x%x prio=%d\n", - pf->vsi[v]->seid, err, app->selector, - app->protocolid, app->priority); + dev_dbg(&pf->pdev->dev, "Deleting app for VSI seid=%d err=%d sel=%d proto=0x%x prio=%d\n", + pf->vsi[v]->seid, err, app->selector, + app->protocolid, app->priority); } } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index c1dd2483e262..d15bd62eb874 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -953,24 +953,6 @@ static void i40e_dbg_dump_veb_all(struct i40e_pf *pf) } } -/** - * i40e_dbg_cmd_fd_ctrl - Enable/disable FD sideband/ATR - * @pf: the PF that would be altered - * @flag: flag that needs enabling or disabling - * @enable: Enable/disable FD SD/ATR - **/ -static void i40e_dbg_cmd_fd_ctrl(struct i40e_pf *pf, u64 flag, bool enable) -{ - if (enable) { - pf->flags |= flag; - } else { - pf->flags &= ~flag; - pf->auto_disable_flags |= flag; - } - dev_info(&pf->pdev->dev, "requesting a PF reset\n"); - i40e_do_reset_safe(pf, BIT(__I40E_PF_RESET_REQUESTED)); -} - #define I40E_MAX_DEBUG_OUT_BUFFER (4096*4) /** * i40e_dbg_command_write - write into command datum @@ -1759,10 +1741,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp, raw_packet = NULL; kfree(asc_packet); asc_packet = NULL; - } else if (strncmp(cmd_buf, "fd-atr off", 10) == 0) { - i40e_dbg_cmd_fd_ctrl(pf, I40E_FLAG_FD_ATR_ENABLED, false); - } else if (strncmp(cmd_buf, "fd-atr on", 9) == 0) { - i40e_dbg_cmd_fd_ctrl(pf, I40E_FLAG_FD_ATR_ENABLED, true); } else if (strncmp(cmd_buf, "fd current cnt", 14) == 0) { dev_info(&pf->pdev->dev, "FD current total filter count for this interface: %d\n", i40e_get_current_fd_count(pf)); @@ -1989,8 +1967,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp, dev_info(&pf->pdev->dev, " send indirect aq_cmd <flags> <opcode> <datalen> <retval> <cookie_h> <cookie_l> <param0> <param1> <param2> <param3> <buffer_len>\n"); dev_info(&pf->pdev->dev, " add fd_filter <dest q_index> <flex_off> <pctype> <dest_vsi> <dest_ctl> <fd_status> <cnt_index> <fd_id> <packet_len> <packet>\n"); dev_info(&pf->pdev->dev, " rem fd_filter <dest q_index> <flex_off> <pctype> <dest_vsi> <dest_ctl> <fd_status> <cnt_index> <fd_id> <packet_len> <packet>\n"); - dev_info(&pf->pdev->dev, " fd-atr off\n"); - dev_info(&pf->pdev->dev, " fd-atr on\n"); dev_info(&pf->pdev->dev, " fd current cnt"); dev_info(&pf->pdev->dev, " lldp start\n"); dev_info(&pf->pdev->dev, " lldp stop\n"); diff --git a/drivers/net/ethernet/intel/i40e/i40e_devids.h b/drivers/net/ethernet/intel/i40e/i40e_devids.h new file mode 100644 index 000000000000..c601ca4a610c --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_devids.h @@ -0,0 +1,55 @@ +/******************************************************************************* + * + * Intel Ethernet Controller XL710 Family Linux Driver + * Copyright(c) 2013 - 2015 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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/>. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * e1000-devel Mailing List <[email protected]> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + ******************************************************************************/ + +#ifndef _I40E_DEVIDS_H_ +#define _I40E_DEVIDS_H_ + +/* Device IDs */ +#define I40E_DEV_ID_SFP_XL710 0x1572 +#define I40E_DEV_ID_QEMU 0x1574 +#define I40E_DEV_ID_KX_A 0x157F +#define I40E_DEV_ID_KX_B 0x1580 +#define I40E_DEV_ID_KX_C 0x1581 +#define I40E_DEV_ID_QSFP_A 0x1583 +#define I40E_DEV_ID_QSFP_B 0x1584 +#define I40E_DEV_ID_QSFP_C 0x1585 +#define I40E_DEV_ID_10G_BASE_T 0x1586 +#define I40E_DEV_ID_20G_KR2 0x1587 +#define I40E_DEV_ID_20G_KR2_A 0x1588 +#define I40E_DEV_ID_10G_BASE_T4 0x1589 +#define I40E_DEV_ID_VF 0x154C +#define I40E_DEV_ID_VF_HV 0x1571 +#define I40E_DEV_ID_SFP_X722 0x37D0 +#define I40E_DEV_ID_1G_BASE_T_X722 0x37D1 +#define I40E_DEV_ID_10G_BASE_T_X722 0x37D2 +#define I40E_DEV_ID_X722_VF 0x37CD +#define I40E_DEV_ID_X722_VF_HV 0x37D9 + +#define i40e_is_40G_device(d) ((d) == I40E_DEV_ID_QSFP_A || \ + (d) == I40E_DEV_ID_QSFP_B || \ + (d) == I40E_DEV_ID_QSFP_C) + +#endif /* _I40E_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 148f61461076..8fd26fdd7705 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -90,9 +90,6 @@ static const struct i40e_stats i40e_gstrings_misc_stats[] = { I40E_VSI_STAT("tx_linearize", tx_linearize), }; -static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, - struct ethtool_rxnfc *cmd); - /* These PF_STATs might look like duplicates of some NETDEV_STATs, * but they are separate. This device supports Virtualization, and * as such might have several netdevs supporting VMDq and FCoE going @@ -231,6 +228,8 @@ static const char i40e_gstrings_test[][ETH_GSTRING_LEN] = { static const char i40e_priv_flags_strings[][ETH_GSTRING_LEN] = { "NPAR", "LinkPolling", + "flow-director-atr", + "veb-stats", }; #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_priv_flags_strings) @@ -254,7 +253,8 @@ static void i40e_partition_setting_complaint(struct i40e_pf *pf) **/ static void i40e_get_settings_link_up(struct i40e_hw *hw, struct ethtool_cmd *ecmd, - struct net_device *netdev) + struct net_device *netdev, + struct i40e_pf *pf) { struct i40e_link_status *hw_link_info = &hw->phy.link_info; u32 link_speed = hw_link_info->link_speed; @@ -273,65 +273,49 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, case I40E_PHY_TYPE_40GBASE_AOC: ecmd->supported = SUPPORTED_40000baseCR4_Full; break; - case I40E_PHY_TYPE_40GBASE_KR4: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_40000baseKR4_Full; - ecmd->advertising = ADVERTISED_Autoneg | - ADVERTISED_40000baseKR4_Full; - break; case I40E_PHY_TYPE_40GBASE_SR4: ecmd->supported = SUPPORTED_40000baseSR4_Full; break; case I40E_PHY_TYPE_40GBASE_LR4: ecmd->supported = SUPPORTED_40000baseLR4_Full; break; - case I40E_PHY_TYPE_20GBASE_KR2: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_20000baseKR2_Full; - ecmd->advertising = ADVERTISED_Autoneg | - ADVERTISED_20000baseKR2_Full; - break; - case I40E_PHY_TYPE_10GBASE_KX4: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_10000baseKX4_Full; - ecmd->advertising = ADVERTISED_Autoneg | - ADVERTISED_10000baseKX4_Full; - break; - case I40E_PHY_TYPE_10GBASE_KR: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_10000baseKR_Full; - ecmd->advertising = ADVERTISED_Autoneg | - ADVERTISED_10000baseKR_Full; - break; case I40E_PHY_TYPE_10GBASE_SR: case I40E_PHY_TYPE_10GBASE_LR: case I40E_PHY_TYPE_1000BASE_SX: case I40E_PHY_TYPE_1000BASE_LX: - ecmd->supported = SUPPORTED_10000baseT_Full | - SUPPORTED_1000baseT_Full; + ecmd->supported = SUPPORTED_10000baseT_Full; + if (hw_link_info->module_type[2] & + I40E_MODULE_TYPE_1000BASE_SX || + hw_link_info->module_type[2] & + I40E_MODULE_TYPE_1000BASE_LX) { + ecmd->supported |= SUPPORTED_1000baseT_Full; + if (hw_link_info->requested_speeds & + I40E_LINK_SPEED_1GB) + ecmd->advertising |= ADVERTISED_1000baseT_Full; + } if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) ecmd->advertising |= ADVERTISED_10000baseT_Full; - if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - ecmd->advertising |= ADVERTISED_1000baseT_Full; - break; - case I40E_PHY_TYPE_1000BASE_KX: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_1000baseKX_Full; - ecmd->advertising = ADVERTISED_Autoneg | - ADVERTISED_1000baseKX_Full; break; case I40E_PHY_TYPE_10GBASE_T: case I40E_PHY_TYPE_1000BASE_T: - case I40E_PHY_TYPE_100BASE_TX: ecmd->supported = SUPPORTED_Autoneg | SUPPORTED_10000baseT_Full | - SUPPORTED_1000baseT_Full | - SUPPORTED_100baseT_Full; + SUPPORTED_1000baseT_Full; ecmd->advertising = ADVERTISED_Autoneg; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) ecmd->advertising |= ADVERTISED_10000baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) ecmd->advertising |= ADVERTISED_1000baseT_Full; + break; + case I40E_PHY_TYPE_1000BASE_T_OPTICAL: + ecmd->supported = SUPPORTED_Autoneg | + SUPPORTED_1000baseT_Full; + ecmd->advertising = ADVERTISED_Autoneg | + ADVERTISED_1000baseT_Full; + break; + case I40E_PHY_TYPE_100BASE_TX: + ecmd->supported = SUPPORTED_Autoneg | + SUPPORTED_100baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) ecmd->advertising |= ADVERTISED_100baseT_Full; break; @@ -351,12 +335,24 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, break; case I40E_PHY_TYPE_SGMII: ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full | - SUPPORTED_100baseT_Full; + SUPPORTED_1000baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) ecmd->advertising |= ADVERTISED_1000baseT_Full; - if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) - ecmd->advertising |= ADVERTISED_100baseT_Full; + if (pf->hw.mac.type == I40E_MAC_X722) { + ecmd->supported |= SUPPORTED_100baseT_Full; + if (hw_link_info->requested_speeds & + I40E_LINK_SPEED_100MB) + ecmd->advertising |= ADVERTISED_100baseT_Full; + } + break; + /* Backplane is set based on supported phy types in get_settings + * so don't set anything here but don't warn either + */ + case I40E_PHY_TYPE_40GBASE_KR4: + case I40E_PHY_TYPE_20GBASE_KR2: + case I40E_PHY_TYPE_10GBASE_KR: + case I40E_PHY_TYPE_10GBASE_KX4: + case I40E_PHY_TYPE_1000BASE_KX: break; default: /* if we got here and link is up something bad is afoot */ @@ -395,66 +391,73 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, * Reports link settings that can be determined when link is down **/ static void i40e_get_settings_link_down(struct i40e_hw *hw, - struct ethtool_cmd *ecmd) + struct ethtool_cmd *ecmd, + struct i40e_pf *pf) { - struct i40e_link_status *hw_link_info = &hw->phy.link_info; + enum i40e_aq_capabilities_phy_type phy_types = hw->phy.phy_types; /* link is down and the driver needs to fall back on - * device ID to determine what kinds of info to display, - * it's mostly a guess that may change when link is up + * supported phy types to figure out what info to display */ - switch (hw->device_id) { - case I40E_DEV_ID_QSFP_A: - case I40E_DEV_ID_QSFP_B: - case I40E_DEV_ID_QSFP_C: - /* pluggable QSFP */ - ecmd->supported = SUPPORTED_40000baseSR4_Full | - SUPPORTED_40000baseCR4_Full | - SUPPORTED_40000baseLR4_Full; - ecmd->advertising = ADVERTISED_40000baseSR4_Full | - ADVERTISED_40000baseCR4_Full | - ADVERTISED_40000baseLR4_Full; - break; - case I40E_DEV_ID_KX_B: - /* backplane 40G */ - ecmd->supported = SUPPORTED_40000baseKR4_Full; - ecmd->advertising = ADVERTISED_40000baseKR4_Full; - break; - case I40E_DEV_ID_KX_C: - /* backplane 10G */ - ecmd->supported = SUPPORTED_10000baseKR_Full; - ecmd->advertising = ADVERTISED_10000baseKR_Full; - break; - case I40E_DEV_ID_10G_BASE_T: - case I40E_DEV_ID_10G_BASE_T4: - ecmd->supported = SUPPORTED_10000baseT_Full | - SUPPORTED_1000baseT_Full | - SUPPORTED_100baseT_Full; - /* Figure out what has been requested */ - if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - ecmd->advertising |= ADVERTISED_10000baseT_Full; - if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - ecmd->advertising |= ADVERTISED_1000baseT_Full; - if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) + ecmd->supported = 0x0; + ecmd->advertising = 0x0; + if (phy_types & I40E_CAP_PHY_TYPE_SGMII) { + ecmd->supported |= SUPPORTED_Autoneg | + SUPPORTED_1000baseT_Full; + ecmd->advertising |= ADVERTISED_Autoneg | + ADVERTISED_1000baseT_Full; + if (pf->hw.mac.type == I40E_MAC_X722) { + ecmd->supported |= SUPPORTED_100baseT_Full; ecmd->advertising |= ADVERTISED_100baseT_Full; - break; - case I40E_DEV_ID_20G_KR2: - case I40E_DEV_ID_20G_KR2_A: - /* backplane 20G */ - ecmd->supported = SUPPORTED_20000baseKR2_Full; - ecmd->advertising = ADVERTISED_20000baseKR2_Full; - break; - default: - /* all the rest are 10G/1G */ - ecmd->supported = SUPPORTED_10000baseT_Full | - SUPPORTED_1000baseT_Full; - /* Figure out what has been requested */ - if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - ecmd->advertising |= ADVERTISED_10000baseT_Full; - if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - ecmd->advertising |= ADVERTISED_1000baseT_Full; - break; + } + } + if (phy_types & I40E_CAP_PHY_TYPE_XAUI || + phy_types & I40E_CAP_PHY_TYPE_XFI || + phy_types & I40E_CAP_PHY_TYPE_SFI || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_AOC) + ecmd->supported |= SUPPORTED_10000baseT_Full; + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_T || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR) { + ecmd->supported |= SUPPORTED_Autoneg | + SUPPORTED_10000baseT_Full; + ecmd->advertising |= ADVERTISED_Autoneg | + ADVERTISED_10000baseT_Full; + } + if (phy_types & I40E_CAP_PHY_TYPE_XLAUI || + phy_types & I40E_CAP_PHY_TYPE_XLPPI || + phy_types & I40E_CAP_PHY_TYPE_40GBASE_AOC) + ecmd->supported |= SUPPORTED_40000baseCR4_Full; + if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4_CU || + phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4) { + ecmd->supported |= SUPPORTED_Autoneg | + SUPPORTED_40000baseCR4_Full; + ecmd->advertising |= ADVERTISED_Autoneg | + ADVERTISED_40000baseCR4_Full; + } + if ((phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) && + !(phy_types & I40E_CAP_PHY_TYPE_1000BASE_T)) { + ecmd->supported |= SUPPORTED_Autoneg | + SUPPORTED_100baseT_Full; + ecmd->advertising |= ADVERTISED_Autoneg | + ADVERTISED_100baseT_Full; } + if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_T || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL) { + ecmd->supported |= SUPPORTED_Autoneg | + SUPPORTED_1000baseT_Full; + ecmd->advertising |= ADVERTISED_Autoneg | + ADVERTISED_1000baseT_Full; + } + if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4) + ecmd->supported |= SUPPORTED_40000baseSR4_Full; + if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_LR4) + ecmd->supported |= SUPPORTED_40000baseLR4_Full; /* With no link speed and duplex are unknown */ ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); @@ -478,12 +481,43 @@ static int i40e_get_settings(struct net_device *netdev, bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP; if (link_up) - i40e_get_settings_link_up(hw, ecmd, netdev); + i40e_get_settings_link_up(hw, ecmd, netdev, pf); else - i40e_get_settings_link_down(hw, ecmd); + i40e_get_settings_link_down(hw, ecmd, pf); /* Now set the settings that don't rely on link being up/down */ + /* For backplane, supported and advertised are only reliant on the + * phy types the NVM specifies are supported. + */ + if (hw->device_id == I40E_DEV_ID_KX_B || + hw->device_id == I40E_DEV_ID_KX_C || + hw->device_id == I40E_DEV_ID_20G_KR2 || + hw->device_id == I40E_DEV_ID_20G_KR2_A) { + ecmd->supported = SUPPORTED_Autoneg; + ecmd->advertising = ADVERTISED_Autoneg; + if (hw->phy.phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4) { + ecmd->supported |= SUPPORTED_40000baseKR4_Full; + ecmd->advertising |= ADVERTISED_40000baseKR4_Full; + } + if (hw->phy.phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2) { + ecmd->supported |= SUPPORTED_20000baseKR2_Full; + ecmd->advertising |= ADVERTISED_20000baseKR2_Full; + } + if (hw->phy.phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR) { + ecmd->supported |= SUPPORTED_10000baseKR_Full; + ecmd->advertising |= ADVERTISED_10000baseKR_Full; + } + if (hw->phy.phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) { + ecmd->supported |= SUPPORTED_10000baseKX4_Full; + ecmd->advertising |= ADVERTISED_10000baseKX4_Full; + } + if (hw->phy.phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX) { + ecmd->supported |= SUPPORTED_1000baseKX_Full; + ecmd->advertising |= ADVERTISED_1000baseKX_Full; + } + } + /* Set autoneg settings */ ecmd->autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ? AUTONEG_ENABLE : AUTONEG_DISABLE); @@ -583,6 +617,14 @@ static int i40e_set_settings(struct net_device *netdev, hw->phy.link_info.link_info & I40E_AQ_LINK_UP) return -EOPNOTSUPP; + if (hw->device_id == I40E_DEV_ID_KX_B || + hw->device_id == I40E_DEV_ID_KX_C || + hw->device_id == I40E_DEV_ID_20G_KR2 || + hw->device_id == I40E_DEV_ID_20G_KR2_A) { + netdev_info(netdev, "Changing settings is not supported on backplane.\n"); + return -EOPNOTSUPP; + } + /* get our own copy of the bits to check against */ memset(&safe_ecmd, 0, sizeof(struct ethtool_cmd)); i40e_get_settings(netdev, &safe_ecmd); @@ -619,28 +661,31 @@ static int i40e_set_settings(struct net_device *netdev, /* Check autoneg */ if (autoneg == AUTONEG_ENABLE) { - /* If autoneg is not supported, return error */ - if (!(safe_ecmd.supported & SUPPORTED_Autoneg)) { - netdev_info(netdev, "Autoneg not supported on this phy\n"); - return -EINVAL; - } /* If autoneg was not already enabled */ if (!(hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED)) { + /* If autoneg is not supported, return error */ + if (!(safe_ecmd.supported & SUPPORTED_Autoneg)) { + netdev_info(netdev, "Autoneg not supported on this phy\n"); + return -EINVAL; + } + /* Autoneg is allowed to change */ config.abilities = abilities.abilities | I40E_AQ_PHY_ENABLE_AN; change = true; } } else { - /* If autoneg is supported 10GBASE_T is the only phy that - * can disable it, so otherwise return error - */ - if (safe_ecmd.supported & SUPPORTED_Autoneg && - hw->phy.link_info.phy_type != I40E_PHY_TYPE_10GBASE_T) { - netdev_info(netdev, "Autoneg cannot be disabled on this phy\n"); - return -EINVAL; - } /* If autoneg is currently enabled */ if (hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED) { + /* If autoneg is supported 10GBASE_T is the only PHY + * that can disable it, so otherwise return error + */ + if (safe_ecmd.supported & SUPPORTED_Autoneg && + hw->phy.link_info.phy_type != + I40E_PHY_TYPE_10GBASE_T) { + netdev_info(netdev, "Autoneg cannot be disabled on this phy\n"); + return -EINVAL; + } + /* Autoneg is allowed to change */ config.abilities = abilities.abilities & ~I40E_AQ_PHY_ENABLE_AN; change = true; @@ -704,11 +749,11 @@ static int i40e_set_settings(struct net_device *netdev, return -EAGAIN; } - status = i40e_aq_get_link_info(hw, true, NULL, NULL); + status = i40e_update_link_info(hw); if (status) - netdev_info(netdev, "Updating link info failed with err %s aq_err %s\n", - i40e_stat_str(hw, status), - i40e_aq_str(hw, hw->aq.asq_last_status)); + netdev_dbg(netdev, "Updating link info failed with err %s aq_err %s\n", + i40e_stat_str(hw, status), + i40e_aq_str(hw, hw->aq.asq_last_status)); } else { netdev_info(netdev, "Nothing changed, exiting without setting anything.\n"); @@ -958,9 +1003,7 @@ static int i40e_get_eeprom(struct net_device *netdev, cmd = (struct i40e_nvm_access *)eeprom; ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno); - if (ret_val && - ((hw->aq.asq_last_status != I40E_AQ_RC_EACCES) || - (hw->debug_mask & I40E_DEBUG_NVM))) + if (ret_val && (hw->debug_mask & I40E_DEBUG_NVM)) dev_info(&pf->pdev->dev, "NVMUpdate read failed err=%d status=0x%x errno=%d module=%d offset=0x%x size=%d\n", ret_val, hw->aq.asq_last_status, errno, @@ -1064,10 +1107,7 @@ static int i40e_set_eeprom(struct net_device *netdev, cmd = (struct i40e_nvm_access *)eeprom; ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno); - if (ret_val && - ((hw->aq.asq_last_status != I40E_AQ_RC_EPERM && - hw->aq.asq_last_status != I40E_AQ_RC_EBUSY) || - (hw->debug_mask & I40E_DEBUG_NVM))) + if (ret_val && (hw->debug_mask & I40E_DEBUG_NVM)) dev_info(&pf->pdev->dev, "NVMUpdate write failed err=%d status=0x%x errno=%d module=%d offset=0x%x size=%d\n", ret_val, hw->aq.asq_last_status, errno, @@ -1087,11 +1127,10 @@ static void i40e_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->driver, i40e_driver_name, sizeof(drvinfo->driver)); strlcpy(drvinfo->version, i40e_driver_version_str, sizeof(drvinfo->version)); - strlcpy(drvinfo->fw_version, i40e_fw_version_str(&pf->hw), + strlcpy(drvinfo->fw_version, i40e_nvm_version_str(&pf->hw), sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(pf->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_priv_flags = I40E_PRIV_FLAGS_STR_LEN; } static void i40e_get_ringparam(struct net_device *netdev, @@ -1815,6 +1854,14 @@ static int i40e_get_coalesce(struct net_device *netdev, ec->rx_coalesce_usecs = vsi->rx_itr_setting & ~I40E_ITR_DYNAMIC; ec->tx_coalesce_usecs = vsi->tx_itr_setting & ~I40E_ITR_DYNAMIC; + /* we use the _usecs_high to store/set the interrupt rate limit + * that the hardware supports, that almost but not quite + * fits the original intent of the ethtool variable, + * the rx_coalesce_usecs_high limits total interrupts + * per second from both tx/rx sources. + */ + ec->rx_coalesce_usecs_high = vsi->int_rate_limit; + ec->tx_coalesce_usecs_high = vsi->int_rate_limit; return 0; } @@ -1833,6 +1880,17 @@ static int i40e_set_coalesce(struct net_device *netdev, if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq) vsi->work_limit = ec->tx_max_coalesced_frames_irq; + /* tx_coalesce_usecs_high is ignored, use rx-usecs-high instead */ + if (ec->tx_coalesce_usecs_high != vsi->int_rate_limit) { + netif_info(pf, drv, netdev, "tx-usecs-high is not used, please program rx-usecs-high\n"); + return -EINVAL; + } + + if (ec->rx_coalesce_usecs_high >= INTRL_REG_TO_USEC(I40E_MAX_INTRL)) { + netif_info(pf, drv, netdev, "Invalid value, rx-usecs-high range is 0-235\n"); + return -EINVAL; + } + vector = vsi->base_vector; if ((ec->rx_coalesce_usecs >= (I40E_MIN_ITR << 1)) && (ec->rx_coalesce_usecs <= (I40E_MAX_ITR << 1))) { @@ -1846,6 +1904,8 @@ static int i40e_set_coalesce(struct net_device *netdev, return -EINVAL; } + vsi->int_rate_limit = ec->rx_coalesce_usecs_high; + if ((ec->tx_coalesce_usecs >= (I40E_MIN_ITR << 1)) && (ec->tx_coalesce_usecs <= (I40E_MAX_ITR << 1))) { vsi->tx_itr_setting = ec->tx_coalesce_usecs; @@ -1870,11 +1930,14 @@ static int i40e_set_coalesce(struct net_device *netdev, vsi->tx_itr_setting &= ~I40E_ITR_DYNAMIC; for (i = 0; i < vsi->num_q_vectors; i++, vector++) { + u16 intrl = INTRL_USEC_TO_REG(vsi->int_rate_limit); + q_vector = vsi->q_vectors[i]; q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting); wr32(hw, I40E_PFINT_ITRN(0, vector - 1), q_vector->rx.itr); q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting); wr32(hw, I40E_PFINT_ITRN(1, vector - 1), q_vector->tx.itr); + wr32(hw, I40E_PFINT_RATEN(vector - 1), intrl); i40e_flush(hw); } @@ -2639,6 +2702,10 @@ static u32 i40e_get_priv_flags(struct net_device *dev) I40E_PRIV_FLAGS_NPAR_FLAG : 0; ret_flags |= pf->flags & I40E_FLAG_LINK_POLLING_ENABLED ? I40E_PRIV_FLAGS_LINKPOLL_FLAG : 0; + ret_flags |= pf->flags & I40E_FLAG_FD_ATR_ENABLED ? + I40E_PRIV_FLAGS_FD_ATR : 0; + ret_flags |= pf->flags & I40E_FLAG_VEB_STATS_ENABLED ? + I40E_PRIV_FLAGS_VEB_STATS : 0; return ret_flags; } @@ -2659,6 +2726,22 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) else pf->flags &= ~I40E_FLAG_LINK_POLLING_ENABLED; + /* allow the user to control the state of the Flow + * Director ATR (Application Targeted Routing) feature + * of the driver + */ + if (flags & I40E_PRIV_FLAGS_FD_ATR) { + pf->flags |= I40E_FLAG_FD_ATR_ENABLED; + } else { + pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED; + pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + } + + if (flags & I40E_PRIV_FLAGS_VEB_STATS) + pf->flags |= I40E_FLAG_VEB_STATS_ENABLED; + else + pf->flags &= ~I40E_FLAG_VEB_STATS_ENABLED; + return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c index eaedc1f4c257..fe5d9bf3ed6d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c +++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c @@ -284,7 +284,7 @@ void i40e_init_pf_fcoe(struct i40e_pf *pf) pf->fcoe_hmc_filt_num = 0; if (!pf->hw.func_caps.fcoe) { - dev_info(&pf->pdev->dev, "FCoE capability is disabled\n"); + dev_dbg(&pf->pdev->dev, "FCoE capability is disabled\n"); return; } @@ -1516,10 +1516,12 @@ void i40e_fcoe_config_netdev(struct net_device *netdev, struct i40e_vsi *vsi) * same PCI function. */ netdev->dev_port = 1; + spin_lock_bh(&vsi->mac_filter_list_lock); i40e_add_filter(vsi, hw->mac.san_addr, 0, false, false); i40e_add_filter(vsi, (u8[6]) FC_FCOE_FLOGI_MAC, 0, false, false); i40e_add_filter(vsi, FIP_ALL_FCOE_MACS, 0, false, false); i40e_add_filter(vsi, FIP_ALL_ENODE_MACS, 0, false, false); + spin_unlock_bh(&vsi->mac_filter_list_lock); /* use san mac */ ether_addr_copy(netdev->dev_addr, hw->mac.san_addr); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index a484f2265524..cc8c0aeab9bb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -39,7 +39,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 3 -#define DRV_VERSION_BUILD 21 +#define DRV_VERSION_BUILD 38 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -1355,6 +1355,9 @@ static int i40e_rm_default_mac_filter(struct i40e_vsi *vsi, u8 *macaddr) * @is_netdev: make sure its a netdev filter, else doesn't matter * * Returns ptr to the filter object or NULL when no memory available. + * + * NOTE: This function is expected to be called with mac_filter_list_lock + * being held. **/ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, u8 *macaddr, s16 vlan, @@ -1413,6 +1416,9 @@ add_filter_out: * @vlan: the vlan * @is_vf: make sure it's a VF filter, else doesn't matter * @is_netdev: make sure it's a netdev filter, else doesn't matter + * + * NOTE: This function is expected to be called with mac_filter_list_lock + * being held. **/ void i40e_del_filter(struct i40e_vsi *vsi, u8 *macaddr, s16 vlan, @@ -1519,8 +1525,10 @@ static int i40e_set_mac(struct net_device *netdev, void *p) element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH; i40e_aq_remove_macvlan(&pf->hw, vsi->seid, &element, 1, NULL); } else { + spin_lock_bh(&vsi->mac_filter_list_lock); i40e_del_filter(vsi, netdev->dev_addr, I40E_VLAN_ANY, false, false); + spin_unlock_bh(&vsi->mac_filter_list_lock); } if (ether_addr_equal(addr->sa_data, hw->mac.addr)) { @@ -1531,10 +1539,12 @@ static int i40e_set_mac(struct net_device *netdev, void *p) element.flags = cpu_to_le16(I40E_AQC_MACVLAN_ADD_PERFECT_MATCH); i40e_aq_add_macvlan(&pf->hw, vsi->seid, &element, 1, NULL); } else { + spin_lock_bh(&vsi->mac_filter_list_lock); f = i40e_add_filter(vsi, addr->sa_data, I40E_VLAN_ANY, false, false); if (f) f->is_laa = true; + spin_unlock_bh(&vsi->mac_filter_list_lock); } i40e_sync_vsi_filters(vsi, false); @@ -1707,6 +1717,8 @@ static void i40e_set_rx_mode(struct net_device *netdev) struct netdev_hw_addr *mca; struct netdev_hw_addr *ha; + spin_lock_bh(&vsi->mac_filter_list_lock); + /* add addr if not already in the filter list */ netdev_for_each_uc_addr(uca, netdev) { if (!i40e_find_mac(vsi, uca->addr, false, true)) { @@ -1754,6 +1766,7 @@ static void i40e_set_rx_mode(struct net_device *netdev) bottom_of_search_loop: continue; } + spin_unlock_bh(&vsi->mac_filter_list_lock); /* check for other flag changes */ if (vsi->current_netdev_flags != vsi->netdev->flags) { @@ -1763,6 +1776,79 @@ bottom_of_search_loop: } /** + * i40e_mac_filter_entry_clone - Clones a MAC filter entry + * @src: source MAC filter entry to be clones + * + * Returns the pointer to newly cloned MAC filter entry or NULL + * in case of error + **/ +static struct i40e_mac_filter *i40e_mac_filter_entry_clone( + struct i40e_mac_filter *src) +{ + struct i40e_mac_filter *f; + + f = kzalloc(sizeof(*f), GFP_ATOMIC); + if (!f) + return NULL; + *f = *src; + + INIT_LIST_HEAD(&f->list); + + return f; +} + +/** + * i40e_undo_del_filter_entries - Undo the changes made to MAC filter entries + * @vsi: pointer to vsi struct + * @from: Pointer to list which contains MAC filter entries - changes to + * those entries needs to be undone. + * + * MAC filter entries from list were slated to be removed from device. + **/ +static void i40e_undo_del_filter_entries(struct i40e_vsi *vsi, + struct list_head *from) +{ + struct i40e_mac_filter *f, *ftmp; + + list_for_each_entry_safe(f, ftmp, from, list) { + f->changed = true; + /* Move the element back into MAC filter list*/ + list_move_tail(&f->list, &vsi->mac_filter_list); + } +} + +/** + * i40e_undo_add_filter_entries - Undo the changes made to MAC filter entries + * @vsi: pointer to vsi struct + * + * MAC filter entries from list were slated to be added from device. + **/ +static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi) +{ + struct i40e_mac_filter *f, *ftmp; + + list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { + if (!f->changed && f->counter) + f->changed = true; + } +} + +/** + * i40e_cleanup_add_list - Deletes the element from add list and release + * memory + * @add_list: Pointer to list which contains MAC filter entries + **/ +static void i40e_cleanup_add_list(struct list_head *add_list) +{ + struct i40e_mac_filter *f, *ftmp; + + list_for_each_entry_safe(f, ftmp, add_list, list) { + list_del(&f->list); + kfree(f); + } +} + +/** * i40e_sync_vsi_filters - Update the VSI filter list to the HW * @vsi: ptr to the VSI * @grab_rtnl: whether RTNL needs to be grabbed @@ -1773,11 +1859,13 @@ bottom_of_search_loop: **/ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl) { - struct i40e_mac_filter *f, *ftmp; + struct list_head tmp_del_list, tmp_add_list; + struct i40e_mac_filter *f, *ftmp, *fclone; bool promisc_forced_on = false; bool add_happened = false; int filter_list_len = 0; u32 changed_flags = 0; + bool err_cond = false; i40e_status ret = 0; struct i40e_pf *pf; int num_add = 0; @@ -1798,17 +1886,13 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl) vsi->current_netdev_flags = vsi->netdev->flags; } + INIT_LIST_HEAD(&tmp_del_list); + INIT_LIST_HEAD(&tmp_add_list); + if (vsi->flags & I40E_VSI_FLAG_FILTER_CHANGED) { vsi->flags &= ~I40E_VSI_FLAG_FILTER_CHANGED; - filter_list_len = pf->hw.aq.asq_buf_size / - sizeof(struct i40e_aqc_remove_macvlan_element_data); - del_list = kcalloc(filter_list_len, - sizeof(struct i40e_aqc_remove_macvlan_element_data), - GFP_KERNEL); - if (!del_list) - return -ENOMEM; - + spin_lock_bh(&vsi->mac_filter_list_lock); list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { if (!f->changed) continue; @@ -1816,6 +1900,58 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl) if (f->counter != 0) continue; f->changed = false; + + /* Move the element into temporary del_list */ + list_move_tail(&f->list, &tmp_del_list); + } + + list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { + if (!f->changed) + continue; + + if (f->counter == 0) + continue; + f->changed = false; + + /* Clone MAC filter entry and add into temporary list */ + fclone = i40e_mac_filter_entry_clone(f); + if (!fclone) { + err_cond = true; + break; + } + list_add_tail(&fclone->list, &tmp_add_list); + } + + /* if failed to clone MAC filter entry - undo */ + if (err_cond) { + i40e_undo_del_filter_entries(vsi, &tmp_del_list); + i40e_undo_add_filter_entries(vsi); + } + spin_unlock_bh(&vsi->mac_filter_list_lock); + + if (err_cond) + i40e_cleanup_add_list(&tmp_add_list); + } + + /* Now process 'del_list' outside the lock */ + if (!list_empty(&tmp_del_list)) { + filter_list_len = pf->hw.aq.asq_buf_size / + sizeof(struct i40e_aqc_remove_macvlan_element_data); + del_list = kcalloc(filter_list_len, + sizeof(struct i40e_aqc_remove_macvlan_element_data), + GFP_KERNEL); + if (!del_list) { + i40e_cleanup_add_list(&tmp_add_list); + + /* Undo VSI's MAC filter entry element updates */ + spin_lock_bh(&vsi->mac_filter_list_lock); + i40e_undo_del_filter_entries(vsi, &tmp_del_list); + i40e_undo_add_filter_entries(vsi); + spin_unlock_bh(&vsi->mac_filter_list_lock); + return -ENOMEM; + } + + list_for_each_entry_safe(f, ftmp, &tmp_del_list, list) { cmd_flags = 0; /* add to delete list */ @@ -1828,10 +1964,6 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl) del_list[num_del].flags = cmd_flags; num_del++; - /* unlink from filter list */ - list_del(&f->list); - kfree(f); - /* flush a full buffer */ if (num_del == filter_list_len) { ret = i40e_aq_remove_macvlan(&pf->hw, @@ -1842,12 +1974,18 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl) memset(del_list, 0, sizeof(*del_list)); if (ret && aq_err != I40E_AQ_RC_ENOENT) - dev_info(&pf->pdev->dev, - "ignoring delete macvlan error, err %s, aq_err %s while flushing a full buffer\n", - i40e_stat_str(&pf->hw, ret), - i40e_aq_str(&pf->hw, aq_err)); + 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, ret), + i40e_aq_str(&pf->hw, aq_err)); } + /* Release memory for MAC filter entries which were + * synced up with HW. + */ + list_del(&f->list); + kfree(f); } + if (num_del) { ret = i40e_aq_remove_macvlan(&pf->hw, vsi->seid, del_list, num_del, NULL); @@ -1863,6 +2001,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl) kfree(del_list); del_list = NULL; + } + + if (!list_empty(&tmp_add_list)) { /* do all the adds now */ filter_list_len = pf->hw.aq.asq_buf_size / @@ -1870,16 +2011,19 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl) add_list = kcalloc(filter_list_len, sizeof(struct i40e_aqc_add_macvlan_element_data), GFP_KERNEL); - if (!add_list) + if (!add_list) { + /* Purge element from temporary lists */ + i40e_cleanup_add_list(&tmp_add_list); + + /* Undo add filter entries from VSI MAC filter list */ + spin_lock_bh(&vsi->mac_filter_list_lock); + i40e_undo_add_filter_entries(vsi); + spin_unlock_bh(&vsi->mac_filter_list_lock); return -ENOMEM; + } - list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { - if (!f->changed) - continue; + list_for_each_entry_safe(f, ftmp, &tmp_add_list, list) { - if (f->counter == 0) - continue; - f->changed = false; add_happened = true; cmd_flags = 0; @@ -1906,7 +2050,13 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl) break; memset(add_list, 0, sizeof(*add_list)); } + /* Entries from tmp_add_list were cloned from MAC + * filter list, hence clean those cloned entries + */ + list_del(&f->list); + kfree(f); } + if (num_add) { ret = i40e_aq_add_macvlan(&pf->hw, vsi->seid, add_list, num_add, NULL); @@ -2158,6 +2308,9 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) is_vf = (vsi->type == I40E_VSI_SRIOV); is_netdev = !!(vsi->netdev); + /* Locked once because all functions invoked below iterates list*/ + spin_lock_bh(&vsi->mac_filter_list_lock); + if (is_netdev) { add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, vid, is_vf, is_netdev); @@ -2165,6 +2318,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) dev_info(&vsi->back->pdev->dev, "Could not add vlan filter %d for %pM\n", vid, vsi->netdev->dev_addr); + spin_unlock_bh(&vsi->mac_filter_list_lock); return -ENOMEM; } } @@ -2175,6 +2329,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) dev_info(&vsi->back->pdev->dev, "Could not add vlan filter %d for %pM\n", vid, f->macaddr); + spin_unlock_bh(&vsi->mac_filter_list_lock); return -ENOMEM; } } @@ -2196,6 +2351,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) dev_info(&vsi->back->pdev->dev, "Could not add filter 0 for %pM\n", vsi->netdev->dev_addr); + spin_unlock_bh(&vsi->mac_filter_list_lock); return -ENOMEM; } } @@ -2204,22 +2360,28 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) /* Do not assume that I40E_VLAN_ANY should be reset to VLAN 0 */ if (vid > 0 && !vsi->info.pvid) { list_for_each_entry(f, &vsi->mac_filter_list, list) { - if (i40e_find_filter(vsi, f->macaddr, I40E_VLAN_ANY, - is_vf, is_netdev)) { - i40e_del_filter(vsi, f->macaddr, I40E_VLAN_ANY, - is_vf, is_netdev); - add_f = i40e_add_filter(vsi, f->macaddr, - 0, is_vf, is_netdev); - if (!add_f) { - dev_info(&vsi->back->pdev->dev, - "Could not add filter 0 for %pM\n", - f->macaddr); - return -ENOMEM; - } + if (!i40e_find_filter(vsi, f->macaddr, I40E_VLAN_ANY, + is_vf, is_netdev)) + continue; + i40e_del_filter(vsi, f->macaddr, I40E_VLAN_ANY, + is_vf, is_netdev); + add_f = i40e_add_filter(vsi, f->macaddr, + 0, is_vf, is_netdev); + if (!add_f) { + dev_info(&vsi->back->pdev->dev, + "Could not add filter 0 for %pM\n", + f->macaddr); + spin_unlock_bh(&vsi->mac_filter_list_lock); + return -ENOMEM; } } } + /* Make sure to release before sync_vsi_filter because that + * function will lock/unlock as necessary + */ + spin_unlock_bh(&vsi->mac_filter_list_lock); + if (test_bit(__I40E_DOWN, &vsi->back->state) || test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) return 0; @@ -2244,6 +2406,9 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid) is_vf = (vsi->type == I40E_VSI_SRIOV); is_netdev = !!(netdev); + /* Locked once because all functions invoked below iterates list */ + spin_lock_bh(&vsi->mac_filter_list_lock); + if (is_netdev) i40e_del_filter(vsi, netdev->dev_addr, vid, is_vf, is_netdev); @@ -2274,6 +2439,7 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid) dev_info(&vsi->back->pdev->dev, "Could not add filter %d for %pM\n", I40E_VLAN_ANY, netdev->dev_addr); + spin_unlock_bh(&vsi->mac_filter_list_lock); return -ENOMEM; } } @@ -2282,16 +2448,22 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid) list_for_each_entry(f, &vsi->mac_filter_list, list) { i40e_del_filter(vsi, f->macaddr, 0, is_vf, is_netdev); add_f = i40e_add_filter(vsi, f->macaddr, I40E_VLAN_ANY, - is_vf, is_netdev); + is_vf, is_netdev); if (!add_f) { dev_info(&vsi->back->pdev->dev, "Could not add filter %d for %pM\n", I40E_VLAN_ANY, f->macaddr); + spin_unlock_bh(&vsi->mac_filter_list_lock); return -ENOMEM; } } } + /* Make sure to release before sync_vsi_filter because that + * function with lock/unlock as necessary + */ + spin_unlock_bh(&vsi->mac_filter_list_lock); + if (test_bit(__I40E_DOWN, &vsi->back->state) || test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) return 0; @@ -2901,11 +3073,9 @@ static int i40e_vsi_configure(struct i40e_vsi *vsi) static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; - struct i40e_q_vector *q_vector; struct i40e_hw *hw = &pf->hw; u16 vector; int i, q; - u32 val; u32 qp; /* The interrupt indexing is offset by 1 in the PFINT_ITRn @@ -2915,7 +3085,9 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) qp = vsi->base_queue; vector = vsi->base_vector; for (i = 0; i < vsi->num_q_vectors; i++, vector++) { - q_vector = vsi->q_vectors[i]; + struct i40e_q_vector *q_vector = vsi->q_vectors[i]; + + q_vector->itr_countdown = ITR_COUNTDOWN_START; q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting); q_vector->rx.latency_range = I40E_LOW_LATENCY; wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1), @@ -2924,10 +3096,14 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) q_vector->tx.latency_range = I40E_LOW_LATENCY; wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), q_vector->tx.itr); + wr32(hw, I40E_PFINT_RATEN(vector - 1), + INTRL_USEC_TO_REG(vsi->int_rate_limit)); /* Linked list for the queuepairs assigned to this vector */ wr32(hw, I40E_PFINT_LNKLSTN(vector - 1), qp); for (q = 0; q < q_vector->num_ringpairs; q++) { + u32 val; + val = I40E_QINT_RQCTL_CAUSE_ENA_MASK | (I40E_RX_ITR << I40E_QINT_RQCTL_ITR_INDX_SHIFT) | (vector << I40E_QINT_RQCTL_MSIX_INDX_SHIFT) | @@ -3007,6 +3183,7 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi) u32 val; /* set the ITR configuration */ + q_vector->itr_countdown = ITR_COUNTDOWN_START; q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting); q_vector->rx.latency_range = I40E_LOW_LATENCY; wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.itr); @@ -3092,7 +3269,7 @@ static irqreturn_t i40e_msix_clean_rings(int irq, void *data) if (!q_vector->tx.ring && !q_vector->rx.ring) return IRQ_HANDLED; - napi_schedule(&q_vector->napi); + napi_schedule_irqoff(&q_vector->napi); return IRQ_HANDLED; } @@ -3261,6 +3438,8 @@ static irqreturn_t i40e_intr(int irq, void *data) /* only q0 is used in MSI/Legacy mode, and none are used in MSIX */ if (icr0 & I40E_PFINT_ICR0_QUEUE_0_MASK) { + struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + struct i40e_q_vector *q_vector = vsi->q_vectors[0]; /* temporarily disable queue cause for NAPI processing */ u32 qval = rd32(hw, I40E_QINT_RQCTL(0)); @@ -3273,7 +3452,7 @@ static irqreturn_t i40e_intr(int irq, void *data) wr32(hw, I40E_QINT_TQCTL(0), qval); if (!test_bit(__I40E_DOWN, &pf->state)) - napi_schedule(&pf->vsi[pf->lan_vsi]->q_vectors[0]->napi); + napi_schedule_irqoff(&q_vector->napi); } if (icr0 & I40E_PFINT_ICR0_ADMINQ_MASK) { @@ -3574,14 +3753,12 @@ static void i40e_netpoll(struct net_device *netdev) if (test_bit(__I40E_DOWN, &vsi->state)) return; - pf->flags |= I40E_FLAG_IN_NETPOLL; if (pf->flags & I40E_FLAG_MSIX_ENABLED) { for (i = 0; i < vsi->num_q_vectors; i++) i40e_msix_clean_rings(0, vsi->q_vectors[i]); } else { i40e_intr(pf->pdev->irq, netdev); } - pf->flags &= ~I40E_FLAG_IN_NETPOLL; } #endif @@ -4844,8 +5021,8 @@ out: */ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) { - char speed[SPEED_SIZE] = "Unknown"; - char fc[FC_SIZE] = "RX/TX"; + char *speed = "Unknown"; + char *fc = "Unknown"; if (vsi->current_isup == isup) return; @@ -4866,19 +5043,19 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) switch (vsi->back->hw.phy.link_info.link_speed) { case I40E_LINK_SPEED_40GB: - strlcpy(speed, "40 Gbps", SPEED_SIZE); + speed = "40 G"; break; case I40E_LINK_SPEED_20GB: - strncpy(speed, "20 Gbps", SPEED_SIZE); + speed = "20 G"; break; case I40E_LINK_SPEED_10GB: - strlcpy(speed, "10 Gbps", SPEED_SIZE); + speed = "10 G"; break; case I40E_LINK_SPEED_1GB: - strlcpy(speed, "1000 Mbps", SPEED_SIZE); + speed = "1000 M"; break; case I40E_LINK_SPEED_100MB: - strncpy(speed, "100 Mbps", SPEED_SIZE); + speed = "100 M"; break; default: break; @@ -4886,20 +5063,20 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) switch (vsi->back->hw.fc.current_mode) { case I40E_FC_FULL: - strlcpy(fc, "RX/TX", FC_SIZE); + fc = "RX/TX"; break; case I40E_FC_TX_PAUSE: - strlcpy(fc, "TX", FC_SIZE); + fc = "TX"; break; case I40E_FC_RX_PAUSE: - strlcpy(fc, "RX", FC_SIZE); + fc = "RX"; break; default: - strlcpy(fc, "None", FC_SIZE); + fc = "None"; break; } - netdev_info(vsi->netdev, "NIC Link is Up %s Full Duplex, Flow Control: %s\n", + netdev_info(vsi->netdev, "NIC Link is Up %sbps Full Duplex, Flow Control: %s\n", speed, fc); } @@ -6220,8 +6397,9 @@ static void i40e_config_bridge_mode(struct i40e_veb *veb) { struct i40e_pf *pf = veb->pf; - dev_info(&pf->pdev->dev, "enabling bridge mode: %s\n", - veb->bridge_mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB"); + if (pf->hw.debug_mask & I40E_DEBUG_LAN) + dev_info(&pf->pdev->dev, "enabling bridge mode: %s\n", + veb->bridge_mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB"); if (veb->bridge_mode & BRIDGE_MODE_VEPA) i40e_disable_pf_switch_lb(pf); else @@ -6353,12 +6531,6 @@ static int i40e_get_capabilities(struct i40e_pf *pf) } } while (err); - if (((pf->hw.aq.fw_maj_ver == 2) && (pf->hw.aq.fw_min_ver < 22)) || - (pf->hw.aq.fw_maj_ver < 2)) { - pf->hw.func_caps.num_msix_vectors++; - pf->hw.func_caps.num_msix_vectors_vf++; - } - if (pf->hw.debug_mask & I40E_DEBUG_USER) dev_info(&pf->pdev->dev, "pf=%d, num_vfs=%d, msix_pf=%d, msix_vf=%d, fd_g=%d, fd_b=%d, pf_max_q=%d num_vsi=%d\n", @@ -6593,9 +6765,9 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) /* make sure our flow control settings are restored */ ret = i40e_set_fc(&pf->hw, &set_fc_aq_fail, true); if (ret) - dev_info(&pf->pdev->dev, "set fc fail, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), - i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + dev_dbg(&pf->pdev->dev, "setting flow control: ret = %s last_status = %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); /* Rebuild the VSIs and VEBs that existed before reset. * They are still in our local switch element arrays, so only @@ -7047,6 +7219,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type) vsi->idx = vsi_idx; vsi->rx_itr_setting = pf->rx_itr_default; vsi->tx_itr_setting = pf->tx_itr_default; + vsi->int_rate_limit = 0; vsi->rss_table_size = (vsi->type == I40E_VSI_MAIN) ? pf->rss_table_size : 64; vsi->netdev_registered = false; @@ -7065,6 +7238,8 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type) /* Setup default MSIX irq handler for VSI */ i40e_vsi_setup_irqhandler(vsi, i40e_msix_clean_rings); + /* Initialize VSI lock */ + spin_lock_init(&vsi->mac_filter_list_lock); pf->vsi[vsi_idx] = vsi; ret = vsi_idx; goto unlock_pf; @@ -7955,12 +8130,12 @@ static int i40e_sw_init(struct i40e_pf *pf) (pf->hw.func_caps.fd_filters_best_effort > 0)) { pf->flags |= I40E_FLAG_FD_ATR_ENABLED; pf->atr_sample_rate = I40E_DEFAULT_ATR_SAMPLE_RATE; - if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) { - pf->flags |= I40E_FLAG_FD_SB_ENABLED; - } else { + if (pf->flags & I40E_FLAG_MFP_ENABLED && + pf->hw.num_partitions > 1) dev_info(&pf->pdev->dev, "Flow Director Sideband mode Disabled in MFP mode\n"); - } + else + pf->flags |= I40E_FLAG_FD_SB_ENABLED; pf->fdir_pf_filter_count = pf->hw.func_caps.fd_filters_guaranteed; pf->hw.fdir_shared_filter_count = @@ -8330,13 +8505,15 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, * @seq: RTNL message seq # * @dev: the netdev being configured * @filter_mask: unused + * @nlflags: netlink flags passed in * * Return the mode in which the hardware bridge is operating in * i.e VEB or VEPA. **/ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 filter_mask, int nlflags) + u32 __always_unused filter_mask, + int nlflags) { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; @@ -8365,7 +8542,7 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, /** * i40e_features_check - Validate encapsulated packet conforms to limits * @skb: skb buff - * @netdev: This physical port's netdev + * @dev: This physical port's netdev * @features: Offload features that the stack believes apply **/ static netdev_features_t i40e_features_check(struct sk_buff *skb, @@ -8446,6 +8623,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_GRE | NETIF_F_TSO; netdev->features = NETIF_F_SG | @@ -8453,6 +8631,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) NETIF_F_SCTP_CSUM | NETIF_F_HIGHDMA | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_GRE | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | @@ -8478,17 +8657,26 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) * default a MAC-VLAN filter that accepts any tagged packet * which must be replaced by a normal filter. */ - if (!i40e_rm_default_mac_filter(vsi, mac_addr)) + if (!i40e_rm_default_mac_filter(vsi, mac_addr)) { + spin_lock_bh(&vsi->mac_filter_list_lock); i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY, false, true); + spin_unlock_bh(&vsi->mac_filter_list_lock); + } } else { /* relate the VSI_VMDQ name to the VSI_MAIN name */ snprintf(netdev->name, IFNAMSIZ, "%sv%%d", pf->vsi[pf->lan_vsi]->netdev->name); random_ether_addr(mac_addr); + + spin_lock_bh(&vsi->mac_filter_list_lock); i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY, false, false); + spin_unlock_bh(&vsi->mac_filter_list_lock); } + + spin_lock_bh(&vsi->mac_filter_list_lock); i40e_add_filter(vsi, brdcast, I40E_VLAN_ANY, false, false); + spin_unlock_bh(&vsi->mac_filter_list_lock); ether_addr_copy(netdev->dev_addr, mac_addr); ether_addr_copy(netdev->perm_addr, mac_addr); @@ -8562,10 +8750,13 @@ int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi) static int i40e_add_vsi(struct i40e_vsi *vsi) { int ret = -ENODEV; - struct i40e_mac_filter *f, *ftmp; + u8 laa_macaddr[ETH_ALEN]; + bool found_laa_mac_filter = false; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_vsi_context ctxt; + struct i40e_mac_filter *f, *ftmp; + u8 enabled_tc = 0x1; /* TC0 enabled */ int f_count = 0; @@ -8737,32 +8928,41 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) vsi->id = ctxt.vsi_number; } + spin_lock_bh(&vsi->mac_filter_list_lock); /* If macvlan filters already exist, force them to get loaded */ list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { f->changed = true; f_count++; + /* Expected to have only one MAC filter entry for LAA in list */ if (f->is_laa && vsi->type == I40E_VSI_MAIN) { - struct i40e_aqc_remove_macvlan_element_data element; + ether_addr_copy(laa_macaddr, f->macaddr); + found_laa_mac_filter = true; + } + } + spin_unlock_bh(&vsi->mac_filter_list_lock); - memset(&element, 0, sizeof(element)); - ether_addr_copy(element.mac_addr, f->macaddr); - element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH; - ret = i40e_aq_remove_macvlan(hw, vsi->seid, - &element, 1, NULL); - if (ret) { - /* some older FW has a different default */ - element.flags |= - I40E_AQC_MACVLAN_DEL_IGNORE_VLAN; - i40e_aq_remove_macvlan(hw, vsi->seid, - &element, 1, NULL); - } + if (found_laa_mac_filter) { + struct i40e_aqc_remove_macvlan_element_data element; - i40e_aq_mac_address_write(hw, - I40E_AQC_WRITE_TYPE_LAA_WOL, - f->macaddr, NULL); + memset(&element, 0, sizeof(element)); + ether_addr_copy(element.mac_addr, laa_macaddr); + element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH; + ret = i40e_aq_remove_macvlan(hw, vsi->seid, + &element, 1, NULL); + if (ret) { + /* some older FW has a different default */ + element.flags |= + I40E_AQC_MACVLAN_DEL_IGNORE_VLAN; + i40e_aq_remove_macvlan(hw, vsi->seid, + &element, 1, NULL); } + + i40e_aq_mac_address_write(hw, + I40E_AQC_WRITE_TYPE_LAA_WOL, + laa_macaddr, NULL); } + if (f_count) { vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; pf->flags |= I40E_FLAG_FILTER_SYNC; @@ -8825,9 +9025,12 @@ int i40e_vsi_release(struct i40e_vsi *vsi) i40e_vsi_disable_irq(vsi); } + spin_lock_bh(&vsi->mac_filter_list_lock); list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) i40e_del_filter(vsi, f->macaddr, f->vlan, f->is_vf, f->is_netdev); + spin_unlock_bh(&vsi->mac_filter_list_lock); + i40e_sync_vsi_filters(vsi, false); i40e_vsi_delete(vsi); @@ -9727,7 +9930,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) i40e_config_rss(pf); /* fill in link information and enable LSE reporting */ - i40e_aq_get_link_info(&pf->hw, true, NULL, NULL); + i40e_update_link_info(&pf->hw); i40e_link_event(pf); /* Initialize user-specific link properties */ @@ -9845,8 +10048,14 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf) } pf->queues_left = queues_left; + dev_dbg(&pf->pdev->dev, + "qs_avail=%d FD SB=%d lan_qs=%d lan_tc0=%d vf=%d*%d vmdq=%d*%d, remaining=%d\n", + pf->hw.func_caps.num_tx_qp, + !!(pf->flags & I40E_FLAG_FD_SB_ENABLED), + pf->num_lan_qps, pf->rss_size, pf->num_req_vfs, pf->num_vf_qps, + pf->num_vmdq_vsis, pf->num_vmdq_qps, queues_left); #ifdef I40E_FCOE - dev_info(&pf->pdev->dev, "fcoe queues = %d\n", pf->num_fcoe_qps); + dev_dbg(&pf->pdev->dev, "fcoe queues = %d\n", pf->num_fcoe_qps); #endif } @@ -9923,6 +10132,10 @@ static void i40e_print_features(struct i40e_pf *pf) if (pf->flags & I40E_FLAG_FCOE_ENABLED) buf += sprintf(buf, "FCOE "); #endif + if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED) + buf += sprintf(buf, "VEB "); + else + buf += sprintf(buf, "VEPA "); BUG_ON(buf > (string + INFO_STRING_LEN)); dev_info(&pf->pdev->dev, "%s\n", string); @@ -9948,7 +10161,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) static u16 pfs_found; u16 wol_nvm_bits; u16 link_status; - int err = 0; + int err; u32 len; u32 i; @@ -10062,7 +10275,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pf->hw.fc.requested_mode = I40E_FC_NONE; err = i40e_init_adminq(hw); - dev_info(&pdev->dev, "%s\n", i40e_fw_version_str(hw)); + + /* provide nvm, fw, api versions */ + dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s\n", + hw->aq.fw_maj_ver, hw->aq.fw_min_ver, hw->aq.fw_build, + hw->aq.api_maj_ver, hw->aq.api_min_ver, + i40e_nvm_version_str(hw)); + if (err) { dev_info(&pdev->dev, "The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n"); @@ -10299,37 +10518,73 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i40e_fcoe_vsi_setup(pf); #endif - /* Get the negotiated link width and speed from PCI config space */ - pcie_capability_read_word(pf->pdev, PCI_EXP_LNKSTA, &link_status); +#define PCI_SPEED_SIZE 8 +#define PCI_WIDTH_SIZE 8 + /* Devices on the IOSF bus do not have this information + * and will report PCI Gen 1 x 1 by default so don't bother + * checking them. + */ + if (!(pf->flags & I40E_FLAG_NO_PCI_LINK_CHECK)) { + char speed[PCI_SPEED_SIZE] = "Unknown"; + char width[PCI_WIDTH_SIZE] = "Unknown"; - i40e_set_pci_config_data(hw, link_status); + /* Get the negotiated link width and speed from PCI config + * space + */ + pcie_capability_read_word(pf->pdev, PCI_EXP_LNKSTA, + &link_status); + + i40e_set_pci_config_data(hw, link_status); + + switch (hw->bus.speed) { + case i40e_bus_speed_8000: + strncpy(speed, "8.0", PCI_SPEED_SIZE); break; + case i40e_bus_speed_5000: + strncpy(speed, "5.0", PCI_SPEED_SIZE); break; + case i40e_bus_speed_2500: + strncpy(speed, "2.5", PCI_SPEED_SIZE); break; + default: + break; + } + switch (hw->bus.width) { + case i40e_bus_width_pcie_x8: + strncpy(width, "8", PCI_WIDTH_SIZE); break; + case i40e_bus_width_pcie_x4: + strncpy(width, "4", PCI_WIDTH_SIZE); break; + case i40e_bus_width_pcie_x2: + strncpy(width, "2", PCI_WIDTH_SIZE); break; + case i40e_bus_width_pcie_x1: + strncpy(width, "1", PCI_WIDTH_SIZE); break; + default: + break; + } - dev_info(&pdev->dev, "PCI-Express: %s %s\n", - (hw->bus.speed == i40e_bus_speed_8000 ? "Speed 8.0GT/s" : - hw->bus.speed == i40e_bus_speed_5000 ? "Speed 5.0GT/s" : - hw->bus.speed == i40e_bus_speed_2500 ? "Speed 2.5GT/s" : - "Unknown"), - (hw->bus.width == i40e_bus_width_pcie_x8 ? "Width x8" : - hw->bus.width == i40e_bus_width_pcie_x4 ? "Width x4" : - hw->bus.width == i40e_bus_width_pcie_x2 ? "Width x2" : - hw->bus.width == i40e_bus_width_pcie_x1 ? "Width x1" : - "Unknown")); + dev_info(&pdev->dev, "PCI-Express: Speed %sGT/s Width x%s\n", + speed, width); - if (hw->bus.width < i40e_bus_width_pcie_x8 || - hw->bus.speed < i40e_bus_speed_8000) { - dev_warn(&pdev->dev, "PCI-Express bandwidth available for this device may be insufficient for optimal performance.\n"); - dev_warn(&pdev->dev, "Please move the device to a different PCI-e link with more lanes and/or higher transfer rate.\n"); + if (hw->bus.width < i40e_bus_width_pcie_x8 || + hw->bus.speed < i40e_bus_speed_8000) { + dev_warn(&pdev->dev, "PCI-Express bandwidth available for this device may be insufficient for optimal performance.\n"); + dev_warn(&pdev->dev, "Please move the device to a different PCI-e link with more lanes and/or higher transfer rate.\n"); + } } /* get the requested speeds from the fw */ err = i40e_aq_get_phy_capabilities(hw, false, false, &abilities, NULL); if (err) - dev_info(&pf->pdev->dev, - "get phy capabilities failed, err %s aq_err %s, advertised speed settings may not be correct\n", - i40e_stat_str(&pf->hw, err), - i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + dev_dbg(&pf->pdev->dev, "get requested speeds ret = %s last_status = %s\n", + i40e_stat_str(&pf->hw, err), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); pf->hw.phy.link_info.requested_speeds = abilities.link_speed; + /* get the supported phy types from the fw */ + err = i40e_aq_get_phy_capabilities(hw, false, true, &abilities, NULL); + if (err) + dev_dbg(&pf->pdev->dev, "get supported phy types ret = %s last_status = %s\n", + i40e_stat_str(&pf->hw, err), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + pf->hw.phy.phy_types = le32_to_cpu(abilities.phy_type); + /* print a string summarizing features */ i40e_print_features(pf); @@ -10377,6 +10632,7 @@ err_dma: static void i40e_remove(struct pci_dev *pdev) { struct i40e_pf *pf = pci_get_drvdata(pdev); + struct i40e_hw *hw = &pf->hw; i40e_status ret_code; int i; @@ -10384,6 +10640,10 @@ static void i40e_remove(struct pci_dev *pdev) i40e_ptp_stop(pf); + /* Disable RSS in hw */ + wr32(hw, I40E_PFQF_HENA(0), 0); + wr32(hw, I40E_PFQF_HENA(1), 0); + /* no more scheduling of any task */ set_bit(__I40E_DOWN, &pf->state); del_timer_sync(&pf->service_timer); diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 2142e1004a2f..58e384a372a0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -290,9 +290,18 @@ static i40e_status i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset, i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, u16 *data) { - if (hw->mac.type == I40E_MAC_X722) - return i40e_read_nvm_word_aq(hw, offset, data); - return i40e_read_nvm_word_srctl(hw, offset, data); + enum i40e_status_code ret_code = 0; + + if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) { + ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); + if (!ret_code) { + ret_code = i40e_read_nvm_word_aq(hw, offset, data); + i40e_release_nvm(hw); + } + } else { + ret_code = i40e_read_nvm_word_srctl(hw, offset, data); + } + return ret_code; } /** @@ -397,9 +406,19 @@ read_nvm_buffer_aq_exit: i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, u16 *words, u16 *data) { - if (hw->mac.type == I40E_MAC_X722) - return i40e_read_nvm_buffer_aq(hw, offset, words, data); - return i40e_read_nvm_buffer_srctl(hw, offset, words, data); + enum i40e_status_code ret_code = 0; + + if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) { + ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); + if (!ret_code) { + ret_code = i40e_read_nvm_buffer_aq(hw, offset, words, + data); + i40e_release_nvm(hw); + } + } else { + ret_code = i40e_read_nvm_buffer_srctl(hw, offset, words, data); + } + return ret_code; } /** @@ -632,7 +651,7 @@ static inline u8 i40e_nvmupd_get_transaction(u32 val) return (u8)((val & I40E_NVM_TRANS_MASK) >> I40E_NVM_TRANS_SHIFT); } -static char *i40e_nvm_update_state_str[] = { +static const char * const i40e_nvm_update_state_str[] = { "I40E_NVMUPD_INVALID", "I40E_NVMUPD_READ_CON", "I40E_NVMUPD_READ_SNT", diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index e51e1567837c..10bf2ba8bc15 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -58,8 +58,8 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void i40e_idle_aq(struct i40e_hw *hw); bool i40e_check_asq_alive(struct i40e_hw *hw); i40e_status i40e_aq_queue_shutdown(struct i40e_hw *hw, bool unloading); -char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err); -char *i40e_stat_str(struct i40e_hw *hw, i40e_status stat_err); +const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err); +const char *i40e_stat_str(struct i40e_hw *hw, i40e_status stat_err); i40e_status i40e_aq_get_rss_lut(struct i40e_hw *hw, u16 seid, bool pf_lut, u8 *lut, u16 lut_size); @@ -259,6 +259,7 @@ i40e_status i40e_pf_reset(struct i40e_hw *hw); void i40e_clear_hw(struct i40e_hw *hw); void i40e_clear_pxe_mode(struct i40e_hw *hw); i40e_status i40e_get_link_status(struct i40e_hw *hw, bool *link_up); +i40e_status i40e_update_link_info(struct i40e_hw *hw); i40e_status i40e_get_mac_addr(struct i40e_hw *hw, u8 *mac_addr); i40e_status i40e_read_bw_from_alt_ram(struct i40e_hw *hw, u32 *max_bw, u32 *min_bw, bool *min_valid, diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 552c84e2e05d..565ca7c835bc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -674,8 +674,8 @@ void i40e_ptp_init(struct i40e_pf *pf) struct timespec64 ts; u32 regval; - dev_info(&pf->pdev->dev, "%s: added PHC on %s\n", __func__, - netdev->name); + if (pf->hw.debug_mask & I40E_DEBUG_LAN) + dev_info(&pf->pdev->dev, "PHC enabled\n"); pf->flags |= I40E_FLAG_PTP; /* Ensure the clocks are running. */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 01e5ece8046d..006f0fb4720c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -815,6 +815,8 @@ void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) * i40e_set_new_dynamic_itr - Find new ITR level * @rc: structure containing ring performance data * + * Returns true if ITR changed, false if not + * * Stores a new ITR value based on packets and byte counts during * the last interrupt. The advantage of per interrupt computation * is faster updates and more accurate ITR for the current traffic @@ -823,21 +825,32 @@ void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) * testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) +static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) { enum i40e_latency_range new_latency_range = rc->latency_range; + struct i40e_q_vector *qv = rc->ring->q_vector; u32 new_itr = rc->itr; int bytes_per_int; + int usecs; if (rc->total_packets == 0 || !rc->itr) - return; + return false; /* simple throttlerate management - * 0-10MB/s lowest (100000 ints/s) + * 0-10MB/s lowest (50000 ints/s) * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (8000 ints/s) + * 20-1249MB/s bulk (18000 ints/s) + * > 40000 Rx packets per second (8000 ints/s) + * + * The math works out because the divisor is in 10^(-6) which + * turns the bytes/us input value into MB/s values, but + * make sure to use usecs, as the register values written + * are in 2 usec increments in the ITR registers, and make sure + * to use the smoothed values that the countdown timer gives us. */ - bytes_per_int = rc->total_bytes / rc->itr; + usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; + bytes_per_int = rc->total_bytes / usecs; + switch (new_latency_range) { case I40E_LOWEST_LATENCY: if (bytes_per_int > 10) @@ -850,35 +863,52 @@ static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) new_latency_range = I40E_LOWEST_LATENCY; break; case I40E_BULK_LATENCY: - if (bytes_per_int <= 20) - new_latency_range = I40E_LOW_LATENCY; - break; + case I40E_ULTRA_LATENCY: default: if (bytes_per_int <= 20) new_latency_range = I40E_LOW_LATENCY; break; } + + /* this is to adjust RX more aggressively when streaming small + * packets. The value of 40000 was picked as it is just beyond + * what the hardware can receive per second if in low latency + * mode. + */ +#define RX_ULTRA_PACKET_RATE 40000 + + if ((((rc->total_packets * 1000000) / usecs) > RX_ULTRA_PACKET_RATE) && + (&qv->rx == rc)) + new_latency_range = I40E_ULTRA_LATENCY; + rc->latency_range = new_latency_range; switch (new_latency_range) { case I40E_LOWEST_LATENCY: - new_itr = I40E_ITR_100K; + new_itr = I40E_ITR_50K; break; case I40E_LOW_LATENCY: new_itr = I40E_ITR_20K; break; case I40E_BULK_LATENCY: + new_itr = I40E_ITR_18K; + break; + case I40E_ULTRA_LATENCY: new_itr = I40E_ITR_8K; break; default: break; } - if (new_itr != rc->itr) - rc->itr = new_itr; - rc->total_bytes = 0; rc->total_packets = 0; + + if (new_itr != rc->itr) { + rc->itr = new_itr; + return true; + } + + return false; } /** @@ -1268,16 +1298,11 @@ static void i40e_receive_skb(struct i40e_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) { struct i40e_q_vector *q_vector = rx_ring->q_vector; - struct i40e_vsi *vsi = rx_ring->vsi; - u64 flags = vsi->back->flags; if (vlan_tag & VLAN_VID_MASK) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); - if (flags & I40E_FLAG_IN_NETPOLL) - netif_rx(skb); - else - napi_gro_receive(&q_vector->napi, skb); + napi_gro_receive(&q_vector->napi, skb); } /** @@ -1752,6 +1777,21 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget) return total_rx_packets; } +static u32 i40e_buildreg_itr(const int type, const u16 itr) +{ + u32 val; + + val = I40E_PFINT_DYN_CTLN_INTENA_MASK | + I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | + (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | + (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT); + + return val; +} + +/* a small macro to shorten up some long lines */ +#define INTREG I40E_PFINT_DYN_CTLN + /** * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt * @vsi: the VSI we care about @@ -1762,54 +1802,69 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { struct i40e_hw *hw = &vsi->back->hw; - u16 old_itr; + bool rx = false, tx = false; + u32 rxval, txval; int vector; - u32 val; vector = (q_vector->v_idx + vsi->base_vector); + + /* avoid dynamic calculation if in countdown mode OR if + * all dynamic is disabled + */ + rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0); + + if (q_vector->itr_countdown > 0 || + (!ITR_IS_DYNAMIC(vsi->rx_itr_setting) && + !ITR_IS_DYNAMIC(vsi->tx_itr_setting))) { + goto enable_int; + } + if (ITR_IS_DYNAMIC(vsi->rx_itr_setting)) { - old_itr = q_vector->rx.itr; - i40e_set_new_dynamic_itr(&q_vector->rx); - if (old_itr != q_vector->rx.itr) { - val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | - (I40E_RX_ITR << - I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | - (q_vector->rx.itr << - I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT); - } else { - val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | - (I40E_ITR_NONE << - I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT); - } - if (!test_bit(__I40E_DOWN, &vsi->state)) - wr32(hw, I40E_PFINT_DYN_CTLN(vector - 1), val); - } else { - i40e_irq_dynamic_enable(vsi, q_vector->v_idx); + rx = i40e_set_new_dynamic_itr(&q_vector->rx); + rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr); } + if (ITR_IS_DYNAMIC(vsi->tx_itr_setting)) { - old_itr = q_vector->tx.itr; - i40e_set_new_dynamic_itr(&q_vector->tx); - if (old_itr != q_vector->tx.itr) { - val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | - (I40E_TX_ITR << - I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | - (q_vector->tx.itr << - I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT); - } else { - val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | - (I40E_ITR_NONE << - I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT); - } - if (!test_bit(__I40E_DOWN, &vsi->state)) - wr32(hw, I40E_PFINT_DYN_CTLN(q_vector->v_idx + - vsi->base_vector - 1), val); - } else { - i40e_irq_dynamic_enable(vsi, q_vector->v_idx); + tx = i40e_set_new_dynamic_itr(&q_vector->tx); + txval = i40e_buildreg_itr(I40E_TX_ITR, q_vector->tx.itr); + } + + if (rx || tx) { + /* get the higher of the two ITR adjustments and + * use the same value for both ITR registers + * when in adaptive mode (Rx and/or Tx) + */ + u16 itr = max(q_vector->tx.itr, q_vector->rx.itr); + + q_vector->tx.itr = q_vector->rx.itr = itr; + txval = i40e_buildreg_itr(I40E_TX_ITR, itr); + tx = true; + rxval = i40e_buildreg_itr(I40E_RX_ITR, itr); + rx = true; } + + /* only need to enable the interrupt once, but need + * to possibly update both ITR values + */ + if (rx) { + /* set the INTENA_MSK_MASK so that this first write + * won't actually enable the interrupt, instead just + * updating the ITR (it's bit 31 PF and VF) + */ + rxval |= BIT(31); + /* don't check _DOWN because interrupt isn't being enabled */ + wr32(hw, INTREG(vector - 1), rxval); + } + +enable_int: + if (!test_bit(__I40E_DOWN, &vsi->state)) + wr32(hw, INTREG(vector - 1), txval); + + if (q_vector->itr_countdown) + q_vector->itr_countdown--; + else + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } /** @@ -1830,7 +1885,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) bool clean_complete = true; bool arm_wb = false; int budget_per_ring; - int cleaned; + int work_done = 0; if (test_bit(__I40E_DOWN, &vsi->state)) { napi_complete(napi); @@ -1846,22 +1901,31 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) ring->arm_wb = false; } + /* Handle case where we are called by netpoll with a budget of 0 */ + if (budget <= 0) + goto tx_only; + /* We attempt to distribute budget to each Rx queue fairly, but don't * allow the budget to go below 1 because that would exit polling early. */ budget_per_ring = max(budget/q_vector->num_ringpairs, 1); i40e_for_each_ring(ring, q_vector->rx) { + int cleaned; + if (ring_is_ps_enabled(ring)) cleaned = i40e_clean_rx_irq_ps(ring, budget_per_ring); else cleaned = i40e_clean_rx_irq_1buf(ring, budget_per_ring); + + work_done += cleaned; /* if we didn't clean as many as budgeted, we must be done */ clean_complete &= (budget_per_ring != cleaned); } /* If work not completed, return budget and polling will return */ if (!clean_complete) { +tx_only: if (arm_wb) i40e_force_wb(vsi, q_vector); return budget; @@ -1871,7 +1935,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) q_vector->arm_wb_state = false; /* Work is done so exit the polling mode and re-enable the interrupt */ - napi_complete(napi); + napi_complete_done(napi, work_done); if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) { i40e_update_enable_itr(vsi, q_vector); } else { /* Legacy mode */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 75cecfa6e338..6779fb771d6a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -32,11 +32,14 @@ #define I40E_MAX_ITR 0x0FF0 /* reg uses 2 usec resolution */ #define I40E_MIN_ITR 0x0001 /* reg uses 2 usec resolution */ #define I40E_ITR_100K 0x0005 +#define I40E_ITR_50K 0x000A #define I40E_ITR_20K 0x0019 +#define I40E_ITR_18K 0x001B #define I40E_ITR_8K 0x003E #define I40E_ITR_4K 0x007A -#define I40E_ITR_RX_DEF I40E_ITR_8K -#define I40E_ITR_TX_DEF I40E_ITR_4K +#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ +#define I40E_ITR_RX_DEF I40E_ITR_20K +#define I40E_ITR_TX_DEF I40E_ITR_20K #define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ #define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ @@ -44,6 +47,15 @@ #define ITR_TO_REG(setting) ((setting & ~I40E_ITR_DYNAMIC) >> 1) #define ITR_IS_DYNAMIC(setting) (!!(setting & I40E_ITR_DYNAMIC)) #define ITR_REG_TO_USEC(itr_reg) (itr_reg << 1) +/* 0x40 is the enable bit for interrupt rate limiting, and must be set if + * the value of the rate limit is non-zero + */ +#define INTRL_ENA BIT(6) +#define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) +#define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0) +#define I40E_INTRL_8K 125 /* 8000 ints/sec */ +#define I40E_INTRL_62K 16 /* 62500 ints/sec */ +#define I40E_INTRL_83K 12 /* 83333 ints/sec */ #define I40E_QUEUE_END_OF_LIST 0x7FF @@ -286,6 +298,7 @@ enum i40e_latency_range { I40E_LOWEST_LATENCY = 0, I40E_LOW_LATENCY = 1, I40E_BULK_LATENCY = 2, + I40E_ULTRA_LATENCY = 3, }; struct i40e_ring_container { diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index d1ec5a4326cf..dd2da356d9a1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -33,31 +33,7 @@ #include "i40e_adminq.h" #include "i40e_hmc.h" #include "i40e_lan_hmc.h" - -/* Device IDs */ -#define I40E_DEV_ID_SFP_XL710 0x1572 -#define I40E_DEV_ID_QEMU 0x1574 -#define I40E_DEV_ID_KX_A 0x157F -#define I40E_DEV_ID_KX_B 0x1580 -#define I40E_DEV_ID_KX_C 0x1581 -#define I40E_DEV_ID_QSFP_A 0x1583 -#define I40E_DEV_ID_QSFP_B 0x1584 -#define I40E_DEV_ID_QSFP_C 0x1585 -#define I40E_DEV_ID_10G_BASE_T 0x1586 -#define I40E_DEV_ID_20G_KR2 0x1587 -#define I40E_DEV_ID_20G_KR2_A 0x1588 -#define I40E_DEV_ID_10G_BASE_T4 0x1589 -#define I40E_DEV_ID_VF 0x154C -#define I40E_DEV_ID_VF_HV 0x1571 -#define I40E_DEV_ID_SFP_X722 0x37D0 -#define I40E_DEV_ID_1G_BASE_T_X722 0x37D1 -#define I40E_DEV_ID_10G_BASE_T_X722 0x37D2 -#define I40E_DEV_ID_X722_VF 0x37CD -#define I40E_DEV_ID_X722_VF_HV 0x37D9 - -#define i40e_is_40G_device(d) ((d) == I40E_DEV_ID_QSFP_A || \ - (d) == I40E_DEV_ID_QSFP_B || \ - (d) == I40E_DEV_ID_QSFP_C) +#include "i40e_devids.h" /* I40E_MASK is a macro used on 32 bit registers */ #define I40E_MASK(mask, shift) (mask << shift) @@ -191,16 +167,65 @@ struct i40e_link_status { bool crc_enable; u8 pacing; u8 requested_speeds; + u8 module_type[3]; + /* 1st byte: module identifier */ +#define I40E_MODULE_TYPE_SFP 0x03 +#define I40E_MODULE_TYPE_QSFP 0x0D + /* 2nd byte: ethernet compliance codes for 10/40G */ +#define I40E_MODULE_TYPE_40G_ACTIVE 0x01 +#define I40E_MODULE_TYPE_40G_LR4 0x02 +#define I40E_MODULE_TYPE_40G_SR4 0x04 +#define I40E_MODULE_TYPE_40G_CR4 0x08 +#define I40E_MODULE_TYPE_10G_BASE_SR 0x10 +#define I40E_MODULE_TYPE_10G_BASE_LR 0x20 +#define I40E_MODULE_TYPE_10G_BASE_LRM 0x40 +#define I40E_MODULE_TYPE_10G_BASE_ER 0x80 + /* 3rd byte: ethernet compliance codes for 1G */ +#define I40E_MODULE_TYPE_1000BASE_SX 0x01 +#define I40E_MODULE_TYPE_1000BASE_LX 0x02 +#define I40E_MODULE_TYPE_1000BASE_CX 0x04 +#define I40E_MODULE_TYPE_1000BASE_T 0x08 +}; + +enum i40e_aq_capabilities_phy_type { + I40E_CAP_PHY_TYPE_SGMII = BIT(I40E_PHY_TYPE_SGMII), + I40E_CAP_PHY_TYPE_1000BASE_KX = BIT(I40E_PHY_TYPE_1000BASE_KX), + I40E_CAP_PHY_TYPE_10GBASE_KX4 = BIT(I40E_PHY_TYPE_10GBASE_KX4), + I40E_CAP_PHY_TYPE_10GBASE_KR = BIT(I40E_PHY_TYPE_10GBASE_KR), + I40E_CAP_PHY_TYPE_40GBASE_KR4 = BIT(I40E_PHY_TYPE_40GBASE_KR4), + I40E_CAP_PHY_TYPE_XAUI = BIT(I40E_PHY_TYPE_XAUI), + I40E_CAP_PHY_TYPE_XFI = BIT(I40E_PHY_TYPE_XFI), + I40E_CAP_PHY_TYPE_SFI = BIT(I40E_PHY_TYPE_SFI), + I40E_CAP_PHY_TYPE_XLAUI = BIT(I40E_PHY_TYPE_XLAUI), + I40E_CAP_PHY_TYPE_XLPPI = BIT(I40E_PHY_TYPE_XLPPI), + I40E_CAP_PHY_TYPE_40GBASE_CR4_CU = BIT(I40E_PHY_TYPE_40GBASE_CR4_CU), + I40E_CAP_PHY_TYPE_10GBASE_CR1_CU = BIT(I40E_PHY_TYPE_10GBASE_CR1_CU), + I40E_CAP_PHY_TYPE_10GBASE_AOC = BIT(I40E_PHY_TYPE_10GBASE_AOC), + I40E_CAP_PHY_TYPE_40GBASE_AOC = BIT(I40E_PHY_TYPE_40GBASE_AOC), + I40E_CAP_PHY_TYPE_100BASE_TX = BIT(I40E_PHY_TYPE_100BASE_TX), + I40E_CAP_PHY_TYPE_1000BASE_T = BIT(I40E_PHY_TYPE_1000BASE_T), + I40E_CAP_PHY_TYPE_10GBASE_T = BIT(I40E_PHY_TYPE_10GBASE_T), + I40E_CAP_PHY_TYPE_10GBASE_SR = BIT(I40E_PHY_TYPE_10GBASE_SR), + I40E_CAP_PHY_TYPE_10GBASE_LR = BIT(I40E_PHY_TYPE_10GBASE_LR), + I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU = BIT(I40E_PHY_TYPE_10GBASE_SFPP_CU), + I40E_CAP_PHY_TYPE_10GBASE_CR1 = BIT(I40E_PHY_TYPE_10GBASE_CR1), + I40E_CAP_PHY_TYPE_40GBASE_CR4 = BIT(I40E_PHY_TYPE_40GBASE_CR4), + I40E_CAP_PHY_TYPE_40GBASE_SR4 = BIT(I40E_PHY_TYPE_40GBASE_SR4), + I40E_CAP_PHY_TYPE_40GBASE_LR4 = BIT(I40E_PHY_TYPE_40GBASE_LR4), + I40E_CAP_PHY_TYPE_1000BASE_SX = BIT(I40E_PHY_TYPE_1000BASE_SX), + I40E_CAP_PHY_TYPE_1000BASE_LX = BIT(I40E_PHY_TYPE_1000BASE_LX), + I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL = + BIT(I40E_PHY_TYPE_1000BASE_T_OPTICAL), + I40E_CAP_PHY_TYPE_20GBASE_KR2 = BIT(I40E_PHY_TYPE_20GBASE_KR2) }; struct i40e_phy_info { struct i40e_link_status link_info; struct i40e_link_status link_info_old; - u32 autoneg_advertised; - u32 phy_id; - u32 module_type; bool get_link_info; enum i40e_media_type media_type; + /* all the phy types the NVM is capable of */ + enum i40e_aq_capabilities_phy_type phy_types; }; #define I40E_HW_CAP_MAX_GPIO 30 @@ -289,6 +314,7 @@ struct i40e_nvm_info { bool blank_nvm_mode; /* is NVM empty (no FW present)*/ u16 version; /* NVM package version */ u32 eetrack; /* NVM data version */ + u32 oem_ver; /* OEM version info */ }; /* definitions used in NVM update support */ @@ -417,6 +443,8 @@ struct i40e_fc_info { #define I40E_APP_PROTOID_FIP 0x8914 #define I40E_APP_SEL_ETHTYPE 0x1 #define I40E_APP_SEL_TCPIP 0x2 +#define I40E_CEE_APP_SEL_ETHTYPE 0x0 +#define I40E_CEE_APP_SEL_TCPIP 0x1 /* CEE or IEEE 802.1Qaz ETS Configuration data */ struct i40e_dcb_ets_config { @@ -447,6 +475,8 @@ struct i40e_dcbx_config { u8 dcbx_mode; #define I40E_DCBX_MODE_CEE 0x1 #define I40E_DCBX_MODE_IEEE 0x2 + u8 app_mode; +#define I40E_DCBX_APPS_NON_WILLING 0x1 u32 numapps; u32 tlv_status; /* CEE mode TLV status */ struct i40e_dcb_ets_config etscfg; @@ -514,6 +544,9 @@ struct i40e_hw { struct i40e_dcbx_config remote_dcbx_config; /* Peer Cfg */ struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */ +#define I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE BIT_ULL(0) + u64 flags; + /* debug mask */ u32 debug_mask; char err_str[16]; @@ -1035,8 +1068,8 @@ enum i40e_filter_program_desc_fd_status { }; #define I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT 23 -#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK \ - BIT_ULL(I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT) +#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK (0x1FFUL << \ + I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT) #define I40E_TXD_FLTR_QW1_CMD_SHIFT 4 #define I40E_TXD_FLTR_QW1_CMD_MASK (0xFFFFULL << \ @@ -1204,6 +1237,8 @@ struct i40e_hw_port_stats { #define I40E_SR_EMP_MODULE_PTR 0x0F #define I40E_SR_PBA_FLAGS 0x15 #define I40E_SR_PBA_BLOCK_PTR 0x16 +#define I40E_SR_BOOT_CONFIG_PTR 0x17 +#define I40E_NVM_OEM_VER_OFF 0x83 #define I40E_SR_NVM_DEV_STARTER_VERSION 0x18 #define I40E_SR_NVM_WAKE_ON_LAN 0x19 #define I40E_SR_ALTERNATE_SAN_MAC_ADDRESS_PTR 0x27 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h index 95d0f8c5d484..ae879826084b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h @@ -150,6 +150,7 @@ struct i40e_virtchnl_vsi_resource { #define I40E_VIRTCHNL_VF_OFFLOAD_FCOE 0x00000004 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010 +#define I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 #define I40E_VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000 #define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index ee747dc5d617..b2d95ee7ec69 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -547,6 +547,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) */ if (vf->port_vlan_id) i40e_vsi_add_pvid(vsi, vf->port_vlan_id); + + spin_lock_bh(&vsi->mac_filter_list_lock); f = i40e_add_filter(vsi, vf->default_lan_addr.addr, vf->port_vlan_id ? vf->port_vlan_id : -1, true, false); @@ -559,6 +561,7 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) if (!f) dev_info(&pf->pdev->dev, "Could not allocate VF broadcast filter\n"); + spin_unlock_bh(&vsi->mac_filter_list_lock); } /* program mac filter */ @@ -703,6 +706,7 @@ static void i40e_free_vf_res(struct i40e_vf *vf) */ vf->num_queue_pairs = 0; vf->vf_states = 0; + clear_bit(I40E_VF_STAT_INIT, &vf->vf_states); } /** @@ -841,11 +845,11 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) complete_reset: /* reallocate VF resources to reset the VSI state */ i40e_free_vf_res(vf); - i40e_alloc_vf_res(vf); - i40e_enable_vf_mappings(vf); - set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states); - clear_bit(I40E_VF_STAT_DISABLED, &vf->vf_states); - + if (!i40e_alloc_vf_res(vf)) { + i40e_enable_vf_mappings(vf); + set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states); + clear_bit(I40E_VF_STAT_DISABLED, &vf->vf_states); + } /* tell the VF the reset is done */ wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE); i40e_flush(hw); @@ -964,8 +968,6 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs) /* VF resources get allocated during reset */ i40e_reset_vf(&vfs[i], false); - /* enable VF vplan_qtable mappings */ - i40e_enable_vf_mappings(&vfs[i]); } pf->num_alloc_vfs = num_alloc_vfs; @@ -1103,6 +1105,8 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, } } else { vf->num_valid_msgs++; + /* reset the invalid counter, if a valid message is received. */ + vf->num_invalid_msgs = 0; } aq_ret = i40e_aq_send_msg_to_vf(hw, abs_vf_id, v_opcode, v_retval, @@ -1204,6 +1208,10 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) } else { vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG; } + + if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING) + vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING; + vfres->num_vsis = num_vsis; vfres->num_queue_pairs = vf->num_queue_pairs; vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf; @@ -1593,6 +1601,11 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) } vsi = pf->vsi[vf->lan_vsi_idx]; + /* Lock once, because all function inside for loop accesses VSI's + * MAC filter list which needs to be protected using same lock. + */ + spin_lock_bh(&vsi->mac_filter_list_lock); + /* add new addresses to the list */ for (i = 0; i < al->num_elements; i++) { struct i40e_mac_filter *f; @@ -1611,9 +1624,11 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) dev_err(&pf->pdev->dev, "Unable to add VF MAC filter\n"); ret = I40E_ERR_PARAM; + spin_unlock_bh(&vsi->mac_filter_list_lock); goto error_param; } } + spin_unlock_bh(&vsi->mac_filter_list_lock); /* program the updated filter list */ if (i40e_sync_vsi_filters(vsi, false)) @@ -1661,10 +1676,12 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) } vsi = pf->vsi[vf->lan_vsi_idx]; + spin_lock_bh(&vsi->mac_filter_list_lock); /* delete addresses from the list */ for (i = 0; i < al->num_elements; i++) i40e_del_filter(vsi, al->list[i].addr, I40E_VLAN_ANY, true, false); + spin_unlock_bh(&vsi->mac_filter_list_lock); /* program the updated filter list */ if (i40e_sync_vsi_filters(vsi, false)) @@ -2061,6 +2078,11 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto error_param; } + /* Lock once because below invoked function add/del_filter requires + * mac_filter_list_lock to be held + */ + spin_lock_bh(&vsi->mac_filter_list_lock); + /* delete the temporary mac address */ i40e_del_filter(vsi, vf->default_lan_addr.addr, vf->port_vlan_id ? vf->port_vlan_id : -1, @@ -2072,6 +2094,8 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) list_for_each_entry(f, &vsi->mac_filter_list, list) i40e_del_filter(vsi, f->macaddr, f->vlan, true, false); + spin_unlock_bh(&vsi->mac_filter_list_lock); + dev_info(&pf->pdev->dev, "Setting MAC %pM on VF %d\n", mac, vf_id); /* program mac filter */ if (i40e_sync_vsi_filters(vsi, false)) { @@ -2104,6 +2128,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, u16 vlanprio = vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT); struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; + bool is_vsi_in_vlan = false; struct i40e_vsi *vsi; struct i40e_vf *vf; int ret = 0; @@ -2133,7 +2158,11 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, /* duplicate request, so just return success */ goto error_pvid; - if (le16_to_cpu(vsi->info.pvid) == 0 && i40e_is_vsi_in_vlan(vsi)) { + spin_lock_bh(&vsi->mac_filter_list_lock); + is_vsi_in_vlan = i40e_is_vsi_in_vlan(vsi); + spin_unlock_bh(&vsi->mac_filter_list_lock); + + if (le16_to_cpu(vsi->info.pvid) == 0 && is_vsi_in_vlan) { dev_err(&pf->pdev->dev, "VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n", vf_id); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 736f6f08b4f2..da44995def42 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -29,8 +29,6 @@ #include "i40e.h" -#define I40E_MAX_MACVLAN_FILTERS 256 -#define I40E_MAX_VLAN_FILTERS 256 #define I40E_MAX_VLANID 4095 #define I40E_VIRTCHNL_SUPPORTED_QTYPES 2 @@ -98,7 +96,8 @@ struct i40e_vf { u8 num_queue_pairs; /* num of qps assigned to VF vsis */ u64 num_mdd_events; /* num of mdd events detected */ - u64 num_invalid_msgs; /* num of malformed or invalid msgs detected */ + /* num of continuous malformed or invalid msgs detected */ + u64 num_invalid_msgs; u64 num_valid_msgs; /* num of valid msgs detected */ unsigned long vf_caps; /* vf's adv. capabilities */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index 3eba36913c1d..fd123ca60761 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -373,7 +373,6 @@ static i40e_status i40e_init_asq(struct i40e_hw *hw) hw->aq.asq.next_to_use = 0; hw->aq.asq.next_to_clean = 0; - hw->aq.asq.count = hw->aq.num_asq_entries; /* allocate the ring memory */ ret_code = i40e_alloc_adminq_asq_ring(hw); @@ -391,6 +390,7 @@ static i40e_status i40e_init_asq(struct i40e_hw *hw) goto init_adminq_free_rings; /* success! */ + hw->aq.asq.count = hw->aq.num_asq_entries; goto init_adminq_exit; init_adminq_free_rings: @@ -432,7 +432,6 @@ static i40e_status i40e_init_arq(struct i40e_hw *hw) hw->aq.arq.next_to_use = 0; hw->aq.arq.next_to_clean = 0; - hw->aq.arq.count = hw->aq.num_arq_entries; /* allocate the ring memory */ ret_code = i40e_alloc_adminq_arq_ring(hw); @@ -450,6 +449,7 @@ static i40e_status i40e_init_arq(struct i40e_hw *hw) goto init_adminq_free_rings; /* success! */ + hw->aq.arq.count = hw->aq.num_arq_entries; goto init_adminq_exit; init_adminq_free_rings: diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index c8022092d369..fcb9ef34cc7a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -1719,11 +1719,13 @@ struct i40e_aqc_get_link_status { u8 phy_type; /* i40e_aq_phy_type */ u8 link_speed; /* i40e_aq_link_speed */ u8 link_info; -#define I40E_AQ_LINK_UP 0x01 +#define I40E_AQ_LINK_UP 0x01 /* obsolete */ +#define I40E_AQ_LINK_UP_FUNCTION 0x01 #define I40E_AQ_LINK_FAULT 0x02 #define I40E_AQ_LINK_FAULT_TX 0x04 #define I40E_AQ_LINK_FAULT_RX 0x08 #define I40E_AQ_LINK_FAULT_REMOTE 0x10 +#define I40E_AQ_LINK_UP_PORT 0x20 #define I40E_AQ_MEDIA_AVAILABLE 0x40 #define I40E_AQ_SIGNAL_DETECT 0x80 u8 an_info; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index b98b642b897a..a4c5a49ddbcf 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -87,7 +87,7 @@ i40e_status i40e_set_mac_type(struct i40e_hw *hw) * @hw: pointer to the HW structure * @aq_err: the AQ error code to convert **/ -char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err) +const char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err) { switch (aq_err) { case I40E_AQ_RC_OK: @@ -147,7 +147,7 @@ char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err) * @hw: pointer to the HW structure * @stat_err: the status error code to convert **/ -char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err) +const char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err) { switch (stat_err) { case 0: @@ -443,9 +443,6 @@ static i40e_status i40e_aq_get_set_rss_lut(struct i40e_hw *hw, I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); - cmd_resp->addr_high = cpu_to_le32(high_16_bits((u64)lut)); - cmd_resp->addr_low = cpu_to_le32(lower_32_bits((u64)lut)); - status = i40evf_asq_send_command(hw, &desc, lut, lut_size, NULL); return status; @@ -520,8 +517,6 @@ static i40e_status i40e_aq_get_set_rss_key(struct i40e_hw *hw, I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) & I40E_AQC_SET_RSS_KEY_VSI_ID_MASK)); cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID); - cmd_resp->addr_high = cpu_to_le32(high_16_bits((u64)key)); - cmd_resp->addr_low = cpu_to_le32(lower_32_bits((u64)key)); status = i40evf_asq_send_command(hw, &desc, key, key_size, NULL); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_devids.h b/drivers/net/ethernet/intel/i40evf/i40e_devids.h new file mode 100644 index 000000000000..e6a39c9862e8 --- /dev/null +++ b/drivers/net/ethernet/intel/i40evf/i40e_devids.h @@ -0,0 +1,55 @@ +/******************************************************************************* + * + * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver + * Copyright(c) 2013 - 2015 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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/>. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * e1000-devel Mailing List <[email protected]> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + ******************************************************************************/ + +#ifndef _I40E_DEVIDS_H_ +#define _I40E_DEVIDS_H_ + +/* Device IDs */ +#define I40E_DEV_ID_SFP_XL710 0x1572 +#define I40E_DEV_ID_QEMU 0x1574 +#define I40E_DEV_ID_KX_A 0x157F +#define I40E_DEV_ID_KX_B 0x1580 +#define I40E_DEV_ID_KX_C 0x1581 +#define I40E_DEV_ID_QSFP_A 0x1583 +#define I40E_DEV_ID_QSFP_B 0x1584 +#define I40E_DEV_ID_QSFP_C 0x1585 +#define I40E_DEV_ID_10G_BASE_T 0x1586 +#define I40E_DEV_ID_20G_KR2 0x1587 +#define I40E_DEV_ID_20G_KR2_A 0x1588 +#define I40E_DEV_ID_10G_BASE_T4 0x1589 +#define I40E_DEV_ID_VF 0x154C +#define I40E_DEV_ID_VF_HV 0x1571 +#define I40E_DEV_ID_SFP_X722 0x37D0 +#define I40E_DEV_ID_1G_BASE_T_X722 0x37D1 +#define I40E_DEV_ID_10G_BASE_T_X722 0x37D2 +#define I40E_DEV_ID_X722_VF 0x37CD +#define I40E_DEV_ID_X722_VF_HV 0x37D9 + +#define i40e_is_40G_device(d) ((d) == I40E_DEV_ID_QSFP_A || \ + (d) == I40E_DEV_ID_QSFP_B || \ + (d) == I40E_DEV_ID_QSFP_C) + +#endif /* _I40E_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h index 55ae4b0f8192..8ed0edfbc125 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h @@ -60,8 +60,8 @@ void i40e_idle_aq(struct i40e_hw *hw); void i40evf_resume_aq(struct i40e_hw *hw); bool i40evf_check_asq_alive(struct i40e_hw *hw); i40e_status i40evf_aq_queue_shutdown(struct i40e_hw *hw, bool unloading); -char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err); -char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err); +const char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err); +const char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err); i40e_status i40evf_aq_get_rss_lut(struct i40e_hw *hw, u16 seid, bool pf_lut, u8 *lut, u16 lut_size); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 0e71eb4633d5..47e9a90d6b10 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -318,6 +318,8 @@ static void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector * i40e_set_new_dynamic_itr - Find new ITR level * @rc: structure containing ring performance data * + * Returns true if ITR changed, false if not + * * Stores a new ITR value based on packets and byte counts during * the last interrupt. The advantage of per interrupt computation * is faster updates and more accurate ITR for the current traffic @@ -326,21 +328,32 @@ static void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector * testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) +static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) { enum i40e_latency_range new_latency_range = rc->latency_range; + struct i40e_q_vector *qv = rc->ring->q_vector; u32 new_itr = rc->itr; int bytes_per_int; + int usecs; if (rc->total_packets == 0 || !rc->itr) - return; + return false; /* simple throttlerate management - * 0-10MB/s lowest (100000 ints/s) + * 0-10MB/s lowest (50000 ints/s) * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (8000 ints/s) + * 20-1249MB/s bulk (18000 ints/s) + * > 40000 Rx packets per second (8000 ints/s) + * + * The math works out because the divisor is in 10^(-6) which + * turns the bytes/us input value into MB/s values, but + * make sure to use usecs, as the register values written + * are in 2 usec increments in the ITR registers, and make sure + * to use the smoothed values that the countdown timer gives us. */ - bytes_per_int = rc->total_bytes / rc->itr; + usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; + bytes_per_int = rc->total_bytes / usecs; + switch (new_latency_range) { case I40E_LOWEST_LATENCY: if (bytes_per_int > 10) @@ -353,35 +366,52 @@ static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) new_latency_range = I40E_LOWEST_LATENCY; break; case I40E_BULK_LATENCY: - if (bytes_per_int <= 20) - new_latency_range = I40E_LOW_LATENCY; - break; + case I40E_ULTRA_LATENCY: default: if (bytes_per_int <= 20) new_latency_range = I40E_LOW_LATENCY; break; } + + /* this is to adjust RX more aggressively when streaming small + * packets. The value of 40000 was picked as it is just beyond + * what the hardware can receive per second if in low latency + * mode. + */ +#define RX_ULTRA_PACKET_RATE 40000 + + if ((((rc->total_packets * 1000000) / usecs) > RX_ULTRA_PACKET_RATE) && + (&qv->rx == rc)) + new_latency_range = I40E_ULTRA_LATENCY; + rc->latency_range = new_latency_range; switch (new_latency_range) { case I40E_LOWEST_LATENCY: - new_itr = I40E_ITR_100K; + new_itr = I40E_ITR_50K; break; case I40E_LOW_LATENCY: new_itr = I40E_ITR_20K; break; case I40E_BULK_LATENCY: + new_itr = I40E_ITR_18K; + break; + case I40E_ULTRA_LATENCY: new_itr = I40E_ITR_8K; break; default: break; } - if (new_itr != rc->itr) - rc->itr = new_itr; - rc->total_bytes = 0; rc->total_packets = 0; + + if (new_itr != rc->itr) { + rc->itr = new_itr; + return true; + } + + return false; } /* @@ -742,16 +772,11 @@ static void i40e_receive_skb(struct i40e_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) { struct i40e_q_vector *q_vector = rx_ring->q_vector; - struct i40e_vsi *vsi = rx_ring->vsi; - u64 flags = vsi->back->flags; if (vlan_tag & VLAN_VID_MASK) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); - if (flags & I40E_FLAG_IN_NETPOLL) - netif_rx(skb); - else - napi_gro_receive(&q_vector->napi, skb); + napi_gro_receive(&q_vector->napi, skb); } /** @@ -1192,6 +1217,21 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget) return total_rx_packets; } +static u32 i40e_buildreg_itr(const int type, const u16 itr) +{ + u32 val; + + val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | + I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | + (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | + (itr << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT); + + return val; +} + +/* a small macro to shorten up some long lines */ +#define INTREG I40E_VFINT_DYN_CTLN1 + /** * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt * @vsi: the VSI we care about @@ -1202,55 +1242,67 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { struct i40e_hw *hw = &vsi->back->hw; - u16 old_itr; + bool rx = false, tx = false; + u32 rxval, txval; int vector; - u32 val; vector = (q_vector->v_idx + vsi->base_vector); + + /* avoid dynamic calculation if in countdown mode OR if + * all dynamic is disabled + */ + rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0); + + if (q_vector->itr_countdown > 0 || + (!ITR_IS_DYNAMIC(vsi->rx_itr_setting) && + !ITR_IS_DYNAMIC(vsi->tx_itr_setting))) { + goto enable_int; + } + if (ITR_IS_DYNAMIC(vsi->rx_itr_setting)) { - old_itr = q_vector->rx.itr; - i40e_set_new_dynamic_itr(&q_vector->rx); - if (old_itr != q_vector->rx.itr) { - val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | - (I40E_RX_ITR << - I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | - (q_vector->rx.itr << - I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT); - } else { - val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | - (I40E_ITR_NONE << - I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT); - } - if (!test_bit(__I40E_DOWN, &vsi->state)) - wr32(hw, I40E_VFINT_DYN_CTLN1(vector - 1), val); - } else { - i40evf_irq_enable_queues(vsi->back, 1 - << q_vector->v_idx); + rx = i40e_set_new_dynamic_itr(&q_vector->rx); + rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr); } if (ITR_IS_DYNAMIC(vsi->tx_itr_setting)) { - old_itr = q_vector->tx.itr; - i40e_set_new_dynamic_itr(&q_vector->tx); - if (old_itr != q_vector->tx.itr) { - val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | - (I40E_TX_ITR << - I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | - (q_vector->tx.itr << - I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT); + tx = i40e_set_new_dynamic_itr(&q_vector->tx); + txval = i40e_buildreg_itr(I40E_TX_ITR, q_vector->tx.itr); + } + if (rx || tx) { + /* get the higher of the two ITR adjustments and + * use the same value for both ITR registers + * when in adaptive mode (Rx and/or Tx) + */ + u16 itr = max(q_vector->tx.itr, q_vector->rx.itr); - } else { - val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | - (I40E_ITR_NONE << - I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT); - } - if (!test_bit(__I40E_DOWN, &vsi->state)) - wr32(hw, I40E_VFINT_DYN_CTLN1(vector - 1), val); - } else { - i40evf_irq_enable_queues(vsi->back, BIT(q_vector->v_idx)); + q_vector->tx.itr = q_vector->rx.itr = itr; + txval = i40e_buildreg_itr(I40E_TX_ITR, itr); + tx = true; + rxval = i40e_buildreg_itr(I40E_RX_ITR, itr); + rx = true; + } + + /* only need to enable the interrupt once, but need + * to possibly update both ITR values + */ + if (rx) { + /* set the INTENA_MSK_MASK so that this first write + * won't actually enable the interrupt, instead just + * updating the ITR (it's bit 31 PF and VF) + */ + rxval |= BIT(31); + /* don't check _DOWN because interrupt isn't being enabled */ + wr32(hw, INTREG(vector - 1), rxval); } + +enable_int: + if (!test_bit(__I40E_DOWN, &vsi->state)) + wr32(hw, INTREG(vector - 1), txval); + + if (q_vector->itr_countdown) + q_vector->itr_countdown--; + else + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } /** @@ -1271,7 +1323,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) bool clean_complete = true; bool arm_wb = false; int budget_per_ring; - int cleaned; + int work_done = 0; if (test_bit(__I40E_DOWN, &vsi->state)) { napi_complete(napi); @@ -1287,22 +1339,31 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) ring->arm_wb = false; } + /* Handle case where we are called by netpoll with a budget of 0 */ + if (budget <= 0) + goto tx_only; + /* We attempt to distribute budget to each Rx queue fairly, but don't * allow the budget to go below 1 because that would exit polling early. */ budget_per_ring = max(budget/q_vector->num_ringpairs, 1); i40e_for_each_ring(ring, q_vector->rx) { + int cleaned; + if (ring_is_ps_enabled(ring)) cleaned = i40e_clean_rx_irq_ps(ring, budget_per_ring); else cleaned = i40e_clean_rx_irq_1buf(ring, budget_per_ring); + + work_done += cleaned; /* if we didn't clean as many as budgeted, we must be done */ clean_complete &= (budget_per_ring != cleaned); } /* If work not completed, return budget and polling will return */ if (!clean_complete) { +tx_only: if (arm_wb) i40evf_force_wb(vsi, q_vector); return budget; @@ -1312,7 +1373,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) q_vector->arm_wb_state = false; /* Work is done so exit the polling mode and re-enable the interrupt */ - napi_complete(napi); + napi_complete_done(napi, work_done); i40e_update_enable_itr(vsi, q_vector); return 0; } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 0c13ece00366..ebc1bf77f036 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -32,11 +32,14 @@ #define I40E_MAX_ITR 0x0FF0 /* reg uses 2 usec resolution */ #define I40E_MIN_ITR 0x0001 /* reg uses 2 usec resolution */ #define I40E_ITR_100K 0x0005 +#define I40E_ITR_50K 0x000A #define I40E_ITR_20K 0x0019 +#define I40E_ITR_18K 0x001B #define I40E_ITR_8K 0x003E #define I40E_ITR_4K 0x007A -#define I40E_ITR_RX_DEF I40E_ITR_8K -#define I40E_ITR_TX_DEF I40E_ITR_4K +#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ +#define I40E_ITR_RX_DEF I40E_ITR_20K +#define I40E_ITR_TX_DEF I40E_ITR_20K #define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ #define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ @@ -44,6 +47,15 @@ #define ITR_TO_REG(setting) ((setting & ~I40E_ITR_DYNAMIC) >> 1) #define ITR_IS_DYNAMIC(setting) (!!(setting & I40E_ITR_DYNAMIC)) #define ITR_REG_TO_USEC(itr_reg) (itr_reg << 1) +/* 0x40 is the enable bit for interrupt rate limiting, and must be set if + * the value of the rate limit is non-zero + */ +#define INTRL_ENA BIT(6) +#define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) +#define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0) +#define I40E_INTRL_8K 125 /* 8000 ints/sec */ +#define I40E_INTRL_62K 16 /* 62500 ints/sec */ +#define I40E_INTRL_83K 12 /* 83333 ints/sec */ #define I40E_QUEUE_END_OF_LIST 0x7FF @@ -79,16 +91,16 @@ enum i40e_dyn_idx_t { BIT_ULL(I40E_FILTER_PCTYPE_L2_PAYLOAD)) #define I40E_DEFAULT_RSS_HENA_EXPANDED (I40E_DEFAULT_RSS_HENA | \ - BIT(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \ - BIT(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \ - BIT(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \ - BIT(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \ - BIT(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ - BIT(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) + BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \ + BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \ + BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \ + BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \ + BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ + BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) #define i40e_pf_get_default_rss_hena(pf) \ (((pf)->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) ? \ - I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA) + I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA) /* Supported Rx Buffer Sizes */ #define I40E_RXBUFFER_512 512 /* Used for packet split */ @@ -281,6 +293,7 @@ enum i40e_latency_range { I40E_LOWEST_LATENCY = 0, I40E_LOW_LATENCY = 1, I40E_BULK_LATENCY = 2, + I40E_ULTRA_LATENCY = 3, }; struct i40e_ring_container { diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index a59b60ffd0ce..301fe2b6dd03 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -33,31 +33,7 @@ #include "i40e_adminq.h" #include "i40e_hmc.h" #include "i40e_lan_hmc.h" - -/* Device IDs */ -#define I40E_DEV_ID_SFP_XL710 0x1572 -#define I40E_DEV_ID_QEMU 0x1574 -#define I40E_DEV_ID_KX_A 0x157F -#define I40E_DEV_ID_KX_B 0x1580 -#define I40E_DEV_ID_KX_C 0x1581 -#define I40E_DEV_ID_QSFP_A 0x1583 -#define I40E_DEV_ID_QSFP_B 0x1584 -#define I40E_DEV_ID_QSFP_C 0x1585 -#define I40E_DEV_ID_10G_BASE_T 0x1586 -#define I40E_DEV_ID_20G_KR2 0x1587 -#define I40E_DEV_ID_20G_KR2_A 0x1588 -#define I40E_DEV_ID_10G_BASE_T4 0x1589 -#define I40E_DEV_ID_VF 0x154C -#define I40E_DEV_ID_VF_HV 0x1571 -#define I40E_DEV_ID_SFP_X722 0x37D0 -#define I40E_DEV_ID_1G_BASE_T_X722 0x37D1 -#define I40E_DEV_ID_10G_BASE_T_X722 0x37D2 -#define I40E_DEV_ID_X722_VF 0x37CD -#define I40E_DEV_ID_X722_VF_HV 0x37D9 - -#define i40e_is_40G_device(d) ((d) == I40E_DEV_ID_QSFP_A || \ - (d) == I40E_DEV_ID_QSFP_B || \ - (d) == I40E_DEV_ID_QSFP_C) +#include "i40e_devids.h" /* I40E_MASK is a macro used on 32 bit registers */ #define I40E_MASK(mask, shift) (mask << shift) @@ -191,16 +167,65 @@ struct i40e_link_status { bool crc_enable; u8 pacing; u8 requested_speeds; + u8 module_type[3]; + /* 1st byte: module identifier */ +#define I40E_MODULE_TYPE_SFP 0x03 +#define I40E_MODULE_TYPE_QSFP 0x0D + /* 2nd byte: ethernet compliance codes for 10/40G */ +#define I40E_MODULE_TYPE_40G_ACTIVE 0x01 +#define I40E_MODULE_TYPE_40G_LR4 0x02 +#define I40E_MODULE_TYPE_40G_SR4 0x04 +#define I40E_MODULE_TYPE_40G_CR4 0x08 +#define I40E_MODULE_TYPE_10G_BASE_SR 0x10 +#define I40E_MODULE_TYPE_10G_BASE_LR 0x20 +#define I40E_MODULE_TYPE_10G_BASE_LRM 0x40 +#define I40E_MODULE_TYPE_10G_BASE_ER 0x80 + /* 3rd byte: ethernet compliance codes for 1G */ +#define I40E_MODULE_TYPE_1000BASE_SX 0x01 +#define I40E_MODULE_TYPE_1000BASE_LX 0x02 +#define I40E_MODULE_TYPE_1000BASE_CX 0x04 +#define I40E_MODULE_TYPE_1000BASE_T 0x08 +}; + +enum i40e_aq_capabilities_phy_type { + I40E_CAP_PHY_TYPE_SGMII = BIT(I40E_PHY_TYPE_SGMII), + I40E_CAP_PHY_TYPE_1000BASE_KX = BIT(I40E_PHY_TYPE_1000BASE_KX), + I40E_CAP_PHY_TYPE_10GBASE_KX4 = BIT(I40E_PHY_TYPE_10GBASE_KX4), + I40E_CAP_PHY_TYPE_10GBASE_KR = BIT(I40E_PHY_TYPE_10GBASE_KR), + I40E_CAP_PHY_TYPE_40GBASE_KR4 = BIT(I40E_PHY_TYPE_40GBASE_KR4), + I40E_CAP_PHY_TYPE_XAUI = BIT(I40E_PHY_TYPE_XAUI), + I40E_CAP_PHY_TYPE_XFI = BIT(I40E_PHY_TYPE_XFI), + I40E_CAP_PHY_TYPE_SFI = BIT(I40E_PHY_TYPE_SFI), + I40E_CAP_PHY_TYPE_XLAUI = BIT(I40E_PHY_TYPE_XLAUI), + I40E_CAP_PHY_TYPE_XLPPI = BIT(I40E_PHY_TYPE_XLPPI), + I40E_CAP_PHY_TYPE_40GBASE_CR4_CU = BIT(I40E_PHY_TYPE_40GBASE_CR4_CU), + I40E_CAP_PHY_TYPE_10GBASE_CR1_CU = BIT(I40E_PHY_TYPE_10GBASE_CR1_CU), + I40E_CAP_PHY_TYPE_10GBASE_AOC = BIT(I40E_PHY_TYPE_10GBASE_AOC), + I40E_CAP_PHY_TYPE_40GBASE_AOC = BIT(I40E_PHY_TYPE_40GBASE_AOC), + I40E_CAP_PHY_TYPE_100BASE_TX = BIT(I40E_PHY_TYPE_100BASE_TX), + I40E_CAP_PHY_TYPE_1000BASE_T = BIT(I40E_PHY_TYPE_1000BASE_T), + I40E_CAP_PHY_TYPE_10GBASE_T = BIT(I40E_PHY_TYPE_10GBASE_T), + I40E_CAP_PHY_TYPE_10GBASE_SR = BIT(I40E_PHY_TYPE_10GBASE_SR), + I40E_CAP_PHY_TYPE_10GBASE_LR = BIT(I40E_PHY_TYPE_10GBASE_LR), + I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU = BIT(I40E_PHY_TYPE_10GBASE_SFPP_CU), + I40E_CAP_PHY_TYPE_10GBASE_CR1 = BIT(I40E_PHY_TYPE_10GBASE_CR1), + I40E_CAP_PHY_TYPE_40GBASE_CR4 = BIT(I40E_PHY_TYPE_40GBASE_CR4), + I40E_CAP_PHY_TYPE_40GBASE_SR4 = BIT(I40E_PHY_TYPE_40GBASE_SR4), + I40E_CAP_PHY_TYPE_40GBASE_LR4 = BIT(I40E_PHY_TYPE_40GBASE_LR4), + I40E_CAP_PHY_TYPE_1000BASE_SX = BIT(I40E_PHY_TYPE_1000BASE_SX), + I40E_CAP_PHY_TYPE_1000BASE_LX = BIT(I40E_PHY_TYPE_1000BASE_LX), + I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL = + BIT(I40E_PHY_TYPE_1000BASE_T_OPTICAL), + I40E_CAP_PHY_TYPE_20GBASE_KR2 = BIT(I40E_PHY_TYPE_20GBASE_KR2) }; struct i40e_phy_info { struct i40e_link_status link_info; struct i40e_link_status link_info_old; - u32 autoneg_advertised; - u32 phy_id; - u32 module_type; bool get_link_info; enum i40e_media_type media_type; + /* all the phy types the NVM is capable of */ + enum i40e_aq_capabilities_phy_type phy_types; }; #define I40E_HW_CAP_MAX_GPIO 30 @@ -288,6 +313,7 @@ struct i40e_nvm_info { bool blank_nvm_mode; /* is NVM empty (no FW present)*/ u16 version; /* NVM package version */ u32 eetrack; /* NVM data version */ + u32 oem_ver; /* OEM version info */ }; /* definitions used in NVM update support */ @@ -1029,8 +1055,8 @@ enum i40e_filter_program_desc_fd_status { }; #define I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT 23 -#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK \ - BIT_ULL(I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT) +#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK (0x1FFUL << \ + I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT) #define I40E_TXD_FLTR_QW1_CMD_SHIFT 4 #define I40E_TXD_FLTR_QW1_CMD_MASK (0xFFFFULL << \ @@ -1173,6 +1199,7 @@ struct i40e_hw_port_stats { /* Checksum and Shadow RAM pointers */ #define I40E_SR_NVM_CONTROL_WORD 0x00 #define I40E_SR_EMP_MODULE_PTR 0x0F +#define I40E_NVM_OEM_VER_OFF 0x83 #define I40E_SR_NVM_DEV_STARTER_VERSION 0x18 #define I40E_SR_NVM_WAKE_ON_LAN 0x19 #define I40E_SR_ALTERNATE_SAN_MAC_ADDRESS_PTR 0x27 diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h index cadda642c98c..9f7b279b9d9c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h @@ -150,6 +150,7 @@ struct i40e_virtchnl_vsi_resource { #define I40E_VIRTCHNL_VF_OFFLOAD_FCOE 0x00000004 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010 +#define I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 #define I40E_VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000 #define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index e7a223ea6c25..22fc3d49c4b9 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -87,7 +87,7 @@ struct i40e_vsi { #define I40EVF_MAX_RXBUFFER 16384 /* largest size for single descriptor */ #define I40EVF_MAX_AQ_BUF_SIZE 4096 #define I40EVF_AQ_LEN 32 -#define I40EVF_AQ_MAX_ERR 10 /* times to try before resetting AQ */ +#define I40EVF_AQ_MAX_ERR 20 /* times to try before resetting AQ */ #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) @@ -112,6 +112,8 @@ struct i40e_q_vector { struct i40e_ring_container tx; u32 ring_mask; u8 num_ringpairs; /* total number of ring pairs in vector */ +#define ITR_COUNTDOWN_START 100 + u8 itr_countdown; /* when 0 or 1 update ITR */ int v_idx; /* vector index in list */ char name[IFNAMSIZ + 9]; bool arm_wb_state; @@ -211,7 +213,6 @@ struct i40evf_adapter { #define I40EVF_FLAG_RX_1BUF_CAPABLE BIT(1) #define I40EVF_FLAG_RX_PS_CAPABLE BIT(2) #define I40EVF_FLAG_RX_PS_ENABLED BIT(3) -#define I40EVF_FLAG_IN_NETPOLL BIT(4) #define I40EVF_FLAG_IMIR_ENABLED BIT(5) #define I40EVF_FLAG_MQ_CAPABLE BIT(6) #define I40EVF_FLAG_NEED_LINK_UPDATE BIT(7) @@ -220,10 +221,10 @@ struct i40evf_adapter { #define I40EVF_FLAG_RESET_NEEDED BIT(10) #define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(11) #define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(12) +#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(13) /* duplicates for common code */ #define I40E_FLAG_FDIR_ATR_ENABLED 0 #define I40E_FLAG_DCB_ENABLED 0 -#define I40E_FLAG_IN_NETPOLL I40EVF_FLAG_IN_NETPOLL #define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED #define I40E_FLAG_WB_ON_ITR_CAPABLE I40EVF_FLAG_WB_ON_ITR_CAPABLE #define I40E_FLAG_OUTER_UDP_CSUM_CAPABLE I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index c00e4959f026..10b2a4a33c68 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -34,7 +34,7 @@ char i40evf_driver_name[] = "i40evf"; static const char i40evf_driver_string[] = "Intel(R) XL710/X710 Virtual Function Network Driver"; -#define DRV_VERSION "1.3.13" +#define DRV_VERSION "1.3.25" const char i40evf_driver_version[] = DRV_VERSION; static const char i40evf_copyright[] = "Copyright (c) 2013 - 2015 Intel Corporation."; @@ -334,7 +334,7 @@ static irqreturn_t i40evf_msix_clean_rings(int irq, void *data) if (!q_vector->tx.ring && !q_vector->rx.ring) return IRQ_HANDLED; - napi_schedule(&q_vector->napi); + napi_schedule_irqoff(&q_vector->napi); return IRQ_HANDLED; } @@ -357,6 +357,7 @@ i40evf_map_vector_to_rxq(struct i40evf_adapter *adapter, int v_idx, int r_idx) q_vector->rx.ring = rx_ring; q_vector->rx.count++; q_vector->rx.latency_range = I40E_LOW_LATENCY; + q_vector->itr_countdown = ITR_COUNTDOWN_START; } /** @@ -377,6 +378,7 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) q_vector->tx.ring = tx_ring; q_vector->tx.count++; q_vector->tx.latency_range = I40E_LOW_LATENCY; + q_vector->itr_countdown = ITR_COUNTDOWN_START; q_vector->num_ringpairs++; q_vector->ring_mask |= BIT(t_idx); } @@ -444,6 +446,29 @@ out: return err; } +#ifdef CONFIG_NET_POLL_CONTROLLER +/** + * i40evf_netpoll - A Polling 'interrupt' handler + * @netdev: network interface device structure + * + * This is used by netconsole to send skbs without having to re-enable + * interrupts. It's not called while the normal interrupt routine is executing. + **/ +static void i40evf_netpoll(struct net_device *netdev) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + int q_vectors = adapter->num_msix_vectors - NONQ_VECS; + int i; + + /* if interface is down do nothing */ + if (test_bit(__I40E_DOWN, &adapter->vsi.state)) + return; + + for (i = 0; i < q_vectors; i++) + i40evf_msix_clean_rings(0, adapter->q_vector[i]); +} + +#endif /** * i40evf_request_traffic_irqs - Initialize MSI-X interrupts * @adapter: board private structure @@ -841,6 +866,15 @@ static int i40evf_set_mac(struct net_device *netdev, void *p) if (ether_addr_equal(netdev->dev_addr, addr->sa_data)) return 0; + if (adapter->flags & I40EVF_FLAG_ADDR_SET_BY_PF) + return -EPERM; + + f = i40evf_find_filter(adapter, hw->mac.addr); + if (f) { + f->remove = true; + adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; + } + f = i40evf_add_filter(adapter, addr->sa_data); if (f) { ether_addr_copy(hw->mac.addr, addr->sa_data); @@ -1114,6 +1148,8 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) tx_ring->netdev = adapter->netdev; tx_ring->dev = &adapter->pdev->dev; tx_ring->count = adapter->tx_desc_count; + if (adapter->flags & I40E_FLAG_WB_ON_ITR_CAPABLE) + tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR; adapter->tx_rings[i] = tx_ring; rx_ring = &tx_ring[1]; @@ -1617,7 +1653,7 @@ static void i40evf_reset_task(struct work_struct *work) /* extra wait to make sure minimum wait is met */ msleep(I40EVF_RESET_WAIT_MS); if (i == I40EVF_RESET_WAIT_COUNT) { - struct i40evf_mac_filter *f, *ftmp; + struct i40evf_mac_filter *ftmp; struct i40evf_vlan_filter *fv, *fvtmp; /* reset never finished */ @@ -2038,6 +2074,9 @@ static const struct net_device_ops i40evf_netdev_ops = { .ndo_tx_timeout = i40evf_tx_timeout, .ndo_vlan_rx_add_vid = i40evf_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = i40evf_vlan_rx_kill_vid, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = i40evf_netpoll, +#endif }; /** @@ -2086,7 +2125,10 @@ int i40evf_process_config(struct i40evf_adapter *adapter) if (adapter->vf_res->vf_offload_flags & I40E_VIRTCHNL_VF_OFFLOAD_VLAN) { - netdev->vlan_features = netdev->features; + netdev->vlan_features = netdev->features & + ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER); netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; @@ -2244,10 +2286,13 @@ static void i40evf_init_task(struct work_struct *work) if (!is_valid_ether_addr(adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", adapter->hw.mac.addr); - random_ether_addr(adapter->hw.mac.addr); + eth_hw_addr_random(netdev); + ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); + } else { + adapter->flags |= I40EVF_FLAG_ADDR_SET_BY_PF; + ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); + ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } - ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); - ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); init_timer(&adapter->watchdog_timer); adapter->watchdog_timer.function = &i40evf_watchdog_timer; @@ -2263,6 +2308,9 @@ static void i40evf_init_task(struct work_struct *work) if (err) goto err_sw_init; i40evf_map_rings_to_vectors(adapter); + if (adapter->vf_res->vf_offload_flags & + I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) + adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE; if (!RSS_AQ(adapter)) i40evf_configure_rss(adapter); err = i40evf_request_misc_irq(adapter); @@ -2311,11 +2359,14 @@ err_alloc: err: /* Things went into the weeds, so try again later */ if (++adapter->aq_wait_count > I40EVF_AQ_MAX_ERR) { - dev_err(&pdev->dev, "Failed to communicate with PF; giving up\n"); + dev_err(&pdev->dev, "Failed to communicate with PF; waiting before retry\n"); adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; - return; /* do not reschedule */ + i40evf_shutdown_adminq(hw); + adapter->state = __I40EVF_STARTUP; + schedule_delayed_work(&adapter->init_task, HZ * 5); + return; } - schedule_delayed_work(&adapter->init_task, HZ * 3); + schedule_delayed_work(&adapter->init_task, HZ); } /** diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 4f056efecba4..32e620e1eb5c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -156,7 +156,8 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) caps = I40E_VIRTCHNL_VF_OFFLOAD_L2 | I40E_VIRTCHNL_VF_OFFLOAD_RSS_AQ | I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG | - I40E_VIRTCHNL_VF_OFFLOAD_VLAN; + I40E_VIRTCHNL_VF_OFFLOAD_VLAN | + I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR; adapter->current_op = I40E_VIRTCHNL_OP_GET_VF_RESOURCES; adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG; if (PF_IS_V11(adapter)) diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 74262768b09b..2529bc625de4 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -842,10 +842,6 @@ static void igb_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_stats = IGB_STATS_LEN; - drvinfo->testinfo_len = IGB_TEST_LEN; - drvinfo->regdump_len = igb_get_regs_len(netdev); - drvinfo->eedump_len = igb_get_eeprom_len(netdev); } static void igb_get_ringparam(struct net_device *netdev, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 7e6267503790..ea7b09887245 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -151,7 +151,7 @@ static void igb_setup_dca(struct igb_adapter *); #endif /* CONFIG_IGB_DCA */ static int igb_poll(struct napi_struct *, int); static bool igb_clean_tx_irq(struct igb_q_vector *); -static bool igb_clean_rx_irq(struct igb_q_vector *, int); +static int igb_clean_rx_irq(struct igb_q_vector *, int); static int igb_ioctl(struct net_device *, struct ifreq *, int cmd); static void igb_tx_timeout(struct net_device *); static void igb_reset_task(struct work_struct *); @@ -6364,6 +6364,7 @@ static int igb_poll(struct napi_struct *napi, int budget) struct igb_q_vector, napi); bool clean_complete = true; + int work_done = 0; #ifdef CONFIG_IGB_DCA if (q_vector->adapter->flags & IGB_FLAG_DCA_ENABLED) @@ -6372,15 +6373,19 @@ static int igb_poll(struct napi_struct *napi, int budget) if (q_vector->tx.ring) clean_complete = igb_clean_tx_irq(q_vector); - if (q_vector->rx.ring) - clean_complete &= igb_clean_rx_irq(q_vector, budget); + if (q_vector->rx.ring) { + int cleaned = igb_clean_rx_irq(q_vector, budget); + + work_done += cleaned; + clean_complete &= (cleaned < budget); + } /* If all work not completed, return budget and keep polling */ if (!clean_complete) return budget; /* If not enough Rx work done, exit the polling mode */ - napi_complete(napi); + napi_complete_done(napi, work_done); igb_ring_irq_enable(q_vector); return 0; @@ -6904,7 +6909,7 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring, skb->protocol = eth_type_trans(skb, rx_ring->netdev); } -static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) +static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) { struct igb_ring *rx_ring = q_vector->rx.ring; struct sk_buff *skb = rx_ring->skb; @@ -6978,7 +6983,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) if (cleaned_count) igb_alloc_rx_buffers(rx_ring, cleaned_count); - return total_packets < budget; + return total_packets; } static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c index c6996feb1cb4..b74ce53d7b52 100644 --- a/drivers/net/ethernet/intel/igbvf/ethtool.c +++ b/drivers/net/ethernet/intel/igbvf/ethtool.c @@ -196,8 +196,6 @@ static void igbvf_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->regdump_len = igbvf_get_regs_len(netdev); - drvinfo->eedump_len = igbvf_get_eeprom_len(netdev); } static void igbvf_get_ringparam(struct net_device *netdev, diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index e86d41ed9260..297af801f051 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1211,7 +1211,7 @@ static int igbvf_poll(struct napi_struct *napi, int budget) /* If not enough Rx work done, exit the polling mode */ if (work_done < budget) { - napi_complete(napi); + napi_complete_done(napi, work_done); if (adapter->requested_itr & 3) igbvf_set_itr(adapter); diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c index b311e9e710d2..d2b29b490ae0 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c @@ -479,9 +479,6 @@ ixgb_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_stats = IXGB_STATS_LEN; - drvinfo->regdump_len = ixgb_get_regs_len(netdev); - drvinfo->eedump_len = ixgb_get_eeprom_len(netdev); } static void diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 94c4912b2330..d681273bd39d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -943,9 +943,6 @@ static void ixgbe_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_stats = IXGBE_STATS_LEN; - drvinfo->testinfo_len = IXGBE_TEST_LEN; - drvinfo->regdump_len = ixgbe_get_regs_len(netdev); } static void ixgbe_get_ringparam(struct net_device *netdev, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 191003901adb..9f8a7fd7a195 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2775,7 +2775,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget) container_of(napi, struct ixgbe_q_vector, napi); struct ixgbe_adapter *adapter = q_vector->adapter; struct ixgbe_ring *ring; - int per_ring_budget; + int per_ring_budget, work_done = 0; bool clean_complete = true; #ifdef CONFIG_IXGBE_DCA @@ -2796,9 +2796,13 @@ int ixgbe_poll(struct napi_struct *napi, int budget) else per_ring_budget = budget; - ixgbe_for_each_ring(ring, q_vector->rx) - clean_complete &= (ixgbe_clean_rx_irq(q_vector, ring, - per_ring_budget) < per_ring_budget); + ixgbe_for_each_ring(ring, q_vector->rx) { + int cleaned = ixgbe_clean_rx_irq(q_vector, ring, + per_ring_budget); + + work_done += cleaned; + clean_complete &= (cleaned < per_ring_budget); + } ixgbe_qv_unlock_napi(q_vector); /* If all work not completed, return budget and keep polling */ @@ -2806,7 +2810,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget) return budget; /* all work done, exit the polling mode */ - napi_complete(napi); + napi_complete_done(napi, work_done); if (adapter->rx_itr_setting & 1) ixgbe_set_itr(q_vector); if (!test_bit(__IXGBE_DOWN, &adapter->state)) @@ -3723,14 +3727,20 @@ static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) hw->mac.ops.set_mac_anti_spoofing(hw, (adapter->num_vfs != 0), adapter->num_vfs); - /* Ensure LLDP is set for Ethertype Antispoofing if we will be + /* Ensure LLDP and FC is set for Ethertype Antispoofing if we will be * calling set_ethertype_anti_spoofing for each VF in loop below */ - if (hw->mac.ops.set_ethertype_anti_spoofing) + if (hw->mac.ops.set_ethertype_anti_spoofing) { IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_LLDP), - (IXGBE_ETQF_FILTER_EN | /* enable filter */ - IXGBE_ETQF_TX_ANTISPOOF | /* tx antispoof */ - IXGBE_ETH_P_LLDP)); /* LLDP eth type */ + (IXGBE_ETQF_FILTER_EN | + IXGBE_ETQF_TX_ANTISPOOF | + IXGBE_ETH_P_LLDP)); + + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FC), + (IXGBE_ETQF_FILTER_EN | + IXGBE_ETQF_TX_ANTISPOOF | + ETH_P_PAUSE)); + } /* For VFs that have spoof checking turned off */ for (i = 0; i < adapter->num_vfs; i++) { @@ -5301,7 +5311,6 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter) rss = min_t(int, ixgbe_max_rss_indices(adapter), num_online_cpus()); adapter->ring_feature[RING_F_RSS].limit = rss; adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE; - adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED; adapter->max_q_vectors = MAX_Q_VECTORS_82599; adapter->atr_sample_rate = 20; fdir = min_t(int, IXGBE_MAX_FDIR_INDICES, num_online_cpus()); @@ -5327,7 +5336,6 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter) switch (hw->mac.type) { case ixgbe_mac_82598EB: adapter->flags2 &= ~IXGBE_FLAG2_RSC_CAPABLE; - adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED; if (hw->device_id == IXGBE_DEV_ID_82598AT) adapter->flags |= IXGBE_FLAG_FAN_FAIL_CAPABLE; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 939c90c4ff39..995f03107eac 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -1752,6 +1752,9 @@ enum { * FCoE (0x8906): Filter 2 * 1588 (0x88f7): Filter 3 * FIP (0x8914): Filter 4 + * LLDP (0x88CC): Filter 5 + * LACP (0x8809): Filter 6 + * FC (0x8808): Filter 7 */ #define IXGBE_ETQF_FILTER_EAPOL 0 #define IXGBE_ETQF_FILTER_FCOE 2 @@ -1759,6 +1762,7 @@ enum { #define IXGBE_ETQF_FILTER_FIP 4 #define IXGBE_ETQF_FILTER_LLDP 5 #define IXGBE_ETQF_FILTER_LACP 6 +#define IXGBE_ETQF_FILTER_FC 7 /* VLAN Control Bit Masks */ #define IXGBE_VLNCTRL_VET 0x0000FFFF /* bits 0-15 */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index ed7b2899affe..ebe0ac950b14 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -198,6 +198,7 @@ static s32 ixgbe_write_pe(struct ixgbe_hw *hw, u8 reg, u8 value) * ixgbe_reset_cs4227 - Reset CS4227 using port expander * @hw: pointer to hardware structure * + * This function assumes that the caller has acquired the proper semaphore. * Returns error code */ static s32 ixgbe_reset_cs4227(struct ixgbe_hw *hw) @@ -296,6 +297,14 @@ static void ixgbe_check_cs4227(struct ixgbe_hw *hw) hw->mac.ops.release_swfw_sync(hw, swfw_mask); msleep(IXGBE_CS4227_CHECK_DELAY); } + /* If still pending, assume other instance failed. */ + if (retry == IXGBE_CS4227_RETRIES) { + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_err(hw, "semaphore failed with %d\n", status); + return; + } + } /* Reset the CS4227. */ status = ixgbe_reset_cs4227(hw); @@ -1608,7 +1617,7 @@ static s32 ixgbe_handle_lasi_ext_t_x550em(struct ixgbe_hw *hw) if (status) return status; - if (lsc) + if (lsc && phy->ops.setup_internal_link) return phy->ops.setup_internal_link(hw); return 0; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 35da2d74e73e..7570b5c7ccd8 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1008,7 +1008,7 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget) container_of(napi, struct ixgbevf_q_vector, napi); struct ixgbevf_adapter *adapter = q_vector->adapter; struct ixgbevf_ring *ring; - int per_ring_budget; + int per_ring_budget, work_done = 0; bool clean_complete = true; ixgbevf_for_each_ring(ring, q_vector->tx) @@ -1027,10 +1027,12 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget) else per_ring_budget = budget; - ixgbevf_for_each_ring(ring, q_vector->rx) - clean_complete &= (ixgbevf_clean_rx_irq(q_vector, ring, - per_ring_budget) - < per_ring_budget); + ixgbevf_for_each_ring(ring, q_vector->rx) { + int cleaned = ixgbevf_clean_rx_irq(q_vector, ring, + per_ring_budget); + work_done += cleaned; + clean_complete &= (cleaned < per_ring_budget); + } #ifdef CONFIG_NET_RX_BUSY_POLL ixgbevf_qv_unlock_napi(q_vector); @@ -1040,7 +1042,7 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget) if (!clean_complete) return budget; /* all work done, exit the polling mode */ - napi_complete(napi); + napi_complete_done(napi, work_done); if (adapter->rx_itr_setting & 1) ixgbevf_set_itr(q_vector); if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index c78ae1868097..603d29df5832 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1586,7 +1586,6 @@ static void mv643xx_eth_get_drvinfo(struct net_device *dev, sizeof(drvinfo->version)); strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); - drvinfo->n_stats = ARRAY_SIZE(mv643xx_eth_stats); } static int mv643xx_eth_nway_reset(struct net_device *dev) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index f79d8124321e..ddb5541882f5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -95,9 +95,6 @@ mlx4_en_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) (u16) (mdev->dev->caps.fw_ver & 0xffff)); strlcpy(drvinfo->bus_info, pci_name(mdev->dev->persist->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_stats = 0; - drvinfo->regdump_len = 0; - drvinfo->eedump_len = 0; } static const char mlx4_en_priv_flags[][ETH_GSTRING_LEN] = { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 597d8923c8e1..886e1bc86374 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2816,7 +2816,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, struct mlx4_en_priv *priv; int i; int err; - u64 mac_u64; dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv), MAX_TX_RINGS, MAX_RX_RINGS); @@ -2908,17 +2907,17 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, dev->addr_len = ETH_ALEN; mlx4_en_u64_to_mac(dev->dev_addr, mdev->dev->caps.def_mac[priv->port]); if (!is_valid_ether_addr(dev->dev_addr)) { - if (mlx4_is_slave(priv->mdev->dev)) { - eth_hw_addr_random(dev); - en_warn(priv, "Assigned random MAC address %pM\n", dev->dev_addr); - mac_u64 = mlx4_mac_to_u64(dev->dev_addr); - mdev->dev->caps.def_mac[priv->port] = mac_u64; - } else { - en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n", - priv->port, dev->dev_addr); - err = -EINVAL; - goto out; - } + en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n", + priv->port, dev->dev_addr); + err = -EINVAL; + goto out; + } else if (mlx4_is_slave(priv->mdev->dev) && + (priv->mdev->dev->port_random_macs & 1 << priv->port)) { + /* Random MAC was assigned in mlx4_slave_cap + * in mlx4_core module + */ + dev->addr_assign_type |= NET_ADDR_RANDOM; + en_warn(priv, "Assigned random MAC address %pM\n", dev->dev_addr); } memcpy(priv->current_mac, dev->dev_addr, sizeof(priv->current_mac)); diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 8e81e53c370e..c34488479365 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -1364,6 +1364,10 @@ int mlx4_test_interrupts(struct mlx4_dev *dev) * and performing a NOP command */ for(i = 0; !err && (i < dev->caps.num_comp_vectors); ++i) { + /* Make sure request_irq was called */ + if (!priv->eq_table.eq[i].have_irq) + continue; + /* Temporary use polling for command completions */ mlx4_cmd_use_polling(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index e8ec1dec5789..f13a4d7bbf95 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -2840,3 +2840,19 @@ int set_phv_bit(struct mlx4_dev *dev, u8 port, int new_val) return -EOPNOTSUPP; } EXPORT_SYMBOL(set_phv_bit); + +void mlx4_replace_zero_macs(struct mlx4_dev *dev) +{ + int i; + u8 mac_addr[ETH_ALEN]; + + dev->port_random_macs = 0; + for (i = 1; i <= dev->caps.num_ports; ++i) + if (!dev->caps.def_mac[i] && + dev->caps.port_type[i] == MLX4_PORT_TYPE_ETH) { + eth_random_addr(mac_addr); + dev->port_random_macs |= 1 << i; + dev->caps.def_mac[i] = mlx4_mac_to_u64(mac_addr); + } +} +EXPORT_SYMBOL_GPL(mlx4_replace_zero_macs); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 006757f80988..85f1b1e7e505 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -863,6 +863,8 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) return -ENODEV; } + mlx4_replace_zero_macs(dev); + dev->caps.qp0_qkey = kcalloc(dev->caps.num_ports, sizeof(u32), GFP_KERNEL); dev->caps.qp0_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); dev->caps.qp0_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); @@ -2669,14 +2671,11 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) if (msi_x) { int nreq = dev->caps.num_ports * num_online_cpus() + 1; - bool shared_ports = false; nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs, nreq); - if (nreq > MAX_MSIX) { + if (nreq > MAX_MSIX) nreq = MAX_MSIX; - shared_ports = true; - } entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL); if (!entries) @@ -2699,9 +2698,6 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) bitmap_zero(priv->eq_table.eq[MLX4_EQ_ASYNC].actv_ports.ports, dev->caps.num_ports); - if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) - shared_ports = true; - for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) { if (i == MLX4_EQ_ASYNC) continue; @@ -2709,7 +2705,7 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) priv->eq_table.eq[i].irq = entries[i + 1 - !!(i > MLX4_EQ_ASYNC)].vector; - if (shared_ports) { + if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) { bitmap_fill(priv->eq_table.eq[i].actv_ports.ports, dev->caps.num_ports); /* We don't set affinity hint when there diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 232b2b55f23b..e1cf9036af22 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -1378,6 +1378,8 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work); void mlx4_init_quotas(struct mlx4_dev *dev); +/* for VFs, replace zero MACs with randomly-generated MACs at driver start */ +void mlx4_replace_zero_macs(struct mlx4_dev *dev); int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port); /* Returns the VF index of slave */ int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave); diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c index 78f51e103880..93195191f45b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mr.c +++ b/drivers/net/ethernet/mellanox/mlx4/mr.c @@ -318,7 +318,7 @@ int mlx4_mr_hw_get_mpt(struct mlx4_dev *dev, struct mlx4_mr *mmr, key, NULL); } else { mailbox = mlx4_alloc_cmd_mailbox(dev); - if (IS_ERR_OR_NULL(mailbox)) + if (IS_ERR(mailbox)) return PTR_ERR(mailbox); err = mlx4_cmd_box(dev, 0, mailbox->dma, key, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index c3e54b7e8780..fabfc9e0a948 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -256,8 +256,154 @@ static void dump_buf(void *buf, int size, int data_only, int offset) enum { MLX5_DRIVER_STATUS_ABORTED = 0xfe, + MLX5_DRIVER_SYND = 0xbadd00de, }; +static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, + u32 *synd, u8 *status) +{ + *synd = 0; + *status = 0; + + switch (op) { + case MLX5_CMD_OP_TEARDOWN_HCA: + case MLX5_CMD_OP_DISABLE_HCA: + case MLX5_CMD_OP_MANAGE_PAGES: + case MLX5_CMD_OP_DESTROY_MKEY: + case MLX5_CMD_OP_DESTROY_EQ: + case MLX5_CMD_OP_DESTROY_CQ: + case MLX5_CMD_OP_DESTROY_QP: + case MLX5_CMD_OP_DESTROY_PSV: + case MLX5_CMD_OP_DESTROY_SRQ: + case MLX5_CMD_OP_DESTROY_XRC_SRQ: + case MLX5_CMD_OP_DESTROY_DCT: + case MLX5_CMD_OP_DEALLOC_Q_COUNTER: + case MLX5_CMD_OP_DEALLOC_PD: + case MLX5_CMD_OP_DEALLOC_UAR: + case MLX5_CMD_OP_DETTACH_FROM_MCG: + case MLX5_CMD_OP_DEALLOC_XRCD: + case MLX5_CMD_OP_DEALLOC_TRANSPORT_DOMAIN: + case MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT: + case MLX5_CMD_OP_DELETE_L2_TABLE_ENTRY: + case MLX5_CMD_OP_DESTROY_TIR: + case MLX5_CMD_OP_DESTROY_SQ: + case MLX5_CMD_OP_DESTROY_RQ: + case MLX5_CMD_OP_DESTROY_RMP: + case MLX5_CMD_OP_DESTROY_TIS: + case MLX5_CMD_OP_DESTROY_RQT: + case MLX5_CMD_OP_DESTROY_FLOW_TABLE: + case MLX5_CMD_OP_DESTROY_FLOW_GROUP: + case MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY: + return MLX5_CMD_STAT_OK; + + case MLX5_CMD_OP_QUERY_HCA_CAP: + case MLX5_CMD_OP_QUERY_ADAPTER: + case MLX5_CMD_OP_INIT_HCA: + case MLX5_CMD_OP_ENABLE_HCA: + case MLX5_CMD_OP_QUERY_PAGES: + case MLX5_CMD_OP_SET_HCA_CAP: + case MLX5_CMD_OP_QUERY_ISSI: + case MLX5_CMD_OP_SET_ISSI: + case MLX5_CMD_OP_CREATE_MKEY: + case MLX5_CMD_OP_QUERY_MKEY: + case MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS: + case MLX5_CMD_OP_PAGE_FAULT_RESUME: + case MLX5_CMD_OP_CREATE_EQ: + case MLX5_CMD_OP_QUERY_EQ: + case MLX5_CMD_OP_GEN_EQE: + case MLX5_CMD_OP_CREATE_CQ: + case MLX5_CMD_OP_QUERY_CQ: + case MLX5_CMD_OP_MODIFY_CQ: + case MLX5_CMD_OP_CREATE_QP: + case MLX5_CMD_OP_RST2INIT_QP: + case MLX5_CMD_OP_INIT2RTR_QP: + case MLX5_CMD_OP_RTR2RTS_QP: + case MLX5_CMD_OP_RTS2RTS_QP: + case MLX5_CMD_OP_SQERR2RTS_QP: + case MLX5_CMD_OP_2ERR_QP: + case MLX5_CMD_OP_2RST_QP: + case MLX5_CMD_OP_QUERY_QP: + case MLX5_CMD_OP_SQD_RTS_QP: + case MLX5_CMD_OP_INIT2INIT_QP: + case MLX5_CMD_OP_CREATE_PSV: + case MLX5_CMD_OP_CREATE_SRQ: + case MLX5_CMD_OP_QUERY_SRQ: + case MLX5_CMD_OP_ARM_RQ: + case MLX5_CMD_OP_CREATE_XRC_SRQ: + case MLX5_CMD_OP_QUERY_XRC_SRQ: + case MLX5_CMD_OP_ARM_XRC_SRQ: + case MLX5_CMD_OP_CREATE_DCT: + case MLX5_CMD_OP_DRAIN_DCT: + case MLX5_CMD_OP_QUERY_DCT: + case MLX5_CMD_OP_ARM_DCT_FOR_KEY_VIOLATION: + case MLX5_CMD_OP_QUERY_VPORT_STATE: + case MLX5_CMD_OP_MODIFY_VPORT_STATE: + case MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT: + case MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT: + case MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT: + case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT: + case MLX5_CMD_OP_QUERY_ROCE_ADDRESS: + case MLX5_CMD_OP_SET_ROCE_ADDRESS: + case MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT: + case MLX5_CMD_OP_MODIFY_HCA_VPORT_CONTEXT: + case MLX5_CMD_OP_QUERY_HCA_VPORT_GID: + case MLX5_CMD_OP_QUERY_HCA_VPORT_PKEY: + case MLX5_CMD_OP_QUERY_VPORT_COUNTER: + case MLX5_CMD_OP_ALLOC_Q_COUNTER: + case MLX5_CMD_OP_QUERY_Q_COUNTER: + case MLX5_CMD_OP_ALLOC_PD: + case MLX5_CMD_OP_ALLOC_UAR: + case MLX5_CMD_OP_CONFIG_INT_MODERATION: + case MLX5_CMD_OP_ACCESS_REG: + case MLX5_CMD_OP_ATTACH_TO_MCG: + case MLX5_CMD_OP_GET_DROPPED_PACKET_LOG: + case MLX5_CMD_OP_MAD_IFC: + case MLX5_CMD_OP_QUERY_MAD_DEMUX: + case MLX5_CMD_OP_SET_MAD_DEMUX: + case MLX5_CMD_OP_NOP: + case MLX5_CMD_OP_ALLOC_XRCD: + case MLX5_CMD_OP_ALLOC_TRANSPORT_DOMAIN: + case MLX5_CMD_OP_QUERY_CONG_STATUS: + case MLX5_CMD_OP_MODIFY_CONG_STATUS: + case MLX5_CMD_OP_QUERY_CONG_PARAMS: + case MLX5_CMD_OP_MODIFY_CONG_PARAMS: + case MLX5_CMD_OP_QUERY_CONG_STATISTICS: + case MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT: + case MLX5_CMD_OP_SET_L2_TABLE_ENTRY: + case MLX5_CMD_OP_QUERY_L2_TABLE_ENTRY: + case MLX5_CMD_OP_CREATE_TIR: + case MLX5_CMD_OP_MODIFY_TIR: + case MLX5_CMD_OP_QUERY_TIR: + case MLX5_CMD_OP_CREATE_SQ: + case MLX5_CMD_OP_MODIFY_SQ: + case MLX5_CMD_OP_QUERY_SQ: + case MLX5_CMD_OP_CREATE_RQ: + case MLX5_CMD_OP_MODIFY_RQ: + case MLX5_CMD_OP_QUERY_RQ: + case MLX5_CMD_OP_CREATE_RMP: + case MLX5_CMD_OP_MODIFY_RMP: + case MLX5_CMD_OP_QUERY_RMP: + case MLX5_CMD_OP_CREATE_TIS: + case MLX5_CMD_OP_MODIFY_TIS: + case MLX5_CMD_OP_QUERY_TIS: + case MLX5_CMD_OP_CREATE_RQT: + case MLX5_CMD_OP_MODIFY_RQT: + case MLX5_CMD_OP_QUERY_RQT: + case MLX5_CMD_OP_CREATE_FLOW_TABLE: + case MLX5_CMD_OP_QUERY_FLOW_TABLE: + case MLX5_CMD_OP_CREATE_FLOW_GROUP: + case MLX5_CMD_OP_QUERY_FLOW_GROUP: + case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY: + case MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY: + *status = MLX5_DRIVER_STATUS_ABORTED; + *synd = MLX5_DRIVER_SYND; + return -EIO; + default: + mlx5_core_err(dev, "Unknown FW command (%d)\n", op); + return -EINVAL; + } +} + const char *mlx5_command_str(int command) { switch (command) { @@ -592,6 +738,16 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) return err; } +static __be32 *get_synd_ptr(struct mlx5_outbox_hdr *out) +{ + return &out->syndrome; +} + +static u8 *get_status_ptr(struct mlx5_outbox_hdr *out) +{ + return &out->status; +} + /* Notes: * 1. Callback functions may not sleep * 2. page queue commands do not support asynchrous completion @@ -1200,6 +1356,11 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size, return msg; } +static u16 opcode_from_in(struct mlx5_inbox_hdr *in) +{ + return be16_to_cpu(in->opcode); +} + static int is_manage_pages(struct mlx5_inbox_hdr *in) { return be16_to_cpu(in->opcode) == MLX5_CMD_OP_MANAGE_PAGES; @@ -1214,6 +1375,15 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, gfp_t gfp; int err; u8 status = 0; + u32 drv_synd; + + if (pci_channel_offline(dev->pdev) || + dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { + err = mlx5_internal_err_ret_value(dev, opcode_from_in(in), &drv_synd, &status); + *get_synd_ptr(out) = cpu_to_be32(drv_synd); + *get_status_ptr(out) = status; + return err; + } pages_queue = is_manage_pages(in); gfp = callback ? GFP_ATOMIC : GFP_KERNEL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c b/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c index e71563ce05d1..22d603f78273 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c @@ -598,6 +598,8 @@ void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv) return; priv->vlan.filter_disabled = false; + if (priv->netdev->flags & IFF_PROMISC) + return; mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, 0); } @@ -607,6 +609,8 @@ void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv) return; priv->vlan.filter_disabled = true; + if (priv->netdev->flags & IFF_PROMISC) + return; mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, 0); } @@ -717,8 +721,12 @@ void mlx5e_set_rx_mode_work(struct work_struct *work) bool enable_broadcast = !ea->broadcast_enabled && broadcast_enabled; bool disable_broadcast = ea->broadcast_enabled && !broadcast_enabled; - if (enable_promisc) + if (enable_promisc) { mlx5e_add_eth_addr_rule(priv, &ea->promisc, MLX5E_PROMISC); + if (!priv->vlan.filter_disabled) + mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, + 0); + } if (enable_allmulti) mlx5e_add_eth_addr_rule(priv, &ea->allmulti, MLX5E_ALLMULTI); if (enable_broadcast) @@ -730,8 +738,12 @@ void mlx5e_set_rx_mode_work(struct work_struct *work) mlx5e_del_eth_addr_from_flow_table(priv, &ea->broadcast); if (disable_allmulti) mlx5e_del_eth_addr_from_flow_table(priv, &ea->allmulti); - if (disable_promisc) + if (disable_promisc) { + if (!priv->vlan.filter_disabled) + mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, + 0); mlx5e_del_eth_addr_from_flow_table(priv, &ea->promisc); + } ea->promisc_enabled = promisc_enabled; ea->allmulti_enabled = allmulti_enabled; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 9b81e1ceb8de..f5deb642d0d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -34,6 +34,7 @@ #include <linux/module.h> #include <linux/random.h> #include <linux/vmalloc.h> +#include <linux/hardirq.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/cmd.h> #include "mlx5_core.h" @@ -57,6 +58,91 @@ enum { MLX5_HEALTH_SYNDR_HIGH_TEMP = 0x10 }; +enum { + MLX5_NIC_IFC_FULL = 0, + MLX5_NIC_IFC_DISABLED = 1, + MLX5_NIC_IFC_NO_DRAM_NIC = 2 +}; + +static u8 get_nic_interface(struct mlx5_core_dev *dev) +{ + return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 3; +} + +static void trigger_cmd_completions(struct mlx5_core_dev *dev) +{ + unsigned long flags; + u64 vector; + + /* wait for pending handlers to complete */ + synchronize_irq(dev->priv.msix_arr[MLX5_EQ_VEC_CMD].vector); + spin_lock_irqsave(&dev->cmd.alloc_lock, flags); + vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1); + if (!vector) + goto no_trig; + + vector |= MLX5_TRIGGERED_CMD_COMP; + spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); + + mlx5_core_dbg(dev, "vector 0x%llx\n", vector); + mlx5_cmd_comp_handler(dev, vector); + return; + +no_trig: + spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); +} + +static int in_fatal(struct mlx5_core_dev *dev) +{ + struct mlx5_core_health *health = &dev->priv.health; + struct health_buffer __iomem *h = health->health; + + if (get_nic_interface(dev) == MLX5_NIC_IFC_DISABLED) + return 1; + + if (ioread32be(&h->fw_ver) == 0xffffffff) + return 1; + + return 0; +} + +void mlx5_enter_error_state(struct mlx5_core_dev *dev) +{ + if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + return; + + mlx5_core_err(dev, "start\n"); + if (pci_channel_offline(dev->pdev) || in_fatal(dev)) + dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; + + mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 0); + mlx5_core_err(dev, "end\n"); +} + +static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) +{ + u8 nic_interface = get_nic_interface(dev); + + switch (nic_interface) { + case MLX5_NIC_IFC_FULL: + mlx5_core_warn(dev, "Expected to see disabled NIC but it is full driver\n"); + break; + + case MLX5_NIC_IFC_DISABLED: + mlx5_core_warn(dev, "starting teardown\n"); + break; + + case MLX5_NIC_IFC_NO_DRAM_NIC: + mlx5_core_warn(dev, "Expected to see disabled NIC but it is no dram nic\n"); + break; + default: + mlx5_core_warn(dev, "Expected to see disabled NIC but it is has invalid value %d\n", + nic_interface); + } + + mlx5_disable_device(dev); +} + static void health_care(struct work_struct *work) { struct mlx5_core_health *health; @@ -67,6 +153,7 @@ static void health_care(struct work_struct *work) priv = container_of(health, struct mlx5_priv, health); dev = container_of(priv, struct mlx5_core_dev, priv); mlx5_core_warn(dev, "handling bad device here\n"); + mlx5_handle_bad_state(dev); } static const char *hsynd_str(u8 synd) @@ -122,6 +209,10 @@ static void print_health_info(struct mlx5_core_dev *dev) u32 fw; int i; + /* If the syndrom is 0, the device is OK and no need to print buffer */ + if (!ioread8(&h->synd)) + return; + for (i = 0; i < ARRAY_SIZE(h->assert_var); i++) dev_err(&dev->pdev->dev, "assert_var[%d] 0x%08x\n", i, ioread32be(h->assert_var + i)); @@ -136,13 +227,29 @@ static void print_health_info(struct mlx5_core_dev *dev) dev_err(&dev->pdev->dev, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd)); } +static unsigned long get_next_poll_jiffies(void) +{ + unsigned long next; + + get_random_bytes(&next, sizeof(next)); + next %= HZ; + next += jiffies + MLX5_HEALTH_POLL_INTERVAL; + + return next; +} + static void poll_health(unsigned long data) { struct mlx5_core_dev *dev = (struct mlx5_core_dev *)data; struct mlx5_core_health *health = &dev->priv.health; - unsigned long next; u32 count; + if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { + trigger_cmd_completions(dev); + mod_timer(&health->timer, get_next_poll_jiffies()); + return; + } + count = ioread32be(health->health_counter); if (count == health->prev) ++health->miss_counter; @@ -151,14 +258,16 @@ static void poll_health(unsigned long data) health->prev = count; if (health->miss_counter == MAX_MISSES) { - mlx5_core_err(dev, "device's health compromised\n"); + dev_err(&dev->pdev->dev, "device's health compromised - reached miss count\n"); print_health_info(dev); - queue_work(health->wq, &health->work); } else { - get_random_bytes(&next, sizeof(next)); - next %= HZ; - next += jiffies + MLX5_HEALTH_POLL_INTERVAL; - mod_timer(&health->timer, next); + mod_timer(&health->timer, get_next_poll_jiffies()); + } + + if (in_fatal(dev) && !health->sick) { + health->sick = true; + print_health_info(dev); + queue_work(health->wq, &health->work); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index b6edc58766ad..2388aec208fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -39,12 +39,14 @@ #include <linux/slab.h> #include <linux/io-mapping.h> #include <linux/interrupt.h> +#include <linux/delay.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/cq.h> #include <linux/mlx5/qp.h> #include <linux/mlx5/srq.h> #include <linux/debugfs.h> #include <linux/kmod.h> +#include <linux/delay.h> #include <linux/mlx5/mlx5_ifc.h> #include "mlx5_core.h" @@ -151,6 +153,25 @@ static struct mlx5_profile profile[] = { }, }; +#define FW_INIT_TIMEOUT_MILI 2000 +#define FW_INIT_WAIT_MS 2 + +static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili) +{ + unsigned long end = jiffies + msecs_to_jiffies(max_wait_mili); + int err = 0; + + while (fw_initializing(dev)) { + if (time_after(jiffies, end)) { + err = -EBUSY; + break; + } + msleep(FW_INIT_WAIT_MS); + } + + return err; +} + static int set_dma_caps(struct pci_dev *pdev) { int err; @@ -181,6 +202,34 @@ static int set_dma_caps(struct pci_dev *pdev) return err; } +static int mlx5_pci_enable_device(struct mlx5_core_dev *dev) +{ + struct pci_dev *pdev = dev->pdev; + int err = 0; + + mutex_lock(&dev->pci_status_mutex); + if (dev->pci_status == MLX5_PCI_STATUS_DISABLED) { + err = pci_enable_device(pdev); + if (!err) + dev->pci_status = MLX5_PCI_STATUS_ENABLED; + } + mutex_unlock(&dev->pci_status_mutex); + + return err; +} + +static void mlx5_pci_disable_device(struct mlx5_core_dev *dev) +{ + struct pci_dev *pdev = dev->pdev; + + mutex_lock(&dev->pci_status_mutex); + if (dev->pci_status == MLX5_PCI_STATUS_ENABLED) { + pci_disable_device(pdev); + dev->pci_status = MLX5_PCI_STATUS_DISABLED; + } + mutex_unlock(&dev->pci_status_mutex); +} + static int request_bar(struct pci_dev *pdev) { int err = 0; @@ -807,7 +856,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv) if (!priv->dbg_root) return -ENOMEM; - err = pci_enable_device(pdev); + err = mlx5_pci_enable_device(dev); if (err) { dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n"); goto err_dbg; @@ -841,7 +890,7 @@ err_clr_master: pci_clear_master(dev->pdev); release_bar(dev->pdev); err_disable: - pci_disable_device(dev->pdev); + mlx5_pci_disable_device(dev); err_dbg: debugfs_remove(priv->dbg_root); @@ -853,7 +902,7 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev, struct mlx5_priv *priv) iounmap(dev->iseg); pci_clear_master(dev->pdev); release_bar(dev->pdev); - pci_disable_device(dev->pdev); + mlx5_pci_disable_device(dev); debugfs_remove(priv->dbg_root); } @@ -863,13 +912,32 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) struct pci_dev *pdev = dev->pdev; int err; + mutex_lock(&dev->intf_state_mutex); + if (dev->interface_state == MLX5_INTERFACE_STATE_UP) { + dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n", + __func__); + goto out; + } + dev_info(&pdev->dev, "firmware version: %d.%d.%d\n", fw_rev_maj(dev), fw_rev_min(dev), fw_rev_sub(dev)); + /* on load removing any previous indication of internal error, device is + * up + */ + dev->state = MLX5_DEVICE_STATE_UP; + err = mlx5_cmd_init(dev); if (err) { dev_err(&pdev->dev, "Failed initializing command interface, aborting\n"); - return err; + goto out_err; + } + + err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI); + if (err) { + dev_err(&dev->pdev->dev, "Firmware over %d MS in initializing state, aborting\n", + FW_INIT_TIMEOUT_MILI); + goto out_err; } mlx5_pagealloc_init(dev); @@ -994,6 +1062,10 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) if (err) pr_info("failed request module on %s\n", MLX5_IB_MOD); + dev->interface_state = MLX5_INTERFACE_STATE_UP; +out: + mutex_unlock(&dev->intf_state_mutex); + return 0; err_reg_dev: @@ -1024,7 +1096,7 @@ err_stop_poll: mlx5_stop_health_poll(dev); if (mlx5_cmd_teardown_hca(dev)) { dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); - return err; + goto out_err; } err_pagealloc_stop: @@ -1040,13 +1112,23 @@ err_pagealloc_cleanup: mlx5_pagealloc_cleanup(dev); mlx5_cmd_cleanup(dev); +out_err: + dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; + mutex_unlock(&dev->intf_state_mutex); + return err; } static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) { - int err; + int err = 0; + mutex_lock(&dev->intf_state_mutex); + if (dev->interface_state == MLX5_INTERFACE_STATE_DOWN) { + dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n", + __func__); + goto out; + } mlx5_unregister_device(dev); mlx5_cleanup_mr_table(dev); mlx5_cleanup_srq_table(dev); @@ -1072,10 +1154,12 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_cmd_cleanup(dev); out: + dev->interface_state = MLX5_INTERFACE_STATE_DOWN; + mutex_unlock(&dev->intf_state_mutex); return err; } -static void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, +void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param) { struct mlx5_priv *priv = &dev->priv; @@ -1125,6 +1209,8 @@ static int init_one(struct pci_dev *pdev, INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); + mutex_init(&dev->pci_status_mutex); + mutex_init(&dev->intf_state_mutex); err = mlx5_pci_init(dev, priv); if (err) { dev_err(&pdev->dev, "mlx5_pci_init failed with error code %d\n", err); @@ -1172,6 +1258,112 @@ static void remove_one(struct pci_dev *pdev) kfree(dev); } +static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + struct mlx5_priv *priv = &dev->priv; + + dev_info(&pdev->dev, "%s was called\n", __func__); + mlx5_enter_error_state(dev); + mlx5_unload_one(dev, priv); + mlx5_pci_disable_device(dev); + return state == pci_channel_io_perm_failure ? + PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET; +} + +static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) +{ + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + int err = 0; + + dev_info(&pdev->dev, "%s was called\n", __func__); + + err = mlx5_pci_enable_device(dev); + if (err) { + dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n" + , __func__, err); + return PCI_ERS_RESULT_DISCONNECT; + } + pci_set_master(pdev); + pci_set_power_state(pdev, PCI_D0); + pci_restore_state(pdev); + + return err ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; +} + +void mlx5_disable_device(struct mlx5_core_dev *dev) +{ + mlx5_pci_err_detected(dev->pdev, 0); +} + +/* wait for the device to show vital signs. For now we check + * that we can read the device ID and that the health buffer + * shows a non zero value which is different than 0xffffffff + */ +static void wait_vital(struct pci_dev *pdev) +{ + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + struct mlx5_core_health *health = &dev->priv.health; + const int niter = 100; + u32 count; + u16 did; + int i; + + /* Wait for firmware to be ready after reset */ + msleep(1000); + for (i = 0; i < niter; i++) { + if (pci_read_config_word(pdev, 2, &did)) { + dev_warn(&pdev->dev, "failed reading config word\n"); + break; + } + if (did == pdev->device) { + dev_info(&pdev->dev, "device ID correctly read after %d iterations\n", i); + break; + } + msleep(50); + } + if (i == niter) + dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__); + + for (i = 0; i < niter; i++) { + count = ioread32be(health->health_counter); + if (count && count != 0xffffffff) { + dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i); + break; + } + msleep(50); + } + + if (i == niter) + dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__); +} + +static void mlx5_pci_resume(struct pci_dev *pdev) +{ + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + struct mlx5_priv *priv = &dev->priv; + int err; + + dev_info(&pdev->dev, "%s was called\n", __func__); + + pci_save_state(pdev); + wait_vital(pdev); + + err = mlx5_load_one(dev, priv); + if (err) + dev_err(&pdev->dev, "%s: mlx5_load_one failed with error code: %d\n" + , __func__, err); + else + dev_info(&pdev->dev, "%s: device recovered\n", __func__); +} + +static const struct pci_error_handlers mlx5_err_handler = { + .error_detected = mlx5_pci_err_detected, + .slot_reset = mlx5_pci_slot_reset, + .resume = mlx5_pci_resume +}; + static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1011) }, /* Connect-IB */ { PCI_VDEVICE(MELLANOX, 0x1012) }, /* Connect-IB VF */ @@ -1188,7 +1380,8 @@ static struct pci_driver mlx5_core_driver = { .name = DRIVER_NAME, .id_table = mlx5_core_pci_table, .probe = init_one, - .remove = remove_one + .remove = remove_one, + .err_handler = &mlx5_err_handler }; static int __init init(void) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 30c0be721b08..cee5b7a839bc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -86,6 +86,10 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev); int mlx5_query_board_id(struct mlx5_core_dev *dev); int mlx5_cmd_init_hca(struct mlx5_core_dev *dev); int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev); +void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, + unsigned long param); +void mlx5_enter_error_state(struct mlx5_core_dev *dev); +void mlx5_disable_device(struct mlx5_core_dev *dev); void mlx5e_init(void); void mlx5e_cleanup(void); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 76432a510ac2..1cda5d268ec9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -493,15 +493,20 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) struct fw_page *fwp; struct rb_node *p; int nclaimed = 0; - int err; + int err = 0; do { p = rb_first(&dev->priv.page_root); if (p) { fwp = rb_entry(p, struct fw_page, rb_node); - err = reclaim_pages(dev, fwp->func_id, - optimal_reclaimed_pages(), - &nclaimed); + if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { + free_4k(dev, fwp->addr); + nclaimed = 1; + } else { + err = reclaim_pages(dev, fwp->func_id, + optimal_reclaimed_pages(), + &nclaimed); + } if (err) { mlx5_core_warn(dev, "failed reclaiming pages (%d)\n", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index ae302614e74b..a87e773e93f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -302,7 +302,7 @@ static int mlx5_query_port_pvlc(struct mlx5_core_dev *dev, u32 *pvlc, u32 in[MLX5_ST_SZ_DW(pvlc_reg)]; memset(in, 0, sizeof(in)); - MLX5_SET(ptys_reg, in, local_port, local_port); + MLX5_SET(pvlc_reg, in, local_port, local_port); return mlx5_core_access_reg(dev, in, sizeof(in), pvlc, pvlc_size, MLX5_REG_PVLC, 0, 0); diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 2941d9c5ae48..e36e12219c9b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -30,3 +30,14 @@ config MLXSW_SWITCHX2 To compile this driver as a module, choose M here: the module will be called mlxsw_switchx2. + +config MLXSW_SPECTRUM + tristate "Mellanox Technologies Spectrum support" + depends on MLXSW_CORE && NET_SWITCHDEV + default m + ---help--- + This driver supports Mellanox Technologies Spectrum Ethernet + Switch ASICs. + + To compile this driver as a module, choose M here: the + module will be called mlxsw_spectrum. diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 0a05f65ee814..af015818fd19 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -4,3 +4,6 @@ obj-$(CONFIG_MLXSW_PCI) += mlxsw_pci.o mlxsw_pci-objs := pci.o 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 diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h index 770db17eb03f..cd63b8263688 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h +++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h @@ -464,6 +464,8 @@ MLXSW_ITEM32(cmd_mbox, query_aq_cap, max_sg_rq, 0x10, 0, 8); * passed in this command must be pinned. */ +#define MLXSW_CMD_MAP_FA_VPM_ENTRIES_MAX 32 + static inline int mlxsw_cmd_map_fa(struct mlxsw_core *mlxsw_core, char *in_mbox, u32 vpm_entries_count) { @@ -568,7 +570,7 @@ MLXSW_ITEM32(cmd_mbox, config_profile, set_max_vlan_groups, 0x0C, 6, 1); */ MLXSW_ITEM32(cmd_mbox, config_profile, set_max_regions, 0x0C, 7, 1); -/* cmd_mbox_config_profile_set_fid_based +/* cmd_mbox_config_profile_set_flood_mode * Capability bit. Setting a bit to 1 configures the profile * according to the mailbox contents. */ @@ -649,12 +651,8 @@ MLXSW_ITEM32(cmd_mbox, config_profile, max_vlan_groups, 0x28, 0, 12); MLXSW_ITEM32(cmd_mbox, config_profile, max_regions, 0x2C, 0, 16); /* cmd_mbox_config_profile_max_flood_tables - * Maximum number of Flooding Tables. Flooding Tables are associated to - * the different packet types for the different switch partitions. - * Note that the table size depends on the fid_based mode. - * In SwitchX silicon, tables are split equally between the switch - * partitions. e.g. for 2 swids and 8 tables, the first 4 are associated - * with swid-1 and the last 4 are associated with swid-2. + * Maximum number of single-entry flooding tables. Different flooding tables + * can be associated with different packet types. */ MLXSW_ITEM32(cmd_mbox, config_profile, max_flood_tables, 0x30, 16, 4); @@ -665,15 +663,42 @@ MLXSW_ITEM32(cmd_mbox, config_profile, max_flood_tables, 0x30, 16, 4); */ MLXSW_ITEM32(cmd_mbox, config_profile, max_vid_flood_tables, 0x30, 8, 4); -/* cmd_mbox_config_profile_fid_based - * FID Based Flood Mode - * 00 Do not use FID to offset the index into the Port Group Table/Multicast ID - * 01 Use FID to offset the index to the Port Group Table (pgi) - * 10 Use FID to offset the index to the Port Group Table (pgi) and - * the Multicast ID +/* cmd_mbox_config_profile_flood_mode + * Flooding mode to use. + * 0-2 - Backward compatible modes for SwitchX devices. + * 3 - Mixed mode, where: + * max_flood_tables indicates the number of single-entry tables. + * max_vid_flood_tables indicates the number of per-VID tables. + * max_fid_offset_flood_tables indicates the number of FID-offset tables. + * max_fid_flood_tables indicates the number of per-FID tables. */ MLXSW_ITEM32(cmd_mbox, config_profile, flood_mode, 0x30, 0, 2); +/* cmd_mbox_config_profile_max_fid_offset_flood_tables + * Maximum number of FID-offset flooding tables. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, + max_fid_offset_flood_tables, 0x34, 24, 4); + +/* cmd_mbox_config_profile_fid_offset_flood_table_size + * The size (number of entries) of each FID-offset flood table. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, + fid_offset_flood_table_size, 0x34, 0, 16); + +/* cmd_mbox_config_profile_max_fid_flood_tables + * Maximum number of per-FID flooding tables. + * + * Note: This flooding tables cover special FIDs only (vFIDs), starting at + * FID value 4K and higher. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, max_fid_flood_tables, 0x38, 24, 4); + +/* cmd_mbox_config_profile_fid_flood_table_size + * The size (number of entries) of each per-FID table. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, fid_flood_table_size, 0x38, 0, 16); + /* cmd_mbox_config_profile_max_ib_mc * Maximum number of multicast FDB records for InfiniBand * FDB (in 512 chunks) per InfiniBand switch partition. diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index dbcaf5df8967..bd80ac714a8a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -374,26 +374,31 @@ static int __mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core, int err; int ret; + mlxsw_core->emad.trans_active = true; + err = mlxsw_core_skb_transmit(mlxsw_core->driver_priv, skb, tx_info); if (err) { dev_err(mlxsw_core->bus_info->dev, "Failed to transmit EMAD (tid=%llx)\n", mlxsw_core->emad.tid); dev_kfree_skb(skb); - return err; + goto trans_inactive_out; } - mlxsw_core->emad.trans_active = true; ret = wait_event_timeout(mlxsw_core->emad.wait, !(mlxsw_core->emad.trans_active), msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_MS)); if (!ret) { dev_warn(mlxsw_core->bus_info->dev, "EMAD timed-out (tid=%llx)\n", mlxsw_core->emad.tid); - mlxsw_core->emad.trans_active = false; - return -EIO; + err = -EIO; + goto trans_inactive_out; } return 0; + +trans_inactive_out: + mlxsw_core->emad.trans_active = false; + return err; } static int mlxsw_emad_process_status(struct mlxsw_core *mlxsw_core, @@ -506,7 +511,6 @@ static int mlxsw_emad_traps_set(struct mlxsw_core *mlxsw_core) return err; mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_TRAP_TO_CPU, - MLXSW_REG_HTGT_TRAP_GROUP_EMAD, MLXSW_TRAP_ID_ETHEMAD); return mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl); } @@ -551,8 +555,8 @@ static void mlxsw_emad_fini(struct mlxsw_core *mlxsw_core) { char hpkt_pl[MLXSW_REG_HPKT_LEN]; + mlxsw_core->emad.use_emad = false; mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_DISCARD, - MLXSW_REG_HTGT_TRAP_GROUP_EMAD, MLXSW_TRAP_ID_ETHEMAD); mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 165808471188..807827350a89 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -54,6 +54,7 @@ MODULE_ALIAS(MLXSW_MODULE_ALIAS_PREFIX kind) #define MLXSW_DEVICE_KIND_SWITCHX2 "switchx2" +#define MLXSW_DEVICE_KIND_SPECTRUM "spectrum" struct mlxsw_core; struct mlxsw_driver; @@ -153,6 +154,10 @@ struct mlxsw_config_profile { u8 max_flood_tables; u8 max_vid_flood_tables; u8 flood_mode; + u8 max_fid_offset_flood_tables; + u16 fid_offset_flood_table_size; + u8 max_fid_flood_tables; + u16 fid_flood_table_size; u16 max_ib_mc; u16 max_pkey; u8 ar_sec; diff --git a/drivers/net/ethernet/mellanox/mlxsw/item.h b/drivers/net/ethernet/mellanox/mlxsw/item.h index ffd55d030ce2..a94dbda6590b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/item.h +++ b/drivers/net/ethernet/mellanox/mlxsw/item.h @@ -171,15 +171,21 @@ static inline void __mlxsw_item_set64(char *buf, struct mlxsw_item *item, } static inline void __mlxsw_item_memcpy_from(char *buf, char *dst, - struct mlxsw_item *item) + struct mlxsw_item *item, + unsigned short index) { - memcpy(dst, &buf[item->offset], item->size.bytes); + unsigned int offset = __mlxsw_item_offset(item, index, sizeof(char)); + + memcpy(dst, &buf[offset], item->size.bytes); } -static inline void __mlxsw_item_memcpy_to(char *buf, char *src, - struct mlxsw_item *item) +static inline void __mlxsw_item_memcpy_to(char *buf, const char *src, + struct mlxsw_item *item, + unsigned short index) { - memcpy(&buf[item->offset], src, item->size.bytes); + unsigned int offset = __mlxsw_item_offset(item, index, sizeof(char)); + + memcpy(&buf[offset], src, item->size.bytes); } static inline u16 @@ -187,6 +193,7 @@ __mlxsw_item_bit_array_offset(struct mlxsw_item *item, u16 index, u8 *shift) { u16 max_index, be_index; u16 offset; /* byte offset inside the array */ + u8 in_byte_index; BUG_ON(index && !item->element_size); if (item->offset % sizeof(u32) != 0 || @@ -199,7 +206,8 @@ __mlxsw_item_bit_array_offset(struct mlxsw_item *item, u16 index, u8 *shift) max_index = (item->size.bytes << 3) / item->element_size - 1; be_index = max_index - index; offset = be_index * item->element_size >> 3; - *shift = index % (BITS_PER_BYTE / item->element_size) << 1; + in_byte_index = index % (BITS_PER_BYTE / item->element_size); + *shift = in_byte_index * item->element_size; return item->offset + offset; } @@ -371,12 +379,40 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ static inline void \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(char *buf, char *dst) \ { \ - __mlxsw_item_memcpy_from(buf, dst, &__ITEM_NAME(_type, _cname, _iname));\ + __mlxsw_item_memcpy_from(buf, dst, \ + &__ITEM_NAME(_type, _cname, _iname), 0); \ +} \ +static inline void \ +mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, const char *src) \ +{ \ + __mlxsw_item_memcpy_to(buf, src, \ + &__ITEM_NAME(_type, _cname, _iname), 0); \ +} + +#define MLXSW_ITEM_BUF_INDEXED(_type, _cname, _iname, _offset, _sizebytes, \ + _step, _instepoffset) \ +static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ + .offset = _offset, \ + .step = _step, \ + .in_step_offset = _instepoffset, \ + .size = {.bytes = _sizebytes,}, \ + .name = #_type "_" #_cname "_" #_iname, \ +}; \ +static inline void \ +mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(char *buf, \ + unsigned short index, \ + char *dst) \ +{ \ + __mlxsw_item_memcpy_from(buf, dst, \ + &__ITEM_NAME(_type, _cname, _iname), index); \ } \ static inline void \ -mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, char *src) \ +mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, \ + unsigned short index, \ + const char *src) \ { \ - __mlxsw_item_memcpy_to(buf, src, &__ITEM_NAME(_type, _cname, _iname)); \ + __mlxsw_item_memcpy_to(buf, src, \ + &__ITEM_NAME(_type, _cname, _iname), index); \ } #define MLXSW_ITEM_BIT_ARRAY(_type, _cname, _iname, _offset, _sizebytes, \ diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 462cea31ecbb..371ea3f56aed 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -57,6 +57,7 @@ static const char mlxsw_pci_driver_name[] = "mlxsw_pci"; static const struct pci_device_id mlxsw_pci_id_table[] = { {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SWITCHX2), 0}, + {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM), 0}, {0, } }; @@ -67,6 +68,8 @@ static const char *mlxsw_pci_device_kind_get(const struct pci_device_id *id) switch (id->device) { case PCI_DEVICE_ID_MELLANOX_SWITCHX2: return MLXSW_DEVICE_KIND_SWITCHX2; + case PCI_DEVICE_ID_MELLANOX_SPECTRUM: + return MLXSW_DEVICE_KIND_SPECTRUM; default: BUG(); } @@ -171,8 +174,8 @@ struct mlxsw_pci { struct msix_entry msix_entry; struct mlxsw_core *core; struct { - u16 num_pages; struct mlxsw_pci_mem_item *items; + unsigned int count; } fw_area; struct { struct mlxsw_pci_mem_item out_mbox; @@ -431,8 +434,7 @@ static int mlxsw_pci_wqe_frag_map(struct mlxsw_pci *mlxsw_pci, char *wqe, mapaddr = pci_map_single(pdev, frag_data, frag_len, direction); if (unlikely(pci_dma_mapping_error(pdev, mapaddr))) { - if (net_ratelimit()) - dev_err(&pdev->dev, "failed to dma map tx frag\n"); + dev_err_ratelimited(&pdev->dev, "failed to dma map tx frag\n"); return -EIO; } mlxsw_pci_wqe_address_set(wqe, index, mapaddr); @@ -497,6 +499,7 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, struct mlxsw_pci_queue *q) { struct mlxsw_pci_queue_elem_info *elem_info; + u8 sdq_count = mlxsw_pci_sdq_count(mlxsw_pci); int i; int err; @@ -504,9 +507,9 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, q->consumer_counter = 0; /* Set CQ of same number of this RDQ with base - * above MLXSW_PCI_SDQS_MAX as the lower ones are assigned to SDQs. + * above SDQ count as the lower ones are assigned to SDQs. */ - mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, q->num + MLXSW_PCI_SDQS_COUNT); + mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, sdq_count + q->num); mlxsw_cmd_mbox_sw2hw_dq_log2_dq_sz_set(mbox, 3); /* 8 pages */ for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) { dma_addr_t mapaddr = __mlxsw_pci_queue_page_get(q, i); @@ -699,8 +702,8 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, put_new_skb: memset(wqe, 0, q->elem_size); err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info); - if (err && net_ratelimit()) - dev_dbg(&pdev->dev, "Failed to alloc skb for RDQ\n"); + if (err) + dev_dbg_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n"); /* Everything is set up, ring doorbell to pass elem to HW */ q->producer_counter++; mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q); @@ -830,7 +833,8 @@ static void mlxsw_pci_eq_tasklet(unsigned long data) { struct mlxsw_pci_queue *q = (struct mlxsw_pci_queue *) data; struct mlxsw_pci *mlxsw_pci = q->pci; - unsigned long active_cqns[BITS_TO_LONGS(MLXSW_PCI_CQS_COUNT)]; + u8 cq_count = mlxsw_pci_cq_count(mlxsw_pci); + unsigned long active_cqns[BITS_TO_LONGS(MLXSW_PCI_CQS_MAX)]; char *eqe; u8 cqn; bool cq_handle = false; @@ -866,7 +870,7 @@ static void mlxsw_pci_eq_tasklet(unsigned long data) if (!cq_handle) return; - for_each_set_bit(cqn, active_cqns, MLXSW_PCI_CQS_COUNT) { + for_each_set_bit(cqn, active_cqns, cq_count) { q = mlxsw_pci_cq_get(mlxsw_pci, cqn); mlxsw_pci_queue_tasklet_schedule(q); } @@ -1067,10 +1071,8 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox) num_eqs = mlxsw_cmd_mbox_query_aq_cap_max_num_eqs_get(mbox); eq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_eq_sz_get(mbox); - if ((num_sdqs != MLXSW_PCI_SDQS_COUNT) || - (num_rdqs != MLXSW_PCI_RDQS_COUNT) || - (num_cqs != MLXSW_PCI_CQS_COUNT) || - (num_eqs != MLXSW_PCI_EQS_COUNT)) { + if (num_sdqs + num_rdqs > num_cqs || + num_cqs > MLXSW_PCI_CQS_MAX || num_eqs != MLXSW_PCI_EQS_COUNT) { dev_err(&pdev->dev, "Unsupported number of queues\n"); return -EINVAL; } @@ -1215,6 +1217,14 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox, mbox, profile->max_flood_tables); mlxsw_cmd_mbox_config_profile_max_vid_flood_tables_set( mbox, profile->max_vid_flood_tables); + mlxsw_cmd_mbox_config_profile_max_fid_offset_flood_tables_set( + mbox, profile->max_fid_offset_flood_tables); + mlxsw_cmd_mbox_config_profile_fid_offset_flood_table_size_set( + mbox, profile->fid_offset_flood_table_size); + mlxsw_cmd_mbox_config_profile_max_fid_flood_tables_set( + mbox, profile->max_fid_flood_tables); + mlxsw_cmd_mbox_config_profile_fid_flood_table_size_set( + mbox, profile->fid_flood_table_size); } if (profile->used_flood_mode) { mlxsw_cmd_mbox_config_profile_set_flood_mode_set( @@ -1272,6 +1282,7 @@ static int mlxsw_pci_fw_area_init(struct mlxsw_pci *mlxsw_pci, char *mbox, u16 num_pages) { struct mlxsw_pci_mem_item *mem_item; + int nent = 0; int i; int err; @@ -1279,7 +1290,7 @@ static int mlxsw_pci_fw_area_init(struct mlxsw_pci *mlxsw_pci, char *mbox, GFP_KERNEL); if (!mlxsw_pci->fw_area.items) return -ENOMEM; - mlxsw_pci->fw_area.num_pages = num_pages; + mlxsw_pci->fw_area.count = num_pages; mlxsw_cmd_mbox_zero(mbox); for (i = 0; i < num_pages; i++) { @@ -1293,13 +1304,22 @@ static int mlxsw_pci_fw_area_init(struct mlxsw_pci *mlxsw_pci, char *mbox, err = -ENOMEM; goto err_alloc; } - mlxsw_cmd_mbox_map_fa_pa_set(mbox, i, mem_item->mapaddr); - mlxsw_cmd_mbox_map_fa_log2size_set(mbox, i, 0); /* 1 page */ + mlxsw_cmd_mbox_map_fa_pa_set(mbox, nent, mem_item->mapaddr); + mlxsw_cmd_mbox_map_fa_log2size_set(mbox, nent, 0); /* 1 page */ + if (++nent == MLXSW_CMD_MAP_FA_VPM_ENTRIES_MAX) { + err = mlxsw_cmd_map_fa(mlxsw_pci->core, mbox, nent); + if (err) + goto err_cmd_map_fa; + nent = 0; + mlxsw_cmd_mbox_zero(mbox); + } } - err = mlxsw_cmd_map_fa(mlxsw_pci->core, mbox, num_pages); - if (err) - goto err_cmd_map_fa; + if (nent) { + err = mlxsw_cmd_map_fa(mlxsw_pci->core, mbox, nent); + if (err) + goto err_cmd_map_fa; + } return 0; @@ -1322,7 +1342,7 @@ static void mlxsw_pci_fw_area_fini(struct mlxsw_pci *mlxsw_pci) mlxsw_cmd_unmap_fa(mlxsw_pci->core); - for (i = 0; i < mlxsw_pci->fw_area.num_pages; i++) { + for (i = 0; i < mlxsw_pci->fw_area.count; i++) { mem_item = &mlxsw_pci->fw_area.items[i]; pci_free_consistent(mlxsw_pci->pdev, mem_item->size, @@ -1582,11 +1602,11 @@ static int mlxsw_pci_cmd_exec(void *bus_priv, u16 opcode, u8 opcode_mod, if (in_mbox) memcpy(mlxsw_pci->cmd.in_mbox.buf, in_mbox, in_mbox_size); - mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_HI, in_mapaddr >> 32); - mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_LO, in_mapaddr); + mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_HI, upper_32_bits(in_mapaddr)); + mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_LO, lower_32_bits(in_mapaddr)); - mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_HI, out_mapaddr >> 32); - mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_LO, out_mapaddr); + mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_HI, upper_32_bits(out_mapaddr)); + mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_LO, lower_32_bits(out_mapaddr)); mlxsw_pci_write32(mlxsw_pci, CIR_IN_MODIFIER, in_mod); mlxsw_pci_write32(mlxsw_pci, CIR_TOKEN, 0); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h index 1ef9664b4512..142f33d978c5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h @@ -40,6 +40,7 @@ #include "item.h" #define PCI_DEVICE_ID_MELLANOX_SWITCHX2 0xc738 +#define PCI_DEVICE_ID_MELLANOX_SPECTRUM 0xcb84 #define MLXSW_PCI_BAR0_SIZE (1024 * 1024) /* 1MB */ #define MLXSW_PCI_PAGE_SIZE 4096 @@ -71,9 +72,7 @@ #define MLXSW_PCI_DOORBELL(offset, type_offset, num) \ ((offset) + (type_offset) + (num) * 4) -#define MLXSW_PCI_RDQS_COUNT 24 -#define MLXSW_PCI_SDQS_COUNT 24 -#define MLXSW_PCI_CQS_COUNT (MLXSW_PCI_RDQS_COUNT + MLXSW_PCI_SDQS_COUNT) +#define MLXSW_PCI_CQS_MAX 96 #define MLXSW_PCI_EQS_COUNT 2 #define MLXSW_PCI_EQ_ASYNC_NUM 0 #define MLXSW_PCI_EQ_COMP_NUM 1 diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 096e1c12175a..4fcba46bbae0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -99,57 +99,6 @@ static const struct mlxsw_reg_info mlxsw_reg_spad = { */ MLXSW_ITEM_BUF(reg, spad, base_mac, 0x02, 6); -/* SMID - Switch Multicast ID - * -------------------------- - * In multi-chip configuration, each device should maintain mapping between - * Multicast ID (MID) into a list of local ports. This mapping is used in all - * the devices other than the ingress device, and is implemented as part of the - * FDB. The MID record maps from a MID, which is a unique identi- fier of the - * multicast group within the stacking domain, into a list of local ports into - * which the packet is replicated. - */ -#define MLXSW_REG_SMID_ID 0x2007 -#define MLXSW_REG_SMID_LEN 0x420 - -static const struct mlxsw_reg_info mlxsw_reg_smid = { - .id = MLXSW_REG_SMID_ID, - .len = MLXSW_REG_SMID_LEN, -}; - -/* reg_smid_swid - * Switch partition ID. - * Access: Index - */ -MLXSW_ITEM32(reg, smid, swid, 0x00, 24, 8); - -/* reg_smid_mid - * Multicast identifier - global identifier that represents the multicast group - * across all devices - * Access: Index - */ -MLXSW_ITEM32(reg, smid, mid, 0x00, 0, 16); - -/* reg_smid_port - * Local port memebership (1 bit per port). - * Access: RW - */ -MLXSW_ITEM_BIT_ARRAY(reg, smid, port, 0x20, 0x20, 1); - -/* reg_smid_port_mask - * Local port mask (1 bit per port). - * Access: W - */ -MLXSW_ITEM_BIT_ARRAY(reg, smid, port_mask, 0x220, 0x20, 1); - -static inline void mlxsw_reg_smid_pack(char *payload, u16 mid) -{ - MLXSW_REG_ZERO(smid, payload); - mlxsw_reg_smid_swid_set(payload, 0); - mlxsw_reg_smid_mid_set(payload, mid); - mlxsw_reg_smid_port_set(payload, MLXSW_PORT_CPU_PORT, 1); - mlxsw_reg_smid_port_mask_set(payload, MLXSW_PORT_CPU_PORT, 1); -} - /* SSPR - Switch System Port Record Register * ----------------------------------------- * Configures the system port to local port mapping. @@ -208,11 +157,359 @@ static inline void mlxsw_reg_sspr_pack(char *payload, u8 local_port) mlxsw_reg_sspr_system_port_set(payload, local_port); } +/* SFDAT - Switch Filtering Database Aging Time + * -------------------------------------------- + * Controls the Switch aging time. Aging time is able to be set per Switch + * Partition. + */ +#define MLXSW_REG_SFDAT_ID 0x2009 +#define MLXSW_REG_SFDAT_LEN 0x8 + +static const struct mlxsw_reg_info mlxsw_reg_sfdat = { + .id = MLXSW_REG_SFDAT_ID, + .len = MLXSW_REG_SFDAT_LEN, +}; + +/* reg_sfdat_swid + * Switch partition ID. + * Access: Index + */ +MLXSW_ITEM32(reg, sfdat, swid, 0x00, 24, 8); + +/* reg_sfdat_age_time + * Aging time in seconds + * Min - 10 seconds + * Max - 1,000,000 seconds + * Default is 300 seconds. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdat, age_time, 0x04, 0, 20); + +static inline void mlxsw_reg_sfdat_pack(char *payload, u32 age_time) +{ + MLXSW_REG_ZERO(sfdat, payload); + mlxsw_reg_sfdat_swid_set(payload, 0); + mlxsw_reg_sfdat_age_time_set(payload, age_time); +} + +/* SFD - Switch Filtering Database + * ------------------------------- + * The following register defines the access to the filtering database. + * The register supports querying, adding, removing and modifying the database. + * The access is optimized for bulk updates in which case more than one + * FDB record is present in the same command. + */ +#define MLXSW_REG_SFD_ID 0x200A +#define MLXSW_REG_SFD_BASE_LEN 0x10 /* base length, without records */ +#define MLXSW_REG_SFD_REC_LEN 0x10 /* record length */ +#define MLXSW_REG_SFD_REC_MAX_COUNT 64 +#define MLXSW_REG_SFD_LEN (MLXSW_REG_SFD_BASE_LEN + \ + MLXSW_REG_SFD_REC_LEN * MLXSW_REG_SFD_REC_MAX_COUNT) + +static const struct mlxsw_reg_info mlxsw_reg_sfd = { + .id = MLXSW_REG_SFD_ID, + .len = MLXSW_REG_SFD_LEN, +}; + +/* reg_sfd_swid + * Switch partition ID for queries. Reserved on Write. + * Access: Index + */ +MLXSW_ITEM32(reg, sfd, swid, 0x00, 24, 8); + +enum mlxsw_reg_sfd_op { + /* Dump entire FDB a (process according to record_locator) */ + MLXSW_REG_SFD_OP_QUERY_DUMP = 0, + /* Query records by {MAC, VID/FID} value */ + MLXSW_REG_SFD_OP_QUERY_QUERY = 1, + /* Query and clear activity. Query records by {MAC, VID/FID} value */ + MLXSW_REG_SFD_OP_QUERY_QUERY_AND_CLEAR_ACTIVITY = 2, + /* Test. Response indicates if each of the records could be + * added to the FDB. + */ + MLXSW_REG_SFD_OP_WRITE_TEST = 0, + /* Add/modify. Aged-out records cannot be added. This command removes + * the learning notification of the {MAC, VID/FID}. Response includes + * the entries that were added to the FDB. + */ + MLXSW_REG_SFD_OP_WRITE_EDIT = 1, + /* Remove record by {MAC, VID/FID}. This command also removes + * the learning notification and aged-out notifications + * of the {MAC, VID/FID}. The response provides current (pre-removal) + * entries as non-aged-out. + */ + MLXSW_REG_SFD_OP_WRITE_REMOVE = 2, + /* Remove learned notification by {MAC, VID/FID}. The response provides + * the removed learning notification. + */ + MLXSW_REG_SFD_OP_WRITE_REMOVE_NOTIFICATION = 2, +}; + +/* reg_sfd_op + * Operation. + * Access: OP + */ +MLXSW_ITEM32(reg, sfd, op, 0x04, 30, 2); + +/* reg_sfd_record_locator + * Used for querying the FDB. Use record_locator=0 to initiate the + * query. When a record is returned, a new record_locator is + * returned to be used in the subsequent query. + * Reserved for database update. + * Access: Index + */ +MLXSW_ITEM32(reg, sfd, record_locator, 0x04, 0, 30); + +/* reg_sfd_num_rec + * Request: Number of records to read/add/modify/remove + * Response: Number of records read/added/replaced/removed + * See above description for more details. + * Ranges 0..64 + * Access: RW + */ +MLXSW_ITEM32(reg, sfd, num_rec, 0x08, 0, 8); + +static inline void mlxsw_reg_sfd_pack(char *payload, enum mlxsw_reg_sfd_op op, + u32 record_locator) +{ + MLXSW_REG_ZERO(sfd, payload); + mlxsw_reg_sfd_op_set(payload, op); + mlxsw_reg_sfd_record_locator_set(payload, record_locator); +} + +/* reg_sfd_rec_swid + * Switch partition ID. + * Access: Index + */ +MLXSW_ITEM32_INDEXED(reg, sfd, rec_swid, MLXSW_REG_SFD_BASE_LEN, 24, 8, + MLXSW_REG_SFD_REC_LEN, 0x00, false); + +enum mlxsw_reg_sfd_rec_type { + MLXSW_REG_SFD_REC_TYPE_UNICAST = 0x0, +}; + +/* reg_sfd_rec_type + * FDB record type. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, sfd, rec_type, MLXSW_REG_SFD_BASE_LEN, 20, 4, + MLXSW_REG_SFD_REC_LEN, 0x00, false); + +enum mlxsw_reg_sfd_rec_policy { + /* Replacement disabled, aging disabled. */ + MLXSW_REG_SFD_REC_POLICY_STATIC_ENTRY = 0, + /* (mlag remote): Replacement enabled, aging disabled, + * learning notification enabled on this port. + */ + MLXSW_REG_SFD_REC_POLICY_DYNAMIC_ENTRY_MLAG = 1, + /* (ingress device): Replacement enabled, aging enabled. */ + MLXSW_REG_SFD_REC_POLICY_DYNAMIC_ENTRY_INGRESS = 3, +}; + +/* reg_sfd_rec_policy + * Policy. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, sfd, rec_policy, MLXSW_REG_SFD_BASE_LEN, 18, 2, + MLXSW_REG_SFD_REC_LEN, 0x00, false); + +/* reg_sfd_rec_a + * Activity. Set for new static entries. Set for static entries if a frame SMAC + * lookup hits on the entry. + * To clear the a bit, use "query and clear activity" op. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, sfd, rec_a, MLXSW_REG_SFD_BASE_LEN, 16, 1, + MLXSW_REG_SFD_REC_LEN, 0x00, false); + +/* reg_sfd_rec_mac + * MAC address. + * Access: Index + */ +MLXSW_ITEM_BUF_INDEXED(reg, sfd, rec_mac, MLXSW_REG_SFD_BASE_LEN, 6, + MLXSW_REG_SFD_REC_LEN, 0x02); + +enum mlxsw_reg_sfd_rec_action { + /* forward */ + MLXSW_REG_SFD_REC_ACTION_NOP = 0, + /* 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_DISCARD_ERROR = 15, +}; + +/* reg_sfd_rec_action + * Action to apply on the packet. + * Note: Dynamic entries can only be configured with NOP action. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, sfd, rec_action, MLXSW_REG_SFD_BASE_LEN, 28, 4, + MLXSW_REG_SFD_REC_LEN, 0x0C, false); + +/* reg_sfd_uc_sub_port + * LAG sub port. + * Must be 0 if multichannel VEPA is not enabled. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, sfd, uc_sub_port, MLXSW_REG_SFD_BASE_LEN, 16, 8, + MLXSW_REG_SFD_REC_LEN, 0x08, false); + +/* reg_sfd_uc_fid_vid + * Filtering ID or VLAN ID + * For SwitchX and SwitchX-2: + * - Dynamic entries (policy 2,3) use FID + * - Static entries (policy 0) use VID + * - When independent learning is configured, VID=FID + * For Spectrum: use FID for both Dynamic and Static entries. + * VID should not be used. + * Access: Index + */ +MLXSW_ITEM32_INDEXED(reg, sfd, uc_fid_vid, MLXSW_REG_SFD_BASE_LEN, 0, 16, + MLXSW_REG_SFD_REC_LEN, 0x08, false); + +/* reg_sfd_uc_system_port + * Unique port identifier for the final destination of the packet. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, sfd, uc_system_port, MLXSW_REG_SFD_BASE_LEN, 0, 16, + MLXSW_REG_SFD_REC_LEN, 0x0C, false); + +static inline void mlxsw_reg_sfd_uc_pack(char *payload, int rec_index, + enum mlxsw_reg_sfd_rec_policy policy, + const char *mac, u16 vid, + enum mlxsw_reg_sfd_rec_action action, + u8 local_port) +{ + u8 num_rec = mlxsw_reg_sfd_num_rec_get(payload); + + if (rec_index >= num_rec) + mlxsw_reg_sfd_num_rec_set(payload, rec_index + 1); + mlxsw_reg_sfd_rec_swid_set(payload, rec_index, 0); + mlxsw_reg_sfd_rec_type_set(payload, rec_index, + MLXSW_REG_SFD_REC_TYPE_UNICAST); + mlxsw_reg_sfd_rec_policy_set(payload, rec_index, policy); + mlxsw_reg_sfd_rec_mac_memcpy_to(payload, rec_index, mac); + mlxsw_reg_sfd_uc_sub_port_set(payload, rec_index, 0); + mlxsw_reg_sfd_uc_fid_vid_set(payload, rec_index, vid); + mlxsw_reg_sfd_rec_action_set(payload, rec_index, action); + mlxsw_reg_sfd_uc_system_port_set(payload, rec_index, local_port); +} + +static inline void +mlxsw_reg_sfd_uc_unpack(char *payload, int rec_index, + char *mac, u16 *p_vid, + u8 *p_local_port) +{ + mlxsw_reg_sfd_rec_mac_memcpy_from(payload, rec_index, mac); + *p_vid = mlxsw_reg_sfd_uc_fid_vid_get(payload, rec_index); + *p_local_port = mlxsw_reg_sfd_uc_system_port_get(payload, rec_index); +} + +/* SFN - Switch FDB Notification Register + * ------------------------------------------- + * The switch provides notifications on newly learned FDB entries and + * aged out entries. The notifications can be polled by software. + */ +#define MLXSW_REG_SFN_ID 0x200B +#define MLXSW_REG_SFN_BASE_LEN 0x10 /* base length, without records */ +#define MLXSW_REG_SFN_REC_LEN 0x10 /* record length */ +#define MLXSW_REG_SFN_REC_MAX_COUNT 64 +#define MLXSW_REG_SFN_LEN (MLXSW_REG_SFN_BASE_LEN + \ + MLXSW_REG_SFN_REC_LEN * MLXSW_REG_SFN_REC_MAX_COUNT) + +static const struct mlxsw_reg_info mlxsw_reg_sfn = { + .id = MLXSW_REG_SFN_ID, + .len = MLXSW_REG_SFN_LEN, +}; + +/* reg_sfn_swid + * Switch partition ID. + * Access: Index + */ +MLXSW_ITEM32(reg, sfn, swid, 0x00, 24, 8); + +/* reg_sfn_num_rec + * Request: Number of learned notifications and aged-out notification + * records requested. + * Response: Number of notification records returned (must be smaller + * than or equal to the value requested) + * Ranges 0..64 + * Access: OP + */ +MLXSW_ITEM32(reg, sfn, num_rec, 0x04, 0, 8); + +static inline void mlxsw_reg_sfn_pack(char *payload) +{ + MLXSW_REG_ZERO(sfn, payload); + mlxsw_reg_sfn_swid_set(payload, 0); + mlxsw_reg_sfn_num_rec_set(payload, MLXSW_REG_SFN_REC_MAX_COUNT); +} + +/* reg_sfn_rec_swid + * Switch partition ID. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, sfn, rec_swid, MLXSW_REG_SFN_BASE_LEN, 24, 8, + MLXSW_REG_SFN_REC_LEN, 0x00, false); + +enum mlxsw_reg_sfn_rec_type { + /* MAC addresses learned on a regular port. */ + MLXSW_REG_SFN_REC_TYPE_LEARNED_MAC = 0x5, + /* Aged-out MAC address on a regular port */ + MLXSW_REG_SFN_REC_TYPE_AGED_OUT_MAC = 0x7, +}; + +/* reg_sfn_rec_type + * Notification record type. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, sfn, rec_type, MLXSW_REG_SFN_BASE_LEN, 20, 4, + MLXSW_REG_SFN_REC_LEN, 0x00, false); + +/* reg_sfn_rec_mac + * MAC address. + * Access: RO + */ +MLXSW_ITEM_BUF_INDEXED(reg, sfn, rec_mac, MLXSW_REG_SFN_BASE_LEN, 6, + MLXSW_REG_SFN_REC_LEN, 0x02); + +/* reg_sfd_mac_sub_port + * VEPA channel on the local port. + * 0 if multichannel VEPA is not enabled. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, sfn, mac_sub_port, MLXSW_REG_SFN_BASE_LEN, 16, 8, + MLXSW_REG_SFN_REC_LEN, 0x08, false); + +/* reg_sfd_mac_fid + * Filtering identifier. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, sfn, mac_fid, MLXSW_REG_SFN_BASE_LEN, 0, 16, + MLXSW_REG_SFN_REC_LEN, 0x08, false); + +/* reg_sfd_mac_system_port + * Unique port identifier for the final destination of the packet. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, sfn, mac_system_port, MLXSW_REG_SFN_BASE_LEN, 0, 16, + MLXSW_REG_SFN_REC_LEN, 0x0C, false); + +static inline void mlxsw_reg_sfn_mac_unpack(char *payload, int rec_index, + char *mac, u16 *p_vid, + u8 *p_local_port) +{ + mlxsw_reg_sfn_rec_mac_memcpy_from(payload, rec_index, mac); + *p_vid = mlxsw_reg_sfn_mac_fid_get(payload, rec_index); + *p_local_port = mlxsw_reg_sfn_mac_system_port_get(payload, rec_index); +} + /* SPMS - Switch Port MSTP/RSTP State Register * ------------------------------------------- * Configures the spanning tree state of a physical port. */ -#define MLXSW_REG_SPMS_ID 0x200d +#define MLXSW_REG_SPMS_ID 0x200D #define MLXSW_REG_SPMS_LEN 0x404 static const struct mlxsw_reg_info mlxsw_reg_spms = { @@ -243,20 +540,166 @@ enum mlxsw_reg_spms_state { */ MLXSW_ITEM_BIT_ARRAY(reg, spms, state, 0x04, 0x400, 2); -static inline void mlxsw_reg_spms_pack(char *payload, u8 local_port, u16 vid, - enum mlxsw_reg_spms_state state) +static inline void mlxsw_reg_spms_pack(char *payload, u8 local_port) { MLXSW_REG_ZERO(spms, payload); mlxsw_reg_spms_local_port_set(payload, local_port); +} + +static inline void mlxsw_reg_spms_vid_pack(char *payload, u16 vid, + enum mlxsw_reg_spms_state state) +{ mlxsw_reg_spms_state_set(payload, vid, state); } +/* SPVID - Switch Port VID + * ----------------------- + * The switch port VID configures the default VID for a port. + */ +#define MLXSW_REG_SPVID_ID 0x200E +#define MLXSW_REG_SPVID_LEN 0x08 + +static const struct mlxsw_reg_info mlxsw_reg_spvid = { + .id = MLXSW_REG_SPVID_ID, + .len = MLXSW_REG_SPVID_LEN, +}; + +/* reg_spvid_local_port + * Local port number. + * Access: Index + */ +MLXSW_ITEM32(reg, spvid, local_port, 0x00, 16, 8); + +/* reg_spvid_sub_port + * Virtual port within the physical port. + * Should be set to 0 when virtual ports are not enabled on the port. + * Access: Index + */ +MLXSW_ITEM32(reg, spvid, sub_port, 0x00, 8, 8); + +/* reg_spvid_pvid + * Port default VID + * Access: RW + */ +MLXSW_ITEM32(reg, spvid, pvid, 0x04, 0, 12); + +static inline void mlxsw_reg_spvid_pack(char *payload, u8 local_port, u16 pvid) +{ + MLXSW_REG_ZERO(spvid, payload); + mlxsw_reg_spvid_local_port_set(payload, local_port); + mlxsw_reg_spvid_pvid_set(payload, pvid); +} + +/* SPVM - Switch Port VLAN Membership + * ---------------------------------- + * The Switch Port VLAN Membership register configures the VLAN membership + * of a port in a VLAN denoted by VID. VLAN membership is managed per + * virtual port. The register can be used to add and remove VID(s) from a port. + */ +#define MLXSW_REG_SPVM_ID 0x200F +#define MLXSW_REG_SPVM_BASE_LEN 0x04 /* base length, without records */ +#define MLXSW_REG_SPVM_REC_LEN 0x04 /* record length */ +#define MLXSW_REG_SPVM_REC_MAX_COUNT 256 +#define MLXSW_REG_SPVM_LEN (MLXSW_REG_SPVM_BASE_LEN + \ + MLXSW_REG_SPVM_REC_LEN * MLXSW_REG_SPVM_REC_MAX_COUNT) + +static const struct mlxsw_reg_info mlxsw_reg_spvm = { + .id = MLXSW_REG_SPVM_ID, + .len = MLXSW_REG_SPVM_LEN, +}; + +/* reg_spvm_pt + * Priority tagged. If this bit is set, packets forwarded to the port with + * untagged VLAN membership (u bit is set) will be tagged with priority tag + * (VID=0) + * Access: RW + */ +MLXSW_ITEM32(reg, spvm, pt, 0x00, 31, 1); + +/* reg_spvm_pte + * Priority Tagged Update Enable. On Write operations, if this bit is cleared, + * the pt bit will NOT be updated. To update the pt bit, pte must be set. + * Access: WO + */ +MLXSW_ITEM32(reg, spvm, pte, 0x00, 30, 1); + +/* reg_spvm_local_port + * Local port number. + * Access: Index + */ +MLXSW_ITEM32(reg, spvm, local_port, 0x00, 16, 8); + +/* reg_spvm_sub_port + * Virtual port within the physical port. + * Should be set to 0 when virtual ports are not enabled on the port. + * Access: Index + */ +MLXSW_ITEM32(reg, spvm, sub_port, 0x00, 8, 8); + +/* reg_spvm_num_rec + * Number of records to update. Each record contains: i, e, u, vid. + * Access: OP + */ +MLXSW_ITEM32(reg, spvm, num_rec, 0x00, 0, 8); + +/* reg_spvm_rec_i + * Ingress membership in VLAN ID. + * Access: Index + */ +MLXSW_ITEM32_INDEXED(reg, spvm, rec_i, + MLXSW_REG_SPVM_BASE_LEN, 14, 1, + MLXSW_REG_SPVM_REC_LEN, 0, false); + +/* reg_spvm_rec_e + * Egress membership in VLAN ID. + * Access: Index + */ +MLXSW_ITEM32_INDEXED(reg, spvm, rec_e, + MLXSW_REG_SPVM_BASE_LEN, 13, 1, + MLXSW_REG_SPVM_REC_LEN, 0, false); + +/* reg_spvm_rec_u + * Untagged - port is an untagged member - egress transmission uses untagged + * frames on VID<n> + * Access: Index + */ +MLXSW_ITEM32_INDEXED(reg, spvm, rec_u, + MLXSW_REG_SPVM_BASE_LEN, 12, 1, + MLXSW_REG_SPVM_REC_LEN, 0, false); + +/* reg_spvm_rec_vid + * Egress membership in VLAN ID. + * Access: Index + */ +MLXSW_ITEM32_INDEXED(reg, spvm, rec_vid, + MLXSW_REG_SPVM_BASE_LEN, 0, 12, + MLXSW_REG_SPVM_REC_LEN, 0, false); + +static inline void mlxsw_reg_spvm_pack(char *payload, u8 local_port, + u16 vid_begin, u16 vid_end, + bool is_member, bool untagged) +{ + int size = vid_end - vid_begin + 1; + int i; + + MLXSW_REG_ZERO(spvm, payload); + mlxsw_reg_spvm_local_port_set(payload, local_port); + mlxsw_reg_spvm_num_rec_set(payload, size); + + for (i = 0; i < size; i++) { + mlxsw_reg_spvm_rec_i_set(payload, i, is_member); + mlxsw_reg_spvm_rec_e_set(payload, i, is_member); + mlxsw_reg_spvm_rec_u_set(payload, i, untagged); + mlxsw_reg_spvm_rec_vid_set(payload, i, vid_begin + i); + } +} + /* SFGC - Switch Flooding Group Configuration * ------------------------------------------ * The following register controls the association of flooding tables and MIDs * to packet types used for flooding. */ -#define MLXSW_REG_SFGC_ID 0x2011 +#define MLXSW_REG_SFGC_ID 0x2011 #define MLXSW_REG_SFGC_LEN 0x10 static const struct mlxsw_reg_info mlxsw_reg_sfgc = { @@ -265,13 +708,15 @@ static const struct mlxsw_reg_info mlxsw_reg_sfgc = { }; enum mlxsw_reg_sfgc_type { - MLXSW_REG_SFGC_TYPE_BROADCAST = 0, - MLXSW_REG_SFGC_TYPE_UNKNOWN_UNICAST = 1, - MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV4 = 2, - MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6 = 3, - MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_NON_IP = 5, - MLXSW_REG_SFGC_TYPE_IPV4_LINK_LOCAL = 6, - MLXSW_REG_SFGC_TYPE_IPV6_ALL_HOST = 7, + MLXSW_REG_SFGC_TYPE_BROADCAST, + MLXSW_REG_SFGC_TYPE_UNKNOWN_UNICAST, + MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV4, + MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6, + MLXSW_REG_SFGC_TYPE_RESERVED, + MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_NON_IP, + MLXSW_REG_SFGC_TYPE_IPV4_LINK_LOCAL, + MLXSW_REG_SFGC_TYPE_IPV6_ALL_HOST, + MLXSW_REG_SFGC_TYPE_MAX, }; /* reg_sfgc_type @@ -408,7 +853,7 @@ static inline void mlxsw_reg_sftr_pack(char *payload, unsigned int flood_table, unsigned int index, enum mlxsw_flood_table_type table_type, - unsigned int range) + unsigned int range, u8 port, bool set) { MLXSW_REG_ZERO(sftr, payload); mlxsw_reg_sftr_swid_set(payload, 0); @@ -416,8 +861,8 @@ static inline void mlxsw_reg_sftr_pack(char *payload, mlxsw_reg_sftr_index_set(payload, index); mlxsw_reg_sftr_table_type_set(payload, table_type); mlxsw_reg_sftr_range_set(payload, range); - mlxsw_reg_sftr_port_set(payload, MLXSW_PORT_CPU_PORT, 1); - mlxsw_reg_sftr_port_mask_set(payload, MLXSW_PORT_CPU_PORT, 1); + mlxsw_reg_sftr_port_set(payload, port, set); + mlxsw_reg_sftr_port_mask_set(payload, port, 1); } /* SPMLR - Switch Port MAC Learning Register @@ -473,6 +918,285 @@ static inline void mlxsw_reg_spmlr_pack(char *payload, u8 local_port, mlxsw_reg_spmlr_learn_mode_set(payload, mode); } +/* SVFA - Switch VID to FID Allocation Register + * -------------------------------------------- + * Controls the VID to FID mapping and {Port, VID} to FID mapping for + * virtualized ports. + */ +#define MLXSW_REG_SVFA_ID 0x201C +#define MLXSW_REG_SVFA_LEN 0x10 + +static const struct mlxsw_reg_info mlxsw_reg_svfa = { + .id = MLXSW_REG_SVFA_ID, + .len = MLXSW_REG_SVFA_LEN, +}; + +/* reg_svfa_swid + * Switch partition ID. + * Access: Index + */ +MLXSW_ITEM32(reg, svfa, swid, 0x00, 24, 8); + +/* reg_svfa_local_port + * Local port number. + * Access: Index + * + * Note: Reserved for 802.1Q FIDs. + */ +MLXSW_ITEM32(reg, svfa, local_port, 0x00, 16, 8); + +enum mlxsw_reg_svfa_mt { + MLXSW_REG_SVFA_MT_VID_TO_FID, + MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, +}; + +/* reg_svfa_mapping_table + * Mapping table: + * 0 - VID to FID + * 1 - {Port, VID} to FID + * Access: Index + * + * Note: Reserved for SwitchX-2. + */ +MLXSW_ITEM32(reg, svfa, mapping_table, 0x00, 8, 3); + +/* reg_svfa_v + * Valid. + * Valid if set. + * Access: RW + * + * Note: Reserved for SwitchX-2. + */ +MLXSW_ITEM32(reg, svfa, v, 0x00, 0, 1); + +/* reg_svfa_fid + * Filtering ID. + * Access: RW + */ +MLXSW_ITEM32(reg, svfa, fid, 0x04, 16, 16); + +/* reg_svfa_vid + * VLAN ID. + * Access: Index + */ +MLXSW_ITEM32(reg, svfa, vid, 0x04, 0, 12); + +/* reg_svfa_counter_set_type + * Counter set type for flow counters. + * Access: RW + * + * Note: Reserved for SwitchX-2. + */ +MLXSW_ITEM32(reg, svfa, counter_set_type, 0x08, 24, 8); + +/* reg_svfa_counter_index + * Counter index for flow counters. + * Access: RW + * + * Note: Reserved for SwitchX-2. + */ +MLXSW_ITEM32(reg, svfa, counter_index, 0x08, 0, 24); + +static inline void mlxsw_reg_svfa_pack(char *payload, u8 local_port, + enum mlxsw_reg_svfa_mt mt, bool valid, + u16 fid, u16 vid) +{ + MLXSW_REG_ZERO(svfa, payload); + local_port = mt == MLXSW_REG_SVFA_MT_VID_TO_FID ? 0 : local_port; + mlxsw_reg_svfa_swid_set(payload, 0); + mlxsw_reg_svfa_local_port_set(payload, local_port); + mlxsw_reg_svfa_mapping_table_set(payload, mt); + mlxsw_reg_svfa_v_set(payload, valid); + mlxsw_reg_svfa_fid_set(payload, fid); + mlxsw_reg_svfa_vid_set(payload, vid); +} + +/* SVPE - Switch Virtual-Port Enabling Register + * -------------------------------------------- + * Enables port virtualization. + */ +#define MLXSW_REG_SVPE_ID 0x201E +#define MLXSW_REG_SVPE_LEN 0x4 + +static const struct mlxsw_reg_info mlxsw_reg_svpe = { + .id = MLXSW_REG_SVPE_ID, + .len = MLXSW_REG_SVPE_LEN, +}; + +/* reg_svpe_local_port + * Local port number + * Access: Index + * + * Note: CPU port is not supported (uses VLAN mode only). + */ +MLXSW_ITEM32(reg, svpe, local_port, 0x00, 16, 8); + +/* reg_svpe_vp_en + * Virtual port enable. + * 0 - Disable, VLAN mode (VID to FID). + * 1 - Enable, Virtual port mode ({Port, VID} to FID). + * Access: RW + */ +MLXSW_ITEM32(reg, svpe, vp_en, 0x00, 8, 1); + +static inline void mlxsw_reg_svpe_pack(char *payload, u8 local_port, + bool enable) +{ + MLXSW_REG_ZERO(svpe, payload); + mlxsw_reg_svpe_local_port_set(payload, local_port); + mlxsw_reg_svpe_vp_en_set(payload, enable); +} + +/* SFMR - Switch FID Management Register + * ------------------------------------- + * Creates and configures FIDs. + */ +#define MLXSW_REG_SFMR_ID 0x201F +#define MLXSW_REG_SFMR_LEN 0x18 + +static const struct mlxsw_reg_info mlxsw_reg_sfmr = { + .id = MLXSW_REG_SFMR_ID, + .len = MLXSW_REG_SFMR_LEN, +}; + +enum mlxsw_reg_sfmr_op { + MLXSW_REG_SFMR_OP_CREATE_FID, + MLXSW_REG_SFMR_OP_DESTROY_FID, +}; + +/* reg_sfmr_op + * Operation. + * 0 - Create or edit FID. + * 1 - Destroy FID. + * Access: WO + */ +MLXSW_ITEM32(reg, sfmr, op, 0x00, 24, 4); + +/* reg_sfmr_fid + * Filtering ID. + * Access: Index + */ +MLXSW_ITEM32(reg, sfmr, fid, 0x00, 0, 16); + +/* reg_sfmr_fid_offset + * FID offset. + * Used to point into the flooding table selected by SFGC register if + * the table is of type FID-Offset. Otherwise, this field is reserved. + * Access: RW + */ +MLXSW_ITEM32(reg, sfmr, fid_offset, 0x08, 0, 16); + +/* reg_sfmr_vtfp + * Valid Tunnel Flood Pointer. + * If not set, then nve_tunnel_flood_ptr is reserved and considered NULL. + * Access: RW + * + * Note: Reserved for 802.1Q FIDs. + */ +MLXSW_ITEM32(reg, sfmr, vtfp, 0x0C, 31, 1); + +/* reg_sfmr_nve_tunnel_flood_ptr + * Underlay Flooding and BC Pointer. + * Used as a pointer to the first entry of the group based link lists of + * flooding or BC entries (for NVE tunnels). + * Access: RW + */ +MLXSW_ITEM32(reg, sfmr, nve_tunnel_flood_ptr, 0x0C, 0, 24); + +/* reg_sfmr_vv + * VNI Valid. + * If not set, then vni is reserved. + * Access: RW + * + * Note: Reserved for 802.1Q FIDs. + */ +MLXSW_ITEM32(reg, sfmr, vv, 0x10, 31, 1); + +/* reg_sfmr_vni + * Virtual Network Identifier. + * Access: RW + * + * Note: A given VNI can only be assigned to one FID. + */ +MLXSW_ITEM32(reg, sfmr, vni, 0x10, 0, 24); + +static inline void mlxsw_reg_sfmr_pack(char *payload, + enum mlxsw_reg_sfmr_op op, u16 fid, + u16 fid_offset) +{ + MLXSW_REG_ZERO(sfmr, payload); + mlxsw_reg_sfmr_op_set(payload, op); + mlxsw_reg_sfmr_fid_set(payload, fid); + mlxsw_reg_sfmr_fid_offset_set(payload, fid_offset); + mlxsw_reg_sfmr_vtfp_set(payload, false); + mlxsw_reg_sfmr_vv_set(payload, false); +} + +/* SPVMLR - Switch Port VLAN MAC Learning Register + * ----------------------------------------------- + * Controls the switch MAC learning policy per {Port, VID}. + */ +#define MLXSW_REG_SPVMLR_ID 0x2020 +#define MLXSW_REG_SPVMLR_BASE_LEN 0x04 /* base length, without records */ +#define MLXSW_REG_SPVMLR_REC_LEN 0x04 /* record length */ +#define MLXSW_REG_SPVMLR_REC_MAX_COUNT 256 +#define MLXSW_REG_SPVMLR_LEN (MLXSW_REG_SPVMLR_BASE_LEN + \ + MLXSW_REG_SPVMLR_REC_LEN * \ + MLXSW_REG_SPVMLR_REC_MAX_COUNT) + +static const struct mlxsw_reg_info mlxsw_reg_spvmlr = { + .id = MLXSW_REG_SPVMLR_ID, + .len = MLXSW_REG_SPVMLR_LEN, +}; + +/* reg_spvmlr_local_port + * Local ingress port. + * Access: Index + * + * Note: CPU port is not supported. + */ +MLXSW_ITEM32(reg, spvmlr, local_port, 0x00, 16, 8); + +/* reg_spvmlr_num_rec + * Number of records to update. + * Access: OP + */ +MLXSW_ITEM32(reg, spvmlr, num_rec, 0x00, 0, 8); + +/* reg_spvmlr_rec_learn_enable + * 0 - Disable learning for {Port, VID}. + * 1 - Enable learning for {Port, VID}. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, spvmlr, rec_learn_enable, MLXSW_REG_SPVMLR_BASE_LEN, + 31, 1, MLXSW_REG_SPVMLR_REC_LEN, 0x00, false); + +/* reg_spvmlr_rec_vid + * VLAN ID to be added/removed from port or for querying. + * Access: Index + */ +MLXSW_ITEM32_INDEXED(reg, spvmlr, rec_vid, MLXSW_REG_SPVMLR_BASE_LEN, 0, 12, + MLXSW_REG_SPVMLR_REC_LEN, 0x00, false); + +static inline void mlxsw_reg_spvmlr_pack(char *payload, u8 local_port, + u16 vid_begin, u16 vid_end, + bool learn_enable) +{ + int num_rec = vid_end - vid_begin + 1; + int i; + + WARN_ON(num_rec < 1 || num_rec > MLXSW_REG_SPVMLR_REC_MAX_COUNT); + + MLXSW_REG_ZERO(spvmlr, payload); + mlxsw_reg_spvmlr_local_port_set(payload, local_port); + mlxsw_reg_spvmlr_num_rec_set(payload, num_rec); + + for (i = 0; i < num_rec; i++) { + mlxsw_reg_spvmlr_rec_learn_enable_set(payload, i, learn_enable); + mlxsw_reg_spvmlr_rec_vid_set(payload, i, vid_begin + i); + } +} + /* PMLP - Ports Module to Local Port Register * ------------------------------------------ * Configures the assignment of modules to local ports. @@ -1008,12 +1732,88 @@ static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port) mlxsw_reg_ppcnt_prio_tc_set(payload, 0); } +/* PBMC - Port Buffer Management Control Register + * ---------------------------------------------- + * The PBMC register configures and retrieves the port packet buffer + * allocation for different Prios, and the Pause threshold management. + */ +#define MLXSW_REG_PBMC_ID 0x500C +#define MLXSW_REG_PBMC_LEN 0x68 + +static const struct mlxsw_reg_info mlxsw_reg_pbmc = { + .id = MLXSW_REG_PBMC_ID, + .len = MLXSW_REG_PBMC_LEN, +}; + +/* reg_pbmc_local_port + * Local port number. + * Access: Index + */ +MLXSW_ITEM32(reg, pbmc, local_port, 0x00, 16, 8); + +/* reg_pbmc_xoff_timer_value + * When device generates a pause frame, it uses this value as the pause + * timer (time for the peer port to pause in quota-512 bit time). + * Access: RW + */ +MLXSW_ITEM32(reg, pbmc, xoff_timer_value, 0x04, 16, 16); + +/* reg_pbmc_xoff_refresh + * The time before a new pause frame should be sent to refresh the pause RW + * state. Using the same units as xoff_timer_value above (in quota-512 bit + * time). + * Access: RW + */ +MLXSW_ITEM32(reg, pbmc, xoff_refresh, 0x04, 0, 16); + +/* reg_pbmc_buf_lossy + * The field indicates if the buffer is lossy. + * 0 - Lossless + * 1 - Lossy + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, pbmc, buf_lossy, 0x0C, 25, 1, 0x08, 0x00, false); + +/* reg_pbmc_buf_epsb + * Eligible for Port Shared buffer. + * If epsb is set, packets assigned to buffer are allowed to insert the port + * shared buffer. + * When buf_lossy is MLXSW_REG_PBMC_LOSSY_LOSSY this field is reserved. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, pbmc, buf_epsb, 0x0C, 24, 1, 0x08, 0x00, false); + +/* reg_pbmc_buf_size + * The part of the packet buffer array is allocated for the specific buffer. + * Units are represented in cells. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, pbmc, buf_size, 0x0C, 0, 16, 0x08, 0x00, false); + +static inline void mlxsw_reg_pbmc_pack(char *payload, u8 local_port, + u16 xoff_timer_value, u16 xoff_refresh) +{ + MLXSW_REG_ZERO(pbmc, payload); + mlxsw_reg_pbmc_local_port_set(payload, local_port); + mlxsw_reg_pbmc_xoff_timer_value_set(payload, xoff_timer_value); + mlxsw_reg_pbmc_xoff_refresh_set(payload, xoff_refresh); +} + +static inline void mlxsw_reg_pbmc_lossy_buffer_pack(char *payload, + int buf_index, + u16 size) +{ + mlxsw_reg_pbmc_buf_lossy_set(payload, buf_index, 1); + mlxsw_reg_pbmc_buf_epsb_set(payload, buf_index, 0); + mlxsw_reg_pbmc_buf_size_set(payload, buf_index, size); +} + /* PSPA - Port Switch Partition Allocation * --------------------------------------- * Controls the association of a port with a switch partition and enables * configuring ports as stacking ports. */ -#define MLXSW_REG_PSPA_ID 0x500d +#define MLXSW_REG_PSPA_ID 0x500D #define MLXSW_REG_PSPA_LEN 0x8 static const struct mlxsw_reg_info mlxsw_reg_pspa = { @@ -1074,8 +1874,11 @@ MLXSW_ITEM32(reg, htgt, swid, 0x00, 24, 8); */ MLXSW_ITEM32(reg, htgt, type, 0x00, 8, 4); -#define MLXSW_REG_HTGT_TRAP_GROUP_EMAD 0x0 -#define MLXSW_REG_HTGT_TRAP_GROUP_RX 0x1 +enum mlxsw_reg_htgt_trap_group { + MLXSW_REG_HTGT_TRAP_GROUP_EMAD, + MLXSW_REG_HTGT_TRAP_GROUP_RX, + MLXSW_REG_HTGT_TRAP_GROUP_CTRL, +}; /* reg_htgt_trap_group * Trap group number. User defined number specifying which trap groups @@ -1142,6 +1945,7 @@ MLXSW_ITEM32(reg, htgt, local_path_cpu_tclass, 0x10, 16, 6); #define MLXSW_REG_HTGT_LOCAL_PATH_RDQ_EMAD 0x15 #define MLXSW_REG_HTGT_LOCAL_PATH_RDQ_RX 0x14 +#define MLXSW_REG_HTGT_LOCAL_PATH_RDQ_CTRL 0x13 /* reg_htgt_local_path_rdq * Receive descriptor queue (RDQ) to use for the trap group. @@ -1149,21 +1953,29 @@ MLXSW_ITEM32(reg, htgt, local_path_cpu_tclass, 0x10, 16, 6); */ MLXSW_ITEM32(reg, htgt, local_path_rdq, 0x10, 0, 6); -static inline void mlxsw_reg_htgt_pack(char *payload, u8 trap_group) +static inline void mlxsw_reg_htgt_pack(char *payload, + enum mlxsw_reg_htgt_trap_group group) { u8 swid, rdq; MLXSW_REG_ZERO(htgt, payload); - if (MLXSW_REG_HTGT_TRAP_GROUP_EMAD == trap_group) { + switch (group) { + case MLXSW_REG_HTGT_TRAP_GROUP_EMAD: swid = MLXSW_PORT_SWID_ALL_SWIDS; rdq = MLXSW_REG_HTGT_LOCAL_PATH_RDQ_EMAD; - } else { + break; + case MLXSW_REG_HTGT_TRAP_GROUP_RX: swid = 0; rdq = MLXSW_REG_HTGT_LOCAL_PATH_RDQ_RX; + break; + case MLXSW_REG_HTGT_TRAP_GROUP_CTRL: + swid = 0; + rdq = MLXSW_REG_HTGT_LOCAL_PATH_RDQ_CTRL; + break; } mlxsw_reg_htgt_swid_set(payload, swid); mlxsw_reg_htgt_type_set(payload, MLXSW_REG_HTGT_PATH_TYPE_LOCAL); - mlxsw_reg_htgt_trap_group_set(payload, trap_group); + mlxsw_reg_htgt_trap_group_set(payload, group); mlxsw_reg_htgt_pide_set(payload, MLXSW_REG_HTGT_POLICER_DISABLE); mlxsw_reg_htgt_pid_set(payload, 0); mlxsw_reg_htgt_mirror_action_set(payload, MLXSW_REG_HTGT_TRAP_TO_CPU); @@ -1254,17 +2066,290 @@ enum { */ MLXSW_ITEM32(reg, hpkt, ctrl, 0x04, 16, 2); -static inline void mlxsw_reg_hpkt_pack(char *payload, u8 action, - u8 trap_group, u16 trap_id) +static inline void mlxsw_reg_hpkt_pack(char *payload, u8 action, u16 trap_id) { + enum mlxsw_reg_htgt_trap_group trap_group; + MLXSW_REG_ZERO(hpkt, payload); mlxsw_reg_hpkt_ack_set(payload, MLXSW_REG_HPKT_ACK_NOT_REQUIRED); mlxsw_reg_hpkt_action_set(payload, action); + switch (trap_id) { + case MLXSW_TRAP_ID_ETHEMAD: + case MLXSW_TRAP_ID_PUDE: + trap_group = MLXSW_REG_HTGT_TRAP_GROUP_EMAD; + break; + default: + trap_group = MLXSW_REG_HTGT_TRAP_GROUP_RX; + break; + } mlxsw_reg_hpkt_trap_group_set(payload, trap_group); mlxsw_reg_hpkt_trap_id_set(payload, trap_id); mlxsw_reg_hpkt_ctrl_set(payload, MLXSW_REG_HPKT_CTRL_PACKET_DEFAULT); } +/* SBPR - Shared Buffer Pools Register + * ----------------------------------- + * The SBPR configures and retrieves the shared buffer pools and configuration. + */ +#define MLXSW_REG_SBPR_ID 0xB001 +#define MLXSW_REG_SBPR_LEN 0x14 + +static const struct mlxsw_reg_info mlxsw_reg_sbpr = { + .id = MLXSW_REG_SBPR_ID, + .len = MLXSW_REG_SBPR_LEN, +}; + +enum mlxsw_reg_sbpr_dir { + MLXSW_REG_SBPR_DIR_INGRESS, + MLXSW_REG_SBPR_DIR_EGRESS, +}; + +/* reg_sbpr_dir + * Direction. + * Access: Index + */ +MLXSW_ITEM32(reg, sbpr, dir, 0x00, 24, 2); + +/* reg_sbpr_pool + * Pool index. + * Access: Index + */ +MLXSW_ITEM32(reg, sbpr, pool, 0x00, 0, 4); + +/* reg_sbpr_size + * Pool size in buffer cells. + * Access: RW + */ +MLXSW_ITEM32(reg, sbpr, size, 0x04, 0, 24); + +enum mlxsw_reg_sbpr_mode { + MLXSW_REG_SBPR_MODE_STATIC, + MLXSW_REG_SBPR_MODE_DYNAMIC, +}; + +/* reg_sbpr_mode + * Pool quota calculation mode. + * Access: RW + */ +MLXSW_ITEM32(reg, sbpr, mode, 0x08, 0, 4); + +static inline void mlxsw_reg_sbpr_pack(char *payload, u8 pool, + enum mlxsw_reg_sbpr_dir dir, + enum mlxsw_reg_sbpr_mode mode, u32 size) +{ + MLXSW_REG_ZERO(sbpr, payload); + mlxsw_reg_sbpr_pool_set(payload, pool); + mlxsw_reg_sbpr_dir_set(payload, dir); + mlxsw_reg_sbpr_mode_set(payload, mode); + mlxsw_reg_sbpr_size_set(payload, size); +} + +/* SBCM - Shared Buffer Class Management Register + * ---------------------------------------------- + * The SBCM register configures and retrieves the shared buffer allocation + * and configuration according to Port-PG, including the binding to pool + * and definition of the associated quota. + */ +#define MLXSW_REG_SBCM_ID 0xB002 +#define MLXSW_REG_SBCM_LEN 0x28 + +static const struct mlxsw_reg_info mlxsw_reg_sbcm = { + .id = MLXSW_REG_SBCM_ID, + .len = MLXSW_REG_SBCM_LEN, +}; + +/* reg_sbcm_local_port + * Local port number. + * For Ingress: excludes CPU port and Router port + * For Egress: excludes IP Router + * Access: Index + */ +MLXSW_ITEM32(reg, sbcm, local_port, 0x00, 16, 8); + +/* reg_sbcm_pg_buff + * PG buffer - Port PG (dir=ingress) / traffic class (dir=egress) + * For PG buffer: range is 0..cap_max_pg_buffers - 1 + * For traffic class: range is 0..cap_max_tclass - 1 + * Note that when traffic class is in MC aware mode then the traffic + * classes which are MC aware cannot be configured. + * Access: Index + */ +MLXSW_ITEM32(reg, sbcm, pg_buff, 0x00, 8, 6); + +enum mlxsw_reg_sbcm_dir { + MLXSW_REG_SBCM_DIR_INGRESS, + MLXSW_REG_SBCM_DIR_EGRESS, +}; + +/* reg_sbcm_dir + * Direction. + * Access: Index + */ +MLXSW_ITEM32(reg, sbcm, dir, 0x00, 0, 2); + +/* reg_sbcm_min_buff + * Minimum buffer size for the limiter, in cells. + * Access: RW + */ +MLXSW_ITEM32(reg, sbcm, min_buff, 0x18, 0, 24); + +/* reg_sbcm_max_buff + * When the pool associated to the port-pg/tclass is configured to + * static, Maximum buffer size for the limiter configured in cells. + * When the pool associated to the port-pg/tclass is configured to + * dynamic, the max_buff holds the "alpha" parameter, supporting + * the following values: + * 0: 0 + * i: (1/128)*2^(i-1), for i=1..14 + * 0xFF: Infinity + * Access: RW + */ +MLXSW_ITEM32(reg, sbcm, max_buff, 0x1C, 0, 24); + +/* reg_sbcm_pool + * Association of the port-priority to a pool. + * Access: RW + */ +MLXSW_ITEM32(reg, sbcm, pool, 0x24, 0, 4); + +static inline void mlxsw_reg_sbcm_pack(char *payload, u8 local_port, u8 pg_buff, + enum mlxsw_reg_sbcm_dir dir, + u32 min_buff, u32 max_buff, u8 pool) +{ + MLXSW_REG_ZERO(sbcm, payload); + mlxsw_reg_sbcm_local_port_set(payload, local_port); + mlxsw_reg_sbcm_pg_buff_set(payload, pg_buff); + mlxsw_reg_sbcm_dir_set(payload, dir); + mlxsw_reg_sbcm_min_buff_set(payload, min_buff); + mlxsw_reg_sbcm_max_buff_set(payload, max_buff); + mlxsw_reg_sbcm_pool_set(payload, pool); +} + +/* SBPM - Shared Buffer Class Management Register + * ---------------------------------------------- + * The SBPM register configures and retrieves the shared buffer allocation + * and configuration according to Port-Pool, including the definition + * of the associated quota. + */ +#define MLXSW_REG_SBPM_ID 0xB003 +#define MLXSW_REG_SBPM_LEN 0x28 + +static const struct mlxsw_reg_info mlxsw_reg_sbpm = { + .id = MLXSW_REG_SBPM_ID, + .len = MLXSW_REG_SBPM_LEN, +}; + +/* reg_sbpm_local_port + * Local port number. + * For Ingress: excludes CPU port and Router port + * For Egress: excludes IP Router + * Access: Index + */ +MLXSW_ITEM32(reg, sbpm, local_port, 0x00, 16, 8); + +/* reg_sbpm_pool + * The pool associated to quota counting on the local_port. + * Access: Index + */ +MLXSW_ITEM32(reg, sbpm, pool, 0x00, 8, 4); + +enum mlxsw_reg_sbpm_dir { + MLXSW_REG_SBPM_DIR_INGRESS, + MLXSW_REG_SBPM_DIR_EGRESS, +}; + +/* reg_sbpm_dir + * Direction. + * Access: Index + */ +MLXSW_ITEM32(reg, sbpm, dir, 0x00, 0, 2); + +/* reg_sbpm_min_buff + * Minimum buffer size for the limiter, in cells. + * Access: RW + */ +MLXSW_ITEM32(reg, sbpm, min_buff, 0x18, 0, 24); + +/* reg_sbpm_max_buff + * When the pool associated to the port-pg/tclass is configured to + * static, Maximum buffer size for the limiter configured in cells. + * When the pool associated to the port-pg/tclass is configured to + * dynamic, the max_buff holds the "alpha" parameter, supporting + * the following values: + * 0: 0 + * i: (1/128)*2^(i-1), for i=1..14 + * 0xFF: Infinity + * Access: RW + */ +MLXSW_ITEM32(reg, sbpm, max_buff, 0x1C, 0, 24); + +static inline void mlxsw_reg_sbpm_pack(char *payload, u8 local_port, u8 pool, + enum mlxsw_reg_sbpm_dir dir, + u32 min_buff, u32 max_buff) +{ + MLXSW_REG_ZERO(sbpm, payload); + mlxsw_reg_sbpm_local_port_set(payload, local_port); + mlxsw_reg_sbpm_pool_set(payload, pool); + mlxsw_reg_sbpm_dir_set(payload, dir); + mlxsw_reg_sbpm_min_buff_set(payload, min_buff); + mlxsw_reg_sbpm_max_buff_set(payload, max_buff); +} + +/* SBMM - Shared Buffer Multicast Management Register + * -------------------------------------------------- + * The SBMM register configures and retrieves the shared buffer allocation + * and configuration for MC packets according to Switch-Priority, including + * the binding to pool and definition of the associated quota. + */ +#define MLXSW_REG_SBMM_ID 0xB004 +#define MLXSW_REG_SBMM_LEN 0x28 + +static const struct mlxsw_reg_info mlxsw_reg_sbmm = { + .id = MLXSW_REG_SBMM_ID, + .len = MLXSW_REG_SBMM_LEN, +}; + +/* reg_sbmm_prio + * Switch Priority. + * Access: Index + */ +MLXSW_ITEM32(reg, sbmm, prio, 0x00, 8, 4); + +/* reg_sbmm_min_buff + * Minimum buffer size for the limiter, in cells. + * Access: RW + */ +MLXSW_ITEM32(reg, sbmm, min_buff, 0x18, 0, 24); + +/* reg_sbmm_max_buff + * When the pool associated to the port-pg/tclass is configured to + * static, Maximum buffer size for the limiter configured in cells. + * When the pool associated to the port-pg/tclass is configured to + * dynamic, the max_buff holds the "alpha" parameter, supporting + * the following values: + * 0: 0 + * i: (1/128)*2^(i-1), for i=1..14 + * 0xFF: Infinity + * Access: RW + */ +MLXSW_ITEM32(reg, sbmm, max_buff, 0x1C, 0, 24); + +/* reg_sbmm_pool + * Association of the port-priority to a pool. + * Access: RW + */ +MLXSW_ITEM32(reg, sbmm, pool, 0x24, 0, 4); + +static inline void mlxsw_reg_sbmm_pack(char *payload, u8 prio, u32 min_buff, + u32 max_buff, u8 pool) +{ + MLXSW_REG_ZERO(sbmm, payload); + mlxsw_reg_sbmm_prio_set(payload, prio); + mlxsw_reg_sbmm_min_buff_set(payload, min_buff); + mlxsw_reg_sbmm_max_buff_set(payload, max_buff); + mlxsw_reg_sbmm_pool_set(payload, pool); +} + static inline const char *mlxsw_reg_id_str(u16 reg_id) { switch (reg_id) { @@ -1272,18 +2357,34 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id) return "SGCR"; case MLXSW_REG_SPAD_ID: return "SPAD"; - case MLXSW_REG_SMID_ID: - return "SMID"; case MLXSW_REG_SSPR_ID: return "SSPR"; + case MLXSW_REG_SFDAT_ID: + return "SFDAT"; + case MLXSW_REG_SFD_ID: + return "SFD"; + case MLXSW_REG_SFN_ID: + return "SFN"; case MLXSW_REG_SPMS_ID: return "SPMS"; + case MLXSW_REG_SPVID_ID: + return "SPVID"; + case MLXSW_REG_SPVM_ID: + return "SPVM"; case MLXSW_REG_SFGC_ID: return "SFGC"; case MLXSW_REG_SFTR_ID: return "SFTR"; case MLXSW_REG_SPMLR_ID: return "SPMLR"; + case MLXSW_REG_SVFA_ID: + return "SVFA"; + case MLXSW_REG_SVPE_ID: + return "SVPE"; + case MLXSW_REG_SFMR_ID: + return "SFMR"; + case MLXSW_REG_SPVMLR_ID: + return "SPVMLR"; case MLXSW_REG_PMLP_ID: return "PMLP"; case MLXSW_REG_PMTU_ID: @@ -1296,12 +2397,22 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id) return "PAOS"; case MLXSW_REG_PPCNT_ID: return "PPCNT"; + case MLXSW_REG_PBMC_ID: + return "PBMC"; case MLXSW_REG_PSPA_ID: return "PSPA"; case MLXSW_REG_HTGT_ID: return "HTGT"; case MLXSW_REG_HPKT_ID: return "HPKT"; + case MLXSW_REG_SBPR_ID: + return "SBPR"; + case MLXSW_REG_SBCM_ID: + return "SBCM"; + case MLXSW_REG_SBPM_ID: + return "SBPM"; + case MLXSW_REG_SBMM_ID: + return "SBMM"; default: return "*UNKNOWN*"; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c new file mode 100644 index 000000000000..6e9906d8d149 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -0,0 +1,1948 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum.c + * Copyright (c) 2015 Mellanox Technologies. All rights reserved. + * Copyright (c) 2015 Jiri Pirko <[email protected]> + * Copyright (c) 2015 Ido Schimmel <[email protected]> + * Copyright (c) 2015 Elad Raz <[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/module.h> +#include <linux/types.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/ethtool.h> +#include <linux/slab.h> +#include <linux/device.h> +#include <linux/skbuff.h> +#include <linux/if_vlan.h> +#include <linux/if_bridge.h> +#include <linux/workqueue.h> +#include <linux/jiffies.h> +#include <linux/bitops.h> +#include <net/switchdev.h> +#include <generated/utsrelease.h> + +#include "spectrum.h" +#include "core.h" +#include "reg.h" +#include "port.h" +#include "trap.h" +#include "txheader.h" + +static const char mlxsw_sp_driver_name[] = "mlxsw_spectrum"; +static const char mlxsw_sp_driver_version[] = "1.0"; + +/* tx_hdr_version + * Tx header version. + * Must be set to 1. + */ +MLXSW_ITEM32(tx, hdr, version, 0x00, 28, 4); + +/* tx_hdr_ctl + * Packet control type. + * 0 - Ethernet control (e.g. EMADs, LACP) + * 1 - Ethernet data + */ +MLXSW_ITEM32(tx, hdr, ctl, 0x00, 26, 2); + +/* tx_hdr_proto + * Packet protocol type. Must be set to 1 (Ethernet). + */ +MLXSW_ITEM32(tx, hdr, proto, 0x00, 21, 3); + +/* tx_hdr_rx_is_router + * Packet is sent from the router. Valid for data packets only. + */ +MLXSW_ITEM32(tx, hdr, rx_is_router, 0x00, 19, 1); + +/* tx_hdr_fid_valid + * Indicates if the 'fid' field is valid and should be used for + * forwarding lookup. Valid for data packets only. + */ +MLXSW_ITEM32(tx, hdr, fid_valid, 0x00, 16, 1); + +/* tx_hdr_swid + * Switch partition ID. Must be set to 0. + */ +MLXSW_ITEM32(tx, hdr, swid, 0x00, 12, 3); + +/* tx_hdr_control_tclass + * Indicates if the packet should use the control TClass and not one + * of the data TClasses. + */ +MLXSW_ITEM32(tx, hdr, control_tclass, 0x00, 6, 1); + +/* tx_hdr_etclass + * Egress TClass to be used on the egress device on the egress port. + */ +MLXSW_ITEM32(tx, hdr, etclass, 0x00, 0, 4); + +/* tx_hdr_port_mid + * Destination local port for unicast packets. + * Destination multicast ID for multicast packets. + * + * Control packets are directed to a specific egress port, while data + * packets are transmitted through the CPU port (0) into the switch partition, + * where forwarding rules are applied. + */ +MLXSW_ITEM32(tx, hdr, port_mid, 0x04, 16, 16); + +/* tx_hdr_fid + * Forwarding ID used for L2 forwarding lookup. Valid only if 'fid_valid' is + * set, otherwise calculated based on the packet's VID using VID to FID mapping. + * Valid for data packets only. + */ +MLXSW_ITEM32(tx, hdr, fid, 0x08, 0, 16); + +/* tx_hdr_type + * 0 - Data packets + * 6 - Control packets + */ +MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4); + +static void mlxsw_sp_txhdr_construct(struct sk_buff *skb, + const struct mlxsw_tx_info *tx_info) +{ + char *txhdr = skb_push(skb, MLXSW_TXHDR_LEN); + + memset(txhdr, 0, MLXSW_TXHDR_LEN); + + mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1); + mlxsw_tx_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL); + mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH); + mlxsw_tx_hdr_swid_set(txhdr, 0); + mlxsw_tx_hdr_control_tclass_set(txhdr, 1); + mlxsw_tx_hdr_port_mid_set(txhdr, tx_info->local_port); + mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL); +} + +static int mlxsw_sp_base_mac_get(struct mlxsw_sp *mlxsw_sp) +{ + char spad_pl[MLXSW_REG_SPAD_LEN]; + int err; + + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(spad), spad_pl); + if (err) + return err; + mlxsw_reg_spad_base_mac_memcpy_from(spad_pl, mlxsw_sp->base_mac); + return 0; +} + +static int mlxsw_sp_port_admin_status_set(struct mlxsw_sp_port *mlxsw_sp_port, + bool is_up) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char paos_pl[MLXSW_REG_PAOS_LEN]; + + mlxsw_reg_paos_pack(paos_pl, mlxsw_sp_port->local_port, + is_up ? MLXSW_PORT_ADMIN_STATUS_UP : + MLXSW_PORT_ADMIN_STATUS_DOWN); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(paos), paos_pl); +} + +static int mlxsw_sp_port_oper_status_get(struct mlxsw_sp_port *mlxsw_sp_port, + bool *p_is_up) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char paos_pl[MLXSW_REG_PAOS_LEN]; + u8 oper_status; + int err; + + mlxsw_reg_paos_pack(paos_pl, mlxsw_sp_port->local_port, 0); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(paos), paos_pl); + if (err) + return err; + oper_status = mlxsw_reg_paos_oper_status_get(paos_pl); + *p_is_up = oper_status == MLXSW_PORT_ADMIN_STATUS_UP ? true : false; + return 0; +} + +static int mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp, u16 vfid) +{ + char sfmr_pl[MLXSW_REG_SFMR_LEN]; + int err; + + mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_CREATE_FID, + MLXSW_SP_VFID_BASE + vfid, 0); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); + + if (err) + return err; + + set_bit(vfid, mlxsw_sp->active_vfids); + return 0; +} + +static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp, u16 vfid) +{ + char sfmr_pl[MLXSW_REG_SFMR_LEN]; + + clear_bit(vfid, mlxsw_sp->active_vfids); + + mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_DESTROY_FID, + MLXSW_SP_VFID_BASE + vfid, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl); +} + +static int mlxsw_sp_port_dev_addr_set(struct mlxsw_sp_port *mlxsw_sp_port, + unsigned char *addr) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char ppad_pl[MLXSW_REG_PPAD_LEN]; + + mlxsw_reg_ppad_pack(ppad_pl, true, mlxsw_sp_port->local_port); + mlxsw_reg_ppad_mac_memcpy_to(ppad_pl, addr); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ppad), ppad_pl); +} + +static int mlxsw_sp_port_dev_addr_init(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + unsigned char *addr = mlxsw_sp_port->dev->dev_addr; + + ether_addr_copy(addr, mlxsw_sp->base_mac); + addr[ETH_ALEN - 1] += mlxsw_sp_port->local_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; + char pmtu_pl[MLXSW_REG_PMTU_LEN]; + int max_mtu; + int err; + + mtu += MLXSW_TXHDR_LEN + ETH_HLEN; + mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sp_port->local_port, 0); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pmtu), pmtu_pl); + if (err) + return err; + max_mtu = mlxsw_reg_pmtu_max_mtu_get(pmtu_pl); + + if (mtu > max_mtu) + return -EINVAL; + + mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sp_port->local_port, 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) +{ + 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); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pspa), pspa_pl); +} + +static int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port, + bool enable) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char svpe_pl[MLXSW_REG_SVPE_LEN]; + + mlxsw_reg_svpe_pack(svpe_pl, mlxsw_sp_port->local_port, enable); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(svpe), svpe_pl); +} + +int mlxsw_sp_port_vid_to_fid_set(struct mlxsw_sp_port *mlxsw_sp_port, + enum mlxsw_reg_svfa_mt mt, bool valid, u16 fid, + u16 vid) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char svfa_pl[MLXSW_REG_SVFA_LEN]; + + mlxsw_reg_svfa_pack(svfa_pl, mlxsw_sp_port->local_port, mt, valid, + fid, vid); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(svfa), svfa_pl); +} + +static int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, + u16 vid, bool learn_enable) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char *spvmlr_pl; + int err; + + spvmlr_pl = kmalloc(MLXSW_REG_SPVMLR_LEN, GFP_KERNEL); + if (!spvmlr_pl) + return -ENOMEM; + mlxsw_reg_spvmlr_pack(spvmlr_pl, mlxsw_sp_port->local_port, vid, vid, + learn_enable); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvmlr), spvmlr_pl); + kfree(spvmlr_pl); + return err; +} + +static int +mlxsw_sp_port_system_port_mapping_set(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char sspr_pl[MLXSW_REG_SSPR_LEN]; + + mlxsw_reg_sspr_pack(sspr_pl, mlxsw_sp_port->local_port); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sspr), sspr_pl); +} + +static int mlxsw_sp_port_module_check(struct mlxsw_sp_port *mlxsw_sp_port, + bool *p_usable) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char pmlp_pl[MLXSW_REG_PMLP_LEN]; + int err; + + mlxsw_reg_pmlp_pack(pmlp_pl, mlxsw_sp_port->local_port); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); + if (err) + return err; + *p_usable = mlxsw_reg_pmlp_width_get(pmlp_pl) ? true : false; + return 0; +} + +static int mlxsw_sp_port_open(struct net_device *dev) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + int err; + + err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true); + if (err) + return err; + netif_start_queue(dev); + return 0; +} + +static int mlxsw_sp_port_stop(struct net_device *dev) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + + netif_stop_queue(dev); + return mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); +} + +static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_port_pcpu_stats *pcpu_stats; + const struct mlxsw_tx_info tx_info = { + .local_port = mlxsw_sp_port->local_port, + .is_emad = false, + }; + u64 len; + int err; + + if (mlxsw_core_skb_transmit_busy(mlxsw_sp, &tx_info)) + return NETDEV_TX_BUSY; + + if (unlikely(skb_headroom(skb) < MLXSW_TXHDR_LEN)) { + struct sk_buff *skb_orig = skb; + + skb = skb_realloc_headroom(skb, MLXSW_TXHDR_LEN); + if (!skb) { + this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); + dev_kfree_skb_any(skb_orig); + return NETDEV_TX_OK; + } + } + + if (eth_skb_pad(skb)) { + this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); + return NETDEV_TX_OK; + } + + mlxsw_sp_txhdr_construct(skb, &tx_info); + len = skb->len; + /* Due to a race we might fail here because of a full queue. In that + * unlikely case we simply drop the packet. + */ + err = mlxsw_core_skb_transmit(mlxsw_sp, skb, &tx_info); + + if (!err) { + pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats); + u64_stats_update_begin(&pcpu_stats->syncp); + pcpu_stats->tx_packets++; + pcpu_stats->tx_bytes += len; + u64_stats_update_end(&pcpu_stats->syncp); + } else { + this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); + dev_kfree_skb_any(skb); + } + return NETDEV_TX_OK; +} + +static int mlxsw_sp_port_set_mac_address(struct net_device *dev, void *p) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct sockaddr *addr = p; + int err; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + err = mlxsw_sp_port_dev_addr_set(mlxsw_sp_port, addr->sa_data); + if (err) + return err; + memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + return 0; +} + +static int mlxsw_sp_port_change_mtu(struct net_device *dev, int mtu) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + int err; + + err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, mtu); + if (err) + return err; + dev->mtu = mtu; + return 0; +} + +static struct rtnl_link_stats64 * +mlxsw_sp_port_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp_port_pcpu_stats *p; + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + u32 tx_dropped = 0; + unsigned int start; + int i; + + for_each_possible_cpu(i) { + p = per_cpu_ptr(mlxsw_sp_port->pcpu_stats, i); + do { + start = u64_stats_fetch_begin_irq(&p->syncp); + rx_packets = p->rx_packets; + rx_bytes = p->rx_bytes; + tx_packets = p->tx_packets; + tx_bytes = p->tx_bytes; + } while (u64_stats_fetch_retry_irq(&p->syncp, start)); + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; + stats->tx_packets += tx_packets; + stats->tx_bytes += tx_bytes; + /* tx_dropped is u32, updated without syncp protection. */ + tx_dropped += p->tx_dropped; + } + stats->tx_dropped = tx_dropped; + return stats; +} + +int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, + u16 vid_end, bool is_member, bool untagged) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char *spvm_pl; + int err; + + spvm_pl = kmalloc(MLXSW_REG_SPVM_LEN, GFP_KERNEL); + if (!spvm_pl) + return -ENOMEM; + + mlxsw_reg_spvm_pack(spvm_pl, mlxsw_sp_port->local_port, vid_begin, + vid_end, is_member, untagged); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvm), spvm_pl); + kfree(spvm_pl); + return err; +} + +static int mlxsw_sp_port_vp_mode_trans(struct mlxsw_sp_port *mlxsw_sp_port) +{ + enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID; + u16 vid, last_visited_vid; + int err; + + for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) { + err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, true, vid, + vid); + if (err) { + last_visited_vid = vid; + goto err_port_vid_to_fid_set; + } + } + + err = mlxsw_sp_port_vp_mode_set(mlxsw_sp_port, true); + if (err) { + last_visited_vid = VLAN_N_VID; + goto err_port_vid_to_fid_set; + } + + return 0; + +err_port_vid_to_fid_set: + for_each_set_bit(vid, mlxsw_sp_port->active_vlans, last_visited_vid) + mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, false, vid, + vid); + return err; +} + +static int mlxsw_sp_port_vlan_mode_trans(struct mlxsw_sp_port *mlxsw_sp_port) +{ + enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID; + u16 vid; + int err; + + err = mlxsw_sp_port_vp_mode_set(mlxsw_sp_port, false); + if (err) + return err; + + for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) { + err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, false, + vid, vid); + if (err) + return err; + } + + return 0; +} + +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; + char *sftr_pl; + int err; + + /* VLAN 0 is added to HW filter when device goes up, but it is + * reserved in our case, so simply return. + */ + if (!vid) + return 0; + + if (test_bit(vid, mlxsw_sp_port->active_vfids)) { + netdev_warn(dev, "VID=%d already configured\n", vid); + return 0; + } + + if (!test_bit(vid, mlxsw_sp->active_vfids)) { + err = mlxsw_sp_vfid_create(mlxsw_sp, vid); + if (err) { + netdev_err(dev, "Failed to create vFID=%d\n", + MLXSW_SP_VFID_BASE + vid); + return err; + } + + sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); + if (!sftr_pl) { + err = -ENOMEM; + goto err_flood_table_alloc; + } + mlxsw_reg_sftr_pack(sftr_pl, 0, vid, + MLXSW_REG_SFGC_TABLE_TYPE_FID, 0, + MLXSW_PORT_CPU_PORT, true); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); + kfree(sftr_pl); + if (err) { + netdev_err(dev, "Failed to configure flood table\n"); + goto err_flood_table_config; + } + } + + /* In case we fail in the following steps, we intentionally do not + * destroy the associated vFID. + */ + + /* When adding the first VLAN interface on a bridged port we need to + * transition all the active 802.1Q bridge VLANs to use explicit + * {Port, VID} to FID mappings and set the port's mode to Virtual mode. + */ + if (!mlxsw_sp_port->nr_vfids) { + err = mlxsw_sp_port_vp_mode_trans(mlxsw_sp_port); + if (err) { + netdev_err(dev, "Failed to set to Virtual mode\n"); + return err; + } + } + + err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, + MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, + true, MLXSW_SP_VFID_BASE + vid, vid); + if (err) { + netdev_err(dev, "Failed to map {Port, VID=%d} to vFID=%d\n", + vid, MLXSW_SP_VFID_BASE + vid); + goto err_port_vid_to_fid_set; + } + + err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, 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_port, vid, vid, true, false); + 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_port, 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; + } + + mlxsw_sp_port->nr_vfids++; + set_bit(vid, mlxsw_sp_port->active_vfids); + + return 0; + +err_flood_table_config: +err_flood_table_alloc: + mlxsw_sp_vfid_destroy(mlxsw_sp, vid); + return err; + +err_port_stp_state_set: + mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false); +err_port_add_vid: + mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true); +err_port_vid_learning_set: + mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, + MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, false, + MLXSW_SP_VFID_BASE + vid, vid); +err_port_vid_to_fid_set: + mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port); + return err; +} + +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); + int err; + + /* VLAN 0 is removed from HW filter when device goes down, but + * it is reserved in our case, so simply return. + */ + if (!vid) + return 0; + + if (!test_bit(vid, mlxsw_sp_port->active_vfids)) { + netdev_warn(dev, "VID=%d does not exist\n", vid); + return 0; + } + + err = mlxsw_sp_port_stp_state_set(mlxsw_sp_port, 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_port, vid, vid, false, false); + if (err) { + netdev_err(dev, "Failed to set VLAN membership for VID=%d\n", + vid); + return err; + } + + err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true); + if (err) { + netdev_err(dev, "Failed to enable learning for VID=%d\n", vid); + return err; + } + + err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, + MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, + false, MLXSW_SP_VFID_BASE + vid, + vid); + if (err) { + netdev_err(dev, "Failed to invalidate {Port, VID=%d} to vFID=%d mapping\n", + vid, MLXSW_SP_VFID_BASE + vid); + return err; + } + + /* 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 + * mappings and set port's mode to VLAN mode. + */ + if (mlxsw_sp_port->nr_vfids == 1) { + err = mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port); + if (err) { + netdev_err(dev, "Failed to set to VLAN mode\n"); + return err; + } + } + + mlxsw_sp_port->nr_vfids--; + clear_bit(vid, mlxsw_sp_port->active_vfids); + + return 0; +} + +static const struct net_device_ops mlxsw_sp_port_netdev_ops = { + .ndo_open = mlxsw_sp_port_open, + .ndo_stop = mlxsw_sp_port_stop, + .ndo_start_xmit = mlxsw_sp_port_xmit, + .ndo_set_mac_address = mlxsw_sp_port_set_mac_address, + .ndo_change_mtu = mlxsw_sp_port_change_mtu, + .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_fdb_add = switchdev_port_fdb_add, + .ndo_fdb_del = switchdev_port_fdb_del, + .ndo_fdb_dump = switchdev_port_fdb_dump, + .ndo_bridge_setlink = switchdev_port_bridge_setlink, + .ndo_bridge_getlink = switchdev_port_bridge_getlink, + .ndo_bridge_dellink = switchdev_port_bridge_dellink, +}; + +static void mlxsw_sp_port_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *drvinfo) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + + strlcpy(drvinfo->driver, mlxsw_sp_driver_name, sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, mlxsw_sp_driver_version, + sizeof(drvinfo->version)); + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%d", + mlxsw_sp->bus_info->fw_rev.major, + mlxsw_sp->bus_info->fw_rev.minor, + mlxsw_sp->bus_info->fw_rev.subminor); + strlcpy(drvinfo->bus_info, mlxsw_sp->bus_info->device_name, + sizeof(drvinfo->bus_info)); +} + +struct mlxsw_sp_port_hw_stats { + char str[ETH_GSTRING_LEN]; + u64 (*getter)(char *payload); +}; + +static const struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = { + { + .str = "a_frames_transmitted_ok", + .getter = mlxsw_reg_ppcnt_a_frames_transmitted_ok_get, + }, + { + .str = "a_frames_received_ok", + .getter = mlxsw_reg_ppcnt_a_frames_received_ok_get, + }, + { + .str = "a_frame_check_sequence_errors", + .getter = mlxsw_reg_ppcnt_a_frame_check_sequence_errors_get, + }, + { + .str = "a_alignment_errors", + .getter = mlxsw_reg_ppcnt_a_alignment_errors_get, + }, + { + .str = "a_octets_transmitted_ok", + .getter = mlxsw_reg_ppcnt_a_octets_transmitted_ok_get, + }, + { + .str = "a_octets_received_ok", + .getter = mlxsw_reg_ppcnt_a_octets_received_ok_get, + }, + { + .str = "a_multicast_frames_xmitted_ok", + .getter = mlxsw_reg_ppcnt_a_multicast_frames_xmitted_ok_get, + }, + { + .str = "a_broadcast_frames_xmitted_ok", + .getter = mlxsw_reg_ppcnt_a_broadcast_frames_xmitted_ok_get, + }, + { + .str = "a_multicast_frames_received_ok", + .getter = mlxsw_reg_ppcnt_a_multicast_frames_received_ok_get, + }, + { + .str = "a_broadcast_frames_received_ok", + .getter = mlxsw_reg_ppcnt_a_broadcast_frames_received_ok_get, + }, + { + .str = "a_in_range_length_errors", + .getter = mlxsw_reg_ppcnt_a_in_range_length_errors_get, + }, + { + .str = "a_out_of_range_length_field", + .getter = mlxsw_reg_ppcnt_a_out_of_range_length_field_get, + }, + { + .str = "a_frame_too_long_errors", + .getter = mlxsw_reg_ppcnt_a_frame_too_long_errors_get, + }, + { + .str = "a_symbol_error_during_carrier", + .getter = mlxsw_reg_ppcnt_a_symbol_error_during_carrier_get, + }, + { + .str = "a_mac_control_frames_transmitted", + .getter = mlxsw_reg_ppcnt_a_mac_control_frames_transmitted_get, + }, + { + .str = "a_mac_control_frames_received", + .getter = mlxsw_reg_ppcnt_a_mac_control_frames_received_get, + }, + { + .str = "a_unsupported_opcodes_received", + .getter = mlxsw_reg_ppcnt_a_unsupported_opcodes_received_get, + }, + { + .str = "a_pause_mac_ctrl_frames_received", + .getter = mlxsw_reg_ppcnt_a_pause_mac_ctrl_frames_received_get, + }, + { + .str = "a_pause_mac_ctrl_frames_xmitted", + .getter = mlxsw_reg_ppcnt_a_pause_mac_ctrl_frames_transmitted_get, + }, +}; + +#define MLXSW_SP_PORT_HW_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_stats) + +static void mlxsw_sp_port_get_strings(struct net_device *dev, + u32 stringset, u8 *data) +{ + u8 *p = data; + int i; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < MLXSW_SP_PORT_HW_STATS_LEN; i++) { + memcpy(p, mlxsw_sp_port_hw_stats[i].str, + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + break; + } +} + +static void mlxsw_sp_port_get_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char ppcnt_pl[MLXSW_REG_PPCNT_LEN]; + int i; + int err; + + mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sp_port->local_port); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ppcnt), ppcnt_pl); + for (i = 0; i < MLXSW_SP_PORT_HW_STATS_LEN; i++) + data[i] = !err ? mlxsw_sp_port_hw_stats[i].getter(ppcnt_pl) : 0; +} + +static int mlxsw_sp_port_get_sset_count(struct net_device *dev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return MLXSW_SP_PORT_HW_STATS_LEN; + default: + return -EOPNOTSUPP; + } +} + +struct mlxsw_sp_port_link_mode { + u32 mask; + u32 supported; + u32 advertised; + u32 speed; +}; + +static const struct mlxsw_sp_port_link_mode mlxsw_sp_port_link_mode[] = { + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_T, + .supported = SUPPORTED_100baseT_Full, + .advertised = ADVERTISED_100baseT_Full, + .speed = 100, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_TX, + .speed = 100, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_SGMII | + MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX, + .supported = SUPPORTED_1000baseKX_Full, + .advertised = ADVERTISED_1000baseKX_Full, + .speed = 1000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_T, + .supported = SUPPORTED_10000baseT_Full, + .advertised = ADVERTISED_10000baseT_Full, + .speed = 10000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 | + MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4, + .supported = SUPPORTED_10000baseKX4_Full, + .advertised = ADVERTISED_10000baseKX4_Full, + .speed = 10000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR | + MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR | + MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR | + MLXSW_REG_PTYS_ETH_SPEED_10GBASE_ER_LR, + .supported = SUPPORTED_10000baseKR_Full, + .advertised = ADVERTISED_10000baseKR_Full, + .speed = 10000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_20GBASE_KR2, + .supported = SUPPORTED_20000baseKR2_Full, + .advertised = ADVERTISED_20000baseKR2_Full, + .speed = 20000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4, + .supported = SUPPORTED_40000baseCR4_Full, + .advertised = ADVERTISED_40000baseCR4_Full, + .speed = 40000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4, + .supported = SUPPORTED_40000baseKR4_Full, + .advertised = ADVERTISED_40000baseKR4_Full, + .speed = 40000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4, + .supported = SUPPORTED_40000baseSR4_Full, + .advertised = ADVERTISED_40000baseSR4_Full, + .speed = 40000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_LR4_ER4, + .supported = SUPPORTED_40000baseLR4_Full, + .advertised = ADVERTISED_40000baseLR4_Full, + .speed = 40000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR | + MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR | + MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR, + .speed = 25000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_50GBASE_KR4 | + MLXSW_REG_PTYS_ETH_SPEED_50GBASE_CR2 | + MLXSW_REG_PTYS_ETH_SPEED_50GBASE_KR2, + .speed = 50000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_56GBASE_R4, + .supported = SUPPORTED_56000baseKR4_Full, + .advertised = ADVERTISED_56000baseKR4_Full, + .speed = 56000, + }, + { + .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 | + MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 | + MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 | + MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4, + .speed = 100000, + }, +}; + +#define MLXSW_SP_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp_port_link_mode) + +static u32 mlxsw_sp_from_ptys_supported_port(u32 ptys_eth_proto) +{ + if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR | + MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR | + MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 | + MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4 | + MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 | + MLXSW_REG_PTYS_ETH_SPEED_SGMII)) + return SUPPORTED_FIBRE; + + if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR | + MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 | + MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 | + MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 | + MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX)) + return SUPPORTED_Backplane; + return 0; +} + +static u32 mlxsw_sp_from_ptys_supported_link(u32 ptys_eth_proto) +{ + u32 modes = 0; + int i; + + for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) { + if (ptys_eth_proto & mlxsw_sp_port_link_mode[i].mask) + modes |= mlxsw_sp_port_link_mode[i].supported; + } + return modes; +} + +static u32 mlxsw_sp_from_ptys_advert_link(u32 ptys_eth_proto) +{ + u32 modes = 0; + int i; + + for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) { + if (ptys_eth_proto & mlxsw_sp_port_link_mode[i].mask) + modes |= mlxsw_sp_port_link_mode[i].advertised; + } + return modes; +} + +static void mlxsw_sp_from_ptys_speed_duplex(bool carrier_ok, u32 ptys_eth_proto, + struct ethtool_cmd *cmd) +{ + u32 speed = SPEED_UNKNOWN; + u8 duplex = DUPLEX_UNKNOWN; + int i; + + if (!carrier_ok) + goto out; + + for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) { + if (ptys_eth_proto & mlxsw_sp_port_link_mode[i].mask) { + speed = mlxsw_sp_port_link_mode[i].speed; + duplex = DUPLEX_FULL; + break; + } + } +out: + ethtool_cmd_speed_set(cmd, speed); + cmd->duplex = duplex; +} + +static u8 mlxsw_sp_port_connector_port(u32 ptys_eth_proto) +{ + if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR | + MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4 | + MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 | + MLXSW_REG_PTYS_ETH_SPEED_SGMII)) + return PORT_FIBRE; + + if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR | + MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 | + MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4)) + return PORT_DA; + + if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR | + MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 | + MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 | + MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4)) + return PORT_NONE; + + return PORT_OTHER; +} + +static int mlxsw_sp_port_get_settings(struct net_device *dev, + struct ethtool_cmd *cmd) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char ptys_pl[MLXSW_REG_PTYS_LEN]; + u32 eth_proto_cap; + u32 eth_proto_admin; + u32 eth_proto_oper; + int err; + + mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, 0); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl); + if (err) { + netdev_err(dev, "Failed to get proto"); + return err; + } + mlxsw_reg_ptys_unpack(ptys_pl, ð_proto_cap, + ð_proto_admin, ð_proto_oper); + + cmd->supported = mlxsw_sp_from_ptys_supported_port(eth_proto_cap) | + mlxsw_sp_from_ptys_supported_link(eth_proto_cap) | + SUPPORTED_Pause | SUPPORTED_Asym_Pause; + cmd->advertising = mlxsw_sp_from_ptys_advert_link(eth_proto_admin); + mlxsw_sp_from_ptys_speed_duplex(netif_carrier_ok(dev), + eth_proto_oper, cmd); + + eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; + cmd->port = mlxsw_sp_port_connector_port(eth_proto_oper); + cmd->lp_advertising = mlxsw_sp_from_ptys_advert_link(eth_proto_oper); + + cmd->transceiver = XCVR_INTERNAL; + return 0; +} + +static u32 mlxsw_sp_to_ptys_advert_link(u32 advertising) +{ + u32 ptys_proto = 0; + int i; + + for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) { + if (advertising & mlxsw_sp_port_link_mode[i].advertised) + ptys_proto |= mlxsw_sp_port_link_mode[i].mask; + } + return ptys_proto; +} + +static u32 mlxsw_sp_to_ptys_speed(u32 speed) +{ + u32 ptys_proto = 0; + int i; + + for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) { + if (speed == mlxsw_sp_port_link_mode[i].speed) + ptys_proto |= mlxsw_sp_port_link_mode[i].mask; + } + return ptys_proto; +} + +static int mlxsw_sp_port_set_settings(struct net_device *dev, + struct ethtool_cmd *cmd) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char ptys_pl[MLXSW_REG_PTYS_LEN]; + u32 speed; + u32 eth_proto_new; + u32 eth_proto_cap; + u32 eth_proto_admin; + bool is_up; + int err; + + speed = ethtool_cmd_speed(cmd); + + eth_proto_new = cmd->autoneg == AUTONEG_ENABLE ? + mlxsw_sp_to_ptys_advert_link(cmd->advertising) : + mlxsw_sp_to_ptys_speed(speed); + + mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, 0); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl); + if (err) { + netdev_err(dev, "Failed to get proto"); + return err; + } + mlxsw_reg_ptys_unpack(ptys_pl, ð_proto_cap, ð_proto_admin, NULL); + + eth_proto_new = eth_proto_new & eth_proto_cap; + if (!eth_proto_new) { + netdev_err(dev, "Not supported proto admin requested"); + return -EINVAL; + } + if (eth_proto_new == eth_proto_admin) + return 0; + + mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, eth_proto_new); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl); + if (err) { + netdev_err(dev, "Failed to set proto admin"); + return err; + } + + err = mlxsw_sp_port_oper_status_get(mlxsw_sp_port, &is_up); + if (err) { + netdev_err(dev, "Failed to get oper status"); + return err; + } + if (!is_up) + return 0; + + err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); + if (err) { + netdev_err(dev, "Failed to set admin status"); + return err; + } + + err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true); + if (err) { + netdev_err(dev, "Failed to set admin status"); + return err; + } + + return 0; +} + +static const struct ethtool_ops mlxsw_sp_port_ethtool_ops = { + .get_drvinfo = mlxsw_sp_port_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_strings = mlxsw_sp_port_get_strings, + .get_ethtool_stats = mlxsw_sp_port_get_stats, + .get_sset_count = mlxsw_sp_port_get_sset_count, + .get_settings = mlxsw_sp_port_get_settings, + .set_settings = mlxsw_sp_port_set_settings, +}; + +static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port) +{ + struct mlxsw_sp_port *mlxsw_sp_port; + struct net_device *dev; + bool usable; + int err; + + dev = alloc_etherdev(sizeof(struct mlxsw_sp_port)); + if (!dev) + return -ENOMEM; + mlxsw_sp_port = netdev_priv(dev); + mlxsw_sp_port->dev = dev; + mlxsw_sp_port->mlxsw_sp = mlxsw_sp; + mlxsw_sp_port->local_port = local_port; + mlxsw_sp_port->learning = 1; + mlxsw_sp_port->learning_sync = 1; + mlxsw_sp_port->pvid = 1; + + mlxsw_sp_port->pcpu_stats = + netdev_alloc_pcpu_stats(struct mlxsw_sp_port_pcpu_stats); + if (!mlxsw_sp_port->pcpu_stats) { + err = -ENOMEM; + goto err_alloc_stats; + } + + dev->netdev_ops = &mlxsw_sp_port_netdev_ops; + dev->ethtool_ops = &mlxsw_sp_port_ethtool_ops; + + err = mlxsw_sp_port_dev_addr_init(mlxsw_sp_port); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Unable to init port mac address\n", + mlxsw_sp_port->local_port); + goto err_dev_addr_init; + } + + netif_carrier_off(dev); + + dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_LLTX | NETIF_F_SG | + NETIF_F_HW_VLAN_CTAG_FILTER; + + /* Each packet needs to have a Tx header (metadata) on top all other + * headers. + */ + dev->hard_header_len += MLXSW_TXHDR_LEN; + + err = mlxsw_sp_port_module_check(mlxsw_sp_port, &usable); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to check module\n", + mlxsw_sp_port->local_port); + goto err_port_module_check; + } + + if (!usable) { + dev_dbg(mlxsw_sp->bus_info->dev, "Port %d: Not usable, skipping initialization\n", + mlxsw_sp_port->local_port); + goto port_not_usable; + } + + err = mlxsw_sp_port_system_port_mapping_set(mlxsw_sp_port); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set system port mapping\n", + mlxsw_sp_port->local_port); + goto err_port_system_port_mapping_set; + } + + err = mlxsw_sp_port_swid_set(mlxsw_sp_port, 0); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set SWID\n", + mlxsw_sp_port->local_port); + goto err_port_swid_set; + } + + err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, ETH_DATA_LEN); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set MTU\n", + mlxsw_sp_port->local_port); + goto err_port_mtu_set; + } + + err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); + if (err) + goto err_port_admin_status_set; + + err = mlxsw_sp_port_buffers_init(mlxsw_sp_port); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to initialize buffers\n", + mlxsw_sp_port->local_port); + goto err_port_buffers_init; + } + + mlxsw_sp_port_switchdev_init(mlxsw_sp_port); + err = register_netdev(dev); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to register netdev\n", + mlxsw_sp_port->local_port); + goto err_register_netdev; + } + + err = mlxsw_sp_port_vlan_init(mlxsw_sp_port); + if (err) + goto err_port_vlan_init; + + mlxsw_sp->ports[local_port] = mlxsw_sp_port; + return 0; + +err_port_vlan_init: + unregister_netdev(dev); +err_register_netdev: +err_port_buffers_init: +err_port_admin_status_set: +err_port_mtu_set: +err_port_swid_set: +err_port_system_port_mapping_set: +port_not_usable: +err_port_module_check: +err_dev_addr_init: + free_percpu(mlxsw_sp_port->pcpu_stats); +err_alloc_stats: + free_netdev(dev); + return err; +} + +static void mlxsw_sp_vfids_fini(struct mlxsw_sp *mlxsw_sp) +{ + u16 vfid; + + for_each_set_bit(vfid, mlxsw_sp->active_vfids, VLAN_N_VID) + mlxsw_sp_vfid_destroy(mlxsw_sp, vfid); +} + +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]; + + if (!mlxsw_sp_port) + return; + mlxsw_sp_port_kill_vid(mlxsw_sp_port->dev, 0, 1); + unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */ + mlxsw_sp_port_switchdev_fini(mlxsw_sp_port); + free_percpu(mlxsw_sp_port->pcpu_stats); + free_netdev(mlxsw_sp_port->dev); +} + +static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) + mlxsw_sp_port_remove(mlxsw_sp, i); + kfree(mlxsw_sp->ports); +} + +static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp) +{ + size_t alloc_size; + int i; + int err; + + alloc_size = sizeof(struct mlxsw_sp_port *) * MLXSW_PORT_MAX_PORTS; + mlxsw_sp->ports = kzalloc(alloc_size, GFP_KERNEL); + if (!mlxsw_sp->ports) + return -ENOMEM; + + for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) { + err = mlxsw_sp_port_create(mlxsw_sp, i); + if (err) + goto err_port_create; + } + return 0; + +err_port_create: + for (i--; i >= 1; i--) + mlxsw_sp_port_remove(mlxsw_sp, i); + kfree(mlxsw_sp->ports); + return err; +} + +static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg, + char *pude_pl, void *priv) +{ + struct mlxsw_sp *mlxsw_sp = priv; + struct mlxsw_sp_port *mlxsw_sp_port; + enum mlxsw_reg_pude_oper_status status; + u8 local_port; + + 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); + return; + } + + status = mlxsw_reg_pude_oper_status_get(pude_pl); + if (status == MLXSW_PORT_OPER_STATUS_UP) { + netdev_info(mlxsw_sp_port->dev, "link up\n"); + netif_carrier_on(mlxsw_sp_port->dev); + } else { + netdev_info(mlxsw_sp_port->dev, "link down\n"); + netif_carrier_off(mlxsw_sp_port->dev); + } +} + +static struct mlxsw_event_listener mlxsw_sp_pude_event = { + .func = mlxsw_sp_pude_event_func, + .trap_id = MLXSW_TRAP_ID_PUDE, +}; + +static int mlxsw_sp_event_register(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_event_trap_id trap_id) +{ + struct mlxsw_event_listener *el; + char hpkt_pl[MLXSW_REG_HPKT_LEN]; + int err; + + switch (trap_id) { + case MLXSW_TRAP_ID_PUDE: + el = &mlxsw_sp_pude_event; + break; + } + err = mlxsw_core_event_listener_register(mlxsw_sp->core, el, mlxsw_sp); + if (err) + return err; + + mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD, trap_id); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(hpkt), hpkt_pl); + if (err) + goto err_event_trap_set; + + return 0; + +err_event_trap_set: + mlxsw_core_event_listener_unregister(mlxsw_sp->core, el, mlxsw_sp); + return err; +} + +static void mlxsw_sp_event_unregister(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_event_trap_id trap_id) +{ + struct mlxsw_event_listener *el; + + switch (trap_id) { + case MLXSW_TRAP_ID_PUDE: + el = &mlxsw_sp_pude_event; + break; + } + mlxsw_core_event_listener_unregister(mlxsw_sp->core, el, mlxsw_sp); +} + +static void mlxsw_sp_rx_listener_func(struct sk_buff *skb, u8 local_port, + void *priv) +{ + struct mlxsw_sp *mlxsw_sp = priv; + struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port]; + struct mlxsw_sp_port_pcpu_stats *pcpu_stats; + + if (unlikely(!mlxsw_sp_port)) { + dev_warn_ratelimited(mlxsw_sp->bus_info->dev, "Port %d: skb received for non-existent port\n", + local_port); + return; + } + + skb->dev = mlxsw_sp_port->dev; + + pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats); + u64_stats_update_begin(&pcpu_stats->syncp); + pcpu_stats->rx_packets++; + pcpu_stats->rx_bytes += skb->len; + u64_stats_update_end(&pcpu_stats->syncp); + + skb->protocol = eth_type_trans(skb, skb->dev); + netif_receive_skb(skb); +} + +static const struct mlxsw_rx_listener mlxsw_sp_rx_listener[] = { + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_FDB_MC, + }, + /* Traps for specific L2 packet types, not trapped as FDB MC */ + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_STP, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_LACP, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_EAPOL, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_LLDP, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_MMRP, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_MVRP, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_RPVST, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_DHCP, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_IGMP_QUERY, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_IGMP_V1_REPORT, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_IGMP_V2_REPORT, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_IGMP_V2_LEAVE, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_IGMP_V3_REPORT, + }, +}; + +static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp) +{ + char htgt_pl[MLXSW_REG_HTGT_LEN]; + char hpkt_pl[MLXSW_REG_HPKT_LEN]; + int i; + int err; + + mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_RX); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(htgt), htgt_pl); + if (err) + return err; + + mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_CTRL); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(htgt), htgt_pl); + if (err) + return err; + + for (i = 0; i < ARRAY_SIZE(mlxsw_sp_rx_listener); i++) { + err = mlxsw_core_rx_listener_register(mlxsw_sp->core, + &mlxsw_sp_rx_listener[i], + mlxsw_sp); + if (err) + goto err_rx_listener_register; + + mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_TRAP_TO_CPU, + mlxsw_sp_rx_listener[i].trap_id); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(hpkt), hpkt_pl); + if (err) + goto err_rx_trap_set; + } + return 0; + +err_rx_trap_set: + mlxsw_core_rx_listener_unregister(mlxsw_sp->core, + &mlxsw_sp_rx_listener[i], + mlxsw_sp); +err_rx_listener_register: + for (i--; i >= 0; i--) { + mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD, + mlxsw_sp_rx_listener[i].trap_id); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(hpkt), hpkt_pl); + + mlxsw_core_rx_listener_unregister(mlxsw_sp->core, + &mlxsw_sp_rx_listener[i], + mlxsw_sp); + } + return err; +} + +static void mlxsw_sp_traps_fini(struct mlxsw_sp *mlxsw_sp) +{ + char hpkt_pl[MLXSW_REG_HPKT_LEN]; + 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_sp_rx_listener[i].trap_id); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(hpkt), hpkt_pl); + + mlxsw_core_rx_listener_unregister(mlxsw_sp->core, + &mlxsw_sp_rx_listener[i], + mlxsw_sp); + } +} + +static int __mlxsw_sp_flood_init(struct mlxsw_core *mlxsw_core, + enum mlxsw_reg_sfgc_type type, + enum mlxsw_reg_sfgc_bridge_type bridge_type) +{ + enum mlxsw_flood_table_type table_type; + enum mlxsw_sp_flood_table flood_table; + char sfgc_pl[MLXSW_REG_SFGC_LEN]; + + if (bridge_type == MLXSW_REG_SFGC_BRIDGE_TYPE_VFID) { + table_type = MLXSW_REG_SFGC_TABLE_TYPE_FID; + flood_table = 0; + } else { + table_type = MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST; + if (type == MLXSW_REG_SFGC_TYPE_UNKNOWN_UNICAST) + flood_table = MLXSW_SP_FLOOD_TABLE_UC; + else + flood_table = MLXSW_SP_FLOOD_TABLE_BM; + } + + mlxsw_reg_sfgc_pack(sfgc_pl, type, bridge_type, table_type, + flood_table); + return mlxsw_reg_write(mlxsw_core, MLXSW_REG(sfgc), sfgc_pl); +} + +static int mlxsw_sp_flood_init(struct mlxsw_sp *mlxsw_sp) +{ + int type, err; + + /* For non-offloaded netdevs, flood all traffic types to CPU + * port. + */ + for (type = 0; type < MLXSW_REG_SFGC_TYPE_MAX; type++) { + if (type == MLXSW_REG_SFGC_TYPE_RESERVED) + continue; + + err = __mlxsw_sp_flood_init(mlxsw_sp->core, type, + MLXSW_REG_SFGC_BRIDGE_TYPE_VFID); + if (err) + return err; + } + + /* For bridged ports, use one flooding table for unknown unicast + * traffic and a second table for unregistered multicast and + * broadcast. + */ + for (type = 0; type < MLXSW_REG_SFGC_TYPE_MAX; type++) { + if (type == MLXSW_REG_SFGC_TYPE_RESERVED) + continue; + + err = __mlxsw_sp_flood_init(mlxsw_sp->core, type, + MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID); + if (err) + return err; + } + + return 0; +} + +static int mlxsw_sp_init(void *priv, struct mlxsw_core *mlxsw_core, + const struct mlxsw_bus_info *mlxsw_bus_info) +{ + struct mlxsw_sp *mlxsw_sp = priv; + int err; + + mlxsw_sp->core = mlxsw_core; + mlxsw_sp->bus_info = mlxsw_bus_info; + + err = mlxsw_sp_base_mac_get(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to get base mac\n"); + return err; + } + + 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; + } + + 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; + } + + err = mlxsw_sp_traps_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to set traps for RX\n"); + goto err_rx_listener_register; + } + + err = mlxsw_sp_flood_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize flood tables\n"); + goto err_flood_init; + } + + err = mlxsw_sp_buffers_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize buffers\n"); + goto err_buffers_init; + } + + err = mlxsw_sp_switchdev_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize switchdev\n"); + goto err_switchdev_init; + } + + return 0; + +err_switchdev_init: +err_buffers_init: +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); +err_ports_create: + mlxsw_sp_vfids_fini(mlxsw_sp); + return err; +} + +static void mlxsw_sp_fini(void *priv) +{ + struct mlxsw_sp *mlxsw_sp = priv; + + mlxsw_sp_switchdev_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); + mlxsw_sp_vfids_fini(mlxsw_sp); +} + +static struct mlxsw_config_profile mlxsw_sp_config_profile = { + .used_max_vepa_channels = 1, + .max_vepa_channels = 0, + .used_max_lag = 1, + .max_lag = 64, + .used_max_port_per_lag = 1, + .max_port_per_lag = 16, + .used_max_mid = 1, + .max_mid = 7000, + .used_max_pgt = 1, + .max_pgt = 0, + .used_max_system_port = 1, + .max_system_port = 64, + .used_max_vlan_groups = 1, + .max_vlan_groups = 127, + .used_max_regions = 1, + .max_regions = 400, + .used_flood_tables = 1, + .used_flood_mode = 1, + .flood_mode = 3, + .max_fid_offset_flood_tables = 2, + .fid_offset_flood_table_size = VLAN_N_VID - 1, + .max_fid_flood_tables = 1, + .fid_flood_table_size = VLAN_N_VID, + .used_max_ib_mc = 1, + .max_ib_mc = 0, + .used_max_pkey = 1, + .max_pkey = 0, + .swid_config = { + { + .used_type = 1, + .type = MLXSW_PORT_SWID_TYPE_ETH, + } + }, +}; + +static struct mlxsw_driver mlxsw_sp_driver = { + .kind = MLXSW_DEVICE_KIND_SPECTRUM, + .owner = THIS_MODULE, + .priv_size = sizeof(struct mlxsw_sp), + .init = mlxsw_sp_init, + .fini = mlxsw_sp_fini, + .txhdr_construct = mlxsw_sp_txhdr_construct, + .txhdr_len = MLXSW_TXHDR_LEN, + .profile = &mlxsw_sp_config_profile, +}; + +static bool mlxsw_sp_port_dev_check(const struct net_device *dev) +{ + return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; +} + +static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct net_device *dev = mlxsw_sp_port->dev; + int err; + + /* When port is not bridged untagged packets are tagged with + * PVID=VID=1, thereby creating an implicit VLAN interface in + * the device. Remove it and let bridge code take care of its + * own VLANs. + */ + err = mlxsw_sp_port_kill_vid(dev, 0, 1); + if (err) + netdev_err(dev, "Failed to remove VID 1\n"); + + return err; +} + +static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct net_device *dev = mlxsw_sp_port->dev; + int err; + + /* Add implicit VLAN interface in the device, so that untagged + * packets will be classified to the default vFID. + */ + err = mlxsw_sp_port_add_vid(dev, 0, 1); + if (err) + netdev_err(dev, "Failed to add VID 1\n"); + + return err; +} + +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; +} + +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); + struct netdev_notifier_changeupper_info *info; + struct mlxsw_sp_port *mlxsw_sp_port; + struct net_device *upper_dev; + struct mlxsw_sp *mlxsw_sp; + int err; + + if (!mlxsw_sp_port_dev_check(dev)) + return NOTIFY_DONE; + + mlxsw_sp_port = netdev_priv(dev); + mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + info = ptr; + + switch (event) { + case NETDEV_PRECHANGEUPPER: + upper_dev = info->upper_dev; + /* HW limitation forbids to put ports to multiple bridges. */ + if (info->master && info->linking && + netif_is_bridge_master(upper_dev) && + !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev)) + return NOTIFY_BAD; + break; + case NETDEV_CHANGEUPPER: + upper_dev = info->upper_dev; + if (info->master && + 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"); + mlxsw_sp_master_bridge_inc(mlxsw_sp, upper_dev); + mlxsw_sp_port->bridged = true; + } else { + err = mlxsw_sp_port_bridge_leave(mlxsw_sp_port); + if (err) + netdev_err(dev, "Failed to leave bridge\n"); + mlxsw_sp_port->bridged = false; + mlxsw_sp_master_bridge_dec(mlxsw_sp, upper_dev); + } + } + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block mlxsw_sp_netdevice_nb __read_mostly = { + .notifier_call = mlxsw_sp_netdevice_event, +}; + +static int __init mlxsw_sp_module_init(void) +{ + int err; + + register_netdevice_notifier(&mlxsw_sp_netdevice_nb); + err = mlxsw_core_driver_register(&mlxsw_sp_driver); + if (err) + goto err_core_driver_register; + return 0; + +err_core_driver_register: + unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb); + return err; +} + +static void __exit mlxsw_sp_module_exit(void) +{ + mlxsw_core_driver_unregister(&mlxsw_sp_driver); + unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb); +} + +module_init(mlxsw_sp_module_init); +module_exit(mlxsw_sp_module_exit); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_AUTHOR("Jiri Pirko <[email protected]>"); +MODULE_DESCRIPTION("Mellanox Spectrum driver"); +MODULE_MLXSW_DRIVER_ALIAS(MLXSW_DEVICE_KIND_SPECTRUM); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h new file mode 100644 index 000000000000..fc0074902ab5 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -0,0 +1,121 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum.h + * Copyright (c) 2015 Mellanox Technologies. All rights reserved. + * Copyright (c) 2015 Jiri Pirko <[email protected]> + * Copyright (c) 2015 Ido Schimmel <[email protected]> + * Copyright (c) 2015 Elad Raz <[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. + */ + +#ifndef _MLXSW_SPECTRUM_H +#define _MLXSW_SPECTRUM_H + +#include <linux/types.h> +#include <linux/netdevice.h> +#include <linux/bitops.h> +#include <linux/if_vlan.h> +#include <net/switchdev.h> + +#include "core.h" + +#define MLXSW_SP_VFID_BASE VLAN_N_VID + +struct mlxsw_sp_port; + +struct mlxsw_sp { + unsigned long active_vfids[BITS_TO_LONGS(VLAN_N_VID)]; + unsigned long active_fids[BITS_TO_LONGS(VLAN_N_VID)]; + struct mlxsw_sp_port **ports; + struct mlxsw_core *core; + const struct mlxsw_bus_info *bus_info; + unsigned char base_mac[ETH_ALEN]; + struct { + struct delayed_work dw; +#define MLXSW_SP_DEFAULT_LEARNING_INTERVAL 100 + unsigned int interval; /* ms */ + } fdb_notify; +#define MLXSW_SP_DEFAULT_AGEING_TIME 300 + u32 ageing_time; + struct { + struct net_device *dev; + unsigned int ref_count; + } master_bridge; +}; + +struct mlxsw_sp_port_pcpu_stats { + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + struct u64_stats_sync syncp; + u32 tx_dropped; +}; + +struct mlxsw_sp_port { + struct net_device *dev; + struct mlxsw_sp_port_pcpu_stats __percpu *pcpu_stats; + struct mlxsw_sp *mlxsw_sp; + u8 local_port; + u8 stp_state; + u8 learning:1; + u8 learning_sync:1; + u16 pvid; + bool bridged; + /* 802.1Q bridge VLANs */ + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + /* VLAN interfaces */ + unsigned long active_vfids[BITS_TO_LONGS(VLAN_N_VID)]; + u16 nr_vfids; +}; + +enum mlxsw_sp_flood_table { + MLXSW_SP_FLOOD_TABLE_UC, + MLXSW_SP_FLOOD_TABLE_BM, +}; + +int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp); +int mlxsw_sp_port_buffers_init(struct mlxsw_sp_port *mlxsw_sp_port); + +int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp); +int mlxsw_sp_port_vlan_init(struct mlxsw_sp_port *mlxsw_sp_port); +void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port); +void mlxsw_sp_port_switchdev_fini(struct mlxsw_sp_port *mlxsw_sp_port); +int mlxsw_sp_port_vid_to_fid_set(struct mlxsw_sp_port *mlxsw_sp_port, + enum mlxsw_reg_svfa_mt mt, bool valid, u16 fid, + u16 vid); +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); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c new file mode 100644 index 000000000000..d59195e3f7fb --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -0,0 +1,422 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c + * Copyright (c) 2015 Mellanox Technologies. All rights reserved. + * Copyright (c) 2015 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/types.h> + +#include "spectrum.h" +#include "core.h" +#include "port.h" +#include "reg.h" + +struct mlxsw_sp_pb { + u8 index; + u16 size; +}; + +#define MLXSW_SP_PB(_index, _size) \ + { \ + .index = _index, \ + .size = _size, \ + } + +static const struct mlxsw_sp_pb mlxsw_sp_pbs[] = { + MLXSW_SP_PB(0, 208), + MLXSW_SP_PB(1, 208), + MLXSW_SP_PB(2, 208), + MLXSW_SP_PB(3, 208), + MLXSW_SP_PB(4, 208), + MLXSW_SP_PB(5, 208), + MLXSW_SP_PB(6, 208), + MLXSW_SP_PB(7, 208), + MLXSW_SP_PB(9, 208), +}; + +#define MLXSW_SP_PBS_LEN ARRAY_SIZE(mlxsw_sp_pbs) + +static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port) +{ + char pbmc_pl[MLXSW_REG_PBMC_LEN]; + int i; + + mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port, + 0xffff, 0xffff / 2); + for (i = 0; i < MLXSW_SP_PBS_LEN; i++) { + const struct mlxsw_sp_pb *pb; + + pb = &mlxsw_sp_pbs[i]; + mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, pb->index, pb->size); + } + return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, + MLXSW_REG(pbmc), pbmc_pl); +} + +#define MLXSW_SP_SB_BYTES_PER_CELL 96 + +struct mlxsw_sp_sb_pool { + u8 pool; + enum mlxsw_reg_sbpr_dir dir; + enum mlxsw_reg_sbpr_mode mode; + u32 size; +}; + +#define MLXSW_SP_SB_POOL_INGRESS_SIZE \ + ((15000000 - (2 * 20000 * MLXSW_PORT_MAX_PORTS)) / \ + MLXSW_SP_SB_BYTES_PER_CELL) +#define MLXSW_SP_SB_POOL_EGRESS_SIZE \ + ((14000000 - (8 * 1500 * MLXSW_PORT_MAX_PORTS)) / \ + MLXSW_SP_SB_BYTES_PER_CELL) + +#define MLXSW_SP_SB_POOL(_pool, _dir, _mode, _size) \ + { \ + .pool = _pool, \ + .dir = _dir, \ + .mode = _mode, \ + .size = _size, \ + } + +#define MLXSW_SP_SB_POOL_INGRESS(_pool, _size) \ + MLXSW_SP_SB_POOL(_pool, MLXSW_REG_SBPR_DIR_INGRESS, \ + MLXSW_REG_SBPR_MODE_DYNAMIC, _size) + +#define MLXSW_SP_SB_POOL_EGRESS(_pool, _size) \ + MLXSW_SP_SB_POOL(_pool, MLXSW_REG_SBPR_DIR_EGRESS, \ + MLXSW_REG_SBPR_MODE_DYNAMIC, _size) + +static const struct mlxsw_sp_sb_pool mlxsw_sp_sb_pools[] = { + MLXSW_SP_SB_POOL_INGRESS(0, MLXSW_SP_SB_POOL_INGRESS_SIZE), + MLXSW_SP_SB_POOL_INGRESS(1, 0), + MLXSW_SP_SB_POOL_INGRESS(2, 0), + MLXSW_SP_SB_POOL_INGRESS(3, 0), + MLXSW_SP_SB_POOL_EGRESS(0, MLXSW_SP_SB_POOL_EGRESS_SIZE), + MLXSW_SP_SB_POOL_EGRESS(1, 0), + MLXSW_SP_SB_POOL_EGRESS(2, 0), + MLXSW_SP_SB_POOL_EGRESS(2, MLXSW_SP_SB_POOL_EGRESS_SIZE), +}; + +#define MLXSW_SP_SB_POOLS_LEN ARRAY_SIZE(mlxsw_sp_sb_pools) + +static int mlxsw_sp_sb_pools_init(struct mlxsw_sp *mlxsw_sp) +{ + char sbpr_pl[MLXSW_REG_SBPR_LEN]; + int i; + int err; + + for (i = 0; i < MLXSW_SP_SB_POOLS_LEN; i++) { + const struct mlxsw_sp_sb_pool *pool; + + pool = &mlxsw_sp_sb_pools[i]; + mlxsw_reg_sbpr_pack(sbpr_pl, pool->pool, pool->dir, + pool->mode, pool->size); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbpr), sbpr_pl); + if (err) + return err; + } + return 0; +} + +struct mlxsw_sp_sb_cm { + union { + u8 pg; + u8 tc; + } u; + enum mlxsw_reg_sbcm_dir dir; + u32 min_buff; + u32 max_buff; + u8 pool; +}; + +#define MLXSW_SP_SB_CM(_pg_tc, _dir, _min_buff, _max_buff, _pool) \ + { \ + .u.pg = _pg_tc, \ + .dir = _dir, \ + .min_buff = _min_buff, \ + .max_buff = _max_buff, \ + .pool = _pool, \ + } + +#define MLXSW_SP_SB_CM_INGRESS(_pg, _min_buff, _max_buff) \ + MLXSW_SP_SB_CM(_pg, MLXSW_REG_SBCM_DIR_INGRESS, \ + _min_buff, _max_buff, 0) + +#define MLXSW_SP_SB_CM_EGRESS(_tc, _min_buff, _max_buff) \ + MLXSW_SP_SB_CM(_tc, MLXSW_REG_SBCM_DIR_EGRESS, \ + _min_buff, _max_buff, 0) + +#define MLXSW_SP_CPU_PORT_SB_CM_EGRESS(_tc) \ + MLXSW_SP_SB_CM(_tc, MLXSW_REG_SBCM_DIR_EGRESS, 104, 2, 3) + +static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms[] = { + MLXSW_SP_SB_CM_INGRESS(0, 10000 / MLXSW_SP_SB_BYTES_PER_CELL, 8), + MLXSW_SP_SB_CM_INGRESS(1, 0, 0), + MLXSW_SP_SB_CM_INGRESS(2, 0, 0), + MLXSW_SP_SB_CM_INGRESS(3, 0, 0), + MLXSW_SP_SB_CM_INGRESS(4, 0, 0), + MLXSW_SP_SB_CM_INGRESS(5, 0, 0), + MLXSW_SP_SB_CM_INGRESS(6, 0, 0), + MLXSW_SP_SB_CM_INGRESS(7, 0, 0), + MLXSW_SP_SB_CM_INGRESS(9, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff), + MLXSW_SP_SB_CM_EGRESS(0, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9), + MLXSW_SP_SB_CM_EGRESS(1, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9), + MLXSW_SP_SB_CM_EGRESS(2, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9), + MLXSW_SP_SB_CM_EGRESS(3, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9), + MLXSW_SP_SB_CM_EGRESS(4, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9), + MLXSW_SP_SB_CM_EGRESS(5, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9), + MLXSW_SP_SB_CM_EGRESS(6, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9), + MLXSW_SP_SB_CM_EGRESS(7, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9), + MLXSW_SP_SB_CM_EGRESS(8, 0, 0), + MLXSW_SP_SB_CM_EGRESS(9, 0, 0), + MLXSW_SP_SB_CM_EGRESS(10, 0, 0), + MLXSW_SP_SB_CM_EGRESS(11, 0, 0), + MLXSW_SP_SB_CM_EGRESS(12, 0, 0), + MLXSW_SP_SB_CM_EGRESS(13, 0, 0), + MLXSW_SP_SB_CM_EGRESS(14, 0, 0), + MLXSW_SP_SB_CM_EGRESS(15, 0, 0), + MLXSW_SP_SB_CM_EGRESS(16, 1, 0xff), +}; + +#define MLXSW_SP_SB_CMS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms) + +static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = { + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(0), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(1), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(2), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(3), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(4), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(5), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(6), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(7), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(8), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(9), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(10), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(11), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(12), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(13), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(14), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(15), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(16), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(17), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(18), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(19), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(20), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(21), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(22), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(23), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(24), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(25), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(26), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(27), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(28), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(29), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(30), + MLXSW_SP_CPU_PORT_SB_CM_EGRESS(31), +}; + +#define MLXSW_SP_CPU_PORT_SB_MCS_LEN \ + ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms) + +static int mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port, + const struct mlxsw_sp_sb_cm *cms, + size_t cms_len) +{ + char sbcm_pl[MLXSW_REG_SBCM_LEN]; + int i; + int err; + + for (i = 0; i < cms_len; i++) { + const struct mlxsw_sp_sb_cm *cm; + + cm = &cms[i]; + mlxsw_reg_sbcm_pack(sbcm_pl, local_port, cm->u.pg, cm->dir, + cm->min_buff, cm->max_buff, cm->pool); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbcm), sbcm_pl); + if (err) + return err; + } + return 0; +} + +static int mlxsw_sp_port_sb_cms_init(struct mlxsw_sp_port *mlxsw_sp_port) +{ + return mlxsw_sp_sb_cms_init(mlxsw_sp_port->mlxsw_sp, + mlxsw_sp_port->local_port, mlxsw_sp_sb_cms, + MLXSW_SP_SB_CMS_LEN); +} + +static int mlxsw_sp_cpu_port_sb_cms_init(struct mlxsw_sp *mlxsw_sp) +{ + return mlxsw_sp_sb_cms_init(mlxsw_sp, 0, mlxsw_sp_cpu_port_sb_cms, + MLXSW_SP_CPU_PORT_SB_MCS_LEN); +} + +struct mlxsw_sp_sb_pm { + u8 pool; + enum mlxsw_reg_sbpm_dir dir; + u32 min_buff; + u32 max_buff; +}; + +#define MLXSW_SP_SB_PM(_pool, _dir, _min_buff, _max_buff) \ + { \ + .pool = _pool, \ + .dir = _dir, \ + .min_buff = _min_buff, \ + .max_buff = _max_buff, \ + } + +#define MLXSW_SP_SB_PM_INGRESS(_pool, _min_buff, _max_buff) \ + MLXSW_SP_SB_PM(_pool, MLXSW_REG_SBPM_DIR_INGRESS, \ + _min_buff, _max_buff) + +#define MLXSW_SP_SB_PM_EGRESS(_pool, _min_buff, _max_buff) \ + MLXSW_SP_SB_PM(_pool, MLXSW_REG_SBPM_DIR_EGRESS, \ + _min_buff, _max_buff) + +static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms[] = { + MLXSW_SP_SB_PM_INGRESS(0, 0, 0xff), + MLXSW_SP_SB_PM_INGRESS(1, 0, 0), + MLXSW_SP_SB_PM_INGRESS(2, 0, 0), + MLXSW_SP_SB_PM_INGRESS(3, 0, 0), + MLXSW_SP_SB_PM_EGRESS(0, 0, 7), + MLXSW_SP_SB_PM_EGRESS(1, 0, 0), + MLXSW_SP_SB_PM_EGRESS(2, 0, 0), + MLXSW_SP_SB_PM_EGRESS(3, 0, 0), +}; + +#define MLXSW_SP_SB_PMS_LEN ARRAY_SIZE(mlxsw_sp_sb_pms) + +static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port) +{ + char sbpm_pl[MLXSW_REG_SBPM_LEN]; + int i; + int err; + + for (i = 0; i < MLXSW_SP_SB_PMS_LEN; i++) { + const struct mlxsw_sp_sb_pm *pm; + + pm = &mlxsw_sp_sb_pms[i]; + mlxsw_reg_sbpm_pack(sbpm_pl, mlxsw_sp_port->local_port, + pm->pool, pm->dir, + pm->min_buff, pm->max_buff); + err = mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, + MLXSW_REG(sbpm), sbpm_pl); + if (err) + return err; + } + return 0; +} + +struct mlxsw_sp_sb_mm { + u8 prio; + u32 min_buff; + u32 max_buff; + u8 pool; +}; + +#define MLXSW_SP_SB_MM(_prio, _min_buff, _max_buff, _pool) \ + { \ + .prio = _prio, \ + .min_buff = _min_buff, \ + .max_buff = _max_buff, \ + .pool = _pool, \ + } + +static const struct mlxsw_sp_sb_mm mlxsw_sp_sb_mms[] = { + MLXSW_SP_SB_MM(0, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(1, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(2, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(3, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(4, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(5, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(6, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(7, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(8, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(9, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(10, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(11, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(12, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(13, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), + MLXSW_SP_SB_MM(14, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0), +}; + +#define MLXSW_SP_SB_MMS_LEN ARRAY_SIZE(mlxsw_sp_sb_mms) + +static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp) +{ + char sbmm_pl[MLXSW_REG_SBMM_LEN]; + int i; + int err; + + for (i = 0; i < MLXSW_SP_SB_MMS_LEN; i++) { + const struct mlxsw_sp_sb_mm *mc; + + mc = &mlxsw_sp_sb_mms[i]; + mlxsw_reg_sbmm_pack(sbmm_pl, mc->prio, mc->min_buff, + mc->max_buff, mc->pool); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbmm), sbmm_pl); + if (err) + return err; + } + return 0; +} + +int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp) +{ + int err; + + err = mlxsw_sp_sb_pools_init(mlxsw_sp); + if (err) + return err; + err = mlxsw_sp_cpu_port_sb_cms_init(mlxsw_sp); + if (err) + return err; + err = mlxsw_sp_sb_mms_init(mlxsw_sp); + + return err; +} + +int mlxsw_sp_port_buffers_init(struct mlxsw_sp_port *mlxsw_sp_port) +{ + int err; + + err = mlxsw_sp_port_pb_init(mlxsw_sp_port); + if (err) + return err; + err = mlxsw_sp_port_sb_cms_init(mlxsw_sp_port); + if (err) + return err; + err = mlxsw_sp_port_sb_pms_init(mlxsw_sp_port); + + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c new file mode 100644 index 000000000000..c39b7a188726 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -0,0 +1,863 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c + * Copyright (c) 2015 Mellanox Technologies. All rights reserved. + * Copyright (c) 2015 Jiri Pirko <[email protected]> + * Copyright (c) 2015 Ido Schimmel <[email protected]> + * Copyright (c) 2015 Elad Raz <[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/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/slab.h> +#include <linux/device.h> +#include <linux/skbuff.h> +#include <linux/if_vlan.h> +#include <linux/if_bridge.h> +#include <linux/workqueue.h> +#include <linux/jiffies.h> +#include <net/switchdev.h> + +#include "spectrum.h" +#include "core.h" +#include "reg.h" + +static int mlxsw_sp_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: + attr->u.ppid.id_len = sizeof(mlxsw_sp->base_mac); + memcpy(&attr->u.ppid.id, &mlxsw_sp->base_mac, + attr->u.ppid.id_len); + break; + case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: + attr->u.brport_flags = + (mlxsw_sp_port->learning ? BR_LEARNING : 0) | + (mlxsw_sp_port->learning_sync ? BR_LEARNING_SYNC : 0); + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int mlxsw_sp_port_stp_state_set(struct mlxsw_sp_port *mlxsw_sp_port, + u8 state) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + enum mlxsw_reg_spms_state spms_state; + char *spms_pl; + u16 vid; + int err; + + switch (state) { + case BR_STATE_DISABLED: /* fall-through */ + case BR_STATE_FORWARDING: + spms_state = MLXSW_REG_SPMS_STATE_FORWARDING; + break; + case BR_STATE_LISTENING: /* fall-through */ + case BR_STATE_LEARNING: + spms_state = MLXSW_REG_SPMS_STATE_LEARNING; + break; + case BR_STATE_BLOCKING: + spms_state = MLXSW_REG_SPMS_STATE_DISCARDING; + break; + default: + BUG(); + } + + 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); + for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) + mlxsw_reg_spms_vid_pack(spms_pl, vid, spms_state); + + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spms), spms_pl); + kfree(spms_pl); + return err; +} + +static int mlxsw_sp_port_attr_stp_state_set(struct mlxsw_sp_port *mlxsw_sp_port, + struct switchdev_trans *trans, + u8 state) +{ + if (switchdev_trans_ph_prepare(trans)) + return 0; + + mlxsw_sp_port->stp_state = state; + return mlxsw_sp_port_stp_state_set(mlxsw_sp_port, state); +} + +static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port, + struct switchdev_trans *trans, + unsigned long brport_flags) +{ + if (switchdev_trans_ph_prepare(trans)) + return 0; + + mlxsw_sp_port->learning = brport_flags & BR_LEARNING ? 1 : 0; + mlxsw_sp_port->learning_sync = brport_flags & BR_LEARNING_SYNC ? 1 : 0; + return 0; +} + +static int mlxsw_sp_ageing_set(struct mlxsw_sp *mlxsw_sp, u32 ageing_time) +{ + char sfdat_pl[MLXSW_REG_SFDAT_LEN]; + int err; + + mlxsw_reg_sfdat_pack(sfdat_pl, ageing_time); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdat), sfdat_pl); + if (err) + return err; + mlxsw_sp->ageing_time = ageing_time; + return 0; +} + +static int mlxsw_sp_port_attr_br_ageing_set(struct mlxsw_sp_port *mlxsw_sp_port, + struct switchdev_trans *trans, + unsigned long ageing_jiffies) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + u32 ageing_time = jiffies_to_msecs(ageing_jiffies) / 1000; + + if (switchdev_trans_ph_prepare(trans)) + return 0; + + return mlxsw_sp_ageing_set(mlxsw_sp, ageing_time); +} + +static int mlxsw_sp_port_attr_set(struct net_device *dev, + const struct switchdev_attr *attr, + struct switchdev_trans *trans) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + int err = 0; + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_PORT_STP_STATE: + err = mlxsw_sp_port_attr_stp_state_set(mlxsw_sp_port, trans, + attr->u.stp_state); + break; + case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: + err = mlxsw_sp_port_attr_br_flags_set(mlxsw_sp_port, trans, + attr->u.brport_flags); + break; + case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: + err = mlxsw_sp_port_attr_br_ageing_set(mlxsw_sp_port, trans, + attr->u.ageing_time); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char spvid_pl[MLXSW_REG_SPVID_LEN]; + + mlxsw_reg_spvid_pack(spvid_pl, mlxsw_sp_port->local_port, vid); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvid), spvid_pl); +} + +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 (mlxsw_sp_port->nr_vfids) + 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 (!mlxsw_sp_port->nr_vfids) + 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_flood_set(struct mlxsw_sp_port *mlxsw_sp_port, + u16 fid, bool set, bool only_uc) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char *sftr_pl; + int err; + + sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); + if (!sftr_pl) + return -ENOMEM; + + mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_UC, fid, + MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST, 0, + mlxsw_sp_port->local_port, set); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); + if (err) + goto buffer_out; + + /* Flooding control allows one to decide whether a given port will + * flood unicast traffic for which there is no FDB entry. + */ + if (only_uc) + goto buffer_out; + + mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BM, fid, + MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST, 0, + mlxsw_sp_port->local_port, set); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); + +buffer_out: + kfree(sftr_pl); + return err; +} + +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_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; + enum mlxsw_reg_svfa_mt mt; + u16 vid, vid_e; + 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); + return err; + } + } + + /* Set FID mapping according to port's mode */ + err = mlxsw_sp_port_fid_map(mlxsw_sp_port, vid); + if (err) { + netdev_err(dev, "Failed to map FID=%d", vid); + return err; + } + + err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid, true, + false); + if (err) { + netdev_err(dev, "Failed to set flooding for FID=%d", + vid); + return err; + } + } + + for (vid = vid_begin; vid <= vid_end; + vid += MLXSW_REG_SPVM_REC_MAX_COUNT) { + vid_e = min((u16) (vid + MLXSW_REG_SPVM_REC_MAX_COUNT - 1), + vid_end); + + err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid_e, true, + flag_untagged); + if (err) { + netdev_err(mlxsw_sp_port->dev, "Unable to add VIDs %d-%d\n", + vid, vid_e); + return err; + } + } + + vid = vid_begin; + if (flag_pvid && mlxsw_sp_port->pvid != vid) { + err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, vid); + if (err) { + netdev_err(mlxsw_sp_port->dev, "Unable to add PVID %d\n", + vid); + return err; + } + mlxsw_sp_port->pvid = vid; + } + + /* Changing activity bits only if HW operation succeded */ + for (vid = vid_begin; vid <= vid_end; vid++) + set_bit(vid, mlxsw_sp_port->active_vlans); + + return mlxsw_sp_port_stp_state_set(mlxsw_sp_port, + mlxsw_sp_port->stp_state); +} + +static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port, + const struct switchdev_obj_port_vlan *vlan, + struct switchdev_trans *trans) +{ + bool untagged_flag = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; + bool pvid_flag = vlan->flags & BRIDGE_VLAN_INFO_PVID; + + if (switchdev_trans_ph_prepare(trans)) + return 0; + + return __mlxsw_sp_port_vlans_add(mlxsw_sp_port, + vlan->vid_begin, vlan->vid_end, + untagged_flag, pvid_flag); +} + +static int mlxsw_sp_port_fdb_op(struct mlxsw_sp_port *mlxsw_sp_port, + const char *mac, u16 vid, bool adding, + bool dynamic) +{ + enum mlxsw_reg_sfd_rec_policy policy; + enum mlxsw_reg_sfd_op op; + char *sfd_pl; + int err; + + if (!vid) + vid = mlxsw_sp_port->pvid; + + sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL); + if (!sfd_pl) + return -ENOMEM; + + policy = dynamic ? MLXSW_REG_SFD_REC_POLICY_DYNAMIC_ENTRY_INGRESS : + MLXSW_REG_SFD_REC_POLICY_STATIC_ENTRY; + op = adding ? MLXSW_REG_SFD_OP_WRITE_EDIT : + MLXSW_REG_SFD_OP_WRITE_REMOVE; + mlxsw_reg_sfd_pack(sfd_pl, op, 0); + mlxsw_reg_sfd_uc_pack(sfd_pl, 0, policy, + mac, vid, MLXSW_REG_SFD_REC_ACTION_NOP, + mlxsw_sp_port->local_port); + err = mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(sfd), + sfd_pl); + kfree(sfd_pl); + + return err; +} + +static int +mlxsw_sp_port_fdb_static_add(struct mlxsw_sp_port *mlxsw_sp_port, + const struct switchdev_obj_port_fdb *fdb, + struct switchdev_trans *trans) +{ + if (switchdev_trans_ph_prepare(trans)) + return 0; + + return mlxsw_sp_port_fdb_op(mlxsw_sp_port, fdb->addr, fdb->vid, + true, false); +} + +static int mlxsw_sp_port_obj_add(struct net_device *dev, + const struct switchdev_obj *obj, + struct switchdev_trans *trans) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + int err = 0; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + err = mlxsw_sp_port_vlans_add(mlxsw_sp_port, + SWITCHDEV_OBJ_PORT_VLAN(obj), + trans); + break; + case SWITCHDEV_OBJ_ID_PORT_FDB: + err = mlxsw_sp_port_fdb_static_add(mlxsw_sp_port, + SWITCHDEV_OBJ_PORT_FDB(obj), + trans); + break; + default: + err = -EOPNOTSUPP; + break; + } + + 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) +{ + struct net_device *dev = mlxsw_sp_port->dev; + u16 vid, vid_e; + 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); + + for (vid = vid_begin; vid <= vid_end; + vid += MLXSW_REG_SPVM_REC_MAX_COUNT) { + vid_e = min((u16) (vid + MLXSW_REG_SPVM_REC_MAX_COUNT - 1), + vid_end); + err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid_e, false, + false); + if (err) { + netdev_err(mlxsw_sp_port->dev, "Unable to del VIDs %d-%d\n", + vid, vid_e); + return err; + } + } + + if ((mlxsw_sp_port->pvid >= vid_begin) && + (mlxsw_sp_port->pvid <= vid_end)) { + /* Default VLAN is always 1 */ + mlxsw_sp_port->pvid = 1; + err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, + mlxsw_sp_port->pvid); + if (err) { + netdev_err(mlxsw_sp_port->dev, "Unable to del PVID %d\n", + vid); + return err; + } + } + + if (init) + goto out; + + for (vid = vid_begin; vid <= vid_end; vid++) { + err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid, false, + false); + if (err) { + netdev_err(dev, "Failed to clear flooding for FID=%d", + vid); + return err; + } + + /* 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; + } + } + +out: + /* Changing activity bits only if HW operation succeded */ + for (vid = vid_begin; vid <= vid_end; vid++) + clear_bit(vid, mlxsw_sp_port->active_vlans); + + return 0; +} + +static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, + const struct switchdev_obj_port_vlan *vlan) +{ + return __mlxsw_sp_port_vlans_del(mlxsw_sp_port, + vlan->vid_begin, vlan->vid_end, false); +} + +static int +mlxsw_sp_port_fdb_static_del(struct mlxsw_sp_port *mlxsw_sp_port, + const struct switchdev_obj_port_fdb *fdb) +{ + return mlxsw_sp_port_fdb_op(mlxsw_sp_port, fdb->addr, fdb->vid, + false, false); +} + +static int mlxsw_sp_port_obj_del(struct net_device *dev, + const struct switchdev_obj *obj) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + int err = 0; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + err = mlxsw_sp_port_vlans_del(mlxsw_sp_port, + SWITCHDEV_OBJ_PORT_VLAN(obj)); + break; + case SWITCHDEV_OBJ_ID_PORT_FDB: + err = mlxsw_sp_port_fdb_static_del(mlxsw_sp_port, + SWITCHDEV_OBJ_PORT_FDB(obj)); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, + struct switchdev_obj_port_fdb *fdb, + switchdev_obj_dump_cb_t *cb) +{ + char *sfd_pl; + char mac[ETH_ALEN]; + u16 vid; + u8 local_port; + u8 num_rec; + int stored_err = 0; + int i; + int err; + + sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL); + if (!sfd_pl) + return -ENOMEM; + + mlxsw_reg_sfd_pack(sfd_pl, MLXSW_REG_SFD_OP_QUERY_DUMP, 0); + do { + mlxsw_reg_sfd_num_rec_set(sfd_pl, MLXSW_REG_SFD_REC_MAX_COUNT); + err = mlxsw_reg_query(mlxsw_sp_port->mlxsw_sp->core, + MLXSW_REG(sfd), sfd_pl); + if (err) + goto out; + + num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl); + + /* Even in case of error, we have to run the dump to the end + * so the session in firmware is finished. + */ + if (stored_err) + continue; + + for (i = 0; i < num_rec; i++) { + switch (mlxsw_reg_sfd_rec_type_get(sfd_pl, i)) { + case MLXSW_REG_SFD_REC_TYPE_UNICAST: + mlxsw_reg_sfd_uc_unpack(sfd_pl, i, mac, &vid, + &local_port); + if (local_port == mlxsw_sp_port->local_port) { + ether_addr_copy(fdb->addr, mac); + fdb->ndm_state = NUD_REACHABLE; + fdb->vid = vid; + err = cb(&fdb->obj); + if (err) + stored_err = err; + } + } + } + } while (num_rec == MLXSW_REG_SFD_REC_MAX_COUNT); + +out: + kfree(sfd_pl); + return stored_err ? stored_err : err; +} + +static int mlxsw_sp_port_vlan_dump(struct mlxsw_sp_port *mlxsw_sp_port, + struct switchdev_obj_port_vlan *vlan, + switchdev_obj_dump_cb_t *cb) +{ + u16 vid; + int err = 0; + + for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) { + vlan->flags = 0; + if (vid == mlxsw_sp_port->pvid) + vlan->flags |= BRIDGE_VLAN_INFO_PVID; + vlan->vid_begin = vid; + vlan->vid_end = vid; + err = cb(&vlan->obj); + if (err) + break; + } + return err; +} + +static int mlxsw_sp_port_obj_dump(struct net_device *dev, + struct switchdev_obj *obj, + switchdev_obj_dump_cb_t *cb) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + int err = 0; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + err = mlxsw_sp_port_vlan_dump(mlxsw_sp_port, + SWITCHDEV_OBJ_PORT_VLAN(obj), cb); + break; + case SWITCHDEV_OBJ_ID_PORT_FDB: + err = mlxsw_sp_port_fdb_dump(mlxsw_sp_port, + SWITCHDEV_OBJ_PORT_FDB(obj), cb); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +const struct switchdev_ops mlxsw_sp_port_switchdev_ops = { + .switchdev_port_attr_get = mlxsw_sp_port_attr_get, + .switchdev_port_attr_set = mlxsw_sp_port_attr_set, + .switchdev_port_obj_add = mlxsw_sp_port_obj_add, + .switchdev_port_obj_del = mlxsw_sp_port_obj_del, + .switchdev_port_obj_dump = mlxsw_sp_port_obj_dump, +}; + +static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, + char *sfn_pl, int rec_index, + bool adding) +{ + struct mlxsw_sp_port *mlxsw_sp_port; + char mac[ETH_ALEN]; + u8 local_port; + u16 vid; + int err; + + mlxsw_reg_sfn_mac_unpack(sfn_pl, rec_index, mac, &vid, &local_port); + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + if (!mlxsw_sp_port) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect local port in FDB notification\n"); + return; + } + + err = mlxsw_sp_port_fdb_op(mlxsw_sp_port, mac, vid, + adding && mlxsw_sp_port->learning, true); + if (err) { + if (net_ratelimit()) + netdev_err(mlxsw_sp_port->dev, "Failed to set FDB entry\n"); + return; + } + + if (mlxsw_sp_port->learning && mlxsw_sp_port->learning_sync) { + struct switchdev_notifier_fdb_info info; + unsigned long notifier_type; + + info.addr = mac; + info.vid = vid; + notifier_type = adding ? SWITCHDEV_FDB_ADD : SWITCHDEV_FDB_DEL; + call_switchdev_notifiers(notifier_type, mlxsw_sp_port->dev, + &info.info); + } +} + +static void mlxsw_sp_fdb_notify_rec_process(struct mlxsw_sp *mlxsw_sp, + char *sfn_pl, int rec_index) +{ + switch (mlxsw_reg_sfn_rec_type_get(sfn_pl, rec_index)) { + case MLXSW_REG_SFN_REC_TYPE_LEARNED_MAC: + mlxsw_sp_fdb_notify_mac_process(mlxsw_sp, sfn_pl, + rec_index, true); + break; + case MLXSW_REG_SFN_REC_TYPE_AGED_OUT_MAC: + mlxsw_sp_fdb_notify_mac_process(mlxsw_sp, sfn_pl, + rec_index, false); + break; + } +} + +static void mlxsw_sp_fdb_notify_work_schedule(struct mlxsw_sp *mlxsw_sp) +{ + schedule_delayed_work(&mlxsw_sp->fdb_notify.dw, + msecs_to_jiffies(mlxsw_sp->fdb_notify.interval)); +} + +static void mlxsw_sp_fdb_notify_work(struct work_struct *work) +{ + struct mlxsw_sp *mlxsw_sp; + char *sfn_pl; + u8 num_rec; + int i; + int err; + + sfn_pl = kmalloc(MLXSW_REG_SFN_LEN, GFP_KERNEL); + if (!sfn_pl) + return; + + mlxsw_sp = container_of(work, struct mlxsw_sp, fdb_notify.dw.work); + + do { + mlxsw_reg_sfn_pack(sfn_pl); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(sfn), sfn_pl); + if (err) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get FDB notifications\n"); + break; + } + num_rec = mlxsw_reg_sfn_num_rec_get(sfn_pl); + for (i = 0; i < num_rec; i++) + mlxsw_sp_fdb_notify_rec_process(mlxsw_sp, sfn_pl, i); + + } while (num_rec); + + kfree(sfn_pl); + mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp); +} + +static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp) +{ + int err; + + err = mlxsw_sp_ageing_set(mlxsw_sp, MLXSW_SP_DEFAULT_AGEING_TIME); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to set default ageing time\n"); + return err; + } + INIT_DELAYED_WORK(&mlxsw_sp->fdb_notify.dw, mlxsw_sp_fdb_notify_work); + mlxsw_sp->fdb_notify.interval = MLXSW_SP_DEFAULT_LEARNING_INTERVAL; + mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp); + return 0; +} + +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); +} + +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) +{ + struct net_device *dev = mlxsw_sp_port->dev; + int err; + + /* Allow only untagged packets to ingress and tag them internally + * with VID 1. + */ + mlxsw_sp_port->pvid = 1; + err = __mlxsw_sp_port_vlans_del(mlxsw_sp_port, 0, VLAN_N_VID, true); + if (err) { + netdev_err(dev, "Unable to init VLANs\n"); + return err; + } + + /* Add implicit VLAN interface in the device, so that untagged + * packets will be classified to the default vFID. + */ + err = mlxsw_sp_port_add_vid(dev, 0, 1); + if (err) + netdev_err(dev, "Failed to configure default vFID\n"); + + return err; +} + +void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port) +{ + mlxsw_sp_port->dev->switchdev_ops = &mlxsw_sp_port_switchdev_ops; +} + +void mlxsw_sp_port_switchdev_fini(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 d448431bbc83..50e29c4879db 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -57,13 +57,11 @@ static const char mlxsw_sx_driver_version[] = "1.0"; struct mlxsw_sx_port; -#define MLXSW_SW_HW_ID_LEN 6 - struct mlxsw_sx { struct mlxsw_sx_port **ports; struct mlxsw_core *core; const struct mlxsw_bus_info *bus_info; - u8 hw_id[MLXSW_SW_HW_ID_LEN]; + u8 hw_id[ETH_ALEN]; }; struct mlxsw_sx_port_pcpu_stats { @@ -925,7 +923,8 @@ static int mlxsw_sx_port_stp_state_set(struct mlxsw_sx_port *mlxsw_sx_port, spms_pl = kmalloc(MLXSW_REG_SPMS_LEN, GFP_KERNEL); if (!spms_pl) return -ENOMEM; - mlxsw_reg_spms_pack(spms_pl, mlxsw_sx_port->local_port, vid, state); + mlxsw_reg_spms_pack(spms_pl, mlxsw_sx_port->local_port); + mlxsw_reg_spms_vid_pack(spms_pl, vid, state); err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(spms), spms_pl); kfree(spms_pl); return err; @@ -1069,9 +1068,9 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port) return 0; err_register_netdev: -err_port_admin_status_set: err_port_mac_learning_mode_set: err_port_stp_state_set: +err_port_admin_status_set: err_port_mtu_set: err_port_speed_set: err_port_swid_set: @@ -1178,8 +1177,7 @@ static int mlxsw_sx_event_register(struct mlxsw_sx *mlxsw_sx, if (err) return err; - mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD, - MLXSW_REG_HTGT_TRAP_GROUP_EMAD, trap_id); + mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD, trap_id); err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(hpkt), hpkt_pl); if (err) goto err_event_trap_set; @@ -1212,9 +1210,8 @@ static void mlxsw_sx_rx_listener_func(struct sk_buff *skb, u8 local_port, struct mlxsw_sx_port_pcpu_stats *pcpu_stats; if (unlikely(!mlxsw_sx_port)) { - if (net_ratelimit()) - dev_warn(mlxsw_sx->bus_info->dev, "Port %d: skb received for non-existent port\n", - local_port); + dev_warn_ratelimited(mlxsw_sx->bus_info->dev, "Port %d: skb received for non-existent port\n", + local_port); return; } @@ -1316,6 +1313,11 @@ static int mlxsw_sx_traps_init(struct mlxsw_sx *mlxsw_sx) if (err) return err; + mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_CTRL); + err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(htgt), htgt_pl); + if (err) + return err; + for (i = 0; i < ARRAY_SIZE(mlxsw_sx_rx_listener); i++) { err = mlxsw_core_rx_listener_register(mlxsw_sx->core, &mlxsw_sx_rx_listener[i], @@ -1324,7 +1326,6 @@ static int mlxsw_sx_traps_init(struct mlxsw_sx *mlxsw_sx) goto err_rx_listener_register; mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_TRAP_TO_CPU, - MLXSW_REG_HTGT_TRAP_GROUP_RX, mlxsw_sx_rx_listener[i].trap_id); err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(hpkt), hpkt_pl); if (err) @@ -1339,7 +1340,6 @@ err_rx_trap_set: err_rx_listener_register: for (i--; i >= 0; i--) { mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD, - MLXSW_REG_HTGT_TRAP_GROUP_RX, mlxsw_sx_rx_listener[i].trap_id); mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(hpkt), hpkt_pl); @@ -1357,7 +1357,6 @@ static void mlxsw_sx_traps_fini(struct mlxsw_sx *mlxsw_sx) for (i = 0; i < ARRAY_SIZE(mlxsw_sx_rx_listener); i++) { mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD, - MLXSW_REG_HTGT_TRAP_GROUP_RX, mlxsw_sx_rx_listener[i].trap_id); mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(hpkt), hpkt_pl); @@ -1371,25 +1370,15 @@ static int mlxsw_sx_flood_init(struct mlxsw_sx *mlxsw_sx) { char sfgc_pl[MLXSW_REG_SFGC_LEN]; char sgcr_pl[MLXSW_REG_SGCR_LEN]; - char *smid_pl; char *sftr_pl; int err; - /* Due to FW bug, we must configure SMID. */ - smid_pl = kmalloc(MLXSW_REG_SMID_LEN, GFP_KERNEL); - if (!smid_pl) - return -ENOMEM; - mlxsw_reg_smid_pack(smid_pl, MLXSW_PORT_MID); - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(smid), smid_pl); - kfree(smid_pl); - if (err) - return err; - /* Configure a flooding table, which includes only CPU port. */ sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); if (!sftr_pl) return -ENOMEM; - mlxsw_reg_sftr_pack(sftr_pl, 0, 0, MLXSW_REG_SFGC_TABLE_TYPE_SINGLE, 0); + mlxsw_reg_sftr_pack(sftr_pl, 0, 0, MLXSW_REG_SFGC_TABLE_TYPE_SINGLE, 0, + MLXSW_PORT_CPU_PORT, true); err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sftr), sftr_pl); kfree(sftr_pl); if (err) diff --git a/drivers/net/ethernet/mellanox/mlxsw/txheader.h b/drivers/net/ethernet/mellanox/mlxsw/txheader.h index 06fc46c78a0b..fdf94720ca62 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/txheader.h +++ b/drivers/net/ethernet/mellanox/mlxsw/txheader.h @@ -38,6 +38,7 @@ #define MLXSW_TXHDR_LEN 0x10 #define MLXSW_TXHDR_VERSION_0 0 +#define MLXSW_TXHDR_VERSION_1 1 enum { MLXSW_TXHDR_ETH_CTL, diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 2d1b94274079..9ba975853ec6 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -5389,8 +5389,6 @@ static void s2io_ethtool_gdrvinfo(struct net_device *dev, strlcpy(info->driver, s2io_driver_name, sizeof(info->driver)); strlcpy(info->version, s2io_driver_version, sizeof(info->version)); strlcpy(info->bus_info, pci_name(sp->pdev), sizeof(info->bus_info)); - info->regdump_len = XENA_REG_SPACE; - info->eedump_len = XENA_EEPROM_SPACE; } /** diff --git a/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c b/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c index be916eb2f2e7..9a2967016c18 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c @@ -105,10 +105,6 @@ static void vxge_ethtool_gdrvinfo(struct net_device *dev, strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->fw_version, vdev->fw_version, sizeof(info->fw_version)); strlcpy(info->bus_info, pci_name(vdev->pdev), sizeof(info->bus_info)); - info->regdump_len = sizeof(struct vxge_hw_vpath_reg) - * vdev->no_of_vpath; - - info->n_stats = STAT_LEN; } /** diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 66fd868152e5..b159ef8303cc 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -476,13 +476,12 @@ static void __lpc_get_mac(struct netdata_local *pldat, u8 *mac) mac[5] = tmp >> 8; } -static void __lpc_eth_clock_enable(struct netdata_local *pldat, - bool enable) +static void __lpc_eth_clock_enable(struct netdata_local *pldat, bool enable) { if (enable) - clk_enable(pldat->clk); + clk_prepare_enable(pldat->clk); else - clk_disable(pldat->clk); + clk_disable_unprepare(pldat->clk); } static void __lpc_params_setup(struct netdata_local *pldat) @@ -1494,7 +1493,7 @@ err_out_free_irq: err_out_iounmap: iounmap(pldat->net_base); err_out_disable_clocks: - clk_disable(pldat->clk); + clk_disable_unprepare(pldat->clk); clk_put(pldat->clk); err_out_free_dev: free_netdev(ndev); @@ -1519,7 +1518,7 @@ static int lpc_eth_drv_remove(struct platform_device *pdev) iounmap(pldat->net_base); mdiobus_unregister(pldat->mii_bus); mdiobus_free(pldat->mii_bus); - clk_disable(pldat->clk); + clk_disable_unprepare(pldat->clk); clk_put(pldat->clk); free_netdev(ndev); @@ -1540,7 +1539,7 @@ static int lpc_eth_drv_suspend(struct platform_device *pdev, if (netif_running(ndev)) { netif_device_detach(ndev); __lpc_eth_shutdown(pldat); - clk_disable(pldat->clk); + clk_disable_unprepare(pldat->clk); /* * Reset again now clock is disable to be sure diff --git a/drivers/net/ethernet/octeon/octeon_mgmt.c b/drivers/net/ethernet/octeon/octeon_mgmt.c index 7bf9c028d8d7..c177c7cec13b 100644 --- a/drivers/net/ethernet/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/octeon/octeon_mgmt.c @@ -1344,10 +1344,6 @@ static void octeon_mgmt_get_drvinfo(struct net_device *netdev, strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); strlcpy(info->bus_info, "N/A", sizeof(info->bus_info)); - info->n_stats = 0; - info->testinfo_len = 0; - info->regdump_len = 0; - info->eedump_len = 0; } static int octeon_mgmt_get_settings(struct net_device *netdev, diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c index f6fcf7450352..b19be7c6c1f4 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c @@ -164,7 +164,6 @@ static void pch_gbe_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->version, pch_driver_version, sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->regdump_len = pch_gbe_get_regs_len(netdev); } /** diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c index 87e073c6e291..f9034467736c 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c @@ -93,8 +93,6 @@ netxen_nic_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->regdump_len = NETXEN_NIC_REGS_LEN; - drvinfo->eedump_len = netxen_nic_get_eeprom_len(dev); } static int diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 4847713211ca..b09a6b80d107 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -1736,8 +1736,6 @@ static void ql_get_drvinfo(struct net_device *ndev, sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(qdev->pdev), sizeof(drvinfo->bus_info)); - drvinfo->regdump_len = 0; - drvinfo->eedump_len = 0; } static u32 ql_get_msglevel(struct net_device *ndev) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index d6696cfa11d2..46bbea8e023c 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -1092,7 +1092,7 @@ struct qlcnic_filter_hash { struct qlcnic_mailbox { struct workqueue_struct *work_q; struct qlcnic_adapter *adapter; - struct qlcnic_mbx_ops *ops; + const struct qlcnic_mbx_ops *ops; struct work_struct work; struct completion completion; struct list_head cmd_q; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 9f0bdd993955..37a731be7d39 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -4048,7 +4048,7 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work) struct qlcnic_mailbox *mbx = container_of(work, struct qlcnic_mailbox, work); struct qlcnic_adapter *adapter = mbx->adapter; - struct qlcnic_mbx_ops *mbx_ops = mbx->ops; + const struct qlcnic_mbx_ops *mbx_ops = mbx->ops; struct device *dev = &adapter->pdev->dev; atomic_t *rsp_status = &mbx->rsp_status; struct list_head *head = &mbx->cmd_q; @@ -4098,7 +4098,7 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work) } } -static struct qlcnic_mbx_ops qlcnic_83xx_mbx_ops = { +static const struct qlcnic_mbx_ops qlcnic_83xx_mbx_ops = { .enqueue_cmd = qlcnic_83xx_enqueue_mbx_cmd, .dequeue_cmd = qlcnic_83xx_dequeue_mbx_cmd, .decode_resp = qlcnic_83xx_decode_mbx_rsp, diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c index c3c514e332b5..5dade1fd08b8 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c @@ -415,13 +415,6 @@ static void ql_get_drvinfo(struct net_device *ndev, (qdev->fw_rev_id & 0x000000ff)); strlcpy(drvinfo->bus_info, pci_name(qdev->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_stats = 0; - drvinfo->testinfo_len = 0; - if (!test_bit(QL_FRC_COREDUMP, &qdev->flags)) - drvinfo->regdump_len = sizeof(struct ql_mpi_coredump); - else - drvinfo->regdump_len = sizeof(struct ql_reg_dump); - drvinfo->eedump_len = 0; } static void ql_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index 78bb4ceb1cdd..ef668d300800 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -2388,7 +2388,6 @@ static void rtl8139_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo * strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info)); - info->regdump_len = tp->regs_len; } static int rtl8139_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index eafa907965ec..32a80d2df7ff 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -3672,7 +3672,7 @@ static int rocker_port_fdb_flush(struct rocker_port *rocker_port, rocker_port->stp_state == BR_STATE_FORWARDING) return 0; - flags |= ROCKER_OP_FLAG_REMOVE; + flags |= ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE; spin_lock_irqsave(&rocker->fdb_tbl_lock, lock_flags); @@ -4374,7 +4374,7 @@ static int rocker_port_bridge_ageing_time(struct rocker_port *rocker_port, } static int rocker_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr, + const struct switchdev_attr *attr, struct switchdev_trans *trans) { struct rocker_port *rocker_port = netdev_priv(dev); @@ -4382,8 +4382,7 @@ static int rocker_port_attr_set(struct net_device *dev, switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: - err = rocker_port_stp_update(rocker_port, trans, - ROCKER_OP_FLAG_NOWAIT, + err = rocker_port_stp_update(rocker_port, trans, 0, attr->u.stp_state); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: @@ -4469,7 +4468,7 @@ static int rocker_port_obj_add(struct net_device *dev, fib4 = SWITCHDEV_OBJ_IPV4_FIB(obj); err = rocker_port_fib_ipv4(rocker_port, trans, htonl(fib4->dst), fib4->dst_len, - fib4->fi, fib4->tb_id, 0); + &fib4->fi, fib4->tb_id, 0); break; case SWITCHDEV_OBJ_ID_PORT_FDB: err = rocker_port_fdb_add(rocker_port, trans, @@ -4517,7 +4516,7 @@ static int rocker_port_fdb_del(struct rocker_port *rocker_port, const struct switchdev_obj_port_fdb *fdb) { __be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, fdb->vid, NULL); - int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE; + int flags = ROCKER_OP_FLAG_REMOVE; if (!rocker_port_is_bridged(rocker_port)) return -EINVAL; @@ -4541,7 +4540,7 @@ static int rocker_port_obj_del(struct net_device *dev, fib4 = SWITCHDEV_OBJ_IPV4_FIB(obj); err = rocker_port_fib_ipv4(rocker_port, NULL, htonl(fib4->dst), fib4->dst_len, - fib4->fi, fib4->tb_id, + &fib4->fi, fib4->tb_id, ROCKER_OP_FLAG_REMOVE); break; case SWITCHDEV_OBJ_ID_PORT_FDB: @@ -4571,7 +4570,7 @@ static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, hash_for_each_safe(rocker->fdb_tbl, bkt, tmp, found, entry) { if (found->key.rocker_port != rocker_port) continue; - fdb->addr = found->key.addr; + ether_addr_copy(fdb->addr, found->key.addr); fdb->ndm_state = NUD_REACHABLE; fdb->vid = rocker_port_vlan_to_vid(rocker_port, found->key.vlan_id); diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 6ce973187225..062bce9acde6 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -4529,9 +4529,6 @@ static void cas_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver)); strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(cp->pdev), sizeof(info->bus_info)); - info->regdump_len = cp->casreg_len < CAS_MAX_REGS ? - cp->casreg_len : CAS_MAX_REGS; - info->n_stats = CAS_NUM_STAT_KEYS; } static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index a9cac8413e49..14c9d1baa85c 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -2182,11 +2182,6 @@ bdx_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(priv->pdev), sizeof(drvinfo->bus_info)); - - drvinfo->n_stats = ((priv->stats_flag) ? ARRAY_SIZE(bdx_stat_names) : 0); - drvinfo->testinfo_len = 0; - drvinfo->regdump_len = 0; - drvinfo->eedump_len = 0; } /* diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index cba3d9fcb465..77d26fe286c0 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -899,7 +899,6 @@ static void cpmac_get_drvinfo(struct net_device *dev, strlcpy(info->driver, "cpmac", sizeof(info->driver)); strlcpy(info->version, CPMAC_VERSION, sizeof(info->version)); snprintf(info->bus_info, sizeof(info->bus_info), "%s", "cpmac"); - info->regdump_len = 0; } static const struct ethtool_ops cpmac_ethtool_ops = { diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 75584cc36339..3b75adfb3f37 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1784,7 +1784,6 @@ static void cpsw_get_drvinfo(struct net_device *ndev, strlcpy(info->driver, "cpsw", sizeof(info->driver)); strlcpy(info->version, "1.0", sizeof(info->version)); strlcpy(info->bus_info, priv->pdev->name, sizeof(info->bus_info)); - info->regdump_len = cpsw_get_regs_len(ndev); } static u32 cpsw_get_msglevel(struct net_device *ndev) diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index 691ec936e88d..a274cd49afe9 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -791,7 +791,6 @@ static void tlan_get_drvinfo(struct net_device *dev, sizeof(info->bus_info)); else strlcpy(info->bus_info, "EISA", sizeof(info->bus_info)); - info->eedump_len = TLAN_EEPROM_SIZE; } static int tlan_get_eeprom_len(struct net_device *dev) diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index a83263743665..2b7550c43f78 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -2134,10 +2134,11 @@ static int rhine_rx(struct net_device *dev, int limit) } skb_put(skb, pkt_len); - skb->protocol = eth_type_trans(skb, dev); rhine_rx_vlan_tag(skb, desc, data_size); + skb->protocol = eth_type_trans(skb, dev); + netif_receive_skb(skb); u64_stats_update_begin(&rp->rx_stats.syncp); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index d95f9aae95e7..4684644703cc 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1135,7 +1135,6 @@ static void axienet_ethtools_get_drvinfo(struct net_device *ndev, { strlcpy(ed->driver, DRIVER_NAME, sizeof(ed->driver)); strlcpy(ed->version, DRIVER_VERSION, sizeof(ed->version)); - ed->regdump_len = sizeof(u32) * AXIENET_REGS_N; } /** diff --git a/drivers/net/fjes/fjes_ethtool.c b/drivers/net/fjes/fjes_ethtool.c index 0119dd199276..9c218e140c41 100644 --- a/drivers/net/fjes/fjes_ethtool.c +++ b/drivers/net/fjes/fjes_ethtool.c @@ -105,8 +105,6 @@ static void fjes_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->fw_version, "none", sizeof(drvinfo->fw_version)); snprintf(drvinfo->bus_info, sizeof(drvinfo->bus_info), "platform:%s", plat_dev->name); - drvinfo->regdump_len = 0; - drvinfo->eedump_len = 0; } static int fjes_get_settings(struct net_device *netdev, diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 8f5c02eed47d..cde29f8a37bf 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -870,14 +870,14 @@ static int geneve_newlink(struct net *net, struct net_device *dev, __be16 dst_port = htons(GENEVE_UDP_PORT); __u8 ttl = 0, tos = 0; bool metadata = false; - __be32 rem_addr; - __u32 vni; + __be32 rem_addr = 0; + __u32 vni = 0; - if (!data[IFLA_GENEVE_ID] || !data[IFLA_GENEVE_REMOTE]) - return -EINVAL; + if (data[IFLA_GENEVE_ID]) + vni = nla_get_u32(data[IFLA_GENEVE_ID]); - vni = nla_get_u32(data[IFLA_GENEVE_ID]); - rem_addr = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); + if (data[IFLA_GENEVE_REMOTE]) + rem_addr = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); if (data[IFLA_GENEVE_TTL]) ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 24f8dbcf854f..d50887e3df6d 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -348,7 +348,7 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb) struct rtable *rt; int err, ret = NET_XMIT_DROP; struct flowi4 fl4 = { - .flowi4_oif = dev_get_iflink(dev), + .flowi4_oif = dev->ifindex, .flowi4_tos = RT_TOS(ip4h->tos), .flowi4_flags = FLOWI_FLAG_ANYSRC, .daddr = ip4h->daddr, @@ -386,7 +386,7 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) struct dst_entry *dst; int err, ret = NET_XMIT_DROP; struct flowi6 fl6 = { - .flowi6_iif = skb->dev->ifindex, + .flowi6_iif = dev->ifindex, .daddr = ip6h->daddr, .saddr = ip6h->saddr, .flowi6_flags = FLOWI_FLAG_ANYSRC, diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 9d097ae54fb2..a7fb66580cee 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -187,8 +187,6 @@ config MDIO_OCTEON busses. It is required by the Octeon and ThunderX ethernet device drivers. - If in doubt, say Y. - config MDIO_SUN4I tristate "Allwinner sun4i MDIO interface support" depends on ARCH_SUNXI diff --git a/drivers/net/phy/aquantia.c b/drivers/net/phy/aquantia.c index d6111affbcb6..f1936b7a7af6 100644 --- a/drivers/net/phy/aquantia.c +++ b/drivers/net/phy/aquantia.c @@ -171,20 +171,7 @@ static struct phy_driver aquantia_driver[] = { }, }; -static int __init aquantia_init(void) -{ - return phy_drivers_register(aquantia_driver, - ARRAY_SIZE(aquantia_driver)); -} - -static void __exit aquantia_exit(void) -{ - return phy_drivers_unregister(aquantia_driver, - ARRAY_SIZE(aquantia_driver)); -} - -module_init(aquantia_init); -module_exit(aquantia_exit); +module_phy_driver(aquantia_driver); static struct mdio_device_id __maybe_unused aquantia_tbl[] = { { PHY_ID_AQ1202, 0xfffffff0 }, diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index dd79ea6ba023..ddb377e53633 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -15,6 +15,7 @@ #include <linux/brcmphy.h> #include <linux/export.h> #include <linux/mdio.h> +#include <linux/module.h> #include <linux/phy.h> #define MII_BCM_CHANNEL_WIDTH 0x2000 @@ -206,3 +207,7 @@ int bcm_phy_enable_eee(struct phy_device *phydev) return 0; } EXPORT_SYMBOL_GPL(bcm_phy_enable_eee); + +MODULE_DESCRIPTION("Broadcom PHY Library"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Broadcom Corporation"); diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c index 3bc9f03349f3..95f51d7267b3 100644 --- a/drivers/net/phy/mdio-gpio.c +++ b/drivers/net/phy/mdio-gpio.c @@ -25,7 +25,7 @@ #include <linux/interrupt.h> #include <linux/platform_device.h> #include <linux/gpio.h> -#include <linux/mdio-gpio.h> +#include <linux/platform_data/mdio-gpio.h> #include <linux/of_gpio.h> #include <linux/of_mdio.h> diff --git a/drivers/net/phy/teranetics.c b/drivers/net/phy/teranetics.c index 91e1bec6079f..07463fcca212 100644 --- a/drivers/net/phy/teranetics.c +++ b/drivers/net/phy/teranetics.c @@ -112,20 +112,7 @@ static struct phy_driver teranetics_driver[] = { }, }; -static int __init teranetics_init(void) -{ - return phy_drivers_register(teranetics_driver, - ARRAY_SIZE(teranetics_driver)); -} - -static void __exit teranetics_exit(void) -{ - return phy_drivers_unregister(teranetics_driver, - ARRAY_SIZE(teranetics_driver)); -} - -module_init(teranetics_init); -module_exit(teranetics_exit); +module_phy_driver(teranetics_driver); static struct mdio_device_id __maybe_unused teranetics_tbl[] = { { PHY_ID_TN2020, 0xffffffff }, diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 3837ae344f63..2ed75060da50 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -313,7 +313,6 @@ static void pppoe_flush_dev(struct net_device *dev) if (po->pppoe_dev == dev && sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) { pppox_unbind_sock(sk); - sk->sk_state = PPPOX_ZOMBIE; sk->sk_state_change(sk); po->pppoe_dev = NULL; dev_put(dev); diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index 3a8a36c8ded1..7f83504dfa69 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -166,6 +166,7 @@ config USB_NET_AX8817X * Aten UC210T * ASIX AX88172 * Billionton Systems, USB2AR + * Billionton Systems, GUSB2AM-1G-B * Buffalo LUA-U2-KTX * Corega FEther USB2-TX * D-Link DUB-E100 diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index a186b0a12d50..bd9acff1eb7b 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -588,7 +588,6 @@ void asix_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info) usbnet_get_drvinfo(net, info); strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver)); strlcpy(info->version, DRIVER_VERSION, sizeof(info->version)); - info->eedump_len = AX_EEPROM_LEN; } int asix_set_mac_address(struct net_device *net, void *p) diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 1173a24feda3..5cabefc23494 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -959,6 +959,10 @@ static const struct usb_device_id products [] = { USB_DEVICE (0x08dd, 0x90ff), .driver_info = (unsigned long) &ax8817x_info, }, { + // Billionton Systems, GUSB2AM-1G-B + USB_DEVICE(0x08dd, 0x0114), + .driver_info = (unsigned long) &ax88178_info, +}, { // ATEN UC210T USB_DEVICE (0x0557, 0x2009), .driver_info = (unsigned long) &ax8817x_info, diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 6e9c344c7a20..0b4bdd39106b 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -258,7 +258,6 @@ static void dm9601_get_drvinfo(struct net_device *net, { /* Inherit standard device info */ usbnet_get_drvinfo(net, info); - info->eedump_len = DM_EEPROM_LEN; } static u32 dm9601_get_link(struct net_device *net) diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c index 82d844a8ebd0..4f345bd4e6e2 100644 --- a/drivers/net/usb/mcs7830.c +++ b/drivers/net/usb/mcs7830.c @@ -445,7 +445,6 @@ static int mcs7830_get_regs_len(struct net_device *net) static void mcs7830_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *drvinfo) { usbnet_get_drvinfo(net, drvinfo); - drvinfo->regdump_len = mcs7830_get_regs_len(net); } static void mcs7830_get_regs(struct net_device *net, struct ethtool_regs *regs, void *data) diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 953de13267df..a50df0d8fb9a 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -470,14 +470,10 @@ static int sr_get_eeprom(struct net_device *net, static void sr_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info) { - struct usbnet *dev = netdev_priv(net); - struct sr_data *data = (struct sr_data *)&dev->data; - /* Inherit standard device info */ usbnet_get_drvinfo(net, info); strncpy(info->driver, DRIVER_NAME, sizeof(info->driver)); strncpy(info->version, DRIVER_VERSION, sizeof(info->version)); - info->eedump_len = data->eeprom_len; } static u32 sr_get_link(struct net_device *net) diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index a681569ae0b5..9ba11d737753 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -214,10 +214,6 @@ vmxnet3_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_stats = vmxnet3_get_sset_count(netdev, ETH_SS_STATS); - drvinfo->testinfo_len = 0; - drvinfo->eedump_len = 0; - drvinfo->regdump_len = vmxnet3_get_regs_len(netdev); } diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 191579aeab16..92fa3e1ea65c 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -30,6 +30,7 @@ #include <net/arp.h> #include <net/ip.h> #include <net/ip_fib.h> +#include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/rtnetlink.h> #include <net/route.h> @@ -57,6 +58,7 @@ struct slave_queue { struct net_vrf { struct slave_queue queue; struct rtable *rth; + struct rt6_info *rt6; u32 tb_id; }; @@ -104,12 +106,56 @@ static struct dst_ops vrf_dst_ops = { .default_advmss = vrf_default_advmss, }; +/* neighbor handling is done with actual device; do not want + * to flip skb->dev for those ndisc packets. This really fails + * for multiple next protocols (e.g., NEXTHDR_HOP). But it is + * a start. + */ +#if IS_ENABLED(CONFIG_IPV6) +static bool check_ipv6_frame(const struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->data; + size_t hlen = sizeof(*ipv6h); + bool rc = true; + + if (skb->len < hlen) + goto out; + + if (ipv6h->nexthdr == NEXTHDR_ICMP) { + const struct icmp6hdr *icmph; + + if (skb->len < hlen + sizeof(*icmph)) + goto out; + + icmph = (struct icmp6hdr *)(skb->data + sizeof(*ipv6h)); + switch (icmph->icmp6_type) { + case NDISC_ROUTER_SOLICITATION: + case NDISC_ROUTER_ADVERTISEMENT: + case NDISC_NEIGHBOUR_SOLICITATION: + case NDISC_NEIGHBOUR_ADVERTISEMENT: + case NDISC_REDIRECT: + rc = false; + break; + } + } + +out: + return rc; +} +#else +static bool check_ipv6_frame(const struct sk_buff *skb) +{ + return false; +} +#endif + static bool is_ip_rx_frame(struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_IP): - case htons(ETH_P_IPV6): return true; + case htons(ETH_P_IPV6): + return check_ipv6_frame(skb); } return false; } @@ -169,12 +215,53 @@ static struct rtnl_link_stats64 *vrf_get_stats64(struct net_device *dev, return stats; } +#if IS_ENABLED(CONFIG_IPV6) +static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, + struct net_device *dev) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct net *net = dev_net(skb->dev); + struct flowi6 fl6 = { + /* needed to match OIF rule */ + .flowi6_oif = dev->ifindex, + .flowi6_iif = LOOPBACK_IFINDEX, + .daddr = iph->daddr, + .saddr = iph->saddr, + .flowlabel = ip6_flowinfo(iph), + .flowi6_mark = skb->mark, + .flowi6_proto = iph->nexthdr, + .flowi6_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF, + }; + int ret = NET_XMIT_DROP; + struct dst_entry *dst; + struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst; + + dst = ip6_route_output(net, NULL, &fl6); + if (dst == dst_null) + goto err; + + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + ret = ip6_local_out(net, skb->sk, skb); + if (unlikely(net_xmit_eval(ret))) + dev->stats.tx_errors++; + else + ret = NET_XMIT_SUCCESS; + + return ret; +err: + vrf_tx_error(dev, skb); + return NET_XMIT_DROP; +} +#else static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { vrf_tx_error(dev, skb); return NET_XMIT_DROP; } +#endif static int vrf_send_v4_prep(struct sk_buff *skb, struct flowi4 *fl4, struct net_device *vrf_dev) @@ -269,6 +356,157 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } +#if IS_ENABLED(CONFIG_IPV6) +static struct dst_entry *vrf_ip6_check(struct dst_entry *dst, u32 cookie) +{ + return dst; +} + +static struct dst_ops vrf_dst_ops6 = { + .family = AF_INET6, + .local_out = ip6_local_out, + .check = vrf_ip6_check, + .mtu = vrf_v4_mtu, + .destroy = vrf_dst_destroy, + .default_advmss = vrf_default_advmss, +}; + +static int init_dst_ops6_kmem_cachep(void) +{ + vrf_dst_ops6.kmem_cachep = kmem_cache_create("vrf_ip6_dst_cache", + sizeof(struct rt6_info), + 0, + SLAB_HWCACHE_ALIGN, + NULL); + + if (!vrf_dst_ops6.kmem_cachep) + return -ENOMEM; + + return 0; +} + +static void free_dst_ops6_kmem_cachep(void) +{ + kmem_cache_destroy(vrf_dst_ops6.kmem_cachep); +} + +static int vrf_input6(struct sk_buff *skb) +{ + skb->dev->stats.rx_errors++; + kfree_skb(skb); + return 0; +} + +/* modelled after ip6_finish_output2 */ +static int vrf_finish_output6(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct net_device *dev = dst->dev; + struct neighbour *neigh; + struct in6_addr *nexthop; + int ret; + + skb->protocol = htons(ETH_P_IPV6); + skb->dev = dev; + + rcu_read_lock_bh(); + nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); + if (unlikely(!neigh)) + neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); + if (!IS_ERR(neigh)) { + ret = dst_neigh_output(dst, neigh, skb); + rcu_read_unlock_bh(); + return ret; + } + rcu_read_unlock_bh(); + + IP6_INC_STATS(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); + kfree_skb(skb); + return -EINVAL; +} + +/* modelled after ip6_output */ +static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, + net, sk, skb, NULL, skb_dst(skb)->dev, + vrf_finish_output6, + !(IP6CB(skb)->flags & IP6SKB_REROUTED)); +} + +static void vrf_rt6_destroy(struct net_vrf *vrf) +{ + dst_destroy(&vrf->rt6->dst); + free_percpu(vrf->rt6->rt6i_pcpu); + vrf->rt6 = NULL; +} + +static int vrf_rt6_create(struct net_device *dev) +{ + struct net_vrf *vrf = netdev_priv(dev); + struct dst_entry *dst; + struct rt6_info *rt6; + int cpu; + int rc = -ENOMEM; + + rt6 = dst_alloc(&vrf_dst_ops6, dev, 0, + DST_OBSOLETE_NONE, + (DST_HOST | DST_NOPOLICY | DST_NOXFRM)); + if (!rt6) + goto out; + + dst = &rt6->dst; + + rt6->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_KERNEL); + if (!rt6->rt6i_pcpu) { + dst_destroy(dst); + goto out; + } + for_each_possible_cpu(cpu) { + struct rt6_info **p = per_cpu_ptr(rt6->rt6i_pcpu, cpu); + *p = NULL; + } + + memset(dst + 1, 0, sizeof(*rt6) - sizeof(*dst)); + + INIT_LIST_HEAD(&rt6->rt6i_siblings); + INIT_LIST_HEAD(&rt6->rt6i_uncached); + + rt6->dst.input = vrf_input6; + rt6->dst.output = vrf_output6; + + rt6->rt6i_table = fib6_get_table(dev_net(dev), vrf->tb_id); + + atomic_set(&rt6->dst.__refcnt, 2); + + vrf->rt6 = rt6; + rc = 0; +out: + return rc; +} +#else +static int init_dst_ops6_kmem_cachep(void) +{ + return 0; +} + +static void free_dst_ops6_kmem_cachep(void) +{ +} + +static void vrf_rt6_destroy(struct net_vrf *vrf) +{ +} + +static int vrf_rt6_create(struct net_device *dev) +{ + return 0; +} +#endif + /* modelled after ip_finish_output2 */ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -490,6 +728,7 @@ static void vrf_dev_uninit(struct net_device *dev) struct slave *slave, *next; vrf_rtable_destroy(vrf); + vrf_rt6_destroy(vrf); list_for_each_entry_safe(slave, next, head, list) vrf_del_slave(dev, slave->dev); @@ -513,10 +752,15 @@ static int vrf_dev_init(struct net_device *dev) if (!vrf->rth) goto out_stats; + if (vrf_rt6_create(dev) != 0) + goto out_rth; + dev->flags = IFF_MASTER | IFF_NOARP; return 0; +out_rth: + vrf_rtable_destroy(vrf); out_stats: free_percpu(dev->dstats); dev->dstats = NULL; @@ -586,10 +830,30 @@ static void vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) fl4->flowi4_scope = scope; } +#if IS_ENABLED(CONFIG_IPV6) +static struct dst_entry *vrf_get_rt6_dst(const struct net_device *dev, + const struct flowi6 *fl6) +{ + struct rt6_info *rt = NULL; + + if (!(fl6->flowi6_flags & FLOWI_FLAG_L3MDEV_SRC)) { + struct net_vrf *vrf = netdev_priv(dev); + + rt = vrf->rt6; + atomic_inc(&rt->dst.__refcnt); + } + + return (struct dst_entry *)rt; +} +#endif + static const struct l3mdev_ops vrf_l3mdev_ops = { .l3mdev_fib_table = vrf_fib_table, .l3mdev_get_rtable = vrf_get_rtable, .l3mdev_get_saddr = vrf_get_saddr, +#if IS_ENABLED(CONFIG_IPV6) + .l3mdev_get_rt6_dst = vrf_get_rt6_dst, +#endif }; static void vrf_get_drvinfo(struct net_device *dev, @@ -731,6 +995,10 @@ static int __init vrf_init_module(void) if (!vrf_dst_ops.kmem_cachep) return -ENOMEM; + rc = init_dst_ops6_kmem_cachep(); + if (rc != 0) + goto error2; + register_netdevice_notifier(&vrf_notifier_block); rc = rtnl_link_register(&vrf_link_ops); @@ -741,6 +1009,8 @@ static int __init vrf_init_module(void) error: unregister_netdevice_notifier(&vrf_notifier_block); + free_dst_ops6_kmem_cachep(); +error2: kmem_cache_destroy(vrf_dst_ops.kmem_cachep); return rc; } @@ -750,6 +1020,7 @@ static void __exit vrf_cleanup_module(void) rtnl_link_unregister(&vrf_link_ops); unregister_netdevice_notifier(&vrf_notifier_block); kmem_cache_destroy(vrf_dst_ops.kmem_cachep); + free_dst_ops6_kmem_cachep(); } module_init(vrf_init_module); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index ce704df7681b..cf262ccf5047 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2794,11 +2794,10 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, struct vxlan_config conf; int err; - if (!data[IFLA_VXLAN_ID]) - return -EINVAL; - memset(&conf, 0, sizeof(conf)); - conf.vni = nla_get_u32(data[IFLA_VXLAN_ID]); + + if (data[IFLA_VXLAN_ID]) + conf.vni = nla_get_u32(data[IFLA_VXLAN_ID]); if (data[IFLA_VXLAN_GROUP]) { conf.remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]); diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h index bc421a5c5356..80c174ff6b7b 100644 --- a/drivers/net/wireless/ath/ath10k/hw.h +++ b/drivers/net/wireless/ath/ath10k/hw.h @@ -337,7 +337,7 @@ enum ath10k_hw_rate_cck { #define TARGET_10X_MAX_FRAG_ENTRIES 0 /* 10.2 parameters */ -#define TARGET_10_2_DMA_BURST_SIZE 1 +#define TARGET_10_2_DMA_BURST_SIZE 0 /* Target specific defines for WMI-TLV firmware */ #define TARGET_TLV_NUM_VDEVS 4 @@ -391,7 +391,7 @@ enum ath10k_hw_rate_cck { #define TARGET_10_4_TX_DBG_LOG_SIZE 1024 #define TARGET_10_4_NUM_WDS_ENTRIES 32 -#define TARGET_10_4_DMA_BURST_SIZE 1 +#define TARGET_10_4_DMA_BURST_SIZE 0 #define TARGET_10_4_MAC_AGGR_DELIM 0 #define TARGET_10_4_RX_SKIP_DEFRAG_TIMEOUT_DUP_DETECTION_CHECK 1 #define TARGET_10_4_VOW_CONFIG 0 diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c index 5d532c7b813f..2e2b92ba96b8 100644 --- a/drivers/net/wireless/ath/ath9k/init.c +++ b/drivers/net/wireless/ath/ath9k/init.c @@ -881,6 +881,7 @@ static void ath9k_set_hw_capab(struct ath_softc *sc, struct ieee80211_hw *hw) hw->max_rate_tries = 10; hw->sta_data_size = sizeof(struct ath_node); hw->vif_data_size = sizeof(struct ath_vif); + hw->extra_tx_headroom = 4; hw->wiphy->available_antennas_rx = BIT(ah->caps.max_rxchains) - 1; hw->wiphy->available_antennas_tx = BIT(ah->caps.max_txchains) - 1; diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c index 28490702124a..71d3e9adbf3c 100644 --- a/drivers/net/wireless/b43/main.c +++ b/drivers/net/wireless/b43/main.c @@ -120,6 +120,7 @@ MODULE_PARM_DESC(allhwsupport, "Enable support for all hardware (even it if over #ifdef CONFIG_B43_BCMA static const struct bcma_device_id b43_bcma_tbl[] = { BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_80211, 0x11, BCMA_ANY_CLASS), + BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_80211, 0x15, BCMA_ANY_CLASS), BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_80211, 0x17, BCMA_ANY_CLASS), BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_80211, 0x18, BCMA_ANY_CLASS), BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_80211, 0x1C, BCMA_ANY_CLASS), diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c index 39f3e6f5cbcd..ed0adaf1eec4 100644 --- a/drivers/net/wireless/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/ipw2x00/ipw2200.c @@ -10470,7 +10470,6 @@ static void ipw_ethtool_get_drvinfo(struct net_device *dev, vers, date); strlcpy(info->bus_info, pci_name(p->pci_dev), sizeof(info->bus_info)); - info->eedump_len = IPW_EEPROM_IMAGE_SIZE; } static u32 ipw_ethtool_get_link(struct net_device *dev) diff --git a/drivers/net/wireless/iwlwifi/dvm/lib.c b/drivers/net/wireless/iwlwifi/dvm/lib.c index ab45819c1fbb..e18629a16fb0 100644 --- a/drivers/net/wireless/iwlwifi/dvm/lib.c +++ b/drivers/net/wireless/iwlwifi/dvm/lib.c @@ -1020,7 +1020,7 @@ static void iwlagn_wowlan_program_keys(struct ieee80211_hw *hw, u8 *pn = seq.ccmp.pn; ieee80211_get_key_rx_seq(key, i, &seq); - aes_sc->pn = cpu_to_le64( + aes_sc[i].pn = cpu_to_le64( (u64)pn[5] | ((u64)pn[4] << 8) | ((u64)pn[3] << 16) | diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c index d561181f2cff..1a73c7a1da77 100644 --- a/drivers/net/wireless/iwlwifi/iwl-7000.c +++ b/drivers/net/wireless/iwlwifi/iwl-7000.c @@ -341,6 +341,6 @@ const struct iwl_cfg iwl7265d_n_cfg = { }; MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); -MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL3160_UCODE_API_OK)); +MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); MODULE_FIRMWARE(IWL7265D_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); diff --git a/drivers/net/wireless/iwlwifi/mvm/d3.c b/drivers/net/wireless/iwlwifi/mvm/d3.c index 1d54355ad76a..85ae902df7c0 100644 --- a/drivers/net/wireless/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/iwlwifi/mvm/d3.c @@ -274,18 +274,13 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw, break; case WLAN_CIPHER_SUITE_CCMP: if (sta) { - u8 *pn = seq.ccmp.pn; + u64 pn64; aes_sc = data->rsc_tsc->all_tsc_rsc.aes.unicast_rsc; aes_tx_sc = &data->rsc_tsc->all_tsc_rsc.aes.tsc; - ieee80211_get_key_tx_seq(key, &seq); - aes_tx_sc->pn = cpu_to_le64((u64)pn[5] | - ((u64)pn[4] << 8) | - ((u64)pn[3] << 16) | - ((u64)pn[2] << 24) | - ((u64)pn[1] << 32) | - ((u64)pn[0] << 40)); + pn64 = atomic64_read(&key->tx_pn); + aes_tx_sc->pn = cpu_to_le64(pn64); } else { aes_sc = data->rsc_tsc->all_tsc_rsc.aes.multicast_rsc; } @@ -298,12 +293,12 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw, u8 *pn = seq.ccmp.pn; ieee80211_get_key_rx_seq(key, i, &seq); - aes_sc->pn = cpu_to_le64((u64)pn[5] | - ((u64)pn[4] << 8) | - ((u64)pn[3] << 16) | - ((u64)pn[2] << 24) | - ((u64)pn[1] << 32) | - ((u64)pn[0] << 40)); + aes_sc[i].pn = cpu_to_le64((u64)pn[5] | + ((u64)pn[4] << 8) | + ((u64)pn[3] << 16) | + ((u64)pn[2] << 24) | + ((u64)pn[1] << 32) | + ((u64)pn[0] << 40)); } data->use_rsc_tsc = true; break; @@ -1456,15 +1451,15 @@ static void iwl_mvm_d3_update_gtks(struct ieee80211_hw *hw, switch (key->cipher) { case WLAN_CIPHER_SUITE_CCMP: - iwl_mvm_aes_sc_to_seq(&sc->aes.tsc, &seq); iwl_mvm_set_aes_rx_seq(sc->aes.unicast_rsc, key); + atomic64_set(&key->tx_pn, le64_to_cpu(sc->aes.tsc.pn)); break; case WLAN_CIPHER_SUITE_TKIP: iwl_mvm_tkip_sc_to_seq(&sc->tkip.tsc, &seq); iwl_mvm_set_tkip_rx_seq(sc->tkip.unicast_rsc, key); + ieee80211_set_key_tx_seq(key, &seq); break; } - ieee80211_set_key_tx_seq(key, &seq); /* that's it for this key */ return; diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c index 834641e250fb..d906fa13ba97 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/iwlwifi/mvm/fw.c @@ -699,7 +699,7 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm) * abort after reading the nvm in case RF Kill is on, we will complete * the init seq later when RF kill will switch to off */ - if (iwl_mvm_is_radio_killed(mvm)) { + if (iwl_mvm_is_radio_hw_killed(mvm)) { IWL_DEBUG_RF_KILL(mvm, "jump over all phy activities due to RF kill\n"); iwl_remove_notification(&mvm->notif_wait, &calib_wait); @@ -732,7 +732,7 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm) ret = iwl_wait_notification(&mvm->notif_wait, &calib_wait, MVM_UCODE_CALIB_TIMEOUT); - if (ret && iwl_mvm_is_radio_killed(mvm)) { + if (ret && iwl_mvm_is_radio_hw_killed(mvm)) { IWL_DEBUG_RF_KILL(mvm, "RFKILL while calibrating.\n"); ret = 1; } diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c index 8443e14101cf..a38e07bb137f 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c @@ -2373,6 +2373,7 @@ static void iwl_mvm_stop_ap_ibss(struct ieee80211_hw *hw, iwl_mvm_remove_time_event(mvm, mvmvif, &mvmvif->time_event_data); RCU_INIT_POINTER(mvm->csa_vif, NULL); + mvmvif->csa_countdown = false; } if (rcu_access_pointer(mvm->csa_tx_blocked_vif) == vif) { diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h index 0d3aff1b4bad..16c5a6d7e0c9 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h @@ -870,6 +870,11 @@ static inline bool iwl_mvm_is_radio_killed(struct iwl_mvm *mvm) test_bit(IWL_MVM_STATUS_HW_CTKILL, &mvm->status); } +static inline bool iwl_mvm_is_radio_hw_killed(struct iwl_mvm *mvm) +{ + return test_bit(IWL_MVM_STATUS_HW_RFKILL, &mvm->status); +} + /* Must be called with rcu_read_lock() held and it can only be * released when mvmsta is not needed anymore. */ diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c index f0728b784edb..13c97f665ba8 100644 --- a/drivers/net/wireless/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/iwlwifi/mvm/ops.c @@ -602,6 +602,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, ieee80211_unregister_hw(mvm->hw); iwl_mvm_leds_exit(mvm); out_free: + flush_delayed_work(&mvm->fw_dump_wk); iwl_phy_db_free(mvm->phy_db); kfree(mvm->scan_cmd); if (!cfg->no_power_up_nic_in_init || !mvm->nvm_file_name) diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c index b0825c402c73..644b58bc5226 100644 --- a/drivers/net/wireless/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/iwlwifi/pcie/drv.c @@ -414,6 +414,11 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x095A, 0x5590, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095B, 0x5290, iwl7265_2ac_cfg)}, {IWL_PCI_DEVICE(0x095A, 0x5490, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x5F10, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095B, 0x5212, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095B, 0x520A, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x9000, iwl7265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x095A, 0x9400, iwl7265_2ac_cfg)}, /* 8000 Series */ {IWL_PCI_DEVICE(0x24F3, 0x0010, iwl8260_2ac_cfg)}, diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c index 5932306084fd..bf9afbf46c1b 100644 --- a/drivers/net/wireless/rt2x00/rt2800usb.c +++ b/drivers/net/wireless/rt2x00/rt2800usb.c @@ -1114,6 +1114,7 @@ static struct usb_device_id rt2800usb_device_table[] = { { USB_DEVICE(0x0db0, 0x871c) }, { USB_DEVICE(0x0db0, 0x899a) }, /* Ovislink */ + { USB_DEVICE(0x1b75, 0x3070) }, { USB_DEVICE(0x1b75, 0x3071) }, { USB_DEVICE(0x1b75, 0x3072) }, { USB_DEVICE(0x1b75, 0xa200) }, diff --git a/drivers/net/wireless/rtlwifi/pci.h b/drivers/net/wireless/rtlwifi/pci.h index d4567d12e07e..5da6703942d9 100644 --- a/drivers/net/wireless/rtlwifi/pci.h +++ b/drivers/net/wireless/rtlwifi/pci.h @@ -247,6 +247,8 @@ struct rtl_pci { /* MSI support */ bool msi_support; bool using_msi; + /* interrupt clear before set */ + bool int_clear; }; struct mp_adapter { diff --git a/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c index b7f18e2155eb..6e9418ed90c2 100644 --- a/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c +++ b/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c @@ -2253,11 +2253,28 @@ void rtl8821ae_set_qos(struct ieee80211_hw *hw, int aci) } } +static void rtl8821ae_clear_interrupt(struct ieee80211_hw *hw) +{ + struct rtl_priv *rtlpriv = rtl_priv(hw); + u32 tmp = rtl_read_dword(rtlpriv, REG_HISR); + + rtl_write_dword(rtlpriv, REG_HISR, tmp); + + tmp = rtl_read_dword(rtlpriv, REG_HISRE); + rtl_write_dword(rtlpriv, REG_HISRE, tmp); + + tmp = rtl_read_dword(rtlpriv, REG_HSISR); + rtl_write_dword(rtlpriv, REG_HSISR, tmp); +} + void rtl8821ae_enable_interrupt(struct ieee80211_hw *hw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); + if (!rtlpci->int_clear) + rtl8821ae_clear_interrupt(hw);/*clear it here first*/ + rtl_write_dword(rtlpriv, REG_HIMR, rtlpci->irq_mask[0] & 0xFFFFFFFF); rtl_write_dword(rtlpriv, REG_HIMRE, rtlpci->irq_mask[1] & 0xFFFFFFFF); rtlpci->irq_enabled = true; diff --git a/drivers/net/wireless/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/rtlwifi/rtl8821ae/sw.c index a4988121e1ab..8ee141a55bc5 100644 --- a/drivers/net/wireless/rtlwifi/rtl8821ae/sw.c +++ b/drivers/net/wireless/rtlwifi/rtl8821ae/sw.c @@ -96,6 +96,7 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw) rtl8821ae_bt_reg_init(hw); rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; + rtlpci->int_clear = rtlpriv->cfg->mod_params->int_clear; rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer(); rtlpriv->dm.dm_initialgain_enable = 1; @@ -167,6 +168,7 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw) rtlpriv->psc.swctrl_lps = rtlpriv->cfg->mod_params->swctrl_lps; rtlpriv->psc.fwctrl_lps = rtlpriv->cfg->mod_params->fwctrl_lps; rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; + rtlpci->msi_support = rtlpriv->cfg->mod_params->int_clear; if (rtlpriv->cfg->mod_params->disable_watchdog) pr_info("watchdog disabled\n"); rtlpriv->psc.reg_fwctrl_lps = 3; @@ -308,6 +310,7 @@ static struct rtl_mod_params rtl8821ae_mod_params = { .swctrl_lps = false, .fwctrl_lps = true, .msi_support = true, + .int_clear = true, .debug = DBG_EMERG, .disable_watchdog = 0, }; @@ -437,6 +440,7 @@ module_param_named(fwlps, rtl8821ae_mod_params.fwctrl_lps, bool, 0444); module_param_named(msi, rtl8821ae_mod_params.msi_support, bool, 0444); module_param_named(disable_watchdog, rtl8821ae_mod_params.disable_watchdog, bool, 0444); +module_param_named(int_clear, rtl8821ae_mod_params.int_clear, bool, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); @@ -444,6 +448,7 @@ MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 1)\n"); MODULE_PARM_DESC(debug, "Set debug level (0-5) (default 0)"); MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n"); +MODULE_PARM_DESC(int_clear, "Set to 1 to disable interrupt clear before set (default 0)\n"); static SIMPLE_DEV_PM_OPS(rtlwifi_pm_ops, rtl_pci_suspend, rtl_pci_resume); diff --git a/drivers/net/wireless/rtlwifi/wifi.h b/drivers/net/wireless/rtlwifi/wifi.h index b90ca618b123..4544752a2ba8 100644 --- a/drivers/net/wireless/rtlwifi/wifi.h +++ b/drivers/net/wireless/rtlwifi/wifi.h @@ -2249,6 +2249,9 @@ struct rtl_mod_params { /* default 0: 1 means disable */ bool disable_watchdog; + + /* default 0: 1 means do not disable interrupts */ + bool int_clear; }; struct rtl_hal_usbint_cfg { diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 929a6e7e5ecf..56ebd8267386 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -788,6 +788,12 @@ static void connect(struct backend_info *be) /* Use the number of queues requested by the frontend */ be->vif->queues = vzalloc(requested_num_queues * sizeof(struct xenvif_queue)); + if (!be->vif->queues) { + xenbus_dev_fatal(dev, -ENOMEM, + "allocating queues"); + return; + } + be->vif->num_queues = requested_num_queues; be->vif->stalled_queues = requested_num_queues; diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index d3c6676b3c0c..6fd4e5a5ef4a 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -67,7 +67,7 @@ static ssize_t bin_attr_nvmem_read(struct file *filp, struct kobject *kobj, int rc; /* Stop the user from reading */ - if (pos > nvmem->size) + if (pos >= nvmem->size) return 0; if (pos + count > nvmem->size) @@ -92,7 +92,7 @@ static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj, int rc; /* Stop the user from writing */ - if (pos > nvmem->size) + if (pos >= nvmem->size) return 0; if (pos + count > nvmem->size) @@ -825,7 +825,7 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem, return rc; /* shift bits in-place */ - if (cell->bit_offset || cell->bit_offset) + if (cell->bit_offset || cell->nbits) nvmem_shift_read_buffer_in_place(cell, buf); *len = cell->bytes; @@ -938,7 +938,7 @@ int nvmem_cell_write(struct nvmem_cell *cell, void *buf, size_t len) rc = regmap_raw_write(nvmem->regmap, cell->offset, buf, cell->bytes); /* free the tmp buffer */ - if (cell->bit_offset) + if (cell->bit_offset || cell->nbits) kfree(buf); if (IS_ERR_VALUE(rc)) diff --git a/drivers/nvmem/sunxi_sid.c b/drivers/nvmem/sunxi_sid.c index 14777dd5212d..cfa3b85064dd 100644 --- a/drivers/nvmem/sunxi_sid.c +++ b/drivers/nvmem/sunxi_sid.c @@ -103,7 +103,7 @@ static int sunxi_sid_probe(struct platform_device *pdev) struct nvmem_device *nvmem; struct regmap *regmap; struct sunxi_sid *sid; - int i, size; + int ret, i, size; char *randomness; sid = devm_kzalloc(dev, sizeof(*sid), GFP_KERNEL); @@ -131,6 +131,11 @@ static int sunxi_sid_probe(struct platform_device *pdev) return PTR_ERR(nvmem); randomness = kzalloc(sizeof(u8) * size, GFP_KERNEL); + if (!randomness) { + ret = -EINVAL; + goto err_unreg_nvmem; + } + for (i = 0; i < size; i++) randomness[i] = sunxi_sid_read_byte(sid, i); @@ -140,6 +145,10 @@ static int sunxi_sid_probe(struct platform_device *pdev) platform_set_drvdata(pdev, nvmem); return 0; + +err_unreg_nvmem: + nvmem_unregister(nvmem); + return ret; } static int sunxi_sid_remove(struct platform_device *pdev) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index d4497141d083..4a7da3c3e035 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1243,6 +1243,10 @@ static void pci_msi_domain_update_chip_ops(struct msi_domain_info *info) BUG_ON(!chip); if (!chip->irq_write_msi_msg) chip->irq_write_msi_msg = pci_msi_domain_write_msg; + if (!chip->irq_mask) + chip->irq_mask = pci_msi_mask_irq; + if (!chip->irq_unmask) + chip->irq_unmask = pci_msi_unmask_irq; } /** diff --git a/drivers/phy/phy-berlin-sata.c b/drivers/phy/phy-berlin-sata.c index 0062027afb1e..77a2e054fdea 100644 --- a/drivers/phy/phy-berlin-sata.c +++ b/drivers/phy/phy-berlin-sata.c @@ -276,6 +276,7 @@ static const struct of_device_id phy_berlin_sata_of_match[] = { { .compatible = "marvell,berlin2q-sata-phy" }, { }, }; +MODULE_DEVICE_TABLE(of, phy_berlin_sata_of_match); static struct platform_driver phy_berlin_sata_driver = { .probe = phy_berlin_sata_probe, diff --git a/drivers/phy/phy-qcom-ufs.c b/drivers/phy/phy-qcom-ufs.c index 49a1ed0cef56..107cb57c3513 100644 --- a/drivers/phy/phy-qcom-ufs.c +++ b/drivers/phy/phy-qcom-ufs.c @@ -432,6 +432,7 @@ out_disable_src: out: return ret; } +EXPORT_SYMBOL_GPL(ufs_qcom_phy_enable_ref_clk); static int ufs_qcom_phy_disable_vreg(struct phy *phy, @@ -474,6 +475,7 @@ void ufs_qcom_phy_disable_ref_clk(struct phy *generic_phy) phy->is_ref_clk_enabled = false; } } +EXPORT_SYMBOL_GPL(ufs_qcom_phy_disable_ref_clk); #define UFS_REF_CLK_EN (1 << 5) @@ -517,11 +519,13 @@ void ufs_qcom_phy_enable_dev_ref_clk(struct phy *generic_phy) { ufs_qcom_phy_dev_ref_clk_ctrl(generic_phy, true); } +EXPORT_SYMBOL_GPL(ufs_qcom_phy_enable_dev_ref_clk); void ufs_qcom_phy_disable_dev_ref_clk(struct phy *generic_phy) { ufs_qcom_phy_dev_ref_clk_ctrl(generic_phy, false); } +EXPORT_SYMBOL_GPL(ufs_qcom_phy_disable_dev_ref_clk); /* Turn ON M-PHY RMMI interface clocks */ int ufs_qcom_phy_enable_iface_clk(struct phy *generic_phy) @@ -550,6 +554,7 @@ int ufs_qcom_phy_enable_iface_clk(struct phy *generic_phy) out: return ret; } +EXPORT_SYMBOL_GPL(ufs_qcom_phy_enable_iface_clk); /* Turn OFF M-PHY RMMI interface clocks */ void ufs_qcom_phy_disable_iface_clk(struct phy *generic_phy) @@ -562,6 +567,7 @@ void ufs_qcom_phy_disable_iface_clk(struct phy *generic_phy) phy->is_iface_clk_enabled = false; } } +EXPORT_SYMBOL_GPL(ufs_qcom_phy_disable_iface_clk); int ufs_qcom_phy_start_serdes(struct phy *generic_phy) { @@ -578,6 +584,7 @@ int ufs_qcom_phy_start_serdes(struct phy *generic_phy) return ret; } +EXPORT_SYMBOL_GPL(ufs_qcom_phy_start_serdes); int ufs_qcom_phy_set_tx_lane_enable(struct phy *generic_phy, u32 tx_lanes) { @@ -595,6 +602,7 @@ int ufs_qcom_phy_set_tx_lane_enable(struct phy *generic_phy, u32 tx_lanes) return ret; } +EXPORT_SYMBOL_GPL(ufs_qcom_phy_set_tx_lane_enable); void ufs_qcom_phy_save_controller_version(struct phy *generic_phy, u8 major, u16 minor, u16 step) @@ -605,6 +613,7 @@ void ufs_qcom_phy_save_controller_version(struct phy *generic_phy, ufs_qcom_phy->host_ctrl_rev_minor = minor; ufs_qcom_phy->host_ctrl_rev_step = step; } +EXPORT_SYMBOL_GPL(ufs_qcom_phy_save_controller_version); int ufs_qcom_phy_calibrate_phy(struct phy *generic_phy, bool is_rate_B) { @@ -625,6 +634,7 @@ int ufs_qcom_phy_calibrate_phy(struct phy *generic_phy, bool is_rate_B) return ret; } +EXPORT_SYMBOL_GPL(ufs_qcom_phy_calibrate_phy); int ufs_qcom_phy_remove(struct phy *generic_phy, struct ufs_qcom_phy *ufs_qcom_phy) @@ -662,6 +672,7 @@ int ufs_qcom_phy_is_pcs_ready(struct phy *generic_phy) return ufs_qcom_phy->phy_spec_ops-> is_physical_coding_sublayer_ready(ufs_qcom_phy); } +EXPORT_SYMBOL_GPL(ufs_qcom_phy_is_pcs_ready); int ufs_qcom_phy_power_on(struct phy *generic_phy) { diff --git a/drivers/phy/phy-rockchip-usb.c b/drivers/phy/phy-rockchip-usb.c index 5a5c073e72fe..91d6f342c565 100644 --- a/drivers/phy/phy-rockchip-usb.c +++ b/drivers/phy/phy-rockchip-usb.c @@ -98,6 +98,7 @@ static int rockchip_usb_phy_probe(struct platform_device *pdev) struct device_node *child; struct regmap *grf; unsigned int reg_offset; + int err; grf = syscon_regmap_lookup_by_phandle(dev->of_node, "rockchip,grf"); if (IS_ERR(grf)) { @@ -129,6 +130,11 @@ static int rockchip_usb_phy_probe(struct platform_device *pdev) return PTR_ERR(rk_phy->phy); } phy_set_drvdata(rk_phy->phy, rk_phy); + + /* only power up usb phy when it use, so disable it when init*/ + err = rockchip_usb_phy_power(rk_phy, 1); + if (err) + return err; } phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); diff --git a/drivers/pinctrl/freescale/pinctrl-imx25.c b/drivers/pinctrl/freescale/pinctrl-imx25.c index faf635654312..293ed4381cc0 100644 --- a/drivers/pinctrl/freescale/pinctrl-imx25.c +++ b/drivers/pinctrl/freescale/pinctrl-imx25.c @@ -26,7 +26,8 @@ #include "pinctrl-imx.h" enum imx25_pads { - MX25_PAD_RESERVE0 = 1, + MX25_PAD_RESERVE0 = 0, + MX25_PAD_RESERVE1 = 1, MX25_PAD_A10 = 2, MX25_PAD_A13 = 3, MX25_PAD_A14 = 4, @@ -169,6 +170,7 @@ enum imx25_pads { /* Pad names for the pinmux subsystem */ static const struct pinctrl_pin_desc imx25_pinctrl_pads[] = { IMX_PINCTRL_PIN(MX25_PAD_RESERVE0), + IMX_PINCTRL_PIN(MX25_PAD_RESERVE1), IMX_PINCTRL_PIN(MX25_PAD_A10), IMX_PINCTRL_PIN(MX25_PAD_A13), IMX_PINCTRL_PIN(MX25_PAD_A14), diff --git a/drivers/pinctrl/sunxi/pinctrl-sun5i-a10s.c b/drivers/pinctrl/sunxi/pinctrl-sun5i-a10s.c index 63676617bc59..f9a3f8f446f7 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun5i-a10s.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun5i-a10s.c @@ -653,7 +653,7 @@ static const struct sunxi_desc_pin sun5i_a10s_pins[] = { SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "spi1"), /* CS1 */ - SUNXI_FUNCTION(0x3, "uart3"), /* PWM1 */ + SUNXI_FUNCTION(0x3, "pwm"), /* PWM1 */ SUNXI_FUNCTION(0x5, "uart2"), /* CTS */ SUNXI_FUNCTION_IRQ(0x6, 13)), /* EINT13 */ }; diff --git a/drivers/pinctrl/uniphier/pinctrl-ph1-sld8.c b/drivers/pinctrl/uniphier/pinctrl-ph1-sld8.c index 7e9dae54fcb2..2df8bbecebfc 100644 --- a/drivers/pinctrl/uniphier/pinctrl-ph1-sld8.c +++ b/drivers/pinctrl/uniphier/pinctrl-ph1-sld8.c @@ -22,49 +22,49 @@ #define DRIVER_NAME "ph1-sld8-pinctrl" static const struct pinctrl_pin_desc ph1_sld8_pins[] = { - UNIPHIER_PINCTRL_PIN(0, "PCA00", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(0, "PCA00", 0, 15, UNIPHIER_PIN_DRV_4_8, 15, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(1, "PCA01", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(1, "PCA01", 0, 16, UNIPHIER_PIN_DRV_4_8, 16, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(2, "PCA02", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(2, "PCA02", 0, 17, UNIPHIER_PIN_DRV_4_8, 17, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(3, "PCA03", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(3, "PCA03", 0, 18, UNIPHIER_PIN_DRV_4_8, 18, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(4, "PCA04", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(4, "PCA04", 0, 19, UNIPHIER_PIN_DRV_4_8, 19, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(5, "PCA05", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(5, "PCA05", 0, 20, UNIPHIER_PIN_DRV_4_8, 20, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(6, "PCA06", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(6, "PCA06", 0, 21, UNIPHIER_PIN_DRV_4_8, 21, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(7, "PCA07", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(7, "PCA07", 0, 22, UNIPHIER_PIN_DRV_4_8, 22, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(8, "PCA08", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(8, "PCA08", 0, 23, UNIPHIER_PIN_DRV_4_8, 23, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(9, "PCA09", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(9, "PCA09", 0, 24, UNIPHIER_PIN_DRV_4_8, 24, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(10, "PCA10", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(10, "PCA10", 0, 25, UNIPHIER_PIN_DRV_4_8, 25, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(11, "PCA11", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(11, "PCA11", 0, 26, UNIPHIER_PIN_DRV_4_8, 26, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(12, "PCA12", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(12, "PCA12", 0, 27, UNIPHIER_PIN_DRV_4_8, 27, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(13, "PCA13", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(13, "PCA13", 0, 28, UNIPHIER_PIN_DRV_4_8, 28, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(14, "PCA14", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(14, "PCA14", 0, 29, UNIPHIER_PIN_DRV_4_8, 29, UNIPHIER_PIN_PULL_DOWN), UNIPHIER_PINCTRL_PIN(15, "XNFRE_GB", UNIPHIER_PIN_IECTRL_NONE, @@ -118,199 +118,199 @@ static const struct pinctrl_pin_desc ph1_sld8_pins[] = { UNIPHIER_PINCTRL_PIN(31, "NFD7_GB", UNIPHIER_PIN_IECTRL_NONE, 36, UNIPHIER_PIN_DRV_8_12_16_20, 128, UNIPHIER_PIN_PULL_UP), - UNIPHIER_PINCTRL_PIN(32, "SDCLK", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(32, "SDCLK", 8, 40, UNIPHIER_PIN_DRV_8_12_16_20, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(33, "SDCMD", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(33, "SDCMD", 8, 44, UNIPHIER_PIN_DRV_8_12_16_20, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(34, "SDDAT0", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(34, "SDDAT0", 8, 48, UNIPHIER_PIN_DRV_8_12_16_20, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(35, "SDDAT1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(35, "SDDAT1", 8, 52, UNIPHIER_PIN_DRV_8_12_16_20, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(36, "SDDAT2", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(36, "SDDAT2", 8, 56, UNIPHIER_PIN_DRV_8_12_16_20, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(37, "SDDAT3", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(37, "SDDAT3", 8, 60, UNIPHIER_PIN_DRV_8_12_16_20, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(38, "SDCD", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(38, "SDCD", 8, -1, UNIPHIER_PIN_DRV_FIXED_4, 129, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(39, "SDWP", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(39, "SDWP", 8, -1, UNIPHIER_PIN_DRV_FIXED_4, 130, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(40, "SDVOLC", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(40, "SDVOLC", 9, -1, UNIPHIER_PIN_DRV_FIXED_4, 131, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(41, "USB0VBUS", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(41, "USB0VBUS", 0, 37, UNIPHIER_PIN_DRV_4_8, 37, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(42, "USB0OD", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(42, "USB0OD", 0, 38, UNIPHIER_PIN_DRV_4_8, 38, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(43, "USB1VBUS", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(43, "USB1VBUS", 0, 39, UNIPHIER_PIN_DRV_4_8, 39, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(44, "USB1OD", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(44, "USB1OD", 0, 40, UNIPHIER_PIN_DRV_4_8, 40, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(45, "PCRESET", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(45, "PCRESET", 0, 41, UNIPHIER_PIN_DRV_4_8, 41, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(46, "PCREG", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(46, "PCREG", 0, 42, UNIPHIER_PIN_DRV_4_8, 42, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(47, "PCCE2", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(47, "PCCE2", 0, 43, UNIPHIER_PIN_DRV_4_8, 43, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(48, "PCVS1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(48, "PCVS1", 0, 44, UNIPHIER_PIN_DRV_4_8, 44, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(49, "PCCD2", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(49, "PCCD2", 0, 45, UNIPHIER_PIN_DRV_4_8, 45, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(50, "PCCD1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(50, "PCCD1", 0, 46, UNIPHIER_PIN_DRV_4_8, 46, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(51, "PCREADY", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(51, "PCREADY", 0, 47, UNIPHIER_PIN_DRV_4_8, 47, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(52, "PCDOE", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(52, "PCDOE", 0, 48, UNIPHIER_PIN_DRV_4_8, 48, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(53, "PCCE1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(53, "PCCE1", 0, 49, UNIPHIER_PIN_DRV_4_8, 49, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(54, "PCWE", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(54, "PCWE", 0, 50, UNIPHIER_PIN_DRV_4_8, 50, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(55, "PCOE", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(55, "PCOE", 0, 51, UNIPHIER_PIN_DRV_4_8, 51, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(56, "PCWAIT", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(56, "PCWAIT", 0, 52, UNIPHIER_PIN_DRV_4_8, 52, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(57, "PCIOWR", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(57, "PCIOWR", 0, 53, UNIPHIER_PIN_DRV_4_8, 53, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(58, "PCIORD", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(58, "PCIORD", 0, 54, UNIPHIER_PIN_DRV_4_8, 54, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(59, "HS0DIN0", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(59, "HS0DIN0", 0, 55, UNIPHIER_PIN_DRV_4_8, 55, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(60, "HS0DIN1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(60, "HS0DIN1", 0, 56, UNIPHIER_PIN_DRV_4_8, 56, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(61, "HS0DIN2", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(61, "HS0DIN2", 0, 57, UNIPHIER_PIN_DRV_4_8, 57, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(62, "HS0DIN3", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(62, "HS0DIN3", 0, 58, UNIPHIER_PIN_DRV_4_8, 58, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(63, "HS0DIN4", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(63, "HS0DIN4", 0, 59, UNIPHIER_PIN_DRV_4_8, 59, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(64, "HS0DIN5", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(64, "HS0DIN5", 0, 60, UNIPHIER_PIN_DRV_4_8, 60, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(65, "HS0DIN6", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(65, "HS0DIN6", 0, 61, UNIPHIER_PIN_DRV_4_8, 61, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(66, "HS0DIN7", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(66, "HS0DIN7", 0, 62, UNIPHIER_PIN_DRV_4_8, 62, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(67, "HS0BCLKIN", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(67, "HS0BCLKIN", 0, 63, UNIPHIER_PIN_DRV_4_8, 63, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(68, "HS0VALIN", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(68, "HS0VALIN", 0, 64, UNIPHIER_PIN_DRV_4_8, 64, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(69, "HS0SYNCIN", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(69, "HS0SYNCIN", 0, 65, UNIPHIER_PIN_DRV_4_8, 65, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(70, "HSDOUT0", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(70, "HSDOUT0", 0, 66, UNIPHIER_PIN_DRV_4_8, 66, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(71, "HSDOUT1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(71, "HSDOUT1", 0, 67, UNIPHIER_PIN_DRV_4_8, 67, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(72, "HSDOUT2", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(72, "HSDOUT2", 0, 68, UNIPHIER_PIN_DRV_4_8, 68, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(73, "HSDOUT3", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(73, "HSDOUT3", 0, 69, UNIPHIER_PIN_DRV_4_8, 69, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(74, "HSDOUT4", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(74, "HSDOUT4", 0, 70, UNIPHIER_PIN_DRV_4_8, 70, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(75, "HSDOUT5", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(75, "HSDOUT5", 0, 71, UNIPHIER_PIN_DRV_4_8, 71, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(76, "HSDOUT6", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(76, "HSDOUT6", 0, 72, UNIPHIER_PIN_DRV_4_8, 72, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(77, "HSDOUT7", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(77, "HSDOUT7", 0, 73, UNIPHIER_PIN_DRV_4_8, 73, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(78, "HSBCLKOUT", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(78, "HSBCLKOUT", 0, 74, UNIPHIER_PIN_DRV_4_8, 74, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(79, "HSVALOUT", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(79, "HSVALOUT", 0, 75, UNIPHIER_PIN_DRV_4_8, 75, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(80, "HSSYNCOUT", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(80, "HSSYNCOUT", 0, 76, UNIPHIER_PIN_DRV_4_8, 76, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(81, "HS1DIN0", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(81, "HS1DIN0", 0, 77, UNIPHIER_PIN_DRV_4_8, 77, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(82, "HS1DIN1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(82, "HS1DIN1", 0, 78, UNIPHIER_PIN_DRV_4_8, 78, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(83, "HS1DIN2", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(83, "HS1DIN2", 0, 79, UNIPHIER_PIN_DRV_4_8, 79, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(84, "HS1DIN3", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(84, "HS1DIN3", 0, 80, UNIPHIER_PIN_DRV_4_8, 80, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(85, "HS1DIN4", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(85, "HS1DIN4", 0, 81, UNIPHIER_PIN_DRV_4_8, 81, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(86, "HS1DIN5", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(86, "HS1DIN5", 0, 82, UNIPHIER_PIN_DRV_4_8, 82, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(87, "HS1DIN6", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(87, "HS1DIN6", 0, 83, UNIPHIER_PIN_DRV_4_8, 83, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(88, "HS1DIN7", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(88, "HS1DIN7", 0, 84, UNIPHIER_PIN_DRV_4_8, 84, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(89, "HS1BCLKIN", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(89, "HS1BCLKIN", 0, 85, UNIPHIER_PIN_DRV_4_8, 85, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(90, "HS1VALIN", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(90, "HS1VALIN", 0, 86, UNIPHIER_PIN_DRV_4_8, 86, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(91, "HS1SYNCIN", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(91, "HS1SYNCIN", 0, 87, UNIPHIER_PIN_DRV_4_8, 87, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(92, "AGCI", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(92, "AGCI", 3, -1, UNIPHIER_PIN_DRV_FIXED_4, 132, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(93, "AGCR", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(93, "AGCR", 4, -1, UNIPHIER_PIN_DRV_FIXED_4, 133, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(94, "AGCBS", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(94, "AGCBS", 5, -1, UNIPHIER_PIN_DRV_FIXED_4, 134, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(95, "IECOUT", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(95, "IECOUT", 0, 88, UNIPHIER_PIN_DRV_4_8, 88, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(96, "ASMCK", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(96, "ASMCK", 0, 89, UNIPHIER_PIN_DRV_4_8, 89, UNIPHIER_PIN_PULL_DOWN), UNIPHIER_PINCTRL_PIN(97, "ABCKO", UNIPHIER_PIN_IECTRL_NONE, @@ -325,31 +325,31 @@ static const struct pinctrl_pin_desc ph1_sld8_pins[] = { UNIPHIER_PINCTRL_PIN(100, "ASDOUT1", UNIPHIER_PIN_IECTRL_NONE, 93, UNIPHIER_PIN_DRV_4_8, 93, UNIPHIER_PIN_PULL_UP), - UNIPHIER_PINCTRL_PIN(101, "ARCOUT", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(101, "ARCOUT", 0, 94, UNIPHIER_PIN_DRV_4_8, 94, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(102, "SDA0", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(102, "SDA0", 10, -1, UNIPHIER_PIN_DRV_FIXED_4, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(103, "SCL0", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(103, "SCL0", 10, -1, UNIPHIER_PIN_DRV_FIXED_4, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(104, "SDA1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(104, "SDA1", 11, -1, UNIPHIER_PIN_DRV_FIXED_4, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(105, "SCL1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(105, "SCL1", 11, -1, UNIPHIER_PIN_DRV_FIXED_4, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(106, "DMDSDA0", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(106, "DMDSDA0", 12, -1, UNIPHIER_PIN_DRV_FIXED_4, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(107, "DMDSCL0", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(107, "DMDSCL0", 12, -1, UNIPHIER_PIN_DRV_FIXED_4, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(108, "DMDSDA1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(108, "DMDSDA1", 13, -1, UNIPHIER_PIN_DRV_FIXED_4, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(109, "DMDSCL1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(109, "DMDSCL1", 13, -1, UNIPHIER_PIN_DRV_FIXED_4, -1, UNIPHIER_PIN_PULL_NONE), UNIPHIER_PINCTRL_PIN(110, "SBO0", UNIPHIER_PIN_IECTRL_NONE, @@ -358,76 +358,76 @@ static const struct pinctrl_pin_desc ph1_sld8_pins[] = { UNIPHIER_PINCTRL_PIN(111, "SBI0", UNIPHIER_PIN_IECTRL_NONE, 96, UNIPHIER_PIN_DRV_4_8, 96, UNIPHIER_PIN_PULL_UP), - UNIPHIER_PINCTRL_PIN(112, "SBO1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(112, "SBO1", 0, 97, UNIPHIER_PIN_DRV_4_8, 97, UNIPHIER_PIN_PULL_UP), - UNIPHIER_PINCTRL_PIN(113, "SBI1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(113, "SBI1", 0, 98, UNIPHIER_PIN_DRV_4_8, 98, UNIPHIER_PIN_PULL_UP), - UNIPHIER_PINCTRL_PIN(114, "TXD1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(114, "TXD1", 0, 99, UNIPHIER_PIN_DRV_4_8, 99, UNIPHIER_PIN_PULL_UP), - UNIPHIER_PINCTRL_PIN(115, "RXD1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(115, "RXD1", 0, 100, UNIPHIER_PIN_DRV_4_8, 100, UNIPHIER_PIN_PULL_UP), - UNIPHIER_PINCTRL_PIN(116, "HIN", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(116, "HIN", 1, -1, UNIPHIER_PIN_DRV_FIXED_5, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(117, "VIN", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(117, "VIN", 2, -1, UNIPHIER_PIN_DRV_FIXED_5, -1, UNIPHIER_PIN_PULL_NONE), - UNIPHIER_PINCTRL_PIN(118, "TCON0", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(118, "TCON0", 0, 101, UNIPHIER_PIN_DRV_4_8, 101, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(119, "TCON1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(119, "TCON1", 0, 102, UNIPHIER_PIN_DRV_4_8, 102, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(120, "TCON2", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(120, "TCON2", 0, 103, UNIPHIER_PIN_DRV_4_8, 103, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(121, "TCON3", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(121, "TCON3", 0, 104, UNIPHIER_PIN_DRV_4_8, 104, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(122, "TCON4", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(122, "TCON4", 0, 105, UNIPHIER_PIN_DRV_4_8, 105, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(123, "TCON5", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(123, "TCON5", 0, 106, UNIPHIER_PIN_DRV_4_8, 106, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(124, "TCON6", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(124, "TCON6", 0, 107, UNIPHIER_PIN_DRV_4_8, 107, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(125, "TCON7", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(125, "TCON7", 0, 108, UNIPHIER_PIN_DRV_4_8, 108, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(126, "TCON8", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(126, "TCON8", 0, 109, UNIPHIER_PIN_DRV_4_8, 109, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(127, "PWMA", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(127, "PWMA", 0, 110, UNIPHIER_PIN_DRV_4_8, 110, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(128, "XIRQ0", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(128, "XIRQ0", 0, 111, UNIPHIER_PIN_DRV_4_8, 111, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(129, "XIRQ1", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(129, "XIRQ1", 0, 112, UNIPHIER_PIN_DRV_4_8, 112, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(130, "XIRQ2", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(130, "XIRQ2", 0, 113, UNIPHIER_PIN_DRV_4_8, 113, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(131, "XIRQ3", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(131, "XIRQ3", 0, 114, UNIPHIER_PIN_DRV_4_8, 114, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(132, "XIRQ4", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(132, "XIRQ4", 0, 115, UNIPHIER_PIN_DRV_4_8, 115, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(133, "XIRQ5", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(133, "XIRQ5", 0, 116, UNIPHIER_PIN_DRV_4_8, 116, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(134, "XIRQ6", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(134, "XIRQ6", 0, 117, UNIPHIER_PIN_DRV_4_8, 117, UNIPHIER_PIN_PULL_DOWN), - UNIPHIER_PINCTRL_PIN(135, "XIRQ7", UNIPHIER_PIN_IECTRL_NONE, + UNIPHIER_PINCTRL_PIN(135, "XIRQ7", 0, 118, UNIPHIER_PIN_DRV_4_8, 118, UNIPHIER_PIN_PULL_DOWN), }; diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 01bf3476a791..a9567af7cec0 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -192,9 +192,9 @@ static const struct regulator_desc axp22x_regulators[] = { AXP_DESC(AXP22X, DCDC3, "dcdc3", "vin3", 600, 1860, 20, AXP22X_DCDC3_V_OUT, 0x3f, AXP22X_PWR_OUT_CTRL1, BIT(3)), AXP_DESC(AXP22X, DCDC4, "dcdc4", "vin4", 600, 1540, 20, - AXP22X_DCDC4_V_OUT, 0x3f, AXP22X_PWR_OUT_CTRL1, BIT(3)), + AXP22X_DCDC4_V_OUT, 0x3f, AXP22X_PWR_OUT_CTRL1, BIT(4)), AXP_DESC(AXP22X, DCDC5, "dcdc5", "vin5", 1000, 2550, 50, - AXP22X_DCDC5_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL1, BIT(4)), + AXP22X_DCDC5_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL1, BIT(5)), /* secondary switchable output of DCDC1 */ AXP_DESC_SW(AXP22X, DC1SW, "dc1sw", "dcdc1", 1600, 3400, 100, AXP22X_DCDC1_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(7)), diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 7849187d91ae..8a34f6acc801 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1403,6 +1403,10 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) return 0; } + /* Did the lookup explicitly defer for us? */ + if (ret == -EPROBE_DEFER) + return ret; + if (have_full_constraints()) { r = dummy_regulator_rdev; } else { diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index add419d6ff34..a56a7b243e91 100644 --- a/drivers/scsi/3w-9xxx.c +++ b/drivers/scsi/3w-9xxx.c @@ -212,6 +212,17 @@ static const struct file_operations twa_fops = { .llseek = noop_llseek, }; +/* + * The controllers use an inline buffer instead of a mapped SGL for small, + * single entry buffers. Note that we treat a zero-length transfer like + * a mapped SGL. + */ +static bool twa_command_mapped(struct scsi_cmnd *cmd) +{ + return scsi_sg_count(cmd) != 1 || + scsi_bufflen(cmd) >= TW_MIN_SGL_LENGTH; +} + /* This function will complete an aen request from the isr */ static int twa_aen_complete(TW_Device_Extension *tw_dev, int request_id) { @@ -1339,7 +1350,8 @@ static irqreturn_t twa_interrupt(int irq, void *dev_instance) } /* Now complete the io */ - scsi_dma_unmap(cmd); + if (twa_command_mapped(cmd)) + scsi_dma_unmap(cmd); cmd->scsi_done(cmd); tw_dev->state[request_id] = TW_S_COMPLETED; twa_free_request_id(tw_dev, request_id); @@ -1582,7 +1594,8 @@ static int twa_reset_device_extension(TW_Device_Extension *tw_dev) struct scsi_cmnd *cmd = tw_dev->srb[i]; cmd->result = (DID_RESET << 16); - scsi_dma_unmap(cmd); + if (twa_command_mapped(cmd)) + scsi_dma_unmap(cmd); cmd->scsi_done(cmd); } } @@ -1765,12 +1778,14 @@ static int twa_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_ retval = twa_scsiop_execute_scsi(tw_dev, request_id, NULL, 0, NULL); switch (retval) { case SCSI_MLQUEUE_HOST_BUSY: - scsi_dma_unmap(SCpnt); + if (twa_command_mapped(SCpnt)) + scsi_dma_unmap(SCpnt); twa_free_request_id(tw_dev, request_id); break; case 1: SCpnt->result = (DID_ERROR << 16); - scsi_dma_unmap(SCpnt); + if (twa_command_mapped(SCpnt)) + scsi_dma_unmap(SCpnt); done(SCpnt); tw_dev->state[request_id] = TW_S_COMPLETED; twa_free_request_id(tw_dev, request_id); @@ -1831,8 +1846,7 @@ static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, /* Map sglist from scsi layer to cmd packet */ if (scsi_sg_count(srb)) { - if ((scsi_sg_count(srb) == 1) && - (scsi_bufflen(srb) < TW_MIN_SGL_LENGTH)) { + if (!twa_command_mapped(srb)) { if (srb->sc_data_direction == DMA_TO_DEVICE || srb->sc_data_direction == DMA_BIDIRECTIONAL) scsi_sg_copy_to_buffer(srb, @@ -1905,7 +1919,7 @@ static void twa_scsiop_execute_scsi_complete(TW_Device_Extension *tw_dev, int re { struct scsi_cmnd *cmd = tw_dev->srb[request_id]; - if (scsi_bufflen(cmd) < TW_MIN_SGL_LENGTH && + if (!twa_command_mapped(cmd) && (cmd->sc_data_direction == DMA_FROM_DEVICE || cmd->sc_data_direction == DMA_BIDIRECTIONAL)) { if (scsi_sg_count(cmd) == 1) { diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c index de6feb8964c9..804806e1cbb4 100644 --- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c +++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c @@ -160,7 +160,7 @@ static struct scsi_transport_template *cxgb4i_stt; #define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) #define RCV_BUFSIZ_MASK 0x3FFU -#define MAX_IMM_TX_PKT_LEN 128 +#define MAX_IMM_TX_PKT_LEN 256 static int push_tx_frames(struct cxgbi_sock *, int); diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 33c74d3436c9..6bffd91b973a 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -976,13 +976,13 @@ static void iscsi_tmf_rsp(struct iscsi_conn *conn, struct iscsi_hdr *hdr) wake_up(&conn->ehwait); } -static void iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) +static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) { struct iscsi_nopout hdr; struct iscsi_task *task; if (!rhdr && conn->ping_task) - return; + return -EINVAL; memset(&hdr, 0, sizeof(struct iscsi_nopout)); hdr.opcode = ISCSI_OP_NOOP_OUT | ISCSI_OP_IMMEDIATE; @@ -996,13 +996,16 @@ static void iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) hdr.ttt = RESERVED_ITT; task = __iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)&hdr, NULL, 0); - if (!task) + if (!task) { iscsi_conn_printk(KERN_ERR, conn, "Could not send nopout\n"); - else if (!rhdr) { + return -EIO; + } else if (!rhdr) { /* only track our nops */ conn->ping_task = task; conn->last_ping = jiffies; } + + return 0; } static int iscsi_nop_out_rsp(struct iscsi_task *task, @@ -2092,8 +2095,10 @@ static void iscsi_check_transport_timeouts(unsigned long data) if (time_before_eq(last_recv + recv_timeout, jiffies)) { /* send a ping to try to provoke some traffic */ ISCSI_DBG_CONN(conn, "Sending nopout as ping\n"); - iscsi_send_nopout(conn, NULL); - next_timeout = conn->last_ping + (conn->ping_timeout * HZ); + if (iscsi_send_nopout(conn, NULL)) + next_timeout = jiffies + (1 * HZ); + else + next_timeout = conn->last_ping + (conn->ping_timeout * HZ); } else next_timeout = last_recv + recv_timeout; diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c index edb044a7b56d..0a2168e69bbc 100644 --- a/drivers/scsi/scsi_dh.c +++ b/drivers/scsi/scsi_dh.c @@ -111,7 +111,7 @@ static struct scsi_device_handler *scsi_dh_lookup(const char *name) dh = __scsi_dh_lookup(name); if (!dh) { - request_module(name); + request_module("scsi_dh_%s", name); dh = __scsi_dh_lookup(name); } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index cbfc5990052b..126a48c6431e 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1957,7 +1957,7 @@ static int scsi_mq_prep_fn(struct request *req) static void scsi_mq_done(struct scsi_cmnd *cmd) { trace_scsi_dispatch_cmd_done(cmd); - blk_mq_complete_request(cmd->request); + blk_mq_complete_request(cmd->request, cmd->request->errors); } static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c index 3cf9faa6cc3f..a85d863d4a44 100644 --- a/drivers/spi/spi-davinci.c +++ b/drivers/spi/spi-davinci.c @@ -992,11 +992,12 @@ static int davinci_spi_probe(struct platform_device *pdev) goto free_master; } - dspi->irq = platform_get_irq(pdev, 0); - if (dspi->irq <= 0) { + ret = platform_get_irq(pdev, 0); + if (ret == 0) ret = -EINVAL; + if (ret < 0) goto free_master; - } + dspi->irq = ret; ret = devm_request_threaded_irq(&pdev->dev, dspi->irq, davinci_spi_irq, dummy_thread_fn, 0, dev_name(&pdev->dev), dspi); diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c index 769b61193d87..a9bc6e23fc25 100644 --- a/drivers/staging/lustre/lustre/llite/dir.c +++ b/drivers/staging/lustre/lustre/llite/dir.c @@ -224,7 +224,7 @@ static int ll_dir_filler(void *_hash, struct page *page0) prefetchw(&page->flags); ret = add_to_page_cache_lru(page, inode->i_mapping, offset, - GFP_KERNEL); + GFP_NOFS); if (ret == 0) { unlock_page(page); } else { diff --git a/drivers/staging/speakup/fakekey.c b/drivers/staging/speakup/fakekey.c index 4299cf45f947..5e1f16c36b49 100644 --- a/drivers/staging/speakup/fakekey.c +++ b/drivers/staging/speakup/fakekey.c @@ -81,6 +81,7 @@ void speakup_fake_down_arrow(void) __this_cpu_write(reporting_keystroke, true); input_report_key(virt_keyboard, KEY_DOWN, PRESSED); input_report_key(virt_keyboard, KEY_DOWN, RELEASED); + input_sync(virt_keyboard); __this_cpu_write(reporting_keystroke, false); /* reenable preemption */ diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 20932cc9c8f7..b09023b07169 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -343,8 +343,7 @@ static void n_tty_packet_mode_flush(struct tty_struct *tty) spin_lock_irqsave(&tty->ctrl_lock, flags); tty->ctrl_status |= TIOCPKT_FLUSHREAD; spin_unlock_irqrestore(&tty->ctrl_lock, flags); - if (waitqueue_active(&tty->link->read_wait)) - wake_up_interruptible(&tty->link->read_wait); + wake_up_interruptible(&tty->link->read_wait); } } @@ -1382,8 +1381,7 @@ handle_newline: put_tty_queue(c, ldata); smp_store_release(&ldata->canon_head, ldata->read_head); kill_fasync(&tty->fasync, SIGIO, POLL_IN); - if (waitqueue_active(&tty->read_wait)) - wake_up_interruptible_poll(&tty->read_wait, POLLIN); + wake_up_interruptible_poll(&tty->read_wait, POLLIN); return 0; } } @@ -1667,8 +1665,7 @@ static void __receive_buf(struct tty_struct *tty, const unsigned char *cp, if ((read_cnt(ldata) >= ldata->minimum_to_wake) || L_EXTPROC(tty)) { kill_fasync(&tty->fasync, SIGIO, POLL_IN); - if (waitqueue_active(&tty->read_wait)) - wake_up_interruptible_poll(&tty->read_wait, POLLIN); + wake_up_interruptible_poll(&tty->read_wait, POLLIN); } } @@ -1887,10 +1884,8 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old) } /* The termios change make the tty ready for I/O */ - if (waitqueue_active(&tty->write_wait)) - wake_up_interruptible(&tty->write_wait); - if (waitqueue_active(&tty->read_wait)) - wake_up_interruptible(&tty->read_wait); + wake_up_interruptible(&tty->write_wait); + wake_up_interruptible(&tty->read_wait); } /** diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index b1e0ba3e525b..0bbf34035d6a 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -261,6 +261,14 @@ configured less than Maximum supported fifo bytes */ UART_FCR7_64BYTE, .flags = UART_CAP_FIFO, }, + [PORT_RT2880] = { + .name = "Palmchip BK-3103", + .fifo_size = 16, + .tx_loadsz = 16, + .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, + .rxtrig_bytes = {1, 4, 8, 14}, + .flags = UART_CAP_FIFO, + }, }; /* Uart divisor latch read */ diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index 5ca5cf3e9359..538ea03bc101 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -2786,7 +2786,7 @@ static int atmel_serial_probe(struct platform_device *pdev) ret = atmel_init_gpios(port, &pdev->dev); if (ret < 0) { dev_err(&pdev->dev, "Failed to initialize GPIOs."); - goto err; + goto err_clear_bit; } ret = atmel_init_port(port, pdev); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index fe3d41cc8416..d0388a071ba1 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -1631,12 +1631,12 @@ imx_console_write(struct console *co, const char *s, unsigned int count) int locked = 1; int retval; - retval = clk_prepare_enable(sport->clk_per); + retval = clk_enable(sport->clk_per); if (retval) return; - retval = clk_prepare_enable(sport->clk_ipg); + retval = clk_enable(sport->clk_ipg); if (retval) { - clk_disable_unprepare(sport->clk_per); + clk_disable(sport->clk_per); return; } @@ -1675,8 +1675,8 @@ imx_console_write(struct console *co, const char *s, unsigned int count) if (locked) spin_unlock_irqrestore(&sport->port.lock, flags); - clk_disable_unprepare(sport->clk_ipg); - clk_disable_unprepare(sport->clk_per); + clk_disable(sport->clk_ipg); + clk_disable(sport->clk_per); } /* @@ -1777,7 +1777,15 @@ imx_console_setup(struct console *co, char *options) retval = uart_set_options(&sport->port, co, baud, parity, bits, flow); - clk_disable_unprepare(sport->clk_ipg); + clk_disable(sport->clk_ipg); + if (retval) { + clk_unprepare(sport->clk_ipg); + goto error_console; + } + + retval = clk_prepare(sport->clk_per); + if (retval) + clk_disable_unprepare(sport->clk_ipg); error_console: return retval; diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 5a3fa8913880..a660ab181cca 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -242,7 +242,10 @@ void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld) atomic_inc(&buf->priority); mutex_lock(&buf->lock); - while ((next = buf->head->next) != NULL) { + /* paired w/ release in __tty_buffer_request_room; ensures there are + * no pending memory accesses to the freed buffer + */ + while ((next = smp_load_acquire(&buf->head->next)) != NULL) { tty_buffer_free(port, buf->head); buf->head = next; } @@ -290,7 +293,10 @@ static int __tty_buffer_request_room(struct tty_port *port, size_t size, if (n != NULL) { n->flags = flags; buf->tail = n; - b->commit = b->used; + /* paired w/ acquire in flush_to_ldisc(); ensures + * flush_to_ldisc() sees buffer data. + */ + smp_store_release(&b->commit, b->used); /* paired w/ acquire in flush_to_ldisc(); ensures the * latest commit value can be read before the head is * advanced to the next buffer @@ -393,7 +399,10 @@ void tty_schedule_flip(struct tty_port *port) { struct tty_bufhead *buf = &port->buf; - buf->tail->commit = buf->tail->used; + /* paired w/ acquire in flush_to_ldisc(); ensures + * flush_to_ldisc() sees buffer data. + */ + smp_store_release(&buf->tail->commit, buf->tail->used); schedule_work(&buf->work); } EXPORT_SYMBOL(tty_schedule_flip); @@ -467,7 +476,7 @@ static void flush_to_ldisc(struct work_struct *work) struct tty_struct *tty; struct tty_ldisc *disc; - tty = port->itty; + tty = READ_ONCE(port->itty); if (tty == NULL) return; @@ -491,7 +500,10 @@ static void flush_to_ldisc(struct work_struct *work) * is advancing to the next buffer */ next = smp_load_acquire(&head->next); - count = head->commit - head->read; + /* paired w/ release in __tty_buffer_request_room() or in + * tty_buffer_flush(); ensures we see the committed buffer data + */ + count = smp_load_acquire(&head->commit) - head->read; if (!count) { if (next == NULL) { check_other_closed(tty); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 02785d844354..2eefaa6e3e3a 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2128,8 +2128,24 @@ retry_open: if (!noctty && current->signal->leader && !current->signal->tty && - tty->session == NULL) - __proc_set_tty(tty); + tty->session == NULL) { + /* + * Don't let a process that only has write access to the tty + * obtain the privileges associated with having a tty as + * controlling terminal (being able to reopen it with full + * access through /dev/tty, being able to perform pushback). + * Many distributions set the group of all ttys to "tty" and + * grant write-only access to all terminals for setgid tty + * binaries, which should not imply full privileges on all ttys. + * + * This could theoretically break old code that performs open() + * on a write-only file descriptor. In that case, it might be + * necessary to also permit this if + * inode_permission(inode, MAY_READ) == 0. + */ + if (filp->f_mode & FMODE_READ) + __proc_set_tty(tty); + } spin_unlock_irq(¤t->sighand->siglock); read_unlock(&tasklist_lock); tty_unlock(tty); @@ -2418,7 +2434,7 @@ static int fionbio(struct file *file, int __user *p) * Takes ->siglock() when updating signal->tty */ -static int tiocsctty(struct tty_struct *tty, int arg) +static int tiocsctty(struct tty_struct *tty, struct file *file, int arg) { int ret = 0; @@ -2452,6 +2468,13 @@ static int tiocsctty(struct tty_struct *tty, int arg) goto unlock; } } + + /* See the comment in tty_open(). */ + if ((file->f_mode & FMODE_READ) == 0 && !capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto unlock; + } + proc_set_tty(tty); unlock: read_unlock(&tasklist_lock); @@ -2844,7 +2867,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg) no_tty(); return 0; case TIOCSCTTY: - return tiocsctty(tty, arg); + return tiocsctty(tty, file, arg); case TIOCGPGRP: return tiocgpgrp(tty, real_tty, p); case TIOCSPGRP: @@ -3151,13 +3174,18 @@ struct class *tty_class; static int tty_cdev_add(struct tty_driver *driver, dev_t dev, unsigned int index, unsigned int count) { + int err; + /* init here, since reused cdevs cause crashes */ driver->cdevs[index] = cdev_alloc(); if (!driver->cdevs[index]) return -ENOMEM; - cdev_init(driver->cdevs[index], &tty_fops); + driver->cdevs[index]->ops = &tty_fops; driver->cdevs[index]->owner = driver->owner; - return cdev_add(driver->cdevs[index], dev, count); + err = cdev_add(driver->cdevs[index], dev, count); + if (err) + kobject_put(&driver->cdevs[index]->kobj); + return err; } /** diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index d85abfed84cc..f5a381945db2 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -54,6 +54,13 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT }, { USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT }, + /* Logitech ConferenceCam CC3000e */ + { USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT }, + { USB_DEVICE(0x046d, 0x0848), .driver_info = USB_QUIRK_DELAY_INIT }, + + /* Logitech PTZ Pro Camera */ + { USB_DEVICE(0x046d, 0x0853), .driver_info = USB_QUIRK_DELAY_INIT }, + /* Logitech Quickcam Fusion */ { USB_DEVICE(0x046d, 0x08c1), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -78,6 +85,12 @@ static const struct usb_device_id usb_quirk_list[] = { /* Philips PSC805 audio device */ { USB_DEVICE(0x0471, 0x0155), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Plantronic Audio 655 DSP */ + { USB_DEVICE(0x047f, 0xc008), .driver_info = USB_QUIRK_RESET_RESUME }, + + /* Plantronic Audio 648 USB */ + { USB_DEVICE(0x047f, 0xc013), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Artisman Watchdog Dongle */ { USB_DEVICE(0x04b4, 0x0526), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, diff --git a/drivers/usb/gadget/udc/bdc/bdc_ep.c b/drivers/usb/gadget/udc/bdc/bdc_ep.c index d1b81539d632..d6199507f861 100644 --- a/drivers/usb/gadget/udc/bdc/bdc_ep.c +++ b/drivers/usb/gadget/udc/bdc/bdc_ep.c @@ -159,8 +159,10 @@ static int ep_bd_list_alloc(struct bdc_ep *ep) bd_table->start_bd = dma_pool_alloc(bdc->bd_table_pool, GFP_ATOMIC, &dma); - if (!bd_table->start_bd) + if (!bd_table->start_bd) { + kfree(bd_table); goto fail; + } bd_table->dma = dma; diff --git a/drivers/usb/misc/chaoskey.c b/drivers/usb/misc/chaoskey.c index 3ad5d19e4d04..23c794813e6a 100644 --- a/drivers/usb/misc/chaoskey.c +++ b/drivers/usb/misc/chaoskey.c @@ -472,7 +472,7 @@ static int chaoskey_rng_read(struct hwrng *rng, void *data, if (this_time > max) this_time = max; - memcpy(data, dev->buf, this_time); + memcpy(data, dev->buf + dev->used, this_time); dev->used += this_time; diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c index 7b98e1d9194c..d82fa36c3465 100644 --- a/drivers/usb/renesas_usbhs/common.c +++ b/drivers/usb/renesas_usbhs/common.c @@ -476,6 +476,11 @@ static const struct of_device_id usbhs_of_match[] = { .compatible = "renesas,usbhs-r8a7794", .data = (void *)USBHS_TYPE_RCAR_GEN2, }, + { + /* Gen3 is compatible with Gen2 */ + .compatible = "renesas,usbhs-r8a7795", + .data = (void *)USBHS_TYPE_RCAR_GEN2, + }, { }, }; MODULE_DEVICE_TABLE(of, usbhs_of_match); @@ -493,7 +498,7 @@ static struct renesas_usbhs_platform_info *usbhs_parse_dt(struct device *dev) return NULL; dparam = &info->driver_param; - dparam->type = of_id ? (u32)of_id->data : 0; + dparam->type = of_id ? (uintptr_t)of_id->data : 0; if (!of_property_read_u32(dev->of_node, "renesas,buswait", &tmp)) dparam->buswait_bwait = tmp; gpio = of_get_named_gpio_flags(dev->of_node, "renesas,enable-gpio", 0, diff --git a/drivers/video/fbdev/broadsheetfb.c b/drivers/video/fbdev/broadsheetfb.c index 0e5fde1d3ffb..9f9a7bef1ff6 100644 --- a/drivers/video/fbdev/broadsheetfb.c +++ b/drivers/video/fbdev/broadsheetfb.c @@ -752,7 +752,7 @@ static ssize_t broadsheet_loadstore_waveform(struct device *dev, if ((fw_entry->size < 8*1024) || (fw_entry->size > 64*1024)) { dev_err(dev, "Invalid waveform\n"); err = -EINVAL; - goto err_failed; + goto err_fw; } mutex_lock(&(par->io_lock)); @@ -762,13 +762,15 @@ static ssize_t broadsheet_loadstore_waveform(struct device *dev, mutex_unlock(&(par->io_lock)); if (err < 0) { dev_err(dev, "Failed to store broadsheet waveform\n"); - goto err_failed; + goto err_fw; } dev_info(dev, "Stored broadsheet waveform, size %zd\n", fw_entry->size); - return len; + err = len; +err_fw: + release_firmware(fw_entry); err_failed: return err; } diff --git a/drivers/video/fbdev/fsl-diu-fb.c b/drivers/video/fbdev/fsl-diu-fb.c index 7fa2e6f9e322..b335c1ae8625 100644 --- a/drivers/video/fbdev/fsl-diu-fb.c +++ b/drivers/video/fbdev/fsl-diu-fb.c @@ -1628,9 +1628,16 @@ static int fsl_diu_suspend(struct platform_device *ofdev, pm_message_t state) static int fsl_diu_resume(struct platform_device *ofdev) { struct fsl_diu_data *data; + unsigned int i; data = dev_get_drvdata(&ofdev->dev); - enable_lcdc(data->fsl_diu_info); + + fsl_diu_enable_interrupts(data); + update_lcdc(data->fsl_diu_info); + for (i = 0; i < NUM_AOIS; i++) { + if (data->mfb[i].count) + fsl_diu_enable_panel(&data->fsl_diu_info[i]); + } return 0; } diff --git a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c index 9b8bebdf8f86..f9ec5c0484fa 100644 --- a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c +++ b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c @@ -831,6 +831,7 @@ static struct of_device_id of_platform_mb862xx_tbl[] = { { .compatible = "fujitsu,coral", }, { /* end */ } }; +MODULE_DEVICE_TABLE(of, of_platform_mb862xx_tbl); static struct platform_driver of_platform_mb862xxfb_driver = { .driver = { diff --git a/drivers/video/fbdev/omap2/displays-new/connector-dvi.c b/drivers/video/fbdev/omap2/displays-new/connector-dvi.c index a8ce920fa797..d811e6dcaef7 100644 --- a/drivers/video/fbdev/omap2/displays-new/connector-dvi.c +++ b/drivers/video/fbdev/omap2/displays-new/connector-dvi.c @@ -294,7 +294,7 @@ static int dvic_probe_of(struct platform_device *pdev) adapter_node = of_parse_phandle(node, "ddc-i2c-bus", 0); if (adapter_node) { - adapter = of_find_i2c_adapter_by_node(adapter_node); + adapter = of_get_i2c_adapter_by_node(adapter_node); if (adapter == NULL) { dev_err(&pdev->dev, "failed to parse ddc-i2c-bus\n"); omap_dss_put_device(ddata->in); diff --git a/drivers/video/fbdev/omap2/displays-new/panel-sony-acx565akm.c b/drivers/video/fbdev/omap2/displays-new/panel-sony-acx565akm.c index 90cbc4c3406c..c581231c74a5 100644 --- a/drivers/video/fbdev/omap2/displays-new/panel-sony-acx565akm.c +++ b/drivers/video/fbdev/omap2/displays-new/panel-sony-acx565akm.c @@ -898,6 +898,7 @@ static const struct of_device_id acx565akm_of_match[] = { { .compatible = "omapdss,sony,acx565akm", }, {}, }; +MODULE_DEVICE_TABLE(of, acx565akm_of_match); static struct spi_driver acx565akm_driver = { .driver = { diff --git a/drivers/video/fbdev/tridentfb.c b/drivers/video/fbdev/tridentfb.c index 7ed9a227f5ea..01b43e9ce941 100644 --- a/drivers/video/fbdev/tridentfb.c +++ b/drivers/video/fbdev/tridentfb.c @@ -226,7 +226,7 @@ static void blade_image_blit(struct tridentfb_par *par, const char *data, writemmr(par, DST1, point(x, y)); writemmr(par, DST2, point(x + w - 1, y + h - 1)); - memcpy(par->io_virt + 0x10000, data, 4 * size); + iowrite32_rep(par->io_virt + 0x10000, data, size); } static void blade_copy_rect(struct tridentfb_par *par, @@ -673,8 +673,14 @@ static int get_nativex(struct tridentfb_par *par) static inline void set_lwidth(struct tridentfb_par *par, int width) { write3X4(par, VGA_CRTC_OFFSET, width & 0xFF); - write3X4(par, AddColReg, - (read3X4(par, AddColReg) & 0xCF) | ((width & 0x300) >> 4)); + /* chips older than TGUI9660 have only 1 width bit in AddColReg */ + /* touching the other one breaks I2C/DDC */ + if (par->chip_id == TGUI9440 || par->chip_id == CYBER9320) + write3X4(par, AddColReg, + (read3X4(par, AddColReg) & 0xEF) | ((width & 0x100) >> 4)); + else + write3X4(par, AddColReg, + (read3X4(par, AddColReg) & 0xCF) | ((width & 0x300) >> 4)); } /* For resolutions smaller than FP resolution stretch */ diff --git a/drivers/video/of_display_timing.c b/drivers/video/of_display_timing.c index 32d8275e4c88..8a1076beecd3 100644 --- a/drivers/video/of_display_timing.c +++ b/drivers/video/of_display_timing.c @@ -210,6 +210,7 @@ struct display_timings *of_get_display_timings(struct device_node *np) */ pr_err("%s: error in timing %d\n", of_node_full_name(np), disp->num_timings + 1); + kfree(dt); goto timingfail; } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index ecbc63d3143e..9a2ec79e8cfb 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1828,7 +1828,6 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, int found = 0; struct extent_buffer *eb; struct btrfs_inode_extref *extref; - struct extent_buffer *leaf; u32 item_size; u32 cur_offset; unsigned long ptr; @@ -1856,9 +1855,8 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); btrfs_release_path(path); - leaf = path->nodes[0]; - item_size = btrfs_item_size_nr(leaf, slot); - ptr = btrfs_item_ptr_offset(leaf, slot); + item_size = btrfs_item_size_nr(eb, slot); + ptr = btrfs_item_ptr_offset(eb, slot); cur_offset = 0; while (cur_offset < item_size) { @@ -1872,7 +1870,7 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, if (ret) break; - cur_offset += btrfs_inode_extref_name_len(leaf, extref); + cur_offset += btrfs_inode_extref_name_len(eb, extref); cur_offset += sizeof(*extref); } btrfs_tree_read_unlock_blocking(eb); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 295795aebe0b..1e60d00d4ea7 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2847,6 +2847,8 @@ int open_ctree(struct super_block *sb, !extent_buffer_uptodate(chunk_root->node)) { printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n", sb->s_id); + if (!IS_ERR(chunk_root->node)) + free_extent_buffer(chunk_root->node); chunk_root->node = NULL; goto fail_tree_roots; } @@ -2885,6 +2887,8 @@ retry_root_backup: !extent_buffer_uptodate(tree_root->node)) { printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n", sb->s_id); + if (!IS_ERR(tree_root->node)) + free_extent_buffer(tree_root->node); tree_root->node = NULL; goto recovery_tree_root; } diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 8d052209f473..2513a7f53334 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -112,11 +112,11 @@ static struct dentry *btrfs_fh_to_parent(struct super_block *sb, struct fid *fh, u32 generation; if (fh_type == FILEID_BTRFS_WITH_PARENT) { - if (fh_len != BTRFS_FID_SIZE_CONNECTABLE) + if (fh_len < BTRFS_FID_SIZE_CONNECTABLE) return NULL; root_objectid = fid->root_objectid; } else if (fh_type == FILEID_BTRFS_WITH_PARENT_ROOT) { - if (fh_len != BTRFS_FID_SIZE_CONNECTABLE_ROOT) + if (fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) return NULL; root_objectid = fid->parent_root_objectid; } else @@ -136,11 +136,11 @@ static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh, u32 generation; if ((fh_type != FILEID_BTRFS_WITH_PARENT || - fh_len != BTRFS_FID_SIZE_CONNECTABLE) && + fh_len < BTRFS_FID_SIZE_CONNECTABLE) && (fh_type != FILEID_BTRFS_WITH_PARENT_ROOT || - fh_len != BTRFS_FID_SIZE_CONNECTABLE_ROOT) && + fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) && (fh_type != FILEID_BTRFS_WITHOUT_PARENT || - fh_len != BTRFS_FID_SIZE_NON_CONNECTABLE)) + fh_len < BTRFS_FID_SIZE_NON_CONNECTABLE)) return NULL; objectid = fid->objectid; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 9f9604201333..601d7d45d164 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2828,6 +2828,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head; int ret; int run_all = count == (unsigned long)-1; + bool can_flush_pending_bgs = trans->can_flush_pending_bgs; /* We'll clean this up in btrfs_cleanup_transaction */ if (trans->aborted) @@ -2844,6 +2845,7 @@ again: #ifdef SCRAMBLE_DELAYED_REFS delayed_refs->run_delayed_start = find_middle(&delayed_refs->root); #endif + trans->can_flush_pending_bgs = false; ret = __btrfs_run_delayed_refs(trans, root, count); if (ret < 0) { btrfs_abort_transaction(trans, root, ret); @@ -2893,6 +2895,7 @@ again: } out: assert_qgroups_uptodate(trans); + trans->can_flush_pending_bgs = can_flush_pending_bgs; return 0; } @@ -4306,7 +4309,8 @@ out: * the block groups that were made dirty during the lifetime of the * transaction. */ - if (trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) { + if (trans->can_flush_pending_bgs && + trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) { btrfs_create_pending_block_groups(trans, trans->root); btrfs_trans_release_chunk_metadata(trans); } @@ -9560,7 +9564,9 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, struct btrfs_block_group_item item; struct btrfs_key key; int ret = 0; + bool can_flush_pending_bgs = trans->can_flush_pending_bgs; + trans->can_flush_pending_bgs = false; list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { if (ret) goto next; @@ -9581,6 +9587,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, next: list_del_init(&block_group->bg_list); } + trans->can_flush_pending_bgs = can_flush_pending_bgs; } int btrfs_make_block_group(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index e2357e31609a..3915c9473e94 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3132,12 +3132,12 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { struct inode *inode; struct btrfs_ordered_extent *ordered; int index; - u64 prev_em_start = (u64)-1; inode = pages[0]->mapping->host; while (1) { @@ -3153,7 +3153,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, for (index = 0; index < nr_pages; index++) { __do_readpage(tree, pages[index], get_extent, em_cached, bio, - mirror_num, bio_flags, rw, &prev_em_start); + mirror_num, bio_flags, rw, prev_em_start); page_cache_release(pages[index]); } } @@ -3163,7 +3163,8 @@ static void __extent_readpages(struct extent_io_tree *tree, int nr_pages, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { u64 start = 0; u64 end = 0; @@ -3184,7 +3185,7 @@ static void __extent_readpages(struct extent_io_tree *tree, index - first_index, start, end, get_extent, em_cached, bio, mirror_num, bio_flags, - rw); + rw, prev_em_start); start = page_start; end = start + PAGE_CACHE_SIZE - 1; first_index = index; @@ -3195,7 +3196,8 @@ static void __extent_readpages(struct extent_io_tree *tree, __do_contiguous_readpages(tree, &pages[first_index], index - first_index, start, end, get_extent, em_cached, bio, - mirror_num, bio_flags, rw); + mirror_num, bio_flags, rw, + prev_em_start); } static int __extent_read_full_page(struct extent_io_tree *tree, @@ -4207,6 +4209,7 @@ int extent_readpages(struct extent_io_tree *tree, struct page *page; struct extent_map *em_cached = NULL; int nr = 0; + u64 prev_em_start = (u64)-1; for (page_idx = 0; page_idx < nr_pages; page_idx++) { page = list_entry(pages->prev, struct page, lru); @@ -4223,12 +4226,12 @@ int extent_readpages(struct extent_io_tree *tree, if (nr < ARRAY_SIZE(pagepool)) continue; __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, - &bio, 0, &bio_flags, READ); + &bio, 0, &bio_flags, READ, &prev_em_start); nr = 0; } if (nr) __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, - &bio, 0, &bio_flags, READ); + &bio, 0, &bio_flags, READ, &prev_em_start); if (em_cached) free_extent_map(em_cached); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0adf5422fce9..3e3e6130637f 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4639,6 +4639,11 @@ locked: bctl->flags |= BTRFS_BALANCE_TYPE_MASK; } + if (bctl->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) { + ret = -EINVAL; + goto out_bargs; + } + do_balance: /* * Ownership of bctl and mutually_exclusive_operation_running diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index aa72bfd28f7d..a739b825bdd3 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1920,10 +1920,12 @@ static int did_overwrite_ref(struct send_ctx *sctx, /* * We know that it is or will be overwritten. Check this now. * The current inode being processed might have been the one that caused - * inode 'ino' to be orphanized, therefore ow_inode can actually be the - * same as sctx->send_progress. + * inode 'ino' to be orphanized, therefore check if ow_inode matches + * the current inode being processed. */ - if (ow_inode <= sctx->send_progress) + if ((ow_inode < sctx->send_progress) || + (ino != sctx->cur_ino && ow_inode == sctx->cur_ino && + gen == sctx->cur_inode_gen)) ret = 1; else ret = 0; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 74bc3338418b..a5b06442f0bf 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -557,6 +557,7 @@ again: h->delayed_ref_elem.seq = 0; h->type = type; h->allocating_chunk = false; + h->can_flush_pending_bgs = true; h->reloc_reserved = false; h->sync = false; INIT_LIST_HEAD(&h->qgroup_ref_list); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 87964bf8892d..a994bb097ee5 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -118,6 +118,7 @@ struct btrfs_trans_handle { short aborted; short adding_csums; bool allocating_chunk; + bool can_flush_pending_bgs; bool reloc_reserved; bool sync; unsigned int type; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 2ca784a14e84..595279a8b99f 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -376,6 +376,14 @@ struct map_lookup { #define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4) #define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) +#define BTRFS_BALANCE_ARGS_MASK \ + (BTRFS_BALANCE_ARGS_PROFILES | \ + BTRFS_BALANCE_ARGS_USAGE | \ + BTRFS_BALANCE_ARGS_DEVID | \ + BTRFS_BALANCE_ARGS_DRANGE | \ + BTRFS_BALANCE_ARGS_VRANGE | \ + BTRFS_BALANCE_ARGS_LIMIT) + /* * Profile changing flags. When SOFT is set we won't relocate chunk if * it already has the target profile (even though it may be diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 27aea110e923..c3cc1609025f 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -136,5 +136,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.07" +#define CIFS_VERSION "2.08" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index e2a6af1508af..62203c387db4 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3380,6 +3380,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, struct page *page, *tpage; unsigned int expected_index; int rc; + gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping); INIT_LIST_HEAD(tmplist); @@ -3392,7 +3393,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, */ __set_page_locked(page); rc = add_to_page_cache_locked(page, mapping, - page->index, GFP_KERNEL); + page->index, gfp); /* give up if we can't stick it in the cache */ if (rc) { @@ -3418,8 +3419,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, break; __set_page_locked(page); - if (add_to_page_cache_locked(page, mapping, page->index, - GFP_KERNEL)) { + if (add_to_page_cache_locked(page, mapping, page->index, gfp)) { __clear_page_locked(page); break; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index f621b44cb800..6b66dd5d1540 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2034,7 +2034,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, struct tcon_link *tlink = NULL; struct cifs_tcon *tcon = NULL; struct TCP_Server_Info *server; - struct cifs_io_parms io_parms; /* * To avoid spurious oplock breaks from server, in the case of @@ -2056,18 +2055,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, rc = -ENOSYS; cifsFileInfo_put(open_file); cifs_dbg(FYI, "SetFSize for attrs rc = %d\n", rc); - if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) { - unsigned int bytes_written; - - io_parms.netfid = open_file->fid.netfid; - io_parms.pid = open_file->pid; - io_parms.tcon = tcon; - io_parms.offset = 0; - io_parms.length = attrs->ia_size; - rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, - NULL, NULL, 1); - cifs_dbg(FYI, "Wrt seteof rc %d\n", rc); - } } else rc = -EINVAL; @@ -2093,28 +2080,7 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, else rc = -ENOSYS; cifs_dbg(FYI, "SetEOF by path (setattrs) rc = %d\n", rc); - if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) { - __u16 netfid; - int oplock = 0; - rc = SMBLegacyOpen(xid, tcon, full_path, FILE_OPEN, - GENERIC_WRITE, CREATE_NOT_DIR, &netfid, - &oplock, NULL, cifs_sb->local_nls, - cifs_remap(cifs_sb)); - if (rc == 0) { - unsigned int bytes_written; - - io_parms.netfid = netfid; - io_parms.pid = current->tgid; - io_parms.tcon = tcon; - io_parms.offset = 0; - io_parms.length = attrs->ia_size; - rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, NULL, - NULL, 1); - cifs_dbg(FYI, "wrt seteof rc %d\n", rc); - CIFSSMBClose(xid, tcon, netfid); - } - } if (tlink) cifs_put_tlink(tlink); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index ce83e2edbe0a..597a417ba94d 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -922,7 +922,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, if (tcon && tcon->bad_network_name) return -ENOENT; - if ((tcon->seal) && + if ((tcon && tcon->seal) && ((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) { cifs_dbg(VFS, "encryption requested but no server support"); return -EOPNOTSUPP; @@ -285,6 +285,7 @@ static int copy_user_bh(struct page *to, struct buffer_head *bh, static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, struct vm_area_struct *vma, struct vm_fault *vmf) { + struct address_space *mapping = inode->i_mapping; sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9); unsigned long vaddr = (unsigned long)vmf->virtual_address; void __pmem *addr; @@ -292,6 +293,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, pgoff_t size; int error; + i_mmap_lock_read(mapping); + /* * Check truncate didn't happen while we were allocating a block. * If it did, this block may or may not be still allocated to the @@ -321,6 +324,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, error = vm_insert_mixed(vma, vaddr, pfn); out: + i_mmap_unlock_read(mapping); + return error; } @@ -382,17 +387,15 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, * from a read fault and we've raced with a truncate */ error = -EIO; - goto unlock; + goto unlock_page; } - } else { - i_mmap_lock_write(mapping); } error = get_block(inode, block, &bh, 0); if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; /* fs corruption? */ if (error) - goto unlock; + goto unlock_page; if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) { if (vmf->flags & FAULT_FLAG_WRITE) { @@ -403,9 +406,8 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; if (error) - goto unlock; + goto unlock_page; } else { - i_mmap_unlock_write(mapping); return dax_load_hole(mapping, page, vmf); } } @@ -417,15 +419,17 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, else clear_user_highpage(new_page, vaddr); if (error) - goto unlock; + goto unlock_page; vmf->page = page; if (!page) { + i_mmap_lock_read(mapping); /* Check we didn't race with truncate */ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (vmf->pgoff >= size) { + i_mmap_unlock_read(mapping); error = -EIO; - goto unlock; + goto out; } } return VM_FAULT_LOCKED; @@ -461,8 +465,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE)); } - if (!page) - i_mmap_unlock_write(mapping); out: if (error == -ENOMEM) return VM_FAULT_OOM | major; @@ -471,14 +473,11 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, return VM_FAULT_SIGBUS | major; return VM_FAULT_NOPAGE | major; - unlock: + unlock_page: if (page) { unlock_page(page); page_cache_release(page); - } else { - i_mmap_unlock_write(mapping); } - goto out; } EXPORT_SYMBOL(__dax_fault); @@ -556,10 +555,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); bh.b_size = PMD_SIZE; - i_mmap_lock_write(mapping); length = get_block(inode, block, &bh, write); if (length) return VM_FAULT_SIGBUS; + i_mmap_lock_read(mapping); /* * If the filesystem isn't willing to tell us the length of a hole, @@ -569,36 +568,14 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) goto fallback; - sector = bh.b_blocknr << (blkbits - 9); - - if (buffer_unwritten(&bh) || buffer_new(&bh)) { - int i; - - length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn, - bh.b_size); - if (length < 0) { - result = VM_FAULT_SIGBUS; - goto out; - } - if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR)) - goto fallback; - - for (i = 0; i < PTRS_PER_PMD; i++) - clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE); - wmb_pmem(); - count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); - result |= VM_FAULT_MAJOR; - } - /* * If we allocated new storage, make sure no process has any * zero pages covering this hole */ if (buffer_new(&bh)) { - i_mmap_unlock_write(mapping); + i_mmap_unlock_read(mapping); unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0); - i_mmap_lock_write(mapping); + i_mmap_lock_read(mapping); } /* @@ -635,6 +612,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, result = VM_FAULT_NOPAGE; spin_unlock(ptl); } else { + sector = bh.b_blocknr << (blkbits - 9); length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn, bh.b_size); if (length < 0) { @@ -644,15 +622,25 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR)) goto fallback; + if (buffer_unwritten(&bh) || buffer_new(&bh)) { + int i; + for (i = 0; i < PTRS_PER_PMD; i++) + clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE); + wmb_pmem(); + count_vm_event(PGMAJFAULT); + mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); + result |= VM_FAULT_MAJOR; + } + result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write); } out: + i_mmap_unlock_read(mapping); + if (buffer_unwritten(&bh)) complete_unwritten(&bh, !(result & VM_FAULT_ERROR)); - i_mmap_unlock_write(mapping); - return result; fallback: diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 47728da7702c..b46e9fc64196 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -63,7 +63,7 @@ config EXT4_FS If unsure, say N. config EXT4_USE_FOR_EXT2 - bool "Use ext4 for ext2/ext3 file systems" + bool "Use ext4 for ext2 file systems" depends on EXT4_FS depends on EXT2_FS=n default y diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index e26803fb210d..560af0437704 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -165,8 +165,8 @@ int ext4_mpage_readpages(struct address_space *mapping, if (pages) { page = list_entry(pages->prev, struct page, lru); list_del(&page->lru); - if (add_to_page_cache_lru(page, mapping, - page->index, GFP_KERNEL)) + if (add_to_page_cache_lru(page, mapping, page->index, + GFP_KERNEL & mapping_gfp_mask(mapping))) goto next_page; } diff --git a/fs/mpage.c b/fs/mpage.c index 778a4ddef77a..a7c34274f207 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -139,7 +139,8 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block) static struct bio * do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages, sector_t *last_block_in_bio, struct buffer_head *map_bh, - unsigned long *first_logical_block, get_block_t get_block) + unsigned long *first_logical_block, get_block_t get_block, + gfp_t gfp) { struct inode *inode = page->mapping->host; const unsigned blkbits = inode->i_blkbits; @@ -277,8 +278,7 @@ alloc_new: goto out; } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), - min_t(int, nr_pages, BIO_MAX_PAGES), - GFP_KERNEL); + min_t(int, nr_pages, BIO_MAX_PAGES), gfp); if (bio == NULL) goto confused; } @@ -361,6 +361,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; + gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping); map_bh.b_state = 0; map_bh.b_size = 0; @@ -370,12 +371,13 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, prefetchw(&page->flags); list_del(&page->lru); if (!add_to_page_cache_lru(page, mapping, - page->index, GFP_KERNEL)) { + page->index, + gfp)) { bio = do_mpage_readpage(bio, page, nr_pages - page_idx, &last_block_in_bio, &map_bh, &first_logical_block, - get_block); + get_block, gfp); } page_cache_release(page); } @@ -395,11 +397,12 @@ int mpage_readpage(struct page *page, get_block_t get_block) sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; + gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(page->mapping); map_bh.b_state = 0; map_bh.b_size = 0; bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio, - &map_bh, &first_logical_block, get_block); + &map_bh, &first_logical_block, get_block, gfp); if (bio) mpage_bio_submit(READ, bio); return 0; diff --git a/fs/namei.c b/fs/namei.c index 726d211db484..33e9495a3129 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1558,8 +1558,6 @@ static int lookup_fast(struct nameidata *nd, negative = d_is_negative(dentry); if (read_seqcount_retry(&dentry->d_seq, seq)) return -ECHILD; - if (negative) - return -ENOENT; /* * This sequence count validates that the parent had no @@ -1580,6 +1578,12 @@ static int lookup_fast(struct nameidata *nd, goto unlazy; } } + /* + * Note: do negative dentry check after revalidation in + * case that drops it. + */ + if (negative) + return -ENOENT; path->mnt = mnt; path->dentry = dentry; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f93b9cdb4934..5133bb18830e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1458,12 +1458,18 @@ nfs4_opendata_check_deleg(struct nfs4_opendata *data, struct nfs4_state *state) if (delegation) delegation_flags = delegation->flags; rcu_read_unlock(); - if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) { + switch (data->o_arg.claim) { + default: + break; + case NFS4_OPEN_CLAIM_DELEGATE_CUR: + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: pr_err_ratelimited("NFS: Broken NFSv4 server %s is " "returning a delegation for " "OPEN(CLAIM_DELEGATE_CUR)\n", clp->cl_hostname); - } else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0) + return; + } + if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0) nfs_inode_set_delegation(state->inode, data->owner->so_cred, &data->o_res); @@ -1771,6 +1777,9 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, if (IS_ERR(opendata)) return PTR_ERR(opendata); nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid); + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + write_sequnlock(&state->seqlock); clear_bit(NFS_DELEGATED_STATE, &state->flags); switch (type & (FMODE_READ|FMODE_WRITE)) { case FMODE_READ|FMODE_WRITE: @@ -1863,6 +1872,8 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data) data->rpc_done = 0; data->rpc_status = 0; data->timestamp = jiffies; + if (data->is_recover) + nfs4_set_sequence_privileged(&data->c_arg.seq_args); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 5db324635e92..d854693a15b0 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1725,7 +1725,8 @@ restart: if (!test_and_clear_bit(ops->owner_flag_bit, &sp->so_flags)) continue; - atomic_inc(&sp->so_count); + if (!atomic_inc_not_zero(&sp->so_count)) + continue; spin_unlock(&clp->cl_lock); rcu_read_unlock(); diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 28df12e525ba..671cf68fe56b 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -409,7 +409,7 @@ DECLARE_EVENT_CLASS(nfs4_open_event, __entry->flags = flags; __entry->fmode = (__force unsigned int)ctx->mode; __entry->dev = ctx->dentry->d_sb->s_dev; - if (!IS_ERR(state)) + if (!IS_ERR_OR_NULL(state)) inode = state->inode; if (inode != NULL) { __entry->fileid = NFS_FILEID(inode); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 72624dc4a623..75ab7622e0cc 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -569,19 +569,17 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, if (!nfs_pageio_add_request(pgio, req)) { nfs_redirty_request(req); ret = pgio->pg_error; - } + } else + nfs_add_stats(page_file_mapping(page)->host, + NFSIOS_WRITEPAGES, 1); out: return ret; } static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) { - struct inode *inode = page_file_mapping(page)->host; int ret; - nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); - nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); - nfs_pageio_cond_complete(pgio, page_file_index(page)); ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); if (ret == -EAGAIN) { @@ -597,9 +595,11 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc) { struct nfs_pageio_descriptor pgio; + struct inode *inode = page_file_mapping(page)->host; int err; - nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc), + nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); + nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, &nfs_async_write_completion_ops); err = nfs_do_writepage(page, wbc, &pgio); nfs_pageio_complete(&pgio); @@ -1223,7 +1223,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino return 1; if (!flctx || (list_empty_careful(&flctx->flc_flock) && list_empty_careful(&flctx->flc_posix))) - return 0; + return 1; /* Check to see if there are whole file write locks */ ret = 0; diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index cdefaa331a07..c29d9421bd5e 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -56,14 +56,6 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, u32 device_generation = 0; int error; - /* - * We do not attempt to support I/O smaller than the fs block size, - * or not aligned to it. - */ - if (args->lg_minlength < block_size) { - dprintk("pnfsd: I/O too small\n"); - goto out_layoutunavailable; - } if (seg->offset & (block_size - 1)) { dprintk("pnfsd: I/O misaligned\n"); goto out_layoutunavailable; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index ba1323a94924..a586467f6ff6 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -70,6 +70,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) unsigned order; void *data; int ret; + gfp_t gfp = mapping_gfp_mask(inode->i_mapping); /* make various checks */ order = get_order(newsize); @@ -84,7 +85,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) /* allocate enough contiguous pages to be able to satisfy the * request */ - pages = alloc_pages(mapping_gfp_mask(inode->i_mapping), order); + pages = alloc_pages(gfp, order); if (!pages) return -ENOMEM; @@ -108,7 +109,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) struct page *page = pages + loop; ret = add_to_page_cache_lru(page, inode->i_mapping, loop, - GFP_KERNEL); + gfp); if (ret < 0) goto add_error; diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h index 94f9ea8abcae..011dde083f23 100644 --- a/include/asm-generic/word-at-a-time.h +++ b/include/asm-generic/word-at-a-time.h @@ -1,15 +1,10 @@ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H -/* - * This says "generic", but it's actually big-endian only. - * Little-endian can use more efficient versions of these - * interfaces, see for example - * arch/x86/include/asm/word-at-a-time.h - * for those. - */ - #include <linux/kernel.h> +#include <asm/byteorder.h> + +#ifdef __BIG_ENDIAN struct word_at_a_time { const unsigned long high_bits, low_bits; @@ -53,4 +48,73 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct #define zero_bytemask(mask) (~1ul << __fls(mask)) #endif +#else + +/* + * The optimal byte mask counting is probably going to be something + * that is architecture-specific. If you have a reliably fast + * bit count instruction, that might be better than the multiply + * and shift, for example. + */ +struct word_at_a_time { + const unsigned long one_bits, high_bits; +}; + +#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } + +#ifdef CONFIG_64BIT + +/* + * Jan Achrenius on G+: microoptimized version of + * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56" + * that works for the bytemasks without having to + * mask them first. + */ +static inline long count_masked_bytes(unsigned long mask) +{ + return mask*0x0001020304050608ul >> 56; +} + +#else /* 32-bit case */ + +/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ +static inline long count_masked_bytes(long mask) +{ + /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ + long a = (0x0ff0001+mask) >> 23; + /* Fix the 1 for 00 case */ + return a & mask; +} + +#endif + +/* Return nonzero if it has a zero */ +static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) +{ + unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; + *bits = mask; + return mask; +} + +static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) +{ + return bits; +} + +static inline unsigned long create_zero_mask(unsigned long bits) +{ + bits = (bits - 1) & ~bits; + return bits >> 7; +} + +/* The mask we created is directly usable as a bytemask */ +#define zero_bytemask(mask) (mask) + +static inline unsigned long find_zero(unsigned long mask) +{ + return count_masked_bytes(mask); +} + +#endif /* __BIG_ENDIAN */ + #endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h index 2a747a91fded..3febb4b9fce9 100644 --- a/include/drm/drm_crtc_helper.h +++ b/include/drm/drm_crtc_helper.h @@ -240,5 +240,6 @@ extern void drm_kms_helper_hotplug_event(struct drm_device *dev); extern void drm_kms_helper_poll_disable(struct drm_device *dev); extern void drm_kms_helper_poll_enable(struct drm_device *dev); +extern void drm_kms_helper_poll_enable_locked(struct drm_device *dev); #endif diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 499e9f625aef..0212d139a480 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -568,6 +568,10 @@ #define MODE_I2C_READ 4 #define MODE_I2C_STOP 8 +/* DP 1.2 MST PORTs - Section 2.5.1 v1.2a spec */ +#define DP_MST_PHYSICAL_PORT_0 0 +#define DP_MST_LOGICAL_PORT_0 8 + #define DP_LINK_STATUS_SIZE 6 bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE], int lane_count); diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index 86d0b25ed054..5340099741ae 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -253,6 +253,7 @@ struct drm_dp_remote_dpcd_write { u8 *bytes; }; +#define DP_REMOTE_I2C_READ_MAX_TRANSACTIONS 4 struct drm_dp_remote_i2c_read { u8 num_transactions; u8 port_number; @@ -262,7 +263,7 @@ struct drm_dp_remote_i2c_read { u8 *bytes; u8 no_stop_bit; u8 i2c_transaction_delay; - } transactions[4]; + } transactions[DP_REMOTE_I2C_READ_MAX_TRANSACTIONS]; u8 read_i2c_device_id; u8 num_bytes_read; }; @@ -374,6 +375,7 @@ struct drm_dp_mst_topology_mgr; struct drm_dp_mst_topology_cbs { /* create a connector for a port */ struct drm_connector *(*add_connector)(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, const char *path); + void (*register_connector)(struct drm_connector *connector); void (*destroy_connector)(struct drm_dp_mst_topology_mgr *mgr, struct drm_connector *connector); void (*hotplug)(struct drm_dp_mst_topology_mgr *mgr); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 37d1602c4f7a..5e7d43ab61c0 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -145,7 +145,6 @@ enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_SHARED = 1 << 1, BLK_MQ_F_SG_MERGE = 1 << 2, - BLK_MQ_F_SYSFS_UP = 1 << 3, BLK_MQ_F_DEFER_ISSUE = 1 << 4, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, BLK_MQ_F_ALLOC_POLICY_BITS = 1, @@ -215,7 +214,7 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head); void blk_mq_cancel_requeue_work(struct request_queue *q); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_abort_requeue_list(struct request_queue *q); -void blk_mq_complete_request(struct request *rq); +void blk_mq_complete_request(struct request *rq, int error); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); @@ -224,8 +223,6 @@ void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); -void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn, - void *priv); void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv); void blk_mq_freeze_queue(struct request_queue *q); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 99da9ebc7377..19c2e947d4d1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -456,6 +456,8 @@ struct request_queue { struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; struct bio_set *bio_split; + + bool mq_sysfs_init_done; }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index d3ca79236fb0..f644fdb06dd6 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -161,6 +161,11 @@ enum { IRQ_DOMAIN_FLAG_NONCORE = (1 << 16), }; +static inline struct device_node *irq_domain_get_of_node(struct irq_domain *d) +{ + return d->of_node; +} + #ifdef CONFIG_IRQ_DOMAIN struct irq_domain *__irq_domain_add(struct device_node *of_node, int size, irq_hw_number_t hwirq_max, int direct_max, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index baad4cb8e9b0..5a8677bafe04 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -833,6 +833,7 @@ struct mlx4_dev { struct mlx4_quotas quotas; struct radix_tree_root qp_table_tree; u8 rev_id; + u8 port_random_macs; char board_id[MLX4_BOARD_ID_LEN]; int numa_node; int oper_log_mgm_entry_size; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 2a0b95662548..0b473cbfa7ef 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -439,7 +439,8 @@ struct mlx5_init_seg { __be32 cmdq_addr_h; __be32 cmdq_addr_l_sz; __be32 cmd_dbell; - __be32 rsvd1[121]; + __be32 rsvd1[120]; + __be32 initializing; struct health_buffer health; __be32 rsvd2[884]; __be32 health_counter; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 41a32873f608..5c857f2a20d7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -393,6 +393,7 @@ struct mlx5_core_health { struct timer_list timer; u32 prev; int miss_counter; + bool sick; struct workqueue_struct *wq; struct work_struct work; }; @@ -486,8 +487,26 @@ struct mlx5_priv { spinlock_t ctx_lock; }; +enum mlx5_device_state { + MLX5_DEVICE_STATE_UP, + MLX5_DEVICE_STATE_INTERNAL_ERROR, +}; + +enum mlx5_interface_state { + MLX5_INTERFACE_STATE_DOWN, + MLX5_INTERFACE_STATE_UP, +}; + +enum mlx5_pci_status { + MLX5_PCI_STATUS_DISABLED, + MLX5_PCI_STATUS_ENABLED, +}; + struct mlx5_core_dev { struct pci_dev *pdev; + /* sync pci state */ + struct mutex pci_status_mutex; + enum mlx5_pci_status pci_status; u8 rev_id; char board_id[MLX5_BOARD_ID_LEN]; struct mlx5_cmd cmd; @@ -496,6 +515,10 @@ struct mlx5_core_dev { u32 hca_caps_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; + enum mlx5_device_state state; + /* sync interface state */ + struct mutex intf_state_mutex; + enum mlx5_interface_state interface_state; void (*event) (struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); @@ -803,6 +826,11 @@ void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); +static inline int fw_initializing(struct mlx5_core_dev *dev) +{ + return ioread32be(&dev->iseg->initializing) >> 31; +} + static inline u32 mlx5_mkey_to_idx(u32 mkey) { return mkey >> 8; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b3374402c1ea..69fdd427c8cb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2106,6 +2106,7 @@ struct pcpu_sw_netstats { #define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */ #define NETDEV_CHANGEINFODATA 0x0018 #define NETDEV_BONDING_INFO 0x0019 +#define NETDEV_PRECHANGEUPPER 0x001A int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 165ab2d14734..0ad556726181 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -90,7 +90,6 @@ struct nf_hook_ops { /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; - struct module *owner; void *priv; u_int8_t pf; unsigned int hooknum; @@ -347,8 +346,23 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) } #else /* !CONFIG_NETFILTER */ -#define NF_HOOK(pf, hook, net, sk, skb, indev, outdev, okfn) (okfn)(net, sk, skb) -#define NF_HOOK_COND(pf, hook, net, sk, skb, indev, outdev, okfn, cond) (okfn)(net, sk, skb) +static inline int +NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct sk_buff *skb, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + bool cond) +{ + return okfn(net, sk, skb); +} + +static inline int +NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct sk_buff *skb, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) +{ + return okfn(net, sk, skb); +} + static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, @@ -369,24 +383,28 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; void nf_ct_attach(struct sk_buff *, const struct sk_buff *); extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; +#else +static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} +#endif struct nf_conn; enum ip_conntrack_info; struct nlattr; -struct nfq_ct_hook { +struct nfnl_ct_hook { + struct nf_conn *(*get_ct)(const struct sk_buff *skb, + enum ip_conntrack_info *ctinfo); size_t (*build_size)(const struct nf_conn *ct); - int (*build)(struct sk_buff *skb, struct nf_conn *ct); + int (*build)(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + u_int16_t ct_attr, u_int16_t ct_info_attr); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report); void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off); }; -extern struct nfq_ct_hook __rcu *nfq_ct_hook; -#else -static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} -#endif +extern struct nfnl_ct_hook __rcu *nfnl_ct_hook; /** * nf_skb_duplicated - TEE target has sent a packet diff --git a/include/linux/platform_data/atmel.h b/include/linux/platform_data/atmel.h index 527a85c61924..c121ddf74f7f 100644 --- a/include/linux/platform_data/atmel.h +++ b/include/linux/platform_data/atmel.h @@ -74,11 +74,6 @@ struct atmel_uart_data { struct serial_rs485 rs485; /* rs485 settings */ }; -/* CAN */ -struct at91_can_data { - void (*transceiver_switch)(int on); -}; - /* FIXME: this needs a better location, but gets stuff building again */ extern int at91_suspend_entering_slow_clock(void); diff --git a/include/linux/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h index 11f00cdabe3d..11f00cdabe3d 100644 --- a/include/linux/mdio-gpio.h +++ b/include/linux/platform_data/mdio-gpio.h diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4398411236f1..24f4dfd94c51 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -463,6 +463,15 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, return delta_us; } +static inline bool skb_mstamp_after(const struct skb_mstamp *t1, + const struct skb_mstamp *t0) +{ + s32 diff = t1->stamp_jiffies - t0->stamp_jiffies; + + if (!diff) + diff = t1->stamp_us - t0->stamp_us; + return diff > 0; +} /** * struct sk_buff - socket buffer diff --git a/include/linux/string.h b/include/linux/string.h index a8d90db9c4b0..9ef7795e65e4 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -25,6 +25,9 @@ extern char * strncpy(char *,const char *, __kernel_size_t); #ifndef __HAVE_ARCH_STRLCPY size_t strlcpy(char *, const char *, size_t); #endif +#ifndef __HAVE_ARCH_STRSCPY +ssize_t __must_check strscpy(char *, const char *, size_t); +#endif #ifndef __HAVE_ARCH_STRCAT extern char * strcat(char *, const char *); #endif diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 86a7edaa6797..c906f4534581 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -194,6 +194,12 @@ struct tcp_sock { u32 window_clamp; /* Maximal window to advertise */ u32 rcv_ssthresh; /* Current window clamp */ + /* Information of the most recently (s)acked skb */ + struct tcp_rack { + struct skb_mstamp mstamp; /* (Re)sent time of the skb */ + u8 advanced; /* mstamp advanced since last lost marking */ + u8 reord; /* reordering detected */ + } rack; u16 advmss; /* Advertised MSS */ u8 unused; u8 nonagle : 4,/* Disable Nagle algorithm? */ @@ -217,6 +223,9 @@ struct tcp_sock { u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ u32 rtt_seq; /* sequence number to update rttvar */ + struct rtt_meas { + u32 rtt, ts; /* RTT in usec and sampling time in jiffies. */ + } rtt_min[3]; u32 packets_out; /* Packets which are "in flight" */ u32 retrans_out; /* Retransmitted packets out */ @@ -280,8 +289,6 @@ struct tcp_sock { int lost_cnt_hint; u32 retransmit_high; /* L-bits may be on up to this seqno */ - u32 lost_retrans_low; /* Sent seq after any rxmit (lowest) */ - u32 prior_ssthresh; /* ssthresh saved at recovery start */ u32 high_seq; /* snd_nxt at onset of congestion */ @@ -385,8 +392,9 @@ static inline bool tcp_passive_fastopen(const struct sock *sk) static inline void fastopen_queue_tune(struct sock *sk, int backlog) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; + int somaxconn = READ_ONCE(sock_net(sk)->core.sysctl_somaxconn); - queue->fastopenq.max_qlen = backlog; + queue->fastopenq.max_qlen = min_t(unsigned int, backlog, somaxconn); } static inline void tcp_saved_syn_free(struct tcp_sock *tp) diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index 3dd5a781da99..bfb74723f151 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -157,7 +157,7 @@ struct renesas_usbhs_driver_param { */ int pio_dma_border; /* default is 64byte */ - u32 type; + uintptr_t type; u32 enable_gpio; /* diff --git a/include/net/af_unix.h b/include/net/af_unix.h index cb1b9bbda332..b36d837c701e 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -64,7 +64,7 @@ struct unix_sock { struct socket_wq peer_wq; }; -static inline struct unix_sock *unix_sk(struct sock *sk) +static inline struct unix_sock *unix_sk(const struct sock *sk) { return (struct unix_sock *)sk; } diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3208a65d1c28..63615709839d 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -268,13 +268,8 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req); -static inline void inet_csk_reqsk_queue_add(struct sock *sk, - struct request_sock *req, - struct sock *child) -{ - reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child); -} - +void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, + struct sock *child); void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); @@ -299,6 +294,7 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) } void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); +void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); @@ -312,7 +308,7 @@ static inline unsigned int inet_csk_listen_poll(const struct sock *sk) (POLLIN | POLLRDNORM) : 0; } -int inet_csk_listen_start(struct sock *sk, const int nr_table_entries); +int inet_csk_listen_start(struct sock *sk, int backlog); void inet_csk_listen_stop(struct sock *sk); void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index e581fc69129d..c9b3eb70f340 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -113,12 +113,12 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm); -static void inline inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo) +static inline void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo) { __inet_twsk_schedule(tw, timeo, false); } -static void inline inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo) +static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo) { __inet_twsk_schedule(tw, timeo, true); } diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 44a19a171104..774d85b2d5d9 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -19,14 +19,22 @@ * @l3mdev_get_rtable: Get cached IPv4 rtable (dst_entry) for device * * @l3mdev_get_saddr: Get source address for a flow + * + * @l3mdev_get_rt6_dst: Get cached IPv6 rt6_info (dst_entry) for device */ struct l3mdev_ops { u32 (*l3mdev_fib_table)(const struct net_device *dev); + + /* IPv4 ops */ struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev, const struct flowi4 *fl4); void (*l3mdev_get_saddr)(struct net_device *dev, struct flowi4 *fl4); + + /* IPv6 ops */ + struct dst_entry * (*l3mdev_get_rt6_dst)(const struct net_device *dev, + const struct flowi6 *fl6); }; #ifdef CONFIG_NET_L3_MASTER_DEV @@ -123,6 +131,31 @@ static inline void l3mdev_get_saddr(struct net *net, int ifindex, } } +static inline struct dst_entry *l3mdev_get_rt6_dst(const struct net_device *dev, + const struct flowi6 *fl6) +{ + if (netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_get_rt6_dst) + return dev->l3mdev_ops->l3mdev_get_rt6_dst(dev, fl6); + + return NULL; +} + +static inline +struct dst_entry *l3mdev_rt6_dst_by_oif(struct net *net, + const struct flowi6 *fl6) +{ + struct dst_entry *dst = NULL; + struct net_device *dev; + + dev = dev_get_by_index(net, fl6->flowi6_oif); + if (dev) { + dst = l3mdev_get_rt6_dst(dev, fl6); + dev_put(dev); + } + + return dst; +} + #else static inline int l3mdev_master_ifindex_rcu(struct net_device *dev) @@ -171,6 +204,19 @@ static inline void l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4) { } + +static inline +struct dst_entry *l3mdev_get_rt6_dst(const struct net_device *dev, + const struct flowi6 *fl6) +{ + return NULL; +} +static inline +struct dst_entry *l3mdev_rt6_dst_by_oif(struct net *net, + const struct flowi6 *fl6) +{ + return NULL; +} #endif #endif /* _NET_L3MDEV_H_ */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d642f68a7c73..fde4068eec0b 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -183,10 +183,6 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls); void nf_ct_free_hashtable(void *hash, unsigned int size); -struct nf_conntrack_tuple_hash * -__nf_conntrack_find(struct net *net, u16 zone, - const struct nf_conntrack_tuple *tuple); - int nf_conntrack_hash_check_insert(struct nf_conn *ct); bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report); diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 62308713dd7f..f72be38860a7 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -20,10 +20,20 @@ struct ctnl_timeout { }; struct nf_conn_timeout { - struct ctnl_timeout *timeout; + struct ctnl_timeout __rcu *timeout; }; -#define NF_CT_TIMEOUT_EXT_DATA(__t) (unsigned int *) &((__t)->timeout->data) +static inline unsigned int * +nf_ct_timeout_data(struct nf_conn_timeout *t) +{ + struct ctnl_timeout *timeout; + + timeout = rcu_dereference(t->timeout); + if (timeout == NULL) + return NULL; + + return (unsigned int *)timeout->data; +} static inline struct nf_conn_timeout *nf_ct_timeout_find(const struct nf_conn *ct) @@ -47,7 +57,7 @@ struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct, if (timeout_ext == NULL) return NULL; - timeout_ext->timeout = timeout; + rcu_assign_pointer(timeout_ext->timeout, timeout); return timeout_ext; #else @@ -64,10 +74,13 @@ nf_ct_timeout_lookup(struct net *net, struct nf_conn *ct, unsigned int *timeouts; timeout_ext = nf_ct_timeout_find(ct); - if (timeout_ext) - timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext); - else + if (timeout_ext) { + timeouts = nf_ct_timeout_data(timeout_ext); + if (unlikely(!timeouts)) + timeouts = l4proto->get_timeouts(net); + } else { timeouts = l4proto->get_timeouts(net); + } return timeouts; #else diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index e8635854a55b..9c5638ad872e 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -32,7 +32,7 @@ void nf_register_queue_handler(const struct nf_queue_handler *qh); void nf_unregister_queue_handler(void); void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict); -bool nf_queue_entry_get_refs(struct nf_queue_entry *entry); +void nf_queue_entry_get_refs(struct nf_queue_entry *entry); void nf_queue_entry_release_refs(struct nf_queue_entry *entry); static inline void init_hashrandom(u32 *jhash_initval) diff --git a/include/net/netfilter/nfnetlink_queue.h b/include/net/netfilter/nfnetlink_queue.h deleted file mode 100644 index aff88ba91391..000000000000 --- a/include/net/netfilter/nfnetlink_queue.h +++ /dev/null @@ -1,51 +0,0 @@ -#ifndef _NET_NFNL_QUEUE_H_ -#define _NET_NFNL_QUEUE_H_ - -#include <linux/netfilter/nf_conntrack_common.h> - -struct nf_conn; - -#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT -struct nf_conn *nfqnl_ct_get(struct sk_buff *entskb, size_t *size, - enum ip_conntrack_info *ctinfo); -struct nf_conn *nfqnl_ct_parse(const struct sk_buff *skb, - const struct nlattr *attr, - enum ip_conntrack_info *ctinfo); -int nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo); -void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, int diff); -int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, - u32 portid, u32 report); -#else -inline struct nf_conn * -nfqnl_ct_get(struct sk_buff *entskb, size_t *size, enum ip_conntrack_info *ctinfo) -{ - return NULL; -} - -inline struct nf_conn *nfqnl_ct_parse(const struct sk_buff *skb, - const struct nlattr *attr, - enum ip_conntrack_info *ctinfo) -{ - return NULL; -} - -inline int -nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) -{ - return 0; -} - -inline void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, int diff) -{ -} - -inline int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, - u32 portid, u32 report) -{ - return 0; -} -#endif /* NF_CONNTRACK */ -#endif diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 46d336abca92..c68926b4899c 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -74,7 +74,6 @@ struct netns_ipv4 { int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; int sysctl_icmp_errors_use_inbound_ifaddr; - int sysctl_icmp_redirects_use_orig_daddr; struct local_ports ip_local_ports; diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 2e73748956d5..a0dde04eb178 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -186,25 +186,6 @@ static inline bool reqsk_queue_empty(const struct request_sock_queue *queue) return queue->rskq_accept_head == NULL; } -static inline void reqsk_queue_add(struct request_sock_queue *queue, - struct request_sock *req, - struct sock *parent, - struct sock *child) -{ - spin_lock(&queue->rskq_lock); - req->sk = child; - sk_acceptq_added(parent); - - if (queue->rskq_accept_head == NULL) - queue->rskq_accept_head = req; - else - queue->rskq_accept_tail->dl_next = req; - - queue->rskq_accept_tail = req; - req->dl_next = NULL; - spin_unlock(&queue->rskq_lock); -} - static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue, struct sock *parent) { diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index aff6ceb891a9..2f87c1ba13de 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -124,7 +124,8 @@ struct rtnl_af_ops { int (*fill_link_af)(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask); - size_t (*get_link_af_size)(const struct net_device *dev); + size_t (*get_link_af_size)(const struct net_device *dev, + u32 ext_filter_mask); int (*validate_link_af)(const struct net_device *dev, const struct nlattr *attr); diff --git a/include/net/sock.h b/include/net/sock.h index 64a75458d22c..aeed5c95f3ca 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -843,6 +843,14 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s if (sk_rcvqueues_full(sk, limit)) return -ENOBUFS; + /* + * If the skb was allocated from pfmemalloc reserves, only + * allow SOCK_MEMALLOC sockets to use it as this socket is + * helping free memory + */ + if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) + return -ENOMEM; + __sk_add_backlog(sk, skb); sk->sk_backlog.len += skb->truesize; return 0; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 1ce70830357d..bc865e244efe 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -14,9 +14,11 @@ #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/list.h> +#include <net/ip_fib.h> #define SWITCHDEV_F_NO_RECURSE BIT(0) #define SWITCHDEV_F_SKIP_EOPNOTSUPP BIT(1) +#define SWITCHDEV_F_DEFER BIT(2) struct switchdev_trans_item { struct list_head list; @@ -58,8 +60,6 @@ struct switchdev_attr { } u; }; -struct fib_info; - enum switchdev_obj_id { SWITCHDEV_OBJ_ID_UNDEFINED, SWITCHDEV_OBJ_ID_PORT_VLAN, @@ -69,6 +69,7 @@ enum switchdev_obj_id { struct switchdev_obj { enum switchdev_obj_id id; + u32 flags; }; /* SWITCHDEV_OBJ_ID_PORT_VLAN */ @@ -87,7 +88,7 @@ struct switchdev_obj_ipv4_fib { struct switchdev_obj obj; u32 dst; int dst_len; - struct fib_info *fi; + struct fib_info fi; u8 tos; u8 type; u32 nlflags; @@ -100,7 +101,7 @@ struct switchdev_obj_ipv4_fib { /* SWITCHDEV_OBJ_ID_PORT_FDB */ struct switchdev_obj_port_fdb { struct switchdev_obj obj; - const unsigned char *addr; + unsigned char addr[ETH_ALEN]; u16 vid; u16 ndm_state; }; @@ -132,7 +133,7 @@ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, struct switchdev_attr *attr); int (*switchdev_port_attr_set)(struct net_device *dev, - struct switchdev_attr *attr, + const struct switchdev_attr *attr, struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, const struct switchdev_obj *obj, @@ -167,10 +168,11 @@ switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) #ifdef CONFIG_NET_SWITCHDEV +void switchdev_deferred_process(void); int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr); + const struct switchdev_attr *attr); int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj); int switchdev_port_obj_del(struct net_device *dev, @@ -208,6 +210,10 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, #else +static inline void switchdev_deferred_process(void) +{ +} + static inline int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { @@ -215,7 +221,7 @@ static inline int switchdev_port_attr_get(struct net_device *dev, } static inline int switchdev_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr) + const struct switchdev_attr *attr) { return -EOPNOTSUPP; } diff --git a/include/net/tcp.h b/include/net/tcp.h index a6be56d5f0e3..11e320412216 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -279,6 +279,7 @@ extern int sysctl_tcp_limit_output_bytes; extern int sysctl_tcp_challenge_ack_limit; extern unsigned int sysctl_tcp_notsent_lowat; extern int sysctl_tcp_min_tso_segs; +extern int sysctl_tcp_min_rtt_wlen; extern int sysctl_tcp_autocorking; extern int sysctl_tcp_invalid_ratelimit; extern int sysctl_tcp_pacing_ss_ratio; @@ -566,6 +567,7 @@ void tcp_resume_early_retransmit(struct sock *sk); void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk); +void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); @@ -671,6 +673,12 @@ static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) return dst_metric_locked(dst, RTAX_CC_ALGO); } +/* Minimum RTT in usec. ~0 means not available. */ +static inline u32 tcp_min_rtt(const struct tcp_sock *tp) +{ + return tp->rtt_min[0].rtt; +} + /* Compute the actual receive window we are currently advertising. * Rcv_nxt can be after the window if our peer push more data * than the offered window. @@ -1716,7 +1724,7 @@ struct tcp_request_sock_ops { __u32 (*init_seq)(const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, - u16 queue_mapping, struct tcp_fastopen_cookie *foc, + struct tcp_fastopen_cookie *foc, bool attach_req); }; @@ -1743,6 +1751,19 @@ int tcpv4_offload_init(void); void tcp_v4_init(void); void tcp_init(void); +/* tcp_recovery.c */ + +/* Flags to enable various loss recovery features. See below */ +extern int sysctl_tcp_recovery; + +/* Use TCP RACK to detect (some) tail and retransmit losses */ +#define TCP_RACK_LOST_RETRANS 0x1 + +extern int tcp_rack_mark_lost(struct sock *sk); + +extern void tcp_rack_advance(struct tcp_sock *tp, + const struct skb_mstamp *xmit_time, u8 sacked); + /* * Save and compile IPv4 options, return a pointer to it */ diff --git a/include/uapi/asm-generic/signal.h b/include/uapi/asm-generic/signal.h index 9df61f1edb0f..3094618d382f 100644 --- a/include/uapi/asm-generic/signal.h +++ b/include/uapi/asm-generic/signal.h @@ -80,8 +80,10 @@ * SA_RESTORER 0x04000000 */ +#if !defined MINSIGSTKSZ || !defined SIGSTKSZ #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 +#endif #ifndef __ASSEMBLY__ typedef struct { diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index f7b2db44eb4b..70d89230b641 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -263,6 +263,7 @@ header-y += minix_fs.h header-y += mman.h header-y += mmtimer.h header-y += mpls.h +header-y += mpls_iptunnel.h header-y += mqueue.h header-y += mroute6.h header-y += mroute.h diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 564f1f091991..2e032426cfb7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -287,6 +287,17 @@ enum bpf_func_id { * Return: realm if != 0 */ BPF_FUNC_get_route_realm, + + /** + * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample + * @ctx: struct pt_regs* + * @map: pointer to perf_event_array map + * @index: index of event in the map + * @data: data on stack to be output as raw data + * @size: size of data + * Return: 0 on success + */ + BPF_FUNC_perf_event_output, __BPF_FUNC_MAX_ID, }; diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h index 89ddb9dc9bdf..7a291dc1ff15 100644 --- a/include/uapi/linux/can/bcm.h +++ b/include/uapi/linux/can/bcm.h @@ -47,6 +47,11 @@ #include <linux/types.h> #include <linux/can.h> +struct bcm_timeval { + long tv_sec; + long tv_usec; +}; + /** * struct bcm_msg_head - head of messages to/from the broadcast manager * @opcode: opcode, see enum below. @@ -62,7 +67,7 @@ struct bcm_msg_head { __u32 opcode; __u32 flags; __u32 count; - struct timeval ival1, ival2; + struct bcm_timeval ival1, ival2; canid_t can_id; __u32 nframes; struct can_frame frames[0]; diff --git a/include/uapi/linux/netfilter/nfnetlink_log.h b/include/uapi/linux/netfilter/nfnetlink_log.h index 90c2c9575bac..fb21f0c717a1 100644 --- a/include/uapi/linux/netfilter/nfnetlink_log.h +++ b/include/uapi/linux/netfilter/nfnetlink_log.h @@ -51,6 +51,8 @@ enum nfulnl_attr_type { NFULA_HWTYPE, /* hardware type */ NFULA_HWHEADER, /* hardware header */ NFULA_HWLEN, /* hardware header length */ + NFULA_CT, /* nf_conntrack_netlink.h */ + NFULA_CT_INFO, /* enum ip_conntrack_info */ __NFULA_MAX }; @@ -93,5 +95,6 @@ enum nfulnl_attr_config { #define NFULNL_CFG_F_SEQ 0x0001 #define NFULNL_CFG_F_SEQ_GLOBAL 0x0002 +#define NFULNL_CFG_F_CONNTRACK 0x0004 #endif /* _NFNETLINK_LOG_H */ diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 4036e1b1980f..fef125e2d777 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -323,10 +323,10 @@ enum ovs_key_attr { OVS_KEY_ATTR_MPLS, /* array of struct ovs_key_mpls. * The implementation may restrict * the accepted length of the array. */ - OVS_KEY_ATTR_CT_STATE, /* u8 bitmask of OVS_CS_F_* */ + OVS_KEY_ATTR_CT_STATE, /* u32 bitmask of OVS_CS_F_* */ OVS_KEY_ATTR_CT_ZONE, /* u16 connection tracking zone. */ OVS_KEY_ATTR_CT_MARK, /* u32 connection tracking mark */ - OVS_KEY_ATTR_CT_LABEL, /* 16-octet connection tracking label */ + OVS_KEY_ATTR_CT_LABELS, /* 16-octet connection tracking label */ #ifdef __KERNEL__ OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ @@ -441,9 +441,9 @@ struct ovs_key_nd { __u8 nd_tll[ETH_ALEN]; }; -#define OVS_CT_LABEL_LEN 16 -struct ovs_key_ct_label { - __u8 ct_label[OVS_CT_LABEL_LEN]; +#define OVS_CT_LABELS_LEN 16 +struct ovs_key_ct_labels { + __u8 ct_labels[OVS_CT_LABELS_LEN]; }; /* OVS_KEY_ATTR_CT_STATE flags */ @@ -451,9 +451,9 @@ struct ovs_key_ct_label { #define OVS_CS_F_ESTABLISHED 0x02 /* Part of an existing connection. */ #define OVS_CS_F_RELATED 0x04 /* Related to an established * connection. */ -#define OVS_CS_F_INVALID 0x20 /* Could not track connection. */ -#define OVS_CS_F_REPLY_DIR 0x40 /* Flow is in the reply direction. */ -#define OVS_CS_F_TRACKED 0x80 /* Conntrack has occurred. */ +#define OVS_CS_F_REPLY_DIR 0x08 /* Flow is in the reply direction. */ +#define OVS_CS_F_INVALID 0x10 /* Could not track connection. */ +#define OVS_CS_F_TRACKED 0x20 /* Conntrack has occurred. */ /** * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands. @@ -620,22 +620,24 @@ struct ovs_action_hash { /** * enum ovs_ct_attr - Attributes for %OVS_ACTION_ATTR_CT action. - * @OVS_CT_ATTR_FLAGS: u32 connection tracking flags. + * @OVS_CT_ATTR_COMMIT: If present, commits the connection to the conntrack + * table. This allows future packets for the same connection to be identified + * as 'established' or 'related'. * @OVS_CT_ATTR_ZONE: u16 connection tracking zone. * @OVS_CT_ATTR_MARK: u32 value followed by u32 mask. For each bit set in the * mask, the corresponding bit in the value is copied to the connection * tracking mark field in the connection. - * @OVS_CT_ATTR_LABEL: %OVS_CT_LABEL_LEN value followed by %OVS_CT_LABEL_LEN + * @OVS_CT_ATTR_LABEL: %OVS_CT_LABELS_LEN value followed by %OVS_CT_LABELS_LEN * mask. For each bit set in the mask, the corresponding bit in the value is * copied to the connection tracking label field in the connection. * @OVS_CT_ATTR_HELPER: variable length string defining conntrack ALG. */ enum ovs_ct_attr { OVS_CT_ATTR_UNSPEC, - OVS_CT_ATTR_FLAGS, /* u8 bitmask of OVS_CT_F_*. */ + OVS_CT_ATTR_COMMIT, /* No argument, commits connection. */ OVS_CT_ATTR_ZONE, /* u16 zone id. */ OVS_CT_ATTR_MARK, /* mark to associate with this connection. */ - OVS_CT_ATTR_LABEL, /* label to associate with this connection. */ + OVS_CT_ATTR_LABELS, /* labels to associate with this connection. */ OVS_CT_ATTR_HELPER, /* netlink helper to assist detection of related connections. */ __OVS_CT_ATTR_MAX @@ -643,14 +645,6 @@ enum ovs_ct_attr { #define OVS_CT_ATTR_MAX (__OVS_CT_ATTR_MAX - 1) -/* - * OVS_CT_ATTR_FLAGS flags - bitmask of %OVS_CT_F_* - * @OVS_CT_F_COMMIT: Commits the flow to the conntrack table. This allows - * future packets for the same connection to be identified as 'established' - * or 'related'. - */ -#define OVS_CT_F_COMMIT 0x01 - /** * enum ovs_action_attr - Action types. * @@ -707,7 +701,7 @@ enum ovs_action_attr { * data immediately followed by a mask. * The data must be zero for the unmasked * bits. */ - OVS_ACTION_ATTR_CT, /* One nested OVS_CT_ATTR_* . */ + OVS_ACTION_ATTR_CT, /* Nested OVS_CT_ATTR_* . */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 2881145cda86..d3c417615361 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -110,6 +110,7 @@ enum perf_sw_ids { PERF_COUNT_SW_ALIGNMENT_FAULTS = 7, PERF_COUNT_SW_EMULATION_FAULTS = 8, PERF_COUNT_SW_DUMMY = 9, + PERF_COUNT_SW_BPF_OUTPUT = 10, PERF_COUNT_SW_MAX, /* non-ABI */ }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 4db0b3ccb497..123a5af4e8bb 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -160,7 +160,7 @@ struct rtattr { /* Macros to handle rtattributes */ -#define RTA_ALIGNTO 4 +#define RTA_ALIGNTO 4U #define RTA_ALIGN(len) ( ((len)+RTA_ALIGNTO-1) & ~(RTA_ALIGNTO-1) ) #define RTA_OK(rta,len) ((len) >= (int)sizeof(struct rtattr) && \ (rta)->rta_len >= sizeof(struct rtattr) && \ diff --git a/include/xen/interface/sched.h b/include/xen/interface/sched.h index 9ce083960a25..f18490985fc8 100644 --- a/include/xen/interface/sched.h +++ b/include/xen/interface/sched.h @@ -107,5 +107,13 @@ struct sched_watchdog { #define SHUTDOWN_suspend 2 /* Clean up, save suspend info, kill. */ #define SHUTDOWN_crash 3 /* Tell controller we've crashed. */ #define SHUTDOWN_watchdog 4 /* Restart because watchdog time expired. */ +/* + * Domain asked to perform 'soft reset' for it. The expected behavior is to + * reset internal Xen state for the domain returning it to the point where it + * was created but leaving the domain's memory contents and vCPU contexts + * intact. This will allow the domain to start over and set up all Xen specific + * interfaces again. + */ +#define SHUTDOWN_soft_reset 5 #endif /* __XEN_PUBLIC_SCHED_H__ */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index f2d9e698c753..e3cfe46b074f 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -295,6 +295,8 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) return (void *)attr; if (attr->type != PERF_TYPE_RAW && + !(attr->type == PERF_TYPE_SOFTWARE && + attr->config == PERF_COUNT_SW_BPF_OUTPUT) && attr->type != PERF_TYPE_HARDWARE) { perf_event_release_kernel(event); return ERR_PTR(-EINVAL); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f640e5f7afbd..687dd6ca574d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -520,6 +520,7 @@ void bpf_prog_put(struct bpf_prog *prog) { if (atomic_dec_and_test(&prog->aux->refcnt)) { free_used_maps(prog->aux); + bpf_prog_uncharge_memlock(prog); bpf_prog_free(prog); } } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1d6b97be79e1..b56cf51f8d42 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -245,6 +245,7 @@ static const struct { } func_limit[] = { {BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call}, {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read}, + {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output}, }; static void print_verifier_state(struct verifier_env *env) @@ -910,7 +911,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) * don't allow any other map type to be passed into * the special func; */ - if (bool_map != bool_func) + if (bool_func && bool_map != bool_func) return -EINVAL; } diff --git a/kernel/events/core.c b/kernel/events/core.c index b11756f9b6dc..64754bfecd70 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5286,9 +5286,15 @@ void perf_output_sample(struct perf_output_handle *handle, if (sample_type & PERF_SAMPLE_RAW) { if (data->raw) { - perf_output_put(handle, data->raw->size); - __output_copy(handle, data->raw->data, - data->raw->size); + u32 raw_size = data->raw->size; + u32 real_size = round_up(raw_size + sizeof(u32), + sizeof(u64)) - sizeof(u32); + u64 zero = 0; + + perf_output_put(handle, real_size); + __output_copy(handle, data->raw->data, raw_size); + if (real_size - raw_size) + __output_copy(handle, &zero, real_size - raw_size); } else { struct { u32 size; @@ -5420,8 +5426,7 @@ void perf_prepare_sample(struct perf_event_header *header, else size += sizeof(u32); - WARN_ON_ONCE(size & (sizeof(u64)-1)); - header->size += size; + header->size += round_up(size, sizeof(u64)); } if (sample_type & PERF_SAMPLE_BRANCH_STACK) { diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index de41a68fc038..e25a83b67cce 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -22,7 +22,6 @@ /** * handle_bad_irq - handle spurious and unhandled irqs - * @irq: the interrupt number * @desc: description of the interrupt * * Handles spurious and unhandled IRQ's. It also prints a debugmessage. @@ -35,6 +34,7 @@ void handle_bad_irq(struct irq_desc *desc) kstat_incr_irqs_this_cpu(desc); ack_bad_irq(irq); } +EXPORT_SYMBOL_GPL(handle_bad_irq); /* * Special, empty irq handler: diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 7e6512b9dc1f..be9149f62eb8 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -228,11 +228,7 @@ static void msi_domain_update_chip_ops(struct msi_domain_info *info) { struct irq_chip *chip = info->chip; - BUG_ON(!chip); - if (!chip->irq_mask) - chip->irq_mask = pci_msi_mask_irq; - if (!chip->irq_unmask) - chip->irq_unmask = pci_msi_unmask_irq; + BUG_ON(!chip || !chip->irq_mask || !chip->irq_unmask); if (!chip->irq_set_affinity) chip->irq_set_affinity = msi_domain_set_affinity; } diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index e3a8c9577ba6..a50ddc9417ff 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -12,6 +12,7 @@ #include <linux/seq_file.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> +#include <linux/mutex.h> #include "internals.h" @@ -323,18 +324,29 @@ void register_handler_proc(unsigned int irq, struct irqaction *action) void register_irq_proc(unsigned int irq, struct irq_desc *desc) { + static DEFINE_MUTEX(register_lock); char name [MAX_NAMELEN]; - if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir) + if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip)) return; + /* + * irq directories are registered only when a handler is + * added, not when the descriptor is created, so multiple + * tasks might try to register at the same time. + */ + mutex_lock(®ister_lock); + + if (desc->dir) + goto out_unlock; + memset(name, 0, MAX_NAMELEN); sprintf(name, "%d", irq); /* create /proc/irq/1234 */ desc->dir = proc_mkdir(name, root_irq_dir); if (!desc->dir) - return; + goto out_unlock; #ifdef CONFIG_SMP /* create /proc/irq/<irq>/smp_affinity */ @@ -355,6 +367,9 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) proc_create_data("spurious", 0444, desc->dir, &irq_spurious_proc_fops, (void *)(long)irq); + +out_unlock: + mutex_unlock(®ister_lock); } void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 615953141951..10a8faa1b0d4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2517,11 +2517,11 @@ static struct rq *finish_task_switch(struct task_struct *prev) * If a task dies, then it sets TASK_DEAD in tsk->state and calls * schedule one last time. The schedule call will never return, and * the scheduled task must drop that reference. - * The test for TASK_DEAD must occur while the runqueue locks are - * still held, otherwise prev could be scheduled on another cpu, die - * there before we look at prev->state, and then the reference would - * be dropped twice. - * Manfred Spraul <[email protected]> + * + * We must observe prev->state before clearing prev->on_cpu (in + * finish_lock_switch), otherwise a concurrent wakeup can get prev + * running on another CPU and we could rave with its RUNNING -> DEAD + * transition, resulting in a double drop. */ prev_state = prev->state; vtime_task_switch(prev); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 68cda117574c..6d2a119c7ad9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1078,9 +1078,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) * After ->on_cpu is cleared, the task can be moved to a different CPU. * We must ensure this doesn't happen until the switch is completely * finished. + * + * Pairs with the control dependency and rmb in try_to_wake_up(). */ - smp_wmb(); - prev->on_cpu = 0; + smp_store_release(&prev->on_cpu, 0); #endif #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 841b72f720e8..3a38775b50c2 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -217,7 +217,7 @@ static void clocksource_watchdog(unsigned long data) continue; /* Check the deviation from the watchdog clocksource. */ - if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) { + if (abs64(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n", cs->name); pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n", diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3739ac6aa473..44d2cc0436f4 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1251,7 +1251,7 @@ void __init timekeeping_init(void) set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec); tk_set_wall_to_mono(tk, tmp); - timekeeping_update(tk, TK_MIRROR); + timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0fe96c7c8803..47febbe7998e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -215,6 +215,50 @@ const struct bpf_func_proto bpf_perf_event_read_proto = { .arg2_type = ARG_ANYTHING, }; +static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, 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); + void *data = (void *) (long) r4; + struct perf_sample_data sample_data; + struct perf_event *event; + struct perf_raw_record raw = { + .size = size, + .data = data, + }; + + if (unlikely(index >= array->map.max_entries)) + return -E2BIG; + + event = (struct perf_event *)array->ptrs[index]; + if (unlikely(!event)) + return -ENOENT; + + 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())) + return -EOPNOTSUPP; + + perf_sample_data_init(&sample_data, 0, 0); + sample_data.raw = &raw; + perf_event_output(event, &sample_data, regs); + return 0; +} + +static const struct bpf_func_proto bpf_perf_event_output_proto = { + .func = bpf_perf_event_output, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_STACK, + .arg5_type = ARG_CONST_STACK_SIZE, +}; + static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -242,6 +286,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_get_smp_processor_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; + case BPF_FUNC_perf_event_output: + return &bpf_perf_event_output_proto; default: return NULL; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index ca71582fcfab..bcb14cafe007 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1458,13 +1458,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, timer_stats_timer_set_start_info(&dwork->timer); dwork->wq = wq; + /* timer isn't guaranteed to run in this cpu, record earlier */ + if (cpu == WORK_CPU_UNBOUND) + cpu = raw_smp_processor_id(); dwork->cpu = cpu; timer->expires = jiffies + delay; - if (unlikely(cpu != WORK_CPU_UNBOUND)) - add_timer_on(timer, cpu); - else - add_timer(timer); + add_timer_on(timer, cpu); } /** diff --git a/lib/Kconfig b/lib/Kconfig index 2e491ac15622..f0df318104e7 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -220,6 +220,7 @@ config ZLIB_INFLATE config ZLIB_DEFLATE tristate + select BITREVERSE config LZO_COMPRESS tristate diff --git a/lib/string.c b/lib/string.c index 13d1e84ddb80..84775ba873b9 100644 --- a/lib/string.c +++ b/lib/string.c @@ -27,6 +27,10 @@ #include <linux/bug.h> #include <linux/errno.h> +#include <asm/byteorder.h> +#include <asm/word-at-a-time.h> +#include <asm/page.h> + #ifndef __HAVE_ARCH_STRNCASECMP /** * strncasecmp - Case insensitive, length-limited string comparison @@ -146,6 +150,91 @@ size_t strlcpy(char *dest, const char *src, size_t size) EXPORT_SYMBOL(strlcpy); #endif +#ifndef __HAVE_ARCH_STRSCPY +/** + * strscpy - Copy a C-string into a sized buffer + * @dest: Where to copy the string to + * @src: Where to copy the string from + * @count: Size of destination buffer + * + * Copy the string, or as much of it as fits, into the dest buffer. + * The routine returns the number of characters copied (not including + * the trailing NUL) or -E2BIG if the destination buffer wasn't big enough. + * The behavior is undefined if the string buffers overlap. + * The destination buffer is always NUL terminated, unless it's zero-sized. + * + * Preferred to strlcpy() since the API doesn't require reading memory + * from the src string beyond the specified "count" bytes, and since + * the return value is easier to error-check than strlcpy()'s. + * In addition, the implementation is robust to the string changing out + * from underneath it, unlike the current strlcpy() implementation. + * + * Preferred to strncpy() since it always returns a valid string, and + * doesn't unnecessarily force the tail of the destination buffer to be + * zeroed. If the zeroing is desired, it's likely cleaner to use strscpy() + * with an overflow test, then just memset() the tail of the dest buffer. + */ +ssize_t strscpy(char *dest, const char *src, size_t count) +{ + const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; + size_t max = count; + long res = 0; + + if (count == 0) + return -E2BIG; + +#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + /* + * If src is unaligned, don't cross a page boundary, + * since we don't know if the next page is mapped. + */ + if ((long)src & (sizeof(long) - 1)) { + size_t limit = PAGE_SIZE - ((long)src & (PAGE_SIZE - 1)); + if (limit < max) + max = limit; + } +#else + /* If src or dest is unaligned, don't do word-at-a-time. */ + if (((long) dest | (long) src) & (sizeof(long) - 1)) + max = 0; +#endif + + while (max >= sizeof(unsigned long)) { + unsigned long c, data; + + c = *(unsigned long *)(src+res); + if (has_zero(c, &data, &constants)) { + data = prep_zero_mask(c, data, &constants); + data = create_zero_mask(data); + *(unsigned long *)(dest+res) = c & zero_bytemask(data); + return res + find_zero(data); + } + *(unsigned long *)(dest+res) = c; + res += sizeof(unsigned long); + count -= sizeof(unsigned long); + max -= sizeof(unsigned long); + } + + while (count) { + char c; + + c = src[res]; + dest[res] = c; + if (!c) + return res; + res++; + count--; + } + + /* Hit buffer length without finding a NUL; force NUL-termination. */ + if (res) + dest[res-1] = '\0'; + + return -E2BIG; +} +EXPORT_SYMBOL(strscpy); +#endif + #ifndef __HAVE_ARCH_STRCAT /** * strcat - Append one %NUL-terminated string to another diff --git a/mm/filemap.c b/mm/filemap.c index 72940fb38666..1cc5467cf36c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2473,6 +2473,21 @@ ssize_t generic_perform_write(struct file *file, iov_iter_count(i)); again: + /* + * Bring in the user page that we will copy from _first_. + * Otherwise there's a nasty deadlock on copying from the + * same page as we're writing to, without it being marked + * up-to-date. + * + * Not only is this an optimisation, but it is also required + * to check that the address is actually valid, when atomic + * usercopies are used, below. + */ + if (unlikely(iov_iter_fault_in_readable(i, bytes))) { + status = -EFAULT; + break; + } + status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); if (unlikely(status < 0)) @@ -2480,17 +2495,8 @@ again: if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - /* - * 'page' is now locked. If we are trying to copy from a - * mapping of 'page' in userspace, the copy might fault and - * would need PageUptodate() to complete. But, page can not be - * made Uptodate without acquiring the page lock, which we hold. - * Deadlock. Avoid with pagefault_disable(). Fix up below with - * iov_iter_fault_in_readable(). - */ - pagefault_disable(); + copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); - pagefault_enable(); flush_dcache_page(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, @@ -2513,14 +2519,6 @@ again: */ bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset, iov_iter_single_seg_count(i)); - /* - * This is the fallback to recover if the copy from - * userspace above faults. - */ - if (unlikely(iov_iter_fault_in_readable(i, bytes))) { - status = -EFAULT; - break; - } goto again; } pos += copied; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1fedbde68f59..d9b5c817dce8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3387,6 +3387,7 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg, ret = page_counter_memparse(args, "-1", &threshold); if (ret) return ret; + threshold <<= PAGE_SHIFT; mutex_lock(&memcg->thresholds_lock); diff --git a/mm/memory.c b/mm/memory.c index 9cb27470fee9..deb679c31f2a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2426,6 +2426,8 @@ void unmap_mapping_range(struct address_space *mapping, if (details.last_index < details.first_index) details.last_index = ULONG_MAX; + + /* DAX uses i_mmap_lock to serialise file truncate vs page fault */ i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) unmap_mapping_range_tree(&mapping->i_mmap, &details); diff --git a/mm/readahead.c b/mm/readahead.c index 60cd846a9a44..24682f6f4cfd 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -89,8 +89,8 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages, while (!list_empty(pages)) { page = list_to_page(pages); list_del(&page->lru); - if (add_to_page_cache_lru(page, mapping, - page->index, GFP_KERNEL)) { + if (add_to_page_cache_lru(page, mapping, page->index, + GFP_KERNEL & mapping_gfp_mask(mapping))) { read_cache_pages_invalidate_page(mapping, page); continue; } @@ -127,8 +127,8 @@ static int read_pages(struct address_space *mapping, struct file *filp, for (page_idx = 0; page_idx < nr_pages; page_idx++) { struct page *page = list_to_page(pages); list_del(&page->lru); - if (!add_to_page_cache_lru(page, mapping, - page->index, GFP_KERNEL)) { + if (!add_to_page_cache_lru(page, mapping, page->index, + GFP_KERNEL & mapping_gfp_mask(mapping))) { mapping->a_ops->readpage(filp, page); } page_cache_release(page); diff --git a/mm/vmstat.c b/mm/vmstat.c index 4f5cd974e11a..fbf14485a049 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1363,15 +1363,16 @@ static cpumask_var_t cpu_stat_off; static void vmstat_update(struct work_struct *w) { - if (refresh_cpu_vm_stats()) + if (refresh_cpu_vm_stats()) { /* * Counters were updated so we expect more updates * to occur in the future. Keep on running the * update worker thread. */ - schedule_delayed_work(this_cpu_ptr(&vmstat_work), + schedule_delayed_work_on(smp_processor_id(), + this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); - else { + } else { /* * We did not update any counters so the app may be in * a mode where it does not cause counter updates. diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index b4548c739a64..2dda439c8cb8 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -91,10 +91,50 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn) * autoconnect action, remove them completely. If they are, just unmark * them as waiting for connection, by clearing explicit_connect field. */ - if (params->auto_connect == HCI_AUTO_CONN_EXPLICIT) + params->explicit_connect = false; + + list_del_init(¶ms->action); + + switch (params->auto_connect) { + case HCI_AUTO_CONN_EXPLICIT: hci_conn_params_del(conn->hdev, bdaddr, bdaddr_type); - else - params->explicit_connect = false; + /* return instead of break to avoid duplicate scan update */ + return; + case HCI_AUTO_CONN_DIRECT: + case HCI_AUTO_CONN_ALWAYS: + list_add(¶ms->action, &conn->hdev->pend_le_conns); + break; + case HCI_AUTO_CONN_REPORT: + list_add(¶ms->action, &conn->hdev->pend_le_reports); + break; + default: + break; + } + + hci_update_background_scan(conn->hdev); +} + +static void hci_conn_cleanup(struct hci_conn *conn) +{ + struct hci_dev *hdev = conn->hdev; + + if (test_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags)) + hci_conn_params_del(conn->hdev, &conn->dst, conn->dst_type); + + hci_chan_list_flush(conn); + + hci_conn_hash_del(hdev, conn); + + if (hdev->notify) + hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); + + hci_conn_del_sysfs(conn); + + debugfs_remove_recursive(conn->debugfs); + + hci_dev_put(hdev); + + hci_conn_put(conn); } /* This function requires the caller holds hdev->lock */ @@ -102,8 +142,13 @@ static void hci_connect_le_scan_remove(struct hci_conn *conn) { hci_connect_le_scan_cleanup(conn); - hci_conn_hash_del(conn->hdev, conn); - hci_update_background_scan(conn->hdev); + /* We can't call hci_conn_del here since that would deadlock + * with trying to call cancel_delayed_work_sync(&conn->disc_work). + * Instead, call just hci_conn_cleanup() which contains the bare + * minimum cleanup operations needed for a connection in this + * state. + */ + hci_conn_cleanup(conn); } static void hci_acl_create_connection(struct hci_conn *conn) @@ -581,27 +626,17 @@ int hci_conn_del(struct hci_conn *conn) } } - hci_chan_list_flush(conn); - if (conn->amp_mgr) amp_mgr_put(conn->amp_mgr); - hci_conn_hash_del(hdev, conn); - if (hdev->notify) - hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); - skb_queue_purge(&conn->data_q); - hci_conn_del_sysfs(conn); - - debugfs_remove_recursive(conn->debugfs); - - if (test_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags)) - hci_conn_params_del(conn->hdev, &conn->dst, conn->dst_type); - - hci_dev_put(hdev); - - hci_conn_put(conn); + /* Remove the connection from the list and cleanup its remaining + * state. This is a separate function since for some cases like + * BT_CONNECT_SCAN we *only* want the cleanup part without the + * rest of hci_conn_del. + */ + hci_conn_cleanup(conn); return 0; } @@ -973,15 +1008,23 @@ static int hci_explicit_conn_params_set(struct hci_request *req, if (is_connected(hdev, addr, addr_type)) return -EISCONN; - params = hci_conn_params_add(hdev, addr, addr_type); - if (!params) - return -EIO; + params = hci_conn_params_lookup(hdev, addr, addr_type); + if (!params) { + params = hci_conn_params_add(hdev, addr, addr_type); + if (!params) + return -ENOMEM; - /* If we created new params, or existing params were marked as disabled, - * mark them to be used just once to connect. - */ - if (params->auto_connect == HCI_AUTO_CONN_DISABLED) { + /* If we created new params, mark them to be deleted in + * hci_connect_le_scan_cleanup. It's different case than + * existing disabled params, those will stay after cleanup. + */ params->auto_connect = HCI_AUTO_CONN_EXPLICIT; + } + + /* We're trying to connect, so make sure params are at pend_le_conns */ + if (params->auto_connect == HCI_AUTO_CONN_DISABLED || + params->auto_connect == HCI_AUTO_CONN_REPORT || + params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { list_del_init(¶ms->action); list_add(¶ms->action, &hdev->pend_le_conns); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index d2b3dd32d6cf..e4e53bd663df 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2930,13 +2930,6 @@ struct hci_conn_params *hci_explicit_connect_lookup(struct hci_dev *hdev, return param; } - list_for_each_entry(param, &hdev->pend_le_reports, action) { - if (bacmp(¶m->addr, addr) == 0 && - param->addr_type == addr_type && - param->explicit_connect) - return param; - } - return NULL; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 8acec932123a..b4571d84cafa 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -55,7 +55,12 @@ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb) wake_up_bit(&hdev->flags, HCI_INQUIRY); hci_dev_lock(hdev); - hci_discovery_set_state(hdev, DISCOVERY_STOPPED); + /* Set discovery state to stopped if we're not doing LE active + * scanning. + */ + if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) || + hdev->le_scan_type != LE_SCAN_ACTIVE) + hci_discovery_set_state(hdev, DISCOVERY_STOPPED); hci_dev_unlock(hdev); hci_conn_check_pending(hdev); @@ -4648,8 +4653,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, /* If we're not connectable only connect devices that we have in * our pend_le_conns list. */ - params = hci_explicit_connect_lookup(hdev, addr, addr_type); - + params = hci_pend_le_action_lookup(&hdev->pend_le_conns, addr, + addr_type); if (!params) return NULL; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index ccaf5a436d8f..c4fe2fee753f 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3545,6 +3545,7 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, auth_type); } else { u8 addr_type; + struct hci_conn_params *p; /* Convert from L2CAP channel address type to HCI address type */ @@ -3562,7 +3563,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, * If connection parameters already exist, then they * will be kept and this function does nothing. */ - hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + + if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT) + p->auto_connect = HCI_AUTO_CONN_DISABLED; conn = hci_connect_le_scan(hdev, &cp->addr.bdaddr, addr_type, sec_level, @@ -6117,14 +6121,21 @@ static int hci_conn_params_set(struct hci_request *req, bdaddr_t *addr, __hci_update_background_scan(req); break; case HCI_AUTO_CONN_REPORT: - list_add(¶ms->action, &hdev->pend_le_reports); + if (params->explicit_connect) + list_add(¶ms->action, &hdev->pend_le_conns); + else + list_add(¶ms->action, &hdev->pend_le_reports); __hci_update_background_scan(req); break; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: if (!is_connected(hdev, addr, addr_type)) { list_add(¶ms->action, &hdev->pend_le_conns); - __hci_update_background_scan(req); + /* If we are in scan phase of connecting, we were + * already added to pend_le_conns and scanning. + */ + if (params->auto_connect != HCI_AUTO_CONN_EXPLICIT) + __hci_update_background_scan(req); } break; } @@ -6379,7 +6390,8 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - if (params->auto_connect == HCI_AUTO_CONN_DISABLED) { + if (params->auto_connect == HCI_AUTO_CONN_DISABLED || + params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { err = cmd->cmd_complete(cmd, MGMT_STATUS_INVALID_PARAMS); mgmt_pending_remove(cmd); @@ -6415,6 +6427,10 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, if (p->auto_connect == HCI_AUTO_CONN_DISABLED) continue; device_removed(sk, hdev, &p->addr, p->addr_type); + if (p->explicit_connect) { + p->auto_connect = HCI_AUTO_CONN_EXPLICIT; + continue; + } list_del(&p->action); list_del(&p->list); kfree(p); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index bdfb9544ca03..5e88d3e17546 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -56,7 +56,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb); skb_pull(skb, ETH_HLEN); - if (!br_allowed_ingress(br, br_vlan_group(br), skb, &vid)) + if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid)) goto out; if (is_broadcast_ether_addr(dest)) diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index f43ce05c66a6..c88bd8e8937e 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -134,11 +134,14 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr) static void fdb_del_external_learn(struct net_bridge_fdb_entry *f) { struct switchdev_obj_port_fdb fdb = { - .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, - .addr = f->addr.addr, + .obj = { + .id = SWITCHDEV_OBJ_ID_PORT_FDB, + .flags = SWITCHDEV_F_DEFER, + }, .vid = f->vlan_id, }; + ether_addr_copy(fdb.addr, f->addr.addr); switchdev_port_obj_del(f->dst->dev, &fdb.obj); } diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 6d5ed795c3e2..a9d424e20229 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -32,7 +32,7 @@ static inline int should_deliver(const struct net_bridge_port *p, { struct net_bridge_vlan_group *vg; - vg = nbp_vlan_group(p); + vg = nbp_vlan_group_rcu(p); return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING; } @@ -80,7 +80,7 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) { struct net_bridge_vlan_group *vg; - vg = nbp_vlan_group(to); + vg = nbp_vlan_group_rcu(to); skb = br_handle_vlan(to->br, vg, skb); if (!skb) return; @@ -112,7 +112,7 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) return; } - vg = nbp_vlan_group(to); + vg = nbp_vlan_group_rcu(to); skb = br_handle_vlan(to->br, vg, skb); if (!skb) return; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 934cae9fa317..ec02f5869a78 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -24,6 +24,7 @@ #include <linux/slab.h> #include <net/sock.h> #include <linux/if_vlan.h> +#include <net/switchdev.h> #include "br_private.h" @@ -248,7 +249,10 @@ static void del_nbp(struct net_bridge_port *p) list_del_rcu(&p->list); + nbp_vlan_flush(p); br_fdb_delete_by_port(br, p, 0, 1); + switchdev_deferred_process(); + nbp_update_port_count(br); netdev_upper_dev_unlink(dev, br->dev); @@ -256,8 +260,6 @@ static void del_nbp(struct net_bridge_port *p) dev->priv_flags &= ~IFF_BRIDGE_PORT; netdev_rx_handler_unregister(dev); - /* use the synchronize_rcu done by netdev_rx_handler_unregister */ - nbp_vlan_flush(p); br_multicast_del_port(p); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index f5c5a4500e2f..f7fba74108a9 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -44,7 +44,7 @@ static int br_pass_frame_up(struct sk_buff *skb) brstats->rx_bytes += skb->len; u64_stats_update_end(&brstats->syncp); - vg = br_vlan_group(br); + vg = br_vlan_group_rcu(br); /* Bridge is just like any other port. Make sure the * packet is allowed except in promisc modue when someone * may be running packet capture. @@ -140,7 +140,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (!p || p->state == BR_STATE_DISABLED) goto drop; - if (!br_allowed_ingress(p->br, nbp_vlan_group(p), skb, &vid)) + if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid)) goto out; /* insert into forwarding database after filtering to avoid spoofing */ diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 370aa4d4cf4d..7ddbe7ec81d6 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -111,7 +111,6 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb) /* largest possible L2 header, see br_nf_dev_queue_xmit() */ #define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN) -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct brnf_frag_data { char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH]; u8 encap_size; @@ -121,7 +120,6 @@ struct brnf_frag_data { }; static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage); -#endif static void nf_bridge_info_free(struct sk_buff *skb) { @@ -666,7 +664,6 @@ static unsigned int br_nf_forward_arp(void *priv, return NF_STOLEN; } -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) static int br_nf_push_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { struct brnf_frag_data *data; @@ -691,9 +688,7 @@ static int br_nf_push_frag_xmit(struct net *net, struct sock *sk, struct sk_buff nf_bridge_info_free(skb); return br_dev_queue_push_xmit(net, sk, skb); } -#endif -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) static int br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) @@ -711,7 +706,6 @@ br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, return ip_do_fragment(net, sk, skb, output); } -#endif static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) { @@ -734,11 +728,11 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff nf_bridge = nf_bridge_info_get(skb); -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) /* This is wrong! We should preserve the original fragment * boundaries by preserving frag_list rather than refragmenting. */ - if (skb->protocol == htons(ETH_P_IP)) { + if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) && + skb->protocol == htons(ETH_P_IP)) { struct brnf_frag_data *data; if (br_validate_ipv4(net, skb)) @@ -760,9 +754,8 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit); } -#endif -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - if (skb->protocol == htons(ETH_P_IPV6)) { + if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) && + skb->protocol == htons(ETH_P_IPV6)) { const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); struct brnf_frag_data *data; @@ -786,7 +779,6 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff kfree_skb(skb); return -EMSGSIZE; } -#endif nf_bridge_info_free(skb); return br_dev_queue_push_xmit(net, sk, skb); drop: @@ -904,49 +896,42 @@ EXPORT_SYMBOL_GPL(br_netfilter_enable); static struct nf_hook_ops br_nf_ops[] __read_mostly = { { .hook = br_nf_pre_routing, - .owner = THIS_MODULE, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_BRNF, }, { .hook = br_nf_local_in, - .owner = THIS_MODULE, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_IN, .priority = NF_BR_PRI_BRNF, }, { .hook = br_nf_forward_ip, - .owner = THIS_MODULE, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_BRNF - 1, }, { .hook = br_nf_forward_arp, - .owner = THIS_MODULE, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_BRNF, }, { .hook = br_nf_post_routing, - .owner = THIS_MODULE, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_POST_ROUTING, .priority = NF_BR_PRI_LAST, }, { .hook = ip_sabotage_in, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_FIRST, }, { .hook = ip_sabotage_in, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_FIRST, diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index d792d1a848ad..40197ff8918a 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -102,10 +102,10 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev, rcu_read_lock(); if (br_port_exists(dev)) { p = br_port_get_rcu(dev); - vg = nbp_vlan_group(p); + vg = nbp_vlan_group_rcu(p); } else if (dev->priv_flags & IFF_EBRIDGE) { br = netdev_priv(dev); - vg = br_vlan_group(br); + vg = br_vlan_group_rcu(br); } num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); @@ -253,7 +253,7 @@ static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, * if vlaninfo represents a range */ pvid = br_get_pvid(vg); - list_for_each_entry(v, &vg->vlan_list, vlist) { + list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; if (!br_vlan_should_use(v)) continue; @@ -303,7 +303,7 @@ static int br_fill_ifvlaninfo(struct sk_buff *skb, u16 pvid; pvid = br_get_pvid(vg); - list_for_each_entry(v, &vg->vlan_list, vlist) { + list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; @@ -386,22 +386,27 @@ static int br_fill_ifinfo(struct sk_buff *skb, struct nlattr *af; int err; + /* RCU needed because of the VLAN locking rules (rcu || rtnl) */ + rcu_read_lock(); if (port) - vg = nbp_vlan_group(port); + vg = nbp_vlan_group_rcu(port); else - vg = br_vlan_group(br); + vg = br_vlan_group_rcu(br); - if (!vg || !vg->num_vlans) + if (!vg || !vg->num_vlans) { + rcu_read_unlock(); goto done; - + } af = nla_nest_start(skb, IFLA_AF_SPEC); - if (!af) + if (!af) { + rcu_read_unlock(); goto nla_put_failure; - + } if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) err = br_fill_ifvlaninfo_compressed(skb, vg); else err = br_fill_ifvlaninfo(skb, vg); + rcu_read_unlock(); if (err) goto nla_put_failure; nla_nest_end(skb, af); @@ -1209,29 +1214,10 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) return 0; } -static size_t br_get_link_af_size(const struct net_device *dev) -{ - struct net_bridge_port *p; - struct net_bridge *br; - int num_vlans = 0; - - if (br_port_exists(dev)) { - p = br_port_get_rtnl(dev); - num_vlans = br_get_num_vlan_infos(nbp_vlan_group(p), - RTEXT_FILTER_BRVLAN); - } else if (dev->priv_flags & IFF_EBRIDGE) { - br = netdev_priv(dev); - num_vlans = br_get_num_vlan_infos(br_vlan_group(br), - RTEXT_FILTER_BRVLAN); - } - - /* Each VLAN is returned in bridge_vlan_info along with flags */ - return num_vlans * nla_total_size(sizeof(struct bridge_vlan_info)); -} static struct rtnl_af_ops br_af_ops __read_mostly = { .family = AF_BRIDGE, - .get_link_af_size = br_get_link_af_size, + .get_link_af_size = br_get_link_af_size_filtered, }; struct rtnl_link_ops br_link_ops __read_mostly = { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index ba0c67b2159a..216018c76018 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -229,7 +229,7 @@ struct net_bridge_port struct netpoll *np; #endif #ifdef CONFIG_BRIDGE_VLAN_FILTERING - struct net_bridge_vlan_group *vlgrp; + struct net_bridge_vlan_group __rcu *vlgrp; #endif }; @@ -337,7 +337,7 @@ struct net_bridge struct kobject *ifobj; u32 auto_cnt; #ifdef CONFIG_BRIDGE_VLAN_FILTERING - struct net_bridge_vlan_group *vlgrp; + struct net_bridge_vlan_group __rcu *vlgrp; u8 vlan_enabled; __be16 vlan_proto; u16 default_pvid; @@ -700,13 +700,25 @@ int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask); static inline struct net_bridge_vlan_group *br_vlan_group( const struct net_bridge *br) { - return br->vlgrp; + return rtnl_dereference(br->vlgrp); } static inline struct net_bridge_vlan_group *nbp_vlan_group( const struct net_bridge_port *p) { - return p->vlgrp; + return rtnl_dereference(p->vlgrp); +} + +static inline struct net_bridge_vlan_group *br_vlan_group_rcu( + const struct net_bridge *br) +{ + return rcu_dereference(br->vlgrp); +} + +static inline struct net_bridge_vlan_group *nbp_vlan_group_rcu( + const struct net_bridge_port *p) +{ + return rcu_dereference(p->vlgrp); } /* Since bridge now depends on 8021Q module, but the time bridge sees the @@ -853,6 +865,19 @@ static inline struct net_bridge_vlan_group *nbp_vlan_group( { return NULL; } + +static inline struct net_bridge_vlan_group *br_vlan_group_rcu( + const struct net_bridge *br) +{ + return NULL; +} + +static inline struct net_bridge_vlan_group *nbp_vlan_group_rcu( + const struct net_bridge_port *p) +{ + return NULL; +} + #endif struct nf_br_ops { diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index db6d243defb2..80c34d70218c 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -41,13 +41,14 @@ void br_set_state(struct net_bridge_port *p, unsigned int state) { struct switchdev_attr attr = { .id = SWITCHDEV_ATTR_ID_PORT_STP_STATE, + .flags = SWITCHDEV_F_DEFER, .u.stp_state = state, }; int err; p->state = state; err = switchdev_port_attr_set(p->dev, &attr); - if (err && err != -EOPNOTSUPP) + if (err) br_warn(p->br, "error setting offload STP state on port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 4ca449a16132..fa53d7a89f48 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -15,6 +15,7 @@ #include <linux/kmod.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> +#include <net/switchdev.h> #include "br_private.h" #include "br_private_stp.h" @@ -35,11 +36,22 @@ static inline port_id br_make_port_id(__u8 priority, __u16 port_no) /* called under bridge lock */ void br_init_port(struct net_bridge_port *p) { + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, + .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP | SWITCHDEV_F_DEFER, + .u.ageing_time = p->br->ageing_time, + }; + int err; + p->port_id = br_make_port_id(p->priority, p->port_no); br_become_designated_port(p); br_set_state(p, BR_STATE_BLOCKING); p->topology_change_ack = 0; p->config_pending = 0; + + err = switchdev_port_attr_set(p->dev, &attr); + if (err) + netdev_err(p->dev, "failed to set HW ageing time\n"); } /* called under bridge lock */ diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 04ef1926ee7e..8365bd53c421 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -102,7 +102,15 @@ static ssize_t ageing_time_show(struct device *d, static int set_ageing_time(struct net_bridge *br, unsigned long val) { - return br_set_ageing_time(br, val); + int ret; + + if (!rtnl_trylock()) + return restart_syscall(); + + ret = br_set_ageing_time(br, val); + rtnl_unlock(); + + return ret; } static ssize_t ageing_time_store(struct device *d, diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index ad7e4f6b6d6b..5f0d0cc4744f 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -54,9 +54,9 @@ static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags) struct net_bridge_vlan_group *vg; if (br_vlan_is_master(v)) - vg = v->br->vlgrp; + vg = br_vlan_group(v->br); else - vg = v->port->vlgrp; + vg = nbp_vlan_group(v->port); if (flags & BRIDGE_VLAN_INFO_PVID) __vlan_add_pvid(vg, v->vid); @@ -91,11 +91,16 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, static void __vlan_add_list(struct net_bridge_vlan *v) { + struct net_bridge_vlan_group *vg; struct list_head *headp, *hpos; struct net_bridge_vlan *vent; - headp = br_vlan_is_master(v) ? &v->br->vlgrp->vlan_list : - &v->port->vlgrp->vlan_list; + if (br_vlan_is_master(v)) + vg = br_vlan_group(v->br); + else + vg = nbp_vlan_group(v->port); + + headp = &vg->vlan_list; list_for_each_prev(hpos, headp) { vent = list_entry(hpos, struct net_bridge_vlan, vlist); if (v->vid < vent->vid) @@ -137,14 +142,16 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, */ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid) { + struct net_bridge_vlan_group *vg; struct net_bridge_vlan *masterv; - masterv = br_vlan_find(br->vlgrp, vid); + vg = br_vlan_group(br); + masterv = br_vlan_find(vg, vid); if (!masterv) { /* missing global ctx, create it now */ if (br_vlan_add(br, vid, 0)) return NULL; - masterv = br_vlan_find(br->vlgrp, vid); + masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) return NULL; } @@ -155,11 +162,14 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid static void br_vlan_put_master(struct net_bridge_vlan *masterv) { + struct net_bridge_vlan_group *vg; + if (!br_vlan_is_master(masterv)) return; + vg = br_vlan_group(masterv->br); if (atomic_dec_and_test(&masterv->refcnt)) { - rhashtable_remove_fast(&masterv->br->vlgrp->vlan_hash, + rhashtable_remove_fast(&vg->vlan_hash, &masterv->vnode, br_vlan_rht_params); __vlan_del_list(masterv); kfree_rcu(masterv, rcu); @@ -189,12 +199,12 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags) if (br_vlan_is_master(v)) { br = v->br; dev = br->dev; - vg = br->vlgrp; + vg = br_vlan_group(br); } else { p = v->port; br = p->br; dev = p->dev; - vg = p->vlgrp; + vg = nbp_vlan_group(p); } if (p) { @@ -266,10 +276,10 @@ static int __vlan_del(struct net_bridge_vlan *v) int err = 0; if (br_vlan_is_master(v)) { - vg = v->br->vlgrp; + vg = br_vlan_group(v->br); } else { p = v->port; - vg = v->port->vlgrp; + vg = nbp_vlan_group(v->port); masterv = v->brvlan; } @@ -297,15 +307,20 @@ out: return err; } -static void __vlan_flush(struct net_bridge_vlan_group *vlgrp) +static void __vlan_group_free(struct net_bridge_vlan_group *vg) +{ + WARN_ON(!list_empty(&vg->vlan_list)); + rhashtable_destroy(&vg->vlan_hash); + kfree(vg); +} + +static void __vlan_flush(struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *vlan, *tmp; - __vlan_delete_pvid(vlgrp, vlgrp->pvid); - list_for_each_entry_safe(vlan, tmp, &vlgrp->vlan_list, vlist) + __vlan_delete_pvid(vg, vg->pvid); + list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) __vlan_del(vlan); - rhashtable_destroy(&vlgrp->vlan_hash); - kfree(vlgrp); } struct sk_buff *br_handle_vlan(struct net_bridge *br, @@ -467,7 +482,7 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) if (!br->vlan_enabled) return true; - vg = p->vlgrp; + vg = nbp_vlan_group(p); if (!vg || !vg->num_vlans) return false; @@ -493,12 +508,14 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) { + struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; int ret; ASSERT_RTNL(); - vlan = br_vlan_find(br->vlgrp, vid); + vg = br_vlan_group(br); + vlan = br_vlan_find(vg, vid); if (vlan) { if (!br_vlan_is_brentry(vlan)) { /* Trying to change flags of non-existent bridge vlan */ @@ -513,7 +530,7 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) } atomic_inc(&vlan->refcnt); vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; - br->vlgrp->num_vlans++; + vg->num_vlans++; } __vlan_add_flags(vlan, flags); return 0; @@ -541,11 +558,13 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) */ int br_vlan_delete(struct net_bridge *br, u16 vid) { + struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; ASSERT_RTNL(); - v = br_vlan_find(br->vlgrp, vid); + vg = br_vlan_group(br); + v = br_vlan_find(vg, vid); if (!v || !br_vlan_is_brentry(v)) return -ENOENT; @@ -557,9 +576,15 @@ int br_vlan_delete(struct net_bridge *br, u16 vid) void br_vlan_flush(struct net_bridge *br) { + struct net_bridge_vlan_group *vg; + ASSERT_RTNL(); - __vlan_flush(br_vlan_group(br)); + vg = br_vlan_group(br); + __vlan_flush(vg); + RCU_INIT_POINTER(br->vlgrp, NULL); + synchronize_rcu(); + __vlan_group_free(vg); } struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid) @@ -626,6 +651,7 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) int err = 0; struct net_bridge_port *p; struct net_bridge_vlan *vlan; + struct net_bridge_vlan_group *vg; __be16 oldproto; if (br->vlan_proto == proto) @@ -633,7 +659,8 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) /* Add VLANs for the new proto to the device filter. */ list_for_each_entry(p, &br->port_list, list) { - list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) { + vg = nbp_vlan_group(p); + list_for_each_entry(vlan, &vg->vlan_list, vlist) { err = vlan_vid_add(p->dev, proto, vlan->vid); if (err) goto err_filt; @@ -647,19 +674,23 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) br_recalculate_fwd_mask(br); /* Delete VLANs for the old proto from the device filter. */ - list_for_each_entry(p, &br->port_list, list) - list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) + list_for_each_entry(p, &br->port_list, list) { + vg = nbp_vlan_group(p); + list_for_each_entry(vlan, &vg->vlan_list, vlist) vlan_vid_del(p->dev, oldproto, vlan->vid); + } return 0; err_filt: - list_for_each_entry_continue_reverse(vlan, &p->vlgrp->vlan_list, vlist) + list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) vlan_vid_del(p->dev, proto, vlan->vid); - list_for_each_entry_continue_reverse(p, &br->port_list, list) - list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) + list_for_each_entry_continue_reverse(p, &br->port_list, list) { + vg = nbp_vlan_group(p); + list_for_each_entry(vlan, &vg->vlan_list, vlist) vlan_vid_del(p->dev, proto, vlan->vid); + } return err; } @@ -703,11 +734,11 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) /* Disable default_pvid on all ports where it is still * configured. */ - if (vlan_default_pvid(br->vlgrp, pvid)) + if (vlan_default_pvid(br_vlan_group(br), pvid)) br_vlan_delete(br, pvid); list_for_each_entry(p, &br->port_list, list) { - if (vlan_default_pvid(p->vlgrp, pvid)) + if (vlan_default_pvid(nbp_vlan_group(p), pvid)) nbp_vlan_delete(p, pvid); } @@ -717,6 +748,7 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) { const struct net_bridge_vlan *pvent; + struct net_bridge_vlan_group *vg; struct net_bridge_port *p; u16 old_pvid; int err = 0; @@ -737,8 +769,9 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) /* Update default_pvid config only if we do not conflict with * user configuration. */ - pvent = br_vlan_find(br->vlgrp, pvid); - if ((!old_pvid || vlan_default_pvid(br->vlgrp, old_pvid)) && + vg = br_vlan_group(br); + pvent = br_vlan_find(vg, pvid); + if ((!old_pvid || vlan_default_pvid(vg, old_pvid)) && (!pvent || !br_vlan_should_use(pvent))) { err = br_vlan_add(br, pvid, BRIDGE_VLAN_INFO_PVID | @@ -754,9 +787,10 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) /* Update default_pvid config only if we do not conflict with * user configuration. */ + vg = nbp_vlan_group(p); if ((old_pvid && - !vlan_default_pvid(p->vlgrp, old_pvid)) || - br_vlan_find(p->vlgrp, pvid)) + !vlan_default_pvid(vg, old_pvid)) || + br_vlan_find(vg, pvid)) continue; err = nbp_vlan_add(p, pvid, @@ -825,17 +859,19 @@ unlock: int br_vlan_init(struct net_bridge *br) { + struct net_bridge_vlan_group *vg; int ret = -ENOMEM; - br->vlgrp = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL); - if (!br->vlgrp) + vg = kzalloc(sizeof(*vg), GFP_KERNEL); + if (!vg) goto out; - ret = rhashtable_init(&br->vlgrp->vlan_hash, &br_vlan_rht_params); + ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; - INIT_LIST_HEAD(&br->vlgrp->vlan_list); + INIT_LIST_HEAD(&vg->vlan_list); br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; + rcu_assign_pointer(br->vlgrp, vg); ret = br_vlan_add(br, 1, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY); @@ -846,9 +882,9 @@ out: return ret; err_vlan_add: - rhashtable_destroy(&br->vlgrp->vlan_hash); + rhashtable_destroy(&vg->vlan_hash); err_rhtbl: - kfree(br->vlgrp); + kfree(vg); goto out; } @@ -866,9 +902,7 @@ int nbp_vlan_init(struct net_bridge_port *p) if (ret) goto err_rhtbl; INIT_LIST_HEAD(&vg->vlan_list); - /* Make sure everything's committed before publishing vg */ - smp_wmb(); - p->vlgrp = vg; + rcu_assign_pointer(p->vlgrp, vg); if (p->br->default_pvid) { ret = nbp_vlan_add(p, p->br->default_pvid, BRIDGE_VLAN_INFO_PVID | @@ -897,7 +931,7 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) ASSERT_RTNL(); - vlan = br_vlan_find(port->vlgrp, vid); + vlan = br_vlan_find(nbp_vlan_group(port), vid); if (vlan) { __vlan_add_flags(vlan, flags); return 0; @@ -925,7 +959,7 @@ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) ASSERT_RTNL(); - v = br_vlan_find(port->vlgrp, vid); + v = br_vlan_find(nbp_vlan_group(port), vid); if (!v) return -ENOENT; br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); @@ -936,12 +970,13 @@ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) void nbp_vlan_flush(struct net_bridge_port *port) { - struct net_bridge_vlan *vlan; + struct net_bridge_vlan_group *vg; ASSERT_RTNL(); - list_for_each_entry(vlan, &port->vlgrp->vlan_list, vlist) - vlan_vid_del(port->dev, port->br->vlan_proto, vlan->vid); - - __vlan_flush(nbp_vlan_group(port)); + vg = nbp_vlan_group(port); + __vlan_flush(vg); + RCU_INIT_POINTER(port->vlgrp, NULL); + synchronize_rcu(); + __vlan_group_free(vg); } diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index f9242dffa65e..32eccd101f26 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -73,21 +73,18 @@ ebt_out_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops ebt_ops_filter[] __read_mostly = { { .hook = ebt_in_hook, - .owner = THIS_MODULE, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_IN, .priority = NF_BR_PRI_FILTER_BRIDGED, }, { .hook = ebt_in_hook, - .owner = THIS_MODULE, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_FILTER_BRIDGED, }, { .hook = ebt_out_hook, - .owner = THIS_MODULE, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_OUT, .priority = NF_BR_PRI_FILTER_OTHER, diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 4bbefe03ab58..ec55358f00c8 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -73,21 +73,18 @@ ebt_nat_out(void *priv, struct sk_buff *skb, static struct nf_hook_ops ebt_ops_nat[] __read_mostly = { { .hook = ebt_nat_out, - .owner = THIS_MODULE, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_OUT, .priority = NF_BR_PRI_NAT_DST_OTHER, }, { .hook = ebt_nat_out, - .owner = THIS_MODULE, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_POST_ROUTING, .priority = NF_BR_PRI_NAT_SRC, }, { .hook = ebt_nat_in, - .owner = THIS_MODULE, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_NAT_DST_BRIDGED, diff --git a/net/can/bcm.c b/net/can/bcm.c index a1ba6875c2a2..6863310d6973 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -96,7 +96,7 @@ struct bcm_op { canid_t can_id; u32 flags; unsigned long frames_abs, frames_filtered; - struct timeval ival1, ival2; + struct bcm_timeval ival1, ival2; struct hrtimer timer, thrtimer; struct tasklet_struct tsklet, thrtsklet; ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg; @@ -131,6 +131,11 @@ static inline struct bcm_sock *bcm_sk(const struct sock *sk) return (struct bcm_sock *)sk; } +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 OPSIZ sizeof(struct bcm_op) #define MHSIZ sizeof(struct bcm_msg_head) @@ -953,8 +958,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->count = msg_head->count; op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; - op->kt_ival1 = timeval_to_ktime(msg_head->ival1); - op->kt_ival2 = timeval_to_ktime(msg_head->ival2); + op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); + op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); /* disable an active timer due to zero values? */ if (!op->kt_ival1.tv64 && !op->kt_ival2.tv64) @@ -1134,8 +1139,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, /* set timer value */ op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; - op->kt_ival1 = timeval_to_ktime(msg_head->ival1); - op->kt_ival2 = timeval_to_ktime(msg_head->ival2); + op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); + op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); /* disable an active timer due to zero value? */ if (!op->kt_ival1.tv64) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 80b94e37c94a..f79ccac6699f 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -285,6 +285,7 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req, switch (op->op) { case CEPH_OSD_OP_READ: case CEPH_OSD_OP_WRITE: + case CEPH_OSD_OP_WRITEFULL: ceph_osd_data_release(&op->extent.osd_data); break; case CEPH_OSD_OP_CALL: @@ -485,13 +486,14 @@ void osd_req_op_extent_init(struct ceph_osd_request *osd_req, size_t payload_len = 0; BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && - opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE); + opcode != CEPH_OSD_OP_WRITEFULL && opcode != CEPH_OSD_OP_ZERO && + opcode != CEPH_OSD_OP_TRUNCATE); op->extent.offset = offset; op->extent.length = length; op->extent.truncate_size = truncate_size; op->extent.truncate_seq = truncate_seq; - if (opcode == CEPH_OSD_OP_WRITE) + if (opcode == CEPH_OSD_OP_WRITE || opcode == CEPH_OSD_OP_WRITEFULL) payload_len += length; op->payload_len = payload_len; @@ -670,9 +672,11 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, break; case CEPH_OSD_OP_READ: case CEPH_OSD_OP_WRITE: + case CEPH_OSD_OP_WRITEFULL: case CEPH_OSD_OP_ZERO: case CEPH_OSD_OP_TRUNCATE: - if (src->op == CEPH_OSD_OP_WRITE) + if (src->op == CEPH_OSD_OP_WRITE || + src->op == CEPH_OSD_OP_WRITEFULL) request_data_len = src->extent.length; dst->extent.offset = cpu_to_le64(src->extent.offset); dst->extent.length = cpu_to_le64(src->extent.length); @@ -681,7 +685,8 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, dst->extent.truncate_seq = cpu_to_le32(src->extent.truncate_seq); osd_data = &src->extent.osd_data; - if (src->op == CEPH_OSD_OP_WRITE) + if (src->op == CEPH_OSD_OP_WRITE || + src->op == CEPH_OSD_OP_WRITEFULL) ceph_osdc_msg_data_add(req->r_request, osd_data); else ceph_osdc_msg_data_add(req->r_reply, osd_data); diff --git a/net/core/dev.c b/net/core/dev.c index a229bf0d649d..1225b4be8ed6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5346,6 +5346,12 @@ static int __netdev_upper_dev_link(struct net_device *dev, changeupper_info.master = master; changeupper_info.linking = true; + ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + &changeupper_info.info); + ret = notifier_to_errno(ret); + if (ret) + return ret; + ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private, master); if (ret) @@ -5488,6 +5494,9 @@ void netdev_upper_dev_unlink(struct net_device *dev, changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; changeupper_info.linking = false; + call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + &changeupper_info.info); + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); /* Here is the tricky part. We must remove all dev's lower diff --git a/net/core/ethtool.c b/net/core/ethtool.c index b495ab1797fa..29edf74846fc 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1284,7 +1284,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) gstrings.len = ret; - data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); + data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER); if (!data) return -ENOMEM; diff --git a/net/core/filter.c b/net/core/filter.c index 0b00094932ab..672eefbfbe99 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1414,6 +1414,7 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) return dev_forward_skb(dev, skb2); skb2->dev = dev; + skb_sender_cpu_clear(skb2); return dev_queue_xmit(skb2); } @@ -1941,9 +1942,13 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, goto out; /* We're copying the filter that has been originally attached, - * so no conversion/decode needed anymore. + * so no conversion/decode needed anymore. eBPF programs that + * have no original program cannot be dumped through this. */ + ret = -EACCES; fprog = filter->prog->orig_prog; + if (!fprog) + goto out; ret = fprog->len; if (!len) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 24775953fa68..7c78b5aca944 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -497,7 +497,8 @@ void rtnl_af_unregister(struct rtnl_af_ops *ops) } EXPORT_SYMBOL_GPL(rtnl_af_unregister); -static size_t rtnl_link_get_af_size(const struct net_device *dev) +static size_t rtnl_link_get_af_size(const struct net_device *dev, + u32 ext_filter_mask) { struct rtnl_af_ops *af_ops; size_t size; @@ -509,7 +510,7 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev) if (af_ops->get_link_af_size) { /* AF_* + nested data */ size += nla_total_size(sizeof(struct nlattr)) + - af_ops->get_link_af_size(dev); + af_ops->get_link_af_size(dev, ext_filter_mask); } } @@ -900,7 +901,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ - + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + + rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ @@ -3443,4 +3444,3 @@ void __init rtnetlink_init(void) rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, NULL); rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL); } - diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8e99681c8189..59bc180b02d8 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -208,7 +208,6 @@ void dccp_req_err(struct sock *sk, u64 seq) if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - reqsk_put(req); } else { /* * Still in RESPOND, just remove it silently. @@ -218,6 +217,7 @@ void dccp_req_err(struct sock *sk, u64 seq) */ inet_csk_reqsk_queue_drop(req->rsk_listener, req); } + reqsk_put(req); } EXPORT_SYMBOL(dccp_req_err); @@ -799,15 +799,10 @@ static int dccp_v4_rcv(struct sk_buff *skb) DCCP_SKB_CB(skb)->dccpd_ack_seq); } - /* Step 2: - * Look up flow ID in table and get corresponding socket */ +lookup: sk = __inet_lookup_skb(&dccp_hashinfo, skb, dh->dccph_sport, dh->dccph_dport); - /* - * Step 2: - * If no socket ... - */ - if (sk == NULL) { + if (!sk) { dccp_pr_debug("failed to look up flow ID in table and " "get corresponding socket\n"); goto no_dccp_socket; @@ -830,8 +825,12 @@ static int dccp_v4_rcv(struct sk_buff *skb) struct sock *nsk = NULL; sk = req->rsk_listener; - if (sk->sk_state == DCCP_LISTEN) + if (likely(sk->sk_state == DCCP_LISTEN)) { nsk = dccp_check_req(sk, skb, req); + } else { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } if (!nsk) { reqsk_put(req); goto discard_it; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index aed314f8c7c6..d9cc731f2619 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -656,16 +656,11 @@ static int dccp_v6_rcv(struct sk_buff *skb) else DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb); - /* Step 2: - * Look up flow ID in table and get corresponding socket */ +lookup: sk = __inet6_lookup_skb(&dccp_hashinfo, skb, dh->dccph_sport, dh->dccph_dport, inet6_iif(skb)); - /* - * Step 2: - * If no socket ... - */ - if (sk == NULL) { + if (!sk) { dccp_pr_debug("failed to look up flow ID in table and " "get corresponding socket\n"); goto no_dccp_socket; @@ -688,8 +683,12 @@ static int dccp_v6_rcv(struct sk_buff *skb) struct sock *nsk = NULL; sk = req->rsk_listener; - if (sk->sk_state == DCCP_LISTEN) + if (likely(sk->sk_state == DCCP_LISTEN)) { nsk = dccp_check_req(sk, skb, req); + } else { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } if (!nsk) { reqsk_put(req); goto discard_it; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 27fce283117b..607a14f20d88 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -789,9 +789,7 @@ static int dn_forward(struct sk_buff *skb) struct dn_dev *dn_db = rcu_dereference(dst->dev->dn_ptr); struct dn_route *rt; int header_len; -#ifdef CONFIG_NETFILTER struct net_device *dev = skb->dev; -#endif if (skb->pkt_type != PACKET_HOST) goto drop; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index aa398bcef9e3..1eba07feb34a 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -22,6 +22,7 @@ #include <linux/of_platform.h> #include <linux/of_net.h> #include <linux/sysfs.h> +#include <linux/phy_fixed.h> #include "dsa_priv.h" char dsa_driver_version[] = "0.1"; @@ -305,7 +306,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) if (ret < 0) goto out; - ds->slave_mii_bus = mdiobus_alloc(); + ds->slave_mii_bus = devm_mdiobus_alloc(parent); if (ds->slave_mii_bus == NULL) { ret = -ENOMEM; goto out; @@ -314,7 +315,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) ret = mdiobus_register(ds->slave_mii_bus); if (ret < 0) - goto out_free; + goto out; /* @@ -367,10 +368,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) return ret; -out_free: - mdiobus_free(ds->slave_mii_bus); out: - kfree(ds); return ret; } @@ -400,7 +398,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, /* * Allocate and initialise switch state. */ - ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL); + ds = devm_kzalloc(parent, sizeof(*ds) + drv->priv_size, GFP_KERNEL); if (ds == NULL) return ERR_PTR(-ENOMEM); @@ -420,10 +418,47 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, static void dsa_switch_destroy(struct dsa_switch *ds) { + struct device_node *port_dn; + struct phy_device *phydev; + struct dsa_chip_data *cd = ds->pd; + int port; + #ifdef CONFIG_NET_DSA_HWMON if (ds->hwmon_dev) hwmon_device_unregister(ds->hwmon_dev); #endif + + /* Disable configuration of the CPU and DSA ports */ + for (port = 0; port < DSA_MAX_PORTS; port++) { + if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))) + continue; + + port_dn = cd->port_dn[port]; + if (of_phy_is_fixed_link(port_dn)) { + phydev = of_phy_find_device(port_dn); + if (phydev) { + int addr = phydev->addr; + + phy_device_free(phydev); + of_node_put(port_dn); + fixed_phy_del(addr); + } + } + } + + /* Destroy network devices for physical switch ports. */ + for (port = 0; port < DSA_MAX_PORTS; port++) { + if (!(ds->phys_port_mask & (1 << port))) + continue; + + if (!ds->ports[port]) + continue; + + unregister_netdev(ds->ports[port]); + free_netdev(ds->ports[port]); + } + + mdiobus_unregister(ds->slave_mii_bus); } #ifdef CONFIG_PM_SLEEP @@ -802,10 +837,11 @@ static inline void dsa_of_remove(struct device *dev) } #endif -static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, - struct device *parent, struct dsa_platform_data *pd) +static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, + struct device *parent, struct dsa_platform_data *pd) { int i; + unsigned configured = 0; dst->pd = pd; dst->master_netdev = dev; @@ -825,9 +861,17 @@ static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, dst->ds[i] = ds; if (ds->drv->poll_link != NULL) dst->link_poll_needed = 1; + + ++configured; } /* + * If no switch was found, exit cleanly + */ + if (!configured) + return -EPROBE_DEFER; + + /* * 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. @@ -843,6 +887,8 @@ static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, dst->link_poll_timer.expires = round_jiffies(jiffies + HZ); add_timer(&dst->link_poll_timer); } + + return 0; } static int dsa_probe(struct platform_device *pdev) @@ -883,7 +929,7 @@ static int dsa_probe(struct platform_device *pdev) goto out; } - dst = kzalloc(sizeof(*dst), GFP_KERNEL); + dst = devm_kzalloc(&pdev->dev, sizeof(*dst), GFP_KERNEL); if (dst == NULL) { dev_put(dev); ret = -ENOMEM; @@ -892,7 +938,9 @@ static int dsa_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dst); - dsa_setup_dst(dst, dev, &pdev->dev, pd); + ret = dsa_setup_dst(dst, dev, &pdev->dev, pd); + if (ret) + goto out; return 0; @@ -914,7 +962,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) for (i = 0; i < dst->pd->nr_chips; i++) { struct dsa_switch *ds = dst->ds[i]; - if (ds != NULL) + if (ds) dsa_switch_destroy(ds); } } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index bb2bd3b56b16..b0b8da0f5af8 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -393,7 +393,7 @@ static int dsa_slave_port_fdb_dump(struct net_device *dev, if (ret < 0) break; - fdb->addr = addr; + ether_addr_copy(fdb->addr, addr); fdb->vid = vid; fdb->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; @@ -453,7 +453,7 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state) } static int dsa_slave_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr, + const struct switchdev_attr *attr, struct switchdev_trans *trans) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -1276,7 +1276,7 @@ int dsa_slave_netdevice_event(struct notifier_block *unused, goto out; err = dsa_slave_master_changed(dev); - if (err) + if (err && err != -EOPNOTSUPP) netdev_warn(dev, "failed to reflect master change\n"); break; diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 89aacb630a53..c29809f765dc 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -8,6 +8,7 @@ obj-y := route.o inetpeer.o protocol.o \ inet_timewait_sock.o inet_connection_sock.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \ + tcp_recovery.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o \ diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 01308e6e6127..59b3e0e8fd51 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -312,7 +312,7 @@ static void arp_send_dst(int type, int ptype, __be32 dest_ip, if (!skb) return; - skb_dst_set(skb, dst); + skb_dst_set(skb, dst_clone(dst)); arp_xmit(skb); } @@ -384,7 +384,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } if (skb && !(dev->priv_flags & IFF_XMIT_DST_RELEASE)) - dst = dst_clone(skb_dst(skb)); + dst = skb_dst(skb); arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, dst_hw, dev->dev_addr, NULL, dst); } @@ -816,7 +816,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) } else { pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb); - return 0; + goto out_free_dst; } goto out; } @@ -870,6 +870,8 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) out: consume_skb(skb); +out_free_dst: + dst_release(reply_dst); return 0; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 735008472844..cebd9d31e65a 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1644,7 +1644,8 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } -static size_t inet_get_link_af_size(const struct net_device *dev) +static size_t inet_get_link_af_size(const struct net_device *dev, + u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); @@ -2398,4 +2399,3 @@ void __init devinet_init(void) rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf, inet_netconf_dump_devconf, NULL); } - diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index af77298c8b4f..42778d9d71e5 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -545,7 +545,7 @@ static void fib_rebalance(struct fib_info *fi) if (nh->nh_flags & RTNH_F_DEAD) continue; - in_dev = __in_dev_get_rcu(nh->nh_dev); + in_dev = __in_dev_get_rtnl(nh->nh_dev); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && @@ -559,7 +559,7 @@ static void fib_rebalance(struct fib_info *fi) change_nexthops(fi) { int upper_bound; - in_dev = __in_dev_get_rcu(nexthop_nh->nh_dev); + in_dev = __in_dev_get_rtnl(nexthop_nh->nh_dev); if (nexthop_nh->nh_flags & RTNH_F_DEAD) { upper_bound = -1; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index f3c356b7c1f0..36e26977c908 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -659,9 +659,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) */ saddr = iph->daddr; - if (!((type == ICMP_REDIRECT) && - net->ipv4.sysctl_icmp_redirects_use_orig_daddr) && - !(rt->rt_flags & RTCF_LOCAL)) { + if (!(rt->rt_flags & RTCF_LOCAL)) { struct net_device *dev = NULL; rcu_read_lock(); @@ -1224,11 +1222,6 @@ static int __net_init icmp_sk_init(struct net *net) net->ipv4.sysctl_icmp_ratemask = 0x1818; net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; - /* Control paramerer - use the daddr of originating packets as saddr - * in redirect messages? - */ - net->ipv4.sysctl_icmp_redirects_use_orig_daddr = 0; - return 0; fail: diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 514b9e910bd4..8430bc8ccd58 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -546,6 +546,13 @@ void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); +void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req) +{ + inet_csk_reqsk_queue_drop(sk, req); + reqsk_put(req); +} +EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); + static void reqsk_timer_handler(unsigned long data) { struct request_sock *req = (struct request_sock *)data; @@ -608,8 +615,7 @@ static void reqsk_timer_handler(unsigned long data) return; } drop: - inet_csk_reqsk_queue_drop(sk_listener, req); - reqsk_put(req); + inet_csk_reqsk_queue_drop_and_put(sk_listener, req); } static void reqsk_queue_hash_req(struct request_sock *req, @@ -727,14 +733,14 @@ void inet_csk_prepare_forced_close(struct sock *sk) } EXPORT_SYMBOL(inet_csk_prepare_forced_close); -int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) +int inet_csk_listen_start(struct sock *sk, int backlog) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); reqsk_queue_alloc(&icsk->icsk_accept_queue); - sk->sk_max_ack_backlog = 0; + sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); @@ -758,6 +764,53 @@ int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) } EXPORT_SYMBOL_GPL(inet_csk_listen_start); +static void inet_child_forget(struct sock *sk, struct request_sock *req, + struct sock *child) +{ + sk->sk_prot->disconnect(child, O_NONBLOCK); + + sock_orphan(child); + + percpu_counter_inc(sk->sk_prot->orphan_count); + + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { + BUG_ON(tcp_sk(child)->fastopen_rsk != req); + BUG_ON(sk != req->rsk_listener); + + /* Paranoid, to prevent race condition if + * an inbound pkt destined for child is + * blocked by sock lock in tcp_v4_rcv(). + * Also to satisfy an assertion in + * tcp_v4_destroy_sock(). + */ + tcp_sk(child)->fastopen_rsk = NULL; + } + inet_csk_destroy_sock(child); + reqsk_put(req); +} + +void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, + struct sock *child) +{ + struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; + + spin_lock(&queue->rskq_lock); + if (unlikely(sk->sk_state != TCP_LISTEN)) { + inet_child_forget(sk, req, child); + } else { + req->sk = child; + req->dl_next = NULL; + if (queue->rskq_accept_head == NULL) + queue->rskq_accept_head = req; + else + queue->rskq_accept_tail->dl_next = req; + queue->rskq_accept_tail = req; + sk_acceptq_added(sk); + } + spin_unlock(&queue->rskq_lock); +} +EXPORT_SYMBOL(inet_csk_reqsk_queue_add); + /* * This routine closes sockets which have been at least partially * opened, but not yet accepted. @@ -784,31 +837,11 @@ void inet_csk_listen_stop(struct sock *sk) WARN_ON(sock_owned_by_user(child)); sock_hold(child); - sk->sk_prot->disconnect(child, O_NONBLOCK); - - sock_orphan(child); - - percpu_counter_inc(sk->sk_prot->orphan_count); - - if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { - BUG_ON(tcp_sk(child)->fastopen_rsk != req); - BUG_ON(sk != req->rsk_listener); - - /* Paranoid, to prevent race condition if - * an inbound pkt destined for child is - * blocked by sock lock in tcp_v4_rcv(). - * Also to satisfy an assertion in - * tcp_v4_destroy_sock(). - */ - tcp_sk(child)->fastopen_rsk = NULL; - } - inet_csk_destroy_sock(child); - + inet_child_forget(sk, req, child); bh_unlock_sock(child); local_bh_enable(); sock_put(child); - reqsk_put(req); cond_resched(); } if (queue->fastopenq.rskq_rst_head) { @@ -823,7 +856,7 @@ void inet_csk_listen_stop(struct sock *sk) req = next; } } - WARN_ON(sk->sk_ack_backlog); + WARN_ON_ONCE(sk->sk_ack_backlog); } EXPORT_SYMBOL_GPL(inet_csk_listen_stop); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 08643a3616af..958728a22001 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -137,6 +137,10 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; + if (unlikely(!tb)) { + spin_unlock(&head->lock); + return -ENOENT; + } if (tb->port != port) { /* NOTE: using tproxy and redirecting skbs to a proxy * on a different listener port breaks the assumption diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 67404e1fe7d4..50e29737b584 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1596,7 +1596,6 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; - skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb)); ip_push_pending_frames(sk, &fl4); } out: diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index ed4ef09c2136..0bc7412d9e14 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -146,6 +146,10 @@ u8 root_server_path[256] = { 0, }; /* Path to mount as root */ /* vendor class identifier */ static char vendor_class_identifier[253] __initdata; +#if defined(CONFIG_IP_PNP_DHCP) +static char dhcp_client_identifier[253] __initdata; +#endif + /* Persistent data: */ static int ic_proto_used; /* Protocol used, if any */ @@ -728,6 +732,16 @@ ic_dhcp_init_options(u8 *options) memcpy(e, vendor_class_identifier, len); e += len; } + len = strlen(dhcp_client_identifier + 1); + /* the minimum length of identifier is 2, include 1 byte type, + * and can not be larger than the length of options + */ + if (len >= 1 && len < 312 - (e - options) - 1) { + *e++ = 61; + *e++ = len + 1; + memcpy(e, dhcp_client_identifier, len + 1); + e += len + 1; + } } *e++ = 255; /* End of the list */ @@ -1557,8 +1571,24 @@ static int __init ic_proto_name(char *name) return 0; } #ifdef CONFIG_IP_PNP_DHCP - else if (!strcmp(name, "dhcp")) { + else if (!strncmp(name, "dhcp", 4)) { + char *client_id; + ic_proto_enabled &= ~IC_RARP; + client_id = strstr(name, "dhcp,"); + if (client_id) { + char *v; + + client_id = client_id + 5; + v = strchr(client_id, ','); + if (!v) + return 1; + *v = 0; + if (kstrtou8(client_id, 0, dhcp_client_identifier)) + DBG("DHCP: Invalid client identifier type\n"); + strncpy(dhcp_client_identifier + 1, v + 1, 251); + *v = ','; + } return 1; } #endif diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 2dad3e1c5f11..11dccba474b7 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -186,7 +186,7 @@ static inline int arp_packet_match(const struct arphdr *arphdr, if (FWINV(ret != 0, ARPT_INV_VIA_IN)) { dprintf("VIA in mismatch (%s vs %s).%s\n", indev, arpinfo->iniface, - arpinfo->invflags&ARPT_INV_VIA_IN ?" (INV)":""); + arpinfo->invflags & ARPT_INV_VIA_IN ? " (INV)" : ""); return 0; } @@ -195,7 +195,7 @@ static inline int arp_packet_match(const struct arphdr *arphdr, if (FWINV(ret != 0, ARPT_INV_VIA_OUT)) { dprintf("VIA out mismatch (%s vs %s).%s\n", outdev, arpinfo->outiface, - arpinfo->invflags&ARPT_INV_VIA_OUT ?" (INV)":""); + arpinfo->invflags & ARPT_INV_VIA_OUT ? " (INV)" : ""); return 0; } @@ -468,7 +468,7 @@ static int mark_source_chains(const struct xt_table_info *newinfo, pos = newpos; } } - next: +next: duprintf("Finished chain %u\n", hook); } return 1; @@ -632,7 +632,7 @@ static inline void cleanup_entry(struct arpt_entry *e) * newinfo). */ static int translate_table(struct xt_table_info *newinfo, void *entry0, - const struct arpt_replace *repl) + const struct arpt_replace *repl) { struct arpt_entry *iter; unsigned int i; @@ -892,7 +892,7 @@ static int compat_table_info(const struct xt_table_info *info, #endif static int get_info(struct net *net, void __user *user, - const int *len, int compat) + const int *len, int compat) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; @@ -1069,7 +1069,7 @@ static int __do_replace(struct net *net, const char *name, } static int do_replace(struct net *net, const void __user *user, - unsigned int len) + unsigned int len) { int ret; struct arpt_replace tmp; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 42d0946956db..b99affad6ba1 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -102,7 +102,7 @@ ip_packet_match(const struct iphdr *ip, if (FWINV(ret != 0, IPT_INV_VIA_IN)) { dprintf("VIA in mismatch (%s vs %s).%s\n", indev, ipinfo->iniface, - ipinfo->invflags&IPT_INV_VIA_IN ?" (INV)":""); + ipinfo->invflags & IPT_INV_VIA_IN ? " (INV)" : ""); return false; } @@ -111,7 +111,7 @@ ip_packet_match(const struct iphdr *ip, if (FWINV(ret != 0, IPT_INV_VIA_OUT)) { dprintf("VIA out mismatch (%s vs %s).%s\n", outdev, ipinfo->outiface, - ipinfo->invflags&IPT_INV_VIA_OUT ?" (INV)":""); + ipinfo->invflags & IPT_INV_VIA_OUT ? " (INV)" : ""); return false; } @@ -120,7 +120,7 @@ ip_packet_match(const struct iphdr *ip, FWINV(ip->protocol != ipinfo->proto, IPT_INV_PROTO)) { dprintf("Packet protocol %hi does not match %hi.%s\n", ip->protocol, ipinfo->proto, - ipinfo->invflags&IPT_INV_PROTO ? " (INV)":""); + ipinfo->invflags & IPT_INV_PROTO ? " (INV)" : ""); return false; } @@ -431,8 +431,8 @@ ipt_do_table(struct sk_buff *skb, } while (!acpar.hotdrop); pr_debug("Exiting %s; sp at %u\n", __func__, stackidx); - xt_write_recseq_end(addend); - local_bh_enable(); + xt_write_recseq_end(addend); + local_bh_enable(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; @@ -484,7 +484,7 @@ mark_source_chains(const struct xt_table_info *newinfo, unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, - XT_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", @@ -549,7 +549,7 @@ mark_source_chains(const struct xt_table_info *newinfo, pos = newpos; } } - next: +next: duprintf("Finished chain %u\n", hook); } return 1; @@ -804,7 +804,7 @@ cleanup_entry(struct ipt_entry *e, struct net *net) newinfo) */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, - const struct ipt_replace *repl) + const struct ipt_replace *repl) { struct ipt_entry *iter; unsigned int i; @@ -1078,7 +1078,7 @@ static int compat_table_info(const struct xt_table_info *info, #endif static int get_info(struct net *net, void __user *user, - const int *len, int compat) + const int *len, int compat) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; @@ -1304,7 +1304,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len) static int do_add_counters(struct net *net, const void __user *user, - unsigned int len, int compat) + unsigned int len, int compat) { unsigned int i; struct xt_counters_info tmp; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 3f32c03e8b2e..4a9e6db9df8d 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -492,14 +492,14 @@ static void arp_print(struct arp_payload *payload) { #define HBUFFERLEN 30 char hbuffer[HBUFFERLEN]; - int j,k; + int j, k; - for (k=0, j=0; k < HBUFFERLEN-3 && j < ETH_ALEN; j++) { + for (k = 0, j = 0; k < HBUFFERLEN - 3 && j < ETH_ALEN; j++) { hbuffer[k++] = hex_asc_hi(payload->src_hw[j]); hbuffer[k++] = hex_asc_lo(payload->src_hw[j]); - hbuffer[k++]=':'; + hbuffer[k++] = ':'; } - hbuffer[--k]='\0'; + hbuffer[--k] = '\0'; pr_debug("src %pI4@%s, dst %pI4\n", &payload->src_ip, hbuffer, &payload->dst_ip); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index f1a8df8ecc1f..5fdc556514ba 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -231,7 +231,7 @@ synproxy_send_client_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, - niph, nth, tcp_hdr_size); + niph, nth, tcp_hdr_size); } static bool @@ -437,14 +437,12 @@ static struct xt_target synproxy_tg4_reg __read_mostly = { static struct nf_hook_ops ipv4_synproxy_ops[] __read_mostly = { { .hook = ipv4_synproxy_hook, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, }, { .hook = ipv4_synproxy_hook, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, diff --git a/net/ipv4/netfilter/ipt_ah.c b/net/ipv4/netfilter/ipt_ah.c index 14a2aa8b8a14..a787d07f6cb7 100644 --- a/net/ipv4/netfilter/ipt_ah.c +++ b/net/ipv4/netfilter/ipt_ah.c @@ -25,7 +25,7 @@ spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert) bool r; pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n", invert ? '!' : ' ', min, spi, max); - r=(spi >= min && spi <= max) ^ invert; + r = (spi >= min && spi <= max) ^ invert; pr_debug(" result %s\n", r ? "PASS" : "FAILED"); return r; } diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 3a2e4d830a0b..ae2cd2752046 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -68,7 +68,6 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = { /* Before packet filtering, change destination */ { .hook = iptable_nat_ipv4_in, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, @@ -76,7 +75,6 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = { /* After packet filtering, change source */ { .hook = iptable_nat_ipv4_out, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC, @@ -84,7 +82,6 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = { /* Before packet filtering, change destination */ { .hook = iptable_nat_ipv4_local_fn, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST, @@ -92,7 +89,6 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = { /* After packet filtering, change source */ { .hook = iptable_nat_ipv4_fn, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index f534e2f05bad..c2e23d5e9cd4 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -79,7 +79,7 @@ static int __init iptable_security_init(void) int ret; ret = register_pernet_subsys(&iptable_security_net_ops); - if (ret < 0) + if (ret < 0) return ret; sectbl_ops = xt_hook_link(&security_table, iptable_security_hook); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 752fb40adcf8..461ca926fd39 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -166,42 +166,36 @@ static unsigned int ipv4_conntrack_local(void *priv, static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = { { .hook = ipv4_conntrack_in, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_CONNTRACK, }, { .hook = ipv4_conntrack_local, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_CONNTRACK, }, { .hook = ipv4_helper, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_HELPER, }, { .hook = ipv4_confirm, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_CONFIRM, }, { .hook = ipv4_helper, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_CONNTRACK_HELPER, }, { .hook = ipv4_confirm, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_CONNTRACK_CONFIRM, diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index bf25f45b23d2..0e5591c2ee9f 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -95,14 +95,12 @@ static unsigned int ipv4_conntrack_defrag(void *priv, static struct nf_hook_ops ipv4_defrag_ops[] = { { .hook = ipv4_conntrack_defrag, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_CONNTRACK_DEFRAG, }, { .hook = ipv4_conntrack_defrag, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_CONNTRACK_DEFRAG, diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 7c676671329d..ddb894ac1458 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1156,7 +1156,7 @@ static int snmp_parse_mangle(unsigned char *msg, } if (obj->type == SNMP_IPADDR) - mangle_address(ctx.begin, ctx.pointer - 4 , map, check); + mangle_address(ctx.begin, ctx.pointer - 4, map, check); kfree(obj->id); kfree(obj); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 30a531ccbf77..25300c5e283b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -496,6 +496,13 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { + .procname = "tcp_recovery", + .data = &sysctl_tcp_recovery, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "tcp_reordering", .data = &sysctl_tcp_reordering, .maxlen = sizeof(int), @@ -577,6 +584,13 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { + .procname = "tcp_min_rtt_wlen", + .data = &sysctl_tcp_min_rtt_wlen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "tcp_low_latency", .data = &sysctl_tcp_low_latency, .maxlen = sizeof(int), @@ -818,13 +832,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .procname = "icmp_redirects_use_orig_daddr", - .data = &init_net.ipv4.sysctl_icmp_redirects_use_orig_daddr, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "icmp_ratelimit", .data = &init_net.ipv4.sysctl_icmp_ratelimit, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ac1bdbb50352..0cfa7c0c1e80 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -388,6 +388,7 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); + tp->rtt_min[0].rtt = ~0U; /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3b35c3f4d268..fdd88c3803a6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -95,6 +95,7 @@ int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; int sysctl_tcp_max_orphans __read_mostly = NR_FILE; int sysctl_tcp_frto __read_mostly = 2; +int sysctl_tcp_min_rtt_wlen __read_mostly = 300; int sysctl_tcp_thin_dupack __read_mostly; @@ -880,6 +881,7 @@ static void tcp_update_reordering(struct sock *sk, const int metric, if (metric > 0) tcp_disable_early_retrans(tp); + tp->rack.reord = 1; } /* This must be called before lost_out is incremented */ @@ -905,8 +907,7 @@ static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb) } } -static void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, - struct sk_buff *skb) +void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb) { tcp_verify_retransmit_hint(tp, skb); @@ -1047,70 +1048,6 @@ static bool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack, return !before(start_seq, end_seq - tp->max_window); } -/* Check for lost retransmit. This superb idea is borrowed from "ratehalving". - * Event "B". Later note: FACK people cheated me again 8), we have to account - * for reordering! Ugly, but should help. - * - * Search retransmitted skbs from write_queue that were sent when snd_nxt was - * less than what is now known to be received by the other end (derived from - * highest SACK block). Also calculate the lowest snd_nxt among the remaining - * retransmitted skbs to avoid some costly processing per ACKs. - */ -static void tcp_mark_lost_retrans(struct sock *sk, int *flag) -{ - const struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - int cnt = 0; - u32 new_low_seq = tp->snd_nxt; - u32 received_upto = tcp_highest_sack_seq(tp); - - if (!tcp_is_fack(tp) || !tp->retrans_out || - !after(received_upto, tp->lost_retrans_low) || - icsk->icsk_ca_state != TCP_CA_Recovery) - return; - - tcp_for_write_queue(skb, sk) { - u32 ack_seq = TCP_SKB_CB(skb)->ack_seq; - - if (skb == tcp_send_head(sk)) - break; - if (cnt == tp->retrans_out) - break; - if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) - continue; - - if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)) - continue; - - /* TODO: We would like to get rid of tcp_is_fack(tp) only - * constraint here (see above) but figuring out that at - * least tp->reordering SACK blocks reside between ack_seq - * and received_upto is not easy task to do cheaply with - * the available datastructures. - * - * Whether FACK should check here for tp->reordering segs - * in-between one could argue for either way (it would be - * rather simple to implement as we could count fack_count - * during the walk and do tp->fackets_out - fack_count). - */ - if (after(received_upto, ack_seq)) { - TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; - tp->retrans_out -= tcp_skb_pcount(skb); - *flag |= FLAG_LOST_RETRANS; - tcp_skb_mark_lost_uncond_verify(tp, skb); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT); - } else { - if (before(ack_seq, new_low_seq)) - new_low_seq = ack_seq; - cnt += tcp_skb_pcount(skb); - } - } - - if (tp->retrans_out) - tp->lost_retrans_low = new_low_seq; -} - static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, struct tcp_sack_block_wire *sp, int num_sacks, u32 prior_snd_una) @@ -1236,6 +1173,8 @@ static u8 tcp_sacktag_one(struct sock *sk, return sacked; if (!(sacked & TCPCB_SACKED_ACKED)) { + tcp_rack_advance(tp, xmit_time, sacked); + if (sacked & TCPCB_SACKED_RETRANS) { /* If the segment is not tagged as lost, * we do not clear RETRANS, believing @@ -1837,7 +1776,6 @@ advance_sp: ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) tcp_update_reordering(sk, tp->fackets_out - state->reord, 0); - tcp_mark_lost_retrans(sk, &state->flag); tcp_verify_left_out(tp); out: @@ -2314,14 +2252,29 @@ static inline void tcp_moderate_cwnd(struct tcp_sock *tp) tp->snd_cwnd_stamp = tcp_time_stamp; } +static bool tcp_tsopt_ecr_before(const struct tcp_sock *tp, u32 when) +{ + return tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && + before(tp->rx_opt.rcv_tsecr, when); +} + +/* skb is spurious retransmitted if the returned timestamp echo + * reply is prior to the skb transmission time + */ +static bool tcp_skb_spurious_retrans(const struct tcp_sock *tp, + const struct sk_buff *skb) +{ + return (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) && + tcp_tsopt_ecr_before(tp, tcp_skb_timestamp(skb)); +} + /* Nothing was retransmitted or returned timestamp is less * than timestamp of the first retransmission. */ static inline bool tcp_packet_delayed(const struct tcp_sock *tp) { return !tp->retrans_stamp || - (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && - before(tp->rx_opt.rcv_tsecr, tp->retrans_stamp)); + tcp_tsopt_ecr_before(tp, tp->retrans_stamp); } /* Undo procedures. */ @@ -2853,6 +2806,11 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, } } + /* Use RACK to detect loss */ + if (sysctl_tcp_recovery & TCP_RACK_LOST_RETRANS && + tcp_rack_mark_lost(sk)) + flag |= FLAG_LOST_RETRANS; + /* E. Process state. */ switch (icsk->icsk_ca_state) { case TCP_CA_Recovery: @@ -2915,8 +2873,69 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, tcp_xmit_retransmit_queue(sk); } +/* Kathleen Nichols' algorithm for tracking the minimum value of + * a data stream over some fixed time interval. (E.g., the minimum + * RTT over the past five minutes.) It uses constant space and constant + * time per update yet almost always delivers the same minimum as an + * implementation that has to keep all the data in the window. + * + * The algorithm keeps track of the best, 2nd best & 3rd best min + * values, maintaining an invariant that the measurement time of the + * n'th best >= n-1'th best. It also makes sure that the three values + * are widely separated in the time window since that bounds the worse + * case error when that data is monotonically increasing over the window. + * + * Upon getting a new min, we can forget everything earlier because it + * has no value - the new min is <= everything else in the window by + * definition and it's the most recent. So we restart fresh on every new min + * and overwrites 2nd & 3rd choices. The same property holds for 2nd & 3rd + * best. + */ +static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) +{ + const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ; + struct rtt_meas *m = tcp_sk(sk)->rtt_min; + struct rtt_meas rttm = { .rtt = (rtt_us ? : 1), .ts = now }; + u32 elapsed; + + /* Check if the new measurement updates the 1st, 2nd, or 3rd choices */ + if (unlikely(rttm.rtt <= m[0].rtt)) + m[0] = m[1] = m[2] = rttm; + else if (rttm.rtt <= m[1].rtt) + m[1] = m[2] = rttm; + else if (rttm.rtt <= m[2].rtt) + m[2] = rttm; + + elapsed = now - m[0].ts; + if (unlikely(elapsed > wlen)) { + /* Passed entire window without a new min so make 2nd choice + * the new min & 3rd choice the new 2nd. So forth and so on. + */ + m[0] = m[1]; + m[1] = m[2]; + m[2] = rttm; + if (now - m[0].ts > wlen) { + m[0] = m[1]; + m[1] = rttm; + if (now - m[0].ts > wlen) + m[0] = rttm; + } + } else if (m[1].ts == m[0].ts && elapsed > wlen / 4) { + /* Passed a quarter of the window without a new min so + * take 2nd choice from the 2nd quarter of the window. + */ + m[2] = m[1] = rttm; + } else if (m[2].ts == m[1].ts && elapsed > wlen / 2) { + /* Passed half the window without a new min so take the 3rd + * choice from the last half of the window. + */ + m[2] = rttm; + } +} + static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, - long seq_rtt_us, long sack_rtt_us) + long seq_rtt_us, long sack_rtt_us, + long ca_rtt_us) { const struct tcp_sock *tp = tcp_sk(sk); @@ -2925,9 +2944,6 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * Karn's algorithm forbids taking RTT if some retransmitted data * is acked (RFC6298). */ - if (flag & FLAG_RETRANS_DATA_ACKED) - seq_rtt_us = -1L; - if (seq_rtt_us < 0) seq_rtt_us = sack_rtt_us; @@ -2939,11 +2955,16 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, */ if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) - seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - tp->rx_opt.rcv_tsecr); - + seq_rtt_us = ca_rtt_us = jiffies_to_usecs(tcp_time_stamp - + tp->rx_opt.rcv_tsecr); if (seq_rtt_us < 0) return false; + /* ca_rtt_us >= 0 is counting on the invariant that ca_rtt_us is + * always taken together with ACK, SACK, or TS-opts. Any negative + * values will be skipped with the seq_rtt_us < 0 check above. + */ + tcp_update_rtt_min(sk, ca_rtt_us); tcp_rtt_estimator(sk, seq_rtt_us); tcp_set_rto(sk); @@ -2964,7 +2985,7 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) rtt_us = skb_mstamp_us_delta(&now, &tcp_rsk(req)->snt_synack); } - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L); + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L, rtt_us); } @@ -3131,6 +3152,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (sacked & TCPCB_SACKED_ACKED) tp->sacked_out -= acked_pcount; + else if (tcp_is_sack(tp) && !tcp_skb_spurious_retrans(tp, skb)) + tcp_rack_advance(tp, &skb->skb_mstamp, sacked); if (sacked & TCPCB_LOST) tp->lost_out -= acked_pcount; @@ -3169,7 +3192,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, flag |= FLAG_SACK_RENEGING; skb_mstamp_get(&now); - if (likely(first_ackt.v64)) { + if (likely(first_ackt.v64) && !(flag & FLAG_RETRANS_DATA_ACKED)) { seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt); ca_rtt_us = skb_mstamp_us_delta(&now, &last_ackt); } @@ -3178,7 +3201,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, ca_rtt_us = skb_mstamp_us_delta(&now, &sack->last_sackt); } - rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us); + rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us, + ca_rtt_us); if (flag & FLAG_ACKED) { tcp_rearm_rto(sk); @@ -6236,7 +6260,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, } if (fastopen_sk) { af_ops->send_synack(fastopen_sk, dst, &fl, req, - skb_get_queue_mapping(skb), &foc, false); + &foc, false); /* Add the child socket directly into the accept queue */ inet_csk_reqsk_queue_add(sk, req, fastopen_sk); sk->sk_data_ready(sk); @@ -6247,7 +6271,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (!want_cookie) inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); af_ops->send_synack(sk, dst, &fl, req, - skb_get_queue_mapping(skb), &foc, !want_cookie); + &foc, !want_cookie); if (want_cookie) goto drop_and_free; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ddb198392c7f..30dd45c1f568 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -324,7 +324,6 @@ void tcp_req_err(struct sock *sk, u32 seq) if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - reqsk_put(req); } else { /* * Still in SYN_RECV, just remove it silently. @@ -332,9 +331,10 @@ void tcp_req_err(struct sock *sk, u32 seq) * created socket, and POSIX does not want network * errors returned from accept(). */ - NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS); inet_csk_reqsk_queue_drop(req->rsk_listener, req); + NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS); } + reqsk_put(req); } EXPORT_SYMBOL(tcp_req_err); @@ -821,7 +821,6 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, - u16 queue_mapping, struct tcp_fastopen_cookie *foc, bool attach_req) { @@ -839,7 +838,6 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); - skb_set_queue_mapping(skb, queue_mapping); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, ireq->opt); @@ -1572,6 +1570,7 @@ int tcp_v4_rcv(struct sk_buff *skb) TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; +lookup: sk = __inet_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest); if (!sk) goto no_tcp_socket; @@ -1587,8 +1586,12 @@ process: sk = req->rsk_listener; if (tcp_v4_inbound_md5_hash(sk, skb)) goto discard_and_relse; - if (sk->sk_state == TCP_LISTEN) + if (likely(sk->sk_state == TCP_LISTEN)) { nsk = tcp_check_req(sk, skb, req, false); + } else { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } if (!nsk) { reqsk_put(req); goto discard_it; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 41828bdc5d32..1fd5d413a664 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -470,6 +470,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->srtt_us = 0; newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); + newtp->rtt_min[0].rtt = ~0U; newicsk->icsk_rto = TCP_TIMEOUT_INIT; newtp->packets_out = 0; @@ -547,6 +548,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, tcp_ecn_openreq_child(newtp, req); newtp->fastopen_rsk = NULL; newtp->syn_data_acked = 0; + newtp->rack.mstamp.v64 = 0; + newtp->rack.advanced = 0; newtp->saved_syn = req->saved_syn; req->saved_syn = NULL; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6e79fcb0addb..f6f7f9b4901b 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2655,8 +2655,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) net_dbg_ratelimited("retrans_out leaked\n"); } #endif - if (!tp->retrans_out) - tp->lost_retrans_low = tp->snd_nxt; TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS; tp->retrans_out += tcp_skb_pcount(skb); @@ -2664,10 +2662,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (!tp->retrans_stamp) tp->retrans_stamp = tcp_skb_timestamp(skb); - /* snd_nxt is stored to detect loss of retransmitted segment, - * see tcp_input.c tcp_sacktag_write_queue(). - */ - TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt; } else if (err != -EBUSY) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); } @@ -3518,7 +3512,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) int res; tcp_rsk(req)->txhash = net_tx_rndhash(); - res = af_ops->send_synack(sk, NULL, &fl, req, 0, NULL, true); + res = af_ops->send_synack(sk, NULL, &fl, req, NULL, true); if (!res) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c new file mode 100644 index 000000000000..5353085fd0b2 --- /dev/null +++ b/net/ipv4/tcp_recovery.c @@ -0,0 +1,109 @@ +#include <linux/tcp.h> +#include <net/tcp.h> + +int sysctl_tcp_recovery __read_mostly = TCP_RACK_LOST_RETRANS; + +/* Marks a packet lost, if some packet sent later has been (s)acked. + * The underlying idea is similar to the traditional dupthresh and FACK + * but they look at different metrics: + * + * dupthresh: 3 OOO packets delivered (packet count) + * FACK: sequence delta to highest sacked sequence (sequence space) + * RACK: sent time delta to the latest delivered packet (time domain) + * + * The advantage of RACK is it applies to both original and retransmitted + * packet and therefore is robust against tail losses. Another advantage + * is being more resilient to reordering by simply allowing some + * "settling delay", instead of tweaking the dupthresh. + * + * The current version is only used after recovery starts but can be + * easily extended to detect the first loss. + */ +int tcp_rack_mark_lost(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + u32 reo_wnd, prior_retrans = tp->retrans_out; + + if (inet_csk(sk)->icsk_ca_state < TCP_CA_Recovery || !tp->rack.advanced) + return 0; + + /* Reset the advanced flag to avoid unnecessary queue scanning */ + tp->rack.advanced = 0; + + /* To be more reordering resilient, allow min_rtt/4 settling delay + * (lower-bounded to 1000uS). We use min_rtt instead of the smoothed + * RTT because reordering is often a path property and less related + * to queuing or delayed ACKs. + * + * TODO: measure and adapt to the observed reordering delay, and + * use a timer to retransmit like the delayed early retransmit. + */ + reo_wnd = 1000; + if (tp->rack.reord && tcp_min_rtt(tp) != ~0U) + reo_wnd = max(tcp_min_rtt(tp) >> 2, reo_wnd); + + tcp_for_write_queue(skb, sk) { + struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + + if (skb == tcp_send_head(sk)) + break; + + /* Skip ones already (s)acked */ + if (!after(scb->end_seq, tp->snd_una) || + scb->sacked & TCPCB_SACKED_ACKED) + continue; + + if (skb_mstamp_after(&tp->rack.mstamp, &skb->skb_mstamp)) { + + if (skb_mstamp_us_delta(&tp->rack.mstamp, + &skb->skb_mstamp) <= reo_wnd) + continue; + + /* skb is lost if packet sent later is sacked */ + tcp_skb_mark_lost_uncond_verify(tp, skb); + if (scb->sacked & TCPCB_SACKED_RETRANS) { + scb->sacked &= ~TCPCB_SACKED_RETRANS; + tp->retrans_out -= tcp_skb_pcount(skb); + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPLOSTRETRANSMIT); + } + } else if (!(scb->sacked & TCPCB_RETRANS)) { + /* Original data are sent sequentially so stop early + * b/c the rest are all sent after rack_sent + */ + break; + } + } + return prior_retrans - tp->retrans_out; +} + +/* Record the most recently (re)sent time among the (s)acked packets */ +void tcp_rack_advance(struct tcp_sock *tp, + const struct skb_mstamp *xmit_time, u8 sacked) +{ + if (tp->rack.mstamp.v64 && + !skb_mstamp_after(xmit_time, &tp->rack.mstamp)) + return; + + if (sacked & TCPCB_RETRANS) { + struct skb_mstamp now; + + /* If the sacked packet was retransmitted, it's ambiguous + * whether the retransmission or the original (or the prior + * retransmission) was sacked. + * + * If the original is lost, there is no ambiguity. Otherwise + * we assume the original can be delayed up to aRTT + min_rtt. + * the aRTT term is bounded by the fast recovery or timeout, + * so it's at least one RTT (i.e., retransmission is at least + * an RTT later). + */ + skb_mstamp_get(&now); + if (skb_mstamp_us_delta(&now, xmit_time) < tcp_min_rtt(tp)) + return; + } + + tp->rack.mstamp = *xmit_time; + tp->rack.advanced = 1; +} diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c8380f1876f1..d0c685cdc345 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -81,6 +81,7 @@ #include <net/ip.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/l3mdev.h> #include <linux/if_tunnel.h> #include <linux/rtnetlink.h> #include <linux/netconf.h> @@ -2146,7 +2147,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, unsigned long expires, u32 flags) { struct fib6_config cfg = { - .fc_table = RT6_TABLE_PREFIX, + .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX, .fc_metric = IP6_RT_PRIO_ADDRCONF, .fc_ifindex = dev->ifindex, .fc_expires = expires, @@ -2179,8 +2180,9 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, struct fib6_node *fn; struct rt6_info *rt = NULL; struct fib6_table *table; + u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX; - table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX); + table = fib6_get_table(dev_net(dev), tb_id); if (!table) return NULL; @@ -2211,7 +2213,7 @@ out: static void addrconf_add_mroute(struct net_device *dev) { struct fib6_config cfg = { - .fc_table = RT6_TABLE_LOCAL, + .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_LOCAL, .fc_metric = IP6_RT_PRIO_ADDRCONF, .fc_ifindex = dev->ifindex, .fc_dst_len = 8, @@ -3029,6 +3031,10 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) { struct in6_addr addr; + /* no link local addresses on L3 master devices */ + if (netif_is_l3_master(idev->dev)) + return; + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY) { @@ -3119,6 +3125,8 @@ static void addrconf_gre_config(struct net_device *dev) } addrconf_addr_gen(idev, true); + if (dev->flags & IFF_POINTOPOINT) + addrconf_add_mroute(dev); } #endif @@ -4780,7 +4788,8 @@ nla_put_failure: return -EMSGSIZE; } -static size_t inet6_get_link_af_size(const struct net_device *dev) +static size_t inet6_get_link_af_size(const struct net_device *dev, + u32 ext_filter_mask) { if (!__in6_dev_get(dev)) return 0; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 6c2b2132c8d3..efb1c00f2270 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -68,6 +68,7 @@ #include <net/xfrm.h> #include <net/inet_common.h> #include <net/dsfield.h> +#include <net/l3mdev.h> #include <asm/uaccess.h> @@ -496,6 +497,9 @@ 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; + if (!fl6.flowi6_oif) + fl6.flowi6_oif = l3mdev_master_ifindex(skb->dev); + dst = icmpv6_route_lookup(net, skb, sk, &fl6); if (IS_ERR(dst)) goto out; @@ -575,7 +579,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) fl6.daddr = ipv6_hdr(skb)->saddr; if (saddr) fl6.saddr = *saddr; - fl6.flowi6_oif = skb->dev->ifindex; + fl6.flowi6_oif = l3mdev_fib_oif(skb->dev); 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/ip6_fib.c b/net/ipv6/ip6_fib.c index 7d2e0023c72d..09fddf70cca4 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -264,6 +264,7 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) return NULL; } +EXPORT_SYMBOL_GPL(fib6_get_table); static void __net_init fib6_tables_init(struct net *net) { diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 08b62047c67f..eeca943f12dc 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -264,6 +264,9 @@ static int ipv6_gro_complete(struct sk_buff *skb, int nhoff) struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff); int err = -ENOSYS; + if (skb->encapsulation) + skb_set_inner_network_header(skb, nhoff); + iph->payload_len = htons(skb->len - nhoff - sizeof(*iph)); rcu_read_lock(); @@ -280,6 +283,13 @@ out_unlock: return err; } +static int sit_gro_complete(struct sk_buff *skb, int nhoff) +{ + skb->encapsulation = 1; + skb_shinfo(skb)->gso_type |= SKB_GSO_SIT; + return ipv6_gro_complete(skb, nhoff); +} + static struct packet_offload ipv6_packet_offload __read_mostly = { .type = cpu_to_be16(ETH_P_IPV6), .callbacks = { @@ -292,6 +302,8 @@ static struct packet_offload ipv6_packet_offload __read_mostly = { static const struct net_offload sit_offload = { .callbacks = { .gso_segment = ipv6_gso_segment, + .gro_receive = ipv6_gro_receive, + .gro_complete = sit_gro_complete, }, }; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 32583b507c2e..0c89671e0767 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -55,6 +55,7 @@ #include <net/xfrm.h> #include <net/checksum.h> #include <linux/mroute6.h> +#include <net/l3mdev.h> static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -388,6 +389,9 @@ int ip6_forward(struct sk_buff *skb) if (skb->pkt_type != PACKET_HOST) goto drop; + if (unlikely(skb->sk)) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -885,7 +889,8 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, #ifdef CONFIG_IPV6_SUBTREES ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) || #endif - (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) { + (!(fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) && + (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex))) { dst_release(dst); dst = NULL; } @@ -1037,7 +1042,7 @@ struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; if (!fl6->flowi6_oif) - fl6->flowi6_oif = dst->dev->ifindex; + fl6->flowi6_oif = l3mdev_fib_oif(dst->dev); return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index b18012f9f9fc..3e0f855e1bea 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -67,6 +67,7 @@ #include <net/flow.h> #include <net/ip6_checksum.h> #include <net/inet_common.h> +#include <net/l3mdev.h> #include <linux/proc_fs.h> #include <linux/netfilter.h> @@ -147,6 +148,7 @@ struct neigh_table nd_tbl = { .gc_thresh2 = 512, .gc_thresh3 = 1024, }; +EXPORT_SYMBOL_GPL(nd_tbl); static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data) { @@ -441,8 +443,11 @@ static void ndisc_send_skb(struct sk_buff *skb, if (!dst) { struct flowi6 fl6; + int oif = l3mdev_fib_oif(skb->dev); - icmpv6_flow_init(sk, &fl6, type, saddr, daddr, skb->dev->ifindex); + icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif); + if (oif != skb->dev->ifindex) + fl6.flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC; dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { kfree_skb(skb); @@ -766,7 +771,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { - +have_ifp: if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { if (dad) { /* @@ -792,6 +797,18 @@ static void ndisc_recv_ns(struct sk_buff *skb) } else { struct net *net = dev_net(dev); + /* perhaps an address on the master device */ + if (netif_is_l3_slave(dev)) { + struct net_device *mdev; + + mdev = netdev_master_upper_dev_get_rcu(dev); + if (mdev) { + ifp = ipv6_get_ifaddr(net, &msg->target, mdev, 1); + if (ifp) + goto have_ifp; + } + } + idev = in6_dev_get(dev); if (!idev) { /* XXX: count this drop? */ @@ -1483,6 +1500,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) struct flowi6 fl6; int rd_len; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; + int oif = l3mdev_fib_oif(dev); bool ret; if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { @@ -1499,7 +1517,10 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) } icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT, - &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); + &saddr_buf, &ipv6_hdr(skb)->saddr, oif); + + if (oif != skb->dev->ifindex) + fl6.flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC; dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 80e3bd72b715..99425cf2819b 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -117,7 +117,7 @@ ip6_packet_match(const struct sk_buff *skb, if (FWINV(ret != 0, IP6T_INV_VIA_IN)) { dprintf("VIA in mismatch (%s vs %s).%s\n", indev, ip6info->iniface, - ip6info->invflags&IP6T_INV_VIA_IN ?" (INV)":""); + ip6info->invflags & IP6T_INV_VIA_IN ? " (INV)" : ""); return false; } @@ -126,14 +126,14 @@ ip6_packet_match(const struct sk_buff *skb, if (FWINV(ret != 0, IP6T_INV_VIA_OUT)) { dprintf("VIA out mismatch (%s vs %s).%s\n", outdev, ip6info->outiface, - ip6info->invflags&IP6T_INV_VIA_OUT ?" (INV)":""); + ip6info->invflags & IP6T_INV_VIA_OUT ? " (INV)" : ""); return false; } /* ... might want to do something with class and flowlabel here ... */ /* look for the desired protocol header */ - if((ip6info->flags & IP6T_F_PROTO)) { + if (ip6info->flags & IP6T_F_PROTO) { int protohdr; unsigned short _frag_off; @@ -151,9 +151,9 @@ ip6_packet_match(const struct sk_buff *skb, ip6info->proto); if (ip6info->proto == protohdr) { - if(ip6info->invflags & IP6T_INV_PROTO) { + if (ip6info->invflags & IP6T_INV_PROTO) return false; - } + return true; } @@ -443,8 +443,8 @@ ip6t_do_table(struct sk_buff *skb, break; } while (!acpar.hotdrop); - xt_write_recseq_end(addend); - local_bh_enable(); + xt_write_recseq_end(addend); + local_bh_enable(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; @@ -561,7 +561,7 @@ mark_source_chains(const struct xt_table_info *newinfo, pos = newpos; } } - next: +next: duprintf("Finished chain %u\n", hook); } return 1; @@ -816,7 +816,7 @@ static void cleanup_entry(struct ip6t_entry *e, struct net *net) newinfo) */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, - const struct ip6t_replace *repl) + const struct ip6t_replace *repl) { struct ip6t_entry *iter; unsigned int i; @@ -1090,7 +1090,7 @@ static int compat_table_info(const struct xt_table_info *info, #endif static int get_info(struct net *net, void __user *user, - const int *len, int compat) + const int *len, int compat) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; @@ -1152,7 +1152,7 @@ static int get_info(struct net *net, void __user *user, static int get_entries(struct net *net, struct ip6t_get_entries __user *uptr, - const int *len) + const int *len) { int ret; struct ip6t_get_entries get; diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index a10a2a9e9f94..3deed5860a42 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -244,7 +244,7 @@ synproxy_send_client_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, - niph, nth, tcp_hdr_size); + niph, nth, tcp_hdr_size); } static bool @@ -458,14 +458,12 @@ static struct xt_target synproxy_tg6_reg __read_mostly = { static struct nf_hook_ops ipv6_synproxy_ops[] __read_mostly = { { .hook = ipv6_synproxy_hook, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, }, { .hook = ipv6_synproxy_hook, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index abea175d5853..de2a10a565f5 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -70,7 +70,6 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { /* Before packet filtering, change destination */ { .hook = ip6table_nat_in, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, @@ -78,7 +77,6 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { /* After packet filtering, change source */ { .hook = ip6table_nat_out, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, @@ -86,7 +84,6 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { /* Before packet filtering, change destination */ { .hook = ip6table_nat_local_fn, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, @@ -94,7 +91,6 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { /* After packet filtering, change source */ { .hook = ip6table_nat_fn, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index dd83ad42f8f6..1aa5848764a7 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -187,42 +187,36 @@ static unsigned int ipv6_conntrack_local(void *priv, static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { { .hook = ipv6_conntrack_in, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_CONNTRACK, }, { .hook = ipv6_conntrack_local, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_CONNTRACK, }, { .hook = ipv6_helper, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_CONNTRACK_HELPER, }, { .hook = ipv6_confirm, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_LAST, }, { .hook = ipv6_helper, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_CONNTRACK_HELPER, }, { .hook = ipv6_confirm, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_LAST-1, diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index d3b797446cea..660bc10c7a9c 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -57,12 +57,12 @@ static const u_int8_t invmap[] = { [ICMPV6_ECHO_REQUEST - 128] = ICMPV6_ECHO_REPLY + 1, [ICMPV6_ECHO_REPLY - 128] = ICMPV6_ECHO_REQUEST + 1, [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_REPLY + 1, - [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_QUERY +1 + [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_QUERY + 1 }; static const u_int8_t noct_valid_new[] = { [ICMPV6_MGM_QUERY - 130] = 1, - [ICMPV6_MGM_REPORT -130] = 1, + [ICMPV6_MGM_REPORT - 130] = 1, [ICMPV6_MGM_REDUCTION - 130] = 1, [NDISC_ROUTER_SOLICITATION - 130] = 1, [NDISC_ROUTER_ADVERTISEMENT - 130] = 1, diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 2fb86a99bf5f..056f5d4a852a 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -59,7 +59,7 @@ struct nf_ct_frag6_skb_cb struct sk_buff *orig; }; -#define NFCT_FRAG6_CB(skb) ((struct nf_ct_frag6_skb_cb*)((skb)->cb)) +#define NFCT_FRAG6_CB(skb) ((struct nf_ct_frag6_skb_cb *)((skb)->cb)) static struct inet_frags nf_frags; @@ -445,7 +445,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) skb_reset_transport_header(head); skb_push(head, head->data - skb_network_header(head)); - for (fp=head->next; fp; fp = fp->next) { + for (fp = head->next; fp; fp = fp->next) { head->data_len += fp->len; head->len += fp->len; if (head->ip_summed != fp->ip_summed) diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index 5173a89a238e..4fdbed5ebfb6 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -85,14 +85,12 @@ static unsigned int ipv6_defrag(void *priv, static struct nf_hook_ops ipv6_defrag_ops[] = { { .hook = ipv6_defrag, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, }, { .hook = ipv6_defrag, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 7309e475f68b..e0f922b777e3 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -26,7 +26,7 @@ const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb, int tcphoff; proto = oip6h->nexthdr; - tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), + tcphoff = ipv6_skip_exthdr(oldskb, ((u8 *)(oip6h + 1) - oldskb->data), &proto, &frag_off); if ((tcphoff < 0) || (tcphoff > oldskb->len)) { @@ -224,7 +224,7 @@ static bool reject6_csum_ok(struct sk_buff *skb, int hook) return true; proto = ip6h->nexthdr; - thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); + thoff = ipv6_skip_exthdr(skb, ((u8 *)(ip6h + 1) - skb->data), &proto, &fo); if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) return false; diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c index 9df75bd7c94a..71d995ff3108 100644 --- a/net/ipv6/netfilter/nft_chain_route_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -61,11 +61,11 @@ static const struct nf_chain_type nft_chain_route_ipv6 = { .name = "route", .type = NFT_CHAIN_T_ROUTE, .family = NFPROTO_IPV6, - .owner = THIS_MODULE, + .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_LOCAL_OUT), .hooks = { - [NF_INET_LOCAL_OUT] = nf_route_table_hook, - }, + [NF_INET_LOCAL_OUT] = nf_route_table_hook, + }, }; static int __init nft_chain_route_init(void) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index db5b54ad5912..d0619632723a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -61,6 +61,7 @@ #include <net/nexthop.h> #include <net/lwtunnel.h> #include <net/ip_tunnels.h> +#include <net/l3mdev.h> #include <asm/uaccess.h> @@ -142,6 +143,9 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) struct net_device *loopback_dev = net->loopback_dev; int cpu; + if (dev == loopback_dev) + return; + for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); struct rt6_info *rt; @@ -151,14 +155,12 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) struct inet6_dev *rt_idev = rt->rt6i_idev; struct net_device *rt_dev = rt->dst.dev; - if (rt_idev && (rt_idev->dev == dev || !dev) && - rt_idev->dev != loopback_dev) { + if (rt_idev->dev == dev) { rt->rt6i_idev = in6_dev_get(loopback_dev); in6_dev_put(rt_idev); } - if (rt_dev && (rt_dev == dev || !dev) && - rt_dev != loopback_dev) { + if (rt_dev == dev) { rt->dst.dev = loopback_dev; dev_hold(rt->dst.dev); dev_put(rt_dev); @@ -247,12 +249,6 @@ static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, { } -static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst, - unsigned long old) -{ - return NULL; -} - static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, .destroy = ip6_dst_destroy, @@ -261,7 +257,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, .redirect = ip6_rt_blackhole_redirect, - .cow_metrics = ip6_rt_blackhole_cow_metrics, + .cow_metrics = dst_cow_metrics_generic, .neigh_lookup = ip6_neigh_lookup, }; @@ -318,6 +314,15 @@ static const struct rt6_info ip6_blk_hole_entry_template = { #endif +static void rt6_info_init(struct rt6_info *rt) +{ + struct dst_entry *dst = &rt->dst; + + memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); + INIT_LIST_HEAD(&rt->rt6i_siblings); + INIT_LIST_HEAD(&rt->rt6i_uncached); +} + /* allocate dst with ip6_dst_ops */ static struct rt6_info *__ip6_dst_alloc(struct net *net, struct net_device *dev, @@ -326,13 +331,9 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0, DST_OBSOLETE_FORCE_CHK, flags); - if (rt) { - struct dst_entry *dst = &rt->dst; + if (rt) + rt6_info_init(rt); - memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); - INIT_LIST_HEAD(&rt->rt6i_siblings); - INIT_LIST_HEAD(&rt->rt6i_uncached); - } return rt; } @@ -1044,6 +1045,9 @@ static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; + if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) + oif = 0; + redo_rt6_select: rt = rt6_select(fn, oif, strict); if (rt->rt6i_nsiblings) @@ -1141,7 +1145,7 @@ void ip6_route_input(struct sk_buff *skb) int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip_tunnel_info *tun_info; struct flowi6 fl6 = { - .flowi6_iif = skb->dev->ifindex, + .flowi6_iif = l3mdev_fib_oif(skb->dev), .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), @@ -1165,8 +1169,13 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, struct flowi6 *fl6) { + struct dst_entry *dst; int flags = 0; + dst = l3mdev_rt6_dst_by_oif(net, fl6); + if (dst) + return dst; + fl6->flowi6_iif = LOOPBACK_IFINDEX; if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) || @@ -1189,24 +1198,20 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0); if (rt) { - new = &rt->dst; - - memset(new + 1, 0, sizeof(*rt) - sizeof(*new)); + rt6_info_init(rt); + new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; - if (dst_metrics_read_only(&ort->dst)) - new->_metrics = ort->dst._metrics; - else - dst_copy_metrics(new, &ort->dst); + dst_copy_metrics(new, &ort->dst); rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); rt->rt6i_gateway = ort->rt6i_gateway; - rt->rt6i_flags = ort->rt6i_flags; + rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; rt->rt6i_metric = 0; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); @@ -2263,7 +2268,6 @@ static struct rt6_info *rt6_add_route_info(struct net *net, unsigned int pref) { struct fib6_config cfg = { - .fc_table = RT6_TABLE_INFO, .fc_metric = IP6_RT_PRIO_USER, .fc_ifindex = ifindex, .fc_dst_len = prefixlen, @@ -2274,6 +2278,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_nlinfo.nl_net = net, }; + cfg.fc_table = l3mdev_fib_table_by_index(net, ifindex) ? : RT6_TABLE_INFO; cfg.fc_dst = *prefix; cfg.fc_gateway = *gwaddr; @@ -2314,7 +2319,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, unsigned int pref) { struct fib6_config cfg = { - .fc_table = RT6_TABLE_DFLT, + .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, .fc_metric = IP6_RT_PRIO_USER, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | @@ -2361,7 +2366,8 @@ static void rtmsg_to_fib6_config(struct net *net, { memset(cfg, 0, sizeof(*cfg)); - cfg->fc_table = RT6_TABLE_MAIN; + cfg->fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ? + : RT6_TABLE_MAIN; cfg->fc_ifindex = rtmsg->rtmsg_ifindex; cfg->fc_metric = rtmsg->rtmsg_metric; cfg->fc_expires = rtmsg->rtmsg_info; @@ -2470,6 +2476,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, const struct in6_addr *addr, bool anycast) { + u32 tb_id; struct net *net = dev_net(idev->dev); struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, DST_NOCOUNT); @@ -2492,7 +2499,8 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_gateway = *addr; rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; - rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); + tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; + rt->rt6i_table = fib6_get_table(net, tb_id); rt->dst.flags |= DST_NOCACHE; atomic_set(&rt->dst.__refcnt, 1); @@ -2597,7 +2605,8 @@ void rt6_ifdown(struct net *net, struct net_device *dev) fib6_clean_all(net, fib6_ifdown, &adn); icmp6_clean_all(fib6_ifdown, &adn); - rt6_uncached_list_flush_dev(net, dev); + if (dev) + rt6_uncached_list_flush_dev(net, dev); } struct rt6_mtu_change_arg { @@ -3254,6 +3263,11 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) } else { fl6.flowi6_oif = oif; + if (netif_index_is_l3_master(net, oif)) { + fl6.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC | + FLOWI_FLAG_SKIP_NH_OIF; + } + rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2887c8474b65..f495d189f5e0 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -437,7 +437,6 @@ out: static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, - u16 queue_mapping, struct tcp_fastopen_cookie *foc, bool attach_req) { @@ -462,7 +461,6 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); - skb_set_queue_mapping(skb, queue_mapping); err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass); err = net_xmit_eval(err); } @@ -1363,6 +1361,7 @@ static int tcp_v6_rcv(struct sk_buff *skb) th = tcp_hdr(skb); hdr = ipv6_hdr(skb); +lookup: sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest, inet6_iif(skb)); if (!sk) @@ -1382,8 +1381,12 @@ process: reqsk_put(req); goto discard_it; } - if (sk->sk_state == TCP_LISTEN) + if (likely(sk->sk_state == TCP_LISTEN)) { nsk = tcp_check_req(sk, skb, req, false); + } else { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } if (!nsk) { reqsk_put(req); goto discard_it; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 3636b45440ab..4d2aaebd4f97 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -151,7 +151,7 @@ static ssize_t hwflags_read(struct file *file, char __user *user_buf, for (i = 0; i < NUM_IEEE80211_HW_FLAGS; i++) { if (test_bit(i, local->hw.flags)) - pos += scnprintf(pos, end - pos, "%s", + pos += scnprintf(pos, end - pos, "%s\n", hw_flag_names[i]); } diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 7d14bbf8682b..5bad05e9af90 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -101,6 +101,7 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, * when it wakes up for the next time. */ set_sta_flag(sta, WLAN_STA_CLEAR_PS_FILT); + ieee80211_clear_fast_xmit(sta); /* * This code races in the following way: diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 09e38a860a59..bdc224d5053a 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1218,8 +1218,10 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, if (!tx->sta) info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT; - else if (test_and_clear_sta_flag(tx->sta, WLAN_STA_CLEAR_PS_FILT)) + else if (test_and_clear_sta_flag(tx->sta, WLAN_STA_CLEAR_PS_FILT)) { info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT; + ieee80211_check_fast_xmit(tx->sta); + } info->flags |= IEEE80211_TX_CTL_FIRST_FRAGMENT; @@ -2451,7 +2453,8 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) if (test_sta_flag(sta, WLAN_STA_PS_STA) || test_sta_flag(sta, WLAN_STA_PS_DRIVER) || - test_sta_flag(sta, WLAN_STA_PS_DELIVER)) + test_sta_flag(sta, WLAN_STA_PS_DELIVER) || + test_sta_flag(sta, WLAN_STA_CLEAR_PS_FILT)) goto out; if (sdata->noack_map) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 3e1b4abf1897..e22349ea7256 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -354,7 +354,7 @@ config NF_CT_NETLINK_HELPER select NETFILTER_NETLINK depends on NF_CT_NETLINK depends on NETFILTER_NETLINK_QUEUE - depends on NETFILTER_NETLINK_QUEUE_CT + depends on NETFILTER_NETLINK_GLUE_CT depends on NETFILTER_ADVANCED help This option enables the user-space connection tracking helpers @@ -362,13 +362,14 @@ config NF_CT_NETLINK_HELPER If unsure, say `N'. -config NETFILTER_NETLINK_QUEUE_CT - bool "NFQUEUE integration with Connection Tracking" - default n - depends on NETFILTER_NETLINK_QUEUE +config NETFILTER_NETLINK_GLUE_CT + bool "NFQUEUE and NFLOG integration with Connection Tracking" + default n + depends on (NETFILTER_NETLINK_QUEUE || NETFILTER_NETLINK_LOG) && NF_CT_NETLINK help - If this option is enabled, NFQUEUE can include Connection Tracking - information together with the packet is the enqueued via NFNETLINK. + If this option is enabled, NFQUEUE and NFLOG can include + Connection Tracking information together with the packet is + the enqueued via NFNETLINK. config NF_NAT tristate diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 70d026d46fe7..7638c36b498c 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -10,8 +10,6 @@ obj-$(CONFIG_NETFILTER) = netfilter.o obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o -nfnetlink_queue-y := nfnetlink_queue_core.o -nfnetlink_queue-$(CONFIG_NETFILTER_NETLINK_QUEUE_CT) += nfnetlink_queue_ct.o obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 2e907335ee81..09e661c3ae58 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -313,8 +313,6 @@ next_hook: int err = nf_queue(skb, elem, state, verdict >> NF_VERDICT_QBITS); if (err < 0) { - if (err == -ECANCELED) - goto next_hook; if (err == -ESRCH && (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) goto next_hook; @@ -348,6 +346,12 @@ int skb_make_writable(struct sk_buff *skb, unsigned int writable_len) } EXPORT_SYMBOL(skb_make_writable); +/* This needs to be compiled in any case to avoid dependencies between the + * nfnetlink_queue code and nf_conntrack. + */ +struct nfnl_ct_hook __rcu *nfnl_ct_hook __read_mostly; +EXPORT_SYMBOL_GPL(nfnl_ct_hook); + #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* This does not belong here, but locally generated errors need it if connection tracking in use: without this, connection may not be in hash table, and hence @@ -385,9 +389,6 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct) } EXPORT_SYMBOL(nf_conntrack_destroy); -struct nfq_ct_hook __rcu *nfq_ct_hook __read_mostly; -EXPORT_SYMBOL_GPL(nfq_ct_hook); - /* Built-in default zone used e.g. by modules. */ const struct nf_conntrack_zone nf_ct_zone_dflt = { .id = NF_CT_DEFAULT_ZONE_ID, diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index d1d168c7fc68..85ca189bdc3d 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1347,23 +1347,20 @@ flush_again: */ int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs) { - struct net *net = ipvs->net; - atomic_set(&ipvs->conn_count, 0); - proc_create("ip_vs_conn", 0, net->proc_net, &ip_vs_conn_fops); - proc_create("ip_vs_conn_sync", 0, net->proc_net, &ip_vs_conn_sync_fops); + proc_create("ip_vs_conn", 0, ipvs->net->proc_net, &ip_vs_conn_fops); + proc_create("ip_vs_conn_sync", 0, ipvs->net->proc_net, + &ip_vs_conn_sync_fops); return 0; } void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs) { - struct net *net = ipvs->net; - /* flush all the connection entries first */ ip_vs_conn_flush(ipvs); - remove_proc_entry("ip_vs_conn", net->proc_net); - remove_proc_entry("ip_vs_conn_sync", net->proc_net); + remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); + remove_proc_entry("ip_vs_conn_sync", ipvs->net->proc_net); } int __init ip_vs_conn_init(void) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 07a791ecdfba..1e24fff53e4b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -547,7 +547,6 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, return cp; } -#ifdef CONFIG_SYSCTL static inline int ip_vs_addr_is_unicast(struct net *net, int af, union nf_inet_addr *addr) { @@ -557,7 +556,6 @@ static inline int ip_vs_addr_is_unicast(struct net *net, int af, #endif return (inet_addr_type(net, addr->ip) == RTN_UNICAST); } -#endif /* * Pass or drop the packet. @@ -1174,7 +1172,6 @@ drop: static unsigned int ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) { - struct net *net = ipvs->net; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; @@ -1274,7 +1271,7 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (!skb->dev) - skb->dev = net->loopback_dev; + skb->dev = ipvs->net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, @@ -1926,7 +1923,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply4, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 2, @@ -1936,7 +1932,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { * applied to IPVS. */ { .hook = ip_vs_remote_request4, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 1, @@ -1944,7 +1939,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_local_reply4, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 1, @@ -1952,7 +1946,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { /* After mangle, schedule and forward local requests */ { .hook = ip_vs_local_request4, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 2, @@ -1961,7 +1954,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 99, @@ -1969,7 +1961,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply4, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 100, @@ -1978,7 +1969,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 2, @@ -1988,7 +1978,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { * applied to IPVS. */ { .hook = ip_vs_remote_request6, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 1, @@ -1996,7 +1985,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_local_reply6, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, @@ -2004,7 +1992,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { /* After mangle, schedule and forward local requests */ { .hook = ip_vs_local_request6, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 2, @@ -2013,7 +2000,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp_v6, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 99, @@ -2021,7 +2007,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 100, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 09d1d19b2ab9..3cb3cb831591 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -940,10 +940,13 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL; - if (timeout_ext) - timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext); - else + if (timeout_ext) { + timeouts = nf_ct_timeout_data(timeout_ext); + if (unlikely(!timeouts)) + timeouts = l4proto->get_timeouts(net); + } else { timeouts = l4proto->get_timeouts(net); + } if (!l4proto->new(ct, skb, dataoff, timeouts)) { nf_conntrack_free(ct); @@ -952,7 +955,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } if (timeout_ext) - nf_ct_timeout_ext_add(ct, timeout_ext->timeout, GFP_ATOMIC); + nf_ct_timeout_ext_add(ct, rcu_dereference(timeout_ext->timeout), + GFP_ATOMIC); nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 94a66541e0b7..9f5272968abb 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2133,9 +2133,9 @@ ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask); -#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT +#ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT static size_t -ctnetlink_nfqueue_build_size(const struct nf_conn *ct) +ctnetlink_glue_build_size(const struct nf_conn *ct) { return 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ @@ -2162,8 +2162,19 @@ ctnetlink_nfqueue_build_size(const struct nf_conn *ct) ; } -static int -ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct) +static struct nf_conn *ctnetlink_glue_get_ct(const struct sk_buff *skb, + enum ip_conntrack_info *ctinfo) +{ + struct nf_conn *ct; + + ct = nf_ct_get(skb, ctinfo); + if (ct && nf_ct_is_untracked(ct)) + ct = NULL; + + return ct; +} + +static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; @@ -2236,7 +2247,32 @@ nla_put_failure: } static int -ctnetlink_nfqueue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) +ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + u_int16_t ct_attr, u_int16_t ct_info_attr) +{ + struct nlattr *nest_parms; + + nest_parms = nla_nest_start(skb, ct_attr | NLA_F_NESTED); + if (!nest_parms) + goto nla_put_failure; + + if (__ctnetlink_glue_build(skb, ct) < 0) + goto nla_put_failure; + + nla_nest_end(skb, nest_parms); + + if (nla_put_be32(skb, ct_info_attr, htonl(ctinfo))) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static int +ctnetlink_glue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) { int err; @@ -2276,7 +2312,7 @@ ctnetlink_nfqueue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) } static int -ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct) +ctnetlink_glue_parse(const struct nlattr *attr, struct nf_conn *ct) { struct nlattr *cda[CTA_MAX+1]; int ret; @@ -2286,16 +2322,16 @@ ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct) return ret; spin_lock_bh(&nf_conntrack_expect_lock); - ret = ctnetlink_nfqueue_parse_ct((const struct nlattr **)cda, ct); + ret = ctnetlink_glue_parse_ct((const struct nlattr **)cda, ct); spin_unlock_bh(&nf_conntrack_expect_lock); return ret; } -static int ctnetlink_nfqueue_exp_parse(const struct nlattr * const *cda, - const struct nf_conn *ct, - struct nf_conntrack_tuple *tuple, - struct nf_conntrack_tuple *mask) +static int ctnetlink_glue_exp_parse(const struct nlattr * const *cda, + const struct nf_conn *ct, + struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple *mask) { int err; @@ -2309,8 +2345,8 @@ static int ctnetlink_nfqueue_exp_parse(const struct nlattr * const *cda, } static int -ctnetlink_nfqueue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, - u32 portid, u32 report) +ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, + u32 portid, u32 report) { struct nlattr *cda[CTA_EXPECT_MAX+1]; struct nf_conntrack_tuple tuple, mask; @@ -2322,8 +2358,8 @@ ctnetlink_nfqueue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, if (err < 0) return err; - err = ctnetlink_nfqueue_exp_parse((const struct nlattr * const *)cda, - ct, &tuple, &mask); + err = ctnetlink_glue_exp_parse((const struct nlattr * const *)cda, + ct, &tuple, &mask); if (err < 0) return err; @@ -2350,14 +2386,24 @@ ctnetlink_nfqueue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, return 0; } -static struct nfq_ct_hook ctnetlink_nfqueue_hook = { - .build_size = ctnetlink_nfqueue_build_size, - .build = ctnetlink_nfqueue_build, - .parse = ctnetlink_nfqueue_parse, - .attach_expect = ctnetlink_nfqueue_attach_expect, - .seq_adjust = nf_ct_tcp_seqadj_set, +static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, int diff) +{ + if (!(ct->status & IPS_NAT_MASK)) + return; + + nf_ct_tcp_seqadj_set(skb, ct, ctinfo, diff); +} + +static struct nfnl_ct_hook ctnetlink_glue_hook = { + .get_ct = ctnetlink_glue_get_ct, + .build_size = ctnetlink_glue_build_size, + .build = ctnetlink_glue_build, + .parse = ctnetlink_glue_parse, + .attach_expect = ctnetlink_glue_attach_expect, + .seq_adjust = ctnetlink_glue_seqadj, }; -#endif /* CONFIG_NETFILTER_NETLINK_QUEUE_CT */ +#endif /* CONFIG_NETFILTER_NETLINK_GLUE_CT */ /*********************************************************************** * EXPECT @@ -3341,9 +3387,9 @@ static int __init ctnetlink_init(void) pr_err("ctnetlink_init: cannot register pernet operations\n"); goto err_unreg_exp_subsys; } -#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT +#ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT /* setup interaction between nf_queue and nf_conntrack_netlink. */ - RCU_INIT_POINTER(nfq_ct_hook, &ctnetlink_nfqueue_hook); + RCU_INIT_POINTER(nfnl_ct_hook, &ctnetlink_glue_hook); #endif return 0; @@ -3362,8 +3408,8 @@ static void __exit ctnetlink_exit(void) unregister_pernet_subsys(&ctnetlink_net_ops); nfnetlink_subsys_unregister(&ctnl_exp_subsys); nfnetlink_subsys_unregister(&ctnl_subsys); -#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT - RCU_INIT_POINTER(nfq_ct_hook, NULL); +#ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT + RCU_INIT_POINTER(nfnl_ct_hook, NULL); #endif } diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 34f628e16a4c..5baa8e24e6ac 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -69,19 +69,14 @@ void nf_queue_entry_release_refs(struct nf_queue_entry *entry) dev_put(physdev); } #endif - /* Drop reference to owner of hook which queued us. */ - module_put(entry->elem->owner); } EXPORT_SYMBOL_GPL(nf_queue_entry_release_refs); /* Bump dev refs so they don't vanish while packet is out */ -bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) +void nf_queue_entry_get_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; - if (!try_module_get(entry->elem->owner)) - return false; - if (state->in) dev_hold(state->in); if (state->out) @@ -100,8 +95,6 @@ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) dev_hold(physdev); } #endif - - return true; } EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); @@ -131,22 +124,20 @@ int nf_queue(struct sk_buff *skb, const struct nf_queue_handler *qh; /* QUEUE == DROP if no one is waiting, to be safe. */ - rcu_read_lock(); - qh = rcu_dereference(queue_handler); if (!qh) { status = -ESRCH; - goto err_unlock; + goto err; } afinfo = nf_get_afinfo(state->pf); if (!afinfo) - goto err_unlock; + goto err; entry = kmalloc(sizeof(*entry) + afinfo->route_key_size, GFP_ATOMIC); if (!entry) { status = -ENOMEM; - goto err_unlock; + goto err; } *entry = (struct nf_queue_entry) { @@ -156,16 +147,11 @@ int nf_queue(struct sk_buff *skb, .size = sizeof(*entry) + afinfo->route_key_size, }; - if (!nf_queue_entry_get_refs(entry)) { - status = -ECANCELED; - goto err_unlock; - } + nf_queue_entry_get_refs(entry); skb_dst_force(skb); afinfo->saveroute(skb, entry); status = qh->outfn(entry, queuenum); - rcu_read_unlock(); - if (status < 0) { nf_queue_entry_release_refs(entry); goto err; @@ -173,8 +159,6 @@ int nf_queue(struct sk_buff *skb, return 0; -err_unlock: - rcu_read_unlock(); err: kfree(entry); return status; @@ -187,15 +171,11 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) const struct nf_afinfo *afinfo; int err; - rcu_read_lock(); - nf_queue_entry_release_refs(entry); /* Continue traversal iff userspace said ok... */ - if (verdict == NF_REPEAT) { - elem = list_entry(elem->list.prev, struct nf_hook_ops, list); - verdict = NF_ACCEPT; - } + if (verdict == NF_REPEAT) + verdict = elem->hook(elem->priv, skb, &entry->state); if (verdict == NF_ACCEPT) { afinfo = nf_get_afinfo(entry->state.pf); @@ -222,8 +202,6 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) err = nf_queue(skb, elem, &entry->state, verdict >> NF_VERDICT_QBITS); if (err < 0) { - if (err == -ECANCELED) - goto next_hook; if (err == -ESRCH && (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) goto next_hook; @@ -235,7 +213,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) default: kfree_skb(skb); } - rcu_read_unlock(); + kfree(entry); } EXPORT_SYMBOL(nf_reinject); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4a41eb92bcc0..93cc4737018f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1433,7 +1433,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, for (i = 0; i < afi->nops; i++) { ops = &basechain->ops[i]; ops->pf = family; - ops->owner = afi->owner; ops->hooknum = hooknum; ops->priority = priority; ops->priv = chain; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 476accd17145..c7a2d0e1c462 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -291,6 +291,34 @@ cttimeout_get_timeout(struct sock *ctnl, struct sk_buff *skb, return ret; } +static void untimeout(struct nf_conntrack_tuple_hash *i, + struct ctnl_timeout *timeout) +{ + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i); + struct nf_conn_timeout *timeout_ext = nf_ct_timeout_find(ct); + + if (timeout_ext && (!timeout || timeout_ext->timeout == timeout)) + RCU_INIT_POINTER(timeout_ext->timeout, NULL); +} + +static void ctnl_untimeout(struct ctnl_timeout *timeout) +{ + struct nf_conntrack_tuple_hash *h; + const struct hlist_nulls_node *nn; + int i; + + local_bh_disable(); + for (i = 0; i < init_net.ct.htable_size; i++) { + spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + if (i < init_net.ct.htable_size) { + hlist_nulls_for_each_entry(h, nn, &init_net.ct.hash[i], hnnode) + untimeout(h, timeout); + } + spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + } + local_bh_enable(); +} + /* try to delete object, fail if it is still in use. */ static int ctnl_timeout_try_del(struct ctnl_timeout *timeout) { @@ -301,6 +329,7 @@ static int ctnl_timeout_try_del(struct ctnl_timeout *timeout) /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); nf_ct_l4proto_put(timeout->l4proto); + ctnl_untimeout(timeout); kfree_rcu(timeout, rcu_head); } else { /* still in use, restore reference counter. */ @@ -567,6 +596,10 @@ static void __exit cttimeout_exit(void) pr_info("cttimeout: unregistering from nfnetlink.\n"); nfnetlink_subsys_unregister(&cttimeout_subsys); + + /* Make sure no conntrack objects refer to custom timeouts anymore. */ + ctnl_untimeout(NULL); + list_for_each_entry_safe(cur, tmp, &cttimeout_list, head) { list_del_rcu(&cur->head); /* We are sure that our objects have no clients at this point, @@ -579,6 +612,7 @@ static void __exit cttimeout_exit(void) RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL); RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL); #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ + rcu_barrier(); } module_init(cttimeout_init); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index cc2300f4e177..06eb48fceb42 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -27,6 +27,7 @@ #include <net/netlink.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_log.h> +#include <linux/netfilter/nf_conntrack_common.h> #include <linux/spinlock.h> #include <linux/sysctl.h> #include <linux/proc_fs.h> @@ -401,7 +402,9 @@ __build_packet_message(struct nfnl_log_net *log, unsigned int hooknum, const struct net_device *indev, const struct net_device *outdev, - const char *prefix, unsigned int plen) + const char *prefix, unsigned int plen, + const struct nfnl_ct_hook *nfnl_ct, + struct nf_conn *ct, enum ip_conntrack_info ctinfo) { struct nfulnl_msg_packet_hdr pmsg; struct nlmsghdr *nlh; @@ -575,6 +578,10 @@ __build_packet_message(struct nfnl_log_net *log, htonl(atomic_inc_return(&log->global_seq)))) goto nla_put_failure; + if (ct && nfnl_ct->build(inst->skb, ct, ctinfo, + NFULA_CT, NFULA_CT_INFO) < 0) + goto nla_put_failure; + if (data_len) { struct nlattr *nla; int size = nla_attr_size(data_len); @@ -620,12 +627,16 @@ nfulnl_log_packet(struct net *net, const struct nf_loginfo *li_user, const char *prefix) { - unsigned int size, data_len; + size_t size; + unsigned int data_len; struct nfulnl_instance *inst; const struct nf_loginfo *li; unsigned int qthreshold; unsigned int plen; struct nfnl_log_net *log = nfnl_log_pernet(net); + const struct nfnl_ct_hook *nfnl_ct = NULL; + struct nf_conn *ct = NULL; + enum ip_conntrack_info uninitialized_var(ctinfo); if (li_user && li_user->type == NF_LOG_TYPE_ULOG) li = li_user; @@ -671,6 +682,14 @@ nfulnl_log_packet(struct net *net, size += nla_total_size(sizeof(u_int32_t)); if (inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) size += nla_total_size(sizeof(u_int32_t)); + if (inst->flags & NFULNL_CFG_F_CONNTRACK) { + nfnl_ct = rcu_dereference(nfnl_ct_hook); + if (nfnl_ct != NULL) { + ct = nfnl_ct->get_ct(skb, &ctinfo); + if (ct != NULL) + size += nfnl_ct->build_size(ct); + } + } qthreshold = inst->qthreshold; /* per-rule qthreshold overrides per-instance */ @@ -715,7 +734,8 @@ nfulnl_log_packet(struct net *net, inst->qlen++; __build_packet_message(log, inst, skb, data_len, pf, - hooknum, in, out, prefix, plen); + hooknum, in, out, prefix, plen, + nfnl_ct, ct, ctinfo); if (inst->qlen >= qthreshold) __nfulnl_flush(inst); @@ -805,6 +825,7 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, struct net *net = sock_net(ctnl); struct nfnl_log_net *log = nfnl_log_pernet(net); int ret = 0; + u16 flags; if (nfula[NFULA_CFG_CMD]) { u_int8_t pf = nfmsg->nfgen_family; @@ -826,6 +847,28 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, goto out_put; } + /* Check if we support these flags in first place, dependencies should + * be there too not to break atomicity. + */ + if (nfula[NFULA_CFG_FLAGS]) { + flags = ntohs(nla_get_be16(nfula[NFULA_CFG_FLAGS])); + + if ((flags & NFULNL_CFG_F_CONNTRACK) && + !rcu_access_pointer(nfnl_ct_hook)) { +#ifdef CONFIG_MODULES + nfnl_unlock(NFNL_SUBSYS_ULOG); + request_module("ip_conntrack_netlink"); + nfnl_lock(NFNL_SUBSYS_ULOG); + if (rcu_access_pointer(nfnl_ct_hook)) { + ret = -EAGAIN; + goto out_put; + } +#endif + ret = -EOPNOTSUPP; + goto out_put; + } + } + if (cmd != NULL) { switch (cmd->command) { case NFULNL_CFG_CMD_BIND: @@ -854,16 +897,15 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, ret = -ENOTSUPP; break; } + } else if (!inst) { + ret = -ENODEV; + goto out; } if (nfula[NFULA_CFG_MODE]) { - struct nfulnl_msg_config_mode *params; - params = nla_data(nfula[NFULA_CFG_MODE]); + struct nfulnl_msg_config_mode *params = + nla_data(nfula[NFULA_CFG_MODE]); - if (!inst) { - ret = -ENODEV; - goto out; - } nfulnl_set_mode(inst, params->copy_mode, ntohl(params->copy_range)); } @@ -871,42 +913,23 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, if (nfula[NFULA_CFG_TIMEOUT]) { __be32 timeout = nla_get_be32(nfula[NFULA_CFG_TIMEOUT]); - if (!inst) { - ret = -ENODEV; - goto out; - } nfulnl_set_timeout(inst, ntohl(timeout)); } if (nfula[NFULA_CFG_NLBUFSIZ]) { __be32 nlbufsiz = nla_get_be32(nfula[NFULA_CFG_NLBUFSIZ]); - if (!inst) { - ret = -ENODEV; - goto out; - } nfulnl_set_nlbufsiz(inst, ntohl(nlbufsiz)); } if (nfula[NFULA_CFG_QTHRESH]) { __be32 qthresh = nla_get_be32(nfula[NFULA_CFG_QTHRESH]); - if (!inst) { - ret = -ENODEV; - goto out; - } nfulnl_set_qthresh(inst, ntohl(qthresh)); } - if (nfula[NFULA_CFG_FLAGS]) { - __be16 flags = nla_get_be16(nfula[NFULA_CFG_FLAGS]); - - if (!inst) { - ret = -ENODEV; - goto out; - } - nfulnl_set_flags(inst, ntohs(flags)); - } + if (nfula[NFULA_CFG_FLAGS]) + nfulnl_set_flags(inst, flags); out_put: instance_put(inst); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue.c index 41583e30051b..7d81d280cb4f 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue.c @@ -28,12 +28,12 @@ #include <linux/netfilter_bridge.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_queue.h> +#include <linux/netfilter/nf_conntrack_common.h> #include <linux/list.h> #include <net/sock.h> #include <net/tcp_states.h> #include <net/netfilter/nf_queue.h> #include <net/netns/generic.h> -#include <net/netfilter/nfnetlink_queue.h> #include <linux/atomic.h> @@ -313,6 +313,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct net_device *outdev; struct nf_conn *ct = NULL; enum ip_conntrack_info uninitialized_var(ctinfo); + struct nfnl_ct_hook *nfnl_ct; bool csum_verify; char *secdata = NULL; u32 seclen = 0; @@ -364,8 +365,14 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, break; } - if (queue->flags & NFQA_CFG_F_CONNTRACK) - ct = nfqnl_ct_get(entskb, &size, &ctinfo); + if (queue->flags & NFQA_CFG_F_CONNTRACK) { + nfnl_ct = rcu_dereference(nfnl_ct_hook); + if (nfnl_ct != NULL) { + ct = nfnl_ct->get_ct(entskb, &ctinfo); + if (ct != NULL) + size += nfnl_ct->build_size(ct); + } + } if (queue->flags & NFQA_CFG_F_UID_GID) { size += (nla_total_size(sizeof(u_int32_t)) /* uid */ @@ -493,9 +500,10 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (entskb->tstamp.tv64) { struct nfqnl_msg_packet_timestamp ts; - struct timeval tv = ktime_to_timeval(entskb->tstamp); - ts.sec = cpu_to_be64(tv.tv_sec); - ts.usec = cpu_to_be64(tv.tv_usec); + struct timespec64 kts = ktime_to_timespec64(skb->tstamp); + + ts.sec = cpu_to_be64(kts.tv_sec); + ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC); if (nla_put(skb, NFQA_TIMESTAMP, sizeof(ts), &ts)) goto nla_put_failure; @@ -508,7 +516,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (seclen && nla_put(skb, NFQA_SECCTX, seclen, secdata)) goto nla_put_failure; - if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0) + if (ct && nfnl_ct->build(skb, ct, ctinfo, NFQA_CT, NFQA_CT_INFO) < 0) goto nla_put_failure; if (cap_len > data_len && @@ -598,12 +606,9 @@ static struct nf_queue_entry * nf_queue_entry_dup(struct nf_queue_entry *e) { struct nf_queue_entry *entry = kmemdup(e, e->size, GFP_ATOMIC); - if (entry) { - if (nf_queue_entry_get_refs(entry)) - return entry; - kfree(entry); - } - return NULL; + if (entry) + nf_queue_entry_get_refs(entry); + return entry; } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) @@ -698,7 +703,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) nf_bridge_adjust_skb_data(skb); segs = skb_gso_segment(skb, 0); /* Does not use PTR_ERR to limit the number of error codes that can be - * returned by nf_queue. For instance, callers rely on -ECANCELED to + * returned by nf_queue. For instance, callers rely on -ESRCH to * mean 'ignore this hook'. */ if (IS_ERR_OR_NULL(segs)) @@ -1001,6 +1006,28 @@ nfqnl_recv_verdict_batch(struct sock *ctnl, struct sk_buff *skb, return 0; } +static struct nf_conn *nfqnl_ct_parse(struct nfnl_ct_hook *nfnl_ct, + const struct nlmsghdr *nlh, + const struct nlattr * const nfqa[], + struct nf_queue_entry *entry, + enum ip_conntrack_info *ctinfo) +{ + struct nf_conn *ct; + + ct = nfnl_ct->get_ct(entry->skb, ctinfo); + if (ct == NULL) + return NULL; + + if (nfnl_ct->parse(nfqa[NFQA_CT], ct) < 0) + return NULL; + + if (nfqa[NFQA_EXP]) + nfnl_ct->attach_expect(nfqa[NFQA_EXP], ct, + NETLINK_CB(entry->skb).portid, + nlmsg_report(nlh)); + return ct; +} + static int nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, @@ -1014,6 +1041,7 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, unsigned int verdict; struct nf_queue_entry *entry; enum ip_conntrack_info uninitialized_var(ctinfo); + struct nfnl_ct_hook *nfnl_ct; struct nf_conn *ct = NULL; struct net *net = sock_net(ctnl); @@ -1037,12 +1065,10 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, return -ENOENT; if (nfqa[NFQA_CT]) { - ct = nfqnl_ct_parse(entry->skb, nfqa[NFQA_CT], &ctinfo); - if (ct && nfqa[NFQA_EXP]) { - nfqnl_attach_expect(ct, nfqa[NFQA_EXP], - NETLINK_CB(skb).portid, - nlmsg_report(nlh)); - } + /* rcu lock already held from nfnl->call_rcu. */ + nfnl_ct = rcu_dereference(nfnl_ct_hook); + if (nfnl_ct != NULL) + ct = nfqnl_ct_parse(nfnl_ct, nlh, nfqa, entry, &ctinfo); } if (nfqa[NFQA_PAYLOAD]) { @@ -1053,8 +1079,8 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, payload_len, entry, diff) < 0) verdict = NF_DROP; - if (ct) - nfqnl_ct_seq_adjust(entry->skb, ct, ctinfo, diff); + if (ct && diff) + nfnl_ct->seq_adjust(entry->skb, ct, ctinfo, diff); } if (nfqa[NFQA_MARK]) diff --git a/net/netfilter/nfnetlink_queue_ct.c b/net/netfilter/nfnetlink_queue_ct.c deleted file mode 100644 index 96cac50e0d12..000000000000 --- a/net/netfilter/nfnetlink_queue_ct.c +++ /dev/null @@ -1,113 +0,0 @@ -/* - * (C) 2012 by Pablo Neira Ayuso <[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 - * published by the Free Software Foundation. - * - */ - -#include <linux/skbuff.h> -#include <linux/netfilter.h> -#include <linux/netfilter/nfnetlink.h> -#include <linux/netfilter/nfnetlink_queue.h> -#include <net/netfilter/nf_conntrack.h> -#include <net/netfilter/nfnetlink_queue.h> - -struct nf_conn *nfqnl_ct_get(struct sk_buff *entskb, size_t *size, - enum ip_conntrack_info *ctinfo) -{ - struct nfq_ct_hook *nfq_ct; - struct nf_conn *ct; - - /* rcu_read_lock()ed by __nf_queue already. */ - nfq_ct = rcu_dereference(nfq_ct_hook); - if (nfq_ct == NULL) - return NULL; - - ct = nf_ct_get(entskb, ctinfo); - if (ct) { - if (!nf_ct_is_untracked(ct)) - *size += nfq_ct->build_size(ct); - else - ct = NULL; - } - return ct; -} - -struct nf_conn * -nfqnl_ct_parse(const struct sk_buff *skb, const struct nlattr *attr, - enum ip_conntrack_info *ctinfo) -{ - struct nfq_ct_hook *nfq_ct; - struct nf_conn *ct; - - /* rcu_read_lock()ed by __nf_queue already. */ - nfq_ct = rcu_dereference(nfq_ct_hook); - if (nfq_ct == NULL) - return NULL; - - ct = nf_ct_get(skb, ctinfo); - if (ct && !nf_ct_is_untracked(ct)) - nfq_ct->parse(attr, ct); - - return ct; -} - -int nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo) -{ - struct nfq_ct_hook *nfq_ct; - struct nlattr *nest_parms; - u_int32_t tmp; - - nfq_ct = rcu_dereference(nfq_ct_hook); - if (nfq_ct == NULL) - return 0; - - nest_parms = nla_nest_start(skb, NFQA_CT | NLA_F_NESTED); - if (!nest_parms) - goto nla_put_failure; - - if (nfq_ct->build(skb, ct) < 0) - goto nla_put_failure; - - nla_nest_end(skb, nest_parms); - - tmp = ctinfo; - if (nla_put_be32(skb, NFQA_CT_INFO, htonl(tmp))) - goto nla_put_failure; - - return 0; - -nla_put_failure: - return -1; -} - -void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, int diff) -{ - struct nfq_ct_hook *nfq_ct; - - nfq_ct = rcu_dereference(nfq_ct_hook); - if (nfq_ct == NULL) - return; - - if ((ct->status & IPS_NAT_MASK) && diff) - nfq_ct->seq_adjust(skb, ct, ctinfo, diff); -} - -int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, - u32 portid, u32 report) -{ - struct nfq_ct_hook *nfq_ct; - - if (nf_ct_is_untracked(ct)) - return 0; - - nfq_ct = rcu_dereference(nfq_ct_hook); - if (nfq_ct == NULL) - return -EOPNOTSUPP; - - return nfq_ct->attach_expect(attr, ct, portid, report); -} diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 9b42b5ea6dcd..d4aaad747ea9 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1193,7 +1193,6 @@ struct nf_hook_ops *xt_hook_link(const struct xt_table *table, nf_hookfn *fn) if (!(hook_mask & 1)) continue; ops[i].hook = fn; - ops[i].owner = table->me; ops[i].pf = table->af; ops[i].hooknum = hooknum; ops[i].priority = table->priority; diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index faf32d888198..e7ac07e53b59 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -171,6 +171,9 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, if (timeout_ext == NULL) ret = -ENOMEM; + rcu_read_unlock(); + return ret; + err_put_timeout: __xt_ct_tg_timeout_put(timeout); out: @@ -318,8 +321,10 @@ static void xt_ct_destroy_timeout(struct nf_conn *ct) if (timeout_put) { timeout_ext = nf_ct_timeout_find(ct); - if (timeout_ext) + if (timeout_ext) { timeout_put(timeout_ext->timeout); + RCU_INIT_POINTER(timeout_ext->timeout, NULL); + } } rcu_read_unlock(); #endif diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 8f060d7f9a0e..0a49a8c7c564 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2785,6 +2785,7 @@ static int netlink_dump(struct sock *sk) struct sk_buff *skb = NULL; struct nlmsghdr *nlh; int len, err = -ENOBUFS; + int alloc_min_size; int alloc_size; mutex_lock(nlk->cb_mutex); @@ -2793,9 +2794,6 @@ static int netlink_dump(struct sock *sk) goto errout_skb; } - cb = &nlk->cb; - alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); - if (!netlink_rx_is_mmaped(sk) && atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto errout_skb; @@ -2805,23 +2803,35 @@ static int netlink_dump(struct sock *sk) * to reduce number of system calls on dump operations, if user * ever provided a big enough buffer. */ - if (alloc_size < nlk->max_recvmsg_len) { - skb = netlink_alloc_skb(sk, - nlk->max_recvmsg_len, - nlk->portid, + cb = &nlk->cb; + alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); + + if (alloc_min_size < nlk->max_recvmsg_len) { + alloc_size = nlk->max_recvmsg_len; + skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); - /* available room should be exact amount to avoid MSG_TRUNC */ - if (skb) - skb_reserve(skb, skb_tailroom(skb) - - nlk->max_recvmsg_len); } - if (!skb) + if (!skb) { + alloc_size = alloc_min_size; skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL); + } if (!skb) goto errout_skb; + + /* Trim skb to allocated size. User is expected to provide buffer as + * large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at + * netlink_recvmsg())). dump will pack as many smaller messages as + * could fit within the allocated skb. skb is typically allocated + * with larger space than required (could be as much as near 2x the + * requested size with align to next power of 2 approach). Allowing + * dump to use the excess space makes it difficult for a user to have a + * reasonable static buffer based on the expected largest dump of a + * single netdev. The outcome is MSG_TRUNC error. + */ + skb_reserve(skb, skb_tailroom(skb) - alloc_size); netlink_skb_set_owner_r(skb, sk); len = cb->dump(skb, cb); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 1d21ab9d2b5c..c6087233d7fc 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -684,7 +684,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, { if (skb_network_offset(skb) > MAX_L2_LEN) { OVS_NLERR(1, "L2 header too long to fragment"); - return; + goto err; } if (ethertype == htons(ETH_P_IP)) { @@ -708,8 +708,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, struct rt6_info ovs_rt; if (!v6ops) { - kfree_skb(skb); - return; + goto err; } prepare_frag(vport, skb); @@ -728,8 +727,12 @@ static void ovs_fragment(struct net *net, struct vport *vport, WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", ovs_vport_name(vport), ntohs(ethertype), mru, vport->dev->mtu); - kfree_skb(skb); + goto err; } + + return; +err: + kfree_skb(skb); } static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, @@ -969,7 +972,7 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_STATE: case OVS_KEY_ATTR_CT_ZONE: case OVS_KEY_ATTR_CT_MARK: - case OVS_KEY_ATTR_CT_LABEL: + case OVS_KEY_ATTR_CT_LABELS: err = -EINVAL; break; } @@ -1100,6 +1103,12 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; case OVS_ACTION_ATTR_CT: + if (!is_flow_key_valid(key)) { + err = ovs_flow_key_update(skb, key); + if (err) + return err; + } + err = ovs_ct_execute(ovs_dp_get_net(dp), skb, key, nla_data(a)); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index ad614267cc2a..9ed833e9bb7d 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -37,9 +37,9 @@ struct md_mark { }; /* Metadata label for masked write to conntrack label. */ -struct md_label { - struct ovs_key_ct_label value; - struct ovs_key_ct_label mask; +struct md_labels { + struct ovs_key_ct_labels value; + struct ovs_key_ct_labels mask; }; /* Conntrack action context for execution. */ @@ -47,10 +47,10 @@ struct ovs_conntrack_info { struct nf_conntrack_helper *helper; struct nf_conntrack_zone zone; struct nf_conn *ct; - u32 flags; + u8 commit : 1; u16 family; struct md_mark mark; - struct md_label label; + struct md_labels labels; }; static u16 key_to_nfproto(const struct sw_flow_key *key) @@ -109,21 +109,21 @@ static u32 ovs_ct_get_mark(const struct nf_conn *ct) #endif } -static void ovs_ct_get_label(const struct nf_conn *ct, - struct ovs_key_ct_label *label) +static void ovs_ct_get_labels(const struct nf_conn *ct, + struct ovs_key_ct_labels *labels) { struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL; if (cl) { size_t len = cl->words * sizeof(long); - if (len > OVS_CT_LABEL_LEN) - len = OVS_CT_LABEL_LEN; - else if (len < OVS_CT_LABEL_LEN) - memset(label, 0, OVS_CT_LABEL_LEN); - memcpy(label, cl->bits, len); + if (len > OVS_CT_LABELS_LEN) + len = OVS_CT_LABELS_LEN; + else if (len < OVS_CT_LABELS_LEN) + memset(labels, 0, OVS_CT_LABELS_LEN); + memcpy(labels, cl->bits, len); } else { - memset(label, 0, OVS_CT_LABEL_LEN); + memset(labels, 0, OVS_CT_LABELS_LEN); } } @@ -134,7 +134,7 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, key->ct.state = state; key->ct.zone = zone->id; key->ct.mark = ovs_ct_get_mark(ct); - ovs_ct_get_label(ct, &key->ct.label); + ovs_ct_get_labels(ct, &key->ct.labels); } /* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has @@ -167,7 +167,7 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) { - if (nla_put_u8(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state)) + if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && @@ -179,8 +179,8 @@ int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - nla_put(skb, OVS_KEY_ATTR_CT_LABEL, sizeof(key->ct.label), - &key->ct.label)) + nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(key->ct.labels), + &key->ct.labels)) return -EMSGSIZE; return 0; @@ -213,9 +213,9 @@ static int ovs_ct_set_mark(struct sk_buff *skb, struct sw_flow_key *key, #endif } -static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key, - const struct ovs_key_ct_label *label, - const struct ovs_key_ct_label *mask) +static int ovs_ct_set_labels(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_key_ct_labels *labels, + const struct ovs_key_ct_labels *mask) { enum ip_conntrack_info ctinfo; struct nf_conn_labels *cl; @@ -235,15 +235,15 @@ static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key, nf_ct_labels_ext_add(ct); cl = nf_ct_labels_find(ct); } - if (!cl || cl->words * sizeof(long) < OVS_CT_LABEL_LEN) + if (!cl || cl->words * sizeof(long) < OVS_CT_LABELS_LEN) return -ENOSPC; - err = nf_connlabels_replace(ct, (u32 *)label, (u32 *)mask, - OVS_CT_LABEL_LEN / sizeof(u32)); + err = nf_connlabels_replace(ct, (u32 *)labels, (u32 *)mask, + OVS_CT_LABELS_LEN / sizeof(u32)); if (err) return err; - ovs_ct_get_label(ct, &key->ct.label); + ovs_ct_get_labels(ct, &key->ct.labels); return 0; } @@ -465,12 +465,12 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, return 0; } -static bool label_nonzero(const struct ovs_key_ct_label *label) +static bool labels_nonzero(const struct ovs_key_ct_labels *labels) { size_t i; - for (i = 0; i < sizeof(*label); i++) - if (label->ct_label[i]) + for (i = 0; i < sizeof(*labels); i++) + if (labels->ct_labels[i]) return true; return false; @@ -493,7 +493,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, return err; } - if (info->flags & OVS_CT_F_COMMIT) + if (info->commit) err = ovs_ct_commit(net, key, info, skb); else err = ovs_ct_lookup(net, key, info, skb); @@ -506,9 +506,9 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, if (err) goto err; } - if (label_nonzero(&info->label.mask)) - err = ovs_ct_set_label(skb, key, &info->label.value, - &info->label.mask); + 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); return err; @@ -539,14 +539,13 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, } static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { - [OVS_CT_ATTR_FLAGS] = { .minlen = sizeof(u32), - .maxlen = sizeof(u32) }, + [OVS_CT_ATTR_COMMIT] = { .minlen = 0, .maxlen = 0 }, [OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16), .maxlen = sizeof(u16) }, [OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark), .maxlen = sizeof(struct md_mark) }, - [OVS_CT_ATTR_LABEL] = { .minlen = sizeof(struct md_label), - .maxlen = sizeof(struct md_label) }, + [OVS_CT_ATTR_LABELS] = { .minlen = sizeof(struct md_labels), + .maxlen = sizeof(struct md_labels) }, [OVS_CT_ATTR_HELPER] = { .minlen = 1, .maxlen = NF_CT_HELPER_NAME_LEN } }; @@ -576,8 +575,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, } switch (type) { - case OVS_CT_ATTR_FLAGS: - info->flags = nla_get_u32(a); + case OVS_CT_ATTR_COMMIT: + info->commit = true; break; #ifdef CONFIG_NF_CONNTRACK_ZONES case OVS_CT_ATTR_ZONE: @@ -593,10 +592,10 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, } #endif #ifdef CONFIG_NF_CONNTRACK_LABELS - case OVS_CT_ATTR_LABEL: { - struct md_label *label = nla_data(a); + case OVS_CT_ATTR_LABELS: { + struct md_labels *labels = nla_data(a); - info->label = *label; + info->labels = *labels; break; } #endif @@ -633,7 +632,7 @@ bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr) attr == OVS_KEY_ATTR_CT_MARK) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - attr == OVS_KEY_ATTR_CT_LABEL) { + attr == OVS_KEY_ATTR_CT_LABELS) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); return ovs_net->xt_label; @@ -701,7 +700,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, if (!start) return -EMSGSIZE; - if (nla_put_u32(skb, OVS_CT_ATTR_FLAGS, ct_info->flags)) + if (ct_info->commit && nla_put_flag(skb, OVS_CT_ATTR_COMMIT)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id)) @@ -711,8 +710,8 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, &ct_info->mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - nla_put(skb, OVS_CT_ATTR_LABEL, sizeof(ct_info->label), - &ct_info->label)) + nla_put(skb, OVS_CT_ATTR_LABELS, sizeof(ct_info->labels), + &ct_info->labels)) return -EMSGSIZE; if (ct_info->helper) { if (nla_put_string(skb, OVS_CT_ATTR_HELPER, @@ -737,7 +736,7 @@ void ovs_ct_free_action(const struct nlattr *a) void ovs_ct_init(struct net *net) { - unsigned int n_bits = sizeof(struct ovs_key_ct_label) * BITS_PER_BYTE; + unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_net *ovs_net = net_generic(net, ovs_net_id); if (nf_connlabels_get(net, n_bits)) { diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index 43f5dd7a5577..da8714942c95 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -34,6 +34,13 @@ int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *, void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb); void ovs_ct_free_action(const struct nlattr *a); + +static inline bool ovs_ct_state_supported(u32 state) +{ + return !(state & ~(OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | + OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | + OVS_CS_F_INVALID | OVS_CS_F_TRACKED)); +} #else #include <linux/errno.h> @@ -46,6 +53,11 @@ static inline bool ovs_ct_verify(struct net *net, int attr) return false; } +static inline bool ovs_ct_state_supported(u32 state) +{ + return false; +} + static inline int ovs_ct_copy_action(struct net *net, const struct nlattr *nla, const struct sw_flow_key *key, struct sw_flow_actions **acts, bool log) @@ -72,7 +84,7 @@ static inline void ovs_ct_fill_key(const struct sk_buff *skb, key->ct.state = 0; key->ct.zone = 0; key->ct.mark = 0; - memset(&key->ct.label, 0, sizeof(key->ct.label)); + memset(&key->ct.labels, 0, sizeof(key->ct.labels)); } static inline int ovs_ct_put_key(const struct sw_flow_key *key, diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 5688e33e2de6..1d055c559eaf 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -117,7 +117,7 @@ struct sw_flow_key { u16 zone; u32 mark; u8 state; - struct ovs_key_ct_label label; + struct ovs_key_ct_labels labels; } ct; } __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 77850f177a47..80e1f09397c0 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -291,10 +291,10 @@ size_t ovs_key_attr_size(void) + nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */ + nla_total_size(4) /* OVS_KEY_ATTR_DP_HASH */ + nla_total_size(4) /* OVS_KEY_ATTR_RECIRC_ID */ - + nla_total_size(1) /* OVS_KEY_ATTR_CT_STATE */ + + nla_total_size(4) /* OVS_KEY_ATTR_CT_STATE */ + nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */ + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ - + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABEL */ + + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */ + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */ @@ -351,10 +351,10 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED, .next = ovs_tunnel_key_lens, }, [OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) }, - [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u8) }, + [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) }, [OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) }, - [OVS_KEY_ATTR_CT_LABEL] = { .len = sizeof(struct ovs_key_ct_label) }, + [OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) }, }; static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) @@ -548,11 +548,11 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) { + bool ttl = false, ipv4 = false, ipv6 = false; + __be16 tun_flags = 0; + int opts_type = 0; struct nlattr *a; int rem; - bool ttl = false; - __be16 tun_flags = 0, ipv4 = false, ipv6 = false; - int opts_type = 0; nla_for_each_nested(a, attr, rem) { int type = nla_type(a); @@ -864,7 +864,13 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, if (*attrs & (1 << OVS_KEY_ATTR_CT_STATE) && ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) { - u8 ct_state = nla_get_u8(a[OVS_KEY_ATTR_CT_STATE]); + u32 ct_state = nla_get_u32(a[OVS_KEY_ATTR_CT_STATE]); + + if (!is_mask && !ovs_ct_state_supported(ct_state)) { + OVS_NLERR(log, "ct_state flags %08x unsupported", + ct_state); + return -EINVAL; + } SW_FLOW_KEY_PUT(match, ct.state, ct_state, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_STATE); @@ -883,14 +889,14 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, SW_FLOW_KEY_PUT(match, ct.mark, mark, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_MARK); } - if (*attrs & (1 << OVS_KEY_ATTR_CT_LABEL) && - ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABEL)) { - const struct ovs_key_ct_label *cl; + if (*attrs & (1 << OVS_KEY_ATTR_CT_LABELS) && + ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABELS)) { + const struct ovs_key_ct_labels *cl; - cl = nla_data(a[OVS_KEY_ATTR_CT_LABEL]); - SW_FLOW_KEY_MEMCPY(match, ct.label, cl->ct_label, + cl = nla_data(a[OVS_KEY_ATTR_CT_LABELS]); + SW_FLOW_KEY_MEMCPY(match, ct.labels, cl->ct_labels, sizeof(*cl), is_mask); - *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABEL); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS); } return 0; } @@ -2025,7 +2031,7 @@ static int validate_set(const struct nlattr *a, case OVS_KEY_ATTR_PRIORITY: case OVS_KEY_ATTR_SKB_MARK: case OVS_KEY_ATTR_CT_MARK: - case OVS_KEY_ATTR_CT_LABEL: + case OVS_KEY_ATTR_CT_LABELS: case OVS_KEY_ATTR_ETHERNET: break; diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 95dbcedf0bd4..d073fff82fdb 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -93,7 +93,8 @@ struct sw_flow *ovs_flow_alloc(void) /* Initialize the default stat node. */ stats = kmem_cache_alloc_node(flow_stats_cache, - GFP_KERNEL | __GFP_ZERO, 0); + GFP_KERNEL | __GFP_ZERO, + node_online(0) ? 0 : NUMA_NO_NODE); if (!stats) goto err; diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 2735e9c4a3b8..7a568ca8da54 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -128,7 +128,7 @@ static struct vport_ops ovs_geneve_vport_ops = { .create = geneve_create, .destroy = ovs_netdev_tunnel_destroy, .get_options = geneve_get_options, - .send = ovs_netdev_send, + .send = dev_queue_xmit, .owner = THIS_MODULE, .get_egress_tun_info = geneve_get_egress_tun_info, }; diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 4d24481669c9..cdb758ab01cf 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -94,7 +94,7 @@ static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, static struct vport_ops ovs_gre_vport_ops = { .type = OVS_VPORT_TYPE_GRE, .create = gre_create, - .send = ovs_netdev_send, + .send = dev_queue_xmit, .get_egress_tun_info = gre_get_egress_tun_info, .destroy = ovs_netdev_tunnel_destroy, .owner = THIS_MODULE, diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 388b8a6bf112..7f0a8bd08857 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -202,22 +202,21 @@ static void internal_dev_destroy(struct vport *vport) rtnl_unlock(); } -static void internal_dev_recv(struct vport *vport, struct sk_buff *skb) +static netdev_tx_t internal_dev_recv(struct sk_buff *skb) { - struct net_device *netdev = vport->dev; + struct net_device *netdev = skb->dev; struct pcpu_sw_netstats *stats; if (unlikely(!(netdev->flags & IFF_UP))) { kfree_skb(skb); netdev->stats.rx_dropped++; - return; + return NETDEV_TX_OK; } skb_dst_drop(skb); nf_reset(skb); secpath_reset(skb); - skb->dev = netdev; skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, netdev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); @@ -229,6 +228,7 @@ static void internal_dev_recv(struct vport *vport, struct sk_buff *skb) u64_stats_update_end(&stats->syncp); netif_rx(skb); + return NETDEV_TX_OK; } static struct vport_ops ovs_internal_vport_ops = { diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index f7e8dcce7ada..b327368a3848 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -190,37 +190,6 @@ void ovs_netdev_tunnel_destroy(struct vport *vport) } EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy); -static unsigned int packet_length(const struct sk_buff *skb) -{ - unsigned int length = skb->len - ETH_HLEN; - - if (skb->protocol == htons(ETH_P_8021Q)) - length -= VLAN_HLEN; - - return length; -} - -void ovs_netdev_send(struct vport *vport, struct sk_buff *skb) -{ - int mtu = vport->dev->mtu; - - if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) { - net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n", - vport->dev->name, - packet_length(skb), mtu); - vport->dev->stats.tx_errors++; - goto drop; - } - - skb->dev = vport->dev; - dev_queue_xmit(skb); - return; - -drop: - kfree_skb(skb); -} -EXPORT_SYMBOL_GPL(ovs_netdev_send); - /* Returns null if this device is not attached to a datapath. */ struct vport *ovs_netdev_get_vport(struct net_device *dev) { @@ -235,7 +204,7 @@ static struct vport_ops ovs_netdev_vport_ops = { .type = OVS_VPORT_TYPE_NETDEV, .create = netdev_create, .destroy = netdev_destroy, - .send = ovs_netdev_send, + .send = dev_queue_xmit, }; int __init ovs_netdev_init(void) diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h index bf22fcedbc69..19e29c12adcc 100644 --- a/net/openvswitch/vport-netdev.h +++ b/net/openvswitch/vport-netdev.h @@ -27,7 +27,6 @@ struct vport *ovs_netdev_get_vport(struct net_device *dev); struct vport *ovs_netdev_link(struct vport *vport, const char *name); -void ovs_netdev_send(struct vport *vport, struct sk_buff *skb); void ovs_netdev_detach_dev(struct vport *); int __init ovs_netdev_init(void); diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index fb3cdb85905d..6f700710d413 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -170,7 +170,7 @@ static struct vport_ops ovs_vxlan_netdev_vport_ops = { .create = vxlan_create, .destroy = ovs_netdev_tunnel_destroy, .get_options = vxlan_get_options, - .send = ovs_netdev_send, + .send = dev_queue_xmit, .get_egress_tun_info = vxlan_get_egress_tun_info, }; diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index dc81dc619aa2..ef19d0b77d13 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -280,35 +280,19 @@ void ovs_vport_del(struct vport *vport) */ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) { - struct net_device *dev = vport->dev; - int i; - - memset(stats, 0, sizeof(*stats)); - stats->rx_errors = dev->stats.rx_errors; - stats->tx_errors = dev->stats.tx_errors; - stats->tx_dropped = dev->stats.tx_dropped; - stats->rx_dropped = dev->stats.rx_dropped; - - stats->rx_dropped += atomic_long_read(&dev->rx_dropped); - stats->tx_dropped += atomic_long_read(&dev->tx_dropped); - - for_each_possible_cpu(i) { - const struct pcpu_sw_netstats *percpu_stats; - struct pcpu_sw_netstats local_stats; - unsigned int start; - - percpu_stats = per_cpu_ptr(dev->tstats, i); - - do { - start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); - local_stats = *percpu_stats; - } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); - - stats->rx_bytes += local_stats.rx_bytes; - stats->rx_packets += local_stats.rx_packets; - stats->tx_bytes += local_stats.tx_bytes; - stats->tx_packets += local_stats.tx_packets; - } + const struct rtnl_link_stats64 *dev_stats; + struct rtnl_link_stats64 temp; + + dev_stats = dev_get_stats(vport->dev, &temp); + stats->rx_errors = dev_stats->rx_errors; + stats->tx_errors = dev_stats->tx_errors; + stats->tx_dropped = dev_stats->tx_dropped; + stats->rx_dropped = dev_stats->rx_dropped; + + stats->rx_bytes = dev_stats->rx_bytes; + stats->rx_packets = dev_stats->rx_packets; + stats->tx_bytes = dev_stats->tx_bytes; + stats->tx_packets = dev_stats->tx_packets; } /** @@ -460,6 +444,15 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb, OVS_CB(skb)->input_vport = vport; OVS_CB(skb)->mru = 0; + if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) { + u32 mark; + + mark = skb->mark; + skb_scrub_packet(skb, true); + skb->mark = mark; + tun_info = NULL; + } + /* Extract flow from 'skb' into 'key'. */ error = ovs_flow_key_extract(tun_info, skb, &key); if (unlikely(error)) { @@ -544,3 +537,33 @@ int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, return vport->ops->get_egress_tun_info(vport, skb, upcall); } + +static unsigned int packet_length(const struct sk_buff *skb) +{ + unsigned int length = skb->len - ETH_HLEN; + + if (skb->protocol == htons(ETH_P_8021Q)) + length -= VLAN_HLEN; + + return length; +} + +void ovs_vport_send(struct vport *vport, struct sk_buff *skb) +{ + int mtu = vport->dev->mtu; + + if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) { + net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n", + vport->dev->name, + packet_length(skb), mtu); + vport->dev->stats.tx_errors++; + goto drop; + } + + skb->dev = vport->dev; + vport->ops->send(skb); + return; + +drop: + kfree_skb(skb); +} diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index a413f3ae6a7b..885607f28d56 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -153,7 +153,7 @@ struct vport_ops { int (*set_options)(struct vport *, struct nlattr *); int (*get_options)(const struct vport *, struct sk_buff *); - void (*send)(struct vport *, struct sk_buff *); + netdev_tx_t (*send) (struct sk_buff *skb); int (*get_egress_tun_info)(struct vport *, struct sk_buff *, struct dp_upcall_info *upcall); @@ -234,9 +234,6 @@ static inline struct rtable *ovs_tunnel_route_lookup(struct net *net, return rt; } -static inline void ovs_vport_send(struct vport *vport, struct sk_buff *skb) -{ - vport->ops->send(vport, skb); -} +void ovs_vport_send(struct vport *vport, struct sk_buff *skb); #endif /* vport.h */ diff --git a/net/rds/bind.c b/net/rds/bind.c index bc6b93ecedb5..61925667b7a4 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -196,7 +196,14 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; if (rs->rs_transport) { /* previously bound */ - ret = 0; + trans = rs->rs_transport; + if (trans->laddr_check(sock_net(sock->sk), + sin->sin_addr.s_addr) != 0) { + ret = -ENOPROTOOPT; + rds_remove_bound(rs); + } else { + ret = 0; + } goto out; } trans = rds_trans_get_preferred(sock_net(sock->sk), diff --git a/net/rds/send.c b/net/rds/send.c index ee49c2556f47..827155c2ead1 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1182,9 +1182,8 @@ rds_send_pong(struct rds_connection *conn, __be16 dport) rds_stats_inc(s_send_queued); rds_stats_inc(s_send_pong); - ret = rds_send_xmit(conn); - if (ret == -ENOMEM || ret == -EAGAIN) - queue_delayed_work(rds_wq, &conn->c_send_w, 1); + /* schedule the send work on rds_wq */ + queue_delayed_work(rds_wq, &conn->c_send_w, 1); rds_message_put(rm); return 0; diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 1d90240e5d82..0936a4a32b47 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -125,6 +125,9 @@ int rds_tcp_accept_one(struct socket *sock) new_sock = NULL; ret = 0; goto out; + } else if (rs_tcp->t_sock) { + rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp); + conn->c_outgoing = 0; } rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 2d1be4a760fd..32fcdecdb9e2 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -31,13 +31,17 @@ #define MIRRED_TAB_MASK 7 static LIST_HEAD(mirred_list); +static DEFINE_SPINLOCK(mirred_list_lock); static void tcf_mirred_release(struct tc_action *a, int bind) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1); + /* We could be called either in a RCU callback or with RTNL lock held. */ + spin_lock_bh(&mirred_list_lock); list_del(&m->tcfm_list); + spin_unlock_bh(&mirred_list_lock); if (dev) dev_put(dev); } @@ -103,10 +107,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } else { if (bind) return 0; - if (!ovr) { - tcf_hash_release(a, bind); + + tcf_hash_release(a, bind); + if (!ovr) return -EEXIST; - } } m = to_mirred(a); @@ -123,7 +127,9 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } if (ret == ACT_P_CREATED) { + spin_lock_bh(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); + spin_unlock_bh(&mirred_list_lock); tcf_hash_insert(a); } @@ -173,6 +179,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; + skb_sender_cpu_clear(skb2); err = dev_queue_xmit(skb2); if (err) { @@ -221,7 +228,8 @@ static int mirred_device_event(struct notifier_block *unused, struct tcf_mirred *m; ASSERT_RTNL(); - if (event == NETDEV_UNREGISTER) + if (event == NETDEV_UNREGISTER) { + spin_lock_bh(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); @@ -231,6 +239,8 @@ static int mirred_device_event(struct notifier_block *unused, RCU_INIT_POINTER(m->tcfm_dev, NULL); } } + spin_unlock_bh(&mirred_list_lock); + } return NOTIFY_DONE; } diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 9d15cb6b8cb1..86b04e31e60b 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -368,6 +368,15 @@ static unsigned int hhf_drop(struct Qdisc *sch) 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) { struct hhf_sched_data *q = qdisc_priv(sch); @@ -696,7 +705,7 @@ static struct Qdisc_ops hhf_qdisc_ops __read_mostly = { .enqueue = hhf_enqueue, .dequeue = hhf_dequeue, .peek = qdisc_peek_dequeued, - .drop = hhf_drop, + .drop = hhf_qdisc_drop, .init = hhf_init, .reset = hhf_reset, .destroy = hhf_destroy, diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index cb5174284074..f0c3ff67ca98 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -136,7 +136,8 @@ int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, ctxt->direction = DMA_FROM_DEVICE; ctxt->read_hdr = head; pages_needed = min_t(int, pages_needed, xprt->sc_max_sge_rd); - read = min_t(int, pages_needed << PAGE_SHIFT, rs_length); + read = min_t(int, (pages_needed << PAGE_SHIFT) - *page_offset, + rs_length); for (pno = 0; pno < pages_needed; pno++) { int len = min_t(int, rs_length, PAGE_SIZE - pg_off); @@ -235,7 +236,8 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt, ctxt->direction = DMA_FROM_DEVICE; ctxt->frmr = frmr; pages_needed = min_t(int, pages_needed, xprt->sc_frmr_pg_list_len); - read = min_t(int, pages_needed << PAGE_SHIFT, rs_length); + read = min_t(int, (pages_needed << PAGE_SHIFT) - *page_offset, + rs_length); frmr->kva = page_address(rqstp->rq_arg.pages[pg_no]); frmr->direction = DMA_FROM_DEVICE; @@ -531,7 +533,7 @@ static int rdma_read_complete(struct svc_rqst *rqstp, rqstp->rq_arg.page_base = head->arg.page_base; /* rq_respages starts after the last arg page */ - rqstp->rq_respages = &rqstp->rq_arg.pages[page_no]; + rqstp->rq_respages = &rqstp->rq_pages[page_no]; rqstp->rq_next_page = rqstp->rq_respages + 1; /* Rebuild rq_arg head and tail. */ diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 64443eb754ad..41e452bc580c 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -270,8 +270,8 @@ xprt_rdma_destroy(struct rpc_xprt *xprt) xprt_clear_connected(xprt); - rpcrdma_buffer_destroy(&r_xprt->rx_buf); rpcrdma_ep_destroy(&r_xprt->rx_ep, &r_xprt->rx_ia); + rpcrdma_buffer_destroy(&r_xprt->rx_buf); rpcrdma_ia_close(&r_xprt->rx_ia); xprt_rdma_free_addresses(xprt); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index eb081ad05e33..5502d4dade74 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -543,11 +543,8 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) } if (memreg == RPCRDMA_FRMR) { - /* Requires both frmr reg and local dma lkey */ - if (((devattr->device_cap_flags & - (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) != - (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) || - (devattr->max_fast_reg_page_list_len == 0)) { + if (!(devattr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) || + (devattr->max_fast_reg_page_list_len == 0)) { dprintk("RPC: %s: FRMR registration " "not supported by HCA\n", __func__); memreg = RPCRDMA_MTHCAFMR; @@ -557,6 +554,7 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) if (!ia->ri_device->alloc_fmr) { dprintk("RPC: %s: MTHCAFMR registration " "not supported by HCA\n", __func__); + rc = -EINVAL; goto out3; } } @@ -755,19 +753,22 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) cancel_delayed_work_sync(&ep->rep_connect_worker); - if (ia->ri_id->qp) { + if (ia->ri_id->qp) rpcrdma_ep_disconnect(ep, ia); + + rpcrdma_clean_cq(ep->rep_attr.recv_cq); + rpcrdma_clean_cq(ep->rep_attr.send_cq); + + if (ia->ri_id->qp) { rdma_destroy_qp(ia->ri_id); ia->ri_id->qp = NULL; } - rpcrdma_clean_cq(ep->rep_attr.recv_cq); rc = ib_destroy_cq(ep->rep_attr.recv_cq); if (rc) dprintk("RPC: %s: ib_destroy_cq returned %i\n", __func__, rc); - rpcrdma_clean_cq(ep->rep_attr.send_cq); rc = ib_destroy_cq(ep->rep_attr.send_cq); if (rc) dprintk("RPC: %s: ib_destroy_cq returned %i\n", diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 7a9ab90363be..1eb76956b439 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -15,8 +15,11 @@ #include <linux/mutex.h> #include <linux/notifier.h> #include <linux/netdevice.h> +#include <linux/etherdevice.h> #include <linux/if_bridge.h> #include <linux/list.h> +#include <linux/workqueue.h> +#include <linux/if_vlan.h> #include <net/ip_fib.h> #include <net/switchdev.h> @@ -92,6 +95,85 @@ static void switchdev_trans_items_warn_destroy(struct net_device *dev, switchdev_trans_items_destroy(trans); } +static LIST_HEAD(deferred); +static DEFINE_SPINLOCK(deferred_lock); + +typedef void switchdev_deferred_func_t(struct net_device *dev, + const void *data); + +struct switchdev_deferred_item { + struct list_head list; + struct net_device *dev; + switchdev_deferred_func_t *func; + unsigned long data[0]; +}; + +static struct switchdev_deferred_item *switchdev_deferred_dequeue(void) +{ + struct switchdev_deferred_item *dfitem; + + spin_lock_bh(&deferred_lock); + if (list_empty(&deferred)) { + dfitem = NULL; + goto unlock; + } + dfitem = list_first_entry(&deferred, + struct switchdev_deferred_item, list); + list_del(&dfitem->list); +unlock: + spin_unlock_bh(&deferred_lock); + return dfitem; +} + +/** + * switchdev_deferred_process - Process ops in deferred queue + * + * Called to flush the ops currently queued in deferred ops queue. + * rtnl_lock must be held. + */ +void switchdev_deferred_process(void) +{ + struct switchdev_deferred_item *dfitem; + + ASSERT_RTNL(); + + while ((dfitem = switchdev_deferred_dequeue())) { + dfitem->func(dfitem->dev, dfitem->data); + dev_put(dfitem->dev); + kfree(dfitem); + } +} +EXPORT_SYMBOL_GPL(switchdev_deferred_process); + +static void switchdev_deferred_process_work(struct work_struct *work) +{ + rtnl_lock(); + switchdev_deferred_process(); + rtnl_unlock(); +} + +static DECLARE_WORK(deferred_process_work, switchdev_deferred_process_work); + +static int switchdev_deferred_enqueue(struct net_device *dev, + const void *data, size_t data_len, + switchdev_deferred_func_t *func) +{ + struct switchdev_deferred_item *dfitem; + + dfitem = kmalloc(sizeof(*dfitem) + data_len, GFP_ATOMIC); + if (!dfitem) + return -ENOMEM; + dfitem->dev = dev; + dfitem->func = func; + memcpy(dfitem->data, data, data_len); + dev_hold(dev); + spin_lock_bh(&deferred_lock); + list_add_tail(&dfitem->list, &deferred); + spin_unlock_bh(&deferred_lock); + schedule_work(&deferred_process_work); + return 0; +} + /** * switchdev_port_attr_get - Get port attribute * @@ -135,7 +217,7 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) EXPORT_SYMBOL_GPL(switchdev_port_attr_get); static int __switchdev_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr, + const struct switchdev_attr *attr, struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; @@ -170,74 +252,12 @@ done: return err; } -struct switchdev_attr_set_work { - struct work_struct work; - struct net_device *dev; - struct switchdev_attr attr; -}; - -static void switchdev_port_attr_set_work(struct work_struct *work) -{ - struct switchdev_attr_set_work *asw = - container_of(work, struct switchdev_attr_set_work, work); - int err; - - rtnl_lock(); - err = switchdev_port_attr_set(asw->dev, &asw->attr); - if (err && err != -EOPNOTSUPP) - netdev_err(asw->dev, "failed (err=%d) to set attribute (id=%d)\n", - err, asw->attr.id); - rtnl_unlock(); - - dev_put(asw->dev); - kfree(work); -} - -static int switchdev_port_attr_set_defer(struct net_device *dev, - struct switchdev_attr *attr) -{ - struct switchdev_attr_set_work *asw; - - asw = kmalloc(sizeof(*asw), GFP_ATOMIC); - if (!asw) - return -ENOMEM; - - INIT_WORK(&asw->work, switchdev_port_attr_set_work); - - dev_hold(dev); - asw->dev = dev; - memcpy(&asw->attr, attr, sizeof(asw->attr)); - - schedule_work(&asw->work); - - return 0; -} - -/** - * switchdev_port_attr_set - Set port attribute - * - * @dev: port device - * @attr: attribute to set - * - * Use a 2-phase prepare-commit transaction model to ensure - * system is not left in a partially updated state due to - * failure from driver/device. - */ -int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) +static int switchdev_port_attr_set_now(struct net_device *dev, + const struct switchdev_attr *attr) { struct switchdev_trans trans; int err; - if (!rtnl_is_locked()) { - /* Running prepare-commit transaction across stacked - * devices requires nothing moves, so if rtnl_lock is - * not held, schedule a worker thread to hold rtnl_lock - * while setting attr. - */ - - return switchdev_port_attr_set_defer(dev, attr); - } - switchdev_trans_init(&trans); /* Phase I: prepare for attr set. Driver/device should fail @@ -274,6 +294,47 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) return err; } + +static void switchdev_port_attr_set_deferred(struct net_device *dev, + const void *data) +{ + const struct switchdev_attr *attr = data; + int err; + + err = switchdev_port_attr_set_now(dev, attr); + if (err && err != -EOPNOTSUPP) + netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n", + err, attr->id); +} + +static int switchdev_port_attr_set_defer(struct net_device *dev, + const struct switchdev_attr *attr) +{ + return switchdev_deferred_enqueue(dev, attr, sizeof(*attr), + switchdev_port_attr_set_deferred); +} + +/** + * switchdev_port_attr_set - Set port attribute + * + * @dev: port device + * @attr: attribute to set + * + * Use a 2-phase prepare-commit transaction model to ensure + * system is not left in a partially updated state due to + * failure from driver/device. + * + * rtnl_lock must be held and must not be in atomic section, + * in case SWITCHDEV_F_DEFER flag is not set. + */ +int switchdev_port_attr_set(struct net_device *dev, + const struct switchdev_attr *attr) +{ + if (attr->flags & SWITCHDEV_F_DEFER) + return switchdev_port_attr_set_defer(dev, attr); + ASSERT_RTNL(); + return switchdev_port_attr_set_now(dev, attr); +} EXPORT_SYMBOL_GPL(switchdev_port_attr_set); static int __switchdev_port_obj_add(struct net_device *dev, @@ -302,21 +363,8 @@ static int __switchdev_port_obj_add(struct net_device *dev, return err; } -/** - * switchdev_port_obj_add - Add port object - * - * @dev: port device - * @id: object ID - * @obj: object to add - * - * Use a 2-phase prepare-commit transaction model to ensure - * system is not left in a partially updated state due to - * failure from driver/device. - * - * rtnl_lock must be held. - */ -int switchdev_port_obj_add(struct net_device *dev, - const struct switchdev_obj *obj) +static int switchdev_port_obj_add_now(struct net_device *dev, + const struct switchdev_obj *obj) { struct switchdev_trans trans; int err; @@ -358,18 +406,53 @@ int switchdev_port_obj_add(struct net_device *dev, return err; } -EXPORT_SYMBOL_GPL(switchdev_port_obj_add); + +static void switchdev_port_obj_add_deferred(struct net_device *dev, + const void *data) +{ + const struct switchdev_obj *obj = data; + int err; + + err = switchdev_port_obj_add_now(dev, obj); + if (err && err != -EOPNOTSUPP) + netdev_err(dev, "failed (err=%d) to add object (id=%d)\n", + err, obj->id); +} + +static int switchdev_port_obj_add_defer(struct net_device *dev, + const struct switchdev_obj *obj) +{ + return switchdev_deferred_enqueue(dev, obj, sizeof(*obj), + switchdev_port_obj_add_deferred); +} /** - * switchdev_port_obj_del - Delete port object + * switchdev_port_obj_add - Add port object * * @dev: port device * @id: object ID - * @obj: object to delete + * @obj: object to add + * + * Use a 2-phase prepare-commit transaction model to ensure + * system is not left in a partially updated state due to + * failure from driver/device. + * + * rtnl_lock must be held and must not be in atomic section, + * in case SWITCHDEV_F_DEFER flag is not set. */ -int switchdev_port_obj_del(struct net_device *dev, +int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj) { + if (obj->flags & SWITCHDEV_F_DEFER) + return switchdev_port_obj_add_defer(dev, obj); + ASSERT_RTNL(); + return switchdev_port_obj_add_now(dev, obj); +} +EXPORT_SYMBOL_GPL(switchdev_port_obj_add); + +static int switchdev_port_obj_del_now(struct net_device *dev, + const struct switchdev_obj *obj) +{ const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; struct list_head *iter; @@ -384,13 +467,51 @@ int switchdev_port_obj_del(struct net_device *dev, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_obj_del(lower_dev, obj); + err = switchdev_port_obj_del_now(lower_dev, obj); if (err) break; } return err; } + +static void switchdev_port_obj_del_deferred(struct net_device *dev, + const void *data) +{ + const struct switchdev_obj *obj = data; + int err; + + err = switchdev_port_obj_del_now(dev, obj); + if (err && err != -EOPNOTSUPP) + netdev_err(dev, "failed (err=%d) to del object (id=%d)\n", + err, obj->id); +} + +static int switchdev_port_obj_del_defer(struct net_device *dev, + const struct switchdev_obj *obj) +{ + return switchdev_deferred_enqueue(dev, obj, sizeof(*obj), + switchdev_port_obj_del_deferred); +} + +/** + * switchdev_port_obj_del - Delete port object + * + * @dev: port device + * @id: object ID + * @obj: object to delete + * + * rtnl_lock must be held and must not be in atomic section, + * in case SWITCHDEV_F_DEFER flag is not set. + */ +int switchdev_port_obj_del(struct net_device *dev, + const struct switchdev_obj *obj) +{ + if (obj->flags & SWITCHDEV_F_DEFER) + return switchdev_port_obj_del_defer(dev, obj); + ASSERT_RTNL(); + return switchdev_port_obj_del_now(dev, obj); +} EXPORT_SYMBOL_GPL(switchdev_port_obj_del); /** @@ -400,6 +521,8 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_del); * @id: object ID * @obj: object to dump * @cb: function to call with a filled object + * + * rtnl_lock must be held. */ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb) @@ -409,6 +532,8 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, struct list_head *iter; int err = -EOPNOTSUPP; + ASSERT_RTNL(); + if (ops && ops->switchdev_port_obj_dump) return ops->switchdev_port_obj_dump(dev, obj, cb); @@ -722,11 +847,16 @@ static int switchdev_port_br_afspec(struct net_device *dev, if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo = nla_data(attr); + if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK) + return -EINVAL; vlan.flags = vinfo->flags; if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { if (vlan.vid_begin) return -EINVAL; vlan.vid_begin = vinfo->vid; + /* don't allow range of pvids */ + if (vlan.flags & BRIDGE_VLAN_INFO_PVID) + return -EINVAL; } else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) { if (!vlan.vid_begin) return -EINVAL; @@ -829,10 +959,10 @@ int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], { struct switchdev_obj_port_fdb fdb = { .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, - .addr = addr, .vid = vid, }; + ether_addr_copy(fdb.addr, addr); return switchdev_port_obj_add(dev, &fdb.obj); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_add); @@ -854,10 +984,10 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], { struct switchdev_obj_port_fdb fdb = { .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, - .addr = addr, .vid = vid, }; + ether_addr_copy(fdb.addr, addr); return switchdev_port_obj_del(dev, &fdb.obj); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); @@ -974,6 +1104,8 @@ static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) struct net_device *dev = NULL; int nhsel; + ASSERT_RTNL(); + /* For this route, all nexthop devs must be on the same switch. */ for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) { @@ -1019,7 +1151,6 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, .obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB, .dst = dst, .dst_len = dst_len, - .fi = fi, .tos = tos, .type = type, .nlflags = nlflags, @@ -1028,6 +1159,8 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, struct net_device *dev; int err = 0; + memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi)); + /* Don't offload route if using custom ip rules or if * IPv4 FIB offloading has been disabled completely. */ @@ -1071,7 +1204,6 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, .obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB, .dst = dst, .dst_len = dst_len, - .fi = fi, .tos = tos, .type = type, .nlflags = 0, @@ -1080,6 +1212,8 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, struct net_device *dev; int err = 0; + memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi)); + if (!(fi->fib_flags & RTNH_F_OFFLOAD)) return 0; @@ -1202,10 +1336,11 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, u32 mark = dev->ifindex; u32 reset_mark = 0; - if (group_dev && joining) { - mark = switchdev_port_fwd_mark_get(dev, group_dev); - } else if (group_dev && !joining) { - if (dev->offload_fwd_mark == mark) + if (group_dev) { + ASSERT_RTNL(); + if (joining) + mark = switchdev_port_fwd_mark_get(dev, group_dev); + else if (dev->offload_fwd_mark == mark) /* Ohoh, this port was the mark reference port, * but it's leaving the group, so reset the * mark for the remaining ports in the group. diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index ce9f7bfc0b92..82b278668ab7 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -362,6 +362,7 @@ static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr) b_ptr->media->disable_media(b_ptr); tipc_node_delete_links(net, b_ptr->identity); + RCU_INIT_POINTER(b_ptr->media_ptr, NULL); if (b_ptr->link_req) tipc_disc_delete(b_ptr->link_req); @@ -399,16 +400,13 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, /* tipc_disable_l2_media - detach TIPC bearer from an L2 interface * - * Mark L2 bearer as inactive so that incoming buffers are thrown away, - * then get worker thread to complete bearer cleanup. (Can't do cleanup - * here because cleanup code needs to sleep and caller holds spinlocks.) + * Mark L2 bearer as inactive so that incoming buffers are thrown away */ void tipc_disable_l2_media(struct tipc_bearer *b) { struct net_device *dev; dev = (struct net_device *)rtnl_dereference(b->media_ptr); - RCU_INIT_POINTER(b->media_ptr, NULL); RCU_INIT_POINTER(dev->tipc_ptr, NULL); synchronize_net(); dev_put(dev); @@ -554,7 +552,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, case NETDEV_CHANGE: if (netif_carrier_ok(dev)) break; - case NETDEV_DOWN: + case NETDEV_GOING_DOWN: case NETDEV_CHANGEMTU: tipc_reset_bearer(net, b_ptr); break; diff --git a/net/tipc/link.c b/net/tipc/link.c index 75db07c78a69..ff9b0b92e62e 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -120,11 +120,21 @@ bool tipc_link_is_up(struct tipc_link *l) return link_is_up(l); } +bool tipc_link_peer_is_down(struct tipc_link *l) +{ + return l->state == LINK_PEER_RESET; +} + bool tipc_link_is_reset(struct tipc_link *l) { return l->state & (LINK_RESET | LINK_FAILINGOVER | LINK_ESTABLISHING); } +bool tipc_link_is_establishing(struct tipc_link *l) +{ + return l->state == LINK_ESTABLISHING; +} + bool tipc_link_is_synching(struct tipc_link *l) { return l->state == LINK_SYNCHING; @@ -321,14 +331,15 @@ int tipc_link_fsm_evt(struct tipc_link *l, int evt) switch (evt) { case LINK_ESTABLISH_EVT: l->state = LINK_ESTABLISHED; - rc |= TIPC_LINK_UP_EVT; break; case LINK_FAILOVER_BEGIN_EVT: l->state = LINK_FAILINGOVER; break; - case LINK_PEER_RESET_EVT: case LINK_RESET_EVT: + l->state = LINK_RESET; + break; case LINK_FAILURE_EVT: + case LINK_PEER_RESET_EVT: case LINK_SYNCH_BEGIN_EVT: case LINK_FAILOVER_END_EVT: break; @@ -578,8 +589,6 @@ void tipc_link_purge_queues(struct tipc_link *l_ptr) void tipc_link_reset(struct tipc_link *l) { - tipc_link_fsm_evt(l, LINK_RESET_EVT); - /* Link is down, accept any session */ l->peer_session = WILDCARD_SESSION; @@ -953,7 +962,7 @@ static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb, case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: case CONN_MANAGER: - __skb_queue_tail(inputq, skb); + skb_queue_tail(inputq, skb); return true; case NAME_DISTRIBUTOR: node->bclink.recv_permitted = true; @@ -982,6 +991,7 @@ static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb, struct tipc_msg *hdr = buf_msg(skb); struct sk_buff **reasm_skb = &l->reasm_buf; struct sk_buff *iskb; + struct sk_buff_head tmpq; int usr = msg_user(hdr); int rc = 0; int pos = 0; @@ -1006,10 +1016,12 @@ static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb, } if (usr == MSG_BUNDLER) { + skb_queue_head_init(&tmpq); l->stats.recv_bundles++; l->stats.recv_bundled += msg_msgcnt(hdr); while (tipc_msg_extract(skb, &iskb, &pos)) - tipc_data_input(l, iskb, inputq); + tipc_data_input(l, iskb, &tmpq); + tipc_skb_queue_splice_tail(&tmpq, inputq); return 0; } else if (usr == MSG_FRAGMENTER) { l->stats.recv_fragments++; @@ -1044,49 +1056,76 @@ static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked) return released; } +/* tipc_link_build_ack_msg: prepare link acknowledge message for transmission + */ +void tipc_link_build_ack_msg(struct tipc_link *l, struct sk_buff_head *xmitq) +{ + l->rcv_unacked = 0; + l->stats.sent_acks++; + tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, xmitq); +} + +/* tipc_link_build_reset_msg: prepare link RESET or ACTIVATE message + */ +void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq) +{ + int mtyp = RESET_MSG; + + if (l->state == LINK_ESTABLISHING) + mtyp = ACTIVATE_MSG; + + tipc_link_build_proto_msg(l, mtyp, 0, 0, 0, 0, xmitq); +} + +/* tipc_link_build_nack_msg: prepare link nack message for transmission + */ +static void tipc_link_build_nack_msg(struct tipc_link *l, + struct sk_buff_head *xmitq) +{ + u32 def_cnt = ++l->stats.deferred_recv; + + if ((skb_queue_len(&l->deferdq) == 1) || !(def_cnt % TIPC_NACK_INTV)) + tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, xmitq); +} + /* tipc_link_rcv - process TIPC packets/messages arriving from off-node - * @link: the link that should handle the message + * @l: the link that should handle the message * @skb: TIPC packet * @xmitq: queue to place packets to be sent after this call */ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq) { - struct sk_buff_head *arrvq = &l->deferdq; - struct sk_buff_head tmpq; + struct sk_buff_head *defq = &l->deferdq; struct tipc_msg *hdr; - u16 seqno, rcv_nxt; + u16 seqno, rcv_nxt, win_lim; int rc = 0; - __skb_queue_head_init(&tmpq); - - if (unlikely(!__tipc_skb_queue_sorted(arrvq, skb))) { - if (!(skb_queue_len(arrvq) % TIPC_NACK_INTV)) - tipc_link_build_proto_msg(l, STATE_MSG, 0, - 0, 0, 0, xmitq); - return rc; - } - - while ((skb = skb_peek(arrvq))) { + do { hdr = buf_msg(skb); + seqno = msg_seqno(hdr); + rcv_nxt = l->rcv_nxt; + win_lim = rcv_nxt + TIPC_MAX_LINK_WIN; /* Verify and update link state */ - if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) { - __skb_dequeue(arrvq); - rc = tipc_link_proto_rcv(l, skb, xmitq); - continue; - } + if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) + return tipc_link_proto_rcv(l, skb, xmitq); if (unlikely(!link_is_up(l))) { - rc = tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); - if (!link_is_up(l)) { - kfree_skb(__skb_dequeue(arrvq)); - goto exit; - } + if (l->state == LINK_ESTABLISHING) + rc = TIPC_LINK_UP_EVT; + goto drop; } + /* Don't send probe at next timeout expiration */ l->silent_intv_cnt = 0; + /* Drop if outside receive window */ + if (unlikely(less(seqno, rcv_nxt) || more(seqno, win_lim))) { + l->stats.duplicates++; + goto drop; + } + /* Forward queues and wake up waiting users */ if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) { tipc_link_advance_backlog(l, xmitq); @@ -1094,39 +1133,28 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, link_prepare_wakeup(l); } - /* Defer reception if there is a gap in the sequence */ - seqno = msg_seqno(hdr); - rcv_nxt = l->rcv_nxt; - if (unlikely(less(rcv_nxt, seqno))) { - l->stats.deferred_recv++; - goto exit; - } - - __skb_dequeue(arrvq); - - /* Drop if packet already received */ - if (unlikely(more(rcv_nxt, seqno))) { - l->stats.duplicates++; - kfree_skb(skb); - goto exit; + /* Defer delivery if sequence gap */ + if (unlikely(seqno != rcv_nxt)) { + __tipc_skb_queue_sorted(defq, seqno, skb); + tipc_link_build_nack_msg(l, xmitq); + break; } - /* Packet can be delivered */ + /* Deliver packet */ l->rcv_nxt++; l->stats.recv_info++; - if (unlikely(!tipc_data_input(l, skb, &tmpq))) - rc = tipc_link_input(l, skb, &tmpq); + if (!tipc_data_input(l, skb, l->inputq)) + rc = tipc_link_input(l, skb, l->inputq); + if (unlikely(rc)) + break; + if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) + tipc_link_build_ack_msg(l, xmitq); + + } while ((skb = __skb_dequeue(defq))); - /* Ack at regular intervals */ - if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) { - l->rcv_unacked = 0; - l->stats.sent_acks++; - tipc_link_build_proto_msg(l, STATE_MSG, - 0, 0, 0, 0, xmitq); - } - } -exit: - tipc_skb_queue_splice_tail(&tmpq, l->inputq); + return rc; +drop: + kfree_skb(skb); return rc; } @@ -1250,7 +1278,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, } /* tipc_link_tnl_prepare(): prepare and return a list of tunnel packets - * with contents of the link's tranmsit and backlog queues. + * with contents of the link's transmit and backlog queues. */ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, int mtyp, struct sk_buff_head *xmitq) @@ -1331,6 +1359,7 @@ 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; + int mtyp = msg_type(hdr); char *if_name; int rc = 0; @@ -1340,7 +1369,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (link_own_addr(l) > msg_prevnode(hdr)) l->net_plane = msg_net_plane(hdr); - switch (msg_type(hdr)) { + switch (mtyp) { case RESET_MSG: /* Ignore duplicate RESET with old session number */ @@ -1367,12 +1396,14 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) l->priority = peers_prio; - if (msg_type(hdr) == RESET_MSG) { - rc |= tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); - } else if (!link_is_up(l)) { - tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); - rc |= tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); - } + /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ + if ((mtyp == RESET_MSG) || !link_is_up(l)) + rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); + + /* ACTIVATE_MSG takes up link if it was already locally reset */ + if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING)) + rc = TIPC_LINK_UP_EVT; + l->peer_session = msg_session(hdr); l->peer_bearer_id = msg_bearer_id(hdr); if (l->mtu > msg_max_pkt(hdr)) @@ -1389,9 +1420,12 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, l->stats.recv_states++; if (msg_probe(hdr)) l->stats.recv_probes++; - rc = tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); - if (!link_is_up(l)) + + if (!link_is_up(l)) { + if (l->state == LINK_ESTABLISHING) + rc = TIPC_LINK_UP_EVT; break; + } /* 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/link.h b/net/tipc/link.h index 39ff8b6919a4..0201212cb49a 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -185,7 +185,7 @@ struct tipc_link { } backlog[5]; u16 snd_nxt; u16 last_retransm; - u32 window; + u16 window; u32 stale_count; /* Reception */ @@ -213,10 +213,13 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, int mtyp, struct sk_buff_head *xmitq); void tipc_link_build_bcast_sync_msg(struct tipc_link *l, struct sk_buff_head *xmitq); +void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq); int tipc_link_fsm_evt(struct tipc_link *l, int evt); void tipc_link_reset_fragments(struct tipc_link *l_ptr); bool tipc_link_is_up(struct tipc_link *l); +bool tipc_link_peer_is_down(struct tipc_link *l); bool tipc_link_is_reset(struct tipc_link *l); +bool tipc_link_is_establishing(struct tipc_link *l); bool tipc_link_is_synching(struct tipc_link *l); bool tipc_link_is_failingover(struct tipc_link *l); bool tipc_link_is_blocked(struct tipc_link *l); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index c5ac436235e0..454f5ec275c8 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -590,3 +590,34 @@ error: kfree_skb(head); return NULL; } + +/* tipc_skb_queue_sorted(); sort pkt into list according to sequence number + * @list: list to be appended to + * @seqno: sequence number of buffer to add + * @skb: buffer to add + */ +void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno, + struct sk_buff *skb) +{ + struct sk_buff *_skb, *tmp; + + if (skb_queue_empty(list) || less(seqno, buf_seqno(skb_peek(list)))) { + __skb_queue_head(list, skb); + return; + } + + if (more(seqno, buf_seqno(skb_peek_tail(list)))) { + __skb_queue_tail(list, skb); + return; + } + + skb_queue_walk_safe(list, _skb, tmp) { + if (more(seqno, buf_seqno(_skb))) + continue; + if (seqno == buf_seqno(_skb)) + break; + __skb_queue_before(list, _skb, skb); + return; + } + kfree_skb(skb); +} diff --git a/net/tipc/msg.h b/net/tipc/msg.h index a82c5848d4bc..9f0ef54be612 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -357,7 +357,7 @@ static inline u32 msg_importance(struct tipc_msg *m) if (likely((usr <= TIPC_CRITICAL_IMPORTANCE) && !msg_errcode(m))) return usr; if ((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER)) - return msg_bits(m, 5, 13, 0x7); + return msg_bits(m, 9, 0, 0x7); return TIPC_SYSTEM_IMPORTANCE; } @@ -366,7 +366,7 @@ static inline void msg_set_importance(struct tipc_msg *m, u32 i) int usr = msg_user(m); if (likely((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER))) - msg_set_bits(m, 5, 13, 0x7, i); + msg_set_bits(m, 9, 0, 0x7, i); else if (i < TIPC_SYSTEM_IMPORTANCE) msg_set_user(m, i); else @@ -790,6 +790,8 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int mtu, struct sk_buff_head *list); bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err); struct sk_buff *tipc_msg_reassemble(struct sk_buff_head *list); +void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno, + struct sk_buff *skb); static inline u16 buf_seqno(struct sk_buff *skb) { @@ -862,38 +864,6 @@ static inline struct sk_buff *tipc_skb_dequeue(struct sk_buff_head *list, return skb; } -/* tipc_skb_queue_sorted(); sort pkt into list according to sequence number - * @list: list to be appended to - * @skb: buffer to add - * Returns true if queue should treated further, otherwise false - */ -static inline bool __tipc_skb_queue_sorted(struct sk_buff_head *list, - struct sk_buff *skb) -{ - struct sk_buff *_skb, *tmp; - struct tipc_msg *hdr = buf_msg(skb); - u16 seqno = msg_seqno(hdr); - - if (skb_queue_empty(list) || (msg_user(hdr) == LINK_PROTOCOL)) { - __skb_queue_head(list, skb); - return true; - } - if (likely(less(seqno, buf_seqno(skb_peek(list))))) { - __skb_queue_head(list, skb); - return true; - } - if (!more(seqno, buf_seqno(skb_peek_tail(list)))) { - skb_queue_walk_safe(list, _skb, tmp) { - if (likely(less(seqno, buf_seqno(_skb)))) { - __skb_queue_before(list, _skb, skb); - return true; - } - } - } - __skb_queue_tail(list, skb); - return false; -} - /* tipc_skb_queue_splice_tail - append an skb list to lock protected list * @list: the new list to append. Not lock protected * @head: target list. Lock protected. diff --git a/net/tipc/node.c b/net/tipc/node.c index 703875fd6cde..2670751d0e2e 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -317,7 +317,11 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id, struct tipc_link *ol = node_active_link(n, 0); struct tipc_link *nl = n->links[bearer_id].link; - if (!nl || !tipc_link_is_up(nl)) + if (!nl) + return; + + tipc_link_fsm_evt(nl, LINK_ESTABLISH_EVT); + if (!tipc_link_is_up(nl)) return; n->working_links++; @@ -416,7 +420,13 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, } if (!tipc_node_is_up(n)) { + if (tipc_link_peer_is_down(l)) + tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT); + tipc_node_fsm_evt(n, SELF_LOST_CONTACT_EVT); + tipc_link_fsm_evt(l, LINK_RESET_EVT); tipc_link_reset(l); + tipc_link_build_reset_msg(l, xmitq); + *maddr = &n->links[*bearer_id].maddr; node_lost_contact(n, &le->inputq); return; } @@ -428,6 +438,7 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, n->sync_point = tnl->rcv_nxt + (U16_MAX / 2 - 1); tipc_link_tnl_prepare(l, tnl, FAILOVER_MSG, xmitq); tipc_link_reset(l); + tipc_link_fsm_evt(l, LINK_RESET_EVT); tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT); tipc_node_fsm_evt(n, NODE_FAILOVER_BEGIN_EVT); *maddr = &n->links[tnl->bearer_id].maddr; @@ -437,20 +448,28 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) { struct tipc_link_entry *le = &n->links[bearer_id]; + struct tipc_link *l = le->link; struct tipc_media_addr *maddr; struct sk_buff_head xmitq; + if (!l) + return; + __skb_queue_head_init(&xmitq); tipc_node_lock(n); - __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr); - if (delete && le->link) { - kfree(le->link); - le->link = NULL; - n->link_cnt--; + if (!tipc_link_is_establishing(l)) { + __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr); + if (delete) { + kfree(l); + le->link = NULL; + n->link_cnt--; + } + } else { + /* Defuse pending tipc_node_link_up() */ + tipc_link_fsm_evt(l, LINK_RESET_EVT); } tipc_node_unlock(n); - tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr); tipc_sk_rcv(n->net, &le->inputq); } @@ -567,6 +586,7 @@ void tipc_node_check_dest(struct net *net, u32 onode, goto exit; } tipc_link_reset(l); + tipc_link_fsm_evt(l, LINK_RESET_EVT); if (n->state == NODE_FAILINGOVER) tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT); le->link = l; @@ -579,7 +599,7 @@ void tipc_node_check_dest(struct net *net, u32 onode, memcpy(&le->maddr, maddr, sizeof(*maddr)); exit: tipc_node_unlock(n); - if (reset) + if (reset && !tipc_link_is_reset(l)) tipc_node_link_down(n, b->identity, false); tipc_node_put(n); } @@ -686,10 +706,10 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt) break; case SELF_ESTABL_CONTACT_EVT: case PEER_LOST_CONTACT_EVT: - break; case NODE_SYNCH_END_EVT: - case NODE_SYNCH_BEGIN_EVT: case NODE_FAILOVER_BEGIN_EVT: + break; + case NODE_SYNCH_BEGIN_EVT: case NODE_FAILOVER_END_EVT: default: goto illegal_evt; @@ -849,9 +869,6 @@ static void node_lost_contact(struct tipc_node *n_ptr, tipc_link_fsm_evt(l, LINK_FAILOVER_END_EVT); } - /* Prevent re-contact with node until cleanup is done */ - tipc_node_fsm_evt(n_ptr, SELF_LOST_CONTACT_EVT); - /* Notify publications from this node */ n_ptr->action_flags |= TIPC_NOTIFY_NODE_DOWN; @@ -1116,7 +1133,7 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, } /* Ignore duplicate packets */ - if (less(oseqno, rcv_nxt)) + if ((usr != LINK_PROTOCOL) && less(oseqno, rcv_nxt)) return true; /* Initiate or update failover mode if applicable */ @@ -1146,8 +1163,8 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, if (!pl || !tipc_link_is_up(pl)) return true; - /* Initiate or update synch mode if applicable */ - if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG)) { + /* Initiate synch mode if applicable */ + if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG) && (oseqno == 1)) { syncpt = iseqno + exp_pkts - 1; if (!tipc_link_is_up(l)) { tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index c170d3138953..9bc0b1e515fa 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -425,7 +425,6 @@ static void tipc_udp_disable(struct tipc_bearer *b) } if (ub->ubsock) sock_set_flag(ub->ubsock->sk, SOCK_DEAD); - RCU_INIT_POINTER(b->media_ptr, NULL); RCU_INIT_POINTER(ub->bearer, NULL); /* sock_release need to be done outside of rtnl lock */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ef31b40ad550..94f658235fb4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2064,6 +2064,11 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) goto out; } + if (flags & MSG_PEEK) + skip = sk_peek_offset(sk, flags); + else + skip = 0; + do { int chunk; struct sk_buff *skb, *last; @@ -2112,7 +2117,6 @@ unlock: break; } - skip = sk_peek_offset(sk, flags); while (skip >= unix_skb_len(skb)) { skip -= unix_skb_len(skb); last = skb; @@ -2179,14 +2183,12 @@ unlock: if (UNIXCB(skb).fp) scm.fp = scm_fp_dup(UNIXCB(skb).fp); - if (skip) { - sk_peek_offset_fwd(sk, chunk); - skip -= chunk; - } + sk_peek_offset_fwd(sk, chunk); if (UNIXCB(skb).fp) break; + skip = 0; last = skb; last_len = skb->len; unix_state_lock(sk); diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 63e7d50e6a4f..b30514514e37 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -13,6 +13,7 @@ hostprogs-y += tracex3 hostprogs-y += tracex4 hostprogs-y += tracex5 hostprogs-y += tracex6 +hostprogs-y += trace_output hostprogs-y += lathist test_verifier-objs := test_verifier.o libbpf.o @@ -27,6 +28,7 @@ tracex3-objs := bpf_load.o libbpf.o tracex3_user.o tracex4-objs := bpf_load.o libbpf.o tracex4_user.o tracex5-objs := bpf_load.o libbpf.o tracex5_user.o tracex6-objs := bpf_load.o libbpf.o tracex6_user.o +trace_output-objs := bpf_load.o libbpf.o trace_output_user.o lathist-objs := bpf_load.o libbpf.o lathist_user.o # Tell kbuild to always build the programs @@ -40,6 +42,7 @@ always += tracex3_kern.o always += tracex4_kern.o always += tracex5_kern.o always += tracex6_kern.o +always += trace_output_kern.o always += tcbpf1_kern.o always += lathist_kern.o @@ -55,6 +58,7 @@ HOSTLOADLIBES_tracex3 += -lelf HOSTLOADLIBES_tracex4 += -lelf -lrt HOSTLOADLIBES_tracex5 += -lelf HOSTLOADLIBES_tracex6 += -lelf +HOSTLOADLIBES_trace_output += -lelf -lrt HOSTLOADLIBES_lathist += -lelf # point this to your LLVM backend with bpf support @@ -64,3 +68,6 @@ $(obj)/%.o: $(src)/%.c clang $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \ -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \ -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@ + clang $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \ + -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \ + -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=asm -o [email protected] diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 21aa1b44c30c..b35c21e0b43f 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -37,6 +37,8 @@ static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) = (void *) BPF_FUNC_clone_redirect; static int (*bpf_redirect)(int ifindex, int flags) = (void *) BPF_FUNC_redirect; +static int (*bpf_perf_event_output)(void *ctx, void *map, int index, void *data, int size) = + (void *) BPF_FUNC_perf_event_output; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c new file mode 100644 index 000000000000..8d8d1ec429eb --- /dev/null +++ b/samples/bpf/trace_output_kern.c @@ -0,0 +1,31 @@ +#include <linux/ptrace.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include "bpf_helpers.h" + +struct bpf_map_def SEC("maps") my_map = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(u32), + .max_entries = 2, +}; + +SEC("kprobe/sys_write") +int bpf_prog1(struct pt_regs *ctx) +{ + struct S { + u64 pid; + u64 cookie; + } data; + + memset(&data, 0, sizeof(data)); + data.pid = bpf_get_current_pid_tgid(); + data.cookie = 0x12345678; + + bpf_perf_event_output(ctx, &my_map, 0, &data, sizeof(data)); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c new file mode 100644 index 000000000000..661a7d052f2c --- /dev/null +++ b/samples/bpf/trace_output_user.c @@ -0,0 +1,196 @@ +/* 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 <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <fcntl.h> +#include <poll.h> +#include <sys/ioctl.h> +#include <linux/perf_event.h> +#include <linux/bpf.h> +#include <errno.h> +#include <assert.h> +#include <sys/syscall.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <time.h> +#include <signal.h> +#include "libbpf.h" +#include "bpf_load.h" + +static int pmu_fd; + +int page_size; +int page_cnt = 8; +volatile struct perf_event_mmap_page *header; + +typedef void (*print_fn)(void *data, int size); + +static int perf_event_mmap(int fd) +{ + void *base; + int mmap_size; + + page_size = getpagesize(); + mmap_size = page_size * (page_cnt + 1); + + base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (base == MAP_FAILED) { + printf("mmap err\n"); + return -1; + } + + header = base; + return 0; +} + +static int perf_event_poll(int fd) +{ + struct pollfd pfd = { .fd = fd, .events = POLLIN }; + + return poll(&pfd, 1, 1000); +} + +struct perf_event_sample { + struct perf_event_header header; + __u32 size; + char data[]; +}; + +void perf_event_read(print_fn fn) +{ + __u64 data_tail = header->data_tail; + __u64 data_head = header->data_head; + __u64 buffer_size = page_cnt * page_size; + void *base, *begin, *end; + char buf[256]; + + asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */ + if (data_head == data_tail) + return; + + base = ((char *)header) + page_size; + + begin = base + data_tail % buffer_size; + end = base + data_head % buffer_size; + + while (begin != end) { + struct perf_event_sample *e; + + e = begin; + if (begin + e->header.size > base + buffer_size) { + long len = base + buffer_size - begin; + + assert(len < e->header.size); + memcpy(buf, begin, len); + memcpy(buf + len, base, e->header.size - len); + e = (void *) buf; + begin = base + e->header.size - len; + } else if (begin + e->header.size == base + buffer_size) { + begin = base; + } else { + begin += e->header.size; + } + + if (e->header.type == PERF_RECORD_SAMPLE) { + fn(e->data, e->size); + } else if (e->header.type == PERF_RECORD_LOST) { + struct { + struct perf_event_header header; + __u64 id; + __u64 lost; + } *lost = (void *) e; + printf("lost %lld events\n", lost->lost); + } else { + printf("unknown event type=%d size=%d\n", + e->header.type, e->header.size); + } + } + + __sync_synchronize(); /* smp_mb() */ + header->data_tail = data_head; +} + +static __u64 time_get_ns(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000ull + ts.tv_nsec; +} + +static __u64 start_time; + +#define MAX_CNT 100000ll + +static void print_bpf_output(void *data, int size) +{ + static __u64 cnt; + struct { + __u64 pid; + __u64 cookie; + } *e = data; + + if (e->cookie != 0x12345678) { + printf("BUG pid %llx cookie %llx sized %d\n", + e->pid, e->cookie, size); + kill(0, SIGINT); + } + + cnt++; + + if (cnt == MAX_CNT) { + printf("recv %lld events per sec\n", + MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); + kill(0, SIGINT); + } +} + +static void test_bpf_perf_event(void) +{ + struct perf_event_attr attr = { + .sample_type = PERF_SAMPLE_RAW, + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_BPF_OUTPUT, + }; + int key = 0; + + pmu_fd = perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0); + + assert(pmu_fd >= 0); + assert(bpf_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0); + ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); +} + +int main(int argc, char **argv) +{ + char filename[256]; + FILE *f; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + test_bpf_perf_event(); + + if (perf_event_mmap(pmu_fd) < 0) + return 1; + + f = popen("taskset 1 dd if=/dev/zero of=/dev/null", "r"); + (void) f; + + start_time = time_get_ns(); + for (;;) { + perf_event_poll(pmu_fd); + perf_event_read(print_bpf_output); + } + + return 0; +} diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 0cd46e129920..b967e4f9fed2 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -115,7 +115,7 @@ esac BUILD_DEBUG="$(grep -s '^CONFIG_DEBUG_INFO=y' $KCONFIG_CONFIG || true)" # Setup the directory structure -rm -rf "$tmpdir" "$fwdir" "$kernel_headers_dir" "$libc_headers_dir" "$dbg_dir" +rm -rf "$tmpdir" "$fwdir" "$kernel_headers_dir" "$libc_headers_dir" "$dbg_dir" $objtree/debian/files mkdir -m 755 -p "$tmpdir/DEBIAN" mkdir -p "$tmpdir/lib" "$tmpdir/boot" mkdir -p "$fwdir/lib/firmware/$version/" @@ -408,7 +408,7 @@ binary-arch: \$(MAKE) KDEB_SOURCENAME=${sourcename} KDEB_PKGVERSION=${packageversion} bindeb-pkg clean: - rm -rf debian/*tmp + rm -rf debian/*tmp debian/files mv debian/ debian.backup # debian/ might be cleaned away \$(MAKE) clean mv debian.backup debian diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 6e50841ef1f6..26f4039d54b8 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6131,21 +6131,18 @@ security_initcall(selinux_init); static struct nf_hook_ops selinux_nf_ops[] = { { .hook = selinux_ipv4_postroute, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_SELINUX_LAST, }, { .hook = selinux_ipv4_forward, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_SELINUX_FIRST, }, { .hook = selinux_ipv4_output, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_SELINUX_FIRST, @@ -6153,14 +6150,12 @@ static struct nf_hook_ops selinux_nf_ops[] = { #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) { .hook = selinux_ipv6_postroute, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_SELINUX_LAST, }, { .hook = selinux_ipv6_forward, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_SELINUX_FIRST, diff --git a/security/smack/smack_netfilter.c b/security/smack/smack_netfilter.c index a9e41da05d28..6d1706c9777e 100644 --- a/security/smack/smack_netfilter.c +++ b/security/smack/smack_netfilter.c @@ -57,7 +57,6 @@ static unsigned int smack_ipv4_output(void *priv, static struct nf_hook_ops smack_nf_ops[] = { { .hook = smack_ipv4_output, - .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_SELINUX_FIRST, @@ -65,7 +64,6 @@ static struct nf_hook_ops smack_nf_ops[] = { #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) { .hook = smack_ipv6_output, - .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_SELINUX_FIRST, diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index 584a0343ab0c..85813de26da8 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -633,6 +633,7 @@ static const struct snd_pci_quirk cs4208_mac_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x5e00, "MacBookPro 11,2", CS4208_MBP11), SND_PCI_QUIRK(0x106b, 0x7100, "MacBookAir 6,1", CS4208_MBA6), SND_PCI_QUIRK(0x106b, 0x7200, "MacBookAir 6,2", CS4208_MBA6), + SND_PCI_QUIRK(0x106b, 0x7b00, "MacBookPro 12,1", CS4208_MBP11), {} /* terminator */ }; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index afec6dc9f91f..16b8dcba5c12 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5306,6 +5306,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad T440", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad X240", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + 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, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP), diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 9d947aef2c8b..def5cc8dff02 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -4520,7 +4520,11 @@ static int patch_stac92hd73xx(struct hda_codec *codec) return err; spec = codec->spec; - codec->power_save_node = 1; + /* enable power_save_node only for new 92HD89xx chips, as it causes + * click noises on old 92HD73xx chips. + */ + if ((codec->core.vendor_id & 0xfffffff0) != 0x111d7670) + codec->power_save_node = 1; spec->linear_tone_beep = 0; spec->gen.mixer_nid = 0x1d; spec->have_spdif_mux = 1; diff --git a/sound/soc/au1x/db1200.c b/sound/soc/au1x/db1200.c index 58c3164802b8..8c907ebea189 100644 --- a/sound/soc/au1x/db1200.c +++ b/sound/soc/au1x/db1200.c @@ -129,6 +129,8 @@ static struct snd_soc_dai_link db1300_i2s_dai = { .cpu_dai_name = "au1xpsc_i2s.2", .platform_name = "au1xpsc-pcm.2", .codec_name = "wm8731.0-001b", + .dai_fmt = SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_NB_NF | + SND_SOC_DAIFMT_CBM_CFM, .ops = &db1200_i2s_wm8731_ops, }; @@ -146,6 +148,8 @@ static struct snd_soc_dai_link db1550_i2s_dai = { .cpu_dai_name = "au1xpsc_i2s.3", .platform_name = "au1xpsc-pcm.3", .codec_name = "wm8731.0-001b", + .dai_fmt = SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_NB_NF | + SND_SOC_DAIFMT_CBM_CFM, .ops = &db1200_i2s_wm8731_ops, }; diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 268a28bd1df4..5c101af0ac63 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -519,11 +519,11 @@ static const struct snd_kcontrol_new rt5645_snd_controls[] = { RT5645_L_VOL_SFT + 1, RT5645_R_VOL_SFT + 1, 63, 0, adc_vol_tlv), /* ADC Boost Volume Control */ - SOC_DOUBLE_TLV("STO1 ADC Boost Gain", RT5645_ADC_BST_VOL1, + SOC_DOUBLE_TLV("ADC Boost Capture Volume", RT5645_ADC_BST_VOL1, RT5645_STO1_ADC_L_BST_SFT, RT5645_STO1_ADC_R_BST_SFT, 3, 0, adc_bst_tlv), - SOC_DOUBLE_TLV("STO2 ADC Boost Gain", RT5645_ADC_BST_VOL1, - RT5645_STO2_ADC_L_BST_SFT, RT5645_STO2_ADC_R_BST_SFT, 3, 0, + SOC_DOUBLE_TLV("Mono ADC Boost Capture Volume", RT5645_ADC_BST_VOL2, + RT5645_MONO_ADC_L_BST_SFT, RT5645_MONO_ADC_R_BST_SFT, 3, 0, adc_bst_tlv), /* I2S2 function select */ diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h index 0e4cfc6ac649..8c964cfb120d 100644 --- a/sound/soc/codecs/rt5645.h +++ b/sound/soc/codecs/rt5645.h @@ -39,8 +39,8 @@ #define RT5645_STO1_ADC_DIG_VOL 0x1c #define RT5645_MONO_ADC_DIG_VOL 0x1d #define RT5645_ADC_BST_VOL1 0x1e -/* Mixer - D-D */ #define RT5645_ADC_BST_VOL2 0x20 +/* Mixer - D-D */ #define RT5645_STO1_ADC_MIXER 0x27 #define RT5645_MONO_ADC_MIXER 0x28 #define RT5645_AD_DA_MIXER 0x29 @@ -315,12 +315,14 @@ #define RT5645_STO1_ADC_R_BST_SFT 12 #define RT5645_STO1_ADC_COMP_MASK (0x3 << 10) #define RT5645_STO1_ADC_COMP_SFT 10 -#define RT5645_STO2_ADC_L_BST_MASK (0x3 << 8) -#define RT5645_STO2_ADC_L_BST_SFT 8 -#define RT5645_STO2_ADC_R_BST_MASK (0x3 << 6) -#define RT5645_STO2_ADC_R_BST_SFT 6 -#define RT5645_STO2_ADC_COMP_MASK (0x3 << 4) -#define RT5645_STO2_ADC_COMP_SFT 4 + +/* ADC Boost Volume Control (0x20) */ +#define RT5645_MONO_ADC_L_BST_MASK (0x3 << 14) +#define RT5645_MONO_ADC_L_BST_SFT 14 +#define RT5645_MONO_ADC_R_BST_MASK (0x3 << 12) +#define RT5645_MONO_ADC_R_BST_SFT 12 +#define RT5645_MONO_ADC_COMP_MASK (0x3 << 10) +#define RT5645_MONO_ADC_COMP_SFT 10 /* Stereo2 ADC Mixer Control (0x26) */ #define RT5645_STO2_ADC_SRC_MASK (0x1 << 15) diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index bfda25ef0dd4..f540f82b1f27 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -1376,8 +1376,8 @@ static int sgtl5000_probe(struct snd_soc_codec *codec) sgtl5000->micbias_resistor << SGTL5000_BIAS_R_SHIFT); snd_soc_update_bits(codec, SGTL5000_CHIP_MIC_CTRL, - SGTL5000_BIAS_R_MASK, - sgtl5000->micbias_voltage << SGTL5000_BIAS_R_SHIFT); + SGTL5000_BIAS_VOLT_MASK, + sgtl5000->micbias_voltage << SGTL5000_BIAS_VOLT_SHIFT); /* * disable DAP * TODO: @@ -1549,7 +1549,7 @@ static int sgtl5000_i2c_probe(struct i2c_client *client, else { sgtl5000->micbias_voltage = 0; dev_err(&client->dev, - "Unsuitable MicBias resistor\n"); + "Unsuitable MicBias voltage\n"); } } else { sgtl5000->micbias_voltage = 0; diff --git a/sound/soc/codecs/tas2552.c b/sound/soc/codecs/tas2552.c index e3a0bca28bcf..cc1d3981fa4b 100644 --- a/sound/soc/codecs/tas2552.c +++ b/sound/soc/codecs/tas2552.c @@ -549,7 +549,7 @@ static struct snd_soc_dai_driver tas2552_dai[] = { /* * DAC digital volumes. From -7 to 24 dB in 1 dB steps */ -static DECLARE_TLV_DB_SCALE(dac_tlv, -7, 100, 0); +static DECLARE_TLV_DB_SCALE(dac_tlv, -700, 100, 0); static const char * const tas2552_din_source_select[] = { "Muted", diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index 1a82b19b2644..8739126a1f6f 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -1509,14 +1509,17 @@ static int aic3x_init(struct snd_soc_codec *codec) snd_soc_write(codec, PGAL_2_LLOPM_VOL, DEFAULT_VOL); snd_soc_write(codec, PGAR_2_RLOPM_VOL, DEFAULT_VOL); - /* Line2 to HP Bypass default volume, disconnect from Output Mixer */ - snd_soc_write(codec, LINE2L_2_HPLOUT_VOL, DEFAULT_VOL); - snd_soc_write(codec, LINE2R_2_HPROUT_VOL, DEFAULT_VOL); - snd_soc_write(codec, LINE2L_2_HPLCOM_VOL, DEFAULT_VOL); - snd_soc_write(codec, LINE2R_2_HPRCOM_VOL, DEFAULT_VOL); - /* Line2 Line Out default volume, disconnect from Output Mixer */ - snd_soc_write(codec, LINE2L_2_LLOPM_VOL, DEFAULT_VOL); - snd_soc_write(codec, LINE2R_2_RLOPM_VOL, DEFAULT_VOL); + /* On tlv320aic3104, these registers are reserved and must not be written */ + if (aic3x->model != AIC3X_MODEL_3104) { + /* Line2 to HP Bypass default volume, disconnect from Output Mixer */ + snd_soc_write(codec, LINE2L_2_HPLOUT_VOL, DEFAULT_VOL); + snd_soc_write(codec, LINE2R_2_HPROUT_VOL, DEFAULT_VOL); + snd_soc_write(codec, LINE2L_2_HPLCOM_VOL, DEFAULT_VOL); + snd_soc_write(codec, LINE2R_2_HPRCOM_VOL, DEFAULT_VOL); + /* Line2 Line Out default volume, disconnect from Output Mixer */ + snd_soc_write(codec, LINE2L_2_LLOPM_VOL, DEFAULT_VOL); + snd_soc_write(codec, LINE2R_2_RLOPM_VOL, DEFAULT_VOL); + } switch (aic3x->model) { case AIC3X_MODEL_3X: diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 293e47a6ff59..2fbc6ef8cbdb 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -3760,7 +3760,7 @@ static int wm8962_i2c_probe(struct i2c_client *i2c, ret = snd_soc_register_codec(&i2c->dev, &soc_codec_dev_wm8962, &wm8962_dai, 1); if (ret < 0) - goto err_enable; + goto err_pm_runtime; regcache_cache_only(wm8962->regmap, true); @@ -3769,6 +3769,8 @@ static int wm8962_i2c_probe(struct i2c_client *i2c, return 0; +err_pm_runtime: + pm_runtime_disable(&i2c->dev); err_enable: regulator_bulk_disable(ARRAY_SIZE(wm8962->supplies), wm8962->supplies); err: @@ -3778,6 +3780,7 @@ err: static int wm8962_i2c_remove(struct i2c_client *client) { snd_soc_unregister_codec(&client->dev); + pm_runtime_disable(&client->dev); return 0; } diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c index a3e97b46b64e..ba34252b7bba 100644 --- a/sound/soc/dwc/designware_i2s.c +++ b/sound/soc/dwc/designware_i2s.c @@ -131,23 +131,32 @@ static inline void i2s_clear_irqs(struct dw_i2s_dev *dev, u32 stream) if (stream == SNDRV_PCM_STREAM_PLAYBACK) { for (i = 0; i < 4; i++) - i2s_write_reg(dev->i2s_base, TOR(i), 0); + i2s_read_reg(dev->i2s_base, TOR(i)); } else { for (i = 0; i < 4; i++) - i2s_write_reg(dev->i2s_base, ROR(i), 0); + i2s_read_reg(dev->i2s_base, ROR(i)); } } static void i2s_start(struct dw_i2s_dev *dev, struct snd_pcm_substream *substream) { - + u32 i, irq; i2s_write_reg(dev->i2s_base, IER, 1); - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + for (i = 0; i < 4; i++) { + irq = i2s_read_reg(dev->i2s_base, IMR(i)); + i2s_write_reg(dev->i2s_base, IMR(i), irq & ~0x30); + } i2s_write_reg(dev->i2s_base, ITER, 1); - else + } else { + for (i = 0; i < 4; i++) { + irq = i2s_read_reg(dev->i2s_base, IMR(i)); + i2s_write_reg(dev->i2s_base, IMR(i), irq & ~0x03); + } i2s_write_reg(dev->i2s_base, IRER, 1); + } i2s_write_reg(dev->i2s_base, CER, 1); } diff --git a/sound/soc/fsl/imx-ssi.c b/sound/soc/fsl/imx-ssi.c index 48b2d24dd1f0..b95132e2f9dc 100644 --- a/sound/soc/fsl/imx-ssi.c +++ b/sound/soc/fsl/imx-ssi.c @@ -95,7 +95,8 @@ static int imx_ssi_set_dai_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt) switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_I2S: /* data on rising edge of bclk, frame low 1clk before data */ - strcr |= SSI_STCR_TFSI | SSI_STCR_TEFS | SSI_STCR_TXBIT0; + strcr |= SSI_STCR_TXBIT0 | SSI_STCR_TSCKP | SSI_STCR_TFSI | + SSI_STCR_TEFS; scr |= SSI_SCR_NET; if (ssi->flags & IMX_SSI_USE_I2S_SLAVE) { scr &= ~SSI_I2S_MODE_MASK; @@ -104,33 +105,31 @@ static int imx_ssi_set_dai_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt) break; case SND_SOC_DAIFMT_LEFT_J: /* data on rising edge of bclk, frame high with data */ - strcr |= SSI_STCR_TXBIT0; + strcr |= SSI_STCR_TXBIT0 | SSI_STCR_TSCKP; break; case SND_SOC_DAIFMT_DSP_B: /* data on rising edge of bclk, frame high with data */ - strcr |= SSI_STCR_TFSL | SSI_STCR_TXBIT0; + strcr |= SSI_STCR_TXBIT0 | SSI_STCR_TSCKP | SSI_STCR_TFSL; break; case SND_SOC_DAIFMT_DSP_A: /* data on rising edge of bclk, frame high 1clk before data */ - strcr |= SSI_STCR_TFSL | SSI_STCR_TXBIT0 | SSI_STCR_TEFS; + strcr |= SSI_STCR_TXBIT0 | SSI_STCR_TSCKP | SSI_STCR_TFSL | + SSI_STCR_TEFS; break; } /* DAI clock inversion */ switch (fmt & SND_SOC_DAIFMT_INV_MASK) { case SND_SOC_DAIFMT_IB_IF: - strcr |= SSI_STCR_TFSI; - strcr &= ~SSI_STCR_TSCKP; + strcr ^= SSI_STCR_TSCKP | SSI_STCR_TFSI; break; case SND_SOC_DAIFMT_IB_NF: - strcr &= ~(SSI_STCR_TSCKP | SSI_STCR_TFSI); + strcr ^= SSI_STCR_TSCKP; break; case SND_SOC_DAIFMT_NB_IF: - strcr |= SSI_STCR_TFSI | SSI_STCR_TSCKP; + strcr ^= SSI_STCR_TFSI; break; case SND_SOC_DAIFMT_NB_NF: - strcr &= ~SSI_STCR_TFSI; - strcr |= SSI_STCR_TSCKP; break; } diff --git a/sound/synth/emux/emux_oss.c b/sound/synth/emux/emux_oss.c index 82e350e9501c..ac75816ada7c 100644 --- a/sound/synth/emux/emux_oss.c +++ b/sound/synth/emux/emux_oss.c @@ -69,7 +69,8 @@ snd_emux_init_seq_oss(struct snd_emux *emu) struct snd_seq_oss_reg *arg; struct snd_seq_device *dev; - if (snd_seq_device_new(emu->card, 0, SNDRV_SEQ_DEV_ID_OSS, + /* using device#1 here for avoiding conflicts with OPL3 */ + if (snd_seq_device_new(emu->card, 1, SNDRV_SEQ_DEV_ID_OSS, sizeof(struct snd_seq_oss_reg), &dev) < 0) return; diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 349bc96ca1fe..e5f18a288b74 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -17,6 +17,7 @@ libperf-y += levenshtein.o libperf-y += llvm-utils.o libperf-y += parse-options.o libperf-y += parse-events.o +libperf-y += perf_regs.o libperf-y += path.o libperf-y += rbtree.o libperf-y += bitmap.o @@ -103,7 +104,6 @@ libperf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o libperf-y += scripting-engines/ -libperf-$(CONFIG_PERF_REGS) += perf_regs.o libperf-$(CONFIG_ZLIB) += zlib.o libperf-$(CONFIG_LZMA) += lzma.o diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 885e8ac83997..6b8eb13e14e4 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -6,6 +6,7 @@ const struct sample_reg __weak sample_reg_masks[] = { SMPL_REG_END }; +#ifdef HAVE_PERF_REGS_SUPPORT int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) { int i, idx = 0; @@ -29,3 +30,4 @@ out: *valp = regs->cache_regs[id]; return 0; } +#endif diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index 2984dcc54d67..679d6e493962 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -2,6 +2,7 @@ #define __PERF_REGS_H #include <linux/types.h> +#include <linux/compiler.h> struct regs_dump; diff --git a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c index d1b647509596..6cae06117b55 100644 --- a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c +++ b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c @@ -25,10 +25,19 @@ #define FIXUP_SECTION ".ex_fixup" +static inline unsigned long __fls(unsigned long x); + #include "word-at-a-time.h" #include "utils.h" +static inline unsigned long __fls(unsigned long x) +{ + int lz; + + asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (x)); + return sizeof(unsigned long) - 1 - lz; +} static int page_size; static char *mem_region; |